{"meta":{"query_hash":"158b6d6b4639","filters":{"topic":"Radiomics and Machine Learning in Medical Imaging"},"cohort_total":2251,"direct_labels_cover":9,"predictions_cover":2251,"exported":2251,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/158b6d6b4639","api":"https://metacan.xera.ac/api/v1/cohort?topic=Radiomics+and+Machine+Learning+in+Medical+Imaging"},"results":[{"id":"W1019634379","doi":"","title":"Automatic segmentation of lung cancer based on texture features of PET/CT images","year":2011,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto; Health Sciences Centre; Sunnybrook Health Science Centre","funders":"","keywords":"Kurtosis; Artificial intelligence; Pattern recognition (psychology); Skewness; Segmentation; Computer science; Standard deviation; Receiver operating characteristic; Computer-aided diagnosis; Random forest; Grey level; Nuclear medicine; Mathematics; Medicine; Pixel; Statistics","score_opus":0.009067936753669282,"score_gpt":0.3073827478835924,"score_spread":0.2983148111299231,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1019634379","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9491387,0.00036923413,0.0034687307,0.0019258284,0.0002058211,0.00041355647,0.000009034087,0.000081839506,0.04438727],"genre_scores_gemma":[0.9847471,0.000021992259,0.013624293,0.0007672208,0.000028254775,0.000008477965,0.000009703562,0.000012275037,0.0007806991],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99937403,0.000028082188,0.00017895052,0.00010665819,0.00021763578,0.000094633906],"domain_scores_gemma":[0.99958616,0.000057336223,0.00010772699,0.00014301091,0.00005018136,0.000055599536],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00014576444,0.00007980861,0.0002041952,0.00009333942,0.000017111772,0.000002717288,0.000053645555,0.000007768008,0.0016099131],"category_scores_gemma":[0.000113583505,0.000054255343,0.000060883176,0.000089279194,0.00006301537,0.000027561253,0.000008504348,0.00015399541,0.0000012324102],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00048025782,0.0013470082,0.47036427,0.005088524,0.00052691204,0.00047994734,0.0020499174,0.00064427813,0.13188213,0.0013998069,0.06891059,0.31682637],"study_design_scores_gemma":[0.002820331,0.00040270956,0.51490015,0.0011666841,0.000373605,0.00009425398,0.00026699473,0.33018994,0.14942601,0.0000752389,0.00011057939,0.00017348642],"about_ca_topic_score_codex":0.0005125568,"about_ca_topic_score_gemma":0.000004057656,"teacher_disagreement_score":0.32954565,"about_ca_system_score_codex":0.00002349893,"about_ca_system_score_gemma":0.000059871534,"threshold_uncertainty_score":0.99930274},"labels":[],"label_agreement":null},{"id":"W1019962008","doi":"","title":"AJCC TNM COLLABORATIVE INTERNET STAGING VALIDATION FOR OPHTHALMIC TUMORS","year":2013,"lang":"en","type":"article","venue":"Investigative Ophthalmology & Visual Science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre","funders":"","keywords":"Medicine; Medical physics; Staging system; The Internet; Radiology; Computer science; Internal medicine; Cancer; World Wide Web","score_opus":0.029298792136066287,"score_gpt":0.361423595717114,"score_spread":0.33212480358104773,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1019962008","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99147254,0.00005040488,0.00025411887,0.0032660756,0.0003730583,0.0011666276,0.000005892987,0.00007134954,0.0033399507],"genre_scores_gemma":[0.9845162,0.0000019748636,0.01317171,0.00078268436,0.00015005369,0.00024179742,0.000031258576,0.000030225709,0.0010740813],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99752384,0.00014718159,0.0004293362,0.00075095455,0.00048533172,0.0006633728],"domain_scores_gemma":[0.997871,0.0003454027,0.00025857697,0.00023428883,0.00073816045,0.00055259373],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0011195667,0.00026492344,0.0004306429,0.00032278267,0.00033487185,0.00014505802,0.00037673832,0.000095296324,0.00036609557],"category_scores_gemma":[0.003228428,0.00022307986,0.00007540527,0.001097478,0.0038246599,0.00059746514,0.0001646836,0.00043452144,0.00011675342],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000045660014,0.00014009244,0.09035872,0.00006130184,0.000045475266,0.000113846196,0.002074998,0.000056999226,0.9037511,0.0008864421,0.00087319413,0.0015922198],"study_design_scores_gemma":[0.0021925864,0.0027935354,0.22097306,0.00044676496,0.00008685597,0.0013570501,0.002032526,0.05865318,0.69352084,0.01686959,0.00040759926,0.00066642393],"about_ca_topic_score_codex":0.00024954756,"about_ca_topic_score_gemma":1.9504184e-7,"teacher_disagreement_score":0.21023023,"about_ca_system_score_codex":0.00022822806,"about_ca_system_score_gemma":0.0007487477,"threshold_uncertainty_score":0.99888635},"labels":[],"label_agreement":null},{"id":"W1173400778","doi":"10.1118/1.4925762","title":"TU‐G‐303‐02: Robust Radiomics Methods for PET and CT Imaging","year":2015,"lang":"en","type":"article","venue":"Medical Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Radiomics; Radiogenomics; Medical imaging; Medical physics; Medicine; Artificial intelligence; Machine learning; Computer science","score_opus":0.033442230651986773,"score_gpt":0.3747053001044831,"score_spread":0.34126306945249635,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1173400778","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025245931,0.0011676352,0.9539616,0.015728857,0.000795077,0.00038853177,0.000004719431,0.00014588963,0.0025617252],"genre_scores_gemma":[0.55361295,0.00035960544,0.42417437,0.015688408,0.0046908925,0.000087637854,0.00016322594,0.00019660691,0.0010262926],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981729,0.00010571901,0.00034042093,0.00039875004,0.0005380604,0.00044416238],"domain_scores_gemma":[0.9978939,0.00051354483,0.000093975126,0.00029449063,0.00012955014,0.0010745022],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002080797,0.00021794571,0.00053231424,0.000058612037,0.00010313279,0.00004645359,0.00017668451,0.000044318207,0.000035471072],"category_scores_gemma":[0.003955616,0.00018292625,0.0001271447,0.000176864,0.00047832882,0.000104923645,0.000116736686,0.00067180855,0.000009361065],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009828324,0.00019417709,0.0067996047,0.00020902099,0.00010679082,0.00025110468,0.00034024924,0.000050903676,0.00037544692,0.0024946546,0.026238304,0.96284145],"study_design_scores_gemma":[0.009598471,0.00029223983,0.00080562837,0.0003906999,0.00042947775,0.0022118296,0.00025684643,0.7880672,0.0015921643,0.02595675,0.16981755,0.00058112346],"about_ca_topic_score_codex":0.000037978665,"about_ca_topic_score_gemma":4.7182232e-7,"teacher_disagreement_score":0.96226037,"about_ca_system_score_codex":0.00008457964,"about_ca_system_score_gemma":0.00033959278,"threshold_uncertainty_score":0.7459516},"labels":[],"label_agreement":null},{"id":"W1193864810","doi":"10.1118/1.4925763","title":"TU‐G‐303‐03: Machine Learning to Improve Human Learning From Longitudinal Image Sets","year":2015,"lang":"en","type":"article","venue":"Medical Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Radiomics; Radiogenomics; Medical imaging; Machine learning; Artificial intelligence; Computer science; Medical physics; Precision medicine; Medicine; Pathology","score_opus":0.023865496298817443,"score_gpt":0.321071521055217,"score_spread":0.29720602475639957,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1193864810","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90638196,0.0004058294,0.07005755,0.010086735,0.000985831,0.00048970844,0.00001073718,0.0006072898,0.010974362],"genre_scores_gemma":[0.99035853,0.00002286543,0.002771812,0.0023716523,0.002489673,0.000024356339,0.00033359998,0.0001137467,0.0015137753],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99605405,0.00019372161,0.00053880754,0.0007355385,0.001752169,0.0007257013],"domain_scores_gemma":[0.99695426,0.00024099732,0.0001678491,0.0004201158,0.00021075939,0.00200601],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0011838645,0.00038284287,0.00075310917,0.00010006475,0.00028426768,0.00009352844,0.00036484192,0.00020786215,0.00057675707],"category_scores_gemma":[0.0043688472,0.00033607282,0.00019976887,0.00036710367,0.00034561098,0.00015913954,0.0003640324,0.00303566,0.00070577057],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006237391,0.0015726543,0.46074563,0.00033998585,0.000759371,0.0032784857,0.0066131297,0.0011661244,0.036209404,0.00086638227,0.032777965,0.45504713],"study_design_scores_gemma":[0.039018255,0.008716319,0.08559103,0.0034998278,0.0018615085,0.0006213782,0.0018914117,0.53641015,0.021021083,0.020704737,0.27580473,0.004859579],"about_ca_topic_score_codex":0.0010231049,"about_ca_topic_score_gemma":0.000013485507,"teacher_disagreement_score":0.535244,"about_ca_system_score_codex":0.00018355834,"about_ca_system_score_gemma":0.00028546,"threshold_uncertainty_score":0.9999091},"labels":[],"label_agreement":null},{"id":"W1266889966","doi":"10.3233/mas-130272","title":"Meeting Report: STAT-HAWKERS at the JSM-2013, Montreal, Canada","year":2013,"lang":"en","type":"article","venue":"Model Assisted Statistics and Applications","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"stat; Traditional medicine; Medicine; Biology; Genetics","score_opus":0.00984552943645269,"score_gpt":0.26271292219591524,"score_spread":0.2528673927594626,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1266889966","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.047626548,0.00073919457,0.90075076,0.03318588,0.000076965785,0.0013949166,0.00040593397,0.000083392086,0.015736401],"genre_scores_gemma":[0.913839,0.00042056447,0.060654484,0.0034176435,0.000173101,0.0007849887,0.0008593574,0.00006284969,0.019788012],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988957,0.000021763366,0.0003160244,0.00026549905,0.00027030607,0.00023069575],"domain_scores_gemma":[0.99892235,0.00020062937,0.00014779397,0.00035120582,0.00014694808,0.0002310801],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016171951,0.00012703739,0.00018859113,0.000024905941,0.0004406947,0.000057424233,0.000079717865,0.000037042035,0.00006392759],"category_scores_gemma":[0.00012139955,0.00008863906,0.000024089564,0.0000969312,0.00013265612,0.000024146228,0.00006264068,0.0002356051,0.000008542496],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015109801,0.0001376931,0.0049069906,0.00013022037,0.00015645944,0.00008509707,0.00019512058,0.0074501084,0.0015401958,0.006235025,0.8076905,0.17145747],"study_design_scores_gemma":[0.0004383227,0.000014680378,0.023247905,0.000026263695,0.00013000633,0.0002162116,0.00013114982,0.8793883,0.000013090582,0.0025892318,0.09364957,0.00015528401],"about_ca_topic_score_codex":0.3184871,"about_ca_topic_score_gemma":0.118268006,"teacher_disagreement_score":0.87193817,"about_ca_system_score_codex":0.00011082235,"about_ca_system_score_gemma":0.00025769408,"threshold_uncertainty_score":0.8978213},"labels":[],"label_agreement":null},{"id":"W1454366973","doi":"10.1118/1.4925760","title":"TU‐G‐303‐00: Radiomics: Advances in the Use of Quantitative Imaging Used for Predictive Modeling","year":2015,"lang":"en","type":"article","venue":"Medical Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Radiomics; Radiogenomics; Medical imaging; Medical physics; Artificial intelligence; Medicine; Precision medicine; Machine learning; Computer science; Predictive modelling; Pathology","score_opus":0.06117634897989373,"score_gpt":0.3592226924878784,"score_spread":0.2980463435079847,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1454366973","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12376235,0.0014600952,0.86856645,0.0049056956,0.00030724955,0.0006188229,0.000015282929,0.00004137822,0.00032268674],"genre_scores_gemma":[0.98864466,0.0002166,0.008674328,0.0018561896,0.00045022822,0.000055773722,0.000050693092,0.00003618667,0.000015334686],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99789405,0.0001265639,0.0004572341,0.0002828872,0.0009150853,0.00032419962],"domain_scores_gemma":[0.9981263,0.0010135608,0.00013772899,0.0002643469,0.00020658244,0.0002514364],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013127465,0.00016864092,0.00047105603,0.0000769769,0.00005243522,0.000022909373,0.0002391809,0.00006770364,0.0000060478214],"category_scores_gemma":[0.00442694,0.000116390285,0.00013154678,0.00028670856,0.00040622102,0.00033138215,0.000047982867,0.0005963322,0.000002312076],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004499739,0.0042447867,0.129976,0.0019712285,0.0006727481,0.0005337852,0.0707192,0.26421747,0.0014677688,0.04400602,0.02238779,0.45530346],"study_design_scores_gemma":[0.002955982,0.00024025256,0.000107227606,0.00036869926,0.00007299473,0.000021482845,0.001038424,0.98035467,0.00013530241,0.009697211,0.0048852954,0.0001224719],"about_ca_topic_score_codex":0.00008312995,"about_ca_topic_score_gemma":0.000004433805,"teacher_disagreement_score":0.8648823,"about_ca_system_score_codex":0.000074508855,"about_ca_system_score_gemma":0.0003210942,"threshold_uncertainty_score":0.52997804},"labels":[],"label_agreement":null},{"id":"W1458602498","doi":"10.1118/1.4925597","title":"TU‐CD‐BRB‐12: Radiogenomics of MRI‐Guided Prostate Cancer Biopsy Habitats","year":2015,"lang":"en","type":"article","venue":"Medical Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Genome British Columbia","funders":"","keywords":"Radiogenomics; Prostate cancer; Prostate; Medicine; Biopsy; Prostatectomy; Pathology; Cancer; Radiology; Internal medicine; Radiomics","score_opus":0.02568351455757741,"score_gpt":0.3209024599815946,"score_spread":0.2952189454240172,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1458602498","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9368929,0.0022943595,0.023416404,0.025036622,0.0019561322,0.0008019743,0.000040294348,0.00022336225,0.009337928],"genre_scores_gemma":[0.99050605,0.00046255076,0.0031743757,0.0029418513,0.0016749352,0.00003498963,0.00007598018,0.00008278005,0.0010464968],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973732,0.000068186586,0.0005482601,0.00035879874,0.0011986527,0.000452885],"domain_scores_gemma":[0.9980602,0.00011471819,0.00019733078,0.00039710655,0.00022054627,0.0010100974],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000825807,0.00023165146,0.00064181624,0.0000672934,0.000052908323,0.000015872614,0.0002623744,0.00014931157,0.00013393088],"category_scores_gemma":[0.001146941,0.00018967185,0.00016361139,0.00028519283,0.0006462086,0.00007728282,0.000115385985,0.0006957498,0.000040070383],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007796062,0.0018686551,0.28172073,0.0012879609,0.0009556436,0.0010579939,0.0067770057,0.0009919958,0.012689641,0.0035566352,0.22273135,0.4655828],"study_design_scores_gemma":[0.07607058,0.004170172,0.08065614,0.007854901,0.0031752668,0.002821702,0.0016347608,0.26191217,0.06340124,0.061392296,0.4320063,0.0049044746],"about_ca_topic_score_codex":0.00029221404,"about_ca_topic_score_gemma":0.0000045906213,"teacher_disagreement_score":0.4606783,"about_ca_system_score_codex":0.00014938365,"about_ca_system_score_gemma":0.0009391109,"threshold_uncertainty_score":0.7734593},"labels":[],"label_agreement":null},{"id":"W1462988911","doi":"10.1118/1.4925450","title":"MO‐F‐CAMPUS‐J‐04: Tissue Segmentation‐Based MR Electron Density Mapping Method for MR‐Only Radiation Treatment Planning of Brain","year":2015,"lang":"en","type":"article","venue":"Medical Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; University of Toronto; Sunnybrook Health Science Centre","funders":"","keywords":"Voxel; Hounsfield scale; Sagittal plane; Skull; Nuclear medicine; Coronal plane; Histogram; Soft tissue; Intensity (physics); Segmentation; Magnetic resonance imaging; Materials science; Physics; Medicine; Anatomy; Radiology; Computer science; Computed tomography; Artificial intelligence; Optics","score_opus":0.027280479002914644,"score_gpt":0.3720904940719347,"score_spread":0.34481001506902004,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1462988911","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12525126,0.00020255653,0.86687565,0.0066543906,0.00019457539,0.00051664887,0.0000055707283,0.00006524228,0.00023411098],"genre_scores_gemma":[0.9066553,0.00001811003,0.08628968,0.004500843,0.0014777066,0.00007004692,0.0005039205,0.00006261274,0.000421773],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99817735,0.00013553616,0.00038035924,0.00029947323,0.00068377407,0.00032348494],"domain_scores_gemma":[0.9984379,0.0006159799,0.00020533321,0.00018404474,0.00013117123,0.00042560656],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010339313,0.0001859666,0.0004914286,0.00008439806,0.00008016648,0.000013448806,0.00010078859,0.00012453295,0.000017794311],"category_scores_gemma":[0.0014521715,0.00015931787,0.00011767129,0.00021528994,0.0001121058,0.0000620039,0.000021164004,0.00028443974,0.000006019674],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032625423,0.0006315623,0.013714148,0.0002876276,0.00027214835,0.000043447326,0.002356971,0.0016639394,0.028707635,0.0008571968,0.010158529,0.94098055],"study_design_scores_gemma":[0.021298122,0.0031953447,0.0048568933,0.0006570508,0.0005993737,0.00010215102,0.00040789752,0.6067039,0.31600526,0.007904676,0.037665527,0.00060381804],"about_ca_topic_score_codex":0.000097535936,"about_ca_topic_score_gemma":0.0000018540709,"teacher_disagreement_score":0.9403767,"about_ca_system_score_codex":0.00026950747,"about_ca_system_score_gemma":0.0006032436,"threshold_uncertainty_score":0.6496794},"labels":[],"label_agreement":null},{"id":"W1492342382","doi":"10.1117/1.jmi.2.3.034002","title":"Hole filling with oriented sticks in ultrasound volume reconstruction","year":2015,"lang":"en","type":"article","venue":"Journal of Medical Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"National Center for Research Resources; National Institute of Mental Health","keywords":"Interpolation (computer graphics); Medicine; Voxel; Artificial intelligence; Computer vision; Ultrasound; Volume (thermodynamics); Iterative reconstruction; Fidelity; Image (mathematics); Radiology; Computer science","score_opus":0.010760787639555748,"score_gpt":0.289932921175335,"score_spread":0.27917213353577924,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1492342382","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8771998,0.0009736273,0.09832117,0.020375494,0.0010920359,0.00010486552,5.569316e-7,0.000028996643,0.0019034032],"genre_scores_gemma":[0.98783964,0.00013123474,0.009810802,0.0012302708,0.00083094096,0.0000011644041,0.0000034936859,0.000026237976,0.00012619293],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99742013,0.000092859416,0.000614808,0.00015398393,0.0014332976,0.00028488957],"domain_scores_gemma":[0.9983566,0.00016862761,0.00029219198,0.00012253094,0.00029987993,0.000760164],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025835638,0.00012908151,0.00041148378,0.0003042184,0.000036699068,0.000038968523,0.0001497999,0.00007329939,0.00020631375],"category_scores_gemma":[0.0051468336,0.000089898225,0.00007040306,0.00031373397,0.00023318204,0.00023430317,0.000020754316,0.0014231405,0.0000074081518],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042092067,0.00024066135,0.60641724,0.00007176164,0.00009265012,0.0041368394,0.0011324261,0.00063311413,0.0008716676,0.00007246093,0.0077818967,0.37812835],"study_design_scores_gemma":[0.027248474,0.0007447288,0.055493437,0.008582376,0.00044212735,0.09657174,0.009696888,0.7304361,0.00040845753,0.0007205167,0.06902247,0.00063266023],"about_ca_topic_score_codex":0.0000705835,"about_ca_topic_score_gemma":0.0000042351353,"teacher_disagreement_score":0.729803,"about_ca_system_score_codex":0.00017410325,"about_ca_system_score_gemma":0.00061606074,"threshold_uncertainty_score":0.6182916},"labels":[],"label_agreement":null},{"id":"W1496702937","doi":"10.1118/1.4923960","title":"SU‐E‐P‐26: Oncospace: A Shared Radiation Oncology Database System Designed for Personalized Medicine, Decision Support, and Research","year":2015,"lang":"en","type":"article","venue":"Medical Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Health Sciences Centre; Sunnybrook Health Science Centre","funders":"","keywords":"Computer science; Database; DICOM; World Wide Web; Data management","score_opus":0.0866412333439493,"score_gpt":0.438792937745935,"score_spread":0.3521517044019857,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1496702937","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.051550794,0.0026293518,0.879515,0.053663757,0.0016671661,0.0029040398,0.000057705663,0.00050354254,0.0075086607],"genre_scores_gemma":[0.95975924,0.000520592,0.025177695,0.0052555236,0.0064169546,0.00034675896,0.00089037296,0.00020211117,0.0014307792],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99591976,0.00034895065,0.0005100825,0.00055617065,0.0020864196,0.0005786389],"domain_scores_gemma":[0.99507976,0.0023088718,0.00014257508,0.00038666453,0.0005148019,0.0015673272],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0070983614,0.00021459507,0.00073088886,0.00017159455,0.00020910491,0.000040364575,0.0002370623,0.00025511652,0.00011877487],"category_scores_gemma":[0.012842334,0.00016471327,0.000084719206,0.00042570353,0.0009478656,0.00014331302,0.00013650002,0.00091979903,0.000041620122],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021424168,0.00041916413,0.0019222269,0.0007858876,0.00014363605,0.0005666453,0.0036934335,0.000005569164,0.0011946314,0.01302788,0.42982996,0.5462685],"study_design_scores_gemma":[0.048717164,0.006295931,0.0007292191,0.0028222124,0.00055294426,0.0009197296,0.0039880406,0.16635717,0.0005819883,0.0050116507,0.7633925,0.0006314668],"about_ca_topic_score_codex":0.00015185079,"about_ca_topic_score_gemma":0.0000047563,"teacher_disagreement_score":0.90820843,"about_ca_system_score_codex":0.00048488413,"about_ca_system_score_gemma":0.0014137606,"threshold_uncertainty_score":0.9954729},"labels":[],"label_agreement":null},{"id":"W1499937040","doi":"10.1158/1538-7445.sabcs14-p5-10-16","title":"Abstract P5-10-16: Evaluation of RT-qPCR and luminex-based methodolgies in HER2 breast cancer testing","year":2015,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary; Alberta Health Services","funders":"","keywords":"Medicine; Breast cancer; Immunohistochemistry; Internal medicine; Oncology; Cancer; Breast carcinoma; Pathology","score_opus":0.35186833761467967,"score_gpt":0.543468939257221,"score_spread":0.19160060164254128,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1499937040","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98652387,0.003503283,0.0000690463,0.006136679,0.00009595826,0.00041082676,0.000011735185,0.000019630861,0.0032289897],"genre_scores_gemma":[0.99767596,0.00009841607,0.001517326,0.00012701572,0.00020015826,0.00013346715,0.0000076682045,0.000025718417,0.00021430082],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9974207,0.00038763243,0.0002750013,0.00028481608,0.0012806207,0.00035122497],"domain_scores_gemma":[0.99772257,0.00053269265,0.00007786012,0.00020768141,0.0012181896,0.00024098453],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009458936,0.000103984166,0.00028454934,0.0003105412,0.000051771796,0.00002681098,0.00010937724,0.00007040318,0.0004297366],"category_scores_gemma":[0.0051038745,0.00008720446,0.000027037433,0.0005822422,0.0002874873,0.00007946173,0.000053681586,0.000624289,0.0000035030366],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00056571775,0.00015056449,0.352029,0.00074810704,0.000060348073,0.000030658663,0.00087613385,0.0052124797,0.060905483,0.000026605037,0.0067993407,0.5725956],"study_design_scores_gemma":[0.006999843,0.00020765408,0.85249484,0.0023675323,0.0001084946,0.000031080115,0.0009910956,0.12754533,0.0060591456,0.00067268236,0.0022906752,0.00023165932],"about_ca_topic_score_codex":0.014178388,"about_ca_topic_score_gemma":0.0003205902,"teacher_disagreement_score":0.5723639,"about_ca_system_score_codex":0.0005744976,"about_ca_system_score_gemma":0.0017656434,"threshold_uncertainty_score":0.9923863},"labels":[],"label_agreement":null},{"id":"W1525399152","doi":"10.1002/ijc.28683","title":"Improving the TNM classification: Findings from a 10-year continuous literature review","year":2013,"lang":"en","type":"article","venue":"International Journal of Cancer","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":137,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; Queen's University","funders":"Sanofi","keywords":"Documentation; Medicine; Classification scheme; Multidisciplinary approach; Process (computing); Medical physics; MEDLINE; Systematic review; Intensive care medicine; Computer science; Data science; Political science","score_opus":0.009373808064181111,"score_gpt":0.31642174977609855,"score_spread":0.30704794171191746,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1525399152","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4056764,0.2118264,0.0028255603,0.37125757,0.0042423643,0.00056990486,0.000028540213,0.000034362798,0.003538883],"genre_scores_gemma":[0.92088056,0.043938898,0.002485883,0.024991553,0.0042735967,0.000033167675,0.000026963096,0.000030826588,0.0033385842],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988883,0.000033701395,0.00036895042,0.00009543457,0.00051931624,0.000094255],"domain_scores_gemma":[0.9984969,0.00009910111,0.00031524186,0.000109391345,0.0008919579,0.00008740011],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002882093,0.00008087518,0.00020044943,0.000061434665,0.000032413798,0.00011481639,0.0002965431,0.000038154827,0.0025401332],"category_scores_gemma":[0.00057083246,0.00004636886,0.00013310833,0.00008326978,0.00005108155,0.00016923602,0.000030111101,0.0004935911,0.00003700077],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021664969,0.000109288114,0.039446283,0.00023061749,0.0010807016,0.00023245088,0.0006923411,0.000011957361,0.026356416,0.00071459,0.42642978,0.50447893],"study_design_scores_gemma":[0.003951338,0.00017828212,0.19167286,0.021974815,0.00056660484,0.0009874507,0.00022516906,0.0052044867,0.00066745584,0.00096246105,0.77334523,0.00026383763],"about_ca_topic_score_codex":0.000098465556,"about_ca_topic_score_gemma":0.0000013739408,"teacher_disagreement_score":0.51520413,"about_ca_system_score_codex":0.000098334225,"about_ca_system_score_gemma":0.0001174441,"threshold_uncertainty_score":0.99837166},"labels":[],"label_agreement":null},{"id":"W1536516579","doi":"10.1007/978-3-540-85988-8_77","title":"Surface-Based Texture and Morphological Analysis Detects Subtle Cortical Dysplasia","year":2008,"lang":"en","type":"article","venue":"Lecture notes in computer science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":55,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Montreal Neurological Institute and Hospital","funders":"","keywords":"Cortical dysplasia; Computer science; Artificial intelligence; Epilepsy; Pattern recognition (psychology); Classifier (UML); Magnetic resonance imaging; Medicine; Radiology","score_opus":0.013785132927842747,"score_gpt":0.2745169037538729,"score_spread":0.26073177082603016,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1536516579","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.50794166,0.000085198015,0.49056172,0.0012449337,0.000067183,0.00006127647,3.4124838e-7,0.000029266334,0.000008440883],"genre_scores_gemma":[0.8377312,0.000010598258,0.15979071,0.0023959198,0.000060147944,0.000001230334,0.0000027131312,0.000006147947,0.0000013497977],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99838686,0.000060325143,0.0001970977,0.00053597445,0.00044151684,0.000378221],"domain_scores_gemma":[0.9989413,0.00041273655,0.00004337099,0.00028581388,0.00006400269,0.00025279738],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00050046283,0.00014903695,0.00034583642,0.00026110988,0.00021071572,0.000045228786,0.00020091678,0.000098007105,0.000034373275],"category_scores_gemma":[0.00064517884,0.000107125845,0.000070369366,0.0017102672,0.0010597827,0.000058276986,0.00009546928,0.0006532666,0.000004257586],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005755193,0.00013633716,0.77877384,0.000023679459,0.000038601498,0.0014653467,0.0003394335,0.14886086,0.015166502,0.000013426397,0.000017225302,0.05510719],"study_design_scores_gemma":[0.00045091216,0.000131044,0.2804337,0.000018896437,0.000043587304,0.0003822425,2.8161764e-7,0.716393,0.0019475877,0.00008630612,0.000018349352,0.000094093055],"about_ca_topic_score_codex":0.00003962246,"about_ca_topic_score_gemma":0.000008414394,"teacher_disagreement_score":0.5675321,"about_ca_system_score_codex":0.00005784805,"about_ca_system_score_gemma":0.00015972655,"threshold_uncertainty_score":0.43684652},"labels":[],"label_agreement":null},{"id":"W1539433966","doi":"10.1109/iembs.2006.260551","title":"Segmentation of Lung Lobes in Volumetric CT images for Surgical Planning of Treating Lung Cancer","year":2006,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Foothills Medical Centre; University of Calgary","funders":"","keywords":"Lung; Surgical planning; Lung cancer; Radiology; Medicine; Segmentation; Radiation treatment planning; Computer science; Image segmentation; Computer vision; Radiation therapy; Pathology; Internal medicine","score_opus":0.008434649951817204,"score_gpt":0.34501813944670934,"score_spread":0.33658348949489214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1539433966","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9858678,0.0019037307,0.009063164,0.00025563547,0.000054998192,0.00027385794,0.000005239423,0.000017114708,0.0025584379],"genre_scores_gemma":[0.9902862,0.00004093924,0.008812093,0.00002820749,0.00010540991,0.000021988395,0.000030349178,0.000013114362,0.0006617555],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99915,0.000022812423,0.00036859402,0.00013411591,0.00016991448,0.0001545986],"domain_scores_gemma":[0.9994468,0.00026848525,0.00013193708,0.000065139124,0.00005427726,0.00003332884],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003053811,0.00007818957,0.00028811593,0.00018908712,0.000022140746,0.000005851348,0.000037869548,0.00002345875,0.00007005459],"category_scores_gemma":[0.00015711239,0.0000634584,0.00006671292,0.00030125657,0.000042169504,0.00005129979,0.000012163788,0.000105719366,9.537947e-8],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000065474545,0.00007818803,0.97188234,0.00043309567,0.000026915257,0.000020607404,0.00009247779,0.0023330608,0.0069465684,0.00008013961,0.0013513782,0.016689748],"study_design_scores_gemma":[0.0070734834,0.00013004207,0.36609748,0.0008478521,0.00018271545,0.00003079616,0.00029101587,0.5931272,0.031719405,0.000041828276,0.00030675222,0.00015140808],"about_ca_topic_score_codex":0.0031560478,"about_ca_topic_score_gemma":0.0000098483,"teacher_disagreement_score":0.60578483,"about_ca_system_score_codex":0.000063728934,"about_ca_system_score_gemma":0.00003614967,"threshold_uncertainty_score":0.47710213},"labels":[],"label_agreement":null},{"id":"W1539803029","doi":"10.1007/3-540-30005-8_8","title":"Gastrointestinal Nuclear Medicine","year":2006,"lang":"en","type":"book-chapter","venue":"Medical radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St Joseph's Health Centre; Western University; St Joseph's Health Care","funders":"","keywords":"Medicine","score_opus":0.011726552925013508,"score_gpt":0.27369428089627545,"score_spread":0.26196772797126194,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1539803029","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00023661205,0.0015224045,0.0020734437,0.046215765,0.0008306533,0.000306764,0.000007165821,0.00030578498,0.9485014],"genre_scores_gemma":[0.007457727,0.0010718338,0.004791371,0.031771034,0.012909812,0.000013839991,0.0008700962,0.00047375698,0.9406405],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9963614,0.00006552111,0.0009361546,0.0007802089,0.0011897057,0.00066703465],"domain_scores_gemma":[0.9974547,0.00047144474,0.00030625908,0.0005876292,0.0001250815,0.0010548722],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00090955186,0.0005783358,0.0016230177,0.00033883954,0.00011188181,0.000008858372,0.00041458922,0.0006515732,0.024637101],"category_scores_gemma":[0.0026184274,0.00043753852,0.00030739603,0.000048764592,0.0022023027,0.000021146197,0.00014893191,0.0034622613,0.00066764833],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014528121,0.0000564284,0.00048818876,0.0002073973,0.00015375891,0.010340251,0.000026068816,0.0000034405398,0.00009563774,0.08702472,0.8772504,0.024208434],"study_design_scores_gemma":[0.0020794016,0.0010669293,0.00043872593,0.002113169,0.00030382586,0.04100883,0.0000048895076,0.0025433141,4.0631866e-7,0.005189364,0.9449122,0.00033893905],"about_ca_topic_score_codex":0.00008220341,"about_ca_topic_score_gemma":0.0000040125615,"teacher_disagreement_score":0.08183535,"about_ca_system_score_codex":0.00018180933,"about_ca_system_score_gemma":0.00037638334,"threshold_uncertainty_score":0.99980766},"labels":[],"label_agreement":null},{"id":"W1564577891","doi":"","title":"Significance of incidental prostate 18F-FDG uptake on PET/CT and its impact on patient management","year":2012,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brandon Regional Health Authority; McGill University","funders":"","keywords":"Medicine; Malignancy; Standardized uptake value; Radiology; Clinical significance; Lymphoma; Nuclear medicine; Parotid gland; Positron emission tomography; Pathology","score_opus":0.00932501701609366,"score_gpt":0.29900609322549293,"score_spread":0.28968107620939926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1564577891","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9808605,0.00015507224,0.00002136092,0.00049884495,0.00013986966,0.00048178367,0.0000045513248,0.000029431498,0.017808635],"genre_scores_gemma":[0.9973138,0.00009982165,0.0005131206,0.0008618722,0.000052692583,0.000014430557,0.000010175862,0.000018867064,0.0011152007],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99897903,0.000028617405,0.00022092139,0.00017180198,0.0003301046,0.00026954588],"domain_scores_gemma":[0.99945927,0.000046439236,0.00008388215,0.00015418507,0.000022096225,0.00023412218],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026046447,0.00013842239,0.00021384291,0.0000957251,0.000038819675,0.00001000261,0.000044989505,0.0000042376428,0.00017298735],"category_scores_gemma":[0.00006248542,0.000090448826,0.000058651745,0.0000805148,0.000041169395,0.000057454636,0.000040679617,0.0002017927,0.00003426056],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0033663947,0.0050600334,0.39654776,0.0018337488,0.0011765201,0.0039004681,0.0028285338,0.0010356113,0.020494753,0.019868879,0.023611598,0.5202757],"study_design_scores_gemma":[0.00578849,0.0047853035,0.9327247,0.0010446806,0.00027350616,0.0013923978,0.0011848037,0.01522894,0.018852277,0.00013199041,0.017991694,0.00060120155],"about_ca_topic_score_codex":0.000046332436,"about_ca_topic_score_gemma":4.1747253e-7,"teacher_disagreement_score":0.536177,"about_ca_system_score_codex":0.000069926915,"about_ca_system_score_gemma":0.000013997166,"threshold_uncertainty_score":0.3688396},"labels":[],"label_agreement":null},{"id":"W1581953309","doi":"10.1002/9780471420194.tnmc18.pub2","title":"Ampulla of Vater","year":2010,"lang":"en","type":"other","venue":"TNM Online","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Grading (engineering); Pathological; Distant metastasis; Stage (stratigraphy); Lymph node metastasis; Ampulla of Vater; Medicine; Metastasis; Lymph node; Pathology; Cancer; Internal medicine; Biology; Carcinoma; Paleontology","score_opus":0.00866929431326784,"score_gpt":0.3089904714210822,"score_spread":0.30032117710781436,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1581953309","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0038178642,0.00095946353,0.0003505217,0.0035079916,0.0011919462,0.00039079032,0.0006791512,0.00031504707,0.98878723],"genre_scores_gemma":[0.0006654807,0.00020245256,0.023698447,0.0009924013,0.0018335414,0.0000030063134,0.0013200499,0.0004078729,0.97087675],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992406,0.00001259046,0.0002002904,0.00018446571,0.0002080359,0.00015403984],"domain_scores_gemma":[0.9993288,0.000026245902,0.00015407035,0.000349562,0.000027332193,0.00011398022],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000083385195,0.00015555596,0.0004488784,0.00017720657,0.000008075329,0.0000034948266,0.00010627087,0.00026774782,0.026856968],"category_scores_gemma":[0.00019023991,0.000116991934,0.00009632886,0.00007007937,0.00012011175,0.0000047267445,0.000038990962,0.0007724436,0.000079708196],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013289074,0.00015847819,0.0005124489,0.00026459238,0.00008359063,0.00004791986,0.000020264823,1.6272716e-7,0.0021032942,0.000044228545,0.94891447,0.047837276],"study_design_scores_gemma":[0.0005597938,0.00004608481,0.0006446371,0.00052462507,0.00009003302,0.000041886447,0.0000042236848,0.0002556604,0.00006137076,0.000025669682,0.997641,0.000105013714],"about_ca_topic_score_codex":0.00014810056,"about_ca_topic_score_gemma":0.000033216103,"teacher_disagreement_score":0.048726544,"about_ca_system_score_codex":0.000007617771,"about_ca_system_score_gemma":0.00006562323,"threshold_uncertainty_score":0.97403264},"labels":[],"label_agreement":null},{"id":"W1584617426","doi":"10.1118/1.4924336","title":"SU‐E‐J‐250: A Machine Learning Approach for Creating Texture‐Preserved MRI Tumor Models From Clinical Sequences","year":2015,"lang":"en","type":"article","venue":"Medical Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University","funders":"","keywords":"Artificial intelligence; Entropy (arrow of time); Computer science; Texture (cosmology); Pattern recognition (psychology); Gray level; Relaxation (psychology); Mathematics; Image (mathematics); Physics; Medicine","score_opus":0.08026217142550891,"score_gpt":0.3614345043065831,"score_spread":0.2811723328810742,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1584617426","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07939692,0.001033708,0.90445787,0.0040067686,0.0004995088,0.00069636444,0.000027559225,0.00031937944,0.009561945],"genre_scores_gemma":[0.9452322,0.000077814344,0.045400478,0.0035563607,0.0042240326,0.0000863986,0.0007070998,0.0001005098,0.0006150949],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99606,0.00029730462,0.0008490434,0.000745666,0.0014326568,0.00061530777],"domain_scores_gemma":[0.9966345,0.0010445585,0.0002796409,0.000433167,0.00023657233,0.0013716054],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0027768163,0.00033626633,0.0009829454,0.00005173757,0.00020378389,0.000083542865,0.00046077798,0.00025502642,0.00008201369],"category_scores_gemma":[0.00731867,0.00026189245,0.0003584088,0.00024870617,0.00057500036,0.00019592032,0.00021003297,0.0020973561,0.000017929246],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0033282135,0.0061828354,0.4107998,0.0014510325,0.0023277719,0.0010924238,0.006788384,0.050181597,0.00067941356,0.011420306,0.057371583,0.44837663],"study_design_scores_gemma":[0.004568093,0.00041940043,0.00030365575,0.00023194213,0.00020495732,0.000035763333,0.0001880407,0.97426605,0.00008938836,0.013588571,0.0058071106,0.00029704985],"about_ca_topic_score_codex":0.000703946,"about_ca_topic_score_gemma":0.0000045259867,"teacher_disagreement_score":0.9240844,"about_ca_system_score_codex":0.00008552688,"about_ca_system_score_gemma":0.0006094836,"threshold_uncertainty_score":0.9999833},"labels":[],"label_agreement":null},{"id":"W1605460754","doi":"10.1118/1.4925764","title":"TU‐G‐303‐04: Radiomics and the Coming Pan‐Omics Revolution","year":2015,"lang":"en","type":"article","venue":"Medical Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Radiomics; Radiogenomics; Medical imaging; Medical physics; Artificial intelligence; Medicine; Precision medicine; Computer science; Machine learning; Pathology","score_opus":0.016973102453578272,"score_gpt":0.2880504822894855,"score_spread":0.27107737983590724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1605460754","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5914796,0.004546357,0.28499827,0.103655346,0.002109648,0.0010678439,0.0000072389657,0.0003359026,0.011799827],"genre_scores_gemma":[0.98876625,0.0005463238,0.0014182822,0.0070702382,0.0017845988,0.000013849048,0.000033665092,0.000039344195,0.0003274379],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981236,0.00012967254,0.00033230858,0.00026486872,0.00082786946,0.00032167477],"domain_scores_gemma":[0.998519,0.000369926,0.00010575598,0.00032452776,0.00009452509,0.0005862328],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018187335,0.00017090848,0.00045377787,0.00003227144,0.00013719332,0.000036502694,0.00018486887,0.00013423507,0.000015746233],"category_scores_gemma":[0.003105681,0.00011147039,0.00010165947,0.00019000369,0.0011970697,0.00007716454,0.00013875813,0.0009646452,0.000026377618],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013216207,0.00049608096,0.03545443,0.00034342788,0.00039319738,0.00027784103,0.0047617513,0.00008973492,0.00033513556,0.062337115,0.07382393,0.8203657],"study_design_scores_gemma":[0.04838135,0.0005296051,0.008613465,0.0009682131,0.00096170476,0.0016792518,0.0009225956,0.70415413,0.00075982243,0.104060724,0.1279703,0.0009988125],"about_ca_topic_score_codex":0.00010189182,"about_ca_topic_score_gemma":0.0000014638547,"teacher_disagreement_score":0.81936693,"about_ca_system_score_codex":0.00010001183,"about_ca_system_score_gemma":0.00028099873,"threshold_uncertainty_score":0.45456305},"labels":[],"label_agreement":null},{"id":"W1629295276","doi":"10.1520/jfs15212j","title":"The Efficiency of an X-Ray Screening System at a Mass Disaster","year":2002,"lang":"en","type":"article","venue":"Journal of Forensic Sciences","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Office of the Chief Medical Examiner","funders":"","keywords":"Poison control; Forensic engineering; Medical emergency; Engineering; Medicine","score_opus":0.02202984988745869,"score_gpt":0.28571094064995983,"score_spread":0.2636810907625011,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1629295276","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98917615,0.0010401369,0.003919856,0.0023825958,0.00043245745,0.00006197921,3.5991062e-7,0.0000076037077,0.0029788702],"genre_scores_gemma":[0.98775697,0.000035702073,0.011618323,0.00010647872,0.00023515639,3.4485416e-7,1.11031504e-7,0.0000052316072,0.00024168217],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99838966,0.00006660541,0.00043582276,0.00010662639,0.0007876625,0.0002136099],"domain_scores_gemma":[0.99896014,0.00020510376,0.00041987188,0.00013414488,0.00012752946,0.00015320996],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001913392,0.000075811266,0.00023914415,0.000110590285,0.00031335666,0.000047370144,0.00028078337,0.000025047342,0.000027462058],"category_scores_gemma":[0.0004101394,0.000036762987,0.00011370012,0.00027876915,0.0007690613,0.0001385418,0.00002862215,0.00021039376,0.0000026828125],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005418106,0.00047161072,0.17844649,0.000426249,0.00034286763,0.0008535053,0.010602179,0.008619148,0.059057944,0.0047233636,0.01158458,0.72433025],"study_design_scores_gemma":[0.0029703754,0.0036663301,0.025172466,0.0016875876,0.00027221098,0.004661886,0.011495112,0.9378954,0.0045784465,0.0002492191,0.007082867,0.0002680791],"about_ca_topic_score_codex":0.000007903903,"about_ca_topic_score_gemma":0.0000014431553,"teacher_disagreement_score":0.9292763,"about_ca_system_score_codex":0.000030569914,"about_ca_system_score_gemma":0.00003373525,"threshold_uncertainty_score":0.28336385},"labels":[],"label_agreement":null},{"id":"W1652115971","doi":"","title":"Medical image computing and computer-assisted intervention - MICCAI 2003 : 6th International Conference, Montréal, Canada, November 15-18, 2003 : proceedings","year":2003,"lang":"en","type":"book","venue":"Springer eBooks","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Medicine; Library science; Computer science","score_opus":0.010938162908401177,"score_gpt":0.26252342325763395,"score_spread":0.2515852603492328,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1652115971","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00688119,0.0009698464,0.0068743937,0.0014540507,0.0038099377,0.0010429943,0.000037514495,0.00019218973,0.9787379],"genre_scores_gemma":[0.008912586,0.00017757258,0.021726646,0.0055540474,0.0023625887,0.000032984233,0.00037354836,0.00027296253,0.9605871],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99632853,0.00004731011,0.0009299109,0.000836301,0.0012924131,0.000565545],"domain_scores_gemma":[0.9973958,0.000045804944,0.00052296865,0.00025884615,0.0011136725,0.000662888],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00072477973,0.00058454275,0.00092974806,0.00028480784,0.00016405623,0.00020616561,0.00035113978,0.00045501612,0.0010319063],"category_scores_gemma":[0.0005054539,0.0005598965,0.00014011184,0.00010365626,0.00034395873,0.00006687154,0.00032280036,0.0020190587,0.000016157052],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009150963,0.00015430502,0.0018855759,0.0009129239,0.00080487155,0.0008513295,0.00023381072,0.0000010532192,0.00016525055,0.006590313,0.8941034,0.09420565],"study_design_scores_gemma":[0.0041115894,0.00018632853,0.0034615556,0.0050029918,0.00038136594,0.0013111087,0.000068905596,0.06212058,0.000060887167,0.00022961597,0.92219186,0.0008732013],"about_ca_topic_score_codex":0.018830137,"about_ca_topic_score_gemma":0.007620115,"teacher_disagreement_score":0.09333245,"about_ca_system_score_codex":0.00062777416,"about_ca_system_score_gemma":0.0027212752,"threshold_uncertainty_score":0.99988127},"labels":[],"label_agreement":null},{"id":"W1656413649","doi":"10.5430/jbgc.v5n2p1","title":"Evaluating agreement between solid tumor measurements used to assess response","year":2015,"lang":"en","type":"article","venue":"Journal of Biomedical Graphics and Computing","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Cancer Institute; Memorial Sloan-Kettering Cancer Center","keywords":"Limits of agreement; Mean difference; Bland–Altman plot; Statistics; Significant difference; Plot (graphics); Distribution (mathematics); Mathematics; Nuclear medicine; Medicine; Mathematical analysis; Confidence interval","score_opus":0.2153681260112936,"score_gpt":0.4435325674470571,"score_spread":0.2281644414357635,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1656413649","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95297503,0.0002289366,0.03838033,0.0077930754,0.0004224086,0.00014493971,9.946814e-7,0.000014875986,0.00003940489],"genre_scores_gemma":[0.9777507,0.0000048753573,0.019875912,0.0015223994,0.0008125807,6.577501e-7,0.0000022921915,0.000018185214,0.000012366056],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9964559,0.000335479,0.00087640964,0.000209496,0.0017820159,0.0003406688],"domain_scores_gemma":[0.99718076,0.00042606264,0.0004365884,0.00014444714,0.000492977,0.0013191518],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01204316,0.00016378645,0.0005676927,0.00048592614,0.00012741392,0.000072763454,0.00018108074,0.000071903734,0.0000073828237],"category_scores_gemma":[0.004218765,0.00012332828,0.00012705992,0.00048490692,0.0001382379,0.000054649838,0.00013911535,0.000714876,0.0000018605665],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0030681011,0.00094393414,0.5775863,0.00038493206,0.0014013655,0.0013236832,0.005603537,0.00047353018,0.09823431,0.00016000475,0.0071467496,0.30367354],"study_design_scores_gemma":[0.03878432,0.027133496,0.5475237,0.009267756,0.0020178205,0.004854201,0.0031619559,0.3282299,0.0037229357,0.002720333,0.031000333,0.0015832589],"about_ca_topic_score_codex":0.000009789202,"about_ca_topic_score_gemma":3.1920248e-7,"teacher_disagreement_score":0.32775638,"about_ca_system_score_codex":0.00008807527,"about_ca_system_score_gemma":0.00040432098,"threshold_uncertainty_score":0.505056},"labels":[],"label_agreement":null},{"id":"W1666856988","doi":"10.1118/1.4925761","title":"TU‐G‐303‐01: Radiomics: Quantitative Imaging in the Service of Improved Treatment Decision Making","year":2015,"lang":"en","type":"article","venue":"Medical Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Radiomics; Radiogenomics; Medical imaging; Medical physics; Medicine; Precision medicine; Artificial intelligence; Computer science; Machine learning; Pathology","score_opus":0.03087242155890867,"score_gpt":0.3560775288816501,"score_spread":0.32520510732274144,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1666856988","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8560716,0.0010950967,0.12122558,0.01666377,0.0005553453,0.00066183007,0.0000059986196,0.00006303365,0.0036577403],"genre_scores_gemma":[0.9903761,0.00006206129,0.0055459025,0.0035918232,0.00034593986,0.000018029354,0.000018293182,0.000027926426,0.000013915206],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99801785,0.0001291516,0.00043739818,0.00027134237,0.00084092445,0.00030335758],"domain_scores_gemma":[0.9984198,0.00072969,0.00014356709,0.0003554671,0.00012071994,0.00023075865],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012247027,0.0001829731,0.0004452353,0.00007490924,0.000046206173,0.000020331483,0.0002757209,0.00006854588,0.000026846574],"category_scores_gemma":[0.0015254585,0.00011480277,0.000108304484,0.00044291638,0.00022188295,0.000085184554,0.0000673735,0.00046441203,0.00001535936],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000702537,0.0012317238,0.03193094,0.0001479292,0.00010777349,0.0003994168,0.013935475,0.000230156,0.0014367052,0.0027679335,0.0020404186,0.945069],"study_design_scores_gemma":[0.018759944,0.0014109028,0.016298493,0.0026144406,0.0004033598,0.00039103534,0.0062371143,0.91156155,0.0016120969,0.031383444,0.008706062,0.0006215444],"about_ca_topic_score_codex":0.00029804793,"about_ca_topic_score_gemma":0.00002410942,"teacher_disagreement_score":0.94444746,"about_ca_system_score_codex":0.00016812053,"about_ca_system_score_gemma":0.00037217673,"threshold_uncertainty_score":0.4681521},"labels":[],"label_agreement":null},{"id":"W1669943421","doi":"10.1118/1.4923995","title":"SU‐E‐U‐02: The Development of a Practical Ultrasonic System for Cross‐Sectional Imaging of Small Animals","year":2015,"lang":"en","type":"article","venue":"Medical Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Scanner; Imaging phantom; Transducer; Ultrasound; Ultrasonic sensor; Phased array; Medical imaging; Computer science; Biomedical engineering; Materials science; Acoustics; Optics; Physics; Artificial intelligence; Medicine","score_opus":0.04615274562142936,"score_gpt":0.35736535595260066,"score_spread":0.3112126103311713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1669943421","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6134596,0.00021037938,0.38103348,0.0026882729,0.0005063374,0.0004524565,0.000006524221,0.000053885295,0.0015890464],"genre_scores_gemma":[0.9852163,0.000002620639,0.013875105,0.00022820065,0.00055871275,0.000031383875,0.000018329301,0.000024783949,0.000044555192],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9978697,0.000063895626,0.00062247855,0.00021756526,0.00095762254,0.00026874174],"domain_scores_gemma":[0.9981127,0.00073218695,0.00024682123,0.00021301414,0.00036681246,0.00032846731],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002274654,0.00013030432,0.0003668032,0.000031946653,0.00008425248,0.000018481189,0.00017686849,0.000075968506,0.000019080233],"category_scores_gemma":[0.00372155,0.00008664961,0.00013450666,0.0001429764,0.0004852533,0.000040600316,0.00006667447,0.00043246793,0.0000056024546],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014429899,0.0017047921,0.83680433,0.00389623,0.00085273344,0.00008586265,0.006092881,0.00018543481,0.0077443216,0.02799927,0.004520343,0.108670786],"study_design_scores_gemma":[0.038682736,0.0020815518,0.43594736,0.005606042,0.0014204842,0.0025743786,0.0061345636,0.3086134,0.14362283,0.010584558,0.04292505,0.0018070424],"about_ca_topic_score_codex":0.000018258406,"about_ca_topic_score_gemma":0.0000011898084,"teacher_disagreement_score":0.40085697,"about_ca_system_score_codex":0.00011223022,"about_ca_system_score_gemma":0.001385395,"threshold_uncertainty_score":0.4455312},"labels":[],"label_agreement":null},{"id":"W1677190615","doi":"10.1118/1.4925279","title":"MO‐AB‐BRA‐09: Temporally Realistic Manipulation a 4D Biomechanical Lung Phantom for Evaluation of Simultaneous Registration and Segmentation","year":2015,"lang":"en","type":"article","venue":"Medical Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Imaging phantom; Ground truth; Segmentation; Computer science; Bellows; Contouring; Breathing; Computer vision; Nuclear medicine; Biomedical engineering; Artificial intelligence; Simulation; Medicine; Materials science; Computer graphics (images)","score_opus":0.05467691116677252,"score_gpt":0.38202832966961936,"score_spread":0.3273514185028468,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1677190615","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26201987,0.00015171309,0.73499304,0.001600862,0.00018822847,0.000790082,0.000007991236,0.000046563353,0.00020163153],"genre_scores_gemma":[0.9943341,0.000020597943,0.004388109,0.00025992573,0.00048119415,0.000036578986,0.00042017293,0.00002223629,0.000037064925],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99778473,0.00010182365,0.00041157648,0.000253853,0.0012896379,0.00015836365],"domain_scores_gemma":[0.9986361,0.0002691578,0.0002167342,0.00014004292,0.00044096753,0.00029696865],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001957302,0.000120914985,0.0002702854,0.000053355445,0.00005959346,0.000024175608,0.00006208218,0.00012022883,0.000013701244],"category_scores_gemma":[0.0038462877,0.00010774467,0.000052042193,0.00015430758,0.00016684955,0.00009493967,0.000023076913,0.00018191928,0.0000012433337],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008126631,0.0007393278,0.0043612444,0.0010094204,0.00020781909,0.000035011082,0.0012918315,0.0033048645,0.016822588,0.009215008,0.0036021383,0.9585981],"study_design_scores_gemma":[0.0044486895,0.00031625587,0.00018795622,0.00017973346,0.0003425068,0.000030253883,0.00008186227,0.9805364,0.0016526299,0.012014696,0.00010632053,0.00010266657],"about_ca_topic_score_codex":0.000089617744,"about_ca_topic_score_gemma":0.000004820847,"teacher_disagreement_score":0.97723156,"about_ca_system_score_codex":0.00012574931,"about_ca_system_score_gemma":0.00037023818,"threshold_uncertainty_score":0.46046433},"labels":[],"label_agreement":null},{"id":"W174898597","doi":"","title":"Comparison of 3D versus 2D 13N-ammonia PET myocardial perfusion imaging","year":2010,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Cardiac PET; Myocardial perfusion imaging; Nuclear medicine; Medicine; Perfusion; Pet imaging; Cardiac imaging; Radiology; Positron emission tomography","score_opus":0.01372755736774818,"score_gpt":0.3371573957121646,"score_spread":0.3234298383444164,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W174898597","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9553094,0.00008070366,0.0011109087,0.003155928,0.0016949642,0.00013059277,0.0000011706744,0.000087206645,0.038429163],"genre_scores_gemma":[0.97876006,0.000013385321,0.019922763,0.00028743563,0.0004672304,0.0000026174448,0.000018179453,0.000023657149,0.0005046539],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988493,0.000027756125,0.0003002508,0.00022217569,0.0003568591,0.00024366102],"domain_scores_gemma":[0.99920756,0.0001327634,0.00009086884,0.00029817453,0.00008473159,0.00018590612],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003569346,0.00013070127,0.000378777,0.00010245542,0.00008006894,0.000018841845,0.00011339057,0.00004341006,0.00061958766],"category_scores_gemma":[0.00048036163,0.00010433978,0.00010680712,0.000111694884,0.0001680744,0.000054461125,0.00007405486,0.0007702068,0.00004480736],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005844816,0.00034801805,0.45093265,0.00008204688,0.000076376826,0.0000881703,0.00072042906,0.000047409514,0.3294495,0.0011803964,0.014650177,0.20184036],"study_design_scores_gemma":[0.017846595,0.0006822308,0.2029994,0.00023164313,0.00067379547,0.00047778274,0.0014442856,0.5616149,0.020710051,0.000114271286,0.19244823,0.00075681414],"about_ca_topic_score_codex":0.00021479392,"about_ca_topic_score_gemma":0.000016826407,"teacher_disagreement_score":0.5615675,"about_ca_system_score_codex":0.000018953575,"about_ca_system_score_gemma":0.00007229696,"threshold_uncertainty_score":0.67840505},"labels":[],"label_agreement":null},{"id":"W177830474","doi":"10.1007/978-3-319-03813-1_6","title":"Accurate Pathology Segmentation in FLAIR MRI for Robust Shape Characterization","year":2014,"lang":"en","type":"book-chapter","venue":"Lecture notes in computational vision and biomechanics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University of Guelph","funders":"","keywords":"Artificial intelligence; Segmentation; Pattern recognition (psychology); Fluid-attenuated inversion recovery; Multispectral image; Computer science; Hyperintensity; Voxel; Artifact (error); Linear discriminant analysis; Magnetic resonance imaging; Computer vision; Medicine; Radiology","score_opus":0.015890451832243583,"score_gpt":0.2936491769422285,"score_spread":0.2777587251099849,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W177830474","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031023335,0.00015621561,0.9901596,0.0052437126,0.00035800927,0.0007130834,0.000041192612,0.000036322865,0.00018958849],"genre_scores_gemma":[0.67726624,0.0019116921,0.26926717,0.021198869,0.0016459709,0.0001282217,0.024305215,0.00037214157,0.0039044542],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99865454,0.00003536537,0.00046881774,0.0004106189,0.00024435628,0.00018627016],"domain_scores_gemma":[0.9990572,0.00041075793,0.00023444532,0.000104090934,0.00011464966,0.00007885853],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000396724,0.00026983392,0.0004570205,0.0005096169,0.00006179318,0.000039583432,0.000066571105,0.00040228182,0.000073634095],"category_scores_gemma":[0.00018869987,0.00023419644,0.000076215765,0.00009360275,0.00004848015,0.00004144269,0.00004821338,0.0004667307,0.000005678325],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003392318,0.00007675509,0.0000816443,0.0005418363,0.000045646833,0.00006398078,0.00029117783,0.017440442,0.011208106,0.012732065,0.00008404384,0.9570951],"study_design_scores_gemma":[0.0017398467,0.00033801,0.00048147602,0.00052183296,0.00003819366,0.00008483677,0.0000023490434,0.9604619,0.00008495086,0.03137916,0.004632794,0.0002346137],"about_ca_topic_score_codex":0.000002369502,"about_ca_topic_score_gemma":0.0000061993815,"teacher_disagreement_score":0.9568605,"about_ca_system_score_codex":0.00009832872,"about_ca_system_score_gemma":0.00007350379,"threshold_uncertainty_score":0.9550254},"labels":[],"label_agreement":null},{"id":"W1816291279","doi":"10.17169/refubium-6123","title":"Prospektive Studie zum Vergleich von telepathologischem und konventionellem Schnellschnitt in der Routinediagnostik","year":2015,"lang":"de","type":"dissertation","venue":"Refubium (Universitätsbibliothek der Freien Universität Berlin)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science","score_opus":0.017872706974890865,"score_gpt":0.31529097229963554,"score_spread":0.2974182653247447,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1816291279","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8090093,0.07868527,0.010561425,0.007454549,0.010088393,0.0071719084,0.00045514994,0.0011338177,0.07544019],"genre_scores_gemma":[0.8618226,0.030550025,0.012653628,0.0012138216,0.0028312043,0.000051719235,0.011272653,0.0009250223,0.07867929],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9901516,0.00083842,0.0014015706,0.0029000642,0.0023343752,0.0023740148],"domain_scores_gemma":[0.9928801,0.0007241652,0.0015004886,0.0016248216,0.0017314677,0.0015389726],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"category_scores_codex":[0.0020150736,0.0019119644,0.0026888007,0.0104089705,0.0010240761,0.00033179807,0.0019501339,0.0020405226,0.0013226918],"category_scores_gemma":[0.00096055056,0.0021550346,0.0008709353,0.010455413,0.0009374764,0.0036842073,0.00092486927,0.0050549763,0.0018313819],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.02218791,0.018520216,0.40072757,0.009201128,0.03537023,0.09888538,0.09742639,0.0059627965,0.005346801,0.051239934,0.18209885,0.07303279],"study_design_scores_gemma":[0.08226082,0.0071670874,0.06959856,0.017956002,0.048828438,0.0005796679,0.17416526,0.04601175,0.0015517186,0.009084795,0.5287494,0.0140464865],"about_ca_topic_score_codex":0.001404137,"about_ca_topic_score_gemma":0.00061089743,"teacher_disagreement_score":0.34665057,"about_ca_system_score_codex":0.0030999351,"about_ca_system_score_gemma":0.0024217824,"threshold_uncertainty_score":0.9995902},"labels":[],"label_agreement":null},{"id":"W1824790222","doi":"10.3109/0284186x.2015.1061214","title":"External validation of a prognostic CT-based radiomic signature in oropharyngeal squamous cell carcinoma","year":2015,"lang":"en","type":"article","venue":"Acta Oncologica","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":220,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto","funders":"National Cancer Institute; Stichting voor de Technische Wetenschappen; Nederlandse Organisatie voor Wetenschappelijk Onderzoek","keywords":"Medicine; Proportional hazards model; Cohort; Head and neck cancer; Log-rank test; Head and neck squamous-cell carcinoma; Oncology; Lung cancer; Internal medicine; Nuclear medicine; Head and neck; Radiology; Cancer; Surgery","score_opus":0.02121364223199364,"score_gpt":0.2897854946914529,"score_spread":0.2685718524594593,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1824790222","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9939413,0.00047848368,0.0002992481,0.0017064973,0.00019312804,0.00044091622,0.0000028708528,0.00004241158,0.0028951168],"genre_scores_gemma":[0.9947992,0.000005205791,0.0041787317,0.00066227274,0.00014582499,0.000023589684,0.000035658897,0.00001895972,0.00013057378],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99864554,0.00015084984,0.00034053222,0.0002621368,0.00033703967,0.00026390803],"domain_scores_gemma":[0.99901354,0.0003002504,0.00017786742,0.00019979474,0.00008721874,0.00022130088],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000562795,0.00015027038,0.00040557445,0.0001613544,0.000025667892,0.000012466063,0.0001633884,0.00010053956,0.000098832934],"category_scores_gemma":[0.0010654662,0.00011540456,0.000076842785,0.00023241958,0.00009777751,0.00005666915,0.000038500035,0.00054718833,0.000011140236],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010532464,0.0018588521,0.7735867,0.00033187564,0.000013365768,0.0023522843,0.0006275863,0.0014316803,0.20240772,0.000044451535,0.0063565504,0.009935668],"study_design_scores_gemma":[0.03846369,0.010682439,0.74938405,0.00044649767,0.00052680576,0.0007268794,0.00038643557,0.09005867,0.09854249,0.00101425,0.008854536,0.000913261],"about_ca_topic_score_codex":0.0001086427,"about_ca_topic_score_gemma":0.0000020540986,"teacher_disagreement_score":0.10386523,"about_ca_system_score_codex":0.00021076798,"about_ca_system_score_gemma":0.00042240234,"threshold_uncertainty_score":0.47060612},"labels":[],"label_agreement":null},{"id":"W1843413878","doi":"10.1155/2008/923879","title":"Positron Emission Tomography Scanning and Gastroenterology","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Gastroenterology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University Hospital; Western University","funders":"","keywords":"Positron emission tomography; Nuclear medicine; Medical physics; Brain positron emission tomography; Tomography; Positron emission; Medicine; Preclinical imaging; Radiology; Biology; Genetics; In vivo","score_opus":0.008189120409315876,"score_gpt":0.2353476446212566,"score_spread":0.22715852421194072,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1843413878","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99021816,0.00041910994,0.0015864072,0.007133948,0.00035627093,0.000063378204,0.0000026701946,0.0000068792074,0.00021314561],"genre_scores_gemma":[0.9930705,0.00008003319,0.0026477645,0.0038512002,0.00024603397,8.6838423e-7,0.0000049369073,0.000018588857,0.000080083504],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9987509,0.00010390395,0.00037537937,0.00015291627,0.00012091965,0.0004959325],"domain_scores_gemma":[0.9983477,0.000024244237,0.00019344504,0.00011504106,0.0001174752,0.0012020982],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029187454,0.00013563431,0.00042416187,0.0005817641,0.00015163385,0.000011031449,0.00011509157,0.00007589902,0.000062599174],"category_scores_gemma":[0.00014069238,0.00011700882,0.0001227223,0.00007349034,0.00043175108,0.00007091919,0.000016863052,0.0006137063,0.0000013753055],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005304083,0.000017115648,0.9903094,0.000013724186,0.00008035967,0.0018035002,0.00024275505,0.000012393952,0.0013471729,0.000009033466,0.0048544924,0.0007796068],"study_design_scores_gemma":[0.0033836039,0.0049778465,0.90733075,0.00016204001,0.000118650605,0.07625615,0.00008965995,0.0003940174,0.000058179186,0.00005164415,0.007107668,0.0000697874],"about_ca_topic_score_codex":0.000429303,"about_ca_topic_score_gemma":0.00035010354,"teacher_disagreement_score":0.08297868,"about_ca_system_score_codex":0.000062534695,"about_ca_system_score_gemma":0.0002468576,"threshold_uncertainty_score":0.47714812},"labels":[],"label_agreement":null},{"id":"W1844424555","doi":"10.1200/jco.2015.33.7_suppl.25","title":"Using radiogenomics to characterize MRI-guided prostate cancer biopsy heterogenity.","year":2015,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Genome British Columbia","funders":"","keywords":"Radiogenomics; Prostate cancer; Medicine; Prostate; Biopsy; Cancer; Radiology; Pathology; Internal medicine; Radiomics","score_opus":0.26198606516777245,"score_gpt":0.5140470768292913,"score_spread":0.25206101166151884,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1844424555","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96473306,0.00035774717,0.0020937847,0.02882809,0.003286764,0.00022675822,0.0000045847405,0.000013660653,0.00045557317],"genre_scores_gemma":[0.89668316,0.0006249229,0.08041368,0.016694868,0.0051369146,0.000004667297,0.000003918868,0.000053408126,0.0003844849],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99654067,0.00035349236,0.0021603554,0.00021207315,0.0004039963,0.00032939354],"domain_scores_gemma":[0.9960233,0.00039266108,0.0013240922,0.00019518504,0.0006131569,0.0014515996],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0049393564,0.00015611926,0.0014278365,0.00018035676,0.000044462988,0.00002169779,0.00021196168,0.00024397105,0.00005616837],"category_scores_gemma":[0.0054813884,0.00011457791,0.00037809458,0.00018428377,0.00016640386,0.000103705286,0.00008760655,0.0012114807,0.000019831352],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.009580058,0.0019433788,0.46101034,0.000099511126,0.0013755759,0.005441947,0.0014824508,0.002648749,0.034539077,0.00008423118,0.029877609,0.45191708],"study_design_scores_gemma":[0.022338077,0.009339853,0.13994373,0.00044327482,0.0010918115,0.012251801,0.00021635278,0.01711199,0.00048278514,0.00037398582,0.79595464,0.00045169564],"about_ca_topic_score_codex":0.000101289064,"about_ca_topic_score_gemma":0.000003822408,"teacher_disagreement_score":0.76607704,"about_ca_system_score_codex":0.0003695124,"about_ca_system_score_gemma":0.0022830511,"threshold_uncertainty_score":0.656213},"labels":[],"label_agreement":null},{"id":"W1871071110","doi":"10.1164/ajrccm.164.10.2102086","title":"When the Chest X-ray Does Not Tell the Whole Story","year":2001,"lang":"en","type":"article","venue":"American Journal of Respiratory and Critical Care Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Medicine; Medical physics","score_opus":0.01469235318709359,"score_gpt":0.3109012965494872,"score_spread":0.2962089433623936,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1871071110","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.697917,0.014950987,0.0015276669,0.28261945,0.00064730697,0.00016406593,0.000002669999,0.000022036933,0.0021488115],"genre_scores_gemma":[0.9594382,0.00030350368,0.00040170658,0.03758996,0.0021041057,0.0000033442227,7.3988e-7,0.000021660393,0.00013678904],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980302,0.0003991481,0.0004463438,0.00017917994,0.00064997573,0.0002951712],"domain_scores_gemma":[0.9971409,0.0016178854,0.00018823886,0.00029766522,0.00034493557,0.00041038083],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0017593395,0.00017667275,0.0005161039,0.00009798957,0.00030308985,0.00002837069,0.0002553879,0.000041528463,0.0001469798],"category_scores_gemma":[0.003182056,0.000069276975,0.000116316376,0.00018478709,0.0037007201,0.000078435485,0.000045126555,0.0013791285,0.0000041269],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00070283725,0.00009456077,0.03467257,0.00016148899,0.00014879713,0.0012845532,0.008347111,0.000007795248,0.008284657,0.0007842254,0.013013336,0.9324981],"study_design_scores_gemma":[0.0015559997,0.004236063,0.026089966,0.00043147613,0.0005193633,0.001188916,0.039716665,0.00007839768,0.00012658855,0.00017486152,0.9257281,0.00015361459],"about_ca_topic_score_codex":0.000029677798,"about_ca_topic_score_gemma":0.000003328649,"teacher_disagreement_score":0.93234444,"about_ca_system_score_codex":0.000039404884,"about_ca_system_score_gemma":0.00013421441,"threshold_uncertainty_score":0.9990106},"labels":[],"label_agreement":null},{"id":"W1922184826","doi":"10.5489/cuaj.895","title":"MRI and prostate cancer: the next frontier","year":2013,"lang":"en","type":"article","venue":"Canadian Urological Association Journal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Frontier; Prostate cancer; Cancer; Medicine; Prostate; Magnetic resonance imaging; Radiology; Internal medicine; Geography; Archaeology","score_opus":0.007810286932602959,"score_gpt":0.232946386845175,"score_spread":0.22513609991257202,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1922184826","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5826775,0.0012612508,0.000073876305,0.4138113,0.0003127562,0.0001843204,0.0000028335637,0.0000131208635,0.0016630687],"genre_scores_gemma":[0.96866554,0.00090034393,0.00036504018,0.026979946,0.00057205756,0.00001663806,0.0000031048196,0.0000090307185,0.002488302],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9990966,0.0000928731,0.0001710894,0.00010596564,0.00019820059,0.00033531035],"domain_scores_gemma":[0.9990057,0.00008825931,0.00011543724,0.000058765545,0.00013455958,0.00059730135],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000503955,0.00007597316,0.00014607995,0.000055849883,0.0003110359,0.00020253319,0.00007272979,0.00009064102,0.0009769171],"category_scores_gemma":[0.0006210679,0.00004333564,0.000047636953,0.00008290014,0.000054315526,0.000098562035,0.000011411454,0.00079942436,0.000039856885],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005325974,0.000006648316,0.804894,0.0000022004308,0.000056099463,0.000020250405,0.00018836158,0.000023555443,0.00006322943,0.0000931714,0.14104503,0.053602155],"study_design_scores_gemma":[0.00041464096,0.00005489952,0.6834887,0.000009114045,0.000036323458,0.00014915844,0.00008822726,0.004106511,0.0000013168584,0.0011238318,0.3104717,0.000055559598],"about_ca_topic_score_codex":0.005060361,"about_ca_topic_score_gemma":0.00019198147,"teacher_disagreement_score":0.38683134,"about_ca_system_score_codex":0.00029647522,"about_ca_system_score_gemma":0.00022612911,"threshold_uncertainty_score":0.99993634},"labels":[],"label_agreement":null},{"id":"W1943685717","doi":"10.1158/1538-7445.am2014-2490","title":"Abstract 2490: Integrative systems analysis of HPV+ and HPV- oropharyngeal carcinomas","year":2014,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Institute for Cancer Research; University of Toronto; University Health Network","funders":"","keywords":"Concordance; Immunohistochemistry; Biology; Oncology; Cancer research; Computational biology; Medicine; Internal medicine; Bioinformatics; Immunology","score_opus":0.045149015511977614,"score_gpt":0.4098302940119935,"score_spread":0.36468127850001586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1943685717","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9829923,0.0030394811,0.0003866829,0.0012257764,0.00012075039,0.00023975929,0.000012780903,0.000018075645,0.011964387],"genre_scores_gemma":[0.99813527,0.000494976,0.00009877656,0.00007500385,0.000230312,0.000036589565,0.000017762994,0.00001773826,0.0008935698],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9983305,0.00017616057,0.00026061814,0.00030244474,0.0006080712,0.00032224087],"domain_scores_gemma":[0.9986303,0.00040440177,0.000068742804,0.00027917174,0.00035653246,0.0002608861],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016142643,0.00010711562,0.0005339596,0.0005582197,0.00009226141,0.000037529975,0.00013260351,0.000067085784,0.00048139945],"category_scores_gemma":[0.00065113563,0.000076228935,0.00008768326,0.00081537786,0.00037991718,0.00004841146,0.000067428446,0.0007385031,0.0000054799884],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008003976,0.00029818746,0.46783713,0.002314156,0.0043473323,0.00017705876,0.005577482,0.001545616,0.09721369,0.0060781674,0.012680899,0.4011299],"study_design_scores_gemma":[0.0014324988,0.0003681601,0.88762337,0.00024901755,0.0006567172,0.000012820232,0.0010182053,0.09465653,0.0020381794,0.00007596677,0.011692489,0.00017601982],"about_ca_topic_score_codex":0.005894459,"about_ca_topic_score_gemma":0.00007982559,"teacher_disagreement_score":0.41978627,"about_ca_system_score_codex":0.0001229793,"about_ca_system_score_gemma":0.00016913668,"threshold_uncertainty_score":0.89106977},"labels":[],"label_agreement":null},{"id":"W1964761239","doi":"10.1615/critrevbiomedeng.v36.i5-6.10","title":"Segmentation of Images of Abdominal Organs","year":2008,"lang":"en","type":"review","venue":"Critical Reviews in Biomedical Engineering","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St Joseph's Health Care; St. Joseph’s Healthcare Hamilton; McMaster University Medical Centre; McMaster University","funders":"","keywords":"Segmentation; Computer science; Tracing; Artificial intelligence; Pixel; Image segmentation; Computer vision; Boundary (topology); Process (computing); Magnetic resonance imaging; Radiology; Medicine; Mathematics","score_opus":0.029596751069111745,"score_gpt":0.3855143857264657,"score_spread":0.35591763465735393,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1964761239","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00000838525,0.9837837,0.014978995,0.00013894791,0.00030928734,0.000597932,0.000015887254,0.000024321396,0.00014249334],"genre_scores_gemma":[0.000044134733,0.9735806,0.02590665,0.000038270035,0.000217205,0.000057528272,0.000077446704,0.000057803947,0.000020362746],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99662906,0.00012350144,0.0020119562,0.00035452453,0.0005106941,0.00037024778],"domain_scores_gemma":[0.9980811,0.0009429172,0.00023471571,0.00034008117,0.00006610606,0.00033506536],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007554437,0.00037594535,0.0034794456,0.00054527516,0.00001538965,0.0000049709856,0.00023067149,0.00032269603,0.00014486609],"category_scores_gemma":[0.010276618,0.0002811999,0.0006066275,0.00081237196,0.00050158583,0.000051144554,0.00008224872,0.0010595168,0.000015782525],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004014967,0.00017042439,0.0000064865612,0.08932075,0.000042442774,0.00012432494,0.00002838709,0.0000010577096,0.00015511109,0.00018814238,0.0005912665,0.9093676],"study_design_scores_gemma":[0.00039984053,0.00013056767,0.000012155278,0.0885982,0.00047945595,0.00053376565,0.000005570343,0.0008359396,0.000030393949,0.000009716632,0.9087376,0.00022676493],"about_ca_topic_score_codex":0.000007854704,"about_ca_topic_score_gemma":6.3637934e-8,"teacher_disagreement_score":0.9091408,"about_ca_system_score_codex":0.000121116136,"about_ca_system_score_gemma":0.00023010826,"threshold_uncertainty_score":0.999964},"labels":[],"label_agreement":null},{"id":"W1967789417","doi":"10.1118/1.3244150","title":"Poster — Wed Eve—46: Quantitative Evaluation on the Accuracy of Image Registration Methods in SPECT Guided Radiation Therapy for Lung Cancer Patients","year":2009,"lang":"en","type":"article","venue":"Medical Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vancouver General Hospital; Simon Fraser University; University of British Columbia; BC Cancer Agency","funders":"","keywords":"Image registration; Nuclear medicine; Single-photon emission computed tomography; Artificial intelligence; Medical imaging; Radiation treatment planning; Computer science; Medicine; Computer vision; Radiation therapy; Radiology; Image (mathematics)","score_opus":0.05671471116661623,"score_gpt":0.4786747261087563,"score_spread":0.42196001494214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1967789417","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86836934,0.00039572755,0.0876399,0.038922936,0.00034585895,0.0023851003,0.000007646221,0.000028101447,0.0019054057],"genre_scores_gemma":[0.9918908,0.0001880532,0.0028483688,0.00454152,0.00029410174,0.0000852898,0.00011133675,0.000016425312,0.000024109284],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99804246,0.00033290376,0.0004194089,0.00021560775,0.00081961154,0.00017001758],"domain_scores_gemma":[0.99809736,0.0010888783,0.00028198148,0.00019406113,0.00025961266,0.000078108984],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023205602,0.00012414965,0.00027182023,0.000053709853,0.00005493679,0.000014827121,0.00011318782,0.00006314514,0.000095502444],"category_scores_gemma":[0.0078109624,0.00008186462,0.00009434115,0.0002291972,0.000104261315,0.000104407656,0.000007859252,0.00032588834,9.302508e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00069865276,0.0009174878,0.013657823,0.00008376368,0.00010015659,0.0000024622555,0.001965443,0.00013022177,0.011022772,0.0032610716,0.012042793,0.95611733],"study_design_scores_gemma":[0.012776877,0.0015275258,0.38384792,0.0008077001,0.00020532672,0.0000019197344,0.00006572596,0.55306864,0.030716207,0.015998192,0.0006882975,0.00029563523],"about_ca_topic_score_codex":0.00005008372,"about_ca_topic_score_gemma":0.0000015573122,"teacher_disagreement_score":0.9558217,"about_ca_system_score_codex":0.00014400849,"about_ca_system_score_gemma":0.00025605634,"threshold_uncertainty_score":0.93510157},"labels":[],"label_agreement":null},{"id":"W1971115048","doi":"10.1118/1.3613013","title":"MO‐F‐BRC‐06: Relative Gamma Analysis Approach Using an EPID Portal Dose‐Based to Set CBCT Imaging Decision Threshold for Lung Patients","year":2011,"lang":"en","type":"article","venue":"Medical Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hôtel-Dieu de Québec; Centre hospitalier universitaire de Québec","funders":"","keywords":"Medicine; Nuclear medicine; Radiation treatment planning; Radiology; Radiation therapy","score_opus":0.04459113606639825,"score_gpt":0.3407404357886099,"score_spread":0.29614929972221166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1971115048","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34625918,0.00003084263,0.6519591,0.00017014932,0.00013860656,0.0004883071,0.000017691062,0.000067349334,0.00086874614],"genre_scores_gemma":[0.94588584,0.0000027600472,0.050417643,0.002489673,0.0005287604,0.000038027232,0.00053670624,0.00007191963,0.000028652968],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966274,0.00009501172,0.0006285005,0.000748388,0.0012929101,0.00060777983],"domain_scores_gemma":[0.9976824,0.00027699507,0.00021324003,0.00050377083,0.00025460625,0.0010690193],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012117487,0.00033280507,0.0007685477,0.00027057924,0.00022238259,0.000035957106,0.00032164875,0.00015115127,0.00011722799],"category_scores_gemma":[0.0013488602,0.00027526155,0.00040197017,0.000902786,0.00024743564,0.00025894307,0.000111403846,0.00071401394,0.00000763996],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007383558,0.003040908,0.84358734,0.00024149347,0.0011606881,0.00014840224,0.0031961866,0.0038824829,0.0002021446,0.0009009846,0.0032180236,0.13968296],"study_design_scores_gemma":[0.0030015595,0.00020876389,0.024803631,0.00020338062,0.0014144268,0.000007395457,0.00009375611,0.96807146,0.00030920937,0.0013626576,0.00016795246,0.00035580347],"about_ca_topic_score_codex":0.000096505544,"about_ca_topic_score_gemma":0.0000023101275,"teacher_disagreement_score":0.964189,"about_ca_system_score_codex":0.0001437322,"about_ca_system_score_gemma":0.0001957381,"threshold_uncertainty_score":0.99996996},"labels":[],"label_agreement":null},{"id":"W1971351131","doi":"10.1016/j.acra.2014.08.011","title":"Clinical Utility of Quantitative Imaging","year":2014,"lang":"en","type":"review","venue":"Academic Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":104,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Institute of Biomedical Imaging and Bioengineering; Agency for Healthcare Research and Quality; National Institutes of Health; National Cancer Institute; National Heart, Lung, and Blood Institute; Radiological Society of North America","keywords":"Medicine; Clinical Practice; Medical physics; Patient care; Radiology; Family medicine; Nursing","score_opus":0.09076224334840943,"score_gpt":0.4883891103606797,"score_spread":0.3976268670122703,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1971351131","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00008341608,0.9918248,0.0022489864,0.0005595534,0.0009860432,0.00052265363,0.000010349672,0.000064679174,0.0036995348],"genre_scores_gemma":[0.00015441602,0.99429566,0.0035828764,0.00070904795,0.0008412176,0.000022647264,0.00011649724,0.00006807269,0.00020953991],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9950023,0.0013246698,0.0022806886,0.00071378425,0.0002223458,0.00045620208],"domain_scores_gemma":[0.99475646,0.0030986643,0.00119014,0.00058990356,0.00008425781,0.00028054987],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.004132876,0.000406141,0.0049621584,0.0006583405,0.00004305194,0.0000029465734,0.0004609296,0.0010252887,0.00012354391],"category_scores_gemma":[0.006305585,0.00029785794,0.0009998726,0.00050707615,0.0011367438,0.000033089917,0.00013762724,0.005034603,0.00008048093],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021220532,0.00002624966,0.0035000346,0.0071561993,0.0002855147,0.00003122197,0.00003170962,1.4385553e-7,0.0000011136394,0.0015504044,0.018142015,0.9692542],"study_design_scores_gemma":[0.0004987934,0.00013743404,0.0004106387,0.007051426,0.001422124,0.0011963361,0.000010664128,0.0014482437,1.711064e-7,0.0002949512,0.9873157,0.00021347872],"about_ca_topic_score_codex":0.000025613153,"about_ca_topic_score_gemma":1.6217544e-7,"teacher_disagreement_score":0.9691737,"about_ca_system_score_codex":0.000036408906,"about_ca_system_score_gemma":0.00040520914,"threshold_uncertainty_score":0.99994737},"labels":[],"label_agreement":null},{"id":"W1971753344","doi":"10.1109/isbi.2013.6556434","title":"FEM-based automatic segmentation of muscle and fat tissues from thoracic CT images","year":2013,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Jaccard index; Segmentation; Image segmentation; Computer science; Skeletal muscle; Finite element method; Soft tissue; Medicine; Pattern recognition (psychology); Artificial intelligence; Anatomy; Radiology; Physics","score_opus":0.010768902949857686,"score_gpt":0.3115062485770703,"score_spread":0.30073734562721266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1971753344","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9893397,0.00026993034,0.005633244,0.0029667565,0.00004623856,0.000223828,0.000001963432,0.00007104447,0.0014472675],"genre_scores_gemma":[0.9502295,0.0000242491,0.04864601,0.0006009077,0.000044859513,0.000010571653,0.000029963892,0.000011707754,0.00040217504],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99940723,0.00003500067,0.00017359186,0.00012898624,0.00015664863,0.00009854714],"domain_scores_gemma":[0.9995703,0.00012355398,0.000059999053,0.00012288839,0.000035111807,0.000088137705],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00009584466,0.0000764848,0.00018285957,0.00005696764,0.00002841537,0.000025121373,0.000035030756,0.000017350974,0.001310481],"category_scores_gemma":[0.00011842074,0.000055867356,0.000027177102,0.000056844776,0.000076640696,0.00008075696,0.000015215864,0.000094349954,0.00003336673],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000067072797,0.000088862704,0.063664384,0.00023229214,0.00004224977,0.000014327644,0.00029025535,0.000017471222,0.21091385,0.000018025328,0.004180159,0.7205314],"study_design_scores_gemma":[0.0018509352,0.00020667897,0.5224814,0.00041230983,0.0001774555,0.000012889654,0.0008129972,0.3105518,0.16192542,0.00078583945,0.000585717,0.00019659936],"about_ca_topic_score_codex":0.0013294866,"about_ca_topic_score_gemma":0.0000022631975,"teacher_disagreement_score":0.7203348,"about_ca_system_score_codex":0.000012034194,"about_ca_system_score_gemma":0.000014383733,"threshold_uncertainty_score":0.99960244},"labels":[],"label_agreement":null},{"id":"W1975575773","doi":"10.1118/1.3182621","title":"TH‐C‐BRC‐07: An Investigation of the Effect of Micro‐CT Radiation Dose On Tumor Growth in Mice","year":2009,"lang":"en","type":"article","venue":"Medical Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Nuclear medicine; Medicine; Medical imaging; Dosimetry; Melanoma; Radiology","score_opus":0.005721739318917232,"score_gpt":0.26926341519984714,"score_spread":0.2635416758809299,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1975575773","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9953201,0.00005565041,0.00021728768,0.003531906,0.00014397758,0.00026527586,0.0000015347679,0.00001726597,0.00044700195],"genre_scores_gemma":[0.99735457,0.000014627956,0.000095384385,0.0022129072,0.0002723366,0.0000037955695,0.000021153432,0.000012197377,0.000013014754],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99847585,0.00022115072,0.00032686125,0.00017995383,0.00063573365,0.00016047349],"domain_scores_gemma":[0.99917084,0.00026009043,0.0001688906,0.0002005086,0.000034491455,0.00016516878],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007970834,0.00012044058,0.0003380524,0.000053563846,0.000028208888,0.0000045428346,0.00017490587,0.000046753397,0.00001626864],"category_scores_gemma":[0.0012337628,0.00007790643,0.00008919443,0.0003078868,0.000254904,0.000058631987,0.000018803279,0.0005493963,0.0000042551264],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000625982,0.0008137171,0.51033574,0.00080768374,0.00007241466,0.000093491704,0.0018647226,0.00023232376,0.15522125,0.0026527112,0.0021592218,0.32512075],"study_design_scores_gemma":[0.0052138986,0.002026305,0.45970637,0.0012132887,0.00011350429,0.000032452182,0.00001919251,0.013262469,0.51211154,0.006059283,0.000069448004,0.00017225722],"about_ca_topic_score_codex":0.00011882447,"about_ca_topic_score_gemma":0.000001019119,"teacher_disagreement_score":0.35689026,"about_ca_system_score_codex":0.000048735114,"about_ca_system_score_gemma":0.0001393599,"threshold_uncertainty_score":0.3176932},"labels":[],"label_agreement":null},{"id":"W1975910278","doi":"10.1118/1.3613251","title":"TU‐G‐211‐01: Uptake Volume Histograms: A Novel Avenue towards Delineation of Biological Target Volumes (BTV) in Radiotherapy","year":2011,"lang":"en","type":"article","venue":"Medical Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Montreal General Hospital","funders":"","keywords":"Nuclear medicine; Histogram; Radiation therapy; Population; Volume (thermodynamics); Lung volumes; Medicine; Radiation treatment planning; Lung; Radiology; Physics; Internal medicine; Computer science","score_opus":0.03635163575438266,"score_gpt":0.2944357636304203,"score_spread":0.25808412787603763,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1975910278","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49784997,0.0009872712,0.49636713,0.0024099287,0.0005959721,0.00037247926,0.000013682584,0.000102410275,0.0013011702],"genre_scores_gemma":[0.9744443,0.0003094367,0.022110688,0.0018819614,0.0008635422,0.00002473009,0.00009189866,0.00004157536,0.00023181897],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978845,0.00007170327,0.0006231214,0.00035564677,0.0006846998,0.00038029355],"domain_scores_gemma":[0.99903715,0.00006458801,0.00017245865,0.00029810466,0.00009404565,0.00033366575],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008263882,0.0002119774,0.0006401154,0.00009305488,0.000041147567,0.000007341625,0.00025287687,0.0002493649,0.0006869593],"category_scores_gemma":[0.0012174523,0.00017259156,0.00018709555,0.00034214504,0.0005907467,0.00006462772,0.0000533926,0.00075001817,0.000014601072],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041265498,0.0023202277,0.1839369,0.00019270355,0.000154751,0.00014261287,0.0028002872,0.00003595776,0.004427657,0.0009826274,0.004508283,0.80008537],"study_design_scores_gemma":[0.018542362,0.0029003285,0.3442952,0.0015441705,0.00024034888,0.00024383469,0.00033110185,0.39687127,0.005394643,0.007031239,0.2212979,0.0013076169],"about_ca_topic_score_codex":0.0004690128,"about_ca_topic_score_gemma":0.000004877053,"teacher_disagreement_score":0.7987777,"about_ca_system_score_codex":0.0001134868,"about_ca_system_score_gemma":0.00027190143,"threshold_uncertainty_score":0.7521723},"labels":[],"label_agreement":null},{"id":"W1976118866","doi":"10.1118/1.4887919","title":"SU‐D‐9A‐03: STAMP: Simulator for Texture Analysis in MRI/PET","year":2014,"lang":"en","type":"article","venue":"Medical Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Imaging phantom; Monte Carlo method; Scanner; Artificial intelligence; Computer vision; MATLAB; Computer graphics (images); Simulation; Nuclear medicine; Mathematics","score_opus":0.007762166802469499,"score_gpt":0.3052439929228208,"score_spread":0.2974818261203513,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1976118866","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19392611,0.00012661962,0.7879245,0.014791038,0.00035950428,0.00045772013,0.000011982464,0.00012700126,0.0022754981],"genre_scores_gemma":[0.9915434,0.000022811677,0.0011847656,0.0054840366,0.0012072542,0.000023863238,0.00014760165,0.00003799151,0.00034827244],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979165,0.00007232663,0.00039051575,0.00039694266,0.0007842132,0.00043949275],"domain_scores_gemma":[0.9983391,0.00060144655,0.00009062348,0.0003831372,0.000079789614,0.0005058683],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010178341,0.00019350142,0.0006919644,0.00014088441,0.000074142496,0.000027081443,0.00020569764,0.00012852103,0.00025097188],"category_scores_gemma":[0.0023543,0.00015558345,0.0003032067,0.0007011986,0.00024041209,0.0000516794,0.000056878645,0.00075524667,0.000032264703],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00048344373,0.0020682316,0.3316329,0.0010051333,0.0019323144,0.0003408749,0.0012766962,0.0100391675,0.0004992897,0.017263902,0.036754668,0.59670335],"study_design_scores_gemma":[0.0033617537,0.00017917658,0.00989285,0.00014806114,0.0006091875,0.000010471889,0.000029864039,0.92725545,0.00010461367,0.005052378,0.05310404,0.00025217258],"about_ca_topic_score_codex":0.00005325056,"about_ca_topic_score_gemma":0.000013943333,"teacher_disagreement_score":0.91721624,"about_ca_system_score_codex":0.00006396584,"about_ca_system_score_gemma":0.00013201004,"threshold_uncertainty_score":0.63445085},"labels":[],"label_agreement":null},{"id":"W1976244785","doi":"10.1118/1.4889195","title":"MO‐G‐BRF‐02: Enhancement of Texture‐Based Metastasis Prediction Models Via the Optimization of PET/MRI Acquisition Protocols","year":2014,"lang":"en","type":"article","venue":"Medical Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Nuclear medicine; Radiomics; Computer science; Monte Carlo method; Iterative reconstruction; Medical imaging; Artificial intelligence; Medicine; Mathematics; Statistics","score_opus":0.015018033762220252,"score_gpt":0.2979587281232335,"score_spread":0.2829406943610132,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1976244785","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0038319468,0.000023145945,0.9901151,0.0024550564,0.00008669128,0.0026896277,0.000007680323,0.000037149573,0.0007535828],"genre_scores_gemma":[0.98662037,0.000020142561,0.010959686,0.0011068645,0.0003996947,0.0007202343,0.000115877236,0.000027234635,0.000029926672],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976638,0.00015808639,0.00052771415,0.00023578819,0.0012141053,0.00020050688],"domain_scores_gemma":[0.9988,0.0001783695,0.00030218053,0.00033745932,0.00021283345,0.0001691492],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010927519,0.00015355779,0.00041109754,0.00005085805,0.00007307308,0.000009190381,0.00018110915,0.00007279592,0.00019170494],"category_scores_gemma":[0.00028976056,0.00010307136,0.00014642182,0.00025095636,0.00034155446,0.00009095953,0.00004441358,0.00037171438,0.0000028999164],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00062502036,0.0030926017,0.0020735906,0.0021597152,0.00049237406,0.000012385926,0.0008353689,0.62821805,0.01447618,0.005170223,0.0044377856,0.3384067],"study_design_scores_gemma":[0.0016132798,0.00042655642,0.00016639697,0.0004726882,0.00016483436,0.000007830147,0.000011733001,0.97580206,0.018154979,0.0027692458,0.00033132857,0.00007905176],"about_ca_topic_score_codex":0.000019197165,"about_ca_topic_score_gemma":2.086715e-7,"teacher_disagreement_score":0.9827884,"about_ca_system_score_codex":0.000043600117,"about_ca_system_score_gemma":0.00012108916,"threshold_uncertainty_score":0.42031282},"labels":[],"label_agreement":null},{"id":"W1978007126","doi":"10.1118/1.1997469","title":"SU‐EE‐A4‐05: Individual Target Volume Definition in NSCLC Using PET","year":2005,"lang":"en","type":"article","venue":"Medical Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Nuclear medicine; Imaging phantom; Lung cancer; Medicine; PET-CT; Population; Positron emission tomography; Pathology","score_opus":0.025506718849519775,"score_gpt":0.30003179021564974,"score_spread":0.27452507136612997,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1978007126","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91793495,0.0003335551,0.058146905,0.015724644,0.00054809434,0.00030620003,0.000014119139,0.00016155952,0.006829983],"genre_scores_gemma":[0.97932255,0.000040326293,0.0117262,0.0064705787,0.0020930278,0.000009063963,0.00015861503,0.000046356414,0.00013328067],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975401,0.000084290485,0.0004265001,0.0003343298,0.0011244997,0.0004902516],"domain_scores_gemma":[0.99905634,0.000115643685,0.00009431522,0.0002336846,0.00005093312,0.0004491027],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00080198597,0.00019847418,0.00042342037,0.00010093216,0.00008893331,0.00003472904,0.00018828444,0.0001253642,0.0006816418],"category_scores_gemma":[0.00093323644,0.00018355447,0.00011552657,0.0003291753,0.0003057014,0.00014462764,0.000099178236,0.0011988193,0.00012859212],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026761912,0.0032789106,0.22391962,0.00048197448,0.00030703566,0.0027585437,0.002797492,0.0014986052,0.0017925171,0.0071298596,0.045202915,0.7105649],"study_design_scores_gemma":[0.01614301,0.00060502556,0.05991952,0.0023026988,0.00047429485,0.0016376246,0.00030649445,0.79531044,0.0013919083,0.01945749,0.10097314,0.0014783625],"about_ca_topic_score_codex":0.00008979784,"about_ca_topic_score_gemma":0.0000051187562,"teacher_disagreement_score":0.7938118,"about_ca_system_score_codex":0.00014061818,"about_ca_system_score_gemma":0.0002973561,"threshold_uncertainty_score":0.7485134},"labels":[],"label_agreement":null},{"id":"W1980078214","doi":"10.1118/1.4815538","title":"WE‐C‐WAB‐02: Joint FDG‐PET/MR Imaging for the Early Prediction of Tumor Outcomes","year":2013,"lang":"en","type":"article","venue":"Medical Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre; McGill University","funders":"","keywords":"Nuclear medicine; Medicine; Receiver operating characteristic; PET-CT; Positron emission tomography; Radiology; Internal medicine","score_opus":0.014705625794347544,"score_gpt":0.2767912293209407,"score_spread":0.26208560352659316,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1980078214","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5862797,0.00079173857,0.29446414,0.11183017,0.0020348176,0.002111219,0.000033185286,0.0002769842,0.002178064],"genre_scores_gemma":[0.993428,0.000068025816,0.0011593692,0.0036387027,0.0010123927,0.000124034,0.000021532927,0.000046597437,0.00050135556],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979038,0.000041576364,0.0005053075,0.00026884125,0.0009049049,0.00037554605],"domain_scores_gemma":[0.99840003,0.00055244647,0.00017658978,0.00038798578,0.00016104527,0.0003219278],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00062071794,0.00019026992,0.00047611294,0.000046015244,0.00013510058,0.000032674237,0.00023032821,0.00004233056,0.00029810745],"category_scores_gemma":[0.0016315497,0.00011566978,0.0002695722,0.00015517652,0.0004916036,0.00012428356,0.0000859961,0.0006394442,0.00004281664],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000096167045,0.0009640132,0.24918278,0.00091946573,0.00065908773,0.00009366295,0.0019006025,0.000060503262,0.007734667,0.0039031662,0.08931999,0.6451659],"study_design_scores_gemma":[0.010947097,0.0007828686,0.4084628,0.0016639988,0.0010268894,0.00032390378,0.0008158104,0.5104136,0.00732202,0.028234793,0.029334432,0.0006718198],"about_ca_topic_score_codex":0.00023547353,"about_ca_topic_score_gemma":6.445717e-7,"teacher_disagreement_score":0.64449406,"about_ca_system_score_codex":0.000043930813,"about_ca_system_score_gemma":0.00014551826,"threshold_uncertainty_score":0.4716877},"labels":[],"label_agreement":null},{"id":"W1981012799","doi":"10.1118/1.1997646","title":"SU‐FF‐J‐100: Mutual Information as a Metric of Multimodality Contrast Agent Efficacy","year":2005,"lang":"en","type":"article","venue":"Medical Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Metric (unit); Contrast (vision); Mutual information; Image registration; Voxel; Feature (linguistics); Magnetic resonance imaging; Artificial intelligence; Medical imaging; Computer science; Nuclear medicine; Pattern recognition (psychology); Computer vision; Radiology; Medicine; Mathematics; Image (mathematics)","score_opus":0.012810302695358938,"score_gpt":0.3126290314428876,"score_spread":0.2998187287475287,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1981012799","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8774698,0.00020627734,0.100997426,0.010298785,0.0003874397,0.00050691696,0.000010415491,0.00014399362,0.009978983],"genre_scores_gemma":[0.99402535,0.000058996695,0.0011449168,0.003763476,0.0007914371,0.000007878919,0.00008673076,0.000015989244,0.00010522251],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976215,0.00006158605,0.0005759357,0.00017226904,0.0012602787,0.0003084267],"domain_scores_gemma":[0.99858207,0.00031210866,0.00018490483,0.00027449022,0.000141834,0.0005046128],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007332674,0.00016245065,0.00045639055,0.00010729932,0.000060587423,0.000019458734,0.00017932593,0.00013299704,0.00045650513],"category_scores_gemma":[0.0037768118,0.00013258959,0.00016865853,0.0004210104,0.00033290696,0.00019719452,0.0000721888,0.00067794806,0.0002514021],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014535237,0.0008850215,0.004721304,0.0001690645,0.00013083006,0.000022464268,0.0010157053,0.00017906401,0.00029142507,0.0018362614,0.004569241,0.9860343],"study_design_scores_gemma":[0.039041385,0.0018092045,0.12865293,0.0013381015,0.0009877752,0.0003241251,0.00040654416,0.48906955,0.021870656,0.002185113,0.31300402,0.0013105856],"about_ca_topic_score_codex":0.0001438654,"about_ca_topic_score_gemma":0.0000010029538,"teacher_disagreement_score":0.9847237,"about_ca_system_score_codex":0.00009285532,"about_ca_system_score_gemma":0.00026352835,"threshold_uncertainty_score":0.54068464},"labels":[],"label_agreement":null},{"id":"W1981238122","doi":"10.1007/bf02524204","title":"Predictive value of 3D computed tomography in assessing hepatic volumes prior to resection","year":2004,"lang":"en","type":"article","venue":"Annals of Surgical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto General Hospital","funders":"","keywords":"Medicine; Surgical oncology; Computed tomography; Predictive value; Radiology; Resection; Predictive value of tests; Value (mathematics); Internal medicine; Surgery; Statistics","score_opus":0.02862150101191741,"score_gpt":0.3769081281313411,"score_spread":0.3482866271194237,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1981238122","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.976773,0.0002563203,0.003694328,0.014817544,0.00017486565,0.0002798636,0.0000021170297,0.000025371568,0.00397654],"genre_scores_gemma":[0.98951924,0.00024457515,0.009403161,0.000683333,0.0001047678,0.000009242172,0.000008133217,0.000012168646,0.000015368234],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9985551,0.00017264088,0.00052707165,0.00022419827,0.00026866028,0.0002523057],"domain_scores_gemma":[0.99895984,0.00035796515,0.00017449017,0.00013946572,0.00019475301,0.00017350969],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008521228,0.00010483192,0.00061535346,0.0004043897,0.00003033596,0.0000053386966,0.00008818804,0.0001423919,0.000023571274],"category_scores_gemma":[0.000258558,0.00009056429,0.000115663126,0.0006183784,0.00020215513,0.00006902177,0.000053917534,0.00038137083,0.0000022767595],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0050116377,0.0054003717,0.2921963,0.0009179546,0.0005591382,0.0017812934,0.0037263525,0.031997636,0.012088377,0.0050707106,0.0017776818,0.63947254],"study_design_scores_gemma":[0.013857231,0.014017081,0.8433001,0.0030691365,0.0001874441,0.0004679129,0.00049488177,0.056154888,0.011186961,0.004756529,0.052069273,0.0004385496],"about_ca_topic_score_codex":0.00043816486,"about_ca_topic_score_gemma":0.000015774476,"teacher_disagreement_score":0.639034,"about_ca_system_score_codex":0.00005956624,"about_ca_system_score_gemma":0.00021690906,"threshold_uncertainty_score":0.36931047},"labels":[],"label_agreement":null},{"id":"W1981681061","doi":"10.1158/1538-7445.chtme14-a12","title":"Abstract A12: Heterogeneous accumulation of trastuzumab in Her2+ve tumor and metastases models","year":2015,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Studies","funders":"","keywords":"Trastuzumab; Immunohistochemistry; Medicine; Pathology; Breast cancer; Tissue microarray; CD31; Context (archaeology); Cancer; Cancer research; Biology; Internal medicine","score_opus":0.23531661260084896,"score_gpt":0.48797679525375476,"score_spread":0.2526601826529058,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1981681061","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9955202,0.0025310847,0.00018393119,0.0007993588,0.00004379932,0.00024998176,0.000007632661,0.000011249272,0.0006527813],"genre_scores_gemma":[0.99911076,0.00020130929,0.00040539136,0.00008002211,0.000080992126,0.00002960085,0.000008612233,0.000017484821,0.0000658584],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99871576,0.00008945827,0.0002134701,0.00020103986,0.0005204154,0.00025988158],"domain_scores_gemma":[0.9993103,0.000106433385,0.000039204562,0.0001504981,0.00017437973,0.00021916509],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00124114,0.00007409573,0.00023139681,0.00022180355,0.000029536428,0.00001817249,0.00007513389,0.000033436358,0.000053611064],"category_scores_gemma":[0.00038997538,0.00006159407,0.000027418031,0.00022026307,0.00015750663,0.00008947972,0.000047884318,0.00043095436,0.000002606778],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004295713,0.0015175169,0.11587982,0.002631664,0.00048119426,0.001998995,0.013765339,0.1883441,0.1429159,0.001466405,0.009047121,0.5176562],"study_design_scores_gemma":[0.021091593,0.0022533054,0.11969852,0.0029429784,0.00017321804,0.0005518268,0.0038722425,0.7653349,0.05671852,0.016129205,0.010337417,0.00089627784],"about_ca_topic_score_codex":0.0018634776,"about_ca_topic_score_gemma":0.00007709022,"teacher_disagreement_score":0.5769908,"about_ca_system_score_codex":0.00015916734,"about_ca_system_score_gemma":0.00031502935,"threshold_uncertainty_score":0.28170332},"labels":[],"label_agreement":null},{"id":"W1981737356","doi":"10.1016/j.ijrobp.2007.07.124","title":"Comparison of Liver Metastases Volumes on CT, MR and FDG PET Imaging to Pathological Resection Using Deformable Image Registration","year":2007,"lang":"en","type":"article","venue":"International Journal of Radiation Oncology*Biology*Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto General Hospital; Princess Margaret Cancer Centre; University of Toronto","funders":"","keywords":"Medicine; Ex vivo; Nuclear medicine; In vivo; Radiology; Pathological; Image registration; Tomography; Resection; Pathology; Surgery","score_opus":0.03166451045131225,"score_gpt":0.3942360174002908,"score_spread":0.36257150694897855,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1981737356","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8635014,0.00026922085,0.13348155,0.001489183,0.000693816,0.00014066172,0.00001137821,0.000017377806,0.00039541224],"genre_scores_gemma":[0.9673772,0.00013705583,0.0307591,0.00074492,0.0009089535,0.0000014266261,0.000037403708,0.000015652124,0.000018283408],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998329,0.00016594841,0.0007841258,0.00019465559,0.00032392758,0.00020233581],"domain_scores_gemma":[0.9978975,0.00038398794,0.00092139153,0.000101072284,0.0005436012,0.00015241423],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015932391,0.00014408823,0.00044861544,0.00027159922,0.00008765703,0.00002958121,0.00015167113,0.00005656894,0.000022462824],"category_scores_gemma":[0.0010870098,0.00012252903,0.00012337968,0.0001482264,0.00024685464,0.00025029818,0.000048482118,0.0005392739,0.000003958866],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013674132,0.0006376868,0.62306607,0.00003094136,0.000259858,0.00040337472,0.000582983,0.0030910594,0.09865371,0.004610024,0.0012550171,0.26604187],"study_design_scores_gemma":[0.014119474,0.008277996,0.36153948,0.0007330192,0.0008135025,0.009903244,0.001529007,0.49644902,0.068560794,0.007297133,0.030018698,0.0007586112],"about_ca_topic_score_codex":0.00005645126,"about_ca_topic_score_gemma":0.0000056204103,"teacher_disagreement_score":0.493358,"about_ca_system_score_codex":0.00037322097,"about_ca_system_score_gemma":0.00015804706,"threshold_uncertainty_score":0.4996589},"labels":[],"label_agreement":null},{"id":"W1984468499","doi":"10.1016/j.jalz.2010.08.182","title":"P4‐123: Robust Identification of Amnestic MCI Progressors to Probable AD via Baseline MRI Analysis","year":2010,"lang":"en","type":"article","venue":"Alzheimer s & Dementia","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Linear discriminant analysis; Artificial intelligence; Neuroimaging; Robustness (evolution); Missing data; Computer science; Nuclear medicine; Medicine; Pattern recognition (psychology); Statistics; Psychology; Mathematics; Machine learning; Neuroscience","score_opus":0.01474166039737565,"score_gpt":0.294851490054634,"score_spread":0.2801098296572584,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1984468499","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6129905,0.014779293,0.35399628,0.01345123,0.0014295105,0.0022845685,0.000021435506,0.00030021265,0.00074696174],"genre_scores_gemma":[0.9541647,0.00002451293,0.04498829,0.0003962921,0.00012921607,0.00006171846,0.00014702318,0.000033690812,0.000054557688],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980183,0.000064346255,0.0006635514,0.00044516803,0.0004731085,0.00033549155],"domain_scores_gemma":[0.9984958,0.00006296935,0.00026866427,0.000621253,0.00026109387,0.0002901768],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011272463,0.00019072527,0.00042242257,0.00038291246,0.0001011353,0.00004184159,0.0002286767,0.00008885519,0.00042322307],"category_scores_gemma":[0.00033874542,0.00016931807,0.00018162042,0.0009858517,0.00011704223,0.00010194425,0.000074808086,0.00037971063,0.00010225736],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024822805,0.001646532,0.24301584,0.0001582703,0.069131516,0.00007793352,0.0009967348,0.013255716,0.37625661,0.00040605303,0.008343901,0.28646266],"study_design_scores_gemma":[0.0023489771,0.00041604642,0.20469752,0.00013325184,0.19569284,0.00007140449,0.00008378415,0.4805695,0.083215825,0.00027366844,0.031660117,0.0008370739],"about_ca_topic_score_codex":0.000147364,"about_ca_topic_score_gemma":0.0000955923,"teacher_disagreement_score":0.4673138,"about_ca_system_score_codex":0.0000055485098,"about_ca_system_score_gemma":0.00006325777,"threshold_uncertainty_score":0.690459},"labels":[],"label_agreement":null},{"id":"W1984533063","doi":"10.1117/12.2043496","title":"A tool for intraoperative visualization of registration results","year":2014,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Cancer Care Ontario","keywords":"Visualization; Computer science; Glyph (data visualization); Computer vision; Grid; Software; Artificial intelligence; Computer graphics (images); Geometric transformation; Image registration; Image (mathematics)","score_opus":0.010065821799578028,"score_gpt":0.2686880868515269,"score_spread":0.25862226505194885,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1984533063","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9897923,0.000029352848,0.0018556309,0.0050782654,0.00016284572,0.0007515515,0.000030386978,0.00004938924,0.0022502656],"genre_scores_gemma":[0.8405678,0.000050774073,0.15794209,0.0002529708,0.00063250144,0.00012542706,0.000047194037,0.000054999593,0.00032619628],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99803525,2.5705118e-8,0.0008413819,0.00031314974,0.00056388235,0.00024631422],"domain_scores_gemma":[0.99696195,0.00025801687,0.00052839087,0.000056653233,0.0021028544,0.00009212184],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012643547,0.00021070943,0.00044464832,0.00009566923,0.00006448728,0.000049111368,0.00032989134,0.0001527266,0.000004236012],"category_scores_gemma":[0.0046599302,0.00016836895,0.00044281635,0.00022903715,0.00021702124,0.00021009747,0.00005224463,0.0002280376,3.3237163e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039199044,0.00012216208,0.00042975758,0.0008038485,0.00025612055,2.6663253e-8,0.00030691692,0.00015656275,0.49171728,0.50110453,0.003680182,0.0010306021],"study_design_scores_gemma":[0.0071911365,0.0022690613,0.0032385485,0.0014704706,0.0005722112,0.000035758625,0.0010144187,0.6205152,0.3453105,0.003405716,0.01447913,0.0004978082],"about_ca_topic_score_codex":0.00000828701,"about_ca_topic_score_gemma":7.840029e-8,"teacher_disagreement_score":0.6203587,"about_ca_system_score_codex":0.00009202532,"about_ca_system_score_gemma":0.00004672662,"threshold_uncertainty_score":0.68658864},"labels":[],"label_agreement":null},{"id":"W1987054640","doi":"10.1016/j.radonc.2015.02.015","title":"CT-based radiomic signature predicts distant metastasis in lung adenocarcinoma","year":2015,"lang":"en","type":"article","venue":"Radiotherapy and Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":706,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto; University Health Network","funders":"National Cancer Institute; National Institutes of Health; KWF Kankerbestrijding; Stichting voor de Technische Wetenschappen; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Health Foundation Limburg","keywords":"Radiomics; Concordance; Medicine; Univariate; Imaging biomarker; Multivariate analysis; Adenocarcinoma; Multivariate statistics; Biomarker; Concordance correlation coefficient; Oncology; Radiology; Internal medicine; Magnetic resonance imaging; Cancer; Computer science; Statistics; Machine learning; Mathematics","score_opus":0.017070015965515103,"score_gpt":0.31634605360784457,"score_spread":0.29927603764232946,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1987054640","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.932064,0.04163034,0.0074555455,0.016150292,0.0006214603,0.0005844265,0.00000787711,0.00010076607,0.0013853103],"genre_scores_gemma":[0.9852641,0.0006321819,0.008368181,0.005135798,0.00031717398,0.000027636515,0.000029626084,0.000039861225,0.00018542376],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985113,0.00021896808,0.00031452376,0.00036850275,0.00021968895,0.00036698728],"domain_scores_gemma":[0.99904543,0.0001969937,0.00009108772,0.00022447467,0.000036312696,0.00040572666],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008058053,0.00019886227,0.000604814,0.00024071592,0.00004975296,0.000019818453,0.00010890449,0.00013568117,0.00008039721],"category_scores_gemma":[0.00017894617,0.0001601143,0.00007661416,0.00023784651,0.00022002019,0.00006005233,0.000016966154,0.0006495564,0.0000021323654],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0042143473,0.0012331269,0.6805259,0.00045067436,0.0005853885,0.0065203086,0.004240428,0.0015194572,0.012091085,0.0019746993,0.04048109,0.24616349],"study_design_scores_gemma":[0.039988436,0.0037546915,0.09967846,0.00029547818,0.00037761466,0.0025439532,0.0005250508,0.38358262,0.00085750635,0.0005681909,0.46713462,0.00069336436],"about_ca_topic_score_codex":0.000106690626,"about_ca_topic_score_gemma":0.000025805773,"teacher_disagreement_score":0.58084744,"about_ca_system_score_codex":0.0007088712,"about_ca_system_score_gemma":0.00046593114,"threshold_uncertainty_score":0.65292716},"labels":[],"label_agreement":null},{"id":"W1987601442","doi":"10.1118/1.3181122","title":"SU‐FF‐I‐03: Computer‐Aided Diagnostic Scheme for Detection of Hepatocellular Carcinoma in Contrast‐Enhanced Hepatic CT: Preliminary Results","year":2009,"lang":"en","type":"article","venue":"Medical Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"False positive paradox; Hepatocellular carcinoma; Receiver operating characteristic; Segmentation; CAD; Artificial intelligence; Nuclear medicine; Pattern recognition (psychology); Computer-aided diagnosis; Feature (linguistics); Detector; Radiology; Medicine; Computer science; Internal medicine","score_opus":0.010908529497353693,"score_gpt":0.2660638763857717,"score_spread":0.255155346888418,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1987601442","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8109395,0.0002148215,0.18595722,0.0017984544,0.00025237765,0.00066782924,0.00000620604,0.00005231332,0.00011131401],"genre_scores_gemma":[0.9964529,0.00005185665,0.0016262081,0.0009939091,0.0006988669,0.000039245893,0.00008691642,0.000028208626,0.000021845604],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99775213,0.00007855183,0.0007120759,0.00039882245,0.0006491823,0.00040922512],"domain_scores_gemma":[0.9979363,0.0011005957,0.00020201883,0.00031404634,0.00011657717,0.00033044117],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00068443536,0.00021663708,0.0006561536,0.00008972696,0.000059920814,0.000012035555,0.00017242829,0.000110168236,0.000009807118],"category_scores_gemma":[0.0041965204,0.00019687091,0.00016480417,0.00028858052,0.00021416061,0.00006832848,0.000037334008,0.0006091603,0.0000064270234],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0036291631,0.003202734,0.05561837,0.0014811498,0.00015678963,0.00082681875,0.0014618656,0.0004124081,0.07667999,0.000620963,0.0012588418,0.8546509],"study_design_scores_gemma":[0.012829534,0.0037084317,0.07780591,0.0014488529,0.00014847772,0.000068736685,0.000028489674,0.79555076,0.104966186,0.002850442,0.00025826695,0.00033593742],"about_ca_topic_score_codex":0.0000953133,"about_ca_topic_score_gemma":0.000002461534,"teacher_disagreement_score":0.854315,"about_ca_system_score_codex":0.00008684499,"about_ca_system_score_gemma":0.00016747948,"threshold_uncertainty_score":0.8028163},"labels":[],"label_agreement":null},{"id":"W1988284258","doi":"10.1007/s10278-014-9678-z","title":"A Content-Boosted Collaborative Filtering Algorithm for Personalized Training in Interpretation of Radiological Imaging","year":2014,"lang":"en","type":"article","venue":"Journal of Digital Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":19,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"National Natural Science Foundation of China","keywords":"Computer science; Collaborative filtering; Metric (unit); Interpretation (philosophy); Algorithm; Personalized medicine; Content (measure theory); Machine learning; Data mining; Artificial intelligence; Recommender system; Bioinformatics; Mathematics","score_opus":0.02200589460111775,"score_gpt":0.3047266604658938,"score_spread":0.28272076586477607,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1988284258","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34191245,0.00064545404,0.65377134,0.0019296212,0.00029460242,0.00026381467,0.000011632163,0.000018690273,0.0011523676],"genre_scores_gemma":[0.96332026,0.000014341552,0.036030628,0.00035102948,0.00019692314,0.000004766282,0.000011908013,0.000023002725,0.000047154364],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984952,0.00006609914,0.0007673942,0.00016059207,0.00025896874,0.0002517089],"domain_scores_gemma":[0.9983717,0.0004760476,0.00053631497,0.00007810014,0.00040105623,0.00013676715],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008694357,0.00015105492,0.00063566555,0.00031651143,0.000034922,0.000087600456,0.00011521189,0.000028852823,0.000007969706],"category_scores_gemma":[0.002367335,0.00012070132,0.00020567577,0.00019536472,0.00017586368,0.00050872774,0.00002871932,0.00034908895,3.8958555e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004344226,0.00008688774,0.02212244,0.000083946805,0.00009257626,0.00009911291,0.0057588182,0.000119064614,0.024771858,0.00018399126,0.000088591456,0.9461583],"study_design_scores_gemma":[0.010090199,0.0005563228,0.005211318,0.0019360938,0.00013685435,0.0016667094,0.010446824,0.9651186,0.0011599927,0.0010924431,0.0023277916,0.00025683932],"about_ca_topic_score_codex":0.0000028841075,"about_ca_topic_score_gemma":1.7780265e-7,"teacher_disagreement_score":0.96499956,"about_ca_system_score_codex":0.000090960595,"about_ca_system_score_gemma":0.00012818209,"threshold_uncertainty_score":0.4922057},"labels":[],"label_agreement":null},{"id":"W1988384934","doi":"10.1016/j.ijrobp.2012.07.1547","title":"A Prospective Study Measuring Interobserver Variability of GTV With FDG-PET-CT in Stage III Non-small Cell Lung Cancer Using 3D Analysis","year":2012,"lang":"en","type":"article","venue":"International Journal of Radiation Oncology*Biology*Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"CancerCare Manitoba","funders":"","keywords":"Medicine; Stage (stratigraphy); Lung cancer; Nuclear medicine; Radiology; Cancer; Prospective cohort study; Oncology; Pathology; Internal medicine","score_opus":0.020559474973570725,"score_gpt":0.3415854382035662,"score_spread":0.32102596322999544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1988384934","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94684,0.00019501268,0.051404826,0.00018678323,0.0007042971,0.00040604634,0.000012870249,0.000011254413,0.00023891052],"genre_scores_gemma":[0.99202377,0.000059849517,0.006974101,0.00016062136,0.00070392515,0.00001531956,0.000012479896,0.000024948564,0.000024961148],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9978197,0.000381888,0.00089726987,0.00025485535,0.00036267194,0.00028360856],"domain_scores_gemma":[0.9973623,0.0003250914,0.0012879239,0.00017865105,0.00069270877,0.0001533295],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021408745,0.00020416899,0.0008134838,0.00038506067,0.000046941914,0.000016906572,0.0002842843,0.000054656928,0.00006792038],"category_scores_gemma":[0.0003134544,0.00016540922,0.0002111161,0.00049343746,0.00016555392,0.00028481008,0.00008053246,0.0008170911,6.890514e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046028924,0.0015376933,0.9680851,0.000030425821,0.0022050955,0.000074075324,0.0021225496,0.019825587,0.0022441796,0.00013276875,0.000007730326,0.0032744966],"study_design_scores_gemma":[0.009700471,0.0007638243,0.858367,0.0001629111,0.0016919526,0.000115142066,0.0005964779,0.12700999,0.0011560349,0.00011177716,0.00011242111,0.00021199086],"about_ca_topic_score_codex":0.00057843415,"about_ca_topic_score_gemma":0.000052828582,"teacher_disagreement_score":0.1097181,"about_ca_system_score_codex":0.0013540591,"about_ca_system_score_gemma":0.0005485823,"threshold_uncertainty_score":0.6745192},"labels":[],"label_agreement":null},{"id":"W1990876776","doi":"10.1118/1.4815080","title":"SU‐E‐T‐653: Predicting Objective Function Weights for IMRT Prostate Treatment Planning Using Patient Anatomy","year":2013,"lang":"en","type":"article","venue":"Medical Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto","funders":"","keywords":"Prostate; Rectum; Radiation treatment planning; Medicine; Mathematics; Inverse; Nuclear medicine; Radiation therapy; Medical physics; Radiology; Surgery; Geometry; Internal medicine; Cancer","score_opus":0.013647260007489191,"score_gpt":0.2992548017559142,"score_spread":0.285607541748425,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1990876776","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90897,0.00021820662,0.086659476,0.0011843365,0.00063264713,0.0013197983,0.000006839635,0.00015348833,0.000855198],"genre_scores_gemma":[0.99500954,0.000017794951,0.0021352845,0.001044343,0.0012977113,0.00019240551,0.00009921507,0.000058838385,0.00014483815],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979852,0.000039155708,0.0003942617,0.00041732442,0.00066557096,0.0004985175],"domain_scores_gemma":[0.998712,0.00024306726,0.00016527921,0.00021639533,0.00017457697,0.0004886974],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021986206,0.00025356858,0.0004303842,0.000071306175,0.00026177143,0.000052663603,0.00007673344,0.0001290696,0.00010687928],"category_scores_gemma":[0.00039781112,0.00018952013,0.00017389274,0.0001889718,0.00017587832,0.00016941607,0.000045910758,0.00042777933,0.000018789422],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041818622,0.0011313863,0.1208597,0.00034900784,0.00073229935,0.00011243119,0.004687384,0.00064250163,0.0031638665,0.0006997084,0.0027133236,0.8644902],"study_design_scores_gemma":[0.010554185,0.004244769,0.019397028,0.0017127173,0.0008548001,0.00017381633,0.0011306907,0.92519784,0.007982584,0.012574166,0.015380947,0.0007964474],"about_ca_topic_score_codex":0.00024962312,"about_ca_topic_score_gemma":6.120659e-7,"teacher_disagreement_score":0.92455536,"about_ca_system_score_codex":0.00028446954,"about_ca_system_score_gemma":0.00026441182,"threshold_uncertainty_score":0.7728407},"labels":[],"label_agreement":null},{"id":"W1992845372","doi":"10.1016/j.media.2013.04.008","title":"The impact of registration accuracy on imaging validation study design: A novel statistical power calculation","year":2013,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lawson Health Research Institute; Western University","funders":"","keywords":"Statistical power; Context (archaeology); Modalities; Computer science; Image registration; Medical imaging; Statistical model; Statistical hypothesis testing; Monte Carlo method; Power (physics); Artificial intelligence; Medical physics; Statistics; Mathematics; Image (mathematics); Medicine","score_opus":0.017757023342676096,"score_gpt":0.3701413791481233,"score_spread":0.3523843558054472,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1992845372","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36799327,0.00002546755,0.6271374,0.0037497906,0.000039024904,0.0005237609,0.0000031583656,0.00003394502,0.00049417606],"genre_scores_gemma":[0.99527276,0.000013711617,0.0041313,0.00022496011,0.00008273026,0.000038208116,0.0000857937,0.000018930165,0.00013161369],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971512,0.00028883145,0.00067692023,0.00032916115,0.0012676523,0.00028622852],"domain_scores_gemma":[0.997094,0.0014852536,0.00028423755,0.0004692961,0.00033939598,0.00032782913],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0019274531,0.00018275426,0.00044626,0.00025811567,0.00017765134,0.00013333918,0.00017908067,0.000061524996,0.0010128049],"category_scores_gemma":[0.010435475,0.00010575255,0.00028796418,0.0008043432,0.00024938054,0.0001891325,0.00003906219,0.00046073284,0.000037704416],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00094602327,0.007512708,0.5827408,0.00008183209,0.011038128,0.00040433215,0.0025598211,0.010418605,0.0468063,0.0008706482,0.045747988,0.29087284],"study_design_scores_gemma":[0.0011280756,0.0003544899,0.39755514,0.000030135041,0.00095570553,0.000015526166,0.00019836135,0.59933674,0.00016279888,0.0001321782,0.000027083557,0.00010373666],"about_ca_topic_score_codex":0.0016788665,"about_ca_topic_score_gemma":0.00000484931,"teacher_disagreement_score":0.6272795,"about_ca_system_score_codex":0.00011374163,"about_ca_system_score_gemma":0.00019081053,"threshold_uncertainty_score":0.9999004},"labels":[],"label_agreement":null},{"id":"W2003097980","doi":"10.1118/1.3244147","title":"Poster — Wed Eve—43: A Maximum Likelihood/ Simulated Annealing‐Based Validation Method for Tumor Segmentation Techniques","year":2009,"lang":"en","type":"article","venue":"Medical Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Health Science Centre; University of Toronto","funders":"","keywords":"Segmentation; Ground truth; Artificial intelligence; Probabilistic logic; Imaging phantom; Computer science; Image segmentation; Simulated annealing; Pattern recognition (psychology); Medical imaging; Computer vision; Mathematics; Nuclear medicine; Medicine; Algorithm","score_opus":0.01534792316141076,"score_gpt":0.35442501404181337,"score_spread":0.3390770908804026,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2003097980","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.044473562,0.000052373136,0.93559074,0.017913228,0.000161693,0.0009398752,0.000007593562,0.00035272798,0.00050819415],"genre_scores_gemma":[0.87238073,0.000013875231,0.092455186,0.032997333,0.0013079634,0.000051436673,0.00064189546,0.00006716992,0.000084428066],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979095,0.00011055707,0.00044091835,0.00037394528,0.00077582663,0.00038929592],"domain_scores_gemma":[0.9986856,0.00032040238,0.00016012845,0.00025593163,0.00019997194,0.00037795078],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010461042,0.00021654463,0.00041467862,0.00008799592,0.00011491612,0.000039225873,0.00014294469,0.00014073776,0.00010475459],"category_scores_gemma":[0.0009870029,0.00018548536,0.00018024788,0.00026566375,0.0000837253,0.00010128447,0.000020351865,0.0004972192,0.00001059336],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044077332,0.00062850345,0.0017864024,0.00024665886,0.00008074224,0.00006944317,0.00031231472,0.0001389401,0.033497095,0.000113712376,0.004855574,0.95782983],"study_design_scores_gemma":[0.00876666,0.0016702552,0.002416218,0.0010985668,0.00051397947,0.00006344923,0.000041454652,0.60087436,0.34200433,0.03600803,0.0058856145,0.0006570999],"about_ca_topic_score_codex":0.00002447505,"about_ca_topic_score_gemma":2.463097e-7,"teacher_disagreement_score":0.95717275,"about_ca_system_score_codex":0.000095816686,"about_ca_system_score_gemma":0.00022010726,"threshold_uncertainty_score":0.75638735},"labels":[],"label_agreement":null},{"id":"W2004171117","doi":"10.1118/1.4888760","title":"SU‐E‐T‐427: Cell Surviving Fractions Derived From Tumor‐Volume Variation During Radiotherapy for Non‐Small Cell Lung Cancer: Comparison with Predictive Assays","year":2014,"lang":"en","type":"article","venue":"Medical Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"London Health Sciences Centre","funders":"","keywords":"Lung cancer; Radiation therapy; Nuclear medicine; Population; Cancer; Dosimetry; Cell; Lung volumes; Medicine; Lung; Pathology; Biology; Internal medicine","score_opus":0.006774497353563342,"score_gpt":0.26460927054298106,"score_spread":0.2578347731894177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2004171117","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43744573,0.000149339,0.5600589,0.00096092897,0.0003616355,0.00045735016,0.000017347013,0.00009626969,0.0004524832],"genre_scores_gemma":[0.9865818,0.00008413979,0.009083519,0.0009356757,0.0026662743,0.00016408403,0.00015174644,0.00010277309,0.0002299949],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997542,0.0001387279,0.00045069391,0.00056056597,0.00079858874,0.00050940446],"domain_scores_gemma":[0.9979296,0.0006932426,0.0003286179,0.00035906382,0.00017567165,0.0005138247],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005567049,0.00030814626,0.00070704974,0.00006568614,0.00031675244,0.000065574415,0.00022756224,0.0001604354,0.00018398033],"category_scores_gemma":[0.00033013045,0.00026718705,0.00014619887,0.00021634846,0.00017821274,0.00013038129,0.00004606361,0.00102705,0.0000062414333],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010748972,0.0021770366,0.8769713,0.0013274896,0.0007942728,0.0000528793,0.006602123,0.012318969,0.069520436,0.0000664722,0.0049628285,0.024131306],"study_design_scores_gemma":[0.0063178204,0.00035708462,0.110555306,0.00052813516,0.00045134567,0.0000062876893,0.00010849526,0.8717151,0.008157523,0.000121634876,0.0013406858,0.00034052687],"about_ca_topic_score_codex":0.0009570198,"about_ca_topic_score_gemma":0.000032030828,"teacher_disagreement_score":0.85939616,"about_ca_system_score_codex":0.0002651814,"about_ca_system_score_gemma":0.0003349117,"threshold_uncertainty_score":0.999978},"labels":[],"label_agreement":null},{"id":"W2004442042","doi":"10.1118/1.2965914","title":"Sci-Thurs PM: Delivery-07: Evaluation of prospects to use daily megavoltage CT studies for adaptive radiotherapy","year":2008,"lang":"en","type":"article","venue":"Medical Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"London Health Sciences Centre","funders":"","keywords":"Tomotherapy; Radiation therapy; Medicine; Nuclear medicine; Radiation treatment planning; Lung cancer; Radiology; Oncology","score_opus":0.07968795741034748,"score_gpt":0.371421163179655,"score_spread":0.2917332057693075,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2004442042","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91174513,0.0015682362,0.07898599,0.0050191516,0.0005433913,0.0016767823,0.000013186004,0.000080159836,0.00036796439],"genre_scores_gemma":[0.98968744,0.0004883482,0.006008267,0.0025727565,0.00082058314,0.00011991522,0.00002354107,0.00004679406,0.00023235648],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969997,0.00009844863,0.00039460056,0.00037316076,0.001805371,0.00032874974],"domain_scores_gemma":[0.9980235,0.0004684567,0.00014070013,0.00030003555,0.00069525035,0.00037203458],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011388871,0.00020193521,0.0006178277,0.00007887519,0.00016725252,0.000009210131,0.00014754766,0.000058456055,0.00006104409],"category_scores_gemma":[0.0040181894,0.00016257752,0.00016504884,0.00029277857,0.00053641223,0.00012221598,0.00005093699,0.00037362572,0.000010353067],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0024770072,0.0031336462,0.037937112,0.0011573086,0.0035468282,0.0005051053,0.018501915,0.0033875639,0.0103275245,0.0046707178,0.1429263,0.77142894],"study_design_scores_gemma":[0.05001986,0.008035096,0.06274035,0.0052275746,0.0030673102,0.00068898994,0.0016753144,0.7747492,0.031037638,0.012237814,0.04841458,0.002106266],"about_ca_topic_score_codex":0.000050979423,"about_ca_topic_score_gemma":0.0000034510142,"teacher_disagreement_score":0.77136165,"about_ca_system_score_codex":0.00021559186,"about_ca_system_score_gemma":0.0004415609,"threshold_uncertainty_score":0.66297185},"labels":[],"label_agreement":null},{"id":"W2007586852","doi":"10.6000/1927-7229.2013.02.03.2","title":"Hepatocellular Carcinoma Microvessel Density Quantitation with Image Analysis: Correlation with Prognosis","year":2013,"lang":"en","type":"article","venue":"Journal of Analytical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Hepatocellular carcinoma; Microvessel; Medicine; Correlation; Pathology; Internal medicine; Carcinoma; Gastroenterology; Immunohistochemistry; Mathematics","score_opus":0.011439554049641695,"score_gpt":0.2888982695967843,"score_spread":0.2774587155471426,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2007586852","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8947089,0.00006472378,0.09612734,0.008046996,0.00004427343,0.00017554627,2.8850906e-7,0.000010124016,0.0008218441],"genre_scores_gemma":[0.96321994,0.000017130718,0.03585122,0.0006012706,0.00013200582,0.000003165764,0.000008660074,0.000015091531,0.00015150361],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99857515,0.000114248876,0.00051950774,0.00017350297,0.00039422172,0.00022334729],"domain_scores_gemma":[0.9980168,0.00021691118,0.0004814492,0.0001294533,0.0008457078,0.0003096906],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00050671044,0.0001367065,0.0006941085,0.00040526423,0.000058672966,0.00004181797,0.000085092266,0.000107059874,0.00015360853],"category_scores_gemma":[0.00027947288,0.00008260777,0.00018096149,0.0006291121,0.00022662908,0.00020600975,0.000015142918,0.0006353296,0.000019908868],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005154908,0.00036978733,0.9900061,0.000035427962,0.0012439467,0.0009636494,0.00015562102,0.00025186397,0.0028204517,0.000241914,0.0011317421,0.002264027],"study_design_scores_gemma":[0.0021941254,0.003424992,0.64549583,0.000064705964,0.0048316224,0.0015583772,0.00028561288,0.3411635,0.00026080417,0.00007202484,0.0005319987,0.0001164303],"about_ca_topic_score_codex":0.0001221195,"about_ca_topic_score_gemma":0.000009759914,"teacher_disagreement_score":0.34451026,"about_ca_system_score_codex":0.00016814323,"about_ca_system_score_gemma":0.00032521214,"threshold_uncertainty_score":0.33686468},"labels":[],"label_agreement":null},{"id":"W2009469378","doi":"10.1016/s0167-8140(06)80904-7","title":"163 British columbia cancer agency audit of the use of PET/CT in head and neck patients: Post-treatment management","year":2006,"lang":"en","type":"article","venue":"Radiotherapy and Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Audit; Head and neck cancer; Medicine; Agency (philosophy); Head and neck; Medical physics; Radiology; Business; Surgery; Radiation therapy; Accounting; Sociology","score_opus":0.010672480569051634,"score_gpt":0.2864254755024465,"score_spread":0.2757529949333949,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2009469378","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9954727,0.0022870982,0.000014636146,0.0013963648,0.00013251821,0.00040409478,0.0000148067975,0.0000057330994,0.00027204107],"genre_scores_gemma":[0.98554516,0.008927268,0.0022940494,0.0013996143,0.000057103436,0.00002747967,0.000009966031,0.000015166174,0.0017242242],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99929404,0.000068735324,0.00024560458,0.00016056922,0.00009222263,0.00013881447],"domain_scores_gemma":[0.99963945,0.00006196652,0.00010885079,0.000111511385,0.0000380227,0.000040210267],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007859398,0.00006994989,0.00031354537,0.00003608985,0.00004186382,0.000013704506,0.00003954143,0.000017432914,0.00010687882],"category_scores_gemma":[0.000020222928,0.000064810745,0.00004302901,0.00008634289,0.00017662,0.000030685034,0.000017707016,0.0000951027,7.26141e-8],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000732423,0.00047349837,0.7783036,0.00008073589,0.00007356093,0.00014757889,0.0001321378,0.000048722653,0.00023125272,0.00002677166,0.0016977959,0.2187111],"study_design_scores_gemma":[0.004405,0.00077152037,0.8926129,0.00016283916,0.000050697847,0.00013295122,0.00001671088,0.0005599958,0.000013067739,0.000042647047,0.1011768,0.00005487549],"about_ca_topic_score_codex":0.06374153,"about_ca_topic_score_gemma":0.03334296,"teacher_disagreement_score":0.21865621,"about_ca_system_score_codex":0.0002012788,"about_ca_system_score_gemma":0.000056039346,"threshold_uncertainty_score":0.984296},"labels":[],"label_agreement":null},{"id":"W2009911194","doi":"10.1016/j.media.2014.07.003","title":"Comparing algorithms for automated vessel segmentation in computed tomography scans of the lung: the VESSEL12 study","year":2014,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":158,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Heart, Lung, and Blood Institute","keywords":"Segmentation; Computer science; Automation; Artificial intelligence; Computed tomography; Algorithm; Data mining; Machine learning; Radiology; Medicine; Engineering","score_opus":0.012072452417376455,"score_gpt":0.32582657637598206,"score_spread":0.3137541239586056,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2009911194","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.74316144,0.00011975133,0.24964423,0.005779485,0.00015792793,0.0007961295,0.0000031047773,0.00010095178,0.00023698516],"genre_scores_gemma":[0.9957392,0.0000066000307,0.0032511612,0.00074951496,0.00010497501,0.0000499596,0.000048713493,0.000016459,0.0000334172],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99767774,0.00036037745,0.00058211095,0.0002883411,0.0008318069,0.00025962671],"domain_scores_gemma":[0.9985811,0.0005035009,0.0001979801,0.00042773545,0.0001366139,0.00015306644],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021777898,0.00015056899,0.0006124961,0.00033192252,0.00014611604,0.00003778344,0.0003824384,0.0000639024,0.0000545619],"category_scores_gemma":[0.0010914662,0.000083745275,0.00031856247,0.002145392,0.00028578803,0.000053835418,0.000095249816,0.00041964298,0.0000010166945],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000054621745,0.00095368776,0.9749787,0.00012454591,0.0019846736,0.000013412949,0.0019397856,0.002605286,0.00085400476,0.000041371724,0.0034730781,0.012976859],"study_design_scores_gemma":[0.00152763,0.00005789203,0.3228437,0.00006080501,0.0013335724,0.0000030167384,0.00047260438,0.6734378,0.000111414076,0.000013958354,0.00007880112,0.000058847858],"about_ca_topic_score_codex":0.00062793755,"about_ca_topic_score_gemma":0.00008328503,"teacher_disagreement_score":0.67083246,"about_ca_system_score_codex":0.00003950367,"about_ca_system_score_gemma":0.000063841035,"threshold_uncertainty_score":0.34150332},"labels":[],"label_agreement":null},{"id":"W2010595888","doi":"10.1118/1.3476154","title":"Poster — Thur Eve — 49: Investigating the Effects of Motion on Texture within the Lung","year":2010,"lang":"en","type":"article","venue":"Medical Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto; Sunnybrook Health Science Centre","funders":"","keywords":"Segmentation; Lung cancer; Artificial intelligence; Pattern recognition (psychology); Lung; Nuclear medicine; Feature (linguistics); Context (archaeology); Image segmentation; Computed tomography; Computer science; Medicine; Radiology; Pathology; Internal medicine; Biology","score_opus":0.005550741524727022,"score_gpt":0.2709020699638274,"score_spread":0.26535132843910036,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2010595888","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9625556,0.00009523193,0.0015784528,0.03079355,0.0010751887,0.0004033595,7.542701e-7,0.000049447168,0.0034484277],"genre_scores_gemma":[0.98538,0.000005860728,0.00004812871,0.013063793,0.0013313643,0.000012981205,0.00000897077,0.000024693827,0.0001242164],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99836904,0.00011289216,0.0002474254,0.0001850592,0.0008899849,0.00019557393],"domain_scores_gemma":[0.9982264,0.00096494553,0.00014942163,0.00039660523,0.00006021483,0.00020240537],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008653641,0.00013999605,0.00023023196,0.000017814524,0.00014857516,0.000018343304,0.0002580778,0.0001255748,0.000041020176],"category_scores_gemma":[0.005906375,0.00006518231,0.00010015633,0.00017662636,0.0007132826,0.000036029687,0.00007157859,0.002214422,0.000015232012],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020352511,0.0014960378,0.25317207,0.0030965253,0.00076889497,0.00025155494,0.019175857,0.0000747809,0.17342821,0.051705983,0.06326691,0.43335965],"study_design_scores_gemma":[0.010439928,0.0014072972,0.60980904,0.006612925,0.001380868,0.00045369868,0.00028292518,0.21916655,0.09822004,0.046191923,0.004944755,0.0010900241],"about_ca_topic_score_codex":0.00002801991,"about_ca_topic_score_gemma":0.0000015588874,"teacher_disagreement_score":0.43226963,"about_ca_system_score_codex":0.000014579766,"about_ca_system_score_gemma":0.000114020644,"threshold_uncertainty_score":0.96206844},"labels":[],"label_agreement":null},{"id":"W2011685133","doi":"10.1016/j.nima.2005.03.081","title":"Identifying markers of pathology in SAXS data of malignant tissues of the brain","year":2005,"lang":"en","type":"article","venue":"Nuclear Instruments and Methods in Physics Research Section A Accelerators Spectrometers Detectors and Associated Equipment","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":31,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Royal University Hospital Foundation; University of Saskatchewan","keywords":"Small-angle X-ray scattering; Malignancy; Pathology; Medicine; Brain tissue; Synchrotron radiation; Scattering; Biomedical engineering; Optics; Physics","score_opus":0.07468646095529648,"score_gpt":0.4280454671599913,"score_spread":0.35335900620469485,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2011685133","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99856544,0.0001296239,0.00016332543,0.00041003595,0.00013217276,0.0003439913,0.00001104194,0.000006881852,0.00023747417],"genre_scores_gemma":[0.9839286,0.0006513813,0.015270274,0.00005499692,0.000039868013,0.000005101846,0.0000054364195,0.000021677059,0.000022632312],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9974636,0.000816041,0.0005566897,0.00034642752,0.0004811139,0.00033612974],"domain_scores_gemma":[0.9990024,0.00025492182,0.0002660812,0.00031977452,0.000073237214,0.00008360195],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038693752,0.00013328182,0.00047879337,0.0003814869,0.00008035037,0.000024699808,0.00022449419,0.00010538718,0.000034143388],"category_scores_gemma":[0.0006821949,0.000103524435,0.000057156085,0.00079834776,0.00033563722,0.00014468981,0.00043610652,0.00067360315,1.01805284e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018894294,0.00036817958,0.06553624,0.00020111108,0.00014863351,0.0000059670438,0.0015408071,0.00000937729,0.61937946,0.00018002352,0.000055152028,0.3123861],"study_design_scores_gemma":[0.009298779,0.002587806,0.60924274,0.0025666894,0.00015388415,0.00005392423,0.0048254444,0.034635536,0.33069023,0.0036072992,0.001803535,0.0005341238],"about_ca_topic_score_codex":0.00042113633,"about_ca_topic_score_gemma":0.00003865197,"teacher_disagreement_score":0.54370654,"about_ca_system_score_codex":0.00020512045,"about_ca_system_score_gemma":0.000059674938,"threshold_uncertainty_score":0.4221604},"labels":[],"label_agreement":null},{"id":"W2015512691","doi":"10.1155/2012/347120","title":"Tissue-Based MRI Intensity Standardization: Application to Multicentric Datasets","year":2012,"lang":"en","type":"article","venue":"International Journal of Biomedical Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":53,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; Institut Universitaire en Santé Mentale de Québec","funders":"National Institute on Aging; University of California, San Diego; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; University of California, Los Angeles; Genentech; National Institutes of Health; Servier; Eisai; Ministère du Développement Économique, de l’Innovation et de l’Exportation; Northern California Institute for Research and Education; Pfizer; Biogen; BioClinica; Alzheimer's Association; Amorfix Life Sciences; F. Hoffmann-La Roche; Medpace; Bristol-Myers Squibb; Eli Lilly and Company; AstraZeneca; Novartis Pharmaceuticals Corporation; Synarc; Dana Foundation; Bayer HealthCare; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; Foundation for the National Institutes of Health","keywords":"Standardization; Computer science; Data mining; Data science; Information retrieval","score_opus":0.007427794554730022,"score_gpt":0.33703760292353535,"score_spread":0.3296098083688053,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2015512691","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019761235,0.00033234898,0.9329468,0.044538707,0.0020287398,0.00015728791,0.000034663826,0.000029814464,0.00017038528],"genre_scores_gemma":[0.95553726,0.000026272492,0.03534252,0.006831268,0.002032645,0.0000018388467,0.00018929617,0.000019499515,0.00001939436],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977624,0.00004308681,0.00056776043,0.00014653723,0.0012087986,0.00027145157],"domain_scores_gemma":[0.9981091,0.000111797846,0.00028427056,0.0001610929,0.00064472354,0.0006890103],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010413987,0.00012574508,0.00026950723,0.00049812556,0.00005102803,0.000055015636,0.00030417036,0.000042687145,0.0001611815],"category_scores_gemma":[0.0012436096,0.00010250695,0.00009182308,0.00028375624,0.000121156794,0.00025697544,0.000087008004,0.00039146017,0.00004660737],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00096974085,0.0013313395,0.14681007,0.000074232696,0.0003795239,0.0006535274,0.00060335954,0.00066761184,0.04893116,0.00021119109,0.09191673,0.7074515],"study_design_scores_gemma":[0.0036045578,0.00014651951,0.031975884,0.00042458365,0.00018664607,0.002077646,0.00013258334,0.048950076,0.006893434,0.000060837283,0.9053153,0.00023196581],"about_ca_topic_score_codex":0.000019001538,"about_ca_topic_score_gemma":1.6616072e-7,"teacher_disagreement_score":0.93577605,"about_ca_system_score_codex":0.00025567834,"about_ca_system_score_gemma":0.0001492941,"threshold_uncertainty_score":0.41801122},"labels":[],"label_agreement":null},{"id":"W2015849950","doi":"10.1117/12.2081638","title":"Evaluation metrics for bone segmentation in ultrasound","year":2015,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Ground truth; Segmentation; Image segmentation; Artificial intelligence; Frame (networking); Computer vision; Volume (thermodynamics); 3D ultrasound; Data mining; Ultrasound","score_opus":0.02364134357598873,"score_gpt":0.29574098053857406,"score_spread":0.2720996369625853,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2015849950","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99261045,0.00024307444,0.00034583185,0.003742651,0.00028025574,0.0011614067,0.000015784253,0.000042554442,0.0015579666],"genre_scores_gemma":[0.7156766,0.0001068921,0.28264162,0.0002855241,0.00059876824,0.00038570588,0.000049091526,0.00006956204,0.00018621862],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99753606,2.7320223e-8,0.0006548843,0.0003094794,0.0011954067,0.0003041368],"domain_scores_gemma":[0.99632496,0.00026386007,0.000319888,0.00004438632,0.0028795728,0.00016734598],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003195881,0.00020914657,0.0003976069,0.0002099568,0.000042067084,0.00006632126,0.0002999656,0.00014561448,0.0000071376794],"category_scores_gemma":[0.0069030384,0.00017500264,0.00036926536,0.0004658164,0.000127067,0.00033454274,0.00005221373,0.00031194388,7.3828716e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004133143,0.00041871183,0.0064196214,0.0009493215,0.00062239944,2.4102187e-7,0.00088534335,0.0009071444,0.80950004,0.16308016,0.010534129,0.006269547],"study_design_scores_gemma":[0.015636196,0.0016552822,0.0070971902,0.0010159691,0.0014727497,0.00012473046,0.0064822934,0.8189985,0.12844871,0.009852433,0.008484125,0.0007318004],"about_ca_topic_score_codex":0.00001563333,"about_ca_topic_score_gemma":1.8375502e-7,"teacher_disagreement_score":0.8180914,"about_ca_system_score_codex":0.00045149057,"about_ca_system_score_gemma":0.00011079402,"threshold_uncertainty_score":0.826408},"labels":[],"label_agreement":null},{"id":"W2017622630","doi":"10.1118/1.3611747","title":"SU‐E‐I‐173: Factor Analysis with Prior Information Using Projected Gradient Method — Application to 11C‐DTBZ Dynamic PET Dataset for Early Detection of Parkinsonˈs Disease","year":2011,"lang":"en","type":"article","venue":"Medical Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Voxel; Pattern recognition (psychology); Artificial intelligence; Metric (unit); Mathematics; Computer science; Nuclear medicine; Medicine","score_opus":0.017261873209788912,"score_gpt":0.32227319591430037,"score_spread":0.3050113227045115,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2017622630","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3409904,0.000005007722,0.6578647,0.00014807806,0.000038124454,0.00065865857,0.00025563713,0.0000303063,0.000009077715],"genre_scores_gemma":[0.96797913,0.000004601094,0.02957727,0.00035426466,0.00008113976,0.000106108986,0.0018721179,0.000020762025,0.0000046272435],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983554,0.00005964834,0.00040955766,0.00027312257,0.00065388455,0.00024838632],"domain_scores_gemma":[0.99861366,0.00009564019,0.0002514716,0.00037670558,0.00018570831,0.00047684653],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040632655,0.00016606285,0.0003964898,0.00021246044,0.00009061801,0.00001880058,0.00014588056,0.000052772568,0.000020599777],"category_scores_gemma":[0.0005164132,0.00012917626,0.00011843992,0.0008169545,0.000104868115,0.00020745517,0.000042734773,0.00025684235,0.000003804782],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0039106808,0.0015019047,0.066463836,0.0016185561,0.0021089162,0.000034350473,0.0051629697,0.0010783504,0.008583789,0.0003201509,0.00021969134,0.9089968],"study_design_scores_gemma":[0.002349298,0.0005770767,0.13661672,0.00016324638,0.0023947672,0.000014684148,0.00008718014,0.8520962,0.00310259,0.00032848035,0.001958524,0.00031124556],"about_ca_topic_score_codex":0.00044040577,"about_ca_topic_score_gemma":0.000019602185,"teacher_disagreement_score":0.90868556,"about_ca_system_score_codex":0.00009894832,"about_ca_system_score_gemma":0.00017839464,"threshold_uncertainty_score":0.52676547},"labels":[],"label_agreement":null},{"id":"W2019099758","doi":"10.1118/1.4814321","title":"SU‐E‐J‐109: Registration/Segmentation for Adaptive Radiotherapy Using the Jensen Renyi Divergence","year":2013,"lang":"en","type":"article","venue":"Medical Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University","funders":"","keywords":"Imaging phantom; Image registration; Divergence (linguistics); Segmentation; Mathematics; Metric (unit); Artificial intelligence; Computer science; Nuclear medicine; Pattern recognition (psychology); Medicine; Image (mathematics)","score_opus":0.03147214589090163,"score_gpt":0.3318348082938781,"score_spread":0.3003626624029765,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2019099758","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09165083,0.00024214503,0.89258957,0.013747323,0.00040304035,0.00084981497,0.000003841346,0.000056205714,0.00045726317],"genre_scores_gemma":[0.96202993,0.0001788793,0.025468318,0.008443909,0.0026543548,0.00013225999,0.00007775258,0.000053034146,0.0009615481],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985758,0.00005689581,0.00026255441,0.00022710474,0.0006277521,0.00024991127],"domain_scores_gemma":[0.9990394,0.00027447796,0.00012283816,0.00023022,0.00011879736,0.00021422595],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040074918,0.00013029388,0.00021629027,0.000020237228,0.00021329231,0.00004477243,0.00015603664,0.000076347336,0.00029096333],"category_scores_gemma":[0.0004678518,0.0000865837,0.00010818142,0.0001501646,0.0003564475,0.000113690454,0.00002513383,0.00034730553,0.0000119538445],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003407287,0.0007109961,0.02269985,0.0002874974,0.0006581268,0.000046909667,0.0038410902,0.0009786919,0.05200549,0.012310176,0.12634878,0.7797717],"study_design_scores_gemma":[0.0038397466,0.0005220284,0.0035266036,0.00032078486,0.00023078058,0.00008750919,0.0005203421,0.9598686,0.0040760217,0.014531914,0.0120894415,0.00038624147],"about_ca_topic_score_codex":0.00022426834,"about_ca_topic_score_gemma":0.0000013943978,"teacher_disagreement_score":0.9588899,"about_ca_system_score_codex":0.000083489635,"about_ca_system_score_gemma":0.00017337216,"threshold_uncertainty_score":0.35307807},"labels":[],"label_agreement":null},{"id":"W2019682317","doi":"10.3390/informatics1020160","title":"How Using Dedicated Software Can Improve RECIST Readings","year":2014,"lang":"en","type":"article","venue":"Informatics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Response Evaluation Criteria in Solid Tumors; Reproducibility; Computer science; Software; Reading (process); Medicine; Medical physics; Radiology; Nuclear medicine; Data mining; Clinical trial; Programming language; Statistics; Mathematics; Pathology","score_opus":0.011924059876083587,"score_gpt":0.264730609304937,"score_spread":0.25280654942885344,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2019682317","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4824496,0.0000421697,0.5011485,0.006416127,0.00074894703,0.00038043468,0.000009364155,0.00037655112,0.008428274],"genre_scores_gemma":[0.81052595,0.000021427762,0.181151,0.0059565967,0.00045761137,0.0000055097594,0.00007072141,0.000045123375,0.0017660558],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99893737,0.000016899225,0.00033941597,0.00008708419,0.0003215208,0.00029773492],"domain_scores_gemma":[0.9990647,0.000091242066,0.00020026864,0.0002744876,0.00011093357,0.00025838576],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042006784,0.00014064135,0.00027312146,0.000113977825,0.00011686606,0.000108278124,0.00012554332,0.00009842005,0.000014939575],"category_scores_gemma":[0.0020768514,0.000114065406,0.00006520043,0.00016150577,0.00011183897,0.00015664288,0.000054565,0.00046214322,0.000015008869],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000799797,0.00011426577,0.030255944,0.0015038953,0.00022004165,0.000040313542,0.007419386,0.00025575142,0.0077281115,0.002171058,0.015656048,0.93455523],"study_design_scores_gemma":[0.002184285,0.000245324,0.0009490774,0.00046006686,0.00019831945,0.00037956724,0.0007716987,0.7563903,0.0019902529,0.0005126425,0.23553653,0.00038196915],"about_ca_topic_score_codex":0.0000786533,"about_ca_topic_score_gemma":0.0000020390905,"teacher_disagreement_score":0.9341732,"about_ca_system_score_codex":0.00009093413,"about_ca_system_score_gemma":0.00008909823,"threshold_uncertainty_score":0.46514523},"labels":[],"label_agreement":null},{"id":"W2020530055","doi":"10.1118/1.3244148","title":"Poster — Wed Eve—44: CO‐Registered Multi‐Modality Pattern Analysis Segmentation System (COMPASS) for Radiation Targeting of Head and Neck Cancer Using FDG PET/CT","year":2009,"lang":"en","type":"article","venue":"Medical Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Health Science Centre; University of Toronto","funders":"","keywords":"Voxel; Segmentation; Artificial intelligence; Nuclear medicine; Medicine; Head and neck cancer; Head and neck; Radiation therapy; Radiation treatment planning; Medical imaging; Computer science; Radiology; Pattern recognition (psychology)","score_opus":0.032367300404395026,"score_gpt":0.36765621295342504,"score_spread":0.33528891254903004,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2020530055","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.71962047,0.00018780818,0.27769485,0.0019744735,0.00010780512,0.00033031421,0.000019264342,0.000035012024,0.000029994226],"genre_scores_gemma":[0.9967672,0.000030470717,0.0014831359,0.0010392484,0.00040419138,0.000013570608,0.00022656671,0.000019427787,0.00001619486],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981995,0.000098263874,0.0005396869,0.0003255224,0.00057690387,0.0002601085],"domain_scores_gemma":[0.9989932,0.00012431298,0.00033595512,0.0001890888,0.00010532757,0.00025208612],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005910789,0.00017187759,0.0006115785,0.00008573729,0.00010696419,0.000025299118,0.00008443547,0.000030520343,0.000024592582],"category_scores_gemma":[0.00022541199,0.00015003115,0.00017900736,0.00025340708,0.000109489796,0.000094664065,0.000019379686,0.0002607538,6.7520784e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029538403,0.00067836494,0.70625126,0.002236367,0.0013609567,0.0001348455,0.0011275834,0.0021313303,0.014130935,0.000059426824,0.00071725954,0.2708763],"study_design_scores_gemma":[0.0048241266,0.00013223571,0.12958938,0.0006143532,0.0012534828,0.000033799504,0.00011668407,0.8597722,0.003311688,0.00005785642,0.00007590124,0.0002182726],"about_ca_topic_score_codex":0.0005852502,"about_ca_topic_score_gemma":0.0000085014135,"teacher_disagreement_score":0.85764086,"about_ca_system_score_codex":0.00016339634,"about_ca_system_score_gemma":0.00009978869,"threshold_uncertainty_score":0.61180925},"labels":[],"label_agreement":null},{"id":"W2021225636","doi":"10.1002/ana.1013","title":"Texture analysis and morphological processing of magnetic resonance imaging assist detection of focal cortical dysplasia in extra-temporal partial epilepsy","year":2001,"lang":"en","type":"article","venue":"Annals of Neurology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":178,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Montreal Neurological Institute and Hospital","funders":"","keywords":"Cortical dysplasia; Magnetic resonance imaging; Voxel; White matter; Nuclear medicine; Lesion; Medicine; Radiology; Pathology","score_opus":0.021526246847701713,"score_gpt":0.31406854346647645,"score_spread":0.29254229661877473,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2021225636","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9914298,0.0020406556,0.0031163408,0.003165571,0.000035248406,0.000096567055,0.0000021371643,0.000010938932,0.000102717924],"genre_scores_gemma":[0.9986215,0.00018450947,0.00031949417,0.0008067261,0.00004126197,0.000004294506,0.0000045244765,0.000009893934,0.000007747145],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9985252,0.00018755363,0.00055220485,0.0002948095,0.00019205819,0.00024815937],"domain_scores_gemma":[0.9992991,0.00015991397,0.00020294101,0.00014834823,0.00009252039,0.00009714986],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044757864,0.000115986026,0.00058344123,0.00028457,0.000026506337,0.0000042446227,0.00007366558,0.00011473604,0.000042990778],"category_scores_gemma":[0.00054824445,0.00009898649,0.000101746715,0.0005292178,0.0005383538,0.000044542438,0.000038717488,0.0004817122,2.758005e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008157914,0.0001685666,0.84651023,0.000048955502,0.00001724312,0.00037829948,0.000064310894,0.00003786971,0.036581725,0.00002807784,0.000008991513,0.11533994],"study_design_scores_gemma":[0.0007074476,0.0008280434,0.90775263,0.00003444455,0.000140587,0.0004278523,0.000011915275,0.08766703,0.0019646208,0.00012202579,0.0002824247,0.00006094343],"about_ca_topic_score_codex":0.00014362665,"about_ca_topic_score_gemma":0.000029461067,"teacher_disagreement_score":0.115279,"about_ca_system_score_codex":0.0000030101219,"about_ca_system_score_gemma":0.00003181648,"threshold_uncertainty_score":0.4036552},"labels":[],"label_agreement":null},{"id":"W2022204055","doi":"10.1118/1.4815231","title":"MO‐D‐105‐05: A Novel Web‐Based Tool for Quantification of VMAT/IMRT Treatment Plan Quality","year":2013,"lang":"en","type":"article","venue":"Medical Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; SQL; Database; Plan (archaeology); Python (programming language); Web site; Web application; Information retrieval; Medical physics; World Wide Web; Medicine; The Internet","score_opus":0.05163965970491435,"score_gpt":0.35628394421999193,"score_spread":0.3046442845150776,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2022204055","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49121758,0.000053489835,0.4955814,0.01117252,0.0002814033,0.0010715098,0.000045681907,0.00010354412,0.0004728635],"genre_scores_gemma":[0.9918817,0.000018441671,0.005252501,0.0016339514,0.00049328856,0.00018212078,0.00024188528,0.000032133485,0.0002639791],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981774,0.000044946937,0.0005219675,0.0003023644,0.0006709772,0.00028233885],"domain_scores_gemma":[0.9985218,0.0005036957,0.00018993084,0.00033827912,0.00015686774,0.00028943372],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005483518,0.00017651179,0.00050394493,0.000043345306,0.00006600959,0.000017108754,0.00014127974,0.00012562003,0.00015650684],"category_scores_gemma":[0.0011164751,0.00013251753,0.00020073022,0.00013741759,0.0002657839,0.000060190327,0.00002033653,0.00023667289,0.000033667202],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004948388,0.006617524,0.028252147,0.0016851613,0.00048370648,0.000012142882,0.00071370014,0.00022209744,0.1563624,0.015727358,0.022375729,0.7670532],"study_design_scores_gemma":[0.028079374,0.0022610237,0.048765887,0.0010152799,0.00059350306,0.000031630523,0.00016017532,0.81340873,0.05450326,0.00624503,0.044079952,0.0008561729],"about_ca_topic_score_codex":0.00024112183,"about_ca_topic_score_gemma":0.0000018480046,"teacher_disagreement_score":0.8131866,"about_ca_system_score_codex":0.00008725193,"about_ca_system_score_gemma":0.000320909,"threshold_uncertainty_score":0.5403908},"labels":[],"label_agreement":null},{"id":"W2022280107","doi":"10.1118/1.4866219","title":"Early prediction of tumor recurrence based on CT texture changes after stereotactic ablative radiotherapy (SABR) for lung cancer","year":2014,"lang":"en","type":"article","venue":"Medical Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":114,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Cancer Care Ontario; Western University","funders":"","keywords":"SABR volatility model; Ablative case; Radiation therapy; Radiosurgery; Medicine; Lung cancer; Radiology; Stereotactic radiotherapy; Medical imaging; Nuclear medicine; Medical physics; Oncology; Mathematics","score_opus":0.01026204065219425,"score_gpt":0.3007954426123658,"score_spread":0.2905334019601715,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2022280107","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44971272,0.00078172423,0.5312262,0.014568898,0.0013885642,0.0013288304,0.0001077467,0.00012710803,0.00075815845],"genre_scores_gemma":[0.9922053,0.00006412548,0.0007515535,0.005220963,0.0014008329,0.00017452193,0.000030338038,0.000041023675,0.00011133417],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99838686,0.00008366573,0.00024054295,0.00030963944,0.000704438,0.0002748822],"domain_scores_gemma":[0.9987767,0.00044598157,0.0001553857,0.00025287282,0.00010677369,0.00026233203],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000476663,0.00018235644,0.0004161436,0.00006049789,0.000053941363,0.000012255777,0.000121069155,0.000063236366,0.00019382745],"category_scores_gemma":[0.00070348085,0.00013990069,0.0001155196,0.00016654239,0.00023868491,0.000050230265,0.00001396021,0.00054563314,0.000001317391],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002185673,0.0011122888,0.18204129,0.0021261426,0.0005242195,0.000061849656,0.0017472648,0.00037822244,0.0014623915,0.00051785243,0.010931595,0.7969112],"study_design_scores_gemma":[0.0050519854,0.0015523556,0.047304668,0.0023513036,0.00025420962,0.000010765993,0.0000126539835,0.93103886,0.0017786517,0.00032328843,0.01008554,0.00023572205],"about_ca_topic_score_codex":0.000044471588,"about_ca_topic_score_gemma":0.0000022799734,"teacher_disagreement_score":0.93066067,"about_ca_system_score_codex":0.00008827183,"about_ca_system_score_gemma":0.00015107299,"threshold_uncertainty_score":0.57049847},"labels":[],"label_agreement":null},{"id":"W2027556349","doi":"10.1007/s11548-006-0044-6","title":"Model for defining and reporting reference-based validation protocols in medical image processing","year":2006,"lang":"en","type":"article","venue":"International Journal of Computer Assisted Radiology and Surgery","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":62,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Montreal Neurological Institute and Hospital","funders":"","keywords":"Computer science; Standardization; Terminology; Image processing; Segmentation; Reference model; Process (computing); Image registration; Data mining; Checklist; Data validation; Information retrieval; Artificial intelligence; Image (mathematics); Software engineering; Database","score_opus":0.05690473528402875,"score_gpt":0.3747669587707829,"score_spread":0.3178622234867542,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2027556349","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6143396,0.00015441104,0.38018036,0.004761156,0.00014465605,0.00033498125,0.0000010105379,0.000010522766,0.00007329908],"genre_scores_gemma":[0.9395357,0.0000152363245,0.059284776,0.0007315986,0.00033622043,0.000049556274,0.0000289783,0.0000091934,0.000008759961],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99828744,0.000074128926,0.001099279,0.00014090049,0.00027036984,0.00012789718],"domain_scores_gemma":[0.9980549,0.000588238,0.0009456593,0.000040409584,0.00029140836,0.00007937732],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022636782,0.0000878185,0.00040575318,0.0003155841,0.00004254425,0.000046378693,0.00006497149,0.0001060348,0.0000043001423],"category_scores_gemma":[0.001124239,0.00006970064,0.00007417363,0.00005064172,0.00010415534,0.0001103005,0.000018497776,0.00033912482,7.39424e-8],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008509094,0.00023336626,0.66580194,0.00022327442,0.000106448635,0.0011755481,0.000121630896,0.0033303131,0.0014035936,0.00046069248,0.0017411567,0.3245511],"study_design_scores_gemma":[0.0015186024,0.00005845872,0.15064988,0.00093256525,0.000019806568,0.004285171,0.000005589727,0.8413724,0.00005646585,0.00067131576,0.00035661308,0.00007313965],"about_ca_topic_score_codex":0.000006739933,"about_ca_topic_score_gemma":0.0000013708009,"teacher_disagreement_score":0.8380421,"about_ca_system_score_codex":0.000039120365,"about_ca_system_score_gemma":0.00036243585,"threshold_uncertainty_score":0.28423098},"labels":[],"label_agreement":null},{"id":"W2029315206","doi":"10.1118/1.4736292","title":"TH‐C‐213AB‐03: Bayesian Network Framework for Biophysical Radiation Pneumonitis Modeling","year":2012,"lang":"en","type":"article","venue":"Medical Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Logistic regression; Biomarker; Radiation Pneumonitis; Radiation therapy; Medicine; Artificial intelligence; Nuclear medicine; Machine learning; Internal medicine; Computer science; Biology","score_opus":0.016878886966712817,"score_gpt":0.312957968022047,"score_spread":0.2960790810553342,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2029315206","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03683336,0.00047906165,0.95306456,0.006905127,0.0012635445,0.00038670015,0.000004700778,0.0001645746,0.00089834334],"genre_scores_gemma":[0.9604183,0.0001343167,0.01847746,0.004605058,0.016041366,0.00006326442,0.00011248431,0.00007894253,0.00006881175],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975518,0.00006228362,0.00039171457,0.0003153524,0.0008377039,0.00084114587],"domain_scores_gemma":[0.99808234,0.0004900847,0.000102093894,0.00032630478,0.0000728021,0.00092638633],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007030644,0.00023999347,0.00050078647,0.000036209203,0.00021790956,0.000032195036,0.00018026703,0.0002721262,0.00012827785],"category_scores_gemma":[0.0014462391,0.00020981119,0.00025544834,0.00028767035,0.00018634931,0.00015942937,0.00006592037,0.0010465755,0.00006554044],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022240271,0.0013318906,0.029456643,0.00048272384,0.00036858217,0.000042515992,0.0011432513,0.003483413,0.00043771102,0.12075825,0.014510283,0.8277623],"study_design_scores_gemma":[0.0014634599,0.00019143848,0.0012314171,0.00052665366,0.00024413958,0.000042597716,0.000034838227,0.9285238,0.00027883484,0.05882699,0.008261411,0.00037444165],"about_ca_topic_score_codex":0.000016955664,"about_ca_topic_score_gemma":1.9486167e-7,"teacher_disagreement_score":0.9345871,"about_ca_system_score_codex":0.00008333859,"about_ca_system_score_gemma":0.00014361698,"threshold_uncertainty_score":0.85558516},"labels":[],"label_agreement":null},{"id":"W2031120760","doi":"10.1093/neuonc/nou253.4","title":"ED-04 * SURVIVAL RATES AMONG CANADIAN PATIENTS WITH PRIMARY MALIGNANT BRAIN TUMOURS: AN ANALYSIS BASED ON STATISTICS CANADA DATA, 1992-2010","year":2014,"lang":"en","type":"article","venue":"Neuro-Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Medicine; Cancer registry; Survival analysis; Demography; Proportional hazards model; Population; Confidence interval; Brain tumor; Brain cancer; Cancer; Pathology; Internal medicine; Environmental health","score_opus":0.008608183512767128,"score_gpt":0.264361654253417,"score_spread":0.25575347074064986,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2031120760","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9762813,0.000010375793,0.0060111224,0.012893243,0.0011503834,0.0005326115,0.00095053326,0.00005907915,0.0021113707],"genre_scores_gemma":[0.9639786,0.0000037021023,0.0032766638,0.02599837,0.0002495647,0.000010597615,0.0063683772,0.000059829184,0.00005430831],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9972666,0.00055934204,0.00035718858,0.0006573207,0.00055849546,0.0006010664],"domain_scores_gemma":[0.99663895,0.0011325105,0.00020106457,0.00088749774,0.00014143669,0.0009985144],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007353685,0.00025753982,0.00068034214,0.00031979382,0.00017404403,0.000037266796,0.00038669567,0.000112813155,0.00014380612],"category_scores_gemma":[0.0014787791,0.00020711079,0.000034231714,0.00037161724,0.0002014749,0.00007752967,0.0000557528,0.00071646454,0.0000048877428],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017870811,0.00019810055,0.93565273,0.000031538468,0.00012130921,0.00059761305,0.000038826656,0.0020807765,0.00021672767,0.000052872143,0.049099404,0.011731407],"study_design_scores_gemma":[0.0020999254,0.0013088289,0.7332459,0.000023642693,0.00052620785,0.000007810983,0.000027064858,0.19206375,0.000017378708,0.0000045064676,0.070453435,0.0002215384],"about_ca_topic_score_codex":0.9027543,"about_ca_topic_score_gemma":0.9778984,"teacher_disagreement_score":0.20240681,"about_ca_system_score_codex":0.0005910582,"about_ca_system_score_gemma":0.0035976982,"threshold_uncertainty_score":0.84457326},"labels":[],"label_agreement":null},{"id":"W2032152347","doi":"10.1155/2000/461695","title":"Specific Changes of Chromatin Structure in Nuclei of Normal Epithelium Adjacent to Laryngeal Squamous Cell Carcinoma","year":2000,"lang":"en","type":"article","venue":"Analytical Cellular Pathology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency","funders":"","keywords":"Epithelium; Pathology; Texture (cosmology); Medicine; Chemistry; Biology; Artificial intelligence","score_opus":0.00866495460927775,"score_gpt":0.2413037708365576,"score_spread":0.23263881622727986,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2032152347","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99315876,0.0005595343,0.00023549773,0.0018006625,0.000077860524,0.000226286,0.00001972934,0.000013826865,0.0039078183],"genre_scores_gemma":[0.99689955,0.000042844447,0.0018767994,0.000513057,0.0001456064,0.000002753132,0.000037082522,0.000027666007,0.00045464595],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9983784,0.00013362919,0.00047824995,0.0003375004,0.0002724733,0.0003997226],"domain_scores_gemma":[0.9991836,0.0000879512,0.00008729418,0.00036196428,0.000054076307,0.00022512741],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00030765246,0.00017786249,0.0006546087,0.00024687752,0.000021869175,0.000004145913,0.00016808714,0.00016663101,0.0021374258],"category_scores_gemma":[0.00009036693,0.00015351006,0.000108434324,0.00032210385,0.00021005758,0.000019485527,0.000056221685,0.00044786825,0.000034142242],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006089896,0.00086562266,0.09565416,0.000621625,0.000027224844,0.003341439,0.0020992896,0.0007961833,0.8637397,0.00060571235,0.0011574888,0.030482523],"study_design_scores_gemma":[0.009804482,0.0057266573,0.51219195,0.0002479173,0.00045659105,0.00084332266,0.00054426887,0.058256954,0.39226553,0.00043215763,0.01830976,0.00092042313],"about_ca_topic_score_codex":0.00010165182,"about_ca_topic_score_gemma":0.000017125329,"teacher_disagreement_score":0.4714742,"about_ca_system_score_codex":0.000040150895,"about_ca_system_score_gemma":0.00004490053,"threshold_uncertainty_score":0.99877477},"labels":[],"label_agreement":null},{"id":"W2034002253","doi":"10.1118/1.2031046","title":"Sci‐AM1 Sat ‐ 05: Fractal and motion modeling of PET/CT tumours","year":2005,"lang":"en","type":"article","venue":"Medical Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; Sunnybrook Health Science Centre","funders":"","keywords":"Computer vision; Scanner; Image resolution; Partial volume; Fractal; Interpolation (computer graphics); Pixel; Volume (thermodynamics); Artificial intelligence; Curvature; Nuclear medicine; Fractal analysis; Computer science; Physics; Fractal dimension; Motion (physics); Mathematics; Medicine; Geometry","score_opus":0.011530162100276247,"score_gpt":0.2879967505953875,"score_spread":0.27646658849511124,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2034002253","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8920582,0.00028616434,0.096485354,0.009188628,0.00015664162,0.00011091573,0.0000019574006,0.000054586515,0.0016575779],"genre_scores_gemma":[0.99557906,0.00010319655,0.0018763301,0.0013896349,0.0008968747,0.0000027161248,0.000025868247,0.000024330073,0.00010199778],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99848455,0.000030819585,0.00028877248,0.00022579821,0.0007349029,0.00023513638],"domain_scores_gemma":[0.9992593,0.000084387604,0.000072505965,0.00016483203,0.000057084548,0.00036187356],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045219556,0.00012763625,0.00032630347,0.00004496047,0.00006203515,0.000011111726,0.00009080506,0.000021063966,0.00011370465],"category_scores_gemma":[0.00063263363,0.00010706052,0.000083252846,0.000118328586,0.0002733933,0.0001215453,0.000061975705,0.00061286095,0.00001548077],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010750534,0.00094605103,0.021023255,0.00049157446,0.00014510956,0.000775276,0.0005470472,0.0035928322,0.0015793109,0.002793836,0.0038595488,0.9641386],"study_design_scores_gemma":[0.0013963932,0.00008921044,0.00092238514,0.0002835021,0.00009325656,0.00056167005,0.00003774323,0.9931907,0.00057281245,0.0016381962,0.0010872793,0.0001268701],"about_ca_topic_score_codex":0.000037652662,"about_ca_topic_score_gemma":0.0000013127982,"teacher_disagreement_score":0.98959786,"about_ca_system_score_codex":0.00003592937,"about_ca_system_score_gemma":0.00009632747,"threshold_uncertainty_score":0.43658012},"labels":[],"label_agreement":null},{"id":"W2035111150","doi":"10.1016/j.ijrobp.2008.06.198","title":"Automatic Definition of Radiation Targets using Textural Characteristics of Co-registered PET-CT Images","year":2008,"lang":"en","type":"article","venue":"International Journal of Radiation Oncology*Biology*Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Voxel; Medicine; Artificial intelligence; Segmentation; Radiation oncologist; Nuclear medicine; Pattern recognition (psychology); Radiation therapy; PET-CT; Head and neck; Histogram; Positron emission tomography; Radiology; Computer science; Image (mathematics)","score_opus":0.03200373640058233,"score_gpt":0.34975798374590433,"score_spread":0.317754247345322,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2035111150","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97570324,0.00035039103,0.020953102,0.0010146572,0.0013156185,0.00016333167,0.00007066223,0.00002344628,0.00040558033],"genre_scores_gemma":[0.98218477,0.00074975914,0.015362366,0.00037219777,0.0010657983,0.00000228731,0.00022233873,0.000026608881,0.000013887781],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9977691,0.00022452448,0.0012464848,0.00016870831,0.00040212038,0.00018907142],"domain_scores_gemma":[0.9960006,0.0004022015,0.0026212006,0.00014675474,0.00071219285,0.000117067764],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006213659,0.00018009578,0.00071183866,0.00027123324,0.00007291422,0.000010731838,0.00025028735,0.00007206852,0.00008262249],"category_scores_gemma":[0.0011870849,0.00016389381,0.0002660175,0.00014427022,0.00047276582,0.00024996357,0.000032727465,0.0004850263,0.0000061398373],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004286371,0.00083723257,0.6600496,0.00012493988,0.0009586253,0.0004199338,0.00079455285,0.00040957116,0.06611876,0.0032212446,0.001146528,0.26549032],"study_design_scores_gemma":[0.01996608,0.0031697561,0.73878086,0.0008729859,0.0009615933,0.015738519,0.0002344508,0.16698626,0.03655834,0.009544462,0.0064854105,0.0007013097],"about_ca_topic_score_codex":0.000030421066,"about_ca_topic_score_gemma":2.1747083e-7,"teacher_disagreement_score":0.26478902,"about_ca_system_score_codex":0.0003912401,"about_ca_system_score_gemma":0.00056249957,"threshold_uncertainty_score":0.66833955},"labels":[],"label_agreement":null},{"id":"W2036075041","doi":"10.1080/00207160310001650035","title":"MPI-implementation of PFI-code for numerical modeling of the anatomy of breast cancer","year":2004,"lang":"en","type":"article","venue":"International Journal of Computer Mathematics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"McMaster University","keywords":"Breast cancer; Code (set theory); Mathematics; Computer science; Medicine; Calculus (dental); Cancer; Internal medicine; Programming language; Orthodontics","score_opus":0.017910437227818134,"score_gpt":0.37604335360596725,"score_spread":0.3581329163781491,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2036075041","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39900905,0.00003532776,0.59712446,0.0034247967,0.00028754224,0.000079550206,0.000021151523,0.00000164284,0.000016500753],"genre_scores_gemma":[0.8790931,0.000024518717,0.12050183,0.00014328162,0.00022247463,0.0000011569816,0.0000015038355,0.000008862366,0.0000032573885],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99867535,0.000011915797,0.00069878984,0.000048518195,0.0004998538,0.0000655594],"domain_scores_gemma":[0.9983087,0.00007798365,0.0007378036,0.00007897854,0.0007595874,0.00003690536],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027555772,0.00006328036,0.00026924248,0.00010056568,0.000011585855,0.0000062124514,0.00024096474,0.000022605604,0.000019757214],"category_scores_gemma":[0.000046114204,0.000041604308,0.00018306127,0.00006338973,0.000042877986,0.000054994092,0.000041180745,0.00012369754,9.178507e-8],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00055829104,0.0022984475,0.028862184,0.0019358973,0.0034513548,0.000029862567,0.012346663,0.76547915,0.019478371,0.047270045,0.0011425647,0.1171472],"study_design_scores_gemma":[0.0042972886,0.00019651584,0.0055796453,0.0018598177,0.00022525183,0.00061146566,0.00030970693,0.966632,0.0063424143,0.013710473,0.00015753342,0.00007786498],"about_ca_topic_score_codex":0.000033414704,"about_ca_topic_score_gemma":0.0000016019436,"teacher_disagreement_score":0.48008406,"about_ca_system_score_codex":0.000059230006,"about_ca_system_score_gemma":0.00017672677,"threshold_uncertainty_score":0.16965745},"labels":[],"label_agreement":null},{"id":"W2038858587","doi":"10.2350/07-06-0303.1","title":"Pathologist Interobserver Variability of Histologic Features in Childhood Brain Tumors: Results from the CCG-945 Study","year":2008,"lang":"en","type":"article","venue":"Pediatric and Developmental Pathology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":54,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hospital for Sick Children","funders":"","keywords":"Pathology; Medicine","score_opus":0.014493931814448168,"score_gpt":0.2557826704509446,"score_spread":0.24128873863649644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2038858587","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9962163,0.0007039246,0.0000796388,0.0018137846,0.00015409407,0.0004135508,0.000022257025,0.000032156026,0.0005643121],"genre_scores_gemma":[0.9948429,0.00018220676,0.00349029,0.0011671679,0.00013087761,0.000018386714,0.000059193233,0.000011797873,0.00009720981],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9980859,0.00038880965,0.0006030968,0.00048460075,0.00018699023,0.00025059204],"domain_scores_gemma":[0.9985428,0.0009389016,0.00017116648,0.00022832071,0.000033730463,0.00008508984],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012880903,0.0001832359,0.0004802017,0.000101398386,0.00011549417,0.0000058661976,0.00016827688,0.0001166467,0.000026659493],"category_scores_gemma":[0.0035536403,0.000119478056,0.00005142194,0.00024515335,0.00034977542,0.000039305298,0.00020227632,0.00059673056,0.000005939307],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019023583,0.0006030888,0.9854545,0.000012252298,0.000013796521,0.0009747869,0.008831416,0.0000029271453,0.000094420706,0.000010454774,0.0019746686,0.001837429],"study_design_scores_gemma":[0.0032460524,0.0002859014,0.99405503,0.0000134704505,0.000035529036,0.00088390434,0.0009924326,0.000019838451,0.000009270713,0.00023765792,0.00010321604,0.00011769598],"about_ca_topic_score_codex":0.00041917476,"about_ca_topic_score_gemma":0.00003447325,"teacher_disagreement_score":0.008600507,"about_ca_system_score_codex":0.000064156215,"about_ca_system_score_gemma":0.0001513037,"threshold_uncertainty_score":0.4872174},"labels":[],"label_agreement":null},{"id":"W2039112550","doi":"10.1016/j.acra.2014.09.001","title":"Methods and Challenges in Quantitative Imaging Biomarker Development","year":2014,"lang":"en","type":"review","venue":"Academic Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":95,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Institute of Biomedical Imaging and Bioengineering; National Cancer Institute","keywords":"Biomarker; Alliance; Medicine; Imaging biomarker; Field (mathematics); Radiomics; Task (project management); Task force; Biomarker discovery; Engineering ethics; Medical physics; Data science; Radiology; Computer science; Political science; Magnetic resonance imaging; Engineering; Systems engineering","score_opus":0.16747503555272222,"score_gpt":0.4854903350973562,"score_spread":0.3180152995446339,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2039112550","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000029701614,0.99324346,0.0019675312,0.0024909752,0.00033004783,0.00046528864,7.9290925e-7,0.00005011016,0.0014220777],"genre_scores_gemma":[0.0000055787227,0.9426759,0.05646245,0.0004128188,0.00015752118,0.000090582624,0.000038879232,0.00006702118,0.00008927732],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99629927,0.0013084154,0.0010043414,0.00075747457,0.00012539483,0.0005051014],"domain_scores_gemma":[0.997209,0.0019368232,0.0003643561,0.0002579849,0.000024339572,0.00020750276],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0040446827,0.0004377845,0.002723509,0.0014045066,0.00005125542,0.000006394835,0.00022808289,0.00066223496,0.000017365244],"category_scores_gemma":[0.0019710485,0.00033044053,0.00014896918,0.00038080532,0.00033252273,0.000039460647,0.0001474237,0.0024897323,0.000023769137],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008557637,0.000008493868,0.00015483556,0.00741247,0.00014668985,0.000058450798,0.00037410692,1.3392228e-7,0.0000068218674,0.0013875331,0.0003909251,0.990051],"study_design_scores_gemma":[0.00044982746,0.000029157602,0.00038678927,0.00821013,0.00028543384,0.0025384114,0.00005507008,0.0007916746,5.0520646e-7,0.00019241968,0.9867619,0.00029864837],"about_ca_topic_score_codex":0.000011978643,"about_ca_topic_score_gemma":9.636565e-7,"teacher_disagreement_score":0.98975235,"about_ca_system_score_codex":0.00013335215,"about_ca_system_score_gemma":0.00023209421,"threshold_uncertainty_score":0.99991477},"labels":[],"label_agreement":null},{"id":"W2039159729","doi":"10.1136/bmj.323.7310.453","title":"Synchronous chemoradiation for squamous carcinomas","year":2001,"lang":"en","type":"article","venue":"BMJ","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Victoria Hospital; University of Victoria","funders":"","keywords":"Medicine; Oncology; Internal medicine","score_opus":0.01654569893933075,"score_gpt":0.31632430521530275,"score_spread":0.29977860627597197,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2039159729","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91444147,0.00047323736,0.026744634,0.034811374,0.0004924868,0.0009559697,0.000002387878,0.0001426864,0.021935733],"genre_scores_gemma":[0.98847175,0.000015229515,0.0060494673,0.001691624,0.0011259856,0.000049929782,0.00003510972,0.000020344918,0.002540563],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993942,0.00001027299,0.00015529021,0.00014097574,0.000120277546,0.00017902719],"domain_scores_gemma":[0.9995693,0.00007453024,0.00004940564,0.00015628476,0.000042499814,0.00010798963],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024723884,0.000069644404,0.00014987275,0.000048491547,0.000056385492,0.000012313643,0.00004239551,0.000044277862,0.00007715769],"category_scores_gemma":[0.0005947895,0.0000610491,0.000065618704,0.00007207853,0.000026952173,0.000028619725,0.000009386369,0.00011144281,0.000029745948],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005775008,0.00036671432,0.25639886,0.0004000051,0.000105807565,0.00041197706,0.0007754324,0.0004999988,0.009919561,0.0019152869,0.24597414,0.48265472],"study_design_scores_gemma":[0.0065857945,0.000569009,0.17792532,0.000082084916,0.00019674815,0.0012346057,0.00011624681,0.22133957,0.0008225281,0.00057329447,0.59023494,0.00031988646],"about_ca_topic_score_codex":0.000046464313,"about_ca_topic_score_gemma":0.000001683323,"teacher_disagreement_score":0.48233482,"about_ca_system_score_codex":0.000057900023,"about_ca_system_score_gemma":0.0000655114,"threshold_uncertainty_score":0.24895099},"labels":[],"label_agreement":null},{"id":"W2039470741","doi":"10.1118/1.3613482","title":"TH‐A‐220‐04: MVCT Noise Reduction and Feature Enhancement for Target Delineation","year":2011,"lang":"en","type":"article","venue":"Medical Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"London Health Sciences Centre","funders":"","keywords":"Tomotherapy; Contouring; Contrast-to-noise ratio; Feature (linguistics); Nuclear medicine; Medicine; Standard deviation; Artificial intelligence; Computer science; Mathematics; Image quality; Radiation therapy; Radiology; Image (mathematics); Statistics","score_opus":0.01768190281218959,"score_gpt":0.2933248571359975,"score_spread":0.2756429543238079,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2039470741","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12972416,0.00045557535,0.85658514,0.0099375695,0.00076412753,0.0005731212,0.000004627338,0.0000898482,0.001865805],"genre_scores_gemma":[0.9654794,0.00025575355,0.027826399,0.0023184165,0.0023138693,0.00006605803,0.00017473241,0.000038403872,0.0015269942],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99889475,0.000022927976,0.00019134003,0.00025916073,0.00040896639,0.0002228483],"domain_scores_gemma":[0.99934393,0.00004217045,0.00007145943,0.0001578745,0.00009430851,0.00029026403],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038354896,0.00012852176,0.00023527107,0.000029351548,0.00009296508,0.000010537446,0.00006719499,0.0001148404,0.00015170229],"category_scores_gemma":[0.00045367732,0.00010259779,0.00006927994,0.00009250824,0.00017180399,0.000068837035,0.000031353855,0.00038417196,0.000009241726],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000481843,0.00081612956,0.0047973804,0.0005013117,0.00018772786,0.000031528743,0.0024910206,0.0000070259794,0.010846281,0.0027796335,0.052550055,0.92451006],"study_design_scores_gemma":[0.025296472,0.004731751,0.02225725,0.0024918285,0.0016293632,0.0006540091,0.0009841074,0.33000278,0.2323667,0.05608001,0.3213835,0.0021222208],"about_ca_topic_score_codex":0.00002119862,"about_ca_topic_score_gemma":3.3839547e-7,"teacher_disagreement_score":0.92238784,"about_ca_system_score_codex":0.000035586287,"about_ca_system_score_gemma":0.00008666172,"threshold_uncertainty_score":0.41838163},"labels":[],"label_agreement":null},{"id":"W2040101654","doi":"10.1118/1.3476110","title":"Poster — Thur Eve — 05: Semi‐Automated Segmentation of Lung Tumours on CT Scans Using Level Set Sparse Field Active Model","year":2010,"lang":"en","type":"article","venue":"Medical Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; Robarts Clinical Trials","funders":"","keywords":"Thresholding; Segmentation; Active contour model; Artificial intelligence; Image segmentation; Pattern recognition (psychology); Computer science; Standard deviation; Level set (data structures); Nuclear medicine; Computer vision; Mathematics; Medicine; Image (mathematics); Statistics","score_opus":0.03206057481821158,"score_gpt":0.34801622525438086,"score_spread":0.3159556504361693,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2040101654","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9717742,0.0000071257464,0.023568735,0.0024538457,0.000382275,0.00024561601,0.000025538446,0.0001013438,0.0014412971],"genre_scores_gemma":[0.99449354,0.0000076231286,0.0006680995,0.004163505,0.00041975913,0.0000062905424,0.0000800886,0.000039010105,0.00012205357],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982056,0.00004734501,0.00031343437,0.00027960376,0.00086411595,0.00028987223],"domain_scores_gemma":[0.998963,0.000192414,0.00015651148,0.00026757197,0.0001046849,0.0003158366],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032037075,0.00018863055,0.00035950687,0.00006569597,0.000074777075,0.0000130499075,0.00014895668,0.00011375221,0.00014219458],"category_scores_gemma":[0.0007041622,0.0001591791,0.00010228218,0.00018496953,0.00019986383,0.00008074469,0.00006155421,0.0010833396,0.00000795799],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021568458,0.0039099264,0.14234874,0.001679068,0.0013165252,0.0010551441,0.010008603,0.016674558,0.53658557,0.002031086,0.11148765,0.1707463],"study_design_scores_gemma":[0.0016659297,0.0001343007,0.0040362673,0.00038249666,0.00015384272,0.00007946476,0.00004711571,0.9421347,0.050855923,0.0003004972,0.00003224842,0.00017721172],"about_ca_topic_score_codex":0.00009926649,"about_ca_topic_score_gemma":0.0000044146122,"teacher_disagreement_score":0.92546016,"about_ca_system_score_codex":0.000058488906,"about_ca_system_score_gemma":0.0003373868,"threshold_uncertainty_score":0.6491135},"labels":[],"label_agreement":null},{"id":"W2041112729","doi":"10.1016/j.radonc.2011.10.014","title":"Combined PET/CT image characteristics for radiotherapy tumor response in lung cancer","year":2011,"lang":"en","type":"article","venue":"Radiotherapy and Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":199,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Canadian Institutes of Health Research; Foundation for Barnes-Jewish Hospital","keywords":"Medicine; Logistic regression; Radiation therapy; Lung cancer; Correlation; Univariate analysis; Cancer; Histogram; Nuclear medicine; Univariate; Feature (linguistics); Radiology; Multivariate analysis; Multivariate statistics; Internal medicine; Mathematics; Computer science; Artificial intelligence; Statistics; Image (mathematics)","score_opus":0.015445068404891406,"score_gpt":0.3421089100691341,"score_spread":0.32666384166424267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2041112729","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9848066,0.0025916563,0.0050928784,0.005896238,0.0004805065,0.0007782446,0.000013968167,0.000058076148,0.00028181254],"genre_scores_gemma":[0.9129558,0.0071015405,0.06347652,0.014263976,0.000630114,0.0003522241,0.000022539683,0.00012938694,0.0010678498],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9986005,0.0002045219,0.00037134727,0.00033459175,0.000098947494,0.00039008984],"domain_scores_gemma":[0.99902695,0.00039731845,0.00014050775,0.0001975564,0.00004778903,0.0001898529],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00093228254,0.00020133295,0.0006619751,0.00019360981,0.000084738735,0.000015907151,0.00010843135,0.00003375533,0.00042403166],"category_scores_gemma":[0.00019237181,0.0001731337,0.0000900304,0.00012518196,0.00023788131,0.00006435672,0.0000118294265,0.00037088137,7.872483e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.10927182,0.0023678925,0.4436555,0.00097434036,0.0009872514,0.009978279,0.010153562,0.000009032617,0.1980793,0.0021742876,0.01068,0.21166876],"study_design_scores_gemma":[0.04005816,0.008662869,0.5491047,0.00038876344,0.0002342948,0.004082956,0.00025160413,0.14319314,0.0013060617,0.0002979666,0.25159156,0.0008279091],"about_ca_topic_score_codex":0.00014334517,"about_ca_topic_score_gemma":0.000012011451,"teacher_disagreement_score":0.24091156,"about_ca_system_score_codex":0.00047771653,"about_ca_system_score_gemma":0.00028380274,"threshold_uncertainty_score":0.7060187},"labels":[],"label_agreement":null},{"id":"W2041154020","doi":"10.1158/0008-5472.sabcs10-p3-10-17","title":"Abstract P3-10-17: The Fractal Analysis of Tumor Histology Is an Independent Prognostic Factor in Breast Cancer Patients","year":2010,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Medicine; Breast cancer; Internal medicine; Oncology; Fractal dimension; Univariate; Proportional hazards model; Fractal analysis; Multivariate analysis; Lymph node; Univariate analysis; Fractal; Cancer; Pathology; Multivariate statistics; Mathematics; Statistics","score_opus":0.03363363490030733,"score_gpt":0.40242294624933694,"score_spread":0.3687893113490296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2041154020","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9941032,0.00016842304,0.0000038575618,0.004669564,0.00019443812,0.0003787452,0.00011659308,0.00001146025,0.00035372662],"genre_scores_gemma":[0.99883235,0.00006394589,0.000025040616,0.00041825915,0.00016949384,0.00011977706,0.000032862306,0.000022893075,0.00031535488],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9978204,0.000113232476,0.00033603096,0.0003679998,0.0008873118,0.0004750427],"domain_scores_gemma":[0.9985526,0.00026068793,0.00011622785,0.00038791168,0.000442081,0.0002404763],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007948957,0.00012557575,0.0003863079,0.00055708876,0.00009949393,0.000026192314,0.00033566024,0.00009889423,0.0074270032],"category_scores_gemma":[0.0004344324,0.00008372697,0.00010081008,0.0009005108,0.0004001581,0.000079959864,0.000087210865,0.0018095869,0.000009237605],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002062576,0.00034524885,0.96416694,0.000056491896,0.00023148373,0.000033611384,0.0009177088,0.00004110393,0.013534917,0.000009308177,0.0019615944,0.018495357],"study_design_scores_gemma":[0.0007648193,0.00009545984,0.992274,0.00006129195,0.00012435239,0.0000053957538,0.000095747186,0.0036607287,0.0003486525,0.000014309638,0.0024720202,0.000083242085],"about_ca_topic_score_codex":0.010308958,"about_ca_topic_score_gemma":0.0024038884,"teacher_disagreement_score":0.028107062,"about_ca_system_score_codex":0.00022316705,"about_ca_system_score_gemma":0.00053060515,"threshold_uncertainty_score":0.9962815},"labels":[],"label_agreement":null},{"id":"W2042282848","doi":"10.1016/j.ijrobp.2007.07.081","title":"A Multi-Institution Deformable Registration Accuracy Study2","year":2007,"lang":"en","type":"article","venue":"International Journal of Radiation Oncology*Biology*Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre","funders":"","keywords":"Medicine; DICOM; Voxel; Nuclear medicine; Prostate; Lung; Displacement (psychology); Image registration; Radiology; Image (mathematics); Artificial intelligence; Internal medicine; Computer science; Cancer","score_opus":0.02542659822357966,"score_gpt":0.3781612521467613,"score_spread":0.3527346539231816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2042282848","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4513005,0.0003909189,0.5378367,0.004418211,0.0034436602,0.00024652615,0.000007574526,0.000059060887,0.0022968652],"genre_scores_gemma":[0.9680224,0.0004382225,0.026068226,0.0017249953,0.0035397203,0.0000032567139,0.000072265604,0.0000203904,0.00011052267],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981984,0.00010063174,0.00089128065,0.00018800714,0.00036700536,0.00025467403],"domain_scores_gemma":[0.99740314,0.00034393824,0.001157123,0.00013714952,0.00077270827,0.00018594165],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018153706,0.00015962703,0.000366766,0.00021138939,0.000109186614,0.000035923782,0.00028010196,0.00019603019,0.000036340298],"category_scores_gemma":[0.0017910721,0.00013797151,0.00019472129,0.00017423161,0.00023609184,0.00043256348,0.00004121494,0.0007508156,0.000028068584],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00074174197,0.0009484199,0.30092338,0.000017406759,0.0005724847,0.00021262588,0.0007328332,0.0017505005,0.021131033,0.0132997865,0.0016936802,0.65797615],"study_design_scores_gemma":[0.037680745,0.0040483866,0.27827105,0.00041919545,0.00067434827,0.0042912397,0.00074151065,0.1432967,0.012419037,0.010585889,0.506764,0.00080792274],"about_ca_topic_score_codex":0.000032569056,"about_ca_topic_score_gemma":0.0000057727443,"teacher_disagreement_score":0.6571682,"about_ca_system_score_codex":0.0007720374,"about_ca_system_score_gemma":0.00057652075,"threshold_uncertainty_score":0.5626315},"labels":[],"label_agreement":null},{"id":"W2042539101","doi":"10.1118/1.4894887","title":"Sci—Thur AM: YIS ‐ 02: Radiogenomic Modeling of Normal Tissue Toxicities in Prostate Cancer Patients Receiving Hypofractionated Radiotherapy","year":2014,"lang":"en","type":"article","venue":"Medical Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre","funders":"","keywords":"Medicine; Radiation therapy; Radiogenomics; Single-nucleotide polymorphism; Receiver operating characteristic; Prostate cancer; SNP; Oncology; Internal medicine; Nuclear medicine; Cancer; Radiology; Genotype; Biology; Genetics","score_opus":0.008699202046843366,"score_gpt":0.28167979524987236,"score_spread":0.272980593203029,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2042539101","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9787514,0.0004169196,0.017234704,0.001995412,0.00047096118,0.00029736766,0.00000588288,0.00005367059,0.0007736659],"genre_scores_gemma":[0.99628794,0.0006353003,0.0006739619,0.0014634402,0.00065478944,0.000026089669,0.000046984587,0.000052342748,0.0001591474],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978268,0.000102207,0.0005478875,0.00031569882,0.0008124661,0.00039489692],"domain_scores_gemma":[0.99905574,0.00016879331,0.0001633607,0.0002119077,0.00012499896,0.0002752026],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00062277453,0.00020057935,0.0005514507,0.00012557404,0.000074505595,0.000015524449,0.00017436103,0.0001105495,0.000167244],"category_scores_gemma":[0.000636288,0.00017927619,0.00008250543,0.0002996094,0.00024980758,0.00016810367,0.000045338693,0.0007060969,0.0000057918874],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038365411,0.0008970108,0.174788,0.0005271992,0.0001902399,0.000031343807,0.0025463526,0.022721663,0.009563249,0.00024192092,0.0010918716,0.78701746],"study_design_scores_gemma":[0.0051817573,0.00033065822,0.01238503,0.0009315092,0.000059120117,0.000011133729,0.000046553316,0.9738354,0.004051676,0.0006676725,0.0021882167,0.00031126043],"about_ca_topic_score_codex":0.0005666226,"about_ca_topic_score_gemma":0.000012880808,"teacher_disagreement_score":0.95111376,"about_ca_system_score_codex":0.00019458187,"about_ca_system_score_gemma":0.00021319957,"threshold_uncertainty_score":0.73106706},"labels":[],"label_agreement":null},{"id":"W2043731110","doi":"10.1016/j.acra.2014.04.005","title":"Differentiation of Lipoma From Liposarcoma on MRI Using Texture and Shape Analysis","year":2014,"lang":"en","type":"article","venue":"Academic Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":51,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital","funders":"","keywords":"Liposarcoma; Lipoma; Medicine; Kappa; Radiology; Magnetic resonance imaging; Confidence interval; Linear discriminant analysis; Nuclear medicine; Pathology; Sarcoma; Artificial intelligence; Mathematics; Computer science; Internal medicine; Geometry","score_opus":0.012469419905813952,"score_gpt":0.29525365767791356,"score_spread":0.2827842377720996,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2043731110","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9849356,0.0008538977,0.011165032,0.0025394864,0.00012705638,0.00008806207,0.00000463135,0.000026751673,0.0002595256],"genre_scores_gemma":[0.99536425,0.00067022507,0.0020528934,0.0013569137,0.00042979914,0.0000019170725,0.0000709024,0.000014601801,0.00003848143],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99887663,0.00016796001,0.00032121528,0.00030222276,0.00014147742,0.00019048592],"domain_scores_gemma":[0.9990575,0.0004096175,0.00018225847,0.0002035847,0.000026241403,0.00012080063],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003075288,0.00013117926,0.0005503568,0.00052193116,0.00004635406,0.000003902108,0.000101826656,0.0003012284,0.00008527419],"category_scores_gemma":[0.00046102898,0.00010388486,0.000096589254,0.00039971116,0.00015470949,0.00002993241,0.000036267567,0.00074836623,0.0000029645132],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016376175,0.000045801706,0.80972064,0.000040537478,0.0010079682,0.000009629783,0.0005170953,0.0006384615,0.12243265,0.0018687147,0.00086452,0.06269025],"study_design_scores_gemma":[0.0008375717,0.00016597773,0.46518925,0.00006601296,0.000936569,0.000058985534,0.000019430376,0.52973264,0.00057833403,0.0008126659,0.0015053408,0.00009720046],"about_ca_topic_score_codex":0.00015413928,"about_ca_topic_score_gemma":0.0000018568757,"teacher_disagreement_score":0.5290942,"about_ca_system_score_codex":0.000022258164,"about_ca_system_score_gemma":0.000015225649,"threshold_uncertainty_score":0.42363015},"labels":[],"label_agreement":null},{"id":"W2044898010","doi":"10.1016/j.jalz.2010.05.143","title":"IC‐P‐128: Robust, Large‐Scale Intensity Standardization of ADNI MRI Dataset","year":2010,"lang":"en","type":"article","venue":"Alzheimer s & Dementia","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Standardization; Histogram; Artificial intelligence; Matching (statistics); Pattern recognition (psychology); Scanner; Computer science; Histogram matching; Percentile; Mathematics; Divergence (linguistics); Standard deviation; Intensity (physics); Nuclear medicine; Statistics; Image (mathematics); Medicine","score_opus":0.01413730709413762,"score_gpt":0.2896128905301862,"score_spread":0.27547558343604855,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2044898010","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38325804,0.022993324,0.5547774,0.019008167,0.0060579935,0.0019782644,0.0022869068,0.00044256568,0.00919736],"genre_scores_gemma":[0.9607236,0.0000687001,0.03528739,0.0014450282,0.00023601715,0.0000058396085,0.002186948,0.00003107767,0.000015392672],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99870586,0.000033792727,0.0003400403,0.0002817279,0.0003607941,0.00027778436],"domain_scores_gemma":[0.998992,0.000031660868,0.00014396253,0.00048393972,0.00016986889,0.00017851804],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006234506,0.0001439588,0.00031129172,0.00008966053,0.00009638686,0.000021506932,0.00015069167,0.00008969739,0.0010185353],"category_scores_gemma":[0.00014446733,0.00012696095,0.00007782426,0.00015119744,0.00013160118,0.00011395392,0.00012103663,0.0004969787,0.000035237725],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00054139,0.00102338,0.16621274,0.00011076799,0.014727713,0.00012615618,0.0014275891,0.00047069316,0.07977047,0.0019326117,0.6638713,0.06978519],"study_design_scores_gemma":[0.0030049828,0.00021500495,0.028418949,0.00007447843,0.014480327,0.00010426065,0.00018760587,0.022241531,0.03916424,0.00014599966,0.8916028,0.00035978985],"about_ca_topic_score_codex":0.000082009916,"about_ca_topic_score_gemma":0.00005980679,"teacher_disagreement_score":0.5774656,"about_ca_system_score_codex":0.0000025624513,"about_ca_system_score_gemma":0.00006940033,"threshold_uncertainty_score":0.9998947},"labels":[],"label_agreement":null},{"id":"W2047103489","doi":"10.1088/0031-9155/54/18/s02","title":"Predicting radiotherapy outcomes using statistical learning techniques","year":2009,"lang":"en","type":"article","venue":"Physics in Medicine and Biology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":79,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre","funders":"National Cancer Institute; National Institutes of Health","keywords":"Bivariate analysis; Computer science; Artificial intelligence; Support vector machine; Machine learning; Resampling; Nonlinear system; Logistic regression; Artificial neural network; Pattern recognition (psychology); Kernel (algebra); Mathematics","score_opus":0.10621752600679644,"score_gpt":0.44684293350871696,"score_spread":0.3406254075019205,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2047103489","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8436076,0.0011474073,0.14255251,0.010173794,0.00015589829,0.00027855966,0.0000014737648,0.00015060234,0.0019321442],"genre_scores_gemma":[0.96751744,0.00058892614,0.026942808,0.0041670697,0.0007050695,0.0000032046962,0.000024691579,0.00001514687,0.000035675184],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99897164,0.00009441637,0.0002916008,0.00026500816,0.00010012015,0.0002772008],"domain_scores_gemma":[0.9994059,0.00026741714,0.00007730564,0.00010903443,0.00003062541,0.000109682434],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048338718,0.0001549576,0.0005283153,0.00011219746,0.00007273838,0.0000063888665,0.00005583655,0.00009044398,0.00002478631],"category_scores_gemma":[0.0005147108,0.00010668231,0.000029940009,0.00015020647,0.00027711445,0.000036518748,0.00001835512,0.0006563638,4.3705006e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051790063,0.000078041674,0.682899,0.0000333288,0.000035966004,0.00003685925,0.00043321683,0.000028948629,0.039545365,0.008310848,0.000078095945,0.26846853],"study_design_scores_gemma":[0.0128563205,0.008890059,0.4525539,0.0018885573,0.00046383022,0.0008098875,0.0012633614,0.41653752,0.0017268569,0.078331016,0.023497088,0.0011816066],"about_ca_topic_score_codex":0.00014284118,"about_ca_topic_score_gemma":9.05931e-7,"teacher_disagreement_score":0.4165086,"about_ca_system_score_codex":0.000041006693,"about_ca_system_score_gemma":0.0000309839,"threshold_uncertainty_score":0.43503785},"labels":[],"label_agreement":null},{"id":"W2049151208","doi":"10.1117/12.912479","title":"Evaluating the dose effects of a longitudinal micro-CT study on pulmonary tissue in C57BL/6 mice","year":2012,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Robarts Clinical Trials; Western University","funders":"","keywords":"Nuclear medicine; Lung; Medicine; Radiation therapy; Irradiation; Animal study; Fibrosis; Radiology; Pathology; Surgery; Internal medicine","score_opus":0.01846407550122645,"score_gpt":0.3125193006650043,"score_spread":0.2940552251637778,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2049151208","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9944482,0.00034397264,0.000010177679,0.0024779174,0.00030584473,0.0013070767,0.0000051430957,0.00003655815,0.0010651271],"genre_scores_gemma":[0.97997695,0.000041772222,0.018986136,0.00015074367,0.00049510587,0.0001591157,0.0000036288868,0.00005713935,0.00012940988],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99742573,1.201826e-7,0.0007682865,0.0003493538,0.00097422977,0.00048230262],"domain_scores_gemma":[0.9981312,0.0005763335,0.00040961517,0.00008907043,0.0006405099,0.0001532756],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002103922,0.00031422623,0.00057439046,0.00014719853,0.00007870621,0.000041265823,0.00063332863,0.00009455569,0.000007813027],"category_scores_gemma":[0.0023600976,0.00021471093,0.00040356937,0.00040836414,0.00024054019,0.0002690012,0.00017928897,0.00072166143,0.0000016618309],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035835852,0.0012630856,0.035802435,0.0013267717,0.0005268203,0.0000015656408,0.0010778139,0.00010435348,0.9303345,0.026320359,0.00046321325,0.0024206943],"study_design_scores_gemma":[0.011197983,0.0071112374,0.3997014,0.0050512934,0.0018633091,0.00043887258,0.00834979,0.088607356,0.4737911,0.00079952314,0.0019420536,0.0011461026],"about_ca_topic_score_codex":0.00003922447,"about_ca_topic_score_gemma":8.612514e-8,"teacher_disagreement_score":0.45654345,"about_ca_system_score_codex":0.00017622474,"about_ca_system_score_gemma":0.000039761646,"threshold_uncertainty_score":0.87556577},"labels":[],"label_agreement":null},{"id":"W2052507258","doi":"10.1371/journal.pone.0102107","title":"Robust Radiomics Feature Quantification Using Semiautomatic Volumetric Segmentation","year":2014,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":603,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University Health Network; Princess Margaret Cancer Centre","funders":"Interreg; National Institutes of Health; National Cancer Institute; KWF Kankerbestrijding; National Center for Research Resources; Center for Translational Molecular Medicine; National Institute of Biomedical Imaging and Bioengineering; Health Foundation Limburg","keywords":"Radiomics; Contouring; Segmentation; Artificial intelligence; Computer science; Pattern recognition (psychology); Robustness (evolution); Medical imaging; Reproducibility; Feature extraction; Feature (linguistics); Computer vision; Mathematics; Statistics","score_opus":0.0569063703711607,"score_gpt":0.27948756990050494,"score_spread":0.22258119952934424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2052507258","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9025783,0.0001856955,0.094111875,0.002084063,0.000092022594,0.00031626783,0.000001264325,0.00013923913,0.00049129897],"genre_scores_gemma":[0.77716833,0.000057428995,0.22098963,0.0006534694,0.00037499986,0.00000954713,0.0000916548,0.000039283255,0.00061562954],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988562,0.000074215866,0.0002203393,0.00023429496,0.00041752605,0.00019745632],"domain_scores_gemma":[0.9992562,0.00010276055,0.00013928559,0.00027099758,0.000095646035,0.00013511928],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046609773,0.00011879377,0.00028772312,0.00024164825,0.000110919376,0.00004789278,0.000078414174,0.00009124251,0.000045422952],"category_scores_gemma":[0.0009428448,0.000111964844,0.000050620318,0.00044370277,0.00004638958,0.000092183516,0.000018359087,0.00034544192,0.00003924095],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005035181,0.0011868308,0.059033126,0.0009995732,0.00036859597,0.000008543232,0.00035522625,0.0020520252,0.9037522,0.00028670265,0.0014781128,0.030428723],"study_design_scores_gemma":[0.00092865346,0.00007803387,0.009885264,0.0003731802,0.0004658441,0.00002663197,0.00003819381,0.97512263,0.012759998,0.00005590884,0.00013743134,0.00012820419],"about_ca_topic_score_codex":0.000023472641,"about_ca_topic_score_gemma":5.814726e-7,"teacher_disagreement_score":0.9730706,"about_ca_system_score_codex":0.0001346879,"about_ca_system_score_gemma":0.00004079243,"threshold_uncertainty_score":0.45657936},"labels":[],"label_agreement":null},{"id":"W2054516549","doi":"10.1155/2013/980769","title":"Automatic Segmentation of Lung Carcinoma Using 3D Texture Features in 18-FDG PET/CT","year":2013,"lang":"en","type":"article","venue":"International Journal of Molecular Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; Sunnybrook Health Science Centre; Health Sciences Centre; McGill University","funders":"","keywords":"Artificial intelligence; Voxel; Segmentation; Ground truth; Positron emission tomography; Thresholding; Pattern recognition (psychology); Medicine; Hounsfield scale; Sørensen–Dice coefficient; Nuclear medicine; Computer science; Image segmentation; Radiology; Computed tomography; Image (mathematics)","score_opus":0.005692390877067885,"score_gpt":0.305973318859074,"score_spread":0.30028092798200606,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2054516549","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9822947,0.00091389415,0.012604562,0.0031587475,0.00040712324,0.00013582145,0.0000010527857,0.000007929087,0.00047621614],"genre_scores_gemma":[0.97407967,0.000018801587,0.024790056,0.0009330309,0.00012847304,0.0000016928617,0.0000064812793,0.000021153845,0.000020616686],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984589,0.00007080963,0.00054790423,0.000115659976,0.0006549445,0.00015178761],"domain_scores_gemma":[0.99893945,0.000055513658,0.00042275904,0.000095264775,0.0003951324,0.00009188778],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033578166,0.00011942768,0.0002639894,0.00047382904,0.000019534353,0.00005877111,0.00020597159,0.000009210592,0.0002322867],"category_scores_gemma":[0.00033223585,0.00010287471,0.0001353187,0.00012200821,0.000058635163,0.00024329724,0.000046747697,0.00043797606,0.0000019304637],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000056947516,0.0002010102,0.36997676,0.0001516566,0.0003253427,0.009326479,0.0005000612,0.0033245052,0.5169245,0.00008436907,0.0015280843,0.097600274],"study_design_scores_gemma":[0.0043992284,0.00007012236,0.21289337,0.0017788084,0.0002086839,0.02889114,0.0005454542,0.72265494,0.027659183,0.00050337875,0.00015996808,0.00023570754],"about_ca_topic_score_codex":0.00024267187,"about_ca_topic_score_gemma":7.2314214e-7,"teacher_disagreement_score":0.71933043,"about_ca_system_score_codex":0.00019899108,"about_ca_system_score_gemma":0.00013044993,"threshold_uncertainty_score":0.41951087},"labels":[],"label_agreement":null},{"id":"W2054955059","doi":"10.1016/j.jocd.2014.07.004","title":"A Trimodality Comparison of Volumetric Bone Imaging Technologies. Part II: 1-Yr Change, Long-Term Precision, and Least Significant Change","year":2014,"lang":"en","type":"article","venue":"Journal of Clinical Densitometry","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hamilton Health Sciences; Osteoporosis Canada; University Health Network; McMaster University","funders":"Canadian Institutes of Health Research","keywords":"Medicine; Term (time); Nuclear medicine","score_opus":0.10345887822122361,"score_gpt":0.43351123592965785,"score_spread":0.3300523577084342,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2054955059","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9823589,0.0053036604,0.0042208955,0.0064377016,0.0012507403,0.00028772966,0.000002864905,0.000051234314,0.00008629129],"genre_scores_gemma":[0.9928125,0.0016556083,0.0031270257,0.00059789175,0.0017265955,0.0000039936335,0.0000033656672,0.00002993725,0.000043079523],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99566144,0.0002961748,0.0024129183,0.0003550037,0.00091405434,0.00036040414],"domain_scores_gemma":[0.99518514,0.0015186393,0.0018796332,0.0004317579,0.0005675527,0.00041730344],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0057756407,0.00023201434,0.0018661679,0.000994433,0.00010793907,0.000036676985,0.0002719942,0.00025881757,0.000025025],"category_scores_gemma":[0.018176083,0.00017242985,0.00040341777,0.001014371,0.0005218522,0.00019712067,0.00026469695,0.0017463722,0.000004028473],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022686669,0.00048523123,0.5821144,0.000103594764,0.000069140195,0.00007215365,0.000057679983,4.148217e-7,0.00021249018,0.000011989295,0.00088584836,0.4157602],"study_design_scores_gemma":[0.0034360476,0.0016169399,0.9810751,0.0010976468,0.00036029887,0.00045054208,0.00012791067,0.00789868,0.0003058699,0.00011525595,0.0033345295,0.00018116522],"about_ca_topic_score_codex":0.000019395678,"about_ca_topic_score_gemma":0.000001103787,"teacher_disagreement_score":0.41557902,"about_ca_system_score_codex":0.000041051917,"about_ca_system_score_gemma":0.00008041673,"threshold_uncertainty_score":0.99009424},"labels":[],"label_agreement":null},{"id":"W2055221833","doi":"10.3747/co.v17i1.394","title":"Application of Machine Learning Methodology for Pet-Based Definition of Lung Cancer","year":2010,"lang":"en","type":"article","venue":"Current Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Alberta Glycomics Centre; University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Cancer Foundation","keywords":"Jaccard index; Standardized uptake value; Nuclear medicine; Positron emission tomography; Lung cancer; Medicine; Segmentation; Radiation therapy; Radiation treatment planning; Computer science; Artificial intelligence; Medical physics; Pattern recognition (psychology); Radiology; Pathology","score_opus":0.11752712531947604,"score_gpt":0.47286927955871705,"score_spread":0.355342154239241,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2055221833","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5808364,0.0010813428,0.41317925,0.0025245443,0.0012028589,0.0005874019,0.000020543224,0.000038977465,0.0005286976],"genre_scores_gemma":[0.9141917,0.000113988506,0.084998496,0.00012043217,0.00021909755,0.00015495504,0.00017005613,0.000018250543,0.000013017381],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99910367,0.00012605941,0.00033212994,0.00018027211,0.00010200456,0.0001558969],"domain_scores_gemma":[0.9984824,0.00078859087,0.0003239093,0.0001352448,0.00019845295,0.00007142238],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008522051,0.00008732717,0.00040432464,0.0001336512,0.000038225324,0.000001316655,0.00007693209,0.00008273686,0.00008206662],"category_scores_gemma":[0.0013467857,0.00007694495,0.00009973594,0.000104645005,0.00016982251,0.000015313464,0.000019164812,0.00057935173,7.715408e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004746579,0.00053188746,0.29911494,0.0012349728,0.00006781706,0.0000020393277,0.00019718047,0.00020636516,0.22925067,0.009979904,0.0003832691,0.4585563],"study_design_scores_gemma":[0.006704339,0.0010068533,0.025051465,0.00015938046,0.0006240298,0.00006037849,0.00004035616,0.8143019,0.011315161,0.00196211,0.13858221,0.00019182185],"about_ca_topic_score_codex":0.00008973406,"about_ca_topic_score_gemma":0.000026701671,"teacher_disagreement_score":0.8140955,"about_ca_system_score_codex":0.000041866813,"about_ca_system_score_gemma":0.00019968234,"threshold_uncertainty_score":0.31377238},"labels":[],"label_agreement":null},{"id":"W2056087501","doi":"10.1088/0031-9155/59/22/7039","title":"An augmented parametric response map with consideration of image registration error: towards guidance of locally adaptive radiotherapy","year":2014,"lang":"en","type":"article","venue":"Physics in Medicine and Biology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"London Health Sciences Centre; Western University","funders":"","keywords":"Parametric statistics; Image registration; Computer science; Artificial intelligence; Ground truth; Voxel; Image (mathematics); Pattern recognition (psychology); Mathematics; Statistics","score_opus":0.0850013464080603,"score_gpt":0.39791726141715705,"score_spread":0.31291591500909677,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2056087501","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7545985,0.00042263744,0.24059999,0.0037652072,0.000052324955,0.00020417459,0.0000021926026,0.0000121713465,0.00034276958],"genre_scores_gemma":[0.97982335,0.00012073947,0.019182436,0.0006731985,0.00014256517,0.0000060141947,0.000028245837,0.000009709433,0.000013764359],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989066,0.00029254987,0.00034129378,0.0002103983,0.00012504958,0.00012409882],"domain_scores_gemma":[0.9990423,0.0003218931,0.00022850581,0.00019318268,0.0001501718,0.00006396422],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001102153,0.00011115693,0.00045469106,0.00013832291,0.000021082573,0.0000023595435,0.0000531742,0.00006341898,0.000009537847],"category_scores_gemma":[0.00056141993,0.00007410836,0.000019592662,0.00023413262,0.0007034107,0.000049150112,0.0000075236126,0.00019605522,1.554472e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.009158723,0.00049964595,0.054395314,0.00033167718,0.00016396027,0.000019118945,0.0018738756,0.00055268046,0.7884883,0.020905776,0.0005638694,0.12304703],"study_design_scores_gemma":[0.027816655,0.045563567,0.2424261,0.0023926804,0.00035887156,0.0001699763,0.0017654116,0.6245134,0.032269176,0.019412575,0.0026795932,0.00063200167],"about_ca_topic_score_codex":0.00024746894,"about_ca_topic_score_gemma":0.000009778303,"teacher_disagreement_score":0.75621915,"about_ca_system_score_codex":0.000023466568,"about_ca_system_score_gemma":0.00009018772,"threshold_uncertainty_score":0.3022051},"labels":[],"label_agreement":null},{"id":"W2059386562","doi":"10.1117/12.830650","title":"Experience gained with texture modeling and classification of 1 meter resolution SAR images","year":2009,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Synthetic aperture radar; Computer science; Artificial intelligence; Radar imaging; Computer vision; Bayesian inference; Pattern recognition (psychology); Speckle pattern; Image resolution; Inference; Remote sensing; Bayesian probability; Radar; Geography","score_opus":0.012542714997472214,"score_gpt":0.258191961474011,"score_spread":0.2456492464765388,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2059386562","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99134636,0.00016560219,0.0011974301,0.005536223,0.00004437428,0.00035547157,0.0000067932397,0.000044513723,0.0013032315],"genre_scores_gemma":[0.8622885,0.00009643316,0.13719136,0.00014340706,0.00015146915,0.000019097191,0.000005931447,0.000023881608,0.00007992773],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99841994,1.8495372e-8,0.0004918133,0.0003007074,0.0005500848,0.00023745629],"domain_scores_gemma":[0.9984503,0.00006015582,0.00027422694,0.000053047585,0.0010489796,0.0001132866],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044471407,0.0002033158,0.0003681056,0.00009585401,0.00005881277,0.00004322946,0.00027140023,0.000121184574,0.000003817977],"category_scores_gemma":[0.00056135794,0.00014665666,0.0002187455,0.00021542847,0.00023573179,0.00031459567,0.000044274926,0.0003240257,1.6013048e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028033738,0.000112731235,0.0011377756,0.00037707333,0.00017619396,1.6520704e-7,0.00050941284,0.00037622504,0.8970071,0.09801717,0.0005849785,0.0014208241],"study_design_scores_gemma":[0.002073212,0.0008880853,0.008639736,0.000965858,0.00029661373,0.00007346159,0.0019058633,0.9225893,0.060697984,0.000985836,0.0005879874,0.00029603305],"about_ca_topic_score_codex":0.000005794322,"about_ca_topic_score_gemma":3.292801e-8,"teacher_disagreement_score":0.9222131,"about_ca_system_score_codex":0.00007107168,"about_ca_system_score_gemma":0.000026480031,"threshold_uncertainty_score":0.5980485},"labels":[],"label_agreement":null},{"id":"W2059939049","doi":"10.1118/1.3613253","title":"TU‐G‐211‐03: Automatic Segmentation of Non‐Small Cell Lung Carcinoma Using 3D Texture Features in Co‐Registered FDG PET/CT Images","year":2011,"lang":"en","type":"article","venue":"Medical Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Health Science Centre","funders":"","keywords":"Segmentation; Artificial intelligence; Ground truth; Pattern recognition (psychology); Skewness; Nuclear medicine; Computer science; Concordance; Sørensen–Dice coefficient; Feature (linguistics); Computer-aided diagnosis; Medicine; Mathematics; Image segmentation; Statistics","score_opus":0.01855030445992611,"score_gpt":0.2994114884300634,"score_spread":0.28086118397013726,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2059939049","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9754043,0.00032727944,0.017999144,0.00032231482,0.00027902971,0.00044962484,0.000006915444,0.00005606902,0.005155295],"genre_scores_gemma":[0.9893847,0.00003153033,0.009191855,0.0007552783,0.0003143838,0.000011511592,0.000057242723,0.000048167152,0.0002053387],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99790204,0.00010881445,0.0005312103,0.00034488848,0.00073120877,0.00038181286],"domain_scores_gemma":[0.9988691,0.0001360311,0.00026365757,0.00035752944,0.000068132154,0.00030555562],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000518383,0.00024767718,0.0005907598,0.00011649009,0.000062247454,0.000016807755,0.00023239723,0.000051647086,0.000249828],"category_scores_gemma":[0.00032939343,0.00020812324,0.00013803676,0.0002623019,0.00033952788,0.000094853654,0.00007276512,0.00086161436,0.000010925617],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003474764,0.0034605085,0.6518772,0.008945631,0.00035653522,0.008936643,0.0123973815,0.00019351608,0.06768446,0.00012972116,0.014000783,0.23167013],"study_design_scores_gemma":[0.014993154,0.0007116844,0.3505711,0.0040253433,0.0010226674,0.0016329379,0.0013834331,0.4877471,0.135643,0.0009148272,0.00020490504,0.0011498567],"about_ca_topic_score_codex":0.00058818876,"about_ca_topic_score_gemma":0.0000064005217,"teacher_disagreement_score":0.48755357,"about_ca_system_score_codex":0.000110063156,"about_ca_system_score_gemma":0.00028073924,"threshold_uncertainty_score":0.84870195},"labels":[],"label_agreement":null},{"id":"W2059967390","doi":"10.1038/ijo.2010.181","title":"Physiology of BAT thermogenesis: a view from the chair","year":2010,"lang":"en","type":"article","venue":"International Journal of Obesity","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; Institut universitaire de cardiologie et de pneumologie de Québec","funders":"Canadian Institutes of Health Research","keywords":"Thermogenesis; Medicine; Physiology; Endocrinology; Obesity","score_opus":0.008516737001907535,"score_gpt":0.29209911585820386,"score_spread":0.28358237885629634,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2059967390","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98847806,0.0003371761,0.00061939773,0.008967561,0.0012863594,0.000035795518,0.0000054652187,0.000003923761,0.0002662824],"genre_scores_gemma":[0.99600947,0.00016901687,0.0012923459,0.0013206549,0.0011534775,4.2972852e-7,0.0000029393632,0.000006227866,0.000045432447],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99921876,0.000043729975,0.00027674626,0.00006442636,0.00032982454,0.000066504974],"domain_scores_gemma":[0.99903524,0.0001933811,0.00028128276,0.000114163355,0.00031759447,0.000058363446],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039592368,0.000058394857,0.00018867379,0.000041640957,0.00002206315,0.00000774016,0.00033828712,0.000039412786,0.00041420726],"category_scores_gemma":[0.00046290466,0.00003310639,0.00013627468,0.000033772467,0.00010441743,0.000042801992,0.000045934677,0.00045574174,0.0000063051357],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002774021,0.00036030417,0.22377221,0.000016637308,0.00061935897,0.000090193025,0.0006101622,0.000023614655,0.71328866,0.0007710355,0.0021282304,0.058042165],"study_design_scores_gemma":[0.0008397457,0.000066388835,0.97955877,0.00011363022,0.00007304035,0.00027751623,0.000031939882,0.0006109947,0.006031384,0.0013671028,0.010991273,0.000038217222],"about_ca_topic_score_codex":0.000112638925,"about_ca_topic_score_gemma":0.00000661269,"teacher_disagreement_score":0.75578654,"about_ca_system_score_codex":0.000015012194,"about_ca_system_score_gemma":0.0000820217,"threshold_uncertainty_score":0.4535279},"labels":[],"label_agreement":null},{"id":"W2060143308","doi":"10.1118/1.4815774","title":"TH‐C‐141‐06: Estimating Cell Density Using Fractional Anisotropy From Postoperative Diffusion Tensor Imaging of High‐Grade Gliomas","year":2013,"lang":"en","type":"article","venue":"Medical Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vancouver General Hospital; BC Cancer Agency; University of British Columbia","funders":"","keywords":"Fractional anisotropy; Diffusion MRI; Nuclear medicine; Magnetic resonance imaging; White matter; Glioma; Medicine; Nuclear magnetic resonance; Radiology; Physics","score_opus":0.010601376488444747,"score_gpt":0.27759641737603963,"score_spread":0.2669950408875949,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2060143308","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.73068064,0.00009529751,0.2653878,0.0030714192,0.00034286937,0.00020142825,0.00000717809,0.000058140267,0.0001552194],"genre_scores_gemma":[0.9412165,0.000013157101,0.055474285,0.001951175,0.0011269555,0.000006629404,0.00011175986,0.00004496024,0.00005452405],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99747866,0.00010286738,0.00048368296,0.000412028,0.0011522002,0.00037056068],"domain_scores_gemma":[0.9983641,0.00039854096,0.00024747875,0.00029873158,0.0002445826,0.00044659167],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023468949,0.00025140488,0.00057305006,0.000068820984,0.00021338761,0.00003987262,0.00017636389,0.00012322709,0.0006649056],"category_scores_gemma":[0.00082362775,0.00020517303,0.00014799714,0.00022669125,0.00043797446,0.00021323128,0.00015637129,0.0009287535,0.00006175333],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001349149,0.0024317845,0.5516289,0.00033334768,0.00025093742,0.00051036285,0.0019805587,0.0013446413,0.3425805,0.0011195935,0.0067894375,0.09089504],"study_design_scores_gemma":[0.0029016845,0.00009810722,0.08161294,0.0005326439,0.00019460455,0.000091678085,0.0001951646,0.8901112,0.01626497,0.00751495,0.00016226836,0.00031981233],"about_ca_topic_score_codex":0.0031518252,"about_ca_topic_score_gemma":0.000001447895,"teacher_disagreement_score":0.8887665,"about_ca_system_score_codex":0.00010888105,"about_ca_system_score_gemma":0.00021503105,"threshold_uncertainty_score":0.83667135},"labels":[],"label_agreement":null},{"id":"W2060360091","doi":"10.1158/1538-7445.am2011-lb-282","title":"Abstract LB-282: Cancer-specific motogenic signals induce collective migratory pattern in myofibroblasts via increased tight junction formation","year":2011,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Myofibroblast; Desmoplasia; Autocrine signalling; Cancer; Cell biology; Cancer cell; Fibroblast; Cancer research; Cell migration; Biology; Paracrine signalling; Pathology; Cell; Chemistry; Cell culture; Medicine; Fibrosis; Biochemistry; Genetics; Pancreatic cancer","score_opus":0.08766472340344603,"score_gpt":0.3721114318808597,"score_spread":0.2844467084774137,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2060360091","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9936391,0.0015059569,0.0008838082,0.000673616,0.00025140453,0.00082344236,0.000012172283,0.0000465607,0.0021639029],"genre_scores_gemma":[0.99734765,0.00082459825,0.000083649145,0.0002780072,0.00038904545,0.00045919864,0.000023740728,0.000045689747,0.00054841326],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99755734,0.0002496154,0.0004002214,0.00041751025,0.00077363255,0.00060169474],"domain_scores_gemma":[0.99877983,0.00015861393,0.00011129006,0.0002837277,0.00036035627,0.00030619054],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0013154788,0.00018131992,0.00031568273,0.00064114487,0.00018614552,0.000037849873,0.00018838387,0.00015828374,0.0014971589],"category_scores_gemma":[0.00015028648,0.00016268021,0.00007971202,0.0008868321,0.00018706813,0.0002539757,0.00006155588,0.001323263,0.00007103021],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012396576,0.00040201968,0.115506545,0.00048454208,0.00012941136,0.00019402866,0.0068794945,0.0000738047,0.65589225,0.00001442513,0.01713884,0.20204496],"study_design_scores_gemma":[0.004254549,0.0004456232,0.8061961,0.0015002973,0.000035778565,0.000037867307,0.0008256435,0.005154046,0.1747212,0.0003923014,0.006038697,0.00039792657],"about_ca_topic_score_codex":0.020536475,"about_ca_topic_score_gemma":0.0012412018,"teacher_disagreement_score":0.6906895,"about_ca_system_score_codex":0.0014144512,"about_ca_system_score_gemma":0.0007173908,"threshold_uncertainty_score":0.99941564},"labels":[],"label_agreement":null},{"id":"W2062112167","doi":"10.1002/path.2729","title":"‘Evidence‐based medicine: the time has come to set standards for staging’. Is a radical overhaul really needed?","year":2010,"lang":"en","type":"letter","venue":"The Journal of Pathology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre","funders":"","keywords":"Set (abstract data type); Medicine; Medical physics; Psychology; Computer science","score_opus":0.047573956595056324,"score_gpt":0.3617793782966894,"score_spread":0.31420542170163307,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2062112167","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009380035,0.0012211332,0.0138933435,0.9728851,0.0015215877,0.0007293171,0.0001007628,0.000026008596,0.00024273418],"genre_scores_gemma":[0.0025130953,0.0002649238,0.0026405102,0.9817621,0.011267891,0.000014698167,0.00003511209,0.00010660211,0.0013950771],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99562544,0.0006930007,0.001116316,0.00030908667,0.0015935462,0.0006626287],"domain_scores_gemma":[0.99338245,0.0036204394,0.0010190012,0.00085139315,0.0008427837,0.00028391933],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.01035436,0.00043402414,0.001401097,0.0004106597,0.00032619928,0.00006216686,0.0011792468,0.00092640036,0.0007530787],"category_scores_gemma":[0.0065723252,0.00020599239,0.0004088244,0.0002454924,0.0014963457,0.000067588226,0.00012665354,0.010072811,0.000019471427],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008083989,0.000021843236,0.00007525732,0.00016168482,0.00016249187,0.0021241556,0.0015669593,0.00001959746,0.004603995,0.000010125011,0.9876268,0.0028187302],"study_design_scores_gemma":[0.0024189283,0.0023339149,0.0002234735,0.001622241,0.0012223537,0.007962314,0.000105884305,0.0012908545,0.00011108808,0.00050546956,0.98199046,0.00021303791],"about_ca_topic_score_codex":0.000064922926,"about_ca_topic_score_gemma":0.000002102433,"teacher_disagreement_score":0.0112528335,"about_ca_system_score_codex":0.00021147821,"about_ca_system_score_gemma":0.001487929,"threshold_uncertainty_score":0.992211},"labels":[],"label_agreement":null},{"id":"W2062382244","doi":"10.1158/0008-5472.sabcs13-p3-14-11","title":"Abstract P3-14-11: Microarray data analysis and long term outcomes of NCIC-CTG MA.22: Neoadjuvant epirubicin and docetaxel with pegfilgrastim support for locally advanced breast cancer","year":2013,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; Ottawa Hospital; Sunnybrook Health Science Centre","funders":"","keywords":"Medicine; Docetaxel; Oncology; Epirubicin; Internal medicine; Breast cancer; Tissue microarray; Cohort; Cancer; Significance analysis of microarrays; Microarray; Gene expression; Biology; Gene","score_opus":0.04157488977611171,"score_gpt":0.40996808868242873,"score_spread":0.368393198906317,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2062382244","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9866618,0.0017124743,0.0028288753,0.0071231327,0.00006548488,0.0010932427,0.00039279895,0.000025170279,0.00009702054],"genre_scores_gemma":[0.9932962,0.0012843686,0.0031938741,0.00032370567,0.00013327166,0.0002228806,0.00018586458,0.000056211804,0.0013036082],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9972975,0.00005778418,0.00044650267,0.0007838067,0.0007136139,0.0007007655],"domain_scores_gemma":[0.9976708,0.00035301785,0.00016333563,0.00073393976,0.00059725955,0.00048159063],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0010866768,0.00025614744,0.00082492863,0.00043784085,0.00016817875,0.000092982584,0.00037578834,0.00009749106,0.0009149857],"category_scores_gemma":[0.0002462773,0.00017678998,0.000079305864,0.0005377983,0.00070487306,0.00026560994,0.00023757223,0.00062788074,0.0000029918046],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00052759744,0.00009989497,0.8044545,0.00072811835,0.000914441,0.000040109942,0.00017302646,0.000102530634,0.03652943,0.000007810715,0.0024706004,0.15395191],"study_design_scores_gemma":[0.0033072662,0.00021557481,0.98831487,0.00044310576,0.00054900575,0.000054591204,0.00016255048,0.0047956887,0.001276188,0.000022134169,0.0006354568,0.00022355953],"about_ca_topic_score_codex":0.0065231454,"about_ca_topic_score_gemma":0.0016799724,"teacher_disagreement_score":0.18386035,"about_ca_system_score_codex":0.00011498155,"about_ca_system_score_gemma":0.00050487556,"threshold_uncertainty_score":0.99999833},"labels":[],"label_agreement":null},{"id":"W2063247743","doi":"10.1159/000171177","title":"Clinical Applications of Nuclear Medicine in Gastroenterology","year":2008,"lang":"en","type":"review","venue":"Digestive Diseases","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Hôtel-Dieu de Montréal","funders":"","keywords":"Medicine; Internal medicine; Gastroenterology; Medical physics","score_opus":0.033733606390982496,"score_gpt":0.40741779788148247,"score_spread":0.3736841914905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2063247743","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001608377,0.99748516,0.00010453357,0.00031146404,0.000107352505,0.00080740993,0.000051682833,0.000037934402,0.0009336386],"genre_scores_gemma":[0.00029384228,0.9980313,0.00022110798,0.00047425312,0.00039649173,0.00010215081,0.0003523102,0.000054450156,0.0000740686],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978037,0.00024654795,0.0010398041,0.0004306579,0.000228761,0.00025051605],"domain_scores_gemma":[0.99821633,0.0005855026,0.0004292766,0.00038106064,0.00008031474,0.00030753145],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015667982,0.00027448536,0.0023905784,0.00033980823,0.000033059292,0.0000023739549,0.00020855838,0.00017003667,0.00011039124],"category_scores_gemma":[0.0011638342,0.0002000405,0.000496127,0.00029178231,0.0009006934,0.000021706082,0.00007517947,0.0007280531,0.000029437428],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000061732855,0.0005284845,0.059373006,0.0043988656,0.00017739643,0.00015959276,0.000029421919,5.905684e-7,7.302413e-8,0.00018662684,0.0038888974,0.9311953],"study_design_scores_gemma":[0.0008474648,0.00033649523,0.0328285,0.010567982,0.00091443973,0.00015873641,0.00001998684,0.000038965896,3.02756e-9,0.000021411228,0.9541568,0.000109222194],"about_ca_topic_score_codex":0.00003495435,"about_ca_topic_score_gemma":4.974415e-7,"teacher_disagreement_score":0.9502679,"about_ca_system_score_codex":0.00005833259,"about_ca_system_score_gemma":0.00023437591,"threshold_uncertainty_score":0.8157415},"labels":[],"label_agreement":null},{"id":"W2071195106","doi":"10.1016/j.ijrobp.2013.06.526","title":"High-Risk CT Features for Detection of Local Recurrence After Stereotactic Ablative Radiation Therapy for Lung Cancer","year":2013,"lang":"en","type":"article","venue":"International Journal of Radiation Oncology*Biology*Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Cancer Care Ontario","funders":"","keywords":"Medicine; Ablative case; Lung cancer; Radiation therapy; Radiology; Stereotactic radiation therapy; Radiosurgery; Lung; Oncology; Internal medicine","score_opus":0.010094260562302398,"score_gpt":0.339928850487566,"score_spread":0.3298345899252636,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2071195106","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.64158547,0.0015275643,0.35124213,0.0024605326,0.0024365385,0.000648852,0.00006890767,0.000014339829,0.000015678237],"genre_scores_gemma":[0.98982424,0.0019335835,0.0051617664,0.0007688132,0.0020153166,0.00017522792,0.000060890678,0.000027956938,0.000032214703],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99859416,0.00016108358,0.00063215184,0.00020341332,0.00021455657,0.00019465463],"domain_scores_gemma":[0.996437,0.00087194087,0.0013715479,0.00009816291,0.0011193856,0.00010194389],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00055081124,0.00016563093,0.0004466273,0.00016937543,0.00006806372,0.000024614303,0.00018301382,0.00013094107,0.00005042694],"category_scores_gemma":[0.0006116379,0.00013568725,0.0002502517,0.00010720974,0.00019223418,0.00030468387,0.000016933402,0.0004729814,0.0000015320738],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012861611,0.00020533249,0.11038152,0.000028504175,0.00092297397,0.0000027884662,0.00039531093,0.0016349861,0.005105598,0.00076154486,0.000983779,0.8782915],"study_design_scores_gemma":[0.037314054,0.0077717723,0.54507506,0.00047575482,0.0011185817,0.00029095702,0.00028659537,0.2946079,0.054919615,0.029121624,0.028323477,0.0006945813],"about_ca_topic_score_codex":0.00017549394,"about_ca_topic_score_gemma":0.000005298592,"teacher_disagreement_score":0.8775969,"about_ca_system_score_codex":0.0005263565,"about_ca_system_score_gemma":0.0003260387,"threshold_uncertainty_score":0.5533166},"labels":[],"label_agreement":null},{"id":"W2072613966","doi":"10.1118/1.4734675","title":"SU‐D‐BRB‐03: Prediction of Tumor Outcomes Through Wavelet Image Fusion and Texture Analysis of PET/MR Imaging","year":2012,"lang":"en","type":"article","venue":"Medical Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; McGill University Health Centre","funders":"","keywords":"Nuclear medicine; Medicine; Spearman's rank correlation coefficient; Correlation; Rank correlation; Radiology; Mathematics; Statistics","score_opus":0.009777558493323735,"score_gpt":0.2930803970007428,"score_spread":0.28330283850741905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2072613966","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95568234,0.0005494004,0.038495883,0.002849751,0.00030351293,0.00018977968,0.000039146278,0.00005826259,0.0018319282],"genre_scores_gemma":[0.99617785,0.0001239009,0.0020184182,0.0010800925,0.00038619214,0.0000047512563,0.00011317788,0.000026321764,0.000069277914],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.997877,0.00006948828,0.0005144351,0.00024226085,0.0009614269,0.0003353814],"domain_scores_gemma":[0.99875957,0.00024011478,0.00024258891,0.0003120002,0.00011752313,0.0003281782],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006829543,0.000190217,0.0008079796,0.00012436994,0.0000636703,0.000010018738,0.000119773424,0.000055142682,0.00025733525],"category_scores_gemma":[0.0009845924,0.00014199923,0.00024872395,0.0005585674,0.0005787509,0.00020236774,0.00011655923,0.00054827717,0.000004033822],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000052870255,0.0006443654,0.94712234,0.00041134492,0.00084380404,0.00005372119,0.0013740687,0.0000065753266,0.00942012,0.0010166586,0.00202451,0.037029598],"study_design_scores_gemma":[0.0035411678,0.00018154002,0.8776587,0.00054921594,0.0049907407,0.00015253168,0.00050288276,0.102795996,0.0054765833,0.0011514145,0.002648538,0.00035066964],"about_ca_topic_score_codex":0.00012699167,"about_ca_topic_score_gemma":8.961279e-7,"teacher_disagreement_score":0.10278942,"about_ca_system_score_codex":0.000033550885,"about_ca_system_score_gemma":0.00007013687,"threshold_uncertainty_score":0.5790561},"labels":[],"label_agreement":null},{"id":"W2073724573","doi":"10.1158/1538-7445.am2011-4847","title":"Abstract 4847: Purifying tumor gene expression profiles leads to predictive models of patient outcome","year":2011,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Occupational Cancer Research Centre; Ontario Institute for Cancer Research; University of Toronto","funders":"","keywords":"Gene signature; Correlation; Cohort; Oncology; Lung cancer; Gene expression; Medicine; Internal medicine; Cancer; Pipeline (software); Gene; Computational biology; Computer science; Biology; Genetics; Mathematics","score_opus":0.12912873320684184,"score_gpt":0.4204885123956065,"score_spread":0.29135977918876466,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2073724573","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99165124,0.00053887285,0.0014095367,0.00050943624,0.00016070016,0.0007429478,0.000018663051,0.00003918039,0.004929428],"genre_scores_gemma":[0.99437153,0.00007286352,0.004664948,0.00020634182,0.0001704029,0.00023924459,0.0000065786953,0.00003899751,0.00022907367],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9977922,0.00008293078,0.00037964166,0.0003607375,0.00090412825,0.0004804038],"domain_scores_gemma":[0.998729,0.000088591834,0.00008300663,0.00035613475,0.00036381508,0.000379481],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008145065,0.00012741485,0.0003140717,0.00028566655,0.00010967683,0.000013268758,0.00021405841,0.00006137253,0.00040107474],"category_scores_gemma":[0.0004398601,0.00009723953,0.00007372061,0.00027469062,0.00017937017,0.00010694227,0.00018146118,0.0008151379,0.000019003539],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013565046,0.0003913717,0.10495174,0.0006949663,0.00006700463,0.0001899239,0.008150753,0.0015177055,0.8583317,0.00018143,0.0035493982,0.020617539],"study_design_scores_gemma":[0.0014364226,0.0010279297,0.059478402,0.0016249042,0.000036740967,0.000022373366,0.00095250184,0.0054934984,0.9278979,0.0007672544,0.0010045613,0.0002575379],"about_ca_topic_score_codex":0.00060383056,"about_ca_topic_score_gemma":0.0000028139034,"teacher_disagreement_score":0.069566205,"about_ca_system_score_codex":0.00017327591,"about_ca_system_score_gemma":0.0002406455,"threshold_uncertainty_score":0.4391487},"labels":[],"label_agreement":null},{"id":"W2074904845","doi":"10.1016/s0735-1097(14)61045-7","title":"TEXTURE ANALYSIS OF DIFFUSE MYOCARDIAL FIBROSIS FROM LATE GADOLINIUM ENHANCED MAGNETIC RESONANCE IMAGING IN AGING RATS","year":2014,"lang":"en","type":"article","venue":"Journal of the American College of Cardiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Medicine; Gadolinium; Magnetic resonance imaging; Myocardial fibrosis; Pathology; Fibrosis; Nuclear magnetic resonance; Radiology","score_opus":0.00446585837433899,"score_gpt":0.2547853122466044,"score_spread":0.2503194538722654,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2074904845","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99040866,0.001635699,0.0039926707,0.003012488,0.0003455543,0.00009505777,0.000034966724,0.000004876145,0.0004700214],"genre_scores_gemma":[0.99657375,0.00038662707,0.0018507328,0.0007020829,0.0004126112,0.0000015653276,0.0000021942021,0.00001849331,0.00005192908],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99776,0.00061282585,0.0008182153,0.00019769707,0.00035979337,0.000251486],"domain_scores_gemma":[0.99761546,0.0006457055,0.0010380431,0.00040438655,0.000191705,0.00010473212],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009119051,0.00015829672,0.0017778126,0.00047341458,0.00003529016,0.000004433631,0.00033326875,0.00004765144,0.000010329875],"category_scores_gemma":[0.0010146556,0.00010905683,0.00073946407,0.0010588038,0.00057593035,0.000041002633,0.0000956588,0.000572655,3.9811252e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010905678,0.000071597424,0.7781159,0.000026469823,0.0009571535,0.00013205098,0.00033386415,0.009930316,0.14960513,0.000030528565,0.0013045503,0.058401864],"study_design_scores_gemma":[0.002127779,0.00035518955,0.9737815,0.00026239094,0.0018128819,0.000092567294,0.00026328777,0.015877098,0.0024506499,0.00015392942,0.00269606,0.00012663109],"about_ca_topic_score_codex":0.00012140615,"about_ca_topic_score_gemma":0.000006896081,"teacher_disagreement_score":0.19566563,"about_ca_system_score_codex":0.00006323376,"about_ca_system_score_gemma":0.00011853165,"threshold_uncertainty_score":0.44472086},"labels":[],"label_agreement":null},{"id":"W2075372833","doi":"10.1118/1.3352709","title":"Comparison of Bayesian network and support vector machine models for two-year survival prediction in lung cancer patients treated with radiotherapy","year":2010,"lang":"en","type":"article","venue":"Medical Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":122,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Princess Margaret Cancer Centre; University Health Network","funders":"","keywords":"Missing data; Support vector machine; Data set; Artificial intelligence; Lung cancer; Radiation therapy; Machine learning; Bayesian network; Medicine; Bayesian probability; Statistics; Computer science; Mathematics; Internal medicine","score_opus":0.009492886713867414,"score_gpt":0.31148247444593496,"score_spread":0.3019895877320676,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2075372833","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90004027,0.00014014448,0.09737968,0.00079552684,0.00040911374,0.0006940561,0.000038368824,0.000046665955,0.00045618956],"genre_scores_gemma":[0.9974138,0.00003948144,0.0014120282,0.00020288456,0.0006532572,0.00004066992,0.00015600627,0.000039113776,0.000042743653],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99863106,0.00003534672,0.0003287897,0.0002443375,0.0004902696,0.00027021894],"domain_scores_gemma":[0.9992726,0.0001300424,0.000116087285,0.00014438755,0.00007968143,0.00025719716],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034242365,0.0001506334,0.0005104243,0.000038429855,0.00004743278,0.00000847928,0.00007862258,0.00010226698,0.000096442236],"category_scores_gemma":[0.000086884116,0.00011376867,0.000047283116,0.00017237858,0.00022060171,0.0000639472,0.000017387,0.0006016486,1.4820364e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00043391364,0.00041252794,0.9753663,0.00014620881,0.000089504734,0.000003422439,0.0002721436,0.0009286441,0.00022815075,0.000450599,0.0007629518,0.020905655],"study_design_scores_gemma":[0.008604992,0.000612029,0.09141312,0.00023189276,0.00011820763,0.0000027389394,0.000009905038,0.89818096,0.00024763914,0.00020362301,0.00024042597,0.00013447809],"about_ca_topic_score_codex":0.00023018698,"about_ca_topic_score_gemma":0.00007996352,"teacher_disagreement_score":0.8972523,"about_ca_system_score_codex":0.00003814999,"about_ca_system_score_gemma":0.00012680548,"threshold_uncertainty_score":0.46393517},"labels":[],"label_agreement":null},{"id":"W2075849929","doi":"10.1118/1.4815454","title":"TU‐G‐108‐05: Assessment of Different Machine Learning Techniques for Multivariate Radiation Pneumonitis Modeling","year":2013,"lang":"en","type":"article","venue":"Medical Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University","funders":"","keywords":"Artificial intelligence; Machine learning; Support vector machine; Biomarker; Naive Bayes classifier; Logistic regression; Medicine; Radiation therapy; Multivariate statistics; Computer science; Nuclear medicine; Mathematics; Internal medicine; Biology","score_opus":0.015760942776940807,"score_gpt":0.32639742676541506,"score_spread":0.31063648398847427,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2075849929","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13976929,0.00008813504,0.85408586,0.004232302,0.00018406697,0.00080668455,0.000007347745,0.00016918738,0.00065712316],"genre_scores_gemma":[0.9882858,0.00018848029,0.0098267365,0.0006083787,0.0005703513,0.00015744934,0.00016392171,0.00005164572,0.00014723255],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980859,0.0000669172,0.0005008416,0.00028964062,0.00072974275,0.0003269624],"domain_scores_gemma":[0.9987191,0.00041633178,0.00017874315,0.00020294375,0.00016612648,0.00031677235],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045434744,0.00020347419,0.00052991306,0.0000713256,0.000110430825,0.000024686682,0.00014631536,0.00013597729,0.00014918315],"category_scores_gemma":[0.0012739042,0.00016049584,0.00017943453,0.0001149902,0.000121504214,0.000098564604,0.00007345083,0.00080144615,0.0000041517596],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031956617,0.0010376174,0.039886676,0.0006699511,0.00018611754,0.000015009265,0.0003436107,0.000668372,0.03296547,0.0014911673,0.000589723,0.9221143],"study_design_scores_gemma":[0.001415372,0.00039232007,0.0035324686,0.00033541385,0.00009437418,0.000011556397,0.000019533598,0.9851335,0.0056598284,0.0027682083,0.00047635796,0.00016101403],"about_ca_topic_score_codex":0.00024960484,"about_ca_topic_score_gemma":8.5007105e-7,"teacher_disagreement_score":0.9844652,"about_ca_system_score_codex":0.00008950666,"about_ca_system_score_gemma":0.0001152306,"threshold_uncertainty_score":0.654483},"labels":[],"label_agreement":null},{"id":"W2077747724","doi":"10.1118/1.3611809","title":"SU-E-J-41: Quantitative Assessment of Anatomical Changes throughout the Course Radiation Therapy with Deformable Registration","year":2011,"lang":"en","type":"article","venue":"Medical Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre hospitalier universitaire de Québec","funders":"","keywords":"Image registration; Image-guided radiation therapy; Artificial intelligence; Computer vision; Displacement (psychology); Computer science; Medical imaging; Deformation (meteorology); Fiducial marker; Nuclear medicine; Medicine; Geology; Image (mathematics)","score_opus":0.03676327913383946,"score_gpt":0.3710678846947406,"score_spread":0.33430460556090114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2077747724","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.78576964,0.00060912536,0.18492734,0.015354494,0.00029834153,0.00074940297,0.0000067471005,0.00009034085,0.012194576],"genre_scores_gemma":[0.99539834,0.0004113805,0.0023499478,0.0014720216,0.00022960988,0.000021697513,0.000041770538,0.000020628455,0.000054621127],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9985167,0.000083090796,0.00022556023,0.00017574863,0.00079808466,0.00020084054],"domain_scores_gemma":[0.9991547,0.00014441536,0.0001939431,0.00025015275,0.00011084366,0.00014595667],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00068168703,0.00012661792,0.00028095706,0.000021425807,0.00008692387,0.000011998966,0.00014262363,0.00007446929,0.00010235823],"category_scores_gemma":[0.00014446786,0.000069925365,0.00005725105,0.0001919947,0.00058024866,0.000087410226,0.000019685946,0.00048111554,0.0000032503337],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001207573,0.0034606014,0.24020277,0.00033726363,0.0011739623,0.00013676198,0.012603235,0.000108152715,0.0020777306,0.15304905,0.0062876744,0.57935524],"study_design_scores_gemma":[0.017975455,0.009084934,0.55911934,0.0010932072,0.000895551,0.00023241118,0.0026301877,0.3476912,0.027764253,0.016485037,0.016016828,0.0010115898],"about_ca_topic_score_codex":0.00016829363,"about_ca_topic_score_gemma":0.000010535376,"teacher_disagreement_score":0.57834363,"about_ca_system_score_codex":0.000039839542,"about_ca_system_score_gemma":0.00034818435,"threshold_uncertainty_score":0.28514737},"labels":[],"label_agreement":null},{"id":"W2079046747","doi":"10.1016/s0360-3016(01)02386-0","title":"Targeting and monitoring radiation therapy of prostate cancer using ultrasonic spectrum-analysis and neural-network classification for tissue-type imaging","year":2001,"lang":"en","type":"article","venue":"International Journal of Radiation Oncology*Biology*Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Cancer Institute; BC Cancer Agency; National Institutes of Health","keywords":"Medicine; Prostate cancer; Ultrasonic sensor; Ultrasound; Prostatectomy; Prostate; Radiation therapy; Radiology; Brachytherapy; Radiation treatment planning; Cancer; Internal medicine","score_opus":0.023609251790747673,"score_gpt":0.3708068689350699,"score_spread":0.34719761714432223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2079046747","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94708216,0.0058172867,0.042340748,0.0034035698,0.001090141,0.00022939629,0.000007800319,0.000015010188,0.000013855256],"genre_scores_gemma":[0.9752219,0.015092646,0.0070338724,0.00021299359,0.0023579185,0.0000057934603,0.000042593994,0.00002181938,0.000010473947],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987072,0.000118549324,0.0006019537,0.00020064319,0.00017918673,0.00019246925],"domain_scores_gemma":[0.99793965,0.00036881832,0.0010732177,0.00007292761,0.00045287464,0.00009249501],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00073408923,0.00013637135,0.00043177538,0.00020488717,0.00009723149,0.00003266705,0.00010767763,0.00008582731,0.000011390606],"category_scores_gemma":[0.00033027923,0.00012281888,0.000102383405,0.0002990551,0.00014889444,0.00021745585,0.000018908446,0.00029991652,1.7242148e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023641376,0.000044143977,0.70972526,0.000007439486,0.00057014066,0.0000042492775,0.0002683857,0.009455472,0.028237263,0.00023720729,0.000031127267,0.2511829],"study_design_scores_gemma":[0.0050464957,0.0005548598,0.3588587,0.000104596234,0.00080110476,0.00017142842,0.00014440993,0.6217047,0.0035526925,0.0029790376,0.0058672614,0.00021469449],"about_ca_topic_score_codex":0.00005728826,"about_ca_topic_score_gemma":9.40224e-7,"teacher_disagreement_score":0.61224926,"about_ca_system_score_codex":0.00025584624,"about_ca_system_score_gemma":0.00017071965,"threshold_uncertainty_score":0.50084084},"labels":[],"label_agreement":null},{"id":"W2079283266","doi":"10.1118/1.4894930","title":"Poster - Thur Eve - 70: Automatic lung bronchial and vessel bifurcations detection algorithm for deformable image registration assessment","year":2014,"lang":"en","type":"article","venue":"Medical Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; Centre Hospitalier de l’Université de Montréal","funders":"","keywords":"Image registration; Segmentation; Computer science; Artificial intelligence; Algorithm; Computer vision; Breathing; Medical imaging; Anatomy; Medicine; Image (mathematics)","score_opus":0.006843584928485065,"score_gpt":0.3010773310794408,"score_spread":0.2942337461509557,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2079283266","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04327553,0.00003249114,0.94753057,0.00617363,0.00029950798,0.000431083,0.0000036533474,0.000108844855,0.002144673],"genre_scores_gemma":[0.983903,0.000024991754,0.012508977,0.0017431531,0.0013391192,0.00008713351,0.00013271603,0.00003501918,0.00022587055],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99864966,0.00005338604,0.0003014946,0.00024275183,0.00050222233,0.000250489],"domain_scores_gemma":[0.99912703,0.0001974634,0.000119557546,0.0001980012,0.00008472535,0.000273211],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006950245,0.00013958839,0.00025790662,0.00004336465,0.00020143228,0.000058040092,0.00007629812,0.00010096296,0.000032612454],"category_scores_gemma":[0.00048897834,0.00011715125,0.00007281016,0.00011131806,0.0002522734,0.00015450573,0.00003430844,0.00040231066,0.0000054247503],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015829115,0.00023555658,0.0017873773,0.00042024633,0.00008397945,0.000004694585,0.00021657016,0.0000046823507,0.0019026621,0.001030218,0.004404952,0.98989326],"study_design_scores_gemma":[0.0020078784,0.00020793623,0.008373172,0.00016062826,0.00016456094,0.000059386726,0.000017419277,0.9827335,0.00090319995,0.0026565972,0.0025719823,0.00014377739],"about_ca_topic_score_codex":0.00004084539,"about_ca_topic_score_gemma":0.0000018253713,"teacher_disagreement_score":0.98974943,"about_ca_system_score_codex":0.000085646396,"about_ca_system_score_gemma":0.00015878961,"threshold_uncertainty_score":0.47772893},"labels":[],"label_agreement":null},{"id":"W2080095171","doi":"10.1118/1.2031049","title":"Sci‐AM1 Sat ‐ 08: Towards MR‐based treatment planning: Characterisation of geometric distortion in 3T MR images","year":2005,"lang":"en","type":"article","venue":"Medical Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Cancer Foundation","funders":"","keywords":"Imaging phantom; Distortion (music); Control point; Computer science; Computer vision; Artificial intelligence; MATLAB; Radiation treatment planning; Software; Point (geometry); Nuclear medicine; Mathematics; Medicine; Radiology; Geometry; Radiation therapy","score_opus":0.021384769111958864,"score_gpt":0.3203832452264761,"score_spread":0.29899847611451724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2080095171","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9476724,0.00036626437,0.04395204,0.006803642,0.00021771253,0.00024386669,0.000007691948,0.000058652622,0.0006777088],"genre_scores_gemma":[0.9972156,0.000091730755,0.0006051843,0.00084016216,0.000846846,0.000020844189,0.0002126357,0.000025518735,0.00014145479],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9980938,0.000058190304,0.00044976585,0.00027513443,0.00083746546,0.00028566475],"domain_scores_gemma":[0.9991422,0.00012998692,0.00016678234,0.00023036587,0.000057487916,0.00027312382],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046016392,0.00017857269,0.00046187468,0.00022968711,0.000045148554,0.000012244282,0.00010700182,0.00011433095,0.00016902835],"category_scores_gemma":[0.00073385856,0.00014376618,0.00012331584,0.0005337029,0.00021960378,0.000098980454,0.000026830125,0.00038455895,0.000025706859],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001366364,0.0012361731,0.09314595,0.00014849473,0.000050471142,0.00007533147,0.000546772,0.0004323671,0.0018620966,0.000022013592,0.00075875287,0.9015849],"study_design_scores_gemma":[0.013739444,0.0016499596,0.8151281,0.0013567912,0.00033072216,0.000036033645,0.00010157117,0.07558894,0.076236024,0.0004031018,0.01480414,0.00062516565],"about_ca_topic_score_codex":0.00009712662,"about_ca_topic_score_gemma":0.0000019648373,"teacher_disagreement_score":0.9009598,"about_ca_system_score_codex":0.00035333034,"about_ca_system_score_gemma":0.00026116587,"threshold_uncertainty_score":0.5862615},"labels":[],"label_agreement":null},{"id":"W2083044521","doi":"10.1587/transinf.e94.d.363","title":"Enhanced Distal Radius Segmentation in DXA Using Modified ASM","year":2011,"lang":"en","type":"article","venue":"IEICE Transactions on Information and Systems","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Segmentation; Computer science; RADIUS; Artificial intelligence; Computer vision; Enhanced Data Rates for GSM Evolution; Image segmentation; Radiography; Soft tissue; Pattern recognition (psychology); Medicine; Radiology","score_opus":0.027645622637437164,"score_gpt":0.28332346727142266,"score_spread":0.2556778446339855,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2083044521","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39038867,0.000024189472,0.60061234,0.00006579226,0.00030203647,0.0002985644,0.0000047263798,0.00004144843,0.008262227],"genre_scores_gemma":[0.9984483,0.000037570015,0.0011996605,0.000158044,0.000020572428,0.000024744379,0.000016216685,0.000006409409,0.00008849849],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99922377,0.000035351724,0.00036751913,0.0000813459,0.0001686066,0.00012342386],"domain_scores_gemma":[0.99966437,0.000023507495,0.000091065,0.00009202585,0.00003883649,0.0000902224],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022695502,0.00008945299,0.00015448578,0.000234836,0.00009058724,0.000041840573,0.000028212438,0.000059570742,0.000042952954],"category_scores_gemma":[0.000014130193,0.000079204074,0.000032089018,0.00014553293,0.000032726915,0.00047265756,9.4722924e-7,0.00020811448,0.000013104074],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002838013,0.0013103103,0.003494297,0.0031189073,0.0005037885,0.000059399736,0.13637261,0.13160421,0.058867328,0.009532661,0.00026822044,0.6520302],"study_design_scores_gemma":[0.004489233,0.00022546921,0.0043043983,0.00042861103,0.000077414086,0.00019439566,0.00826477,0.9769295,0.004070526,0.00003847487,0.00072119554,0.00025602293],"about_ca_topic_score_codex":0.0006745228,"about_ca_topic_score_gemma":0.0000062141794,"teacher_disagreement_score":0.8453253,"about_ca_system_score_codex":0.00006461056,"about_ca_system_score_gemma":0.000033254673,"threshold_uncertainty_score":0.32298484},"labels":[],"label_agreement":null},{"id":"W2085672498","doi":"10.1007/s00330-014-3420-6","title":"Quantitative CT texture and shape analysis: Can it differentiate benign and malignant mediastinal lymph nodes in patients with primary lung cancer?","year":2014,"lang":"en","type":"article","venue":"European Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":167,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; University of Ottawa","funders":"","keywords":"Medicine; Radiology; Malignancy; Neuroradiology; Lung cancer; Receiver operating characteristic; Mediastinum; Biopsy; Metastasis; Lung; Histopathology; Cancer; Pathology; Internal medicine","score_opus":0.006410833204099926,"score_gpt":0.2489018949639221,"score_spread":0.24249106175982216,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2085672498","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9957212,0.0010375435,0.0010079124,0.0012898913,0.00006689071,0.00014692837,0.00001074985,0.000024233797,0.0006946443],"genre_scores_gemma":[0.99695426,0.00030000584,0.0009379951,0.0015239452,0.00008630454,0.0000052738487,0.00010193624,0.000031566393,0.00005868143],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99838114,0.00047811464,0.0002629397,0.00043694966,0.00014670473,0.00029415346],"domain_scores_gemma":[0.9993136,0.00016993601,0.00012819763,0.00015917537,0.000043052474,0.0001860533],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045224474,0.00019721565,0.0005487534,0.00024011492,0.000071601586,0.000020019917,0.00008697716,0.000027569904,0.000034464814],"category_scores_gemma":[0.00018754875,0.00013567253,0.000037299527,0.00019873562,0.0002712765,0.00003472245,0.00006669989,0.00030551766,0.0000010754715],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020974755,0.00005332691,0.9840712,0.00007995879,0.00035063317,0.00011349689,0.0006576918,0.00009248743,0.00016957628,0.00012487495,0.00010603511,0.013970993],"study_design_scores_gemma":[0.0027927414,0.00026400026,0.95910084,0.00018981757,0.00053203874,0.000047043115,0.00005396095,0.036725737,0.0000017928613,0.00000870722,0.00013010773,0.00015318795],"about_ca_topic_score_codex":0.00011769676,"about_ca_topic_score_gemma":0.000039536,"teacher_disagreement_score":0.03663325,"about_ca_system_score_codex":0.000046950663,"about_ca_system_score_gemma":0.00003385951,"threshold_uncertainty_score":0.5532565},"labels":[],"label_agreement":null},{"id":"W2087802142","doi":"10.4103/0971-3026.76065","title":"MRI criterion for prediction of involvement of circumferential resection margin in rectal cancer","year":2011,"lang":"en","type":"article","venue":"Indian journal of radiology and imaging - new series/Indian journal of radiology and imaging/Indian Journal of Radiology & Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital","funders":"","keywords":"Copying; License; Colorectal cancer; Resection; Margin (machine learning); Attribution; Medicine; Computer science; General surgery; Psychology; Cancer; Surgery; Political science; Law; Internal medicine; Machine learning","score_opus":0.013653078053610445,"score_gpt":0.27150361945826573,"score_spread":0.2578505414046553,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2087802142","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9472181,0.03157477,0.007883586,0.008097178,0.004617893,0.00046240393,0.00006482094,0.000012856758,0.00006835767],"genre_scores_gemma":[0.9761131,0.010084834,0.010680227,0.0007448404,0.002217069,0.0000056786807,0.000019916073,0.00009582287,0.00003854055],"study_design_codex":"observational","study_design_gemma":"case_report","domain_scores_codex":[0.9922364,0.0012378672,0.0043388084,0.0005627124,0.0004950041,0.0011292439],"domain_scores_gemma":[0.99050057,0.00063877477,0.0062149847,0.00036053083,0.0012627228,0.0010224034],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.005831043,0.00073287945,0.003060886,0.0037338457,0.00029632,0.00005697845,0.0007299054,0.00040683648,0.0001455564],"category_scores_gemma":[0.0014740838,0.00063964905,0.000793529,0.0005638582,0.0024883004,0.0016688524,0.000099271194,0.0032011475,5.2915374e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0086123515,0.0003126206,0.8896458,0.0006199495,0.0016112311,0.007476456,0.019043885,0.00014201492,0.028050696,0.00012316213,0.0073231906,0.037038635],"study_design_scores_gemma":[0.019837193,0.0066254083,0.26180395,0.003682245,0.0014588092,0.68710977,0.007689141,0.0007563261,0.0045225574,0.0039314977,0.0018933857,0.0006896963],"about_ca_topic_score_codex":0.00011357012,"about_ca_topic_score_gemma":0.000023202883,"teacher_disagreement_score":0.6796333,"about_ca_system_score_codex":0.00039358108,"about_ca_system_score_gemma":0.0019260088,"threshold_uncertainty_score":0.9996055},"labels":[],"label_agreement":null},{"id":"W2087987227","doi":"10.1016/j.mbs.2014.02.006","title":"Oligometastasis as a predictor for occult disease","year":2014,"lang":"en","type":"article","venue":"Mathematical Biosciences","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":17,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Ottawa Hospital","funders":"","keywords":"Occult; Medicine; Disease; Radiological weapon; Radiology; Metastasis; Oncology; Internal medicine; Pathology; Cancer","score_opus":0.0158736781372558,"score_gpt":0.31771429554983877,"score_spread":0.30184061741258295,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2087987227","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7320829,0.00012587727,0.21127309,0.030837543,0.00038428017,0.0009460865,0.000020134508,0.00025804268,0.024072047],"genre_scores_gemma":[0.9620949,0.000007388976,0.033782564,0.0025558192,0.00020587446,0.00005495201,0.0000065587847,0.000012565905,0.001279358],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988068,0.000026267455,0.00021621479,0.0002707308,0.00039756496,0.0002824353],"domain_scores_gemma":[0.9988637,0.00034850807,0.00004974331,0.00020642656,0.00004808966,0.00048356326],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000714303,0.000109149776,0.00024212337,0.00007805199,0.00013099161,0.000061669256,0.0001649732,0.00003011972,0.00017428248],"category_scores_gemma":[0.0058875526,0.000068685215,0.00011931493,0.00018526187,0.00034495862,0.000059347232,0.000037376813,0.00009805543,0.000105517815],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004352191,0.0020528852,0.018554254,0.003225273,0.00018183459,0.000050852323,0.0013924055,0.000031167183,0.014176368,0.77377266,0.015944414,0.17018266],"study_design_scores_gemma":[0.0032340595,0.0014214161,0.015893133,0.0007340077,0.00058275746,0.00012105586,0.00033371398,0.47472334,0.0019676727,0.3643091,0.1360651,0.00061462336],"about_ca_topic_score_codex":0.000002278674,"about_ca_topic_score_gemma":1.0066314e-7,"teacher_disagreement_score":0.4746922,"about_ca_system_score_codex":0.0000138492505,"about_ca_system_score_gemma":0.000064452426,"threshold_uncertainty_score":0.70483756},"labels":[],"label_agreement":null},{"id":"W2088293391","doi":"10.1002/cncr.24343","title":"Conclusions and reflections","year":2009,"lang":"en","type":"article","venue":"Cancer","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre","funders":"","keywords":"Nomogram; Medicine; Outcome (game theory); Clinical trial; Disease; Risk stratification; Intensive care medicine; Cancer; Oncology; Internal medicine; Mathematical economics","score_opus":0.01997036788727629,"score_gpt":0.39301725245405283,"score_spread":0.37304688456677654,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2088293391","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7728416,0.0047714664,0.002970673,0.12321791,0.00045054228,0.00019537775,0.0000024442697,0.00015033419,0.09539969],"genre_scores_gemma":[0.98564816,0.00055375055,0.001350284,0.009391975,0.00024232318,0.0000039313895,0.0000016576491,0.000004171725,0.0028037229],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99975085,0.0000048405436,0.000046815603,0.000075318414,0.000048796952,0.00007335366],"domain_scores_gemma":[0.99981797,0.000010684129,0.0000103127,0.00005708321,0.000016634107,0.00008733735],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000038157432,0.000032047024,0.00006989141,0.000024291416,0.00007346373,0.0000060696234,0.000013319987,0.000018676823,0.00015090947],"category_scores_gemma":[0.000053968382,0.000025217067,0.000014486772,0.000057720245,0.000032796386,0.000015407544,0.0000067659475,0.00012931153,0.0000036336198],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000047996247,0.00008153127,0.022053644,0.000027594877,0.000044898596,0.00005692171,0.000875232,0.00003812632,0.0911361,0.008156818,0.05333144,0.82414967],"study_design_scores_gemma":[0.0013264843,0.00022568685,0.16158836,0.00015683318,0.00009627783,0.00017193818,0.00007904254,0.0041155117,0.0006724973,0.0020385778,0.82940245,0.00012634881],"about_ca_topic_score_codex":0.00002349919,"about_ca_topic_score_gemma":0.0000018041887,"teacher_disagreement_score":0.82402337,"about_ca_system_score_codex":0.000021782038,"about_ca_system_score_gemma":0.00003292121,"threshold_uncertainty_score":0.1652353},"labels":[],"label_agreement":null},{"id":"W2089668245","doi":"10.1088/0031-9155/51/10/007","title":"Wavelet-based feature extraction applied to small-angle x-ray scattering patterns from breast tissue: a tool for differentiating between tissue types","year":2006,"lang":"en","type":"article","venue":"Physics in Medicine and Biology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Engineering and Physical Sciences Research Council; University of New England; University of Saskatchewan","keywords":"Wavelet; Scattering; Small-angle X-ray scattering; Breast tissue; Feature (linguistics); Materials science; Synchrotron; Pattern recognition (psychology); Pixel; Feature extraction; Wavelet transform; Artificial intelligence; Biomedical engineering; Biological system; Optics; Computer science; Physics; Medicine; Biology; Breast cancer","score_opus":0.05439302601695005,"score_gpt":0.3547639366737121,"score_spread":0.300370910656762,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2089668245","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81578976,0.00010957037,0.17566432,0.007647382,0.00016114533,0.00042133732,0.00004937509,0.000039043196,0.000118101685],"genre_scores_gemma":[0.98472077,0.000009516814,0.009928685,0.0012997816,0.0029154427,0.0000546044,0.0009834623,0.000028192555,0.000059564718],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99893576,0.00003676051,0.00026732255,0.00037880032,0.000088137385,0.00029321492],"domain_scores_gemma":[0.9992579,0.0003553935,0.00009814924,0.000161968,0.000038889157,0.00008770182],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022001851,0.00019223802,0.0005077232,0.00009905724,0.000071904215,0.000012884351,0.000078443336,0.00012265459,0.000028980754],"category_scores_gemma":[0.00007690308,0.00014598812,0.000029938643,0.000111923204,0.00007904716,0.000020471582,0.00003388231,0.00034196588,0.000002994118],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009354707,0.000083953004,0.12110958,0.00016822777,0.00004695919,0.000008050648,0.00020620055,0.000041247236,0.38730597,0.0002658733,0.0005555231,0.49011487],"study_design_scores_gemma":[0.00786764,0.0009725199,0.9469924,0.0011434726,0.00048893696,0.000021814498,0.00018925706,0.0070170998,0.013369424,0.005351791,0.015924338,0.0006613291],"about_ca_topic_score_codex":0.0007033214,"about_ca_topic_score_gemma":0.000029804778,"teacher_disagreement_score":0.8258828,"about_ca_system_score_codex":0.000037959537,"about_ca_system_score_gemma":0.000019715764,"threshold_uncertainty_score":0.59532225},"labels":[],"label_agreement":null},{"id":"W2090094981","doi":"10.1016/j.jot.2014.07.122","title":"High resolution imaging of bone microarchitecture in the human appendicular skeleton","year":2014,"lang":"en","type":"article","venue":"Journal of Orthopaedic Translation","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Bone and Joint Health Institute; University of Calgary","funders":"","keywords":"Appendicular skeleton; Skeleton (computer programming); Microarchitecture; Human skeleton; Computer science; Anatomy; Medicine; Artificial intelligence","score_opus":0.008707684636396554,"score_gpt":0.2689405511110558,"score_spread":0.26023286647465926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2090094981","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93629247,0.0012129059,0.05205895,0.009808528,0.00014265378,0.00014415289,6.685074e-7,0.000007381264,0.00033226213],"genre_scores_gemma":[0.9934521,0.000048271082,0.005706456,0.00036680404,0.00039286038,8.745171e-7,0.000012668021,0.000012835386,0.0000071415006],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99838245,0.00021924838,0.00065514795,0.00009620134,0.0004996939,0.0001472886],"domain_scores_gemma":[0.99922657,0.00011201932,0.00038984694,0.00013509094,0.00007524792,0.000061252824],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023758726,0.000096309486,0.00030595498,0.00032202792,0.000055813383,0.000012109832,0.00009325394,0.000051065814,0.000019322102],"category_scores_gemma":[0.00016274858,0.00006290515,0.00019102069,0.00022235271,0.0000968696,0.00008127221,0.0000047398535,0.00067878567,6.3488915e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040154043,0.00038841917,0.23589298,0.00045833338,0.00008751277,0.000254944,0.0040487647,0.0049225283,0.21351692,0.0014978569,0.00066521106,0.537865],"study_design_scores_gemma":[0.012420042,0.0008713156,0.929158,0.001761035,0.00052300247,0.0027035617,0.00036068808,0.025404448,0.0018673796,0.0036689597,0.020997597,0.00026401103],"about_ca_topic_score_codex":0.00005590686,"about_ca_topic_score_gemma":0.000008147115,"teacher_disagreement_score":0.69326496,"about_ca_system_score_codex":0.00002545337,"about_ca_system_score_gemma":0.000041599447,"threshold_uncertainty_score":0.29490235},"labels":[],"label_agreement":null},{"id":"W2090264949","doi":"10.1016/s0960-9776(13)70042-0","title":"PO29 METASTATIC BREAST CANCER IN CANADA: THE LIVED EXPERIENCE OF PATIENTS AND CAREGIVERS PRESENTED BY THE CANADIAN BREAST CANCER NETWORK","year":2013,"lang":"en","type":"article","venue":"The Breast","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Canadian Breast Cancer Network","funders":"","keywords":"Medicine; Breast cancer; Metastatic breast cancer; Cancer; Oncology; Internal medicine","score_opus":0.00799752239242615,"score_gpt":0.24683036387587753,"score_spread":0.23883284148345138,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2090264949","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93692976,0.0012405532,0.000004033361,0.060321074,0.00021900807,0.00067620893,0.00037867588,0.0000072796456,0.00022338344],"genre_scores_gemma":[0.9967356,0.00017463107,0.000007042704,0.0026086713,0.00010475415,0.00012169044,0.000014108218,0.0000216393,0.00021190527],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99854654,0.00016044229,0.00024651986,0.00020882637,0.0003561921,0.00048148158],"domain_scores_gemma":[0.99899054,0.00014432678,0.00013161346,0.000306103,0.00015846388,0.000268945],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021163841,0.00017361836,0.0002607734,0.00003309231,0.00028079984,0.000037852034,0.0003343149,0.000027897499,0.00043665155],"category_scores_gemma":[0.00003243969,0.00008354728,0.00003625131,0.00028156294,0.0004194944,0.00006826642,0.00007182241,0.00041583914,0.0000016557705],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007263905,0.000036882455,0.88863856,0.000042801672,0.00016955215,0.00000891957,0.0049403,0.0008236986,0.000058158123,0.000020055819,0.058739793,0.046448622],"study_design_scores_gemma":[0.0007466329,0.000009020796,0.98497933,0.0001709271,0.00008484881,0.00017888674,0.0024101315,0.009827053,0.00000335013,0.000013270275,0.0014726749,0.000103867686],"about_ca_topic_score_codex":0.9993088,"about_ca_topic_score_gemma":0.99132377,"teacher_disagreement_score":0.09634076,"about_ca_system_score_codex":0.00051233073,"about_ca_system_score_gemma":0.001319287,"threshold_uncertainty_score":0.47810283},"labels":[],"label_agreement":null},{"id":"W2091615985","doi":"10.1158/0008-5472.sabcs13-p1-08-41","title":"Abstract P1-08-41: Pathologic response prediction to neoadjuvant chemotherapy utilizing pretreatment near infrared imaging and tumor pathologic criteria","year":2013,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Medicine; Chemotherapy; Receiver operating characteristic; Biopsy; Area under the curve; Nuclear medicine; Internal medicine; Oncology; Pathology; Radiology","score_opus":0.041908073661846,"score_gpt":0.3986300854668011,"score_spread":0.3567220118049551,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2091615985","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9826521,0.0015617951,0.0001416896,0.013033355,0.00020763364,0.0012988772,0.000019827117,0.00014129102,0.00094342086],"genre_scores_gemma":[0.9921164,0.0005587463,0.003594366,0.0022115326,0.00025623318,0.00053759885,0.000015399432,0.00005494395,0.0006547835],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9972985,0.0003367138,0.000353881,0.0006450621,0.00060323294,0.0007626337],"domain_scores_gemma":[0.9984111,0.0002956266,0.00006644331,0.00044921797,0.0002656699,0.00051193114],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0021939497,0.00023052697,0.00036807088,0.0002872918,0.00037031164,0.0002571827,0.0001762387,0.00008280513,0.0011058168],"category_scores_gemma":[0.0012028482,0.00017804514,0.00006631644,0.00036781267,0.0003883903,0.00018000604,0.00015253764,0.000868068,0.00009390974],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0020750866,0.00022632838,0.07719795,0.00022371866,0.000057348,0.0017458884,0.0034030182,0.000041678344,0.7028179,0.00001299508,0.02051558,0.19168249],"study_design_scores_gemma":[0.0032543913,0.00092635193,0.9618227,0.00071344816,0.000029297578,0.0005011901,0.0012256908,0.009780936,0.0056658196,0.0004414907,0.015353496,0.00028518972],"about_ca_topic_score_codex":0.00046051847,"about_ca_topic_score_gemma":0.0000018429415,"teacher_disagreement_score":0.8846248,"about_ca_system_score_codex":0.0003876695,"about_ca_system_score_gemma":0.00025413634,"threshold_uncertainty_score":0.9998073},"labels":[],"label_agreement":null},{"id":"W2095074548","doi":"10.1016/j.prro.2012.02.001","title":"Determination of planning target volume for whole stomach irradiation using daily megavoltage computed tomographic images","year":2012,"lang":"en","type":"article","venue":"Practical Radiation Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Montreal General Hospital","funders":"","keywords":"Medicine; Nuclear medicine; Computed tomographic; Volume (thermodynamics); Medical physics; Radiology; Radiation treatment planning; Radiation therapy; Computed tomography","score_opus":0.03497225492185256,"score_gpt":0.4075441523813727,"score_spread":0.37257189745952013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2095074548","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2628259,0.00055362517,0.72852135,0.0059513547,0.00076380424,0.0006472201,0.000017352217,0.000081756574,0.0006376455],"genre_scores_gemma":[0.78962225,0.0000139369085,0.2089789,0.0005742304,0.0005385429,0.000024974792,0.00016342539,0.000025902476,0.00005785167],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984425,0.00022444269,0.00048123152,0.00021692035,0.00026550147,0.00036942732],"domain_scores_gemma":[0.9978744,0.0010806695,0.00045899863,0.00014917378,0.00019312491,0.00024362675],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013449192,0.00014077473,0.00039885918,0.00032016172,0.00012884253,0.000020343854,0.00006174984,0.00020033127,0.000057613706],"category_scores_gemma":[0.003329101,0.00014003477,0.000107866676,0.00027749036,0.00011635984,0.00049455144,0.00002664727,0.00037995604,0.0000072958933],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012424579,0.0023730746,0.5651885,0.00063291524,0.00032704914,0.00005269443,0.0036770585,0.003257769,0.13144116,0.0031557195,0.010240978,0.2784106],"study_design_scores_gemma":[0.0025104617,0.0005687341,0.15251474,0.000044691333,0.00028291342,0.0001859624,0.00016377002,0.7731,0.0010532008,0.00027860363,0.069125764,0.00017110379],"about_ca_topic_score_codex":0.000022172919,"about_ca_topic_score_gemma":2.666589e-7,"teacher_disagreement_score":0.76984227,"about_ca_system_score_codex":0.00022933519,"about_ca_system_score_gemma":0.00022009175,"threshold_uncertainty_score":0.5710452},"labels":[],"label_agreement":null},{"id":"W2099698084","doi":"10.1088/0031-9155/60/14/5471","title":"A radiomics model from joint FDG-PET and MRI texture features for the prediction of lung metastases in soft-tissue sarcomas of the extremities","year":2015,"lang":"en","type":"article","venue":"Physics in Medicine and Biology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":895,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Medicine; Radiomics; Voxel; Nuclear medicine; Feature selection; Radiology; Artificial intelligence; Pattern recognition (psychology); Computer science","score_opus":0.11971171596931252,"score_gpt":0.3639329413583748,"score_spread":0.24422122538906227,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2099698084","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8294577,0.034884524,0.11297899,0.020855434,0.0004284872,0.0010300442,0.0001481988,0.000016940587,0.00019970324],"genre_scores_gemma":[0.9959145,0.0014556419,0.0016662608,0.0005984379,0.00026219708,0.000013678192,0.000052408657,0.000009742699,0.000027118662],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99925226,0.00007325179,0.00027020456,0.00017368542,0.00009620569,0.00013439398],"domain_scores_gemma":[0.99915844,0.00043294515,0.00012882454,0.0001746217,0.00005603884,0.00004914891],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005311962,0.000113299255,0.0004503956,0.00005103745,0.000033354874,0.000002673929,0.00008712162,0.00006001251,0.0000022888007],"category_scores_gemma":[0.0005283944,0.000056804674,0.000034204393,0.00010143142,0.00065596483,0.000025883113,0.00006133505,0.00031925875,1.878055e-8],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016790971,0.00064460124,0.3842377,0.0011673331,0.0008468919,0.000023916406,0.03296002,0.016499916,0.14770584,0.026113762,0.03416837,0.35395253],"study_design_scores_gemma":[0.0055491133,0.00043875794,0.025623053,0.0005768728,0.0003720228,0.000059125323,0.002499823,0.9207383,0.0010090132,0.04167357,0.0013510052,0.0001093625],"about_ca_topic_score_codex":0.0008207909,"about_ca_topic_score_gemma":0.00005420927,"teacher_disagreement_score":0.90423834,"about_ca_system_score_codex":0.000016911907,"about_ca_system_score_gemma":0.000056613277,"threshold_uncertainty_score":0.24169299},"labels":[],"label_agreement":null},{"id":"W2103004421","doi":"10.1038/ncomms5006","title":"Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach","year":2014,"lang":"en","type":"article","venue":"Nature Communications","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":5145,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University Health Network; Princess Margaret Cancer Centre","funders":"Interreg; National Cancer Institute; National Institutes of Health; Innovative Medicines Initiative; European Federation of Pharmaceutical Industries and Associations; Center for Translational Molecular Medicine; KWF Kankerbestrijding","keywords":"Radiomics; Radiogenomics; Lung cancer; Medicine; Head and neck cancer; Phenotype; Head and neck; Medical imaging; Cancer; Pathology; Radiology; Bioinformatics; Gene; Biology; Internal medicine; Surgery","score_opus":0.02495140181129539,"score_gpt":0.3432160363981265,"score_spread":0.3182646345868311,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2103004421","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21004085,0.036831737,0.639318,0.035069052,0.00081493484,0.0013670089,0.00004419327,0.0006140746,0.075900175],"genre_scores_gemma":[0.70351297,0.00022239708,0.29396963,0.0019545946,0.00008036535,0.0000104442115,0.00015619853,0.00003831763,0.00005508104],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986647,0.00022322393,0.00029508836,0.00028667698,0.00023996596,0.00029036982],"domain_scores_gemma":[0.9978002,0.00056265254,0.00017680564,0.0010770002,0.0002018788,0.00018149088],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00067059015,0.00018637317,0.0003306412,0.00016101343,0.00046321875,0.00006701433,0.00061697525,0.00014951616,0.0000097790535],"category_scores_gemma":[0.0016614709,0.00017452383,0.00011022839,0.00037202158,0.00027302522,0.0001280311,0.00022612988,0.0019576903,0.000010540969],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027313238,0.002153068,0.09494112,0.00045849945,0.0009361558,0.000032316177,0.0077906274,0.0017433026,0.38693947,0.36529228,0.07060973,0.068830304],"study_design_scores_gemma":[0.0010547674,0.000037216912,0.0012943825,0.00014229353,0.00019478405,0.0001854449,0.0004980013,0.9591377,0.00047107905,0.00043581708,0.036288723,0.000259792],"about_ca_topic_score_codex":0.00006283552,"about_ca_topic_score_gemma":0.0000057091383,"teacher_disagreement_score":0.9573944,"about_ca_system_score_codex":0.00014356195,"about_ca_system_score_gemma":0.00011061997,"threshold_uncertainty_score":0.8505299},"labels":[],"label_agreement":null},{"id":"W2106127561","doi":"10.1109/iembs.2010.5626469","title":"Identification of lobar fissures in pathological lungs","year":2010,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Foothills Medical Centre; University of Calgary","funders":"","keywords":"Fissure; Pathological; Oblique case; Identification (biology); Computer science; Artificial intelligence; Pattern recognition (psychology); Medicine; Geology; Pathology; Biology","score_opus":0.006645260435224976,"score_gpt":0.3028356846078534,"score_spread":0.2961904241726284,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2106127561","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9904145,0.000023805183,0.001137777,0.0029758436,0.00012724489,0.00007896694,3.2139593e-7,0.000022053753,0.00521946],"genre_scores_gemma":[0.99671656,0.000010791732,0.0021244949,0.00034999917,0.000049920363,0.0000027516207,0.000003947448,0.000004289925,0.00073722145],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99946874,0.000014994013,0.00020979214,0.00010559065,0.000117673306,0.00008322272],"domain_scores_gemma":[0.99970615,0.00003854495,0.0000416981,0.0001348311,0.000028669685,0.000050124385],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043419164,0.00004061571,0.00012298043,0.000061281215,0.000009903819,0.000004950665,0.0000521031,0.000055476095,0.00027006242],"category_scores_gemma":[0.00072355126,0.000028820486,0.000029426954,0.00008634511,0.00007787061,0.000022237411,0.000014508251,0.00030405642,0.000013424845],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018521887,0.000120083205,0.25568238,0.000032312084,0.0000044733083,0.000031772674,0.00011902515,0.0000062158506,0.72297674,0.0044956626,0.0009075713,0.015605241],"study_design_scores_gemma":[0.00071469415,0.00005530945,0.96431,0.000022761025,0.000017055474,0.000069979535,0.00005247599,0.011838208,0.018123284,0.0010601024,0.0036732554,0.00006286797],"about_ca_topic_score_codex":0.000037275346,"about_ca_topic_score_gemma":0.0000071237764,"teacher_disagreement_score":0.70862764,"about_ca_system_score_codex":0.000004388601,"about_ca_system_score_gemma":0.000016026599,"threshold_uncertainty_score":0.29569942},"labels":[],"label_agreement":null},{"id":"W2107990686","doi":"10.1109/iembs.2009.5333083","title":"A study on using texture analysis methods for identifying lobar fissure regions in isotropic CT images","year":2009,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Artificial intelligence; Computer science; Texture (cosmology); Pattern recognition (psychology); Fissure; Segmentation; Materials science; Visualization; Computer vision; Artificial neural network; Gray level; Image (mathematics); Composite material","score_opus":0.0650109108299163,"score_gpt":0.4728163564509305,"score_spread":0.40780544562101423,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2107990686","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40246353,0.00028889868,0.5895292,0.005684547,0.00008971596,0.0007053554,0.0000013705019,0.00007486917,0.001162515],"genre_scores_gemma":[0.8637354,0.000012308338,0.13382982,0.001525792,0.00010673443,0.000009258334,0.000009522656,0.000015154413,0.00075600896],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99863976,0.00017600946,0.00032252862,0.00038000176,0.00019535398,0.00028633102],"domain_scores_gemma":[0.9991955,0.00020733211,0.00008121131,0.0003396904,0.00005357753,0.0001227011],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00083941384,0.0001656256,0.0005493609,0.00057289726,0.00011145075,0.000051978175,0.000113433576,0.00004222871,0.000046964786],"category_scores_gemma":[0.0006888889,0.00012672938,0.00023106275,0.0009287182,0.000028672064,0.00006558966,0.000020340134,0.00041525214,0.0000020280588],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004948903,0.0046577705,0.54624754,0.00023945785,0.0039018514,0.001596458,0.0057350453,0.012382059,0.044203088,0.0030192633,0.0076062316,0.36991635],"study_design_scores_gemma":[0.006582556,0.0013912845,0.6956079,0.00030431623,0.0051011145,0.00012920154,0.0049027754,0.27835736,0.0008950948,0.0023785555,0.0037912223,0.00055863365],"about_ca_topic_score_codex":0.00017769895,"about_ca_topic_score_gemma":0.000019061768,"teacher_disagreement_score":0.46127185,"about_ca_system_score_codex":0.00008075859,"about_ca_system_score_gemma":0.00003590636,"threshold_uncertainty_score":0.51678747},"labels":[],"label_agreement":null},{"id":"W2108471456","doi":"10.1093/jnci/djm273","title":"Press Release: PET Imaging May Improve Lung Cancer Diagnosis","year":2007,"lang":"en","type":"article","venue":"JNCI Journal of the National Cancer Institute","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Lung cancer; Medicine; Pet imaging; Cancer; Radiology; Medical physics; Nuclear medicine; Positron emission tomography; Pathology; Internal medicine","score_opus":0.020346112185732786,"score_gpt":0.3717161922210143,"score_spread":0.35137008003528153,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2108471456","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8243034,0.023676015,0.005219037,0.11069144,0.023171801,0.00077381096,0.00013969233,0.00006022527,0.011964577],"genre_scores_gemma":[0.98379695,0.0016254768,0.0014023596,0.0066591855,0.0050832327,0.000031747153,0.0000029150249,0.000026419124,0.0013717246],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99789387,0.00003200749,0.0005189,0.00015043108,0.0011478842,0.00025688892],"domain_scores_gemma":[0.9983003,0.00012960313,0.0005050453,0.00010918343,0.00075613515,0.00019970028],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011020795,0.00014115701,0.00025693746,0.00013880305,0.00017444284,0.00004117521,0.0002911968,0.000036335314,0.0001483064],"category_scores_gemma":[0.0010003012,0.000092079485,0.00021668585,0.00021005374,0.00016205733,0.0003002006,0.00006405311,0.0008262445,0.0000011414414],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008123485,0.00033419763,0.52798736,0.0004001424,0.0009363643,0.00060428726,0.0005187569,0.013268228,0.010209148,0.0021079138,0.29969853,0.14312273],"study_design_scores_gemma":[0.0040804255,0.000053484382,0.14505114,0.0014913009,0.00060602487,0.0014497644,0.00003422824,0.016554607,0.00825925,0.00033357955,0.82178843,0.00029777194],"about_ca_topic_score_codex":0.00050747267,"about_ca_topic_score_gemma":0.00005130228,"teacher_disagreement_score":0.5220899,"about_ca_system_score_codex":0.0007989023,"about_ca_system_score_gemma":0.0007926053,"threshold_uncertainty_score":0.37548926},"labels":[],"label_agreement":null},{"id":"W2109519833","doi":"10.1158/1538-7445.am2014-554","title":"Abstract 554: GPNMB methylation: a new marker of potentially colonic adenoma in African Americans","year":2014,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University; McGill University","funders":"","keywords":"Methylation; Epigenetics; DNA methylation; Colorectal cancer; CpG site; Cancer research; Malignant transformation; Colorectal adenoma; Adenoma; Immunohistochemistry; Biology; Microsatellite instability; Cancer; Pathology; Molecular biology; Medicine; Internal medicine; Gene expression; Gene; Genetics; Allele","score_opus":0.05216958375374868,"score_gpt":0.41813036254488767,"score_spread":0.365960778791139,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2109519833","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9599817,0.0011445703,0.0016420844,0.017858893,0.00013896354,0.00039024386,0.000003134693,0.000025080524,0.01881536],"genre_scores_gemma":[0.99561214,0.00026567266,0.0014222625,0.0002271019,0.00032846772,0.000030408492,0.00000583168,0.000026246691,0.0020818894],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9981344,0.00017909297,0.0002983854,0.0002733093,0.00069153105,0.0004233025],"domain_scores_gemma":[0.9988799,0.00031102975,0.000078562945,0.00028796578,0.00016642602,0.00027608164],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0017020176,0.00009443298,0.00031872178,0.00032820718,0.000052324212,0.00002085581,0.00019880262,0.00006505168,0.00092003535],"category_scores_gemma":[0.00096595864,0.000082899234,0.000066419765,0.00069992023,0.00027595114,0.000047910347,0.00006588215,0.0008534159,0.000020992902],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010930586,0.00027953167,0.07866629,0.00047279874,0.00016741223,0.00013133,0.0020622974,0.0007036695,0.17864458,0.0010619861,0.022469377,0.71424764],"study_design_scores_gemma":[0.003257384,0.00053621817,0.84171385,0.0005799931,0.0000412249,0.000018954759,0.000338773,0.005998708,0.0028523642,0.0010961217,0.14335087,0.00021554784],"about_ca_topic_score_codex":0.0067221522,"about_ca_topic_score_gemma":0.00018515672,"teacher_disagreement_score":0.7630476,"about_ca_system_score_codex":0.00019701067,"about_ca_system_score_gemma":0.0007561309,"threshold_uncertainty_score":0.99999326},"labels":[],"label_agreement":null},{"id":"W2113725597","doi":"10.1016/j.jvir.2011.01.297","title":"Abstract No. 269: Initial experience using a new interventional CT navigation tool (Activiews) for percutaneous CT guided ablation and biopsy","year":2011,"lang":"en","type":"article","venue":"Journal of Vascular and Interventional Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Medicine; Ablation; Percutaneous; Target lesion; Guidance system; Radiology; Point (geometry); Biopsy; Navigation system; Computer vision; Medical physics; Artificial intelligence; Computer science","score_opus":0.05227330252775111,"score_gpt":0.3637325898234286,"score_spread":0.3114592872956775,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2113725597","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9448836,0.001814455,0.05237235,0.00015835547,0.0004890637,0.00016768821,0.0000044290487,0.0000068239547,0.00010323126],"genre_scores_gemma":[0.9774297,0.00012934042,0.02170517,0.00010446311,0.0005302473,0.0000033339534,0.000026625452,0.000015078646,0.000056025496],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9986683,0.00007569523,0.00071204256,0.00018590604,0.00019985993,0.00015820503],"domain_scores_gemma":[0.99906564,0.00008927353,0.00040340144,0.000078875455,0.0002134359,0.00014940207],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00076016015,0.00013640542,0.00037456633,0.00016315604,0.00008636577,0.000026821703,0.00007390562,0.000046319037,0.00033198338],"category_scores_gemma":[0.00064721174,0.00011263807,0.00044922525,0.00004871558,0.00014603084,0.000245813,0.000028375895,0.00029207772,0.0000017342603],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0064726328,0.004317232,0.17043804,0.0043457244,0.008609202,0.0062397397,0.0074878302,0.00062067894,0.27692476,0.012796627,0.007842227,0.4939053],"study_design_scores_gemma":[0.014386354,0.006104833,0.4554208,0.0056487126,0.001397114,0.42298144,0.00067955576,0.058779452,0.0018077892,0.013444297,0.018451517,0.00089813955],"about_ca_topic_score_codex":0.00008591991,"about_ca_topic_score_gemma":7.0554387e-7,"teacher_disagreement_score":0.49300715,"about_ca_system_score_codex":0.00006516328,"about_ca_system_score_gemma":0.0000917343,"threshold_uncertainty_score":0.4593247},"labels":[],"label_agreement":null},{"id":"W2115813732","doi":"10.1259/bjr/25400972","title":"Imaging in antiangiogenesis trial: a clinical trials radiology perspective","year":2003,"lang":"en","type":"review","venue":"British Journal of Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Clinical trial; Medicine; Medical physics; Positron emission tomography; Radiological weapon; Traceability; Radiation treatment planning; Radiology; Radiation therapy; Computer science; Pathology","score_opus":0.1090958938797497,"score_gpt":0.47891879402175597,"score_spread":0.36982290014200625,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2115813732","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00040313872,0.99241966,0.0006577695,0.0005982986,0.004100655,0.0011740506,0.000014991484,0.000019427694,0.0006120066],"genre_scores_gemma":[0.00007551953,0.9930928,0.002272459,0.00069832284,0.0035417671,0.000024673047,0.000024502004,0.00011191358,0.00015805465],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9797924,0.012722206,0.0058283675,0.00066164474,0.0003160299,0.0006793351],"domain_scores_gemma":[0.99045336,0.0046511414,0.003725205,0.00033563704,0.00034211553,0.0004925544],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.027396204,0.0004973755,0.011043305,0.0010799692,0.00007397405,0.000056249217,0.00048121123,0.0008572577,0.00020837084],"category_scores_gemma":[0.03546404,0.00043821058,0.003772304,0.00050201593,0.00059119234,0.00008594765,0.000059579637,0.003653225,0.000013759371],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014759575,0.000304034,0.0004203578,0.0007801096,0.0009996924,0.016880928,0.00003202852,0.0000016338626,7.818825e-7,0.0001182203,0.02596351,0.9530227],"study_design_scores_gemma":[0.02488602,0.00063402683,0.00012282925,0.008313752,0.002425646,0.40202788,0.000066147986,0.000016366715,4.050636e-8,0.00018069099,0.56106526,0.00026136238],"about_ca_topic_score_codex":0.00009565462,"about_ca_topic_score_gemma":0.00000518577,"teacher_disagreement_score":0.9527614,"about_ca_system_score_codex":0.00048387592,"about_ca_system_score_gemma":0.0019779156,"threshold_uncertainty_score":0.99980694},"labels":[],"label_agreement":null},{"id":"W2119440128","doi":"10.3174/ajnr.a2061","title":"Texture Analysis: A Review of Neurologic MR Imaging Applications","year":2010,"lang":"en","type":"review","venue":"American Journal of Neuroradiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":414,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Hospital for Sick Children","funders":"Canadian Institutes of Health Research; Canadian Stroke Network","keywords":"Texture (cosmology); Medicine; Segmentation; Epilepsy; Artificial intelligence; Image texture; Pattern recognition (psychology); Neuroscience; Pathology; Computer vision; Image segmentation; Computer science; Image (mathematics); Biology","score_opus":0.013702511816600533,"score_gpt":0.3628712415156012,"score_spread":0.34916872969900065,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2119440128","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00003649931,0.99414116,0.0023868224,0.0025115618,0.00021840754,0.00043846745,0.000011002301,0.000016687032,0.000239387],"genre_scores_gemma":[0.00024057493,0.99222845,0.001857191,0.005000163,0.00053603254,0.000024101984,0.000038253864,0.000053521726,0.000021695025],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99646044,0.0007255728,0.0017963953,0.00038288353,0.00031382398,0.00032091385],"domain_scores_gemma":[0.99388283,0.0006667563,0.0041616424,0.0006599376,0.00031596582,0.0003128923],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.00096458336,0.00038489327,0.0056179976,0.0009795241,0.000042999018,0.000008670427,0.00061421003,0.00012618786,0.000072862764],"category_scores_gemma":[0.0010656861,0.00025762556,0.00188195,0.0018949962,0.0008545536,0.000036331017,0.000071223934,0.0032645476,0.000006603086],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010880092,0.00007106289,0.00045970242,0.012128035,0.0007254254,0.00026024962,0.000007854493,0.0000023329117,0.000011033437,0.000029741848,0.00065558206,0.9856381],"study_design_scores_gemma":[0.00016161663,0.0005646494,0.00016396493,0.008353046,0.017032348,0.014330041,0.0000059726567,0.00005839123,9.28321e-8,0.000013229375,0.95915973,0.00015690284],"about_ca_topic_score_codex":0.0000067696424,"about_ca_topic_score_gemma":2.1547312e-7,"teacher_disagreement_score":0.9854812,"about_ca_system_score_codex":0.000033176937,"about_ca_system_score_gemma":0.0005066482,"threshold_uncertainty_score":0.9999876},"labels":[],"label_agreement":null},{"id":"W2119872305","doi":"10.1016/j.compmedimag.2015.04.006","title":"Preliminary investigation into sources of uncertainty in quantitative imaging features","year":2015,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":94,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"National Cancer Institute; American Association of Physicists in Medicine; Radiological Society of North America","keywords":"Texture (cosmology); Breathing; Feature (linguistics); Lung cancer; Region of interest; Nuclear medicine; Medicine; Computer science; Mathematics; Radiology; Biomedical engineering; Artificial intelligence; Image (mathematics); Pathology","score_opus":0.017770306139179723,"score_gpt":0.3098605386461667,"score_spread":0.29209023250698696,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2119872305","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9604677,0.0054029417,0.011572457,0.02169523,0.00034355617,0.00020982958,0.0000013598212,0.00009002802,0.00021687527],"genre_scores_gemma":[0.9823059,0.0003123489,0.013820758,0.0033356922,0.00013010061,0.000008302032,0.000035839108,0.000023921366,0.000027180464],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981419,0.00018406853,0.0004486643,0.00034210618,0.0006178848,0.00026536506],"domain_scores_gemma":[0.9985702,0.00035488216,0.00014351356,0.00018512586,0.00016396299,0.00058233814],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013473397,0.00018817768,0.00046991193,0.0003825095,0.00006290352,0.00003386493,0.00014935462,0.00007833941,0.0000044771473],"category_scores_gemma":[0.0017649583,0.0001563226,0.00007090153,0.00041852085,0.000976091,0.000120158875,0.0001470086,0.0007016272,7.48774e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009834176,0.00035335936,0.60849637,0.0009500184,0.00012553281,0.0010959493,0.022033948,0.0004096959,0.0021389062,0.00877308,0.006084704,0.34855503],"study_design_scores_gemma":[0.005670727,0.00025068974,0.08437334,0.0018568808,0.00008235258,0.00067554123,0.0017633971,0.89159065,0.0001223619,0.011077039,0.0022487158,0.00028832728],"about_ca_topic_score_codex":0.0010037145,"about_ca_topic_score_gemma":0.000011393333,"teacher_disagreement_score":0.89118093,"about_ca_system_score_codex":0.000032172986,"about_ca_system_score_gemma":0.00025838497,"threshold_uncertainty_score":0.637465},"labels":[],"label_agreement":null},{"id":"W2120254749","doi":"10.3174/ajnr.a4110","title":"MRI Texture Analysis Predicts p53 Status in Head and Neck Squamous Cell Carcinoma","year":2014,"lang":"en","type":"article","venue":"American Journal of Neuroradiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":91,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Health Services; University of Calgary","funders":"","keywords":"Medicine; Head and neck squamous-cell carcinoma; Radiology; Head and neck cancer; Carcinoma; Pathology; Oncology; Cancer; Internal medicine","score_opus":0.00577654971546891,"score_gpt":0.2612694031756125,"score_spread":0.25549285346014355,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2120254749","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9924552,0.00043983024,0.002474844,0.0038048693,0.0001525617,0.000067436325,0.0000018336598,0.000009915416,0.00059352256],"genre_scores_gemma":[0.9945328,0.00018851705,0.0020974015,0.0028652104,0.00025234118,0.0000010183204,0.000004442729,0.000021401718,0.00003683025],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9982983,0.00037812302,0.0005062368,0.00024357965,0.0001849522,0.00038880887],"domain_scores_gemma":[0.9984782,0.0003845615,0.00043515177,0.00020782276,0.00007622376,0.0004180441],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042584687,0.00016291862,0.0009288987,0.00059891865,0.00003603437,0.000012976757,0.00012828845,0.00005508465,0.000020845097],"category_scores_gemma":[0.00056988513,0.00012701699,0.00014888475,0.0006249554,0.00040684492,0.000048994538,0.000033867353,0.0008947191,0.0000015576361],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023479597,0.00009163219,0.9745819,0.000021859516,0.00006572687,0.00044432687,0.0004084577,0.0011029127,0.0012722693,0.00001940077,0.0004788931,0.021277806],"study_design_scores_gemma":[0.0025285766,0.0042947032,0.9622164,0.00001657907,0.00044171241,0.0017360826,0.00015221328,0.022272196,0.000021757347,0.00003892435,0.0061677224,0.00011316631],"about_ca_topic_score_codex":0.00022094807,"about_ca_topic_score_gemma":0.000013639898,"teacher_disagreement_score":0.021169282,"about_ca_system_score_codex":0.000043158005,"about_ca_system_score_gemma":0.00009433575,"threshold_uncertainty_score":0.51796025},"labels":[],"label_agreement":null},{"id":"W2120507475","doi":"10.1016/j.jvir.2009.04.052","title":"Emerging Technologies Articles","year":2009,"lang":"en","type":"article","venue":"Journal of Vascular and Interventional Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Medicine; Emerging technologies; Interventional radiology; Variety (cybernetics); Library science; Medical physics; Radiology; Computer science; Artificial intelligence","score_opus":0.009796032960949495,"score_gpt":0.3028374812811568,"score_spread":0.2930414483202073,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2120507475","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9538456,0.011854702,0.017097838,0.016657604,0.00015477154,0.00004084245,2.6871183e-7,0.00002257786,0.0003257793],"genre_scores_gemma":[0.99448806,0.0006885759,0.004262404,0.00038331276,0.00012976152,3.3733428e-7,0.0000011403811,0.000003718338,0.00004268924],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9993236,0.000039510873,0.0003182187,0.00007554476,0.00013270386,0.000110408626],"domain_scores_gemma":[0.99964267,0.00003371856,0.00012870667,0.00006433703,0.00007248127,0.000058063706],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005198716,0.00006210618,0.0002480819,0.00017452579,0.00003564333,0.000010096354,0.00006305605,0.000053461583,0.000051188683],"category_scores_gemma":[0.00048448547,0.000044183515,0.00025694675,0.00006492819,0.0000934617,0.0000638575,0.000014626419,0.00030818983,0.0000014833308],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026577213,0.0005267163,0.04107074,0.00008613992,0.00080773263,0.0004718639,0.0002220635,0.00010454334,0.026845522,0.019331105,0.008654123,0.90161365],"study_design_scores_gemma":[0.009343646,0.009995869,0.7267633,0.0013866029,0.0007928684,0.041478414,0.0012194897,0.0107092615,0.003043797,0.08224255,0.11260677,0.00041741977],"about_ca_topic_score_codex":0.000001412142,"about_ca_topic_score_gemma":1.18372455e-7,"teacher_disagreement_score":0.90119624,"about_ca_system_score_codex":0.000018351395,"about_ca_system_score_gemma":0.00002013356,"threshold_uncertainty_score":0.18017514},"labels":[],"label_agreement":null},{"id":"W2121202398","doi":"10.6000/1929-6029.2014.03.04.2","title":"Application of Survival Tree Based on Texture Features Obtained through MRI of Patients with Brain Metastases from Breast Cancer","year":2014,"lang":"en","type":"article","venue":"International Journal of Statistics in Medical Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Covariate; Proportional hazards model; Medicine; Breast cancer; Magnetic resonance imaging; Survival analysis; Cancer; Wavelet; Radiology; Statistics; Artificial intelligence; Internal medicine; Mathematics; Computer science","score_opus":0.015311792806623049,"score_gpt":0.3985411081200439,"score_spread":0.38322931531342086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2121202398","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1736052,0.00014705586,0.78530294,0.03744022,0.00051353825,0.00036280983,0.0014474718,0.0000072356643,0.0011735319],"genre_scores_gemma":[0.98072344,0.00009903645,0.017958462,0.00063928217,0.00034896185,0.0000057767056,0.00018291922,0.000018353438,0.000023782488],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9941987,0.00039874983,0.00061330997,0.00016970896,0.0044295574,0.0001900173],"domain_scores_gemma":[0.9933648,0.0039822464,0.00036401136,0.00015613646,0.00193353,0.00019927965],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025442308,0.00010932658,0.00042211617,0.00034856334,0.000024091236,0.0000147675755,0.00044249816,0.000088831344,0.0003540599],"category_scores_gemma":[0.008234294,0.000073012015,0.000055161876,0.00023980933,0.0004228258,0.000050931154,0.000049713366,0.0011423851,9.4664966e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0064594722,0.0018907714,0.41435483,0.00017446112,0.0004539246,0.0001992295,0.0003797606,0.0018843764,0.00056434236,0.0123870075,0.009720654,0.55153114],"study_design_scores_gemma":[0.00943354,0.0010610396,0.8837663,0.0017088891,0.00006444223,0.00001665095,0.0001162626,0.093712755,0.00025254415,0.005071245,0.004677781,0.000118581906],"about_ca_topic_score_codex":0.00089736737,"about_ca_topic_score_gemma":0.00012184452,"teacher_disagreement_score":0.80711824,"about_ca_system_score_codex":0.00013708916,"about_ca_system_score_gemma":0.00051399565,"threshold_uncertainty_score":0.9857814},"labels":[],"label_agreement":null},{"id":"W2121287965","doi":"10.1016/j.jalz.2011.05.2095","title":"P4‐074: Automated quantification of [18F]flutemetamol amyloid imaging data","year":2011,"lang":"en","type":"article","venue":"Alzheimer s & Dementia","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Nuclear medicine; Voxel; Medicine; Cognitive impairment; Standardized uptake value; Positron emission tomography; Radiology; Psychology; Pathology; Disease","score_opus":0.06807156492970201,"score_gpt":0.33045543272469347,"score_spread":0.26238386779499145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2121287965","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5033417,0.29979247,0.11482918,0.011402662,0.0059388825,0.004368641,0.00021927031,0.004605841,0.055501375],"genre_scores_gemma":[0.9707298,0.00009829031,0.02820668,0.00046143684,0.00008890639,0.000009334366,0.00034962455,0.000042843636,0.000013043005],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982502,0.00007692336,0.000555054,0.0004596148,0.0003510978,0.00030714722],"domain_scores_gemma":[0.99825454,0.000042743613,0.0002644936,0.0011559761,0.00012497714,0.00015729512],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00076179154,0.00018044017,0.00032960266,0.00016157517,0.00008480492,0.000021653155,0.0004683469,0.0000430262,0.00056352734],"category_scores_gemma":[0.00016258057,0.00016252072,0.00007605734,0.0002386497,0.0001700051,0.00025263318,0.0002151174,0.00024105985,0.00009555551],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028555817,0.0014875223,0.27956727,0.00016944479,0.0277301,0.00022538015,0.0016995524,0.00002380468,0.19412693,0.0031715594,0.07945465,0.4120582],"study_design_scores_gemma":[0.0036815447,0.00020962827,0.33729598,0.00030918885,0.0482691,0.00026200278,0.00027343095,0.4555771,0.103405245,0.00038377885,0.049523305,0.00080970523],"about_ca_topic_score_codex":0.0006365829,"about_ca_topic_score_gemma":0.0000048888523,"teacher_disagreement_score":0.46738818,"about_ca_system_score_codex":0.000004393299,"about_ca_system_score_gemma":0.00008099902,"threshold_uncertainty_score":0.66274023},"labels":[],"label_agreement":null},{"id":"W2123970632","doi":"10.1155/2000/965613","title":"Malignancy‐Associated Changes in Breast Tissue Detected by Image Cytometry","year":2000,"lang":"en","type":"article","venue":"Analytical Cellular Pathology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; BC Cancer Agency","funders":"KWF Kankerbestrijding","keywords":"Malignancy; Pathology; Breast cancer; Ductal carcinoma; Feulgen stain; Hyperplasia; Cytometry; Medicine; Carcinoma; Cancer; Atypical hyperplasia; Flow cytometry; Internal medicine; Staining; Immunology","score_opus":0.006180072758052516,"score_gpt":0.2662031254483104,"score_spread":0.2600230526902579,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2123970632","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.984538,0.00044837495,0.0010907964,0.0077723344,0.00006460233,0.00018357417,0.000022168955,0.00010762773,0.0057724966],"genre_scores_gemma":[0.9927477,0.00017551293,0.00045675176,0.0016617703,0.00011168174,0.0000107680635,0.00018170675,0.000041838208,0.004612272],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99816984,0.00020377547,0.0003353896,0.00044691196,0.0002524932,0.0005916066],"domain_scores_gemma":[0.9992369,0.000106889755,0.00005495112,0.00028319092,0.00005210475,0.00026596207],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004934093,0.00020693475,0.0005372344,0.00023990442,0.000052889325,0.00001973113,0.0001400094,0.00026513642,0.0036120783],"category_scores_gemma":[0.00032636378,0.00018685129,0.00007930476,0.00062344933,0.000255632,0.000037692393,0.00003679036,0.0006913278,0.00030432042],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002042114,0.0010322107,0.06955309,0.00009549658,0.00013290464,0.0146226585,0.00023382997,0.000009847171,0.8148609,0.00014318929,0.0074437284,0.091667935],"study_design_scores_gemma":[0.023477942,0.0035903796,0.58624405,0.0010613215,0.0016548288,0.008997327,0.00032986104,0.20780206,0.08925309,0.0016303848,0.07288496,0.003073789],"about_ca_topic_score_codex":0.00008408963,"about_ca_topic_score_gemma":0.0000134578095,"teacher_disagreement_score":0.7256078,"about_ca_system_score_codex":0.00008588823,"about_ca_system_score_gemma":0.000034160497,"threshold_uncertainty_score":0.9972988},"labels":[],"label_agreement":null},{"id":"W2128625986","doi":"10.1038/nrclinonc.2012.196","title":"Predicting outcomes in radiation oncology—multifactorial decision support systems","year":2012,"lang":"en","type":"review","venue":"Nature Reviews Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":395,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Institute for Cancer Research","funders":"Interreg; National Cancer Institute; KWF Kankerbestrijding; Center for Translational Molecular Medicine; European Commission","keywords":"Medicine; Radiation oncology; Predictive modelling; Outcome (game theory); Decision support system; Medical physics; Clinical decision support system; Clinical Oncology; Population; Precision medicine; Oncology; Radiation therapy; Intensive care medicine; Internal medicine; Data mining; Pathology; Computer science; Machine learning; Cancer","score_opus":0.1317209994531531,"score_gpt":0.5501465579063007,"score_spread":0.41842555845314766,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2128625986","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000033229164,0.9651482,0.00010582439,0.0005049234,0.02710715,0.004314504,0.000020272018,0.0000951619,0.0026707212],"genre_scores_gemma":[0.00004411971,0.98358613,0.0038821273,0.0012490007,0.009877093,0.00034502987,0.00047544306,0.00012671844,0.00041432554],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98608404,0.004223312,0.006921728,0.0011620797,0.0006830237,0.0009257977],"domain_scores_gemma":[0.9806278,0.013625143,0.0037148613,0.00097554584,0.0001512276,0.0009054305],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.018430943,0.00086888386,0.013412498,0.000551164,0.000090321395,0.000035124318,0.00059766206,0.007532115,0.00021176579],"category_scores_gemma":[0.0350837,0.00054889603,0.002320226,0.00061668555,0.00022901203,0.00014188579,0.0002552753,0.014275424,0.0005720609],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007664805,0.0008324715,0.013302328,0.007846587,0.00024549698,0.0002133069,0.00002588396,4.885273e-7,5.9309922e-8,0.00006365402,0.00618862,0.97120446],"study_design_scores_gemma":[0.0030838943,0.0010595362,0.0009970727,0.012324572,0.0034949335,0.0004349205,0.000005900073,0.00014464058,7.1397985e-9,0.0000073146757,0.9780357,0.00041152953],"about_ca_topic_score_codex":0.000038858878,"about_ca_topic_score_gemma":0.000020614127,"teacher_disagreement_score":0.97184706,"about_ca_system_score_codex":0.0018909308,"about_ca_system_score_gemma":0.0024933466,"threshold_uncertainty_score":0.99969625},"labels":[],"label_agreement":null},{"id":"W2129806783","doi":"10.1212/wnl.82.10_supplement.p2.242","title":"Rate of Agreement for Manual and Automated Techniques for Determination of New T2 Lesions in Children with Multiple Sclerosis and Acute Demyelination (P2.242)","year":2014,"lang":"en","type":"article","venue":"Neurology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University; Montreal Neurological Institute and Hospital; Hospital for Sick Children; University of Toronto","funders":"","keywords":"Multiple sclerosis; Medicine; Immunology","score_opus":0.013732249487360631,"score_gpt":0.2947323381986735,"score_spread":0.2810000887113129,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2129806783","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95047003,0.0000190409,0.04662841,0.0022275457,0.000013754154,0.0006008289,0.00000560248,0.000027473829,0.000007291281],"genre_scores_gemma":[0.9750832,0.000054206903,0.024322236,0.0004364482,0.000024696292,0.00003423154,0.00002465214,0.000009729918,0.0000106198495],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9995185,0.000037784775,0.00016923471,0.00014074282,0.000042640397,0.000091071444],"domain_scores_gemma":[0.9995784,0.00017014664,0.000105118124,0.0000619702,0.000046154793,0.000038172344],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025931754,0.00006131383,0.00018829315,0.00011670588,0.000022659606,0.0000025971883,0.000026851372,0.000057253837,8.8499576e-7],"category_scores_gemma":[0.0002335639,0.000049681097,0.0000149851585,0.000042260435,0.00006851449,0.000026875188,0.000016789072,0.00007090935,3.1872673e-8],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013245546,0.00012408303,0.37586522,0.00016537787,0.000058973088,9.922312e-7,0.00029623904,0.00002920552,0.09980748,0.00029272353,0.00028727093,0.5217479],"study_design_scores_gemma":[0.0032544048,0.0025387253,0.7496972,0.00004661885,0.00009779285,0.00002636453,0.0000023389227,0.23447055,0.009395684,0.00024948557,0.00017506148,0.000045781893],"about_ca_topic_score_codex":0.000089800094,"about_ca_topic_score_gemma":0.00002750153,"teacher_disagreement_score":0.5217021,"about_ca_system_score_codex":0.000003842911,"about_ca_system_score_gemma":0.000015843236,"threshold_uncertainty_score":0.20259362},"labels":[],"label_agreement":null},{"id":"W2130674512","doi":"10.1002/widm.1131","title":"Biomedical informatics and panomics for evidence‐based radiation therapy","year":2014,"lang":"en","type":"article","venue":"Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Canadian Institutes of Health Research","keywords":"Informatics; Translational bioinformatics; Radiation therapy; Health informatics; Computer science; Medical physics; Data science; Personalized medicine; Precision medicine; Interface (matter); Bioinformatics; Translational research informatics; Radiation oncology; Systems biology; Health informatics tools; Medicine; Genomics; Engineering informatics; Pathology; Biology; Genome; Internal medicine","score_opus":0.08553935413831011,"score_gpt":0.39373271732820714,"score_spread":0.30819336318989704,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2130674512","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5933101,0.18077958,0.2144439,0.006535922,0.0013879198,0.0022671544,0.00020647133,0.00012994288,0.0009389977],"genre_scores_gemma":[0.7242819,0.15740606,0.10389657,0.0045442744,0.0032809419,0.00031471162,0.0052388865,0.00015583253,0.00088080455],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984014,0.00013398138,0.00068443787,0.00038873253,0.00012840651,0.00026302747],"domain_scores_gemma":[0.99807936,0.0007522929,0.00023611182,0.00066053553,0.000041653686,0.00023004539],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002286842,0.000242911,0.0006304909,0.00015010059,0.00021822056,0.00015877957,0.00026409517,0.000098470955,0.000007309739],"category_scores_gemma":[0.0012969159,0.00017281686,0.00008963044,0.00013190649,0.00026648835,0.0007753019,0.0005737076,0.00021880309,0.0000064385204],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017657314,0.00010884916,0.004737082,0.0011461183,0.000041909458,0.0000012833561,0.0013790262,8.394742e-7,0.00021142531,0.00004822548,0.02298231,0.96916634],"study_design_scores_gemma":[0.0027850762,0.0011533413,0.0022840174,0.008029062,0.00024847744,0.00009613898,0.00064286106,0.54053193,0.000028257859,0.00009207205,0.4437367,0.00037207123],"about_ca_topic_score_codex":0.0000019592399,"about_ca_topic_score_gemma":0.0000016503428,"teacher_disagreement_score":0.9687943,"about_ca_system_score_codex":0.00003227427,"about_ca_system_score_gemma":0.00011606616,"threshold_uncertainty_score":0.7047267},"labels":[],"label_agreement":null},{"id":"W2131251288","doi":"10.1109/tbme.2009.2014074","title":"Segmentation of Lung Lobes in High-Resolution Isotropic CT Images","year":2009,"lang":"en","type":"article","venue":"IEEE Transactions on Biomedical Engineering","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":71,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"High resolution; Segmentation; Computer vision; Isotropy; Image segmentation; Artificial intelligence; Image resolution; Computer science; Materials science; Optics; Physics; Geology; Remote sensing","score_opus":0.004772016931179973,"score_gpt":0.2497108987622366,"score_spread":0.2449388818310566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2131251288","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35568312,0.0000861789,0.6423422,0.0013517526,0.0002957925,0.00013095343,0.0000047069652,0.00007315486,0.0000321283],"genre_scores_gemma":[0.9910233,0.00015006195,0.008516992,0.00015993093,0.00007160157,0.000008747975,0.000011500982,0.00001416573,0.00004369965],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99895245,0.000017732174,0.0003205071,0.00017990357,0.00030979328,0.00021961544],"domain_scores_gemma":[0.9996088,0.00006045006,0.000039059116,0.00012790726,0.000021198097,0.00014254758],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015445745,0.00012690373,0.0002475686,0.0003082262,0.000029410232,0.000007696608,0.00006090154,0.00005606689,0.000061868355],"category_scores_gemma":[0.00003395803,0.00011680483,0.0000762973,0.00038552698,0.000054758904,0.00007382434,6.107057e-7,0.00041976882,0.000004790955],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018302732,0.0012891847,0.0005981396,0.0003957668,0.0001280548,0.00022135006,0.00029412913,0.1406456,0.48057124,0.0001934487,0.000393484,0.37508658],"study_design_scores_gemma":[0.0051694717,0.00088982965,0.033907644,0.001009606,0.00015914353,0.00015418968,0.00005842209,0.869902,0.087653466,0.00005161487,0.0006980304,0.00034654848],"about_ca_topic_score_codex":0.00007926451,"about_ca_topic_score_gemma":7.839009e-7,"teacher_disagreement_score":0.72925645,"about_ca_system_score_codex":0.0001206586,"about_ca_system_score_gemma":0.000027697268,"threshold_uncertainty_score":0.4763163},"labels":[],"label_agreement":null},{"id":"W2131495531","doi":"10.1016/j.juro.2014.02.2079","title":"MP67-12 MRI TARGETED BIOPSY FOR THE DETECTION OF PROSTATE CANCER IN PATIENTS AFTER PRIOR NEGATIVE BIOPSIES.","year":2014,"lang":"en","type":"article","venue":"The Journal of Urology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Medicine; Prostate cancer; Biopsy; Prostate biopsy; Cancer detection; Prostate; Cancer; General surgery; Radiology; Internal medicine","score_opus":0.005317508983740602,"score_gpt":0.26032160195795334,"score_spread":0.2550040929742127,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2131495531","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98623246,0.0006851883,0.004419671,0.0078283325,0.0005136148,0.0002923075,0.0000030785789,0.0000029429477,0.00002238646],"genre_scores_gemma":[0.9983913,0.00020666678,0.00023279915,0.000905925,0.00019695798,0.0000102037575,4.3920912e-7,0.00001150383,0.00004420397],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.999165,0.00015788752,0.0003289309,0.000060028175,0.00013635911,0.00015182082],"domain_scores_gemma":[0.99890906,0.00043274296,0.00034943587,0.0001027784,0.00016478698,0.00004121117],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009844486,0.00007245226,0.00022486351,0.000091358765,0.00004309786,0.0000033799072,0.00010447689,0.00004674169,0.000027011802],"category_scores_gemma":[0.0007064938,0.00003477549,0.00006221248,0.00008638426,0.00017648295,0.00003297417,0.000020881884,0.0003915296,6.9828366e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.02336061,0.0004057515,0.6512561,0.00016462312,0.00058746146,0.0000134055435,0.009876103,0.0057388726,0.023297362,0.000031980428,0.00076680176,0.28450096],"study_design_scores_gemma":[0.004693079,0.0017808608,0.9571482,0.000055056113,0.0002797684,0.00005791443,0.00010173049,0.029402254,0.0012658808,0.00041429925,0.0047396854,0.00006128651],"about_ca_topic_score_codex":0.00007827478,"about_ca_topic_score_gemma":0.000019063666,"teacher_disagreement_score":0.3058921,"about_ca_system_score_codex":0.000028870847,"about_ca_system_score_gemma":0.000044044842,"threshold_uncertainty_score":0.17010231},"labels":[],"label_agreement":null},{"id":"W2133240210","doi":"10.1016/j.ijrobp.2010.07.136","title":"Evaluation of Lung Hysteresis using a Bifurcation Tracking Code and Deformable Image Registration","year":2010,"lang":"en","type":"article","venue":"International Journal of Radiation Oncology*Biology*Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Princess Margaret Cancer Centre","funders":"","keywords":"Medicine; Tracking (education); Bifurcation; Hysteresis; Code (set theory); Computer vision; Image registration; Artificial intelligence; Image (mathematics); Physics; Programming language; Nonlinear system; Condensed matter physics","score_opus":0.032543557311701346,"score_gpt":0.39093365223740695,"score_spread":0.3583900949257056,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2133240210","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9390089,0.00019713322,0.057103064,0.001720333,0.0012299616,0.00019787761,0.000010799499,0.000014680482,0.00051727396],"genre_scores_gemma":[0.98292553,0.00013594418,0.015508552,0.00021114995,0.0011437944,0.0000035728733,0.000044717537,0.000018546341,0.000008171434],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998202,0.00022069347,0.0007314315,0.00016095987,0.0005460334,0.00013888038],"domain_scores_gemma":[0.9962598,0.00020765285,0.0013482884,0.00012082458,0.0019667787,0.000096645155],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00301077,0.0001228938,0.0003287614,0.00020280358,0.00007084354,0.000035920402,0.00015620248,0.00016890018,0.00003416874],"category_scores_gemma":[0.0017511537,0.00011201925,0.00011024791,0.00012456096,0.00023533968,0.00045896886,0.00002792389,0.0005607776,0.0000013790035],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020633388,0.00027030063,0.20049225,0.00003925777,0.00045719152,0.000009366237,0.00070157653,0.002165875,0.41607022,0.004621989,0.0001945072,0.37477112],"study_design_scores_gemma":[0.0061601056,0.00038498794,0.066474944,0.00015708308,0.00080253877,0.0006811745,0.00011243159,0.9023957,0.011818742,0.009143911,0.0017070234,0.0001613536],"about_ca_topic_score_codex":0.000032320037,"about_ca_topic_score_gemma":0.0000074782415,"teacher_disagreement_score":0.9002298,"about_ca_system_score_codex":0.00035511312,"about_ca_system_score_gemma":0.0006946602,"threshold_uncertainty_score":0.45680124},"labels":[],"label_agreement":null},{"id":"W2140783866","doi":"10.1109/tmi.2008.2004425","title":"Coregistered FDG PET/CT-Based Textural Characterization of Head and Neck Cancer for Radiation Treatment Planning","year":2008,"lang":"en","type":"article","venue":"IEEE Transactions on Medical Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":188,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Health Science Centre; University of Toronto","funders":"","keywords":"Receiver operating characteristic; Positron emission tomography; Head and neck cancer; Radiation therapy; Nuclear medicine; Artificial intelligence; Radiation treatment planning; PET-CT; Tomography; Medicine; Pattern recognition (psychology); Computer science; Radiology","score_opus":0.024663864765805673,"score_gpt":0.3268608859389012,"score_spread":0.30219702117309555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2140783866","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6416012,0.00014635317,0.35322157,0.004272076,0.00032618406,0.00031783342,0.000023188191,0.000054282693,0.000037314705],"genre_scores_gemma":[0.99633634,0.00033974377,0.0014316137,0.001337223,0.00014865512,0.000096134616,0.00006745176,0.000031942,0.00021088966],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99873537,0.00003918702,0.00034598427,0.0002754837,0.00036630232,0.00023769209],"domain_scores_gemma":[0.9992287,0.00016695772,0.00012306814,0.00014453974,0.00006493238,0.00027177262],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014571288,0.00017427873,0.0003488159,0.00017622138,0.00020736229,0.000012977092,0.000054119035,0.000021195712,0.00009646875],"category_scores_gemma":[0.00005704291,0.0001448706,0.000114692295,0.00013179697,0.0002194764,0.000094106195,7.5383184e-7,0.00025077836,0.000001329543],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008999105,0.0007929967,0.03070689,0.00040137587,0.00021690576,0.00064708694,0.0009287798,0.0019331885,0.044562805,0.00001304318,0.0002408146,0.91865623],"study_design_scores_gemma":[0.011620414,0.0005587104,0.03534946,0.0012441289,0.000321307,0.001489545,0.00007570916,0.9156489,0.028078297,0.0000080641685,0.0052978965,0.0003076184],"about_ca_topic_score_codex":0.00017459875,"about_ca_topic_score_gemma":0.000004197155,"teacher_disagreement_score":0.9183486,"about_ca_system_score_codex":0.00012143106,"about_ca_system_score_gemma":0.00023497218,"threshold_uncertainty_score":0.5907651},"labels":[],"label_agreement":null},{"id":"W2142068201","doi":"10.2967/jnumed.114.144055","title":"<sup>18</sup>F-FDG PET Uptake Characterization Through Texture Analysis: Investigating the Complementary Nature of Heterogeneity and Functional Tumor Volume in a Multi–Cancer Site Patient Cohort","year":2014,"lang":"en","type":"article","venue":"Journal of Nuclear Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":436,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Lung cancer; Correlation; Spearman's rank correlation coefficient; Rank correlation; Head and neck cancer; Medicine; Nuclear medicine; Breast cancer; Cancer; Cohort; Population; Multivariate analysis; Internal medicine; Oncology; Mathematics; Statistics","score_opus":0.017960754198877518,"score_gpt":0.29447229437347533,"score_spread":0.27651154017459784,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2142068201","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98275894,0.00045766018,0.0010540391,0.015319349,0.00013408414,0.00020099543,0.000011266892,0.0000092243345,0.000054413424],"genre_scores_gemma":[0.9867983,0.00016879919,0.0019030119,0.010536384,0.00048996875,0.000002538761,0.00006182927,0.000023354634,0.00001579853],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9979662,0.00017826846,0.0008322483,0.00019534708,0.0006438575,0.00018413807],"domain_scores_gemma":[0.9986011,0.00010510361,0.000730789,0.00017671054,0.0002277858,0.00015853974],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010700003,0.00016843814,0.0006670928,0.00022521315,0.00009790262,0.000013762379,0.00010032828,0.00006043533,0.00035460424],"category_scores_gemma":[0.00066322414,0.000101949794,0.00012367852,0.00042757174,0.0002769957,0.00012673099,0.00005364973,0.0010817457,9.323214e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023377832,0.00016142016,0.95723814,0.00015245758,0.00086259225,0.00006344206,0.0032207551,0.0021175682,0.02694843,0.000046766618,0.0036640943,0.0052905385],"study_design_scores_gemma":[0.0019258911,0.00036172447,0.75902927,0.00053495204,0.000775941,0.00028045662,0.00056074717,0.22121848,0.000021044229,0.000016980357,0.015201437,0.00007306048],"about_ca_topic_score_codex":0.00014187055,"about_ca_topic_score_gemma":0.000019931344,"teacher_disagreement_score":0.21910092,"about_ca_system_score_codex":0.00006623021,"about_ca_system_score_gemma":0.000046278365,"threshold_uncertainty_score":0.4699707},"labels":[],"label_agreement":null},{"id":"W2147023528","doi":"10.1148/radiol.12112428","title":"Non–Small Cell Lung Cancer: Histopathologic Correlates for Texture Parameters at CT","year":2012,"lang":"en","type":"article","venue":"Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":453,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Thomas Hospital","funders":"","keywords":"Medicine; Nuclear medicine; Lung cancer; Pathology; Tongue; Angiogenesis; Radiology; Internal medicine","score_opus":0.0118872542745247,"score_gpt":0.2819139874022782,"score_spread":0.2700267331277535,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2147023528","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9768129,0.01172506,0.005277193,0.0022445947,0.0017151654,0.0005304141,0.000008139094,0.00007406036,0.0016124829],"genre_scores_gemma":[0.9864647,0.0004979109,0.004955969,0.0032445963,0.0005466836,0.00012435135,0.00006280649,0.00003701005,0.004066018],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.998802,0.00005514386,0.00022430366,0.00027006515,0.00006846833,0.00058001635],"domain_scores_gemma":[0.9991213,0.00026509093,0.000116668285,0.00022308715,0.000028086983,0.0002457311],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038781302,0.00017793135,0.00044142644,0.00007695911,0.00011738613,0.000004808259,0.000114738876,0.00013198935,0.0001298251],"category_scores_gemma":[0.00022031328,0.00013695848,0.00014710281,0.00006627723,0.00015408311,0.00002949234,0.000044911332,0.00041973256,0.000024845715],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001339372,0.0000945757,0.9176915,0.0002217417,0.000063000916,0.00008186918,0.0005918378,0.00026557347,0.011015529,0.00015086394,0.057796292,0.0118932435],"study_design_scores_gemma":[0.0108298315,0.0013970323,0.2810656,0.0002776366,0.0019604363,0.008837386,0.00022898518,0.19111899,0.003534715,0.00031536716,0.49916685,0.0012671459],"about_ca_topic_score_codex":0.000043461045,"about_ca_topic_score_gemma":0.0000023175064,"teacher_disagreement_score":0.63662595,"about_ca_system_score_codex":0.00024052872,"about_ca_system_score_gemma":0.000051520205,"threshold_uncertainty_score":0.55850047},"labels":[],"label_agreement":null},{"id":"W2147911853","doi":"10.1016/j.ijrobp.2009.07.578","title":"Evaluation of Early Response Criteria in Glioblastoma Multiforme","year":2009,"lang":"en","type":"article","venue":"International Journal of Radiation Oncology*Biology*Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto","funders":"","keywords":"Medicine; Glioblastoma; Oncology; Medical physics; Cancer research","score_opus":0.024852816272628177,"score_gpt":0.394028265166959,"score_spread":0.3691754488943308,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2147911853","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98663706,0.00024851653,0.0051472066,0.006296567,0.0010788392,0.00018759206,0.000008136014,0.000014397166,0.00038168672],"genre_scores_gemma":[0.9949896,0.000102585946,0.0031196908,0.00085409114,0.00089113344,0.0000034403165,0.000011712452,0.00001317671,0.000014594383],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99755216,0.0006421523,0.00084414263,0.0001573523,0.0006300629,0.00017413517],"domain_scores_gemma":[0.9971372,0.00038269412,0.00086007616,0.00012060347,0.0013949325,0.0001044883],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0044046096,0.00012910983,0.00042235508,0.00035905006,0.000026224689,0.000014972501,0.00024514223,0.00016817203,0.00007452584],"category_scores_gemma":[0.0030019514,0.00011658239,0.0001593691,0.00019804946,0.00014802255,0.00022832307,0.000022332353,0.0005245317,0.000008448834],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0046571847,0.0007571162,0.1309791,0.0000061157193,0.00025525677,0.000062730396,0.0013076147,0.0017948224,0.07091352,0.001973504,0.00046981318,0.7868232],"study_design_scores_gemma":[0.023324322,0.0075625353,0.7732426,0.00033595922,0.00038778552,0.0005323537,0.00014554556,0.1495636,0.008612408,0.029337712,0.0066815643,0.0002736178],"about_ca_topic_score_codex":0.000013952832,"about_ca_topic_score_gemma":0.0000015481833,"teacher_disagreement_score":0.78654957,"about_ca_system_score_codex":0.00072170526,"about_ca_system_score_gemma":0.00078553474,"threshold_uncertainty_score":0.4754092},"labels":[],"label_agreement":null},{"id":"W2150146643","doi":"10.1109/isbi.2011.5872343","title":"Selection of optimal texture descriptors for retrieving ultrasound medical images","year":2011,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Victoria Hospital; Concordia University","funders":"","keywords":"Computer science; Selection (genetic algorithm); Artificial intelligence; Texture (cosmology); Computer vision; Image texture; Pattern recognition (psychology); Image (mathematics); Image segmentation","score_opus":0.01879999375334774,"score_gpt":0.2876742418167776,"score_spread":0.26887424806342985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2150146643","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.60696435,0.00023073316,0.36625808,0.0014383427,0.00049814984,0.0005335907,0.000003831,0.00018686193,0.02388603],"genre_scores_gemma":[0.9302729,0.00005137975,0.06746672,0.0005412607,0.0002236427,0.000008060581,0.000010223559,0.000022796563,0.0014030255],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990039,0.000023259547,0.00026652604,0.00018593702,0.00031059733,0.00020978639],"domain_scores_gemma":[0.99932206,0.0001674445,0.00007464685,0.000108150365,0.00012587979,0.00020181866],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00058358815,0.00010211473,0.00024919104,0.00008871131,0.000056433637,0.0000075843113,0.000089728426,0.00012400094,0.0016364036],"category_scores_gemma":[0.0028292858,0.00007606713,0.00010593925,0.00015474512,0.00012865548,0.00006527123,0.000017280352,0.00031474765,0.0000034014356],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015391209,0.0011092945,0.48657057,0.0011814899,0.00068480225,0.00007274725,0.0032597224,0.000014031976,0.22798853,0.008152442,0.11347746,0.15594979],"study_design_scores_gemma":[0.01576178,0.0055536954,0.28668332,0.0018703181,0.0014184555,0.003804501,0.002714782,0.107896544,0.5078053,0.0018584306,0.06315699,0.0014759006],"about_ca_topic_score_codex":0.0000861554,"about_ca_topic_score_gemma":0.0000020880325,"teacher_disagreement_score":0.32330853,"about_ca_system_score_codex":0.000027433061,"about_ca_system_score_gemma":0.00010861791,"threshold_uncertainty_score":0.9992762},"labels":[],"label_agreement":null},{"id":"W2150911893","doi":"10.1016/j.ijrobp.2008.06.1099","title":"Multiparametric MRI Response during Radiotherapy for Prostate Cancer","year":2008,"lang":"en","type":"article","venue":"International Journal of Radiation Oncology*Biology*Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre","funders":"","keywords":"Medicine; Prostate cancer; Radiation therapy; Multiparametric MRI; Prostate; Cancer; Radiology; Medical physics; Oncology; Internal medicine","score_opus":0.0187037154345812,"score_gpt":0.36424822065724843,"score_spread":0.3455445052226672,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2150911893","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94107217,0.0016249322,0.043605387,0.011155161,0.0020400463,0.0003688791,0.000032714597,0.000040286686,0.000060436287],"genre_scores_gemma":[0.96852,0.005010622,0.020838354,0.0017948855,0.0033993425,0.00003612,0.000026095257,0.000045816898,0.00032875373],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99839455,0.00020027692,0.0006554959,0.00021749697,0.00027550646,0.0002566667],"domain_scores_gemma":[0.9974373,0.00077400886,0.00081463874,0.00010470734,0.0006977224,0.00017162833],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008229381,0.00016736744,0.0004775853,0.00031769904,0.0001300365,0.000016905566,0.00026690692,0.00016014908,0.000045389726],"category_scores_gemma":[0.001285487,0.00014497014,0.0002631809,0.00021695351,0.00026640948,0.00017144803,0.000025623187,0.0005529491,0.0000050903],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.01138382,0.00068944384,0.6296452,0.000032865963,0.0015026422,0.00029538467,0.0021654968,0.008379415,0.09329157,0.0007972451,0.0036467703,0.2481701],"study_design_scores_gemma":[0.056946114,0.004718616,0.46435043,0.00029638282,0.0003667413,0.0055926675,0.00014537878,0.10987423,0.0139489155,0.0030279472,0.34000966,0.00072291243],"about_ca_topic_score_codex":0.00001908424,"about_ca_topic_score_gemma":4.1186706e-7,"teacher_disagreement_score":0.3363629,"about_ca_system_score_codex":0.0008680981,"about_ca_system_score_gemma":0.0007139641,"threshold_uncertainty_score":0.5911711},"labels":[],"label_agreement":null},{"id":"W2155615249","doi":"10.1016/j.ijrobp.2011.06.973","title":"Hemoglobin: A Misunderstood Prognostic Factor in Cervix Cancer","year":2011,"lang":"en","type":"article","venue":"International Journal of Radiation Oncology*Biology*Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hôpital Notre-Dame","funders":"","keywords":"Medicine; Cervix; Hemoglobin; Oncology; Internal medicine; Cancer","score_opus":0.03589493585204051,"score_gpt":0.352333217530569,"score_spread":0.3164382816785285,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2155615249","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97331274,0.00074015785,0.014633759,0.0061016036,0.00288996,0.00024096754,0.000019773079,0.00003682131,0.0020242287],"genre_scores_gemma":[0.99108297,0.000560452,0.0047483463,0.0019835457,0.001511042,0.000011287259,0.00002108169,0.000026674143,0.00005462703],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99850506,0.00014267687,0.0006541006,0.00019741208,0.00025714363,0.00024361204],"domain_scores_gemma":[0.99844396,0.00022859516,0.0006592912,0.00010635053,0.0003958329,0.00016596577],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038208332,0.00016184358,0.0004374478,0.00021233702,0.00003536373,0.000015142439,0.00032006347,0.00018312571,0.00030148323],"category_scores_gemma":[0.00060345937,0.0001400412,0.00017311913,0.00016583769,0.00018904495,0.00018296615,0.000047046633,0.00076795515,0.000019369281],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023427521,0.0004691281,0.84065616,0.0000123699165,0.00030164106,0.00013627921,0.0012005556,0.00009378066,0.0016341569,0.003140597,0.0005353801,0.15158567],"study_design_scores_gemma":[0.019143693,0.0025164383,0.88204145,0.0005142896,0.0003383956,0.0011037163,0.00039476546,0.017131692,0.002853866,0.02810675,0.045294773,0.0005601771],"about_ca_topic_score_codex":0.00010054185,"about_ca_topic_score_gemma":0.00000942686,"teacher_disagreement_score":0.15102549,"about_ca_system_score_codex":0.00068023027,"about_ca_system_score_gemma":0.0006232735,"threshold_uncertainty_score":0.57107145},"labels":[],"label_agreement":null},{"id":"W2161302159","doi":"10.1093/jnci/dju173","title":"Core Symptom Measures in Cancer Clinical Trials","year":2014,"lang":"en","type":"letter","venue":"JNCI Journal of the National Cancer Institute","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Cancer; Core (optical fiber); Clinical trial; Medicine; Psychology; Computer science; Internal medicine","score_opus":0.39153990445249726,"score_gpt":0.5270592538973216,"score_spread":0.1355193494448243,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2161302159","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009693547,0.0030681381,0.00023739653,0.96754205,0.017748354,0.00041319762,0.000054150016,0.0000118468715,0.0012313278],"genre_scores_gemma":[0.024257855,0.0028858264,0.00043659678,0.8994451,0.07079628,0.0000337258,0.000024296245,0.000056597357,0.0020636944],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9940925,0.0007244309,0.0022702771,0.00026894073,0.0023534216,0.00029041048],"domain_scores_gemma":[0.99507475,0.0010962748,0.0023946085,0.00019479591,0.0010932988,0.00014628196],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.009893719,0.00028309057,0.0015435145,0.00037314306,0.000095602154,0.000048723534,0.0006314717,0.00060353137,0.00017838736],"category_scores_gemma":[0.014203354,0.00016491774,0.00093223114,0.000286333,0.00033496585,0.00012838107,0.000066252534,0.00644946,0.000005605848],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017924554,0.000047512043,0.015648447,0.00013059014,0.0005166435,0.00014428467,0.00003784241,0.0017043229,0.00006655588,0.00007662313,0.96794736,0.013500565],"study_design_scores_gemma":[0.0029054282,0.00006821269,0.012513576,0.0023770346,0.00051169295,0.00039116165,0.0000018662186,0.0009413471,0.000016717659,0.0006291655,0.9794723,0.00017151902],"about_ca_topic_score_codex":0.00034684158,"about_ca_topic_score_gemma":0.000087781526,"teacher_disagreement_score":0.06809691,"about_ca_system_score_codex":0.0009700081,"about_ca_system_score_gemma":0.0037782283,"threshold_uncertainty_score":0.9958427},"labels":[],"label_agreement":null},{"id":"W2162217976","doi":"10.1186/1741-7015-10-87","title":"The failure of protein cancer biomarkers to reach the clinic: why, and what can be done to address the problem?","year":2012,"lang":"en","type":"article","venue":"BMC Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":190,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mount Sinai Hospital","funders":"","keywords":"Medicine; Cancer; Cancer biomarkers; Biomarker; Biomarker discovery; Oxymoron; Intensive care medicine; Bioinformatics; Internal medicine; Proteomics","score_opus":0.03217788701264307,"score_gpt":0.3455962183969238,"score_spread":0.3134183313842807,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2162217976","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31058946,0.012068369,0.00051997014,0.67251086,0.00052664045,0.0028373904,0.000005104311,0.000036263456,0.0009059616],"genre_scores_gemma":[0.95087457,0.0017753487,0.002857506,0.037934072,0.002266706,0.0007075118,0.000014728231,0.000073519965,0.0034960147],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979004,0.00026004665,0.00047795632,0.00026367203,0.00061765837,0.00048025316],"domain_scores_gemma":[0.99781317,0.0007963789,0.00017262778,0.0006362017,0.00013202649,0.00044959344],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037887853,0.00020299006,0.00039166395,0.00007292017,0.00028828703,0.000045464178,0.0003475776,0.00006861446,0.00011768799],"category_scores_gemma":[0.0016487087,0.00007740439,0.000057320405,0.00039664863,0.0006129771,0.00008846994,0.00015306882,0.000490535,0.0000042338143],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013986286,0.00021384029,0.05800657,0.00089739775,0.00070326566,0.000013723479,0.034166407,0.00002280278,0.049334414,0.0017738305,0.5393242,0.31414488],"study_design_scores_gemma":[0.0025749872,0.0006810051,0.031380434,0.0031390607,0.00042461682,0.000093722934,0.016031945,0.00023930662,0.0012331399,0.00012151151,0.9438436,0.00023665381],"about_ca_topic_score_codex":0.002392891,"about_ca_topic_score_gemma":0.001239368,"teacher_disagreement_score":0.64028513,"about_ca_system_score_codex":0.000048005102,"about_ca_system_score_gemma":0.0001315931,"threshold_uncertainty_score":0.36173517},"labels":[],"label_agreement":null},{"id":"W2169309000","doi":"10.1373/clinchem.2011.180778","title":"Design of Tumor Biomarker–Monitoring Trials: A Proposal by the European Group on Tumor Markers","year":2012,"lang":"en","type":"article","venue":"Clinical Chemistry","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Mount Sinai Hospital","funders":"","keywords":"Biomarker; Medicine; Randomized controlled trial; Oncology; Clinical trial; Cancer; Internal medicine; Intensive care medicine; Biology","score_opus":0.08689973833276204,"score_gpt":0.39456505316691876,"score_spread":0.3076653148341567,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2169309000","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9791023,0.0010779874,0.0026733442,0.0027332387,0.0014264799,0.0006326243,0.000008503119,0.0001243114,0.012221178],"genre_scores_gemma":[0.99361265,0.00004517079,0.0028584294,0.00047726627,0.002416699,0.00001461143,0.000013989405,0.000051958814,0.0005092111],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99680895,0.0010997093,0.0010531218,0.00029161325,0.00037078842,0.00037582027],"domain_scores_gemma":[0.99575794,0.0029008046,0.0004466764,0.00045156133,0.00006164799,0.00038137703],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.014749925,0.00019722882,0.00062207796,0.000016588796,0.00007893012,0.00002018909,0.0002725055,0.00007151053,0.000102510494],"category_scores_gemma":[0.017853428,0.000120411496,0.00028137458,0.00011828043,0.00039490615,0.000038526265,0.000083910774,0.0009050671,0.000027174156],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0039343545,0.0030463687,0.30795047,0.00092106155,0.0008389695,0.0002032771,0.00016441764,0.0000089922405,0.36332333,0.000024173163,0.14378484,0.17579977],"study_design_scores_gemma":[0.043994654,0.0036444378,0.31590673,0.007441869,0.0041353954,0.0015791206,0.0018928187,0.01431474,0.37662652,0.00037151785,0.22699012,0.0031020532],"about_ca_topic_score_codex":0.000004093581,"about_ca_topic_score_gemma":5.2761613e-9,"teacher_disagreement_score":0.17269771,"about_ca_system_score_codex":0.00003867861,"about_ca_system_score_gemma":0.00007991248,"threshold_uncertainty_score":0.9904196},"labels":[],"label_agreement":null},{"id":"W2181478911","doi":"10.5326/15473317-36-3-192","title":"Fathoming the mysteries of magnetic resonance imaging","year":2000,"lang":"en","type":"review","venue":"Journal of the American Animal Hospital Association","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Magnetic resonance imaging; Nuclear magnetic resonance; Physics; Medicine","score_opus":0.008058368228287954,"score_gpt":0.29081861556959593,"score_spread":0.282760247341308,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2181478911","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006720969,0.98804104,0.0000088029,0.0040468927,0.00037126805,0.00027392406,0.000009650967,0.000008084541,0.0005193626],"genre_scores_gemma":[0.012108048,0.98587054,0.0003954601,0.000308323,0.0006946343,0.0000041046883,0.0000019204838,0.00004474635,0.00057224225],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975827,0.00033923634,0.0009707151,0.00014187818,0.00072286977,0.0002426009],"domain_scores_gemma":[0.99498105,0.000409114,0.0041255294,0.00023537946,0.00017987083,0.00006904497],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010385399,0.00022639874,0.0014865041,0.00010945813,0.00010842525,0.000048011592,0.00043996796,0.00005370028,0.000020185505],"category_scores_gemma":[0.0012622711,0.00011493165,0.0009093879,0.0004664132,0.00025799006,0.00008392925,0.000079625715,0.0010925118,0.000004513577],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000040315495,0.000055964414,0.0056082387,0.00045091606,0.000092152164,0.000018396619,0.00024108999,5.940276e-7,0.000010514877,0.000013451511,0.0021289054,0.99133945],"study_design_scores_gemma":[0.0002919246,0.0008148859,0.018893763,0.007946258,0.0014667341,0.0002926081,0.0001792895,0.00008827267,0.000002190774,0.000025933781,0.96984553,0.00015259329],"about_ca_topic_score_codex":0.00002959341,"about_ca_topic_score_gemma":4.4186567e-7,"teacher_disagreement_score":0.99118686,"about_ca_system_score_codex":0.00046498835,"about_ca_system_score_gemma":0.00028034957,"threshold_uncertainty_score":0.47464806},"labels":[],"label_agreement":null},{"id":"W2198233649","doi":"10.1016/j.jenvrad.2015.10.016","title":"Handling of recent plagiarism in JER","year":2015,"lang":"en","type":"letter","venue":"Journal of Environmental Radioactivity","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Research Manitoba","funders":"","keywords":"Environmental science","score_opus":0.01982202649324205,"score_gpt":0.2793841296794633,"score_spread":0.25956210318622125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2198233649","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5643209,0.002854726,0.0009673512,0.42806715,0.0014803844,0.00040104377,0.000033372136,0.00000861184,0.0018664809],"genre_scores_gemma":[0.76178193,0.0074806656,0.011439932,0.20974098,0.00799563,0.000005757989,0.00010911956,0.00022812338,0.0012178823],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99747247,0.00020270732,0.00077726756,0.00021811624,0.0010415374,0.0002879201],"domain_scores_gemma":[0.9983956,0.0001731809,0.00096767326,0.0002588273,0.000025662846,0.00017904988],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0013189154,0.0002584397,0.0010198585,0.00036467137,0.00002113645,0.000010552341,0.00015281196,0.000551515,0.00023739136],"category_scores_gemma":[0.00037629114,0.00021612944,0.00026265727,0.00009300591,0.0002095734,0.00012009719,0.00006293537,0.005299945,0.000004835519],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00075694046,0.0011970799,0.04832088,0.00036730757,0.00070355984,0.008566166,0.000583177,0.0002992474,0.01878921,0.0000014223568,0.8643791,0.05603588],"study_design_scores_gemma":[0.004696981,0.00086499564,0.027964087,0.00080560724,0.0004561092,0.004037086,0.00009515162,0.00063986186,0.0015279762,0.00012288106,0.95843923,0.00035003465],"about_ca_topic_score_codex":0.000018890432,"about_ca_topic_score_gemma":8.288429e-7,"teacher_disagreement_score":0.21832615,"about_ca_system_score_codex":0.0007317656,"about_ca_system_score_gemma":0.00026807116,"threshold_uncertainty_score":0.99699485},"labels":[],"label_agreement":null},{"id":"W2207540049","doi":"10.1016/j.ijrobp.2015.12.369","title":"Detection of Local Cancer Recurrence After Stereotactic Ablative Radiation Therapy for Lung Cancer: Physician Performance Versus Radiomic Assessment","year":2015,"lang":"en","type":"article","venue":"International Journal of Radiation Oncology*Biology*Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":140,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"London Health Sciences Centre; Western University","funders":"","keywords":"Medicine; SABR volatility model; Radiation therapy; Lung cancer; Radiology; Receiver operating characteristic; Nuclear medicine; Internal medicine","score_opus":0.02431249801399532,"score_gpt":0.3886996421989698,"score_spread":0.3643871441849745,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2207540049","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8527485,0.0025259694,0.13668966,0.0019392393,0.0055135223,0.0003984157,0.000042940956,0.000018920264,0.00012283285],"genre_scores_gemma":[0.9916265,0.0035554275,0.0016551481,0.00061869546,0.0023714951,0.00008656071,0.000042503703,0.0000285137,0.000015181084],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99837077,0.00017652256,0.0006552582,0.00022000226,0.00036041293,0.00021700919],"domain_scores_gemma":[0.9970058,0.00036484151,0.0012791213,0.00011445546,0.0010844646,0.00015128522],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000698629,0.0001870927,0.0004845733,0.00017834413,0.00005607065,0.000019448753,0.000219832,0.00015075783,0.00001887731],"category_scores_gemma":[0.00017322182,0.0001649383,0.0001904168,0.00017358329,0.00023145274,0.00037293803,0.000024811477,0.00053425116,0.0000012046495],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0039744456,0.0002614684,0.16539201,0.000028630031,0.0009730985,0.0000050227295,0.00067757984,0.006352675,0.0035072872,0.0002951781,0.00033308112,0.8181995],"study_design_scores_gemma":[0.040758256,0.0067206845,0.1459208,0.00046173728,0.000717011,0.00008929306,0.00032833565,0.7635379,0.018201593,0.0011830921,0.021579077,0.00050225604],"about_ca_topic_score_codex":0.000073326955,"about_ca_topic_score_gemma":0.000005064343,"teacher_disagreement_score":0.8176973,"about_ca_system_score_codex":0.0018304386,"about_ca_system_score_gemma":0.0012063414,"threshold_uncertainty_score":0.6725989},"labels":[],"label_agreement":null},{"id":"W2231859057","doi":"10.1200/jco.2006.24.18_suppl.17047","title":"Effects of presurgical exercise training on exercise capacity in operable lung cancer: A pilot study","year":2006,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary; University of Alberta","funders":"","keywords":"Medicine; Lung cancer; VO2 max; Physical therapy; Surgery; Internal medicine; Heart rate; Blood pressure","score_opus":0.09363290924795424,"score_gpt":0.44396230979379053,"score_spread":0.3503294005458363,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2231859057","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99343467,0.0011953692,0.00009123605,0.0021649834,0.0010020119,0.0006073069,7.9028644e-7,0.000009929064,0.0014937245],"genre_scores_gemma":[0.99586374,0.0010306459,0.0016406516,0.00047211855,0.0007562129,0.000019185609,5.740959e-7,0.000022026117,0.0001948588],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99583435,0.0005945245,0.0024612357,0.0002478816,0.0005412005,0.00032082634],"domain_scores_gemma":[0.995221,0.0029875694,0.001108643,0.00016556436,0.00019412204,0.00032307536],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.005221714,0.0001717203,0.002371736,0.00023570217,0.000037302125,0.000008926746,0.00021293516,0.00023393931,0.00006040899],"category_scores_gemma":[0.0034196912,0.000121117584,0.0002768628,0.00022109269,0.00021138851,0.00007922565,0.0000442287,0.0026436518,0.0000016994373],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.018453887,0.03617905,0.56587076,0.0005710516,0.0003622035,0.005519852,0.0013869505,0.0042594187,0.0016609229,0.00016062516,0.0052984757,0.3602768],"study_design_scores_gemma":[0.032930654,0.028446864,0.92104876,0.0030038143,0.0009776587,0.00012264942,0.0001916752,0.008986375,0.00020164896,0.00017963698,0.003719181,0.00019110722],"about_ca_topic_score_codex":0.0008028063,"about_ca_topic_score_gemma":0.00005735159,"teacher_disagreement_score":0.36008567,"about_ca_system_score_codex":0.00015468201,"about_ca_system_score_gemma":0.00082196493,"threshold_uncertainty_score":0.9996573},"labels":[],"label_agreement":null},{"id":"W2240998307","doi":"10.1200/jco.2014.32.4_suppl.10","title":"Validation of a genomic classifier for predicting biochemical failure following postoperative radiation therapy in high-risk prostate cancer.","year":2014,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Genome British Columbia","funders":"","keywords":"Medicine; Prostate cancer; Nomogram; Internal medicine; Cumulative incidence; Prostatectomy; Receiver operating characteristic; Radiation therapy; Incidence (geometry); Oncology; Proportional hazards model; Area under the curve; Urology; Gastroenterology; Cancer; Cohort","score_opus":0.034872784798522585,"score_gpt":0.41785314156680636,"score_spread":0.3829803567682838,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2240998307","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9843395,0.00030329087,0.0023532745,0.011769071,0.00084047706,0.00033490345,0.0000036094118,0.0000056590143,0.00005021015],"genre_scores_gemma":[0.9868267,0.00081981305,0.010439606,0.0008899769,0.0009609373,0.000011846797,0.000009068965,0.000017700377,0.000024324136],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9971119,0.00047228282,0.0018572711,0.0001662455,0.00021839296,0.00017387874],"domain_scores_gemma":[0.99518025,0.0025663753,0.0017650222,0.00009286433,0.00023942614,0.00015605472],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005466836,0.000102093,0.0009854217,0.00013218405,0.000037138485,0.000008194919,0.00009922172,0.00025255827,0.000014537165],"category_scores_gemma":[0.010936517,0.00007353222,0.0003228852,0.000097660864,0.00009361977,0.00009103207,0.000016802782,0.0009597136,5.7871085e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021529668,0.00035259553,0.5688692,0.000027354678,0.0002558322,0.00001242597,0.00054267194,0.00070138375,0.025934177,0.00005455009,0.0008015772,0.40029532],"study_design_scores_gemma":[0.049974147,0.021566894,0.83031785,0.00055475143,0.0006403006,0.000071461756,0.00035162392,0.05477195,0.008596957,0.0014907371,0.03140393,0.0002593676],"about_ca_topic_score_codex":0.00007991659,"about_ca_topic_score_gemma":0.0000075991825,"teacher_disagreement_score":0.40003595,"about_ca_system_score_codex":0.00014126222,"about_ca_system_score_gemma":0.0006908082,"threshold_uncertainty_score":0.9973948},"labels":[],"label_agreement":null},{"id":"W2248882779","doi":"10.1200/jco.2015.33.3_suppl.725","title":"The impact of perioperative red blood cell transfusion on long-term survival after hepatectomy for colorectal liver metastases.","year":2015,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Health Sciences Centre; Sunnybrook Health Science Centre","funders":"","keywords":"Medicine; Perioperative; Colorectal cancer; Proportional hazards model; Subgroup analysis; Hepatectomy; Internal medicine; Retrospective cohort study; Overall survival; Blood transfusion; Surgery; Resection; Cancer; Confidence interval","score_opus":0.07599614301314948,"score_gpt":0.45189815767609653,"score_spread":0.37590201466294704,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2248882779","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99366665,0.0006215383,0.00083020143,0.0024612988,0.00094611716,0.00035813928,0.000008537981,0.0000052078267,0.0011023377],"genre_scores_gemma":[0.9958086,0.0009244244,0.0019108424,0.0002802105,0.0008681979,0.000005808937,0.0000036876768,0.000021018124,0.00017723741],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99702346,0.0007293903,0.0014576562,0.00016318912,0.0003864857,0.00023979695],"domain_scores_gemma":[0.9945718,0.0032835123,0.00087178504,0.00014494445,0.0006480077,0.00047995299],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005537036,0.00015298274,0.0012168629,0.000078436664,0.000056584955,0.000014055125,0.00017054332,0.0002122938,0.00007971923],"category_scores_gemma":[0.004973167,0.00007629894,0.00090030953,0.00008940277,0.00033847787,0.000059356742,0.00002838681,0.0011221195,0.000002903949],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.14033441,0.0088807,0.54857457,0.00014862619,0.003537353,0.003485409,0.0019124403,0.00041246702,0.0067264084,0.00007296615,0.003663502,0.28225112],"study_design_scores_gemma":[0.053739633,0.12853631,0.79835224,0.0002675255,0.002235608,0.00085769244,0.00022932654,0.0042546215,0.0020594234,0.00010103618,0.009108536,0.00025805496],"about_ca_topic_score_codex":0.00004870271,"about_ca_topic_score_gemma":0.000030274388,"teacher_disagreement_score":0.28199306,"about_ca_system_score_codex":0.000107226726,"about_ca_system_score_gemma":0.001467527,"threshold_uncertainty_score":0.5953705},"labels":[],"label_agreement":null},{"id":"W2253150690","doi":"10.1038/srep11044","title":"Radiomic feature clusters and Prognostic Signatures specific for Lung and Head &amp; Neck cancer","year":2015,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":437,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University Health Network; Ontario Institute for Cancer Research","funders":"National Institutes of Health; National Cancer Institute; KWF Kankerbestrijding; Health Foundation Limburg","keywords":"Lung cancer; Medicine; Radiomics; Head and neck cancer; Stage (stratigraphy); Internal medicine; Lung; Oncology; Cancer; Radiology; Biology","score_opus":0.022413973819958008,"score_gpt":0.320448033344801,"score_spread":0.29803405952484296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2253150690","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9713524,0.015308553,0.0012485536,0.0057186633,0.0050307265,0.0009172647,0.000003536863,0.0000696197,0.00035068224],"genre_scores_gemma":[0.97491544,0.00013455024,0.013484897,0.00049823005,0.0005639866,0.00007043405,0.00012195412,0.000045796227,0.010164688],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983315,0.000026297323,0.00025947922,0.0006821086,0.00037402668,0.00032659472],"domain_scores_gemma":[0.9988199,0.00006875674,0.00014866721,0.00035570632,0.00015610094,0.0004508873],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011644784,0.00016193227,0.00029347267,0.00015683383,0.00021218527,0.00024574486,0.000051889197,0.00009715742,0.000015019431],"category_scores_gemma":[0.00068554824,0.00012565199,0.0000549814,0.00020071425,0.0003708044,0.00009834269,0.00005405897,0.00029845565,9.1661127e-7],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015467957,0.00007263793,0.14421697,0.00043723025,0.000084679144,0.0004458239,0.0017817966,0.00024014626,0.014283513,0.00006326271,0.81370455,0.02451469],"study_design_scores_gemma":[0.0023528545,0.00012620768,0.021383,0.00064714154,0.00023580267,0.002751935,0.00018758445,0.023762079,0.00042566142,0.00173039,0.946,0.00039737346],"about_ca_topic_score_codex":0.000035737776,"about_ca_topic_score_gemma":0.000018063418,"teacher_disagreement_score":0.1322954,"about_ca_system_score_codex":0.00007268207,"about_ca_system_score_gemma":0.00019865649,"threshold_uncertainty_score":0.51239395},"labels":[],"label_agreement":null},{"id":"W2256150954","doi":"10.1080/21681163.2015.1110295","title":"Special issue: 1st MICCAI workshop on bio- imaging and visualization for patient-customized simulations","year":2015,"lang":"en","type":"article","venue":"Computer Methods in Biomechanics and Biomedical Engineering Imaging & Visualization","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Visualization; Data science; Computer science; Artificial intelligence","score_opus":0.02106730290612639,"score_gpt":0.3689963862591187,"score_spread":0.3479290833529923,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2256150954","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009449108,0.0003610743,0.9855134,0.0016059766,0.0022566204,0.00059425726,0.000010761072,0.00017748713,0.000031306165],"genre_scores_gemma":[0.12311863,0.00035469286,0.8641589,0.0033400087,0.007856797,0.00007138134,0.0008059253,0.00022823451,0.00006540001],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99785656,0.00015356387,0.000621934,0.00059121556,0.00036289435,0.00041385452],"domain_scores_gemma":[0.998557,0.00049378857,0.0001482511,0.00019997775,0.00017358898,0.00042742578],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013140453,0.0003192571,0.0004966911,0.00092833186,0.00010975244,0.00015221673,0.0000990213,0.00013395071,0.000012948606],"category_scores_gemma":[0.001309161,0.00029969244,0.000067332694,0.00076692837,0.00010483921,0.00015573781,0.00014188461,0.00026431942,0.0000012815216],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018781719,0.00030360126,0.0006251463,0.00030127369,0.000055859822,0.000028165012,0.0012442762,0.0014960525,0.0142397005,0.0039722286,0.0039851516,0.97356075],"study_design_scores_gemma":[0.0031301768,0.00014762857,0.00012960838,0.00045097788,0.00005935999,0.000051611605,0.00009375399,0.90484434,0.00048867177,0.00046482604,0.08984848,0.00029053306],"about_ca_topic_score_codex":0.000011614599,"about_ca_topic_score_gemma":2.6480944e-7,"teacher_disagreement_score":0.9732702,"about_ca_system_score_codex":0.00014147972,"about_ca_system_score_gemma":0.00006611441,"threshold_uncertainty_score":0.9999455},"labels":[],"label_agreement":null},{"id":"W2273823362","doi":"10.1200/jco.2006.24.18_suppl.10014","title":"Is mammography adequate for screening BRCA mutation carriers with low breast density?","year":2006,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; Sunnybrook Health Science Centre","funders":"","keywords":"Medicine; Breast cancer; Breast density; Mammography; BRCA mutation; Breast MRI; Breast cancer screening; Oncology; Magnetic resonance imaging; Cancer; Internal medicine; Gynecology; Radiology","score_opus":0.034680718807942566,"score_gpt":0.4069471157934525,"score_spread":0.37226639698550995,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2273823362","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86245376,0.00017712002,0.11087645,0.024616424,0.00067812117,0.00020710725,0.0000042838474,0.000015775151,0.00097093947],"genre_scores_gemma":[0.9406225,0.00002880447,0.052511852,0.004642184,0.0018591108,0.0000030699,0.000008076676,0.000024746218,0.00029966602],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9977037,0.00014996706,0.0013450601,0.00018302219,0.00036227398,0.00025597858],"domain_scores_gemma":[0.9965947,0.0011785752,0.001231438,0.00011892356,0.0005239892,0.00035237477],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024935016,0.00012333965,0.0009274478,0.00017624168,0.000072461255,0.000016586026,0.00010269381,0.0002191865,0.000039653674],"category_scores_gemma":[0.0009810121,0.00008409854,0.0004753761,0.00016575523,0.00026651245,0.000099965895,0.000014866675,0.00094878464,0.0000028988966],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.007133876,0.0007398318,0.40030786,0.00008020116,0.00077505474,0.0019496236,0.00013572384,0.0005127018,0.00013782016,0.0003860117,0.018604053,0.56923723],"study_design_scores_gemma":[0.023953194,0.01178475,0.88566583,0.00047848347,0.0014241836,0.008108456,0.00031103613,0.013714764,0.000102370504,0.0014048081,0.052790616,0.00026150423],"about_ca_topic_score_codex":0.0000678879,"about_ca_topic_score_gemma":0.000015038091,"teacher_disagreement_score":0.56897575,"about_ca_system_score_codex":0.000047415917,"about_ca_system_score_gemma":0.0005224909,"threshold_uncertainty_score":0.412205},"labels":[],"label_agreement":null},{"id":"W2274771262","doi":"10.1200/jco.2012.30.15_suppl.4621","title":"Prognostic role of body composition parameters in renal cell carcinoma (RCC).","year":2012,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Medicine; Interquartile range; Proportional hazards model; Nuclear medicine; Renal cell carcinoma; Internal medicine; Adipose tissue; Population; Log-rank test; Body mass index; Survival analysis; Urology; Oncology","score_opus":0.0470825908929736,"score_gpt":0.41663999952045583,"score_spread":0.3695574086274822,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2274771262","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99335694,0.00074958656,0.00029730235,0.0022883553,0.00063248,0.00011683367,5.46087e-7,0.0000035033347,0.0025544434],"genre_scores_gemma":[0.98735315,0.000083429346,0.010986917,0.00087116845,0.0006664947,0.0000013594015,0.0000025092108,0.000011159024,0.000023839946],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9972047,0.0004253018,0.0017516087,0.00009200867,0.00028271964,0.00024365481],"domain_scores_gemma":[0.99636865,0.0018307366,0.0011748499,0.000104248174,0.00013879547,0.00038270326],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003658372,0.000087535846,0.0009699456,0.00015562367,0.000014669564,0.0000030794106,0.000108843604,0.00020941984,0.00003633225],"category_scores_gemma":[0.0025451842,0.00006426261,0.00027344353,0.00010685295,0.00017883709,0.00008929851,0.00003121906,0.0012931691,0.0000063874686],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010310231,0.0022080427,0.9492982,0.000041352407,0.000048930764,0.00016436916,0.000184295,0.000071353476,0.009110668,0.00006871067,0.000575455,0.037197594],"study_design_scores_gemma":[0.005335695,0.005734565,0.9780737,0.00013620565,0.000270044,0.00043695638,0.00011381159,0.0024777513,0.0014541313,0.00018778758,0.005708604,0.00007074269],"about_ca_topic_score_codex":0.00003053987,"about_ca_topic_score_gemma":0.0000011802144,"teacher_disagreement_score":0.03712685,"about_ca_system_score_codex":0.00007618846,"about_ca_system_score_gemma":0.00040114037,"threshold_uncertainty_score":0.5618248},"labels":[],"label_agreement":null},{"id":"W2278915112","doi":"10.3978/j.issn.2223-4292.2016.02.01","title":"Role of quantitative computed tomography texture analysis in the differentiation of primary lung cancer and granulomatous nodules.","year":2016,"lang":"en","type":"article","venue":"PubMed","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":94,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital","funders":"","keywords":"Lung cancer; Receiver operating characteristic; Medicine; Histopathology; Biopsy; Tomography; Radiology; Nodule (geology); Positron emission tomography; Nuclear medicine; Pathology; Internal medicine; Biology","score_opus":0.007085394103180806,"score_gpt":0.2460429478077672,"score_spread":0.23895755370458638,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2278915112","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9924252,0.0026082925,0.0025399232,0.001837018,0.000025185218,0.00032794347,0.000011359485,0.000008353543,0.00021674884],"genre_scores_gemma":[0.99929154,0.00017157997,0.00026769275,0.00014134705,0.000018117591,0.000080645084,0.000011592289,0.0000054028237,0.000012059612],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99928814,0.00006626414,0.00020913062,0.00012226324,0.00019114184,0.00012305187],"domain_scores_gemma":[0.99947584,0.0001807084,0.00013269267,0.00011964259,0.000049856735,0.00004123403],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031195406,0.000066745655,0.00029561794,0.0002679593,0.000016150738,0.0000048324755,0.000065557804,0.00003348582,0.000004993371],"category_scores_gemma":[0.000094712086,0.000034337176,0.0000807718,0.0005206395,0.000110763125,0.000034185137,0.000017655824,0.00009328209,3.7107355e-8],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000055848166,0.00007349583,0.8526176,0.000097308715,0.0003540614,0.0000014860974,0.0006340687,0.000013352205,0.0021077404,0.0002953322,0.00006776633,0.14368193],"study_design_scores_gemma":[0.0008302635,0.000013146577,0.9921651,0.000056652865,0.00043106035,0.0000017006786,0.00006507229,0.0059847822,0.00022885238,0.00014204615,0.0000414966,0.000039841012],"about_ca_topic_score_codex":0.000208273,"about_ca_topic_score_gemma":0.00004162198,"teacher_disagreement_score":0.14364208,"about_ca_system_score_codex":0.000018854727,"about_ca_system_score_gemma":0.000011354825,"threshold_uncertainty_score":0.14002295},"labels":[],"label_agreement":null},{"id":"W2280343247","doi":"10.1200/jco.2013.31.31_suppl.104","title":"The use of PET scans in the management of non-small cell lung cancer patients relative to evidence-based indications across Canada.","year":2013,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Canadian Partnership Against Cancer","funders":"","keywords":"Medicine; Lung cancer; Cancer; Stage (stratigraphy); Radiation treatment planning; Radiation therapy; Palliative care; Radiology; Oncology; Internal medicine; Nursing","score_opus":0.08639910602653088,"score_gpt":0.44986891835432175,"score_spread":0.36346981232779085,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2280343247","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9556238,0.00017105274,0.0008430848,0.04226745,0.0004169171,0.0004736827,0.0000042521206,8.313011e-7,0.0001989457],"genre_scores_gemma":[0.9893321,0.0005797984,0.0050275354,0.0047967494,0.00009608315,0.000021103178,9.702046e-7,0.000007364645,0.00013833787],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9973073,0.00040329114,0.0015524912,0.00010476856,0.00043988752,0.00019226871],"domain_scores_gemma":[0.9924807,0.005244696,0.0014339722,0.00019823706,0.000464055,0.00017832346],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023832337,0.00007750862,0.0005264324,0.000041152234,0.000059438702,0.000009907181,0.00032501997,0.00006388265,0.000027136219],"category_scores_gemma":[0.0029229056,0.000039804236,0.00013448916,0.00022306273,0.00019105182,0.00008034741,0.00005472846,0.0008589232,8.6362877e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004296544,0.00082557823,0.8929709,0.00011807803,0.00024406894,0.00007747418,0.000883414,0.0024337773,0.00002971144,0.000043843822,0.01886525,0.083078235],"study_design_scores_gemma":[0.0022043318,0.0010968534,0.9783987,0.0006952953,0.00019057981,0.0000038971593,0.00036260317,0.004898548,0.0000123072095,0.000020045562,0.012075458,0.00004137129],"about_ca_topic_score_codex":0.039677244,"about_ca_topic_score_gemma":0.022284184,"teacher_disagreement_score":0.08542779,"about_ca_system_score_codex":0.00019598116,"about_ca_system_score_gemma":0.0015298682,"threshold_uncertainty_score":0.9955566},"labels":[],"label_agreement":null},{"id":"W2281552218","doi":"10.1016/j.nicl.2016.02.012","title":"Application of texture analysis to DAT SPECT imaging: Relationship to clinical assessments","year":2016,"lang":"en","type":"article","venue":"NeuroImage Clinical","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":82,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Michael J. Fox Foundation for Parkinson's Research","keywords":"Spect imaging; Dopamine transporter; Montreal Cognitive Assessment; Medicine; Putamen; Nuclear medicine; Univariate; Multivariate analysis; Parkinson's disease; Multivariate statistics; Cognitive impairment; Internal medicine; Disease; Computer science; Dopamine","score_opus":0.06795642523409624,"score_gpt":0.4822533218034122,"score_spread":0.41429689656931595,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2281552218","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5612615,0.000018367535,0.40115118,0.03397558,0.00048244544,0.0005786661,0.000017767115,0.00010094845,0.0024135574],"genre_scores_gemma":[0.97484803,0.000025712816,0.01655235,0.007021844,0.0006721358,0.000017693268,0.000024918187,0.00003724324,0.00080009253],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99647796,0.0004032911,0.0014535176,0.00086113636,0.00050305785,0.0003010212],"domain_scores_gemma":[0.9953418,0.002352165,0.00029102265,0.001099647,0.00019009938,0.00072527974],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002668227,0.00018528973,0.00078612234,0.0003302324,0.00006494288,0.0000250184,0.0003190999,0.00010546553,0.00012394316],"category_scores_gemma":[0.011073671,0.00012879944,0.00050967623,0.0009604149,0.00020659718,0.0000902225,0.00018392381,0.0006882441,0.00028355067],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016415447,0.00030176813,0.8587634,0.000009718246,0.00013920943,0.000038427344,0.000012141015,0.000010608628,0.0013642941,0.0001435397,0.0057132323,0.13333951],"study_design_scores_gemma":[0.0012672668,0.0003903133,0.9652294,0.0000477024,0.0007116539,0.00001640073,0.000007604453,0.004825656,0.000047263882,0.00011977847,0.027199663,0.00013731174],"about_ca_topic_score_codex":0.000020372749,"about_ca_topic_score_gemma":0.000003422563,"teacher_disagreement_score":0.41358653,"about_ca_system_score_codex":0.000039524464,"about_ca_system_score_gemma":0.00010748897,"threshold_uncertainty_score":0.99725646},"labels":[],"label_agreement":null},{"id":"W2285793395","doi":"10.1200/jco.2012.30.27_suppl.51","title":"Estimation of additional MRI resources needed in British Columbia for screening high-risk women for breast cancer.","year":2012,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Okanagan University College; University of British Columbia, Okanagan Campus; B.C. Women's Hospital & Health Centre; BC Cancer Agency","funders":"","keywords":"Medicine; Breast cancer; Mammography; Family history; Gynecology; Estimation; Population; Breast cancer screening; Breast MRI; Lifetime risk; Family medicine; Demography; Cancer; Obstetrics; Environmental health; Internal medicine","score_opus":0.03756156464595888,"score_gpt":0.4153957006641971,"score_spread":0.37783413601823823,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2285793395","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9810512,0.00017327689,0.012053669,0.0053339377,0.00068192615,0.0002699196,0.00038103838,0.0000055944315,0.000049441816],"genre_scores_gemma":[0.91921824,0.0001878049,0.07674566,0.0012312235,0.0023732914,0.000044763245,0.000032430933,0.000017933025,0.0001486394],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99755794,0.00018530393,0.0016191715,0.00010940236,0.00024203178,0.00028617962],"domain_scores_gemma":[0.99322665,0.004443098,0.0016471759,0.00006651398,0.00028855202,0.00032799743],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0051114326,0.000063227766,0.0009772353,0.000078246136,0.00005731436,0.000017788547,0.00010200548,0.00020998158,0.0006886909],"category_scores_gemma":[0.009159512,0.00007180554,0.00025150215,0.00009673787,0.00016980167,0.00013528,0.000021148322,0.00065903144,4.211181e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014916284,0.00062148087,0.18212229,0.00007864563,0.0001786991,0.000010729824,0.0001613863,0.00086185645,0.000013711558,0.00001267371,0.04718747,0.7672594],"study_design_scores_gemma":[0.011401542,0.0027957337,0.9137633,0.00049544487,0.00021089119,0.0003388313,0.00039188325,0.024216322,0.0000022821596,0.0007383157,0.04556215,0.00008332604],"about_ca_topic_score_codex":0.0020225474,"about_ca_topic_score_gemma":0.0007151294,"teacher_disagreement_score":0.7671761,"about_ca_system_score_codex":0.00014046703,"about_ca_system_score_gemma":0.00045299664,"threshold_uncertainty_score":0.99918675},"labels":[],"label_agreement":null},{"id":"W2288152566","doi":"10.1200/jop.2015.009316","title":"Reply to F. Dayyani et al","year":2016,"lang":"en","type":"letter","venue":"Journal of Oncology Practice","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Columbia College","funders":"","keywords":"Medicine; Biomarker; Disease; Prospective cohort study; Internal medicine; Oncology","score_opus":0.02566821281620939,"score_gpt":0.4083224956143079,"score_spread":0.3826542827980985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2288152566","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00012959125,0.00030066774,0.0026447796,0.9527385,0.0028832443,0.00017524199,0.000003174074,0.00001834346,0.04110643],"genre_scores_gemma":[0.00004495273,0.00080128096,0.032963146,0.95036983,0.009624012,0.0000032781322,0.000006692495,0.00006572252,0.0061210925],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99684346,0.0007842761,0.0008832185,0.0002848424,0.0008013089,0.0004028982],"domain_scores_gemma":[0.9929577,0.003792558,0.0017983771,0.0003744002,0.0007624873,0.0003144899],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0045886277,0.00024085681,0.00095213094,0.00040871635,0.000057677356,0.00003944419,0.00032459432,0.00047508205,0.00031573864],"category_scores_gemma":[0.020550642,0.00015947795,0.00026587275,0.00013345716,0.000102539816,0.00031165162,0.000103023965,0.0079448195,0.00021037225],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005439472,0.00009079941,0.00005763984,0.00003069759,0.00040807735,0.023085719,0.00015009304,0.0000018484446,0.0003911306,0.000019708363,0.93297327,0.042247094],"study_design_scores_gemma":[0.0018105063,0.0027540105,0.000079661266,0.0004161804,0.00065483287,0.04455614,0.000044613385,0.000007932499,0.00001157413,0.000052985706,0.9494577,0.00015384298],"about_ca_topic_score_codex":0.000025687248,"about_ca_topic_score_gemma":2.5810309e-7,"teacher_disagreement_score":0.04209325,"about_ca_system_score_codex":0.0004935339,"about_ca_system_score_gemma":0.0015949067,"threshold_uncertainty_score":0.9943439},"labels":[],"label_agreement":null},{"id":"W2293962048","doi":"10.3322/caac.21339","title":"American Joint Committee on Cancer acceptance criteria for inclusion of risk models for individualized prognosis in the practice of precision medicine","year":2016,"lang":"en","type":"article","venue":"CA A Cancer Journal for Clinicians","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":353,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"National Cancer Institute","keywords":"Inclusion (mineral); Medicine; Cancer; Joint (building); Precision medicine; Family medicine; Medical physics; Internal medicine; Psychology; Engineering; Pathology; Social psychology","score_opus":0.0701277189664954,"score_gpt":0.46273077085504405,"score_spread":0.39260305188854866,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2293962048","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5852872,0.004045705,0.22772066,0.1740111,0.0023724432,0.005049673,0.0011764864,0.000022155862,0.0003145791],"genre_scores_gemma":[0.96715164,0.009433816,0.01708546,0.0044282046,0.0011114592,0.0006598118,0.000011566224,0.00005360753,0.00006442503],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973792,0.0002816897,0.0012037017,0.0002773407,0.00052925054,0.00032882887],"domain_scores_gemma":[0.99060965,0.0065289293,0.0017695187,0.00025216356,0.0007192499,0.00012050811],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0052367733,0.00019094517,0.000877264,0.00021225598,0.00026474125,0.000012104216,0.00033283237,0.000086388616,0.00004332369],"category_scores_gemma":[0.011001036,0.00009794466,0.00030986397,0.0002433175,0.0003181738,0.0001534023,0.000067120185,0.00043730164,1.17250586e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.010754308,0.0007794281,0.007867189,0.00044680186,0.00037010034,0.0000057604707,0.012069303,0.0006550071,0.00419343,0.00044095123,0.040011372,0.9224064],"study_design_scores_gemma":[0.09928455,0.035258282,0.029984985,0.03757437,0.006519222,0.00020553819,0.013441075,0.12201989,0.007259224,0.06093432,0.58625543,0.001263099],"about_ca_topic_score_codex":0.00047712686,"about_ca_topic_score_gemma":0.0001347034,"teacher_disagreement_score":0.92114323,"about_ca_system_score_codex":0.00017351453,"about_ca_system_score_gemma":0.00029148578,"threshold_uncertainty_score":0.9973297},"labels":[],"label_agreement":null},{"id":"W2294860378","doi":"10.1109/nssmic.2014.7430910","title":"Texture and shape analysis on high and low spatial resolution emission images","year":2014,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vancouver Coastal Health; University of British Columbia","funders":"","keywords":"Artificial intelligence; Image resolution; Positron emission tomography; Robustness (evolution); Computer vision; Single-photon emission computed tomography; Shape analysis (program analysis); Region of interest; Computer science; Magnetic resonance imaging; Image texture; Emission computed tomography; Texture (cosmology); Shape context; Pattern recognition (psychology); Nuclear medicine; Image segmentation; Medicine; Segmentation; Chemistry; Image (mathematics); Radiology","score_opus":0.00396477350019133,"score_gpt":0.2555090372402995,"score_spread":0.2515442637401082,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2294860378","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95525676,0.00015501908,0.02986634,0.010128876,0.000054194647,0.000085790074,0.0000011792438,0.000057126283,0.0043947403],"genre_scores_gemma":[0.9950835,0.00010449125,0.0019001259,0.0014208104,0.00018956618,0.0000012833355,0.000022388642,0.000008454398,0.0012693669],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993459,0.00004079999,0.00011049381,0.00022504057,0.00015865912,0.000119086595],"domain_scores_gemma":[0.99957395,0.00008034052,0.000034435398,0.00012716306,0.000023527618,0.00016059977],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026235357,0.00008756971,0.00020913008,0.0001309762,0.000078155215,0.00002706405,0.000024355682,0.0000607476,0.00017185848],"category_scores_gemma":[0.00033498066,0.00005869413,0.00003507005,0.000119990225,0.00006871294,0.000027743665,0.000027583123,0.00021547201,0.0000033306535],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022718706,0.00011345598,0.1554,0.00013109513,0.000264284,0.00002534018,0.00016183646,0.00013490002,0.025538413,0.0009502129,0.009045621,0.80800766],"study_design_scores_gemma":[0.0009339513,0.0002017431,0.42725128,0.000085699336,0.00033941175,0.000016309375,0.000015922375,0.5675304,0.0005827107,0.00017973864,0.0027703943,0.0000924238],"about_ca_topic_score_codex":0.00026819916,"about_ca_topic_score_gemma":0.0000050220833,"teacher_disagreement_score":0.8079153,"about_ca_system_score_codex":0.000011131198,"about_ca_system_score_gemma":0.0000075836037,"threshold_uncertainty_score":0.23934771},"labels":[],"label_agreement":null},{"id":"W2303551175","doi":"10.1117/12.2209121","title":"Phenotypic characterization of glioblastoma identified through shape descriptors","year":2016,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Phenotype; Glioblastoma; Fluid-attenuated inversion recovery; Pathology; Artificial intelligence; Computational biology; Magnetic resonance imaging; Pattern recognition (psychology); Biology; Medicine; Computer science; Cancer research; Radiology; Genetics; Gene","score_opus":0.010574339677968055,"score_gpt":0.24075598070170126,"score_spread":0.2301816410237332,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2303551175","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9930852,0.000054487555,0.00038047045,0.0044843457,0.00041509402,0.0004614196,0.000028510363,0.00007330854,0.0010171693],"genre_scores_gemma":[0.9631429,0.00013223766,0.035205357,0.00020414777,0.00053984235,0.000073439325,0.000009970634,0.00007458642,0.00061755924],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99779624,2.088533e-8,0.00077629153,0.00035392822,0.0007286957,0.00034481543],"domain_scores_gemma":[0.9977772,0.00011614925,0.0005082296,0.00007007425,0.001397068,0.00013126025],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00051655935,0.00026331033,0.000503187,0.00010985227,0.000057323636,0.000043719054,0.0005199006,0.00016686672,0.000064834036],"category_scores_gemma":[0.0009867635,0.00018016355,0.00055104046,0.00030523262,0.0003347444,0.0005224508,0.00012238587,0.00026041773,0.0000024818055],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022042196,0.00012712649,0.0015596444,0.00046317786,0.00039239074,1.6661478e-7,0.00026814628,0.0000023100094,0.8176564,0.17637525,0.00084865006,0.002086335],"study_design_scores_gemma":[0.0053818235,0.0013057032,0.026236828,0.002997524,0.0007439534,0.000085085325,0.0011361869,0.023859262,0.9271785,0.0024490682,0.00795404,0.00067202235],"about_ca_topic_score_codex":0.0000070644073,"about_ca_topic_score_gemma":3.454762e-8,"teacher_disagreement_score":0.17392619,"about_ca_system_score_codex":0.00012931357,"about_ca_system_score_gemma":0.000042093627,"threshold_uncertainty_score":0.73468566},"labels":[],"label_agreement":null},{"id":"W2307184173","doi":"10.1117/12.2214491","title":"GBM heterogeneity characterization by radiomic analysis of phenotype anatomical planes","year":2016,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Glioblastoma; Fluid-attenuated inversion recovery; Phenotype; Artificial intelligence; Linear discriminant analysis; Magnetic resonance imaging; Pattern recognition (psychology); Pathology; Computer science; Biology; Medicine; Radiology; Cancer research; Gene; Genetics","score_opus":0.007790310215029299,"score_gpt":0.2427910680239109,"score_spread":0.2350007578088816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2307184173","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9946098,0.00007850462,0.0003776906,0.0039916835,0.00014555514,0.00032762642,0.0001418598,0.000055365173,0.00027192238],"genre_scores_gemma":[0.98286337,0.00020397308,0.016224492,0.00017448682,0.00024652365,0.000037660437,0.000062488914,0.00004943407,0.00013757864],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9978847,3.280773e-8,0.0007611053,0.00037462806,0.00065993436,0.00031961253],"domain_scores_gemma":[0.99817777,0.00018421892,0.00048130573,0.00007414112,0.00091112923,0.00017146248],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00058301113,0.00025928335,0.00070074864,0.00021876881,0.00004762439,0.00003532394,0.0004926656,0.00018059975,0.000032457243],"category_scores_gemma":[0.00092508044,0.00017663291,0.0007647368,0.0005146853,0.00030382385,0.00026304036,0.00009361846,0.00023794152,9.702819e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021010614,0.00015257481,0.010106229,0.00029604582,0.0021831205,1.2610104e-7,0.00008997428,0.000017051017,0.9440869,0.040672343,0.0010039635,0.0011815279],"study_design_scores_gemma":[0.0049289316,0.0008930989,0.071171686,0.0012309904,0.0047029112,0.000046187844,0.00039766816,0.15171523,0.75517166,0.00038799673,0.008517265,0.0008363573],"about_ca_topic_score_codex":0.00001167578,"about_ca_topic_score_gemma":8.327441e-8,"teacher_disagreement_score":0.18891527,"about_ca_system_score_codex":0.00015259617,"about_ca_system_score_gemma":0.00003659905,"threshold_uncertainty_score":0.7202881},"labels":[],"label_agreement":null},{"id":"W2313645883","doi":"10.1158/1055-9965.gwas-71","title":"Abstract 71: Relationship of mammographic density and gene expression analysis of normal breast tissue surrounding breast cancer.","year":2012,"lang":"en","type":"article","venue":"Cancer Epidemiology Biomarkers & Prevention","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Institute for Cancer Research","funders":"","keywords":"Breast cancer; Gene expression; Medicine; Oncology; Population; Internal medicine; Cancer; Gene signature; Univariate analysis; Cancer research; Gene; Pathology; Biology; Multivariate analysis; Genetics","score_opus":0.03592007282431197,"score_gpt":0.3702122066758445,"score_spread":0.3342921338515325,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2313645883","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98315746,0.0084037855,0.0063335183,0.0014660159,0.00032036955,0.00020604476,0.00004348093,0.000022224162,0.000047117304],"genre_scores_gemma":[0.9948977,0.001201242,0.0034100288,0.00008350895,0.00017839838,0.00002441345,0.00014036761,0.0000153725,0.000048926486],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9980711,0.0004096666,0.00072837697,0.00029515257,0.0001488138,0.00034691603],"domain_scores_gemma":[0.998117,0.00059402245,0.00070351554,0.00024297449,0.00011207648,0.0002303605],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029627692,0.00016576269,0.0007583745,0.00047454634,0.000099828685,0.0000028934053,0.000075895194,0.00020644309,0.00020544261],"category_scores_gemma":[0.00037411184,0.0001444577,0.0002326118,0.0005745746,0.00034893805,0.00017822176,0.00004872262,0.0002729414,6.418508e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023654768,0.00008217858,0.92998624,0.00019369101,0.0010962392,0.0000012669743,0.00008905291,0.00008560086,0.047228843,0.00009371562,0.00022207384,0.020684524],"study_design_scores_gemma":[0.00057061197,0.000027834754,0.99377626,0.0004432657,0.0019526606,0.000049067192,0.00004528184,0.0011627451,0.0016356051,0.00018337791,0.0000387318,0.00011458135],"about_ca_topic_score_codex":0.0013723026,"about_ca_topic_score_gemma":0.00007705538,"teacher_disagreement_score":0.06378997,"about_ca_system_score_codex":0.00008998737,"about_ca_system_score_gemma":0.000066982604,"threshold_uncertainty_score":0.5890814},"labels":[],"label_agreement":null},{"id":"W2314931582","doi":"10.1016/j.jvir.2015.12.080","title":"Fiducial-less fusion imaging of 3D ultrasound with prior CT/MRI in liver interventions","year":2016,"lang":"en","type":"article","venue":"Journal of Vascular and Interventional Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Polytechnique Montréal","funders":"","keywords":"Fiducial marker; Medicine; Image registration; Image fusion; Radiology; Ultrasound; 3D ultrasound; Medical imaging; Nuclear medicine; Artificial intelligence; Computer science; Image (mathematics)","score_opus":0.01187914027329102,"score_gpt":0.29200532124389234,"score_spread":0.2801261809706013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2314931582","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95009744,0.0049627256,0.04270386,0.0017639287,0.00019096155,0.00009898708,0.0000032278658,0.000004099824,0.0001747518],"genre_scores_gemma":[0.9947248,0.0013472612,0.003570473,0.000091207934,0.00015019973,0.0000020790478,0.000003594597,0.000011944739,0.000098455464],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99867743,0.00016131622,0.0006507404,0.00014225439,0.00021663318,0.00015163019],"domain_scores_gemma":[0.9990776,0.0002047819,0.00035890643,0.000102747326,0.00015768564,0.00009823598],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010682918,0.00010496685,0.00043810988,0.00031804576,0.00003293673,0.000008211199,0.00009615578,0.000032963617,0.00026723705],"category_scores_gemma":[0.000437199,0.00006123117,0.00039249906,0.000089407746,0.00024407067,0.00013094205,0.000034391574,0.00027717833,0.0000012725632],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00075539225,0.0011843238,0.8515365,0.00076561025,0.0010223007,0.0007164568,0.00034262612,0.000075469514,0.018725846,0.002412358,0.0017105644,0.12075253],"study_design_scores_gemma":[0.008437924,0.001642212,0.963463,0.007509878,0.00037771536,0.013739002,0.00019994965,0.00052871037,0.0004456987,0.00075383147,0.0027356893,0.00016637566],"about_ca_topic_score_codex":0.000044403452,"about_ca_topic_score_gemma":0.000017062792,"teacher_disagreement_score":0.12058615,"about_ca_system_score_codex":0.000060313538,"about_ca_system_score_gemma":0.00006655148,"threshold_uncertainty_score":0.29260582},"labels":[],"label_agreement":null},{"id":"W2315779332","doi":"10.1021/mp500673u","title":"Noninvasive Visualization of Tumoral Fibrin Deposition Using a Peptidic Fibrin-Binding Single Photon Emission Computed Tomography Tracer","year":2015,"lang":"en","type":"article","venue":"Molecular Pharmaceutics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Center for Translational Molecular Medicine; Hartstichting; Mallinckrodt Pharmaceuticals","keywords":"Biodistribution; Fibrin; In vivo; Ex vivo; Chemistry; Pathology; Stroma; Angiogenesis; In vitro; Single-photon emission computed tomography; Cancer research; Nuclear medicine; Medicine; Biology; Immunology; Immunohistochemistry; Biochemistry","score_opus":0.04716185651402623,"score_gpt":0.3553983749036996,"score_spread":0.30823651838967336,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2315779332","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9182693,0.00057123194,0.079940476,0.00016871399,0.00020811633,0.00035082057,0.000004189099,0.000082458544,0.0004047217],"genre_scores_gemma":[0.9856747,0.000017151911,0.013560312,0.00042535865,0.000100635036,0.0000032592425,0.00012967736,0.00005699881,0.000031927404],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9983239,0.00014568312,0.00040086926,0.0002858244,0.0005423345,0.0003014009],"domain_scores_gemma":[0.9989546,0.00003383962,0.00023096208,0.00018497565,0.0002265604,0.00036906678],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003307778,0.00020734475,0.00034333084,0.00029846333,0.000075202326,0.0000367798,0.00009196455,0.0000995869,0.000017077178],"category_scores_gemma":[0.00013750722,0.0002107347,0.00015409081,0.00055175397,0.000101368474,0.000093978415,0.00006685165,0.00029063007,0.000002982063],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012290438,0.00022613753,0.008641708,0.0002258979,0.000086687214,0.00033311514,0.0004550932,0.0025314714,0.9849887,0.00003448801,0.00012637426,0.0022274514],"study_design_scores_gemma":[0.0018326675,0.0001949226,0.00015841032,0.00043218196,0.00023443716,0.00040604282,0.00008586053,0.33235726,0.66366655,0.00002198013,0.0004554475,0.00015422679],"about_ca_topic_score_codex":0.000034299504,"about_ca_topic_score_gemma":2.569811e-7,"teacher_disagreement_score":0.3298258,"about_ca_system_score_codex":0.00015057242,"about_ca_system_score_gemma":0.00013138757,"threshold_uncertainty_score":0.85935116},"labels":[],"label_agreement":null},{"id":"W2317080695","doi":"10.1158/0008-5472.sabcs12-p1-07-17","title":"Abstract P1-07-17: V Array: A novel tool for constructing virtual tissue microarrays (TMAs), an evaluation of its use in optimizing TMA construction for Ductal Carcinoma in Situ (DCIS).","year":2012,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Health Sciences Centre; Sunnybrook Health Science Centre","funders":"","keywords":"Tissue microarray; Ductal carcinoma; Medicine; Magnification; Pathology; Biomarker; Oncology; Internal medicine; Cancer; Breast cancer; Biology; Computer science; Artificial intelligence","score_opus":0.1370029878654418,"score_gpt":0.44158593964772436,"score_spread":0.30458295178228256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2317080695","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9933239,0.00057062233,0.0029610768,0.00040068635,0.00039312395,0.0020969543,0.0000434152,0.000015663265,0.00019453543],"genre_scores_gemma":[0.97535145,0.000037592585,0.023517858,0.000043623437,0.0005875013,0.000315477,0.00006719776,0.00004449963,0.00003478364],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9974595,0.00014638292,0.00056175,0.00039338865,0.0007243284,0.0007146906],"domain_scores_gemma":[0.99805236,0.00061289425,0.00015847139,0.00023478769,0.0007452161,0.0001962708],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0057041557,0.00016270972,0.00040835544,0.00052015163,0.00011362524,0.00005326107,0.00013175744,0.00015132526,0.00009627137],"category_scores_gemma":[0.0032471523,0.00016405608,0.00006860236,0.00033445962,0.00026815082,0.0005670487,0.0000370431,0.00068972417,0.0000016746894],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005795442,0.00016980521,0.047160957,0.00032844106,0.000030307256,0.0000034370385,0.001605712,0.0015915653,0.90700865,0.0005159923,0.000088791516,0.040916823],"study_design_scores_gemma":[0.031094937,0.0012108403,0.15581648,0.002390527,0.00025626054,0.00038812615,0.011695872,0.07953716,0.7138151,0.00021287319,0.0026880787,0.0008937426],"about_ca_topic_score_codex":0.0005477905,"about_ca_topic_score_gemma":0.00013775428,"teacher_disagreement_score":0.19319353,"about_ca_system_score_codex":0.0004931595,"about_ca_system_score_gemma":0.0007222102,"threshold_uncertainty_score":0.6690013},"labels":[],"label_agreement":null},{"id":"W2319533240","doi":"10.1158/0008-5472.sabcs-09-6015","title":"Advancing Breast Cancer HER2 FISH Quality by Image Analysis.","year":2009,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Mount Sinai Hospital","funders":"","keywords":"Breast cancer; Medicine; Pathology; Stage (stratigraphy); Cancer; Biology; Internal medicine","score_opus":0.02988549941776134,"score_gpt":0.474985907764336,"score_spread":0.44510040834657466,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2319533240","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8675783,0.001991038,0.0012367478,0.124303795,0.00013438676,0.0003372569,0.00012452982,0.000102494676,0.004191442],"genre_scores_gemma":[0.98767805,0.0018105748,0.0004938974,0.005353575,0.00061739964,0.00006168793,0.00005711374,0.000029145993,0.0038985347],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9970837,0.00025525605,0.00032677603,0.0005028074,0.001029996,0.00080141355],"domain_scores_gemma":[0.9984064,0.00015389344,0.000068730704,0.000443733,0.00041987354,0.0005073713],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0021707073,0.00015210305,0.0004787412,0.0003056456,0.00022670736,0.000082020655,0.00024089705,0.000082571714,0.0018916697],"category_scores_gemma":[0.000407936,0.000128413,0.00017108826,0.0014692094,0.00022806376,0.00013394553,0.000057369198,0.0012400631,0.000019357307],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044591867,0.0003390127,0.10265484,0.00021185697,0.0007071146,0.00012727236,0.0004847089,0.00023314884,0.3076444,0.00014970463,0.36367178,0.22333026],"study_design_scores_gemma":[0.0032258907,0.00024270073,0.84858286,0.0004597754,0.0005543523,0.000043923836,0.0004104964,0.0083075315,0.00796376,0.000411976,0.12922734,0.0005693827],"about_ca_topic_score_codex":0.006032068,"about_ca_topic_score_gemma":0.00024543374,"teacher_disagreement_score":0.74592805,"about_ca_system_score_codex":0.00052135077,"about_ca_system_score_gemma":0.00037537058,"threshold_uncertainty_score":0.99902076},"labels":[],"label_agreement":null},{"id":"W2325333960","doi":"10.1017/cjn.2014.72","title":"Characterization of the chemoresistance profiles of malignant gliomas- A step towards a predictive individualized treatment","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Neurological Sciences / Journal Canadien des Sciences Neurologiques","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Medicine; Oncology; Glioma; Glioblastoma; Internal medicine; Cancer research","score_opus":0.01915336343262371,"score_gpt":0.2680762502042669,"score_spread":0.24892288677164318,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2325333960","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9923992,0.00021834418,0.00020697806,0.005397086,0.00043781986,0.00021315296,0.00001739756,0.000006512739,0.0011035126],"genre_scores_gemma":[0.99645644,0.00017944918,0.002158293,0.0010126184,0.00015993069,0.000002712051,5.160923e-7,0.000007973543,0.000022086959],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99671376,0.0007631798,0.0008315002,0.00029839535,0.00079553784,0.0005976582],"domain_scores_gemma":[0.9971427,0.00025757938,0.0012224464,0.00015327697,0.0004248079,0.0007992215],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0029534672,0.00021217986,0.0005915551,0.0004955965,0.00075902225,0.000110448455,0.0009879231,0.00011018598,0.000050004153],"category_scores_gemma":[0.002842002,0.000108559034,0.00025868788,0.001003176,0.005440897,0.00026893127,0.000045499994,0.0005610161,2.0903336e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023842715,0.00008167418,0.9740128,0.00003424875,0.000043617136,0.0004480308,0.0007527838,0.0004465594,0.007181065,0.00084148225,0.0000779016,0.015841395],"study_design_scores_gemma":[0.0009870841,0.05874798,0.911499,0.00024689297,0.0001550033,0.00817453,0.00015075035,0.007663154,0.00750117,0.0023389086,0.0023505422,0.00018497366],"about_ca_topic_score_codex":0.00079370354,"about_ca_topic_score_gemma":0.002987439,"teacher_disagreement_score":0.062513806,"about_ca_system_score_codex":0.00014475638,"about_ca_system_score_gemma":0.0027398153,"threshold_uncertainty_score":0.9972657},"labels":[],"label_agreement":null},{"id":"W2325561875","doi":"10.1097/01.cot.0000352156.57627.1f","title":"RCC: Nomogram Found as Prognosis-Predicting with Targeted Theraphy","year":2009,"lang":"en","type":"article","venue":"Oncology Times","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Nomogram; Medicine; Oncology; Renal cell carcinoma; Internal medicine; Targeted therapy; Cancer; Clinical Oncology","score_opus":0.008313048225915404,"score_gpt":0.30748710924033956,"score_spread":0.2991740610144242,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2325561875","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.74466014,0.0010682625,0.0006269834,0.034700066,0.00023373304,0.0005502639,0.0000011308126,0.00039674185,0.21776266],"genre_scores_gemma":[0.97490895,0.00004950641,0.014185178,0.0077325124,0.0004077154,0.000024578403,0.00002666214,0.000026422462,0.0026384855],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99882287,0.00007157675,0.00021903306,0.00029837273,0.00022298255,0.00036515621],"domain_scores_gemma":[0.99929,0.00012553988,0.00011081181,0.00019064662,0.00007559452,0.00020744387],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032830867,0.00017022439,0.00037370028,0.00012387901,0.00014187377,0.000025958156,0.00011216736,0.00014111835,0.00037800468],"category_scores_gemma":[0.00017206592,0.00011990019,0.00008289344,0.00023093862,0.00018753923,0.000065861714,0.000017098604,0.0005653544,0.00005314999],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011599539,0.0016873698,0.33679518,0.00007339076,0.0006630282,0.0014950535,0.002017442,0.00008604429,0.009053246,0.002604149,0.02815841,0.61620677],"study_design_scores_gemma":[0.012433575,0.022242581,0.32163465,0.0006131368,0.00083875493,0.0031806394,0.0011005886,0.018882284,0.001569783,0.0032257142,0.6134658,0.00081249344],"about_ca_topic_score_codex":0.00004620379,"about_ca_topic_score_gemma":0.000003026533,"teacher_disagreement_score":0.61539423,"about_ca_system_score_codex":0.00006727462,"about_ca_system_score_gemma":0.00020999131,"threshold_uncertainty_score":0.4889388},"labels":[],"label_agreement":null},{"id":"W2325864519","doi":"10.1158/1940-6207.prev-11-a9","title":"Abstract A9: Phenotype matters in the prediction of cancer risk of oral premalignant lesions (OPL)","year":2011,"lang":"en","type":"article","venue":"Cancer Prevention Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency; University of British Columbia","funders":"","keywords":"Dysplasia; Medicine; Carcinoma in situ; Cancer; Histopathology; OPLS; Internal medicine; Pathology; Surrogate endpoint; Histology; Prospective cohort study; Oncology; Chemistry","score_opus":0.11085957511536577,"score_gpt":0.43132803082941407,"score_spread":0.3204684557140483,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2325864519","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99399287,0.0012327444,0.00040956592,0.0017990093,0.00016233338,0.00061150856,0.00003316154,0.000011340786,0.0017474608],"genre_scores_gemma":[0.9966702,0.002280966,0.00036750725,0.000081619015,0.0000639191,0.0001309993,0.000009767836,0.0000141173505,0.00038092132],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99828196,0.0003156811,0.00036824425,0.00019057102,0.0005986414,0.00024489188],"domain_scores_gemma":[0.99919355,0.000110826055,0.0001518573,0.00026732942,0.00020674134,0.00006972087],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0023191068,0.00007593286,0.00020881504,0.00021484557,0.00006825748,0.000006579291,0.00018640413,0.0000623593,0.001033627],"category_scores_gemma":[0.00022689243,0.000050937397,0.00008835475,0.00040260193,0.0002335222,0.000066485205,0.00004278469,0.00063587126,0.0000041632015],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00062262703,0.0008965387,0.6870755,0.0009999191,0.00027159366,0.000020404788,0.0063967584,0.00025926926,0.028690314,0.00058720115,0.009286892,0.26489297],"study_design_scores_gemma":[0.0009794349,0.0001952799,0.9902137,0.00089947146,0.00007891814,0.0000022010374,0.0006267359,0.0012135514,0.0031632797,0.0008807907,0.0016992996,0.00004732256],"about_ca_topic_score_codex":0.011371435,"about_ca_topic_score_gemma":0.00039188043,"teacher_disagreement_score":0.3031382,"about_ca_system_score_codex":0.00008570307,"about_ca_system_score_gemma":0.00026211335,"threshold_uncertainty_score":0.99987954},"labels":[],"label_agreement":null},{"id":"W2328048469","doi":"10.1136/jech-2015-206256.99","title":"PP01 International pooling project of mammographic density - insights of a marker of breast cancer risk from 22 diverse countries","year":2015,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Pooling; Breast cancer; Mammography; Incidence (geometry); Medicine; Digital mammography; Demography; Population; Gynecology; Medical physics; Cancer; Environmental health; Computer science; Artificial intelligence; Internal medicine; Mathematics","score_opus":0.013630455363872154,"score_gpt":0.2903443595331745,"score_spread":0.27671390416930236,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2328048469","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.995927,0.00030243755,0.00087950943,0.0003313913,0.0002631361,0.00013124208,0.000093677925,0.000015564472,0.002056055],"genre_scores_gemma":[0.99696326,0.00043317743,0.002212156,0.00011565125,0.00010578539,0.0000025793352,0.00002264487,0.000009468998,0.00013526069],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9989545,0.00004995958,0.00030837444,0.00014633348,0.00044464518,0.00009624197],"domain_scores_gemma":[0.9990015,0.00008769971,0.00026427023,0.00015024153,0.0004199203,0.000076361284],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002865213,0.00009037699,0.00032090963,0.00018389613,0.000017741288,0.0000047177004,0.00010512706,0.00005178959,0.00032385494],"category_scores_gemma":[0.00023242077,0.00006635392,0.00008566749,0.00015238872,0.00022879108,0.00006746,0.00007329317,0.00018404389,9.810885e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00061668595,0.00011468788,0.9907385,0.00006253008,0.0003521765,0.000012291999,0.0009247116,0.000031707328,0.0015814841,0.00018260031,0.002119321,0.003263272],"study_design_scores_gemma":[0.0032599524,0.00009416333,0.9730737,0.00046041215,0.00036093194,0.000028073067,0.0010704669,0.017100483,0.0021458447,0.00046366168,0.0018206112,0.00012168985],"about_ca_topic_score_codex":0.0272016,"about_ca_topic_score_gemma":0.00018359376,"teacher_disagreement_score":0.027018007,"about_ca_system_score_codex":0.00003354129,"about_ca_system_score_gemma":0.00019461638,"threshold_uncertainty_score":0.97927636},"labels":[],"label_agreement":null},{"id":"W2328428430","doi":"10.1117/12.2216285","title":"3D texture-based classification applied on brain white matter lesions on MR images","year":2016,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Histogram; Artificial intelligence; Texture (cosmology); Pattern recognition (psychology); Computer science; White matter; Co-occurrence matrix; Gray level; Support vector machine; Image texture; Classifier (UML); Computer vision; Contextual image classification; Histogram of oriented gradients; Image processing; Pixel; Magnetic resonance imaging; Image (mathematics); Medicine; Radiology","score_opus":0.01103824542969751,"score_gpt":0.2508402453563278,"score_spread":0.23980199992663032,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2328428430","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90775937,0.000015954178,0.0004018556,0.07966288,0.00016746251,0.0005705244,0.000030401692,0.00009798004,0.011293544],"genre_scores_gemma":[0.93548644,0.000034225726,0.05825037,0.0038133124,0.00067249895,0.00019634899,0.000018126824,0.00010900131,0.0014196632],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9977091,2.996246e-8,0.0005879901,0.00048241596,0.0008274168,0.00039307275],"domain_scores_gemma":[0.9982137,0.00043672786,0.00033789306,0.000100581376,0.0007170248,0.00019406807],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006607943,0.0003303401,0.00043384117,0.00017184795,0.00009683997,0.00007111172,0.00052097614,0.00019901968,0.00007160613],"category_scores_gemma":[0.0011732306,0.00021144746,0.00048953824,0.00023202696,0.00029972,0.00016684004,0.0000665364,0.00048033355,0.000018684652],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036338554,0.00026688876,0.0026156283,0.00035249218,0.00023053023,2.3377737e-7,0.000068783964,0.00007058524,0.7546382,0.19354686,0.044414137,0.0034322895],"study_design_scores_gemma":[0.021770095,0.004130713,0.16443512,0.008364757,0.0012507933,0.0001038358,0.0017672647,0.14172299,0.5639774,0.004363432,0.08550329,0.0026103184],"about_ca_topic_score_codex":0.0000022998527,"about_ca_topic_score_gemma":2.149574e-8,"teacher_disagreement_score":0.19066077,"about_ca_system_score_codex":0.00021188779,"about_ca_system_score_gemma":0.00004636809,"threshold_uncertainty_score":0.8622578},"labels":[],"label_agreement":null},{"id":"W2328828316","doi":"10.1097/01.eem.0000351837.85635.76","title":"Jangʼs Pearls Does This 12-Year-Old Need an X-ray?","year":2009,"lang":"en","type":"article","venue":"Emergency Medicine News","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Medicine; Knee pain; Patella; Basketball; Ligament; Surgery; Physical therapy; Osteoarthritis","score_opus":0.020054438345903532,"score_gpt":0.32501736540265924,"score_spread":0.3049629270567557,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2328828316","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6013529,0.0020132272,0.0017748165,0.13212012,0.007013554,0.0010189418,0.000005337971,0.00069476105,0.25400636],"genre_scores_gemma":[0.86000234,0.0030589434,0.004266342,0.01294326,0.00977627,0.000023050789,0.00017800447,0.00012043824,0.10963134],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99692655,0.00012925711,0.00084751076,0.0006159057,0.0008399571,0.000640823],"domain_scores_gemma":[0.99798304,0.00005160561,0.00019879082,0.00081145455,0.0001445531,0.0008105602],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008046905,0.00037740293,0.0007268011,0.00028902473,0.00017652327,0.000010630908,0.00032423786,0.00016254335,0.017880047],"category_scores_gemma":[0.0012565851,0.00023835331,0.00017939237,0.00044139795,0.00015657987,0.00019366597,0.000035721318,0.0008774932,0.0001918119],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035727082,0.0006496686,0.100475065,0.00015059754,0.00015812022,0.00021682757,0.0052856323,0.00003081655,0.044899426,0.0029175992,0.76820296,0.076656036],"study_design_scores_gemma":[0.007598005,0.00422052,0.18829517,0.000656993,0.00064620026,0.00011675884,0.0027549597,0.006176222,0.00030285382,0.0030253427,0.785271,0.00093598955],"about_ca_topic_score_codex":0.001358085,"about_ca_topic_score_gemma":0.000046276833,"teacher_disagreement_score":0.25864947,"about_ca_system_score_codex":0.00005975869,"about_ca_system_score_gemma":0.00007755741,"threshold_uncertainty_score":0.98301774},"labels":[],"label_agreement":null},{"id":"W2333230019","doi":"10.1097/01206501-200606000-00034","title":"RESULTS OF PATCH TESTING TO A CORTICOSTEROID SERIES: EXPERIENCE WITH 1000 PATIENTS AT MAYO CLINIC","year":2006,"lang":"en","type":"article","venue":"Dermatitis","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine; Patch testing; Series (stratigraphy); Corticosteroid; Dermatology; Internal medicine; Immunology; Contact dermatitis","score_opus":0.01169977170331637,"score_gpt":0.26952637767002313,"score_spread":0.25782660596670676,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2333230019","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98595047,0.000023826522,0.00037233517,0.0020442326,0.000092468465,0.00025880066,0.000019198333,0.000048907925,0.0111897625],"genre_scores_gemma":[0.98787904,0.0000064070887,0.00820601,0.0022402545,0.000064395535,0.000021764978,0.000057626945,0.000022050337,0.0015024234],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9986745,0.000030877076,0.00050088036,0.00021975911,0.0003426361,0.00023132218],"domain_scores_gemma":[0.9991332,0.00012390561,0.00018279676,0.00026077707,0.00015854773,0.00014076676],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010524085,0.00011895938,0.00026172388,0.00006550473,0.00007189369,0.000016141295,0.00008330606,0.000037650556,0.00008074557],"category_scores_gemma":[0.00048603403,0.00009592484,0.000031985346,0.00023884462,0.000098742334,0.000085770385,0.00005994223,0.00013390376,0.00004530924],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013405542,0.00014483184,0.9649188,0.00011894457,0.0000151754075,0.00011009911,0.0019246165,0.000053123855,0.0010818663,0.0000052397286,0.020332437,0.011160791],"study_design_scores_gemma":[0.0028328646,0.0007508038,0.9674946,0.0005612986,0.00003234043,0.00017458611,0.0001470184,0.0007799319,0.0034026464,0.000012472793,0.023648543,0.00016287314],"about_ca_topic_score_codex":0.0007524073,"about_ca_topic_score_gemma":0.00006270981,"teacher_disagreement_score":0.0109979175,"about_ca_system_score_codex":0.000052787214,"about_ca_system_score_gemma":0.000037196965,"threshold_uncertainty_score":0.39117014},"labels":[],"label_agreement":null},{"id":"W2333786086","doi":"10.1017/s1431927614005820","title":"Fusing Multi-scale and Multi-modal 3D Imaging and Characterization","year":2014,"lang":"en","type":"article","venue":"Microscopy and Microanalysis","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Object Research Systems (Canada)","funders":"","keywords":"Characterization (materials science); Modal; Scale (ratio); Computer science; Materials science; Nanotechnology; Geography; Cartography; Composite material","score_opus":0.0071485684014793585,"score_gpt":0.2796510667769305,"score_spread":0.27250249837545115,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2333786086","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8360037,0.0010872416,0.16160178,0.001069589,0.000055008553,0.00010388219,0.0000059283957,0.000036898182,0.0000359661],"genre_scores_gemma":[0.90902025,0.0007598418,0.08787605,0.0015383785,0.00010862796,0.00000410153,0.00008883979,0.000032025673,0.0005718621],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99893355,0.000060815357,0.00025018607,0.00041908058,0.00008644067,0.00024991724],"domain_scores_gemma":[0.9994567,0.000039245904,0.00009665487,0.0001616129,0.000048794453,0.00019699312],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036346714,0.00018645135,0.0003902405,0.00018342175,0.00025480834,0.0001308297,0.00004025819,0.000063713254,0.000019006377],"category_scores_gemma":[0.00007753988,0.00016565551,0.000051615134,0.00014096829,0.00023117772,0.00011533317,0.000078677695,0.0002365397,0.0000027476376],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018504463,0.000038892715,0.1817614,0.000071962764,0.00004836606,0.0000045381094,0.00044168675,9.360513e-7,0.7387411,0.0000028910974,0.000013035348,0.0788567],"study_design_scores_gemma":[0.004122915,0.00005800279,0.28979295,0.00025953568,0.0010256474,0.0003394045,0.00025809387,0.6681439,0.025376141,0.0000093426115,0.010185163,0.00042885778],"about_ca_topic_score_codex":0.00017606631,"about_ca_topic_score_gemma":0.000015661677,"teacher_disagreement_score":0.71336496,"about_ca_system_score_codex":0.000018773051,"about_ca_system_score_gemma":0.000014302268,"threshold_uncertainty_score":0.6755236},"labels":[],"label_agreement":null},{"id":"W2338157841","doi":"10.1007/s11517-016-1495-8","title":"Metastatic liver tumour segmentation with a neural network-guided 3D deformable model","year":2016,"lang":"en","type":"article","venue":"Medical & Biological Engineering & Computing","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":26,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier de l’Université de Montréal; Centre Hospitalier Universitaire Sainte-Justine; Polytechnique Montréal","funders":"Fonds de Recherche du Québec - Santé; Canada Research Chairs","keywords":"Segmentation; Artificial intelligence; Computer science; Voxel; Pattern recognition (psychology); Artificial neural network; Image segmentation; Computer vision","score_opus":0.021900118868427736,"score_gpt":0.2697929201860803,"score_spread":0.24789280131765257,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2338157841","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46753117,0.00018077869,0.5304873,0.0011003242,0.00011584581,0.00017369652,8.54546e-7,0.00020911782,0.00020090994],"genre_scores_gemma":[0.9118146,0.000053500284,0.0862204,0.0013948755,0.00038090607,0.0000108390905,0.000015384443,0.00003154076,0.000077993776],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978383,0.0000622461,0.00046079094,0.00040113626,0.00054338365,0.00069414295],"domain_scores_gemma":[0.9987523,0.00038950169,0.00010125031,0.0001674302,0.00006307238,0.0005264477],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008704469,0.00027222958,0.00048375197,0.00007067349,0.000110164,0.00002581859,0.00018568372,0.00011569613,0.00021862339],"category_scores_gemma":[0.0009339791,0.00013799431,0.00009974214,0.00022744664,0.00013972941,0.00007608481,0.00013507434,0.0005588749,0.00003382904],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018068224,0.00019807428,0.027056532,0.0002243514,0.0002275086,0.0008440779,0.00016358698,0.77425104,0.011922063,0.0007822719,0.0012167912,0.18293302],"study_design_scores_gemma":[0.001686943,0.00025564482,0.006767815,0.0005289471,0.00005442844,0.000635523,0.000007067938,0.98937106,0.00009278148,0.000029581366,0.0003499845,0.00022020747],"about_ca_topic_score_codex":0.000018759149,"about_ca_topic_score_gemma":5.10387e-7,"teacher_disagreement_score":0.44428337,"about_ca_system_score_codex":0.00009470529,"about_ca_system_score_gemma":0.00008226526,"threshold_uncertainty_score":0.5627245},"labels":[],"label_agreement":null},{"id":"W2338674205","doi":"10.1016/j.hpb.2016.02.048","title":"Preoperative T2-weighted MRI predicts long-term outcomes in patients with colorectal liver metastases","year":2016,"lang":"en","type":"article","venue":"HPB","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; Sunnybrook Health Science Centre","funders":"","keywords":"Medicine; Proportional hazards model; Hepatectomy; Magnetic resonance imaging; Colorectal cancer; Internal medicine; Retrospective cohort study; Radiology; Oncology; Surgery; Cancer; Resection","score_opus":0.009070815458252711,"score_gpt":0.26187726109538906,"score_spread":0.25280644563713633,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2338674205","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9962236,0.000071605085,0.0021748678,0.00048453128,0.000110372144,0.00048621444,0.000021611224,0.000056082663,0.00037106845],"genre_scores_gemma":[0.99589425,0.000031299645,0.0025859936,0.00040710781,0.00005586072,0.000027895247,0.000045449342,0.000026530906,0.00092560647],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9988462,0.00007633968,0.00020542865,0.00027313625,0.0003294652,0.0002694408],"domain_scores_gemma":[0.9993672,0.00014575418,0.00006560673,0.00017364799,0.00008526336,0.0001625522],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014020097,0.00016677914,0.00034036904,0.00011404806,0.000043742377,0.000016456072,0.00008381268,0.000050649152,0.00032956002],"category_scores_gemma":[0.00022670627,0.00008318281,0.000047376852,0.00011768887,0.00014322609,0.00013231345,0.000044080207,0.00019575196,0.000042100397],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030923766,0.0003247856,0.9819487,0.000026169375,0.00011176346,0.00012418184,0.00024957387,0.0000013945929,0.00009800139,0.000025592764,0.00040950833,0.016371137],"study_design_scores_gemma":[0.005821374,0.00065948814,0.9919465,0.00028866777,0.00008445996,0.00001045441,0.0000082097695,0.0006312688,0.00022958161,0.0000032730018,0.00018921711,0.00012750844],"about_ca_topic_score_codex":0.000029122783,"about_ca_topic_score_gemma":0.00002281216,"teacher_disagreement_score":0.016243627,"about_ca_system_score_codex":0.00007700024,"about_ca_system_score_gemma":0.00006508521,"threshold_uncertainty_score":0.3608451},"labels":[],"label_agreement":null},{"id":"W2338745346","doi":"","title":"Comparison of semi-automatic cardiac analysis software for the evaluation of the left ventricular ejection fraction in small animal PET","year":2015,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Repeatability; Ejection fraction; Nuclear medicine; Medicine; Tracing; Limits of agreement; Regurgitation (circulation); Heart failure; Cardiology; Internal medicine; Mathematics; Computer science; Statistics","score_opus":0.0490258340009071,"score_gpt":0.37353556171019436,"score_spread":0.32450972770928727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2338745346","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95936835,0.00038548736,0.038702372,0.00068579055,0.00015048645,0.0005619772,0.0000017095288,0.000014392286,0.0001294422],"genre_scores_gemma":[0.9982394,0.0000054340912,0.0015897963,0.00003903066,0.000050619466,0.000017281256,0.000019998603,0.0000066269204,0.000031837062],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988598,0.0001852786,0.00031488642,0.00010786013,0.0004430224,0.00008911053],"domain_scores_gemma":[0.99891114,0.00026464358,0.00021224885,0.00020499669,0.00037281064,0.000034151166],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023041475,0.000063905834,0.00031496724,0.00012674049,0.000037847847,0.0000066665307,0.00006828397,0.00003392757,0.000028342263],"category_scores_gemma":[0.0023299798,0.00003525011,0.0001728502,0.00049804675,0.00003960893,0.000030745283,0.000018569272,0.00016211251,5.438057e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037455335,0.0001080377,0.9560012,0.00006343064,0.00034601326,2.8321767e-7,0.00033954237,0.031588234,0.0006866761,0.000020515987,0.0004658642,0.010342718],"study_design_scores_gemma":[0.00054612436,0.000064479325,0.32290047,0.000030337487,0.0018605043,0.000002434053,0.00080874714,0.67271894,0.0008533131,0.000047910773,0.00014058566,0.000026136733],"about_ca_topic_score_codex":0.0004047501,"about_ca_topic_score_gemma":0.00004907334,"teacher_disagreement_score":0.64113075,"about_ca_system_score_codex":0.00012066481,"about_ca_system_score_gemma":0.000115144474,"threshold_uncertainty_score":0.27893716},"labels":[],"label_agreement":null},{"id":"W2352821201","doi":"","title":"A relation of ultrasonic images of prostate parenchymal nodes to histopathology","year":2003,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"CAE (Canada)","funders":"","keywords":"Medicine; Ultrasonic sensor; Prostate; Histopathology; Radiology; Histopathological examination; Parenchyma; Prostate gland; Pathology; Cancer; Internal medicine","score_opus":0.008373134155826193,"score_gpt":0.2786948905280203,"score_spread":0.27032175637219413,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2352821201","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96942985,0.00016839751,0.009538164,0.0010078815,0.000095125266,0.00016170731,0.0000012138621,0.000019874074,0.019577796],"genre_scores_gemma":[0.97156286,0.000025562507,0.026093282,0.00022919253,0.000011400513,0.0000042976485,0.000004095324,0.000008228735,0.002061084],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9993635,0.000044854016,0.00023647673,0.00011936913,0.000119583325,0.00011626123],"domain_scores_gemma":[0.99958766,0.00006316072,0.000074925745,0.0001320861,0.00007182672,0.000070353846],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032215676,0.00005878878,0.0002092038,0.000088285364,0.000014422106,0.0000016077453,0.00003221441,0.0000327401,0.00014547352],"category_scores_gemma":[0.0010666683,0.00004595477,0.00004129946,0.00011853245,0.000078712445,0.000023938279,0.000007661296,0.0001189171,0.0000059937497],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008352927,0.00016392868,0.5592243,0.0001721004,0.000018761126,0.000023896418,0.0010285003,0.0001947038,0.41980052,0.0076945554,0.0014754516,0.010119756],"study_design_scores_gemma":[0.0020317947,0.0008025043,0.8983681,0.00022753509,0.00011331336,0.00025540133,0.00028514047,0.0010808768,0.08708293,0.000875039,0.0087075755,0.00016974448],"about_ca_topic_score_codex":0.0000423174,"about_ca_topic_score_gemma":8.72577e-7,"teacher_disagreement_score":0.33914387,"about_ca_system_score_codex":0.000019390405,"about_ca_system_score_gemma":0.00005764925,"threshold_uncertainty_score":0.18739812},"labels":[],"label_agreement":null},{"id":"W2358693203","doi":"10.1080/10255842.2016.1181173","title":"Interactive graph-cut segmentation for fast creation of finite element models from clinical ct data for hip fracture prediction","year":2016,"lang":"en","type":"article","venue":"Computer Methods in Biomechanics & Biomedical Engineering","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":65,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Bone and Joint Health Institute; University of Calgary","funders":"National Institute on Aging; National Institutes of Health","keywords":"Segmentation; Finite element method; Graph; Hip fracture; Computer science; Fracture (geology); Artificial intelligence; Geology; Structural engineering; Medicine; Theoretical computer science; Engineering; Geotechnical engineering","score_opus":0.0509533755087771,"score_gpt":0.4094892290350451,"score_spread":0.358535853526268,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2358693203","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035689203,0.00012688492,0.99180007,0.0012275693,0.0017740253,0.0009295465,0.00048313936,0.00008720735,0.0000026452767],"genre_scores_gemma":[0.058808286,0.00020198473,0.9380815,0.0003290791,0.00087274425,0.0001053239,0.0015415092,0.000051040373,0.000008503444],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975107,0.0001458358,0.0010437219,0.0006553739,0.00031980098,0.00032457153],"domain_scores_gemma":[0.9958005,0.003037734,0.0002770098,0.0005317435,0.00012709862,0.00022589609],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027827353,0.0002391093,0.0006010318,0.00044740035,0.00003629176,0.000020278545,0.00034139192,0.00018076299,0.000017534057],"category_scores_gemma":[0.0013459837,0.00017906383,0.00017371193,0.00030385514,0.000071223294,0.00023412282,0.00019680324,0.00031966614,5.260969e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002656627,0.00029601116,0.00007878325,0.00023375379,0.00029958828,0.0000052064493,0.00016525135,0.0015977103,0.10051949,0.00029154788,0.0007371978,0.8955098],"study_design_scores_gemma":[0.0039464408,0.0005315474,0.000116216135,0.0007469268,0.00015192975,0.00000705274,0.000027544955,0.9723359,0.00840418,0.0037800581,0.009784665,0.0001675776],"about_ca_topic_score_codex":0.00002245099,"about_ca_topic_score_gemma":5.045609e-7,"teacher_disagreement_score":0.9707382,"about_ca_system_score_codex":0.00013055309,"about_ca_system_score_gemma":0.00007581746,"threshold_uncertainty_score":0.7302011},"labels":[],"label_agreement":null},{"id":"W2372776145","doi":"","title":"APPLICATION OF NORMAL-AND-TUMOR-TISSUE-CONTRAST SECTION IN TEACHING OF PATHOLOGICAL EXPERIMENT","year":2011,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"CAE (Canada)","funders":"","keywords":"Staining; Pathology; Immunohistochemistry; Reticular connective tissue; Pathological; Frozen section procedure; Biology; Chemistry; Anatomy; Medicine","score_opus":0.013889890707747508,"score_gpt":0.2899445994558117,"score_spread":0.2760547087480642,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2372776145","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9503694,0.000091832204,0.03705975,0.00011811704,0.000035583038,0.00015997158,2.3547398e-7,0.000017162922,0.012147921],"genre_scores_gemma":[0.98704636,0.000011675299,0.012730807,0.000106926964,0.00003530744,0.000012422821,0.000002329317,0.0000054701204,0.000048692054],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9994065,0.00003767291,0.00025362393,0.00012044661,0.000094795694,0.00008694113],"domain_scores_gemma":[0.999729,0.000027196447,0.00008087148,0.00009680079,0.000017936192,0.000048226],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039477565,0.000056528657,0.00019550462,0.00007575455,0.000014406355,0.0000013852332,0.000032497886,0.000036231315,0.000052443065],"category_scores_gemma":[0.00009990363,0.00004273835,0.000021953847,0.00004584553,0.000065523025,0.000032526794,0.00002186887,0.00019739236,8.3555153e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014218417,0.00046909286,0.38812318,0.000104075676,0.00001564698,0.000019038465,0.0035697185,0.000009888776,0.4843107,0.006785376,0.0000348035,0.116416305],"study_design_scores_gemma":[0.0022485394,0.0007518833,0.8468501,0.000121329605,0.000047382033,0.00018146461,0.001216216,0.018305624,0.1287756,0.0004718423,0.0008871302,0.00014291491],"about_ca_topic_score_codex":0.00061765057,"about_ca_topic_score_gemma":0.0000028470029,"teacher_disagreement_score":0.45872688,"about_ca_system_score_codex":0.000014655386,"about_ca_system_score_gemma":0.000008746306,"threshold_uncertainty_score":0.17428192},"labels":[],"label_agreement":null},{"id":"W2373861963","doi":"","title":"Experimental study of multi-slice CT virtual colography in pig colon","year":2005,"lang":"en","type":"article","venue":"Zhongguo yixue yingxiang jishu","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"CAE (Canada)","funders":"","keywords":"Collimated light; Medicine; Nuclear medicine; Significant difference; Volume (thermodynamics); Optics; Physics; Internal medicine","score_opus":0.018358934889567264,"score_gpt":0.3240571206104294,"score_spread":0.30569818572086216,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2373861963","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9968334,0.00048026902,0.000106001484,0.00058207614,0.00024975778,0.0006891837,0.0000028525758,0.00008652842,0.0009699495],"genre_scores_gemma":[0.9962747,0.000014229887,0.0021993075,0.0006921379,0.00018695458,0.000053214262,0.000011441493,0.000044084787,0.00052390934],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9981623,0.00012965365,0.0005149018,0.000406825,0.00039428342,0.00039199946],"domain_scores_gemma":[0.99915236,0.00012270275,0.0001582007,0.00032927486,0.000048445174,0.00018899741],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00051309273,0.00022088016,0.0005209838,0.00039038665,0.00008713127,0.000023347375,0.00020609461,0.0000686864,0.0001031984],"category_scores_gemma":[0.0002450535,0.0002096985,0.00012053423,0.00050059456,0.00014707257,0.00012129425,0.000097898745,0.0005729065,0.000025790938],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004515273,0.01462492,0.84099865,0.00008767305,0.00025386928,0.00076264475,0.012627256,0.0009242499,0.09497896,0.00017524877,0.0018494033,0.03226561],"study_design_scores_gemma":[0.05416653,0.011431536,0.7459974,0.0009865431,0.00043769207,0.00056273525,0.04827292,0.0576482,0.05043396,0.000013234016,0.028506251,0.0015429596],"about_ca_topic_score_codex":0.00073932315,"about_ca_topic_score_gemma":0.00014662016,"teacher_disagreement_score":0.0950012,"about_ca_system_score_codex":0.000119523,"about_ca_system_score_gemma":0.0000600611,"threshold_uncertainty_score":0.85512567},"labels":[],"label_agreement":null},{"id":"W2375617279","doi":"","title":"CT perfusion imaging and interventional therapy of genetically engineered mouse prostate cancer","year":2009,"lang":"en","type":"article","venue":"Contemporary Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Prostate cancer; Medicine; Prostate; Perfusion; Pathology; Cancer; Blood flow; Radiology; Internal medicine","score_opus":0.018532202214245702,"score_gpt":0.3089813472507304,"score_spread":0.29044914503648467,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2375617279","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92554903,0.037469164,0.0008410628,0.033625137,0.00017040136,0.00036895848,0.00000465718,0.00005951662,0.0019120984],"genre_scores_gemma":[0.99347574,0.0027466558,0.00056297367,0.0020448717,0.0002617004,0.000008275595,0.00004268686,0.000019760948,0.0008373178],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9987955,0.00004502807,0.00043315598,0.0002463528,0.0003084395,0.00017152775],"domain_scores_gemma":[0.99931645,0.00005937135,0.00011914495,0.00018085912,0.000114153925,0.00020999892],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042206,0.0001638341,0.0004164582,0.0001541146,0.000040900406,0.000006688589,0.00007704982,0.000023606213,0.00020566097],"category_scores_gemma":[0.00020751962,0.0001156732,0.000065202206,0.000120595134,0.00024158754,0.000066751156,0.000022403672,0.0002735542,9.387242e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00073228794,0.00034187152,0.11411477,0.00018546676,0.00010253052,0.00026684444,0.0012095013,0.000016444137,0.35645482,0.00049790175,0.014298687,0.5117789],"study_design_scores_gemma":[0.052158542,0.007741405,0.66627896,0.008484069,0.00026258276,0.0012115008,0.0013595588,0.08903927,0.03230213,0.001935915,0.13804598,0.0011801091],"about_ca_topic_score_codex":0.00009222286,"about_ca_topic_score_gemma":3.6154862e-7,"teacher_disagreement_score":0.55216414,"about_ca_system_score_codex":0.000020611209,"about_ca_system_score_gemma":0.00009412841,"threshold_uncertainty_score":0.47170162},"labels":[],"label_agreement":null},{"id":"W2392225363","doi":"","title":"The study of hypotonic CT scan technique in gastrointestinal neoplasms","year":2000,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"CAE (Canada)","funders":"","keywords":"Medicine; Stomach; Tonicity; Computed tomography; Benign neoplasms; Radiology; Gastrointestinal tract; Gastroenterology; Internal medicine","score_opus":0.007592151399731891,"score_gpt":0.2774562742150513,"score_spread":0.2698641228153194,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2392225363","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97701067,0.000023590104,0.00022330886,0.0010487372,0.000013281038,0.00052828464,1.3530881e-7,0.00003448524,0.021117521],"genre_scores_gemma":[0.9944351,0.00001601462,0.0031854673,0.00013296952,0.000025026238,0.000033478995,7.0652965e-7,0.000011015038,0.0021602428],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99918604,0.000054791723,0.00024906293,0.00013420287,0.000188896,0.00018702199],"domain_scores_gemma":[0.99951696,0.00014000587,0.000034550878,0.00022143232,0.000019925676,0.000067130575],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00051406,0.00007730581,0.00016905458,0.00005684515,0.000048971302,0.000009587786,0.00011184762,0.000008545034,0.00033065354],"category_scores_gemma":[0.00017929534,0.000045813762,0.00003293018,0.00017636329,0.00008340919,0.000018274615,0.00001876939,0.00036033127,0.00000942478],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029716172,0.0013702586,0.7006474,0.000038879207,0.000032297077,0.00045476365,0.00038062327,0.00038783968,0.0058187526,0.00028508203,0.0012131569,0.28907374],"study_design_scores_gemma":[0.010277817,0.0065693646,0.9004244,0.0012140932,0.000109911634,0.0073814895,0.0038420684,0.05098985,0.002964632,0.0007584828,0.0150560355,0.0004118174],"about_ca_topic_score_codex":0.00070193846,"about_ca_topic_score_gemma":0.00011092118,"teacher_disagreement_score":0.28866193,"about_ca_system_score_codex":0.000030250176,"about_ca_system_score_gemma":0.00005901852,"threshold_uncertainty_score":0.36204243},"labels":[],"label_agreement":null},{"id":"W2395903267","doi":"10.1016/j.brachy.2016.04.133","title":"Is Daily CT-Based Adaptive Endorectal Brachytherapy of Benefit Compared to Using a Single Treatment Plan for Preoperative Treatment of Locally Advanced Rectal Cancer?","year":2016,"lang":"en","type":"article","venue":"Brachytherapy","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Jewish General Hospital","funders":"","keywords":"Medicine; Brachytherapy; Nuclear medicine; Radiation treatment planning; Radiography; Radiology; Mesorectum; Radiation therapy; Colorectal cancer; Dosimetry; Cancer; Internal medicine","score_opus":0.04688007992243,"score_gpt":0.33804312260837704,"score_spread":0.29116304268594706,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2395903267","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96799165,0.001305615,0.026101224,0.0017257502,0.00018778865,0.0021454366,0.0003898371,0.000050909843,0.00010181155],"genre_scores_gemma":[0.97009003,0.00030609005,0.027966212,0.0006053308,0.00018941025,0.00033341328,0.000034723933,0.000080051606,0.00039472475],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99809015,0.00006688571,0.00057434774,0.00054350134,0.00030207846,0.00042305133],"domain_scores_gemma":[0.99843276,0.00037672004,0.00032676675,0.00036342532,0.00025138454,0.0002489256],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00010693457,0.0003965025,0.0010031221,0.00019365012,0.0000947402,0.000012120159,0.00010933746,0.00006414483,0.00013686068],"category_scores_gemma":[0.000040778807,0.0002541324,0.00032557332,0.00022031114,0.0001633098,0.0000888086,0.000009070561,0.00006159479,0.0000016839433],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.01112352,0.0016640121,0.017275242,0.000046275658,0.0007360503,0.000024302675,0.0033121302,0.0023549504,0.47454187,0.0000706278,0.00005885086,0.48879218],"study_design_scores_gemma":[0.042384904,0.034999453,0.01088066,0.0014126447,0.000339446,0.0000782541,0.00037302275,0.038206674,0.8637935,0.00011913725,0.0068068574,0.0006054657],"about_ca_topic_score_codex":0.0006940956,"about_ca_topic_score_gemma":0.00013625633,"teacher_disagreement_score":0.4881867,"about_ca_system_score_codex":0.00068587984,"about_ca_system_score_gemma":0.00037911203,"threshold_uncertainty_score":0.9999911},"labels":[],"label_agreement":null},{"id":"W2397554324","doi":"10.1158/1538-7445.sabcs15-p1-01-04","title":"Abstract P1-01-04: Early stage breast cancer prognostication using whole tumor or Ki67 heterogeneity-based digital imaging","year":2016,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Roche (Canada)","funders":"","keywords":"Medicine; Breast cancer; Immunohistochemistry; Stage (stratigraphy); Cohort; Oncology; Cancer; Internal medicine; Adjuvant therapy; Pathology; Radiology; Biology","score_opus":0.06494183270319297,"score_gpt":0.42374048315077917,"score_spread":0.3587986504475862,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2397554324","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9824871,0.00044021438,0.0021818208,0.01333484,0.00019545316,0.00063346734,0.0002911949,0.0001009078,0.00033501495],"genre_scores_gemma":[0.9971923,0.00007247858,0.00034099637,0.00046214962,0.0007141219,0.00016265684,0.00001954666,0.00008585772,0.0009498779],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9971344,0.00008476606,0.00034006184,0.00057662884,0.001008363,0.0008558162],"domain_scores_gemma":[0.99822366,0.00032904028,0.000109020875,0.0004368324,0.00041360795,0.00048785872],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008154303,0.00021073048,0.00029976416,0.00029451848,0.00026824282,0.00024359152,0.00026683352,0.000057302528,0.00079878856],"category_scores_gemma":[0.00060119084,0.00013486439,0.00009552403,0.0004234404,0.0005024143,0.00037532655,0.00010420914,0.000662676,0.00007448028],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009893429,0.00023072866,0.53611016,0.00045680784,0.00009728559,0.00044991632,0.00013084248,0.00016385688,0.27845967,0.000034613644,0.0018511781,0.18102558],"study_design_scores_gemma":[0.010140056,0.00037380922,0.8267361,0.007887195,0.00016308384,0.00029885405,0.00026530825,0.024984356,0.0477236,0.0001355302,0.08016015,0.0011319671],"about_ca_topic_score_codex":0.0016598178,"about_ca_topic_score_gemma":0.000046053716,"teacher_disagreement_score":0.29062593,"about_ca_system_score_codex":0.00068831106,"about_ca_system_score_gemma":0.0013098151,"threshold_uncertainty_score":0.87461746},"labels":[],"label_agreement":null},{"id":"W2397768676","doi":"10.1016/j.ejca.2016.03.082","title":"RECIST 1.1 – Standardisation and disease-specific adaptations: Perspectives from the RECIST Working Group","year":2016,"lang":"en","type":"review","venue":"European Journal of Cancer","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":380,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"National Cancer Institute; Canadian Cancer Society Research Institute","keywords":"Response Evaluation Criteria in Solid Tumors; Medicine; Clinical trial; Medical physics; Clinical endpoint; Biomarker; Imaging biomarker; Radiology; Phases of clinical research; Internal medicine; Magnetic resonance imaging","score_opus":0.05869387304731272,"score_gpt":0.3462172372383782,"score_spread":0.2875233641910655,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2397768676","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000024684,0.9887686,0.0040614204,0.0037876451,0.00078287727,0.00020873015,0.000043001102,0.0000120083,0.002311069],"genre_scores_gemma":[0.00039550522,0.9929895,0.00094966154,0.00018070327,0.0047941017,0.000004150248,0.000012607638,0.00007824313,0.0005955435],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977061,0.000727528,0.0006782851,0.00024582425,0.00048944354,0.00015280856],"domain_scores_gemma":[0.9978621,0.0005512132,0.0008705794,0.0002462193,0.00017873496,0.00029114028],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014206278,0.0002292712,0.00075658853,0.000106055246,0.00016430658,0.0001162303,0.00021529,0.000028659508,0.00020504242],"category_scores_gemma":[0.00093679415,0.00011617788,0.0003312728,0.00013236876,0.00027019775,0.00007848246,0.00004721131,0.00081119203,0.000010374958],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008264116,0.000013692939,0.000057413974,0.00016915434,0.0002473563,0.00018678505,0.0006172766,9.687158e-7,0.0000014405531,0.0001504748,0.009310725,0.9891621],"study_design_scores_gemma":[0.00059494295,0.000051232295,0.0011041502,0.038769905,0.0007598386,0.000077102384,0.0002681348,0.0000054603747,1.9840492e-8,0.00007756668,0.9581641,0.00012753099],"about_ca_topic_score_codex":0.000007465061,"about_ca_topic_score_gemma":0.0000017097008,"teacher_disagreement_score":0.98903453,"about_ca_system_score_codex":0.00027003328,"about_ca_system_score_gemma":0.0002972714,"threshold_uncertainty_score":0.47375962},"labels":[],"label_agreement":null},{"id":"W2398555955","doi":"","title":"The dmir_tagus team at TAC-KBP 2012.","year":2012,"lang":"en","type":"article","venue":"Theory and applications of categories","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science","score_opus":0.006210658885809437,"score_gpt":0.27731608707708655,"score_spread":0.2711054281912771,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2398555955","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7620046,0.04387417,0.046997186,0.008857331,0.00033401328,0.0014455174,0.000016109896,0.00020369906,0.13626736],"genre_scores_gemma":[0.9899072,0.00052640936,0.000270376,0.00020424653,0.0002500875,0.00008949652,0.000012091222,0.000010562089,0.008729512],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99945396,0.000050834253,0.00014762091,0.000082541024,0.00009990959,0.0001651027],"domain_scores_gemma":[0.99911284,0.0004087114,0.00006946257,0.00025773377,0.000040036655,0.00011123437],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008621681,0.0000719749,0.00012427843,0.00002578281,0.00031418595,0.000011128838,0.00008366067,0.00003400936,0.00005696872],"category_scores_gemma":[0.00012737002,0.000044334072,0.0000329639,0.00008540061,0.00051232066,0.00006716367,0.000054627475,0.00013432538,0.000021919619],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009772128,0.000058873302,0.007113308,0.00004212347,0.00003635819,1.2957474e-7,0.0005446787,9.991603e-7,0.002073344,0.9167926,0.0031788817,0.07006101],"study_design_scores_gemma":[0.00044341476,0.000060069997,0.010746437,0.000016715378,0.000130661,0.00008852235,0.0010374407,0.000048537877,0.0051527503,0.07905551,0.9031044,0.00011553495],"about_ca_topic_score_codex":0.00000598505,"about_ca_topic_score_gemma":5.7303123e-7,"teacher_disagreement_score":0.89992553,"about_ca_system_score_codex":0.000011967871,"about_ca_system_score_gemma":0.000018605855,"threshold_uncertainty_score":0.24164961},"labels":[],"label_agreement":null},{"id":"W2401769792","doi":"10.1158/1538-7445.sabcs15-p1-01-01","title":"Abstract P1-01-01: Analytical validation of a standardized scoring protocol for Ki67: Phase-3 of an international multicenter collaboration","year":2016,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mount Sinai Hospital; Ontario Institute for Cancer Research","funders":"","keywords":"External quality assessment; Intraclass correlation; Medicine; Breast cancer; Protocol (science); Nuclear proliferation; Nuclear medicine; Pathology; Medical physics; Reproducibility; Statistics; Cancer; Internal medicine; Mathematics","score_opus":0.11483865516037185,"score_gpt":0.5499462012080074,"score_spread":0.4351075460476356,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2401769792","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95800877,0.0000065083723,0.006470197,0.0033690818,0.00012730724,0.031178238,0.000112699905,0.000018844163,0.00070834404],"genre_scores_gemma":[0.9759905,0.000011307668,0.0020877442,0.000024859093,0.00033568905,0.021312471,0.000026192507,0.00002130051,0.00018993995],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99840826,0.00007312875,0.00035776658,0.00021541925,0.0007377431,0.00020766439],"domain_scores_gemma":[0.99842376,0.00024438323,0.000120754805,0.00019311758,0.000886562,0.00013140697],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015235387,0.00007079338,0.0002123889,0.00022286558,0.000049118615,0.000024844703,0.0001365061,0.000050720704,0.00053108414],"category_scores_gemma":[0.001527002,0.00004819945,0.000055347053,0.00019783936,0.00018586408,0.00020399441,0.000031260173,0.00017409674,0.0000014700863],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.009409908,0.00074011035,0.011388186,0.00070376234,0.0001685745,0.000007898872,0.0004079246,0.00008387929,0.87657267,0.00059247896,0.001750927,0.098173685],"study_design_scores_gemma":[0.043457624,0.0016126684,0.009554869,0.0026295632,0.00006242964,0.0000036987642,0.00029664012,0.027176755,0.86961627,0.0003053243,0.045100573,0.00018360997],"about_ca_topic_score_codex":0.00006876061,"about_ca_topic_score_gemma":0.0000062826225,"teacher_disagreement_score":0.09799008,"about_ca_system_score_codex":0.00023127823,"about_ca_system_score_gemma":0.0004394699,"threshold_uncertainty_score":0.58149993},"labels":[],"label_agreement":null},{"id":"W2402138580","doi":"10.1615/critrevbiomedeng.2015011026","title":"Review of Texture Quantification of CT Images for Classification of Lung Diseases","year":2015,"lang":"en","type":"article","venue":"Critical Reviews in Biomedical Engineering","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Joseph’s Healthcare Hamilton; St Joseph's Health Care; McMaster University","funders":"","keywords":"Artificial intelligence; Pattern recognition (psychology); Texture (cosmology); Support vector machine; Segmentation; Computer science; Fractal analysis; Lung cancer; Lung; Fractal; Image texture; Image segmentation; Fractal dimension; Medicine; Pathology; Mathematics; Image (mathematics); Internal medicine","score_opus":0.03988242801352217,"score_gpt":0.3865376620677046,"score_spread":0.34665523405418247,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2402138580","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022669502,0.6290561,0.3584951,0.0078467615,0.0005453029,0.001507265,0.00006087147,0.000040189207,0.00018147944],"genre_scores_gemma":[0.86477894,0.10447579,0.029369857,0.0005592093,0.00030712967,0.00018720016,0.00024971936,0.000049503044,0.000022634551],"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982083,0.000058075537,0.0010526363,0.00019269249,0.00031285343,0.00017543237],"domain_scores_gemma":[0.9985412,0.00053502,0.00015786279,0.00027763116,0.00022427182,0.00026400894],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0014440909,0.00012241275,0.00082899665,0.00015452725,0.0000070877077,0.000002465318,0.00013132201,0.000052125382,0.000018737672],"category_scores_gemma":[0.030300416,0.00009466278,0.00017340599,0.0004055149,0.00025638076,0.00005011339,0.000025387755,0.00020548585,0.0000010582736],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012544138,0.0014938457,0.005386373,0.47724214,0.000094316114,0.000018634875,0.00012846594,0.00003073315,0.110597216,0.020437004,0.044770844,0.33967498],"study_design_scores_gemma":[0.0032004656,0.0006437483,0.014193824,0.22932018,0.0011279694,0.00008642238,0.00007718711,0.29334775,0.0035131937,0.0006867185,0.45326734,0.0005352079],"about_ca_topic_score_codex":0.0000047298017,"about_ca_topic_score_gemma":3.2454864e-8,"teacher_disagreement_score":0.862512,"about_ca_system_score_codex":0.00004421157,"about_ca_system_score_gemma":0.00009979783,"threshold_uncertainty_score":0.9778678},"labels":[],"label_agreement":null},{"id":"W2404127287","doi":"10.1158/1538-7445.sabcs15-s4-06","title":"Abstract S4-06: HER2 status as predictive marker for AI vs Tam benefit: A TRANS-AIOG meta-analysis of 12129 patients from ATAC, BIG 1-98 and TEAM with centrally determined HER2","year":2016,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Institute for Cancer Research","funders":"","keywords":"Medicine; Tamoxifen; Oncology; Biomarker; Meta-analysis; Clinical trial; Internal medicine; Breast cancer; Cancer","score_opus":0.045027838102963895,"score_gpt":0.37718226040927016,"score_spread":0.33215442230630626,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2404127287","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9912287,0.0012375225,0.0012205269,0.0035460268,0.00005887599,0.0010980637,0.001226234,0.000026058418,0.000357993],"genre_scores_gemma":[0.99651,0.00076456764,0.0005666109,0.00034353705,0.00013008015,0.0002913016,0.0001569442,0.00005760901,0.0011793239],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9969091,0.000105923056,0.0004523499,0.0006528712,0.0011178837,0.0007618953],"domain_scores_gemma":[0.9973177,0.000839186,0.00014782498,0.00045762776,0.0006931188,0.0005445686],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008733814,0.00024540292,0.0010700953,0.0004162291,0.00012368972,0.000047021964,0.00020662333,0.00011724908,0.00091781176],"category_scores_gemma":[0.00052525033,0.00014153907,0.00036864678,0.00052146724,0.00041997855,0.00013569115,0.00005507728,0.00049002544,0.0000036984425],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.015033597,0.0009091903,0.7109515,0.00057633355,0.10411014,0.00008393594,0.0024475732,0.0001925161,0.01670888,0.00004762613,0.004712232,0.14422649],"study_design_scores_gemma":[0.009843737,0.0022543778,0.9256735,0.00036918788,0.03779277,0.0000031027635,0.00021337552,0.0032880947,0.003368931,0.0003053869,0.016494866,0.00039271294],"about_ca_topic_score_codex":0.0041436106,"about_ca_topic_score_gemma":0.00056365645,"teacher_disagreement_score":0.21472198,"about_ca_system_score_codex":0.00020746813,"about_ca_system_score_gemma":0.00041059853,"threshold_uncertainty_score":0.99999547},"labels":[],"label_agreement":null},{"id":"W2405872640","doi":"10.1016/s0849-5831(16)31439-2","title":"GIGO : défense d’une échographie de haute qualité","year":2001,"lang":"fr","type":"article","venue":"Journal SOGC","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Medicine","score_opus":0.015351758840433332,"score_gpt":0.3236951380314328,"score_spread":0.30834337919099947,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2405872640","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6266537,0.048793644,0.022052642,0.2717489,0.009510685,0.0002136152,0.000007487391,0.00010199947,0.02091739],"genre_scores_gemma":[0.77590173,0.09774661,0.01266495,0.020218488,0.025720233,0.000007928638,0.000016157956,0.00020844277,0.06751547],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9965068,0.000402298,0.00083930505,0.00031793516,0.0006948187,0.0012388531],"domain_scores_gemma":[0.9973653,0.00031275445,0.00039160528,0.0003753722,0.00015413914,0.001400834],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0032207519,0.00032729132,0.0006267612,0.00034774438,0.0004829372,0.00022225016,0.00030875026,0.0002761469,0.0021580795],"category_scores_gemma":[0.0015438113,0.00028770394,0.00048376143,0.0007675839,0.0003839505,0.00023411804,0.00006127004,0.0031910674,0.0003253963],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022087779,0.00071148673,0.18033566,0.00025220163,0.00070640055,0.017049067,0.0029443945,0.0008748116,0.0047792755,0.003822414,0.14266348,0.64563996],"study_design_scores_gemma":[0.002643132,0.00032552407,0.073492266,0.0014865617,0.00047660666,0.025952965,0.00059511734,0.012906523,0.00003833189,0.0065955687,0.8751392,0.00034822346],"about_ca_topic_score_codex":0.00074528024,"about_ca_topic_score_gemma":0.000016590191,"teacher_disagreement_score":0.7324757,"about_ca_system_score_codex":0.0002888361,"about_ca_system_score_gemma":0.00036230427,"threshold_uncertainty_score":0.9999575},"labels":[],"label_agreement":null},{"id":"W2417784721","doi":"","title":"[Russia-Canada meeting on updated techniques of computer image processing in oncology].","year":2005,"lang":"en","type":"other","venue":"PubMed","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Medicine; Computer graphics (images); Medical physics","score_opus":0.00785529425199025,"score_gpt":0.2646591853551515,"score_spread":0.2568038911031612,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2417784721","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006070177,0.00074715173,0.00035718785,0.0042059105,0.00024245204,0.0011449987,0.000008798599,0.00021821751,0.99246824],"genre_scores_gemma":[0.15473907,0.00090399745,0.20652866,0.023234323,0.009528922,0.002143185,0.0006313394,0.0026352701,0.5996552],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99850786,0.000067406036,0.0003944541,0.00031972074,0.00032853143,0.00038201403],"domain_scores_gemma":[0.999236,0.000038896753,0.00034329438,0.00020795359,0.000030347219,0.00014349488],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048166956,0.00022415932,0.0006464859,0.00037321117,0.00001822848,0.000012097798,0.00015340054,0.0002340805,0.00018700615],"category_scores_gemma":[0.00014065625,0.00018768018,0.000052170202,0.0001988373,0.000104865445,0.000020298321,0.000048945145,0.0007603881,0.0000019816944],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026060783,0.00008508436,0.00049155374,0.00019267577,0.00002284447,0.00011558065,0.000017068602,0.0000025956053,0.000028601213,0.000009221278,0.24675635,0.7522524],"study_design_scores_gemma":[0.0008246388,0.00004303396,0.008984265,0.0011056084,0.00005395177,0.000030153162,0.000008535781,0.0012870337,0.00029813778,0.0000054332763,0.98715353,0.00020568805],"about_ca_topic_score_codex":0.024922889,"about_ca_topic_score_gemma":0.011696917,"teacher_disagreement_score":0.7520467,"about_ca_system_score_codex":0.00033535543,"about_ca_system_score_gemma":0.00037130484,"threshold_uncertainty_score":0.98157024},"labels":[],"label_agreement":null},{"id":"W2423965850","doi":"10.3389/fonc.2016.00149","title":"Big Data Analytics for Prostate Radiotherapy","year":2016,"lang":"en","type":"review","venue":"Frontiers in Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre","funders":"","keywords":"Computer science; Radiation therapy; Big data; Prostate cancer; Medical physics; Medicine; Data science; Data mining; Cancer; Internal medicine","score_opus":0.08956828952667914,"score_gpt":0.4215837132533063,"score_spread":0.3320154237266272,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2423965850","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.6129098e-7,0.88899237,0.10195657,0.0018825236,0.0048053055,0.001489193,0.00013720847,0.000036226716,0.0007003143],"genre_scores_gemma":[1.1862409e-7,0.92281795,0.070602186,0.0006575802,0.0018999203,0.00013204581,0.00069228944,0.00010124023,0.0030967],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976658,0.0001977369,0.00076080154,0.00070296065,0.00016175439,0.00051093876],"domain_scores_gemma":[0.99795187,0.0004346902,0.0003863623,0.0009966558,0.000043527743,0.00018689237],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001221206,0.0003394597,0.0028251759,0.00053668715,0.00004368973,0.000015774885,0.0006547005,0.00051590684,0.000023759783],"category_scores_gemma":[0.00094571296,0.00022615831,0.0002632647,0.00026806822,0.00023992464,0.000039052833,0.00013786471,0.0007776584,0.000008160324],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005240091,0.000068107,0.0001168239,0.0037611471,0.00030929287,0.000090864705,0.000024363278,3.0442507e-7,1.7123034e-7,0.000018534687,0.20047624,0.79508173],"study_design_scores_gemma":[0.0021023077,0.00035622285,0.000003082597,0.00582359,0.00068284624,0.00014980051,0.000011168358,0.0022797992,3.6956376e-8,0.00016543495,0.9881906,0.00023509182],"about_ca_topic_score_codex":0.0000086983755,"about_ca_topic_score_gemma":0.0000030511792,"teacher_disagreement_score":0.79484665,"about_ca_system_score_codex":0.0008035399,"about_ca_system_score_gemma":0.0014990722,"threshold_uncertainty_score":0.9222468},"labels":[],"label_agreement":null},{"id":"W2465870337","doi":"10.1118/1.4957368","title":"MO-G-201-02: Comparing Sample Size Requirements for Knowledge-Based Treatment Planning","year":2016,"lang":"en","type":"article","venue":"Medical Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto","funders":"","keywords":"Sample size determination; Sample (material); Statistics; Set (abstract data type); Test set; Mathematics; Prostate; Prostate cancer; Histogram; Computer science; Medicine; Artificial intelligence; Cancer","score_opus":0.06112695344735825,"score_gpt":0.36622961188348846,"score_spread":0.3051026584361302,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2465870337","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17792077,0.00030448948,0.80957264,0.007824283,0.0006988896,0.00073096843,0.000021645359,0.00025579327,0.002670491],"genre_scores_gemma":[0.9912823,0.000022170541,0.005136225,0.0013070524,0.0014701925,0.00008664724,0.000033970045,0.000052951455,0.00060849974],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99821126,0.00004343088,0.0003525817,0.0003780658,0.0005272346,0.00048745098],"domain_scores_gemma":[0.996565,0.002438816,0.00010035579,0.00026922097,0.00008258842,0.0005440376],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041576312,0.00022814149,0.0005155818,0.000037681442,0.00014524361,0.000018867402,0.00016501501,0.00010385531,0.00019511706],"category_scores_gemma":[0.003539661,0.000142643,0.0001931821,0.00010734116,0.00025276968,0.00005736086,0.000046822304,0.00019768674,0.00004623436],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047393425,0.0015695463,0.09629643,0.00031957804,0.00034625566,0.00005567554,0.00054867245,0.0000586651,0.004805485,0.00097620656,0.0127095245,0.88184005],"study_design_scores_gemma":[0.09623354,0.0060176244,0.026419733,0.010139105,0.0015726471,0.00007271547,0.0001847991,0.3420259,0.05864566,0.031804167,0.4245843,0.0022998014],"about_ca_topic_score_codex":0.000035940022,"about_ca_topic_score_gemma":0.0000015787217,"teacher_disagreement_score":0.8795402,"about_ca_system_score_codex":0.0002522307,"about_ca_system_score_gemma":0.00028411963,"threshold_uncertainty_score":0.58168125},"labels":[],"label_agreement":null},{"id":"W2466935751","doi":"10.1118/1.4956636","title":"SU‐F‐T‐451: Doses to Organs‐At‐Risk in the Presence and Absence of a 1.5 T Magnetic Field for NSCLC Patients Undergoing SABR","year":2016,"lang":"en","type":"article","venue":"Medical Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; Sunnybrook Health Science Centre","funders":"","keywords":"SABR volatility model; Nuclear medicine; Radiation treatment planning; Field size; Medicine; Dosimetry; Radiation therapy; Physics; Mathematics; Radiology","score_opus":0.008222382354379052,"score_gpt":0.273823442871033,"score_spread":0.26560106051665394,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2466935751","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95560765,0.00012912031,0.031054646,0.01229352,0.00012644322,0.00043702588,0.000006326019,0.000014392555,0.00033087752],"genre_scores_gemma":[0.9966639,0.00016199937,0.0004985448,0.0023346867,0.00016771743,0.000023947394,0.0000026906503,0.000013340856,0.00013313297],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99874705,0.000058242764,0.00023763868,0.00021725339,0.0005085242,0.00023129731],"domain_scores_gemma":[0.99711394,0.0023717354,0.00006643432,0.00021796208,0.00005155012,0.0001783998],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044576413,0.00010056266,0.00022141369,0.000031687716,0.000057025056,0.000008840185,0.00017919656,0.000060103168,0.000057725763],"category_scores_gemma":[0.0070499578,0.000054677726,0.000043108354,0.00015070754,0.0002034888,0.000038417234,0.00009243913,0.0002065193,0.0000052782125],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001962005,0.00026475225,0.45255697,0.000231773,0.000018655739,0.00001392629,0.0016381171,0.0000029494558,0.00093601306,0.0005493935,0.005986665,0.5376046],"study_design_scores_gemma":[0.032001846,0.011085543,0.8646924,0.009599306,0.00039669793,0.00007466629,0.00078555825,0.009301888,0.0125296,0.036926292,0.021393115,0.0012130878],"about_ca_topic_score_codex":0.00007265976,"about_ca_topic_score_gemma":0.000028407654,"teacher_disagreement_score":0.5363915,"about_ca_system_score_codex":0.000024644281,"about_ca_system_score_gemma":0.0000812997,"threshold_uncertainty_score":0.8439967},"labels":[],"label_agreement":null},{"id":"W2467451464","doi":"10.18632/oncotarget.10523","title":"Association of multiparametric MRI quantitative imaging features with prostate cancer gene expression in MRI-targeted prostate biopsies","year":2016,"lang":"en","type":"article","venue":"Oncotarget","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":106,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Genome British Columbia","funders":"National Cancer Institute; National Institutes of Health","keywords":"Miami; Prostate cancer; Radiogenomics; Medicine; Cancer; Oncology; Internal medicine; Pathology; Radiology","score_opus":0.006760025945077997,"score_gpt":0.2898503214996989,"score_spread":0.2830902955546209,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2467451464","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98315185,0.0027298287,0.0015223362,0.011314507,0.0002510631,0.0006422158,0.000055762775,0.000065560336,0.0002668439],"genre_scores_gemma":[0.9479956,0.0015416878,0.04694658,0.00033939554,0.000101583966,0.00008868551,0.00004525327,0.00005405494,0.0028871738],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9982471,0.00012324068,0.0003701616,0.0003684714,0.00048916595,0.00040187396],"domain_scores_gemma":[0.9987358,0.00030876687,0.00039346545,0.00019263403,0.00024313948,0.00012618421],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00058415864,0.00020315836,0.0004467981,0.00036850484,0.00006286686,0.000019845034,0.0000916993,0.00007191657,0.000072440045],"category_scores_gemma":[0.0009118815,0.00011897881,0.000061188526,0.0005423901,0.00012209977,0.00019724661,0.000040456565,0.00032147398,0.000007747383],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00067536626,0.00011754022,0.7999913,0.00008382844,0.00006345811,0.00004373003,0.0013877536,0.00031933023,0.1892288,0.000008531373,0.0052209594,0.0028593706],"study_design_scores_gemma":[0.0074936743,0.00035855957,0.87367195,0.0018289177,0.000105606334,0.000018309856,0.00040628866,0.005462554,0.1033852,0.00013185378,0.0067805955,0.00035647312],"about_ca_topic_score_codex":0.0004305189,"about_ca_topic_score_gemma":0.00003695338,"teacher_disagreement_score":0.0858436,"about_ca_system_score_codex":0.0003091452,"about_ca_system_score_gemma":0.00016322988,"threshold_uncertainty_score":0.48518148},"labels":[],"label_agreement":null},{"id":"W2471451497","doi":"10.1118/1.4955815","title":"SU‐F‐R‐44: Modeling Lung SBRT Tumor Response Using Bayesian Network Averaging","year":2016,"lang":"en","type":"article","venue":"Medical Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Bayesian network; Markov chain Monte Carlo; Bayesian probability; Probabilistic logic; Lung cancer; Computer science; Graphical model; Medicine; Artificial intelligence; Oncology","score_opus":0.015251857748532561,"score_gpt":0.3000280570164196,"score_spread":0.28477619926788705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2471451497","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3444049,0.00017924192,0.64813447,0.0060459143,0.000486045,0.00015749001,0.0000014822376,0.00014860148,0.00044182158],"genre_scores_gemma":[0.98714435,0.000037577887,0.004398127,0.004771091,0.0032727455,0.000008277496,0.000006825493,0.00008947059,0.0002715146],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968303,0.00020964794,0.0005085565,0.00049494026,0.001162104,0.00079446123],"domain_scores_gemma":[0.9979976,0.0005105187,0.000115394345,0.00046237872,0.00008674943,0.00082738476],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018368434,0.00027754344,0.0005430881,0.00006952187,0.00024461802,0.000042683514,0.0002549861,0.00012962896,0.00037729234],"category_scores_gemma":[0.0018685774,0.00019243217,0.00019778161,0.0003200968,0.0003020093,0.00014750307,0.00015750562,0.00079244317,0.00004194047],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0066503193,0.0015231703,0.17806952,0.00114913,0.0013033402,0.0086046085,0.0024160808,0.045116507,0.04599728,0.007130089,0.03387247,0.6681675],"study_design_scores_gemma":[0.0022213317,0.000071772214,0.00032525856,0.001711443,0.00012470622,0.00023528721,0.000018184952,0.98898774,0.0003051207,0.0032083096,0.0024809504,0.0003098908],"about_ca_topic_score_codex":0.000037973674,"about_ca_topic_score_gemma":6.657717e-7,"teacher_disagreement_score":0.94387126,"about_ca_system_score_codex":0.0002946251,"about_ca_system_score_gemma":0.0005052617,"threshold_uncertainty_score":0.7847156},"labels":[],"label_agreement":null},{"id":"W2471466051","doi":"10.1118/1.4955638","title":"SU‐D‐BRA‐05: Time Series Analysis of EPID Images to Identify Patients in Need of Treatment Adaptation","year":2016,"lang":"en","type":"article","venue":"Medical Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hôtel-Dieu de Québec","funders":"","keywords":"Medicine; Nuclear medicine; Radiology","score_opus":0.011079504208280161,"score_gpt":0.3068423771574635,"score_spread":0.29576287294918335,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2471466051","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9703453,0.000021763735,0.026029332,0.002978786,0.00008173094,0.0001812589,0.00002358881,0.000016809188,0.0003213949],"genre_scores_gemma":[0.9987236,0.000058252386,0.00051944517,0.0002116688,0.0000755555,0.000009680233,0.00006416804,0.000013655453,0.00032392755],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99859834,0.00006466305,0.0004279331,0.00019235015,0.0005412317,0.00017547817],"domain_scores_gemma":[0.9991244,0.00021186304,0.00013549424,0.0002105967,0.000110521374,0.00020711221],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027653034,0.000114080234,0.00056453503,0.00020202184,0.000015121739,0.0000040763985,0.00009325289,0.000057552785,0.00022907696],"category_scores_gemma":[0.001020929,0.000073428826,0.00015291733,0.0006353232,0.00019333477,0.00007782239,0.000037684837,0.00008998474,0.000016988544],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026684967,0.0010241823,0.3697121,0.00008960862,0.0008319492,0.000023634504,0.0014088207,0.00022154208,0.008826654,0.00011818787,0.0011466205,0.61632985],"study_design_scores_gemma":[0.0069156885,0.0020946674,0.93226683,0.00091416546,0.0017681506,0.0000025447273,0.00015087679,0.0071348595,0.04662375,0.0010125324,0.00080675056,0.00030916478],"about_ca_topic_score_codex":0.000318897,"about_ca_topic_score_gemma":0.000011535435,"teacher_disagreement_score":0.6160207,"about_ca_system_score_codex":0.00010039966,"about_ca_system_score_gemma":0.00010427236,"threshold_uncertainty_score":0.29943407},"labels":[],"label_agreement":null},{"id":"W2471515287","doi":"10.1118/1.4956062","title":"SU‐F‐J‐154: Harmonic Analysis for Arbitrary 3D MR Image Distortion Fields","year":2016,"lang":"en","type":"article","venue":"Medical Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto","funders":"","keywords":"Cuboid; Harmonic; Imaging phantom; Distortion (music); Mathematical analysis; Algorithm; Mathematics; Scanner; Physics; Geometry; Optics; Acoustics","score_opus":0.01267431281937155,"score_gpt":0.29580978061190333,"score_spread":0.2831354677925318,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2471515287","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10908893,0.00011613939,0.87015957,0.01857973,0.00029930277,0.00020902429,0.00001176047,0.00010719348,0.0014283779],"genre_scores_gemma":[0.9911574,0.00010336871,0.0028163025,0.0033135512,0.0013288625,0.00003976531,0.00008820842,0.00003234664,0.0011201727],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99826884,0.000038191214,0.00033361057,0.00035066775,0.00064749847,0.00036116864],"domain_scores_gemma":[0.9986879,0.00034596506,0.00009708571,0.0003405269,0.000083646606,0.00044487126],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004685665,0.00016253554,0.0004515746,0.00008034521,0.00009359597,0.000020414316,0.00016523396,0.00014629497,0.00057889643],"category_scores_gemma":[0.0011195658,0.000104660685,0.00037037113,0.0003206575,0.00030551178,0.00010176925,0.000047174308,0.00038719006,0.000046981117],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029329743,0.0007944996,0.055617727,0.0003284967,0.001753241,0.00018659518,0.00029542117,0.000007816737,0.005341294,0.0026146069,0.0338248,0.8989422],"study_design_scores_gemma":[0.044601396,0.0036023182,0.18052605,0.0031672122,0.019633565,0.0002477142,0.00015565864,0.24141638,0.059413284,0.10477968,0.3381891,0.0042676562],"about_ca_topic_score_codex":0.000027139942,"about_ca_topic_score_gemma":0.0000028117072,"teacher_disagreement_score":0.89467454,"about_ca_system_score_codex":0.00007990377,"about_ca_system_score_gemma":0.00015711074,"threshold_uncertainty_score":0.633851},"labels":[],"label_agreement":null},{"id":"W2474046305","doi":"10.1118/1.4955811","title":"SU‐F‐R‐40: Robustness Test of Computed Tomography Textures of Lung Tissues to Varying Scanning Protocols Using a Realistic Phantom Environment","year":2016,"lang":"en","type":"article","venue":"Medical Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Imaging phantom; Robustness (evolution); Artificial intelligence; Hounsfield scale; Scanner; Entropy (arrow of time); Mathematics; Nuclear medicine; Pattern recognition (psychology); Computed tomography; Medicine; Computer science; Radiology; Physics","score_opus":0.020697229110424986,"score_gpt":0.3265016492757177,"score_spread":0.3058044201652927,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2474046305","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20934142,0.0001510676,0.78455675,0.0016455055,0.00011831906,0.0038047694,0.000022179694,0.000078166006,0.0002818453],"genre_scores_gemma":[0.9901658,0.000011132003,0.008773878,0.00028846352,0.00047516666,0.00019131915,0.00001253888,0.000045750905,0.000035938177],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975297,0.000070941256,0.00058626843,0.00034927062,0.0010960712,0.0003677736],"domain_scores_gemma":[0.998382,0.0004534213,0.0002517203,0.00036855027,0.00009152865,0.00045279454],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00053137506,0.00021737033,0.0006736238,0.00013524774,0.00006842041,0.000012033363,0.0002552015,0.000108162676,0.000110592206],"category_scores_gemma":[0.0010061,0.00015006961,0.00014172518,0.0003570299,0.00051054865,0.000063645835,0.00015486416,0.00029194157,0.0000022316958],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006456475,0.0029547042,0.25290063,0.0038553688,0.00063307036,0.00032573772,0.0017517572,0.00870213,0.28950328,0.0008176946,0.0031035622,0.43480644],"study_design_scores_gemma":[0.016251894,0.0025639178,0.04713653,0.04735992,0.0011842697,0.00028085627,0.00011337516,0.6718499,0.20436871,0.0020679764,0.0050596897,0.0017629416],"about_ca_topic_score_codex":0.000096843796,"about_ca_topic_score_gemma":3.9951934e-7,"teacher_disagreement_score":0.78082436,"about_ca_system_score_codex":0.00007137574,"about_ca_system_score_gemma":0.00014295205,"threshold_uncertainty_score":0.61196613},"labels":[],"label_agreement":null},{"id":"W2474575224","doi":"10.1016/j.ijrobp.2016.03.039","title":"In Reply to Sun et al","year":2016,"lang":"en","type":"letter","venue":"International Journal of Radiation Oncology*Biology*Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"London Health Sciences Centre; Western University","funders":"","keywords":"Contouring; Medicine; Radiomics; Scopus; Citation; Lung cancer; Nuclear medicine; Medical physics; MEDLINE; Pathology; Library science; Radiology; Computer science","score_opus":0.016788951490072857,"score_gpt":0.36122866152154026,"score_spread":0.3444397100314674,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2474575224","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005601437,0.00020945362,0.013436687,0.9723983,0.0064470554,0.00024066785,0.000051008214,0.000030110108,0.001585308],"genre_scores_gemma":[0.0077221156,0.0007287825,0.004218471,0.96876806,0.017587475,0.000013616823,0.00017230859,0.00007494718,0.00071421306],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9970649,0.00041711525,0.0011505533,0.0004017192,0.0005644225,0.00040127742],"domain_scores_gemma":[0.99678254,0.000862552,0.0012422856,0.00025378304,0.00067571877,0.0001830896],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0014311996,0.0003105402,0.00089111045,0.00056172966,0.000034248726,0.000037695405,0.0006284646,0.0005267138,0.0001949107],"category_scores_gemma":[0.0016131016,0.00024775424,0.000343498,0.00017479862,0.0002099224,0.000226888,0.00011450918,0.0033788257,0.0001192374],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019692536,0.000098912686,0.018320829,0.0000104671735,0.00036253745,0.0011406984,0.00018684033,0.000066563705,0.00080064643,0.0010765151,0.8993577,0.07838136],"study_design_scores_gemma":[0.003777458,0.0007040027,0.0013383357,0.00030963172,0.00007165482,0.0008135729,0.0000074610048,0.00034737942,0.00010918226,0.005437947,0.98685974,0.00022364658],"about_ca_topic_score_codex":0.00004105488,"about_ca_topic_score_gemma":0.0000013115355,"teacher_disagreement_score":0.087502025,"about_ca_system_score_codex":0.0012189877,"about_ca_system_score_gemma":0.0010224587,"threshold_uncertainty_score":0.9999975},"labels":[],"label_agreement":null},{"id":"W2478629645","doi":"10.1522/030583086","title":"iologie du vetement 101","year":2011,"lang":"fr","type":"book","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Art","score_opus":0.03712281468014411,"score_gpt":0.30018235643619756,"score_spread":0.26305954175605345,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2478629645","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005826827,0.005161409,0.0090588415,0.0071377633,0.0068844147,0.0005517855,0.000008000748,0.0001957943,0.9704193],"genre_scores_gemma":[0.013211298,0.006053767,0.009198754,0.0072390446,0.0074683847,0.000033716988,0.00021506366,0.00013537666,0.9564446],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9970367,0.0001696749,0.0007384374,0.0006964594,0.00045911287,0.00089961727],"domain_scores_gemma":[0.9978862,0.00041674168,0.00025779518,0.0006798498,0.0001270736,0.0006323809],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0012243177,0.00056689756,0.000966516,0.00018170282,0.00016347597,0.000032548207,0.00044158794,0.00059201743,0.029519336],"category_scores_gemma":[0.0012126274,0.00044341205,0.0003552385,0.00007481036,0.0007614097,0.000053423715,0.00028922607,0.0018212853,0.005807612],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000085395695,0.00036158084,0.0099264,0.0009833073,0.00083264965,0.0014239603,0.0003008483,0.000023767292,0.0002797751,0.1860518,0.42272457,0.37700593],"study_design_scores_gemma":[0.001263829,0.0006190518,0.0026135095,0.0013050432,0.00057655276,0.00021256004,0.00006025436,0.0045898766,0.00005007333,0.0027125052,0.9855196,0.00047715768],"about_ca_topic_score_codex":0.00036790717,"about_ca_topic_score_gemma":0.000004552187,"teacher_disagreement_score":0.562795,"about_ca_system_score_codex":0.00057094713,"about_ca_system_score_gemma":0.000798666,"threshold_uncertainty_score":0.99980175},"labels":[],"label_agreement":null},{"id":"W2480199118","doi":"10.1126/science.aaf5101","title":"Countering imprecision in precision medicine","year":2016,"lang":"en","type":"article","venue":"Science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":58,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research; Genome Alberta; Genome Canada","keywords":"Psychological intervention; Precision medicine; Computer science; Data science; Medicine; Pathology; Nursing","score_opus":0.014013783394921799,"score_gpt":0.3420158900937316,"score_spread":0.3280021066988098,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2480199118","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9726605,0.00016864947,0.010061026,0.010020091,0.00064113265,0.00011711496,2.5776265e-7,0.00003673099,0.0062945364],"genre_scores_gemma":[0.9971035,0.000115947376,0.001557355,0.00047332584,0.00015094574,0.0000025931638,2.0156864e-7,0.000006013761,0.00059009873],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9987205,0.000013833319,0.00018852638,0.000279393,0.00055082655,0.00024689894],"domain_scores_gemma":[0.99937934,0.00013597452,0.00003639949,0.00022888984,0.000060468257,0.00015894095],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017057772,0.0000648479,0.00014203854,0.00025684448,0.000061292754,0.000011278689,0.00019112478,0.000022808503,0.0001757664],"category_scores_gemma":[0.0024679792,0.000032607597,0.00001638664,0.00048742662,0.0005727721,0.00017849405,0.0000812471,0.000117933414,0.000039429862],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028546508,0.000014498407,0.03003073,0.000005956511,6.479343e-7,0.00001629803,0.0001573482,0.0000021284884,0.5354747,0.00016126005,0.00027247763,0.43383536],"study_design_scores_gemma":[0.0048108594,0.0006333859,0.8939879,0.0038537465,0.000013225544,0.00029879718,0.0001344385,0.015809862,0.01234409,0.0035755942,0.06428728,0.00025080942],"about_ca_topic_score_codex":0.000031041975,"about_ca_topic_score_gemma":0.0000022536196,"teacher_disagreement_score":0.86395717,"about_ca_system_score_codex":0.000119073746,"about_ca_system_score_gemma":0.00009293747,"threshold_uncertainty_score":0.295458},"labels":[],"label_agreement":null},{"id":"W2482204222","doi":"10.1007/978-3-319-18305-3","title":"Machine Learning in Radiation Oncology","year":2015,"lang":"en","type":"book","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":277,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Radiation oncology; Variety (cybernetics); Medical physics; Medical radiation; Computer science; Medicine; Radiation therapy; Internal medicine; Artificial intelligence","score_opus":0.016061639563721513,"score_gpt":0.3234553194129652,"score_spread":0.30739367984924365,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2482204222","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000931079,0.0028849812,0.00027717414,0.00427067,0.0003447527,0.00027975987,0.0000016917529,0.00013913515,0.99170876],"genre_scores_gemma":[0.0010488488,0.00091568526,0.0013772391,0.0019169728,0.00069781847,0.000009616102,0.0006741121,0.00007142536,0.9932883],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99859154,0.000088301145,0.00039021735,0.0003190705,0.00035079438,0.00026004968],"domain_scores_gemma":[0.9992001,0.00013841505,0.0001645751,0.0001828478,0.0000697247,0.00024430684],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.00091888785,0.00021892384,0.00066680636,0.0003818878,0.000027855043,0.000013266107,0.000093149196,0.00043339,0.00072950637],"category_scores_gemma":[0.0007443066,0.0001865805,0.000092380134,0.00008542866,0.00007106974,0.000033816817,0.00005669337,0.0023297465,0.00022677451],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014897797,0.00012544233,0.006042189,0.0002085832,0.00009825953,0.0008837256,0.00040955297,0.0003344195,0.00003443716,0.003877931,0.34093168,0.64690477],"study_design_scores_gemma":[0.0020369552,0.00032734408,0.00025930128,0.00016382571,0.000071372,0.00015709807,0.0000116445235,0.03125056,0.0000016118627,0.0014427662,0.9641091,0.00016841372],"about_ca_topic_score_codex":0.00013436045,"about_ca_topic_score_gemma":0.000027855542,"teacher_disagreement_score":0.6467364,"about_ca_system_score_codex":0.0010563371,"about_ca_system_score_gemma":0.0015464983,"threshold_uncertainty_score":0.9999719},"labels":[],"label_agreement":null},{"id":"W2482412812","doi":"","title":"SlicerRT – 3D Slicer based open-source toolkit for radiation therapy research","year":2013,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Open source; Computer science; Data source; Computer graphics (images); Operating system; Information retrieval; Software","score_opus":0.06555695499946726,"score_gpt":0.4078024074775042,"score_spread":0.34224545247803695,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2482412812","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4474762,0.00079363247,0.1411602,0.21661463,0.0006211029,0.009746782,0.0000048628967,0.00044302823,0.18313955],"genre_scores_gemma":[0.86948174,0.00016515379,0.047643375,0.026556436,0.001029592,0.000954634,0.00011674268,0.000116745396,0.053935595],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984981,0.00011568592,0.0002328068,0.0003229961,0.00041263353,0.00041779585],"domain_scores_gemma":[0.9985031,0.00054482394,0.00004694139,0.00036765396,0.000295332,0.00024213457],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001647457,0.000118654476,0.00023543857,0.00016826608,0.00022152196,0.00023047991,0.0002933512,0.000089951114,0.003471843],"category_scores_gemma":[0.0007279169,0.00008630049,0.00007136271,0.00024943255,0.00008593707,0.00019302231,0.000064498265,0.00042398507,0.00022984073],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017923256,0.00021549193,0.0059269974,0.000048011647,0.000052937805,0.0000022273357,0.00022750966,0.00006954135,0.0086196,0.0008071237,0.30288538,0.68096596],"study_design_scores_gemma":[0.0041283807,0.0003726654,0.011213565,0.000035894744,0.000010733019,0.0000061824203,0.000088492656,0.2037413,0.0009866785,0.00026773047,0.77902716,0.00012120452],"about_ca_topic_score_codex":0.0016190783,"about_ca_topic_score_gemma":0.0000048547986,"teacher_disagreement_score":0.6808447,"about_ca_system_score_codex":0.00007999059,"about_ca_system_score_gemma":0.00016503995,"threshold_uncertainty_score":0.99743915},"labels":[],"label_agreement":null},{"id":"W2486348856","doi":"10.4018/978-1-4666-6611-5.ch008","title":"The Role of Big Data in Radiation Oncology","year":2015,"lang":"en","type":"book-chapter","venue":"Advances in bioinformatics and biomedical engineering book series","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Big data; Radiation therapy; Radiation oncology; Medical physics; Data science; Demographics; Confidentiality; Data sharing; Medicine; Computer science; Internal medicine; Alternative medicine; Data mining; Pathology","score_opus":0.01208871712092511,"score_gpt":0.2761703648938898,"score_spread":0.26408164777296467,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2486348856","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004431416,0.52146345,0.0040401146,0.0068347338,0.0034020268,0.0016425055,0.00024375002,0.00017527505,0.461755],"genre_scores_gemma":[0.013059196,0.9074088,0.042051204,0.0009114539,0.002032609,0.000055029926,0.0022687411,0.00022696,0.031986043],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986023,0.000006420678,0.00068623095,0.00015038543,0.00034035707,0.00021434232],"domain_scores_gemma":[0.9990752,0.00020647922,0.00019743256,0.0003412022,0.00003598741,0.00014370665],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00068588107,0.00019141712,0.00047633497,0.00023842564,0.000027641667,0.00001586429,0.00022822173,0.00022813705,0.000007336021],"category_scores_gemma":[0.0004960673,0.00013126445,0.000028531367,0.00006963022,0.00042549803,0.00030650684,0.00020439568,0.0006036084,0.0000018697892],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007253658,0.000020955387,0.00011232377,0.000524998,0.000037274556,0.000025880423,0.00033720842,0.00009987549,0.000022443322,0.028365288,0.00031189463,0.97006935],"study_design_scores_gemma":[0.00055717386,0.00020517298,0.000038696508,0.00054069544,0.000023578685,0.00006537874,0.000095736104,0.059387553,0.0000054250195,0.0018290397,0.9371267,0.00012485927],"about_ca_topic_score_codex":0.000010067117,"about_ca_topic_score_gemma":0.000013298999,"teacher_disagreement_score":0.9699445,"about_ca_system_score_codex":0.00008844433,"about_ca_system_score_gemma":0.00020360042,"threshold_uncertainty_score":0.5352809},"labels":[],"label_agreement":null},{"id":"W2489822749","doi":"10.1007/978-1-4939-3995-4_23","title":"Histological Fractal-Based Classification of Brain Tumors","year":2016,"lang":"en","type":"book-chapter","venue":"Springer series in computational neuroscience","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Michael's Hospital; University of Toronto","funders":"","keywords":"Grading (engineering); Fractal; Fractal analysis; Pathology; Fractal dimension; Pattern recognition (psychology); Meningioma; Abnormality; Computer science; Artificial intelligence; Biology; Medicine; Mathematics","score_opus":0.02761778983011747,"score_gpt":0.2939945334852568,"score_spread":0.2663767436551393,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2489822749","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09647364,0.00068992237,0.18305199,0.13799153,0.0044052536,0.002348644,0.00012772388,0.0005388754,0.5743724],"genre_scores_gemma":[0.95447624,0.000021506949,0.007927746,0.0030464304,0.00013675728,0.000010481316,0.000026029442,0.00004785743,0.034306943],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9982023,0.000027306301,0.00048158035,0.0004887923,0.00061035674,0.00018963273],"domain_scores_gemma":[0.99886703,0.00035268193,0.00033138777,0.00022740732,0.00011309495,0.000108373795],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026696923,0.00019988265,0.0003849867,0.00029048522,0.000059600832,0.000015739335,0.00022615118,0.00012149463,0.00009497846],"category_scores_gemma":[0.0008486474,0.00016401398,0.00010117884,0.00008555286,0.0009649554,0.00008917826,0.00007160437,0.00048134523,0.00001085168],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042090676,0.0002433531,0.015274642,0.0004851436,0.000016022028,0.0005902338,0.00011095057,0.009785298,0.025954818,0.91411763,0.0010469044,0.031954065],"study_design_scores_gemma":[0.0032921825,0.0015478728,0.48482835,0.0037500737,0.00008186055,0.0005817637,0.000015603195,0.19192992,0.0004716983,0.10864244,0.2035324,0.0013258568],"about_ca_topic_score_codex":0.0000018203237,"about_ca_topic_score_gemma":5.511089e-7,"teacher_disagreement_score":0.8580026,"about_ca_system_score_codex":0.00010912839,"about_ca_system_score_gemma":0.00037004685,"threshold_uncertainty_score":0.6688296},"labels":[],"label_agreement":null},{"id":"W2494050007","doi":"10.1007/b93810","title":"Medical Image Computing and Computer-Assisted Intervention - MICCAI 2003","year":2003,"lang":"en","type":"book","venue":"Lecture notes in computer science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":284,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Intervention (counseling); Queen (butterfly); Medical imaging; Multimedia; Computer graphics (images); Artificial intelligence; Medicine; Nursing","score_opus":0.008464244655051951,"score_gpt":0.294619389023894,"score_spread":0.28615514436884204,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2494050007","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030730607,0.0010605643,0.98971844,0.0015421615,0.0022769745,0.00042205557,0.0000023007096,0.00010870766,0.0017957261],"genre_scores_gemma":[0.049650375,0.00023155194,0.9297026,0.014868396,0.0032175453,0.000008738166,0.00013658773,0.0001606637,0.00202359],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99603754,0.00014548548,0.0007231853,0.0011714564,0.0012553248,0.0006669893],"domain_scores_gemma":[0.99797714,0.00039731266,0.00028905077,0.00051813386,0.00030671683,0.0005116628],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0021528236,0.00046802303,0.0008507902,0.0006385671,0.00022161898,0.00026225115,0.00058192183,0.0004305204,0.00009151366],"category_scores_gemma":[0.0011160478,0.0004074828,0.0001361876,0.0008143832,0.0014640238,0.00013809917,0.00053484977,0.002203008,0.000015558106],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016120046,0.00013941892,0.0009059968,0.0004066404,0.000037790076,0.000624834,0.0002862371,0.00030225277,0.000093403854,0.00012176406,0.0025851745,0.9944804],"study_design_scores_gemma":[0.0019459139,0.00038717687,0.0026150786,0.004113395,0.00006417119,0.0023323507,5.7396215e-7,0.980617,0.00009804056,0.001878379,0.005424517,0.00052341225],"about_ca_topic_score_codex":0.000032587523,"about_ca_topic_score_gemma":0.000010531687,"teacher_disagreement_score":0.993957,"about_ca_system_score_codex":0.00038939674,"about_ca_system_score_gemma":0.001265924,"threshold_uncertainty_score":0.9998377},"labels":[],"label_agreement":null},{"id":"W2494171310","doi":"10.1007/978-3-319-41501-7_76","title":"Estimating Ejection Fraction and Left Ventricle Volume Using Deep Convolutional Networks","year":2016,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Ejection fraction; Ventricle; Convolutional neural network; Computer science; Artificial intelligence; DICOM; Diastole; End-systolic volume; Cardiology; Stroke volume; Internal medicine; Computer vision; Medicine; Heart failure; Blood pressure","score_opus":0.010666118434644097,"score_gpt":0.26937992193024063,"score_spread":0.25871380349559653,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2494171310","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025084363,0.0005590636,0.99429256,0.0005430856,0.0013762943,0.00017192903,7.0654175e-7,0.00004978448,0.0004981497],"genre_scores_gemma":[0.644547,0.000048784903,0.3509379,0.0012025664,0.002931192,0.000001247051,0.000008691583,0.00004669929,0.00027594448],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984482,0.000017095921,0.00026646006,0.0005449986,0.00041551978,0.0003077361],"domain_scores_gemma":[0.9991681,0.00020029536,0.00018016687,0.00020169468,0.00011146194,0.0001382663],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005247852,0.00020734286,0.0003026939,0.00030827016,0.00024222278,0.00008799725,0.00012660814,0.00019125637,0.00006004427],"category_scores_gemma":[0.00023661292,0.00017122221,0.000052795214,0.00010569473,0.00049998617,0.00016136252,0.00013349003,0.0007638937,0.000005400613],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021921422,0.000015799402,0.011489925,0.00005858023,0.000020215852,0.00006518138,0.000075077296,0.20020263,0.00048084,0.00035132814,0.000012018428,0.7872065],"study_design_scores_gemma":[0.00033651138,0.00006824636,0.0019120296,0.0006977522,0.000029521643,0.00047250235,1.13320795e-7,0.98878276,0.000016266433,0.0070741945,0.00043302504,0.00017705101],"about_ca_topic_score_codex":0.000017445442,"about_ca_topic_score_gemma":0.000002543082,"teacher_disagreement_score":0.7885802,"about_ca_system_score_codex":0.00035508277,"about_ca_system_score_gemma":0.00015434189,"threshold_uncertainty_score":0.69822395},"labels":[],"label_agreement":null},{"id":"W2502392682","doi":"10.1142/9789814460941_0002","title":"DISTRIBUTION MATCHING APPROACHES TO MEDICAL IMAGE SEGMENTATION","year":2013,"lang":"en","type":"book-chapter","venue":"Series in computer vision","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; CARE Canada","funders":"","keywords":"Matching (statistics); Artificial intelligence; Computer science; Segmentation; Pattern recognition (psychology); Distribution (mathematics); Image segmentation; Computer vision; Mathematics; Statistics","score_opus":0.024156559010349,"score_gpt":0.2830106850650491,"score_spread":0.2588541260547001,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2502392682","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010794534,0.00033081917,0.8717259,0.032024864,0.0022176714,0.001962981,0.00003584453,0.00033333054,0.08057404],"genre_scores_gemma":[0.061221987,0.0014492268,0.68645406,0.013918543,0.009347638,0.00018922296,0.009983451,0.0006959021,0.21673998],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979199,0.000037929283,0.0005184396,0.0005115787,0.0007415492,0.00027057467],"domain_scores_gemma":[0.9990253,0.000078337,0.00013036086,0.00032469188,0.00005139945,0.00038994712],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00047214964,0.000315919,0.0005169089,0.00017484748,0.00007789654,0.00009776311,0.00018606479,0.00032931333,0.00088770146],"category_scores_gemma":[0.00008326259,0.00027481644,0.000112957016,0.00005605443,0.00012773852,0.000193302,0.00030634005,0.0009738429,0.00025022298],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019119187,0.00010482601,0.00007576465,0.00057030795,0.000080116966,0.00047938255,0.0006931707,0.0002551458,0.00022881513,0.029057259,0.02810286,0.94016117],"study_design_scores_gemma":[0.006625633,0.0040337658,0.006426728,0.020118326,0.00034539972,0.0024536536,0.00016161968,0.24156365,0.00039982575,0.06777378,0.6471172,0.002980411],"about_ca_topic_score_codex":0.000034269877,"about_ca_topic_score_gemma":0.0000049531413,"teacher_disagreement_score":0.93718076,"about_ca_system_score_codex":0.00022142398,"about_ca_system_score_gemma":0.00010877314,"threshold_uncertainty_score":0.9999704},"labels":[],"label_agreement":null},{"id":"W2508769499","doi":"10.1093/jrr/rrw059","title":"A surveillance study of the current status of reirradiation and patterns of practice","year":2016,"lang":"en","type":"article","venue":"Journal of Radiation Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Current (fluid); Physics","score_opus":0.04041363459056239,"score_gpt":0.4368669601530189,"score_spread":0.3964533255624565,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2508769499","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9934903,0.0011590036,0.0004047872,0.0045128018,0.00013665344,0.00021831179,0.0000045534816,9.96842e-7,0.00007262907],"genre_scores_gemma":[0.99647105,0.0032885494,0.000091681286,0.000016126582,0.000096949974,0.000001198421,3.4224064e-7,0.0000059988074,0.00002809237],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9976963,0.0006159518,0.0005052411,0.000071326576,0.00097450067,0.00013671267],"domain_scores_gemma":[0.99698985,0.0011811383,0.00071526953,0.00015587584,0.0008575433,0.00010035516],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0034792926,0.00004334749,0.00022316651,0.00023303974,0.00003105356,0.0000057839716,0.00009489963,0.000021100608,0.000015267342],"category_scores_gemma":[0.008870163,0.000022612505,0.000043442138,0.00023488946,0.00008200283,0.00010796569,0.00003503194,0.0003808522,2.0597827e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021588837,0.0003258711,0.7194011,0.00008939405,0.00005874195,0.0000026379862,0.0011340008,0.00002448707,0.0037436874,0.00005292882,0.00040524802,0.274546],"study_design_scores_gemma":[0.0025990186,0.00096689456,0.9888143,0.000269829,0.000029897452,0.000018708526,0.0006632094,0.00038370883,0.0007155685,0.000044339205,0.0054710233,0.000023482939],"about_ca_topic_score_codex":0.0001560333,"about_ca_topic_score_gemma":0.000008580308,"teacher_disagreement_score":0.27452254,"about_ca_system_score_codex":0.0000720299,"about_ca_system_score_gemma":0.0002807822,"threshold_uncertainty_score":0.9994785},"labels":[],"label_agreement":null},{"id":"W2510055979","doi":"10.1118/1.4961817","title":"Poster ‐ 43: Analysis of SBRT and SRS dose verification results using the Octavius 1000SRS detector","year":2016,"lang":"en","type":"article","venue":"Medical Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Nova Scotia Cancer Centre; Nova Scotia Health Authority; Dalhousie University","funders":"","keywords":"Nuclear medicine; Medicine; Detector; Dosimetry; Standard deviation; Radiation treatment planning; Significant difference; Mathematics; Radiation therapy; Physics; Statistics; Radiology; Optics; Internal medicine","score_opus":0.019373050324973537,"score_gpt":0.3104910948515477,"score_spread":0.29111804452657414,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2510055979","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.962799,0.00011878406,0.027833236,0.008372835,0.00013986266,0.00014500222,0.000014109168,0.000028863149,0.00054826756],"genre_scores_gemma":[0.9984018,0.00008734367,0.00024430684,0.0008579158,0.00026923188,0.0000028278573,0.000014164897,0.000014931024,0.000107435226],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99851865,0.00007711943,0.00035071486,0.00024452622,0.00061793794,0.00019103511],"domain_scores_gemma":[0.9988021,0.00038567992,0.00014397135,0.00036699392,0.000083194805,0.00021806198],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006755123,0.000111309324,0.00033811058,0.00007781031,0.0000689682,0.00001107669,0.00012872981,0.00008226398,0.0000723841],"category_scores_gemma":[0.0013331859,0.00005723061,0.00012271435,0.000453006,0.000533218,0.000052042156,0.00005806876,0.00024596934,0.0000055354426],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006943052,0.00033595954,0.067823514,0.0001302076,0.0017442972,0.000057897087,0.0015100101,0.000042063653,0.070472874,0.0005238542,0.0011519792,0.85551304],"study_design_scores_gemma":[0.016223142,0.00082913856,0.7251743,0.0017769483,0.010492299,0.00014303054,0.0002600426,0.19270588,0.035578933,0.0020635477,0.013783552,0.00096915686],"about_ca_topic_score_codex":0.00007869919,"about_ca_topic_score_gemma":0.0000037024683,"teacher_disagreement_score":0.85454386,"about_ca_system_score_codex":0.00004406872,"about_ca_system_score_gemma":0.000094326046,"threshold_uncertainty_score":0.23337965},"labels":[],"label_agreement":null},{"id":"W2511601841","doi":"10.1200/jco.2009.27.15_suppl.7575","title":"PET-CT compared to invasive mediastinal staging in non-small cell lung cancer (NSCLC)","year":2009,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; St. Joseph’s Healthcare Hamilton","funders":"","keywords":"Medicine; Mediastinoscopy; Radiology; Lung cancer; Stage (stratigraphy); Nuclear medicine; Thoracotomy; Mediastinum; Lung cancer staging; Surgery; Internal medicine","score_opus":0.058405502823529236,"score_gpt":0.4548734533558647,"score_spread":0.39646795053233547,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2511601841","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.954474,0.00039428088,0.0012542022,0.037711248,0.0013632795,0.00024339894,0.000001259359,0.000009594153,0.004548749],"genre_scores_gemma":[0.9661918,0.00051787903,0.013610629,0.017784294,0.0016757164,0.0000031480565,0.0000017845935,0.000017370085,0.00019735671],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9964441,0.00031414768,0.0021813072,0.00024688372,0.00040877066,0.00040480695],"domain_scores_gemma":[0.99552137,0.0021406866,0.0010596422,0.00016193501,0.00027726823,0.0008391179],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0037336797,0.00017104133,0.0015751537,0.0002940073,0.00003822955,0.000015316858,0.00028353627,0.00006940508,0.00014124802],"category_scores_gemma":[0.0057735033,0.00013119521,0.00030949988,0.0002517617,0.000098348886,0.000073564544,0.000053770167,0.0023580766,0.000010633926],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002566591,0.0019177372,0.72468174,0.00011589219,0.00015200624,0.019626968,0.0008300785,0.0024383946,0.0023990513,0.000027493013,0.024242189,0.22100185],"study_design_scores_gemma":[0.016290383,0.005773427,0.9415709,0.0014344926,0.0003878327,0.001490286,0.00043806699,0.014340958,0.00021455456,0.00014986802,0.0176433,0.00026596553],"about_ca_topic_score_codex":0.00012386584,"about_ca_topic_score_gemma":0.00008721492,"teacher_disagreement_score":0.22073588,"about_ca_system_score_codex":0.00027326265,"about_ca_system_score_gemma":0.002306208,"threshold_uncertainty_score":0.9999435},"labels":[],"label_agreement":null},{"id":"W2512508586","doi":"10.1016/s0167-8140(16)31668-1","title":"OC-0419: Association between pathology and texture features of multi parametric MRI of the prostate","year":2016,"lang":"en","type":"article","venue":"Radiotherapy and Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto","funders":"","keywords":"Medicine; Prostate; Association (psychology); Pathology; Texture (cosmology); Internal medicine; Artificial intelligence; Computer science; Psychology; Cancer","score_opus":0.00915550332130454,"score_gpt":0.30884759880525114,"score_spread":0.2996920954839466,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2512508586","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9745399,0.0037180549,0.0014013567,0.019736113,0.00013735064,0.00026795387,0.000011831632,0.000011142969,0.00017634055],"genre_scores_gemma":[0.9914326,0.003944466,0.002775563,0.0007853242,0.00012393041,0.000004909372,0.0000017091015,0.000011651465,0.0009198486],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9992013,0.00018301672,0.00020959131,0.00015177838,0.00010767545,0.00014663675],"domain_scores_gemma":[0.9989037,0.00062525674,0.00024457724,0.00011923022,0.000048650527,0.000058578466],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00051972683,0.000083246465,0.00039395934,0.000085447646,0.00004066969,0.0000028699574,0.000056965695,0.00018983052,0.000015425721],"category_scores_gemma":[0.0004942903,0.000041861505,0.000049086273,0.00012921834,0.00024864924,0.000022544353,0.000020491898,0.00021909043,1.8298083e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009140928,0.000056893357,0.6279923,0.000046966437,0.00012113566,0.000007644607,0.0006069093,0.0000012538926,0.022132779,0.00015247666,0.00075313606,0.34803715],"study_design_scores_gemma":[0.0041971984,0.0007378647,0.96406794,0.00007546862,0.00010424994,0.00012181168,0.000032627915,0.00018400398,0.0014536101,0.00022111631,0.028737614,0.00006647319],"about_ca_topic_score_codex":0.000025318617,"about_ca_topic_score_gemma":0.00000627364,"teacher_disagreement_score":0.34797066,"about_ca_system_score_codex":0.00010493683,"about_ca_system_score_gemma":0.00006346608,"threshold_uncertainty_score":0.17070626},"labels":[],"label_agreement":null},{"id":"W2512996524","doi":"10.1016/s0167-8140(16)32559-2","title":"EP-1309: Predictive value of FDG-PET in rectal cancer: correlation with tumour characteristics and response.","year":2016,"lang":"en","type":"article","venue":"Radiotherapy and Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; University of Toronto; Sunnybrook Health Science Centre","funders":"","keywords":"Predictive value; Medicine; Colorectal cancer; Correlation; Nuclear medicine; Oncology; Cancer; Internal medicine; Mathematics","score_opus":0.006592885866899868,"score_gpt":0.29590549874537525,"score_spread":0.2893126128784754,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2512996524","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98705834,0.0008240827,0.0051589115,0.0064608776,0.00012303852,0.00019592718,0.000010385763,0.000014934799,0.00015347698],"genre_scores_gemma":[0.99359006,0.0035525677,0.001943765,0.00050017843,0.00012672928,0.000014914869,0.0000026922662,0.000016219848,0.00025284974],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9992133,0.00017465858,0.00019881963,0.00018100323,0.000089263085,0.00014296379],"domain_scores_gemma":[0.9992324,0.00045675083,0.00011879906,0.00007149077,0.000033136897,0.00008739779],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044553273,0.00009329591,0.0003468553,0.0001084867,0.000029901306,0.000003614877,0.000029006766,0.00007279016,0.000037289617],"category_scores_gemma":[0.00017552235,0.000058179012,0.00001609177,0.00007733006,0.00026467245,0.00004507347,0.000008561994,0.0001863852,2.375545e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.014493897,0.00013798493,0.6674575,0.000057264653,0.0001088455,0.000216093,0.002217759,0.00002130393,0.09026467,0.00042598986,0.00019949742,0.22439915],"study_design_scores_gemma":[0.0065192594,0.0033884505,0.9650165,0.00041427178,0.000052993946,0.0007012811,0.00008586171,0.0151398,0.00036399328,0.00008031073,0.008130418,0.00010689876],"about_ca_topic_score_codex":0.00008576107,"about_ca_topic_score_gemma":0.000019114752,"teacher_disagreement_score":0.29755893,"about_ca_system_score_codex":0.00021999003,"about_ca_system_score_gemma":0.00020061574,"threshold_uncertainty_score":0.23724712},"labels":[],"label_agreement":null},{"id":"W2514478266","doi":"10.1016/s0167-8140(16)31669-3","title":"OC-0420: Radiomics in OPSCC: a novel quantitative imaging biomarker for HPV status?","year":2016,"lang":"en","type":"article","venue":"Radiotherapy and Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto","funders":"","keywords":"Radiomics; Biomarker; Imaging biomarker; Medicine; Oncology; Radiology; Internal medicine; Magnetic resonance imaging; Biology; Genetics","score_opus":0.026883267399629103,"score_gpt":0.36807041182900674,"score_spread":0.34118714442937764,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2514478266","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5021821,0.0071649007,0.44385326,0.0432799,0.00072587485,0.0010752951,0.0000387075,0.00009220881,0.0015877124],"genre_scores_gemma":[0.777923,0.009070023,0.19892856,0.012063173,0.00055268686,0.00017217934,0.000029841396,0.00014133546,0.0011191842],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99856853,0.000080983606,0.00034791225,0.00038910168,0.00010871312,0.0005047318],"domain_scores_gemma":[0.9984817,0.0009677722,0.00011639843,0.00016710038,0.00005431643,0.00021273806],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007317763,0.0001860495,0.0005298149,0.00026252615,0.00007643737,0.0000182719,0.00008183884,0.00012364857,0.00010594161],"category_scores_gemma":[0.00042294027,0.00012711358,0.00008931481,0.0001534043,0.0003431774,0.00010704473,0.000019170602,0.00020140826,0.0000022062375],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017413145,0.00028723537,0.057316255,0.0000683574,0.00014427006,0.00006808789,0.0013197786,0.0000056640138,0.14299947,0.006614236,0.0019231993,0.7875121],"study_design_scores_gemma":[0.03589499,0.0015231373,0.10536517,0.00026795606,0.000094047595,0.0007074907,0.00046503992,0.10079949,0.00047096904,0.0013817331,0.7525394,0.00049056526],"about_ca_topic_score_codex":0.00008881096,"about_ca_topic_score_gemma":0.000032905664,"teacher_disagreement_score":0.7870216,"about_ca_system_score_codex":0.00052992394,"about_ca_system_score_gemma":0.00023541128,"threshold_uncertainty_score":0.5183541},"labels":[],"label_agreement":null},{"id":"W2516269408","doi":"10.1016/s0167-8140(16)32560-9","title":"EP-1310: PV of FDG-PET SUV in rectal cancer pts: correlation with tumor characteristics/response to neoadj RT","year":2016,"lang":"en","type":"article","venue":"Radiotherapy and Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; University of Toronto; Sunnybrook Health Science Centre","funders":"","keywords":"Medicine; Colorectal cancer; Correlation; Nuclear medicine; Cancer; Oncology; Internal medicine; Mathematics","score_opus":0.009140296266259488,"score_gpt":0.3079862685449126,"score_spread":0.2988459722786531,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2516269408","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97974646,0.00033999115,0.005269294,0.013940101,0.00023970149,0.00027452127,0.000009337564,0.000019925117,0.00016064053],"genre_scores_gemma":[0.99234664,0.00065180415,0.0030826717,0.002788823,0.00021763284,0.000034003846,0.000003591922,0.000025979396,0.0008488417],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99902296,0.00016219988,0.00026698282,0.00022475567,0.00010718139,0.00021592049],"domain_scores_gemma":[0.9991448,0.00041387547,0.00011989153,0.00012747139,0.00004659617,0.00014736364],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005135282,0.00012034034,0.00043643342,0.00016422638,0.000030589563,0.0000052743358,0.00005572787,0.00006329197,0.00024422424],"category_scores_gemma":[0.00025807117,0.00007605305,0.00002846129,0.00013920396,0.00016027031,0.000045533292,0.000010762379,0.0001958107,0.0000029157006],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.017240884,0.00023603732,0.42762288,0.000055400535,0.00009522935,0.00050605595,0.0018843595,0.000037521946,0.20371719,0.00015467338,0.0010016719,0.34744808],"study_design_scores_gemma":[0.010018542,0.004507596,0.8806884,0.0006454129,0.000054701854,0.00081219454,0.00009288794,0.004355608,0.0008614183,0.00003966348,0.09768742,0.00023615158],"about_ca_topic_score_codex":0.00017164894,"about_ca_topic_score_gemma":0.00006219189,"teacher_disagreement_score":0.4530655,"about_ca_system_score_codex":0.0003323269,"about_ca_system_score_gemma":0.00024219355,"threshold_uncertainty_score":0.31013536},"labels":[],"label_agreement":null},{"id":"W2519502486","doi":"10.1097/01.jto.0000284174.03442.4f","title":"P3-199: CT, FDG PET and pathology: validating imaging to improve radiation targeting in non–small cell lung cancer (NSCLC)","year":2007,"lang":"en","type":"article","venue":"Journal of Thoracic Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto General Hospital; University of Toronto; Sunnybrook Health Science Centre","funders":"","keywords":"Medicine; Lung cancer; Radiation therapy; PET-CT; Positron emission tomography; Radiology; Nuclear medicine; Pathology","score_opus":0.007196511881390643,"score_gpt":0.37959060255778004,"score_spread":0.3723940906763894,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2519502486","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97329223,0.0019832638,0.014848296,0.00737275,0.001063653,0.0002718155,0.0000014823024,0.000013435902,0.0011530994],"genre_scores_gemma":[0.9541017,0.0002360886,0.041859392,0.0026524987,0.0009922369,0.0000053581884,0.0000030647923,0.000032734493,0.000116953524],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9980088,0.00017912524,0.00086293684,0.00025679974,0.00021837548,0.00047397366],"domain_scores_gemma":[0.998309,0.0004139975,0.00066847756,0.00011601357,0.00015357857,0.00033890668],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0046653626,0.00017174694,0.0005914569,0.0005045682,0.00008729386,0.000028810864,0.00013188997,0.00006494672,0.000031950774],"category_scores_gemma":[0.0010260908,0.00014937452,0.00008821217,0.00024737202,0.0000636935,0.00012877137,0.00008434126,0.0011797661,0.0000020194518],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00048804082,0.00014161174,0.22208342,0.00023097155,0.00003684903,0.005911057,0.001894392,0.0003613355,0.13970798,0.0000048358047,0.0015252408,0.62761426],"study_design_scores_gemma":[0.018173551,0.0047958596,0.5826325,0.00416812,0.0022197526,0.027483145,0.0115276575,0.2443454,0.04787909,0.00045124817,0.054452296,0.0018714169],"about_ca_topic_score_codex":0.000118171825,"about_ca_topic_score_gemma":0.000017153536,"teacher_disagreement_score":0.62574285,"about_ca_system_score_codex":0.0004711147,"about_ca_system_score_gemma":0.00030901426,"threshold_uncertainty_score":0.60913163},"labels":[],"label_agreement":null},{"id":"W2519748110","doi":"10.1007/978-3-642-16259-6_3","title":"Rigid Registration of 3D Ultrasound and MRI: Comparing Two Approaches on Nine Tumor Cases","year":2010,"lang":"en","type":"book-chapter","venue":"Advances in intelligent and soft computing","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Montreal Neurological Institute and Hospital","funders":"","keywords":"Ultrasound; Magnetic resonance imaging; Context (archaeology); Mutual information; Artificial intelligence; Computer science; Nuclear medicine; Medicine; Radiology; Geography","score_opus":0.03283028647268323,"score_gpt":0.30621997591869854,"score_spread":0.2733896894460153,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2519748110","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.54030037,0.037069768,0.040992614,0.0004990886,0.0015003128,0.001458,0.000012558631,0.00019102679,0.3779763],"genre_scores_gemma":[0.9833712,0.0019095525,0.010692739,0.00012150283,0.00041215098,0.0000021510648,0.000042266005,0.000045713256,0.0034027195],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985208,0.000018396859,0.0005794576,0.00042619364,0.0002520305,0.00020315268],"domain_scores_gemma":[0.9983936,0.0008751305,0.0003846889,0.00019408485,0.000048783662,0.000103709644],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00045232268,0.00028513116,0.0006421923,0.00018969503,0.00009913166,0.000032651493,0.00008324879,0.000105078005,0.000020430278],"category_scores_gemma":[0.00041815703,0.00025342597,0.000056902853,0.00003414996,0.00039317465,0.000066476205,0.000062979874,0.0010520032,0.0000014098741],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00067275047,0.00030152875,0.10340351,0.0033870179,0.00028079818,0.0006321754,0.0026951204,0.009570184,0.0013496849,0.1581888,0.00009388646,0.71942455],"study_design_scores_gemma":[0.009270505,0.003422675,0.0064752568,0.037557635,0.0012959059,0.0073239645,0.0016458355,0.57787824,0.008590953,0.04111927,0.30078784,0.004631932],"about_ca_topic_score_codex":0.00004466766,"about_ca_topic_score_gemma":0.00004599361,"teacher_disagreement_score":0.7147926,"about_ca_system_score_codex":0.000032585027,"about_ca_system_score_gemma":0.000031429332,"threshold_uncertainty_score":0.9999918},"labels":[],"label_agreement":null},{"id":"W2521706419","doi":"10.1016/j.cviu.2016.08.011","title":"Editorial on Special Issue on Probabilistic Models for Biomedical Image Analysis","year":2016,"lang":"en","type":"article","venue":"Computer Vision and Image Understanding","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Anterior cruciate ligament; Sørensen–Dice coefficient; Standard deviation; Sagittal plane; Segmentation; Medicine; Similarity (geometry); Artificial intelligence; Mathematics; Mean squared error; Nuclear medicine; Root mean square; Cohen's kappa; Computer science; Image segmentation; Image (mathematics); Surgery; Statistics; Radiology; Physics","score_opus":0.02419464614104788,"score_gpt":0.3161537181962582,"score_spread":0.2919590720552103,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2521706419","genre_codex":"methods","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016380273,0.000007469215,0.974833,0.008158519,0.012407373,0.0003781583,0.000017503282,0.00007995535,0.0024799614],"genre_scores_gemma":[0.41815814,0.00015586206,0.09467294,0.0035213227,0.48181185,0.000033249573,0.00011325802,0.00013682926,0.0013965585],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99829704,0.000053922526,0.00030699317,0.0005258057,0.00048642326,0.0003298231],"domain_scores_gemma":[0.9986885,0.0005848323,0.000082983606,0.00024171411,0.00007511598,0.00032683933],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00050233176,0.00021696126,0.00044944073,0.00042631567,0.00020680876,0.00013424386,0.000103298975,0.00011174162,0.00017373223],"category_scores_gemma":[0.00028053322,0.0001308748,0.00019850627,0.00025237794,0.00028584435,0.00015332032,0.00006755745,0.0002339714,0.000019450916],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014207037,0.0004265737,0.00003905756,0.00017066958,0.0003911838,0.000061602266,0.00032814962,0.00007286238,0.004209812,0.017710801,0.87844706,0.09672151],"study_design_scores_gemma":[0.010151431,0.004083214,0.00014364834,0.0009290397,0.00063541124,0.000028543462,0.000119812714,0.72078896,0.00012701632,0.029414827,0.23305432,0.00052375335],"about_ca_topic_score_codex":0.0000025539766,"about_ca_topic_score_gemma":3.866335e-7,"teacher_disagreement_score":0.8801601,"about_ca_system_score_codex":0.00024842005,"about_ca_system_score_gemma":0.00004179861,"threshold_uncertainty_score":0.53369194},"labels":[],"label_agreement":null},{"id":"W2529739186","doi":"10.1016/j.ijrobp.2016.06.1742","title":"Specific Growth Rate in Stage I Non-Small Cell Lung Cancer Treated With Stereotactic Body Radiation Therapy (SBRT)","year":2016,"lang":"en","type":"article","venue":"International Journal of Radiation Oncology*Biology*Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Ottawa Hospital; Princess Margaret Cancer Centre; University of Ottawa","funders":"","keywords":"Medicine; Lung cancer; Stage (stratigraphy); Nuclear medicine; Proportional hazards model; Hazard ratio; Log-rank test; Radiation therapy; Radiology; Oncology; Internal medicine; Confidence interval","score_opus":0.012809526425163273,"score_gpt":0.3130512707654883,"score_spread":0.300241744340325,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2529739186","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9751063,0.0008785274,0.016133875,0.005835253,0.0010307333,0.00033290157,0.000023238474,0.000028557577,0.00063060026],"genre_scores_gemma":[0.9892172,0.007007415,0.00062413415,0.0010543315,0.0017211437,0.000020485693,0.00003668021,0.00004578713,0.0002728111],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9981717,0.00028714794,0.0006982547,0.00028546544,0.0002637403,0.00029369982],"domain_scores_gemma":[0.9975831,0.00050998066,0.0010469649,0.00014427448,0.0005497562,0.0001659356],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00071746483,0.0002339687,0.00051106734,0.00031790754,0.00005150757,0.000034642042,0.00029174107,0.00017258996,0.00015821944],"category_scores_gemma":[0.00015942231,0.00015343957,0.00013738411,0.00023736533,0.00016583514,0.00030413803,0.000025869058,0.00058441126,0.000013732474],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008959555,0.00037649483,0.8781204,0.000012723853,0.00034968124,0.00015388503,0.00033051326,0.0001821704,0.033107422,0.0005727036,0.0006283202,0.08526972],"study_design_scores_gemma":[0.046256002,0.0029887166,0.87857956,0.00052442565,0.00022007401,0.00021568462,0.000068736525,0.0131287165,0.023549216,0.0011197058,0.032768425,0.00058077223],"about_ca_topic_score_codex":0.00006946324,"about_ca_topic_score_gemma":0.0000044654503,"teacher_disagreement_score":0.08468895,"about_ca_system_score_codex":0.0011958892,"about_ca_system_score_gemma":0.0005854419,"threshold_uncertainty_score":0.6257084},"labels":[],"label_agreement":null},{"id":"W2530952499","doi":"10.1038/nrclinonc.2016.162","title":"Imaging biomarker roadmap for cancer studies","year":2016,"lang":"en","type":"review","venue":"Nature Reviews Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1078,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Robarts Clinical Trials","funders":"Innovative Medicines Initiative; European Commission; Wellbeing of Women; Engineering and Physical Sciences Research Council; National Institute for Health and Care Research; National Cancer Institute; Cancer Research UK; Medical Research Council; European Federation of Pharmaceutical Industries and Associations","keywords":"Medicine; Clinical trial; Medical physics; Drug development; Translational research; Standardization; Biomarker; Internal medicine; Pathology; Drug; Pharmacology; Computer science","score_opus":0.2445465864156629,"score_gpt":0.6209623229717565,"score_spread":0.37641573655609356,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2530952499","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.8381037e-7,0.97385246,0.00033594068,0.013023231,0.007319489,0.003943298,0.00004303211,0.00008882987,0.0013935227],"genre_scores_gemma":[2.7687162e-7,0.97413045,0.0049856906,0.01033801,0.0057819346,0.0013767179,0.000093840936,0.00014973663,0.0031433492],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99234724,0.0015207942,0.0038064432,0.0012794867,0.00030426733,0.0007417558],"domain_scores_gemma":[0.9875434,0.0083423685,0.0023324094,0.0008551607,0.00039025626,0.0005363784],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.008369708,0.0008030243,0.011417801,0.00025886926,0.00012957102,0.000018791281,0.0005137935,0.002129639,0.00021028062],"category_scores_gemma":[0.029593827,0.0004088861,0.0038131818,0.00035186615,0.0006241163,0.000059539037,0.0002481542,0.004537026,0.00022001383],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037093556,0.00012489044,0.00004827855,0.024139835,0.00091892126,0.00007135363,0.000005707619,3.5737475e-9,1.9467595e-7,0.00013482578,0.17093015,0.80358875],"study_design_scores_gemma":[0.0014639236,0.00021012692,0.0000108970635,0.07425171,0.0054440005,0.00021756128,0.0000030803374,0.0000223732,2.642351e-8,0.00013300643,0.91783834,0.00040493454],"about_ca_topic_score_codex":0.0000029426878,"about_ca_topic_score_gemma":0.0000043855657,"teacher_disagreement_score":0.8031838,"about_ca_system_score_codex":0.00068595575,"about_ca_system_score_gemma":0.0016963608,"threshold_uncertainty_score":0.9998363},"labels":[],"label_agreement":null},{"id":"W2533382638","doi":"10.1109/embc.2016.7591612","title":"Radiomic analysis of multi-contrast brain MRI for the prediction of survival in patients with glioblastoma multiforme","year":2016,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Fluid-attenuated inversion recovery; Glioblastoma; Contrast (vision); Medicine; Correlation; Pattern recognition (psychology); Radiomics; Magnetic resonance imaging; Radiology; Gray level; Log-rank test; Artificial intelligence; Survival analysis; Computer science; Mathematics; Internal medicine; Image (mathematics)","score_opus":0.007809307318071157,"score_gpt":0.2549587733705833,"score_spread":0.24714946605251215,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2533382638","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8516451,0.000014952451,0.14625056,0.0014303328,0.0000705615,0.00047355914,0.00005583384,0.000014160356,0.000044928755],"genre_scores_gemma":[0.99724597,0.000010336552,0.002370107,0.00008627444,0.000025945237,0.000016201957,0.000017776338,0.00001372692,0.00021367114],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9990207,0.000035590238,0.00036275233,0.00016836669,0.0002440087,0.00016859244],"domain_scores_gemma":[0.9988059,0.0006346316,0.00015363614,0.00021472853,0.00013166427,0.000059438986],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046931594,0.00009699085,0.00040561904,0.00029697389,0.0000248215,0.000003167973,0.000086726315,0.000044926197,0.000047302172],"category_scores_gemma":[0.0005028924,0.000043037897,0.00012498544,0.00040198897,0.00014232106,0.00005317033,0.000014573196,0.00008410838,4.5942073e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010747957,0.0002829217,0.9689843,0.000036926387,0.00082821964,5.071392e-7,0.0002003484,0.00051165617,0.00397652,0.000072806215,0.00013658109,0.023894407],"study_design_scores_gemma":[0.009225197,0.00043259756,0.80705476,0.00008199118,0.0005098946,4.7621302e-7,0.00006246075,0.18173556,0.00069108413,0.0000027965011,0.00015814975,0.000045052457],"about_ca_topic_score_codex":0.00017368885,"about_ca_topic_score_gemma":0.00017274202,"teacher_disagreement_score":0.18122391,"about_ca_system_score_codex":0.000043806074,"about_ca_system_score_gemma":0.00003669046,"threshold_uncertainty_score":0.17550345},"labels":[],"label_agreement":null},{"id":"W2537494909","doi":"10.1594/ecr2015/c-1618","title":"Can breast MRI differentiate radial scar without from radial scar with associated atypia or malignancy?","year":2015,"lang":"en","type":"article","venue":"European Society of Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Malignancy; Atypia; Medicine; Radial fractures; Radiology; Pathology; Wrist","score_opus":0.01633896581676582,"score_gpt":0.2533884342807395,"score_spread":0.23704946846397368,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2537494909","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99056244,0.00047228468,0.0016177762,0.004500625,0.0006018271,0.00033454088,0.00014185059,0.00018384117,0.0015847929],"genre_scores_gemma":[0.9882146,0.0002177231,0.006702443,0.0017399869,0.0012621091,0.00000480845,0.00047567772,0.00012942498,0.0012532144],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9971961,0.0006971697,0.00050988555,0.00058049185,0.00042080312,0.00059558987],"domain_scores_gemma":[0.9982803,0.00014986018,0.00036941693,0.0004509231,0.00018047758,0.00056901306],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00089675817,0.0003645435,0.0009711326,0.00005954171,0.00012799396,0.000027199889,0.00032929124,0.00016889829,0.00013900414],"category_scores_gemma":[0.0002341401,0.00026091855,0.00029348087,0.00022822536,0.00079446175,0.000060952312,0.00011051735,0.0007614024,0.000033385488],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002588788,0.00046458558,0.78977066,0.000101446894,0.0025509396,0.0005545318,0.0085770795,0.00045125256,0.0063805385,0.00007694339,0.17963515,0.008848093],"study_design_scores_gemma":[0.043766156,0.0035564895,0.884772,0.0011892607,0.0018644261,0.0045336,0.0019029042,0.030299293,0.0002968891,0.00019903155,0.026107416,0.0015125364],"about_ca_topic_score_codex":0.00047966884,"about_ca_topic_score_gemma":0.0000383731,"teacher_disagreement_score":0.15352774,"about_ca_system_score_codex":0.00017751873,"about_ca_system_score_gemma":0.00027146353,"threshold_uncertainty_score":0.9999843},"labels":[],"label_agreement":null},{"id":"W2546736938","doi":"10.1186/s12885-016-2886-9","title":"Response biomarkers: re-envisioning the approach to tailoring drug therapy for cancer","year":2016,"lang":"en","type":"review","venue":"BMC Cancer","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary; Alberta Bone and Joint Health Institute","funders":"","keywords":"Medicine; Biomarker; Intensive care medicine; Drug; Drug development; Risk analysis (engineering); Pharmacology","score_opus":0.07691271191571082,"score_gpt":0.413557608232714,"score_spread":0.3366448963170032,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2546736938","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000046382615,0.9851861,0.0054911003,0.0041067274,0.0011050245,0.0029587531,0.00008218861,0.00008259015,0.0009411562],"genre_scores_gemma":[0.000016683622,0.9798596,0.004123126,0.0019826833,0.0020959636,0.0040530213,0.000018200222,0.00018386923,0.0076668635],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972606,0.00037483437,0.0005957257,0.0007539773,0.00043424958,0.00058063795],"domain_scores_gemma":[0.9970897,0.0014519431,0.00033178317,0.0007377694,0.00010399833,0.00028481617],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024109504,0.00048373223,0.0013920007,0.0002477995,0.0002804197,0.000085521475,0.0004797279,0.00018273611,0.00022790793],"category_scores_gemma":[0.00092317275,0.00023932915,0.0006663296,0.00041259613,0.00012575938,0.000054064327,0.000114408875,0.0005689633,0.000023184211],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00068423443,0.000029316574,0.000038767528,0.0030849222,0.00034126377,0.0000022813213,0.00026538252,0.000012570297,0.000012609057,0.000033322183,0.03298762,0.9625077],"study_design_scores_gemma":[0.000980194,0.000051118768,0.00004715872,0.025476383,0.00038485543,0.000016960887,0.00005927397,0.0002443029,0.0000037367947,0.000011094798,0.97239316,0.00033177715],"about_ca_topic_score_codex":0.00022673943,"about_ca_topic_score_gemma":0.000012813359,"teacher_disagreement_score":0.9621759,"about_ca_system_score_codex":0.0005568778,"about_ca_system_score_gemma":0.0013113891,"threshold_uncertainty_score":0.97595596},"labels":[],"label_agreement":null},{"id":"W2549097358","doi":"10.15353/vsnl.v1i1.46","title":"Discovery Radiomics for Imaging-driven Quantitative Personalized Cancer Decision Support","year":2015,"lang":"en","type":"article","venue":"Vision Letters","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Toronto; University of Waterloo","funders":"","keywords":"Radiomics; Feature (linguistics); Cancer; Lung cancer; Prostate cancer; Computer science; Medicine; Artificial intelligence; Oncology; Internal medicine","score_opus":0.02630702879928695,"score_gpt":0.36876166265286786,"score_spread":0.34245463385358094,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2549097358","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5404476,0.00044314866,0.39916402,0.057886157,0.0011638157,0.00052970956,0.00003165462,0.000085480344,0.00024845861],"genre_scores_gemma":[0.7177593,0.00027817767,0.2182686,0.060051683,0.001136087,0.00015349024,0.0002804242,0.00018038285,0.0018918434],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99846846,0.000044092238,0.0003041686,0.0003902121,0.0004596631,0.0003334077],"domain_scores_gemma":[0.9989487,0.00028187208,0.00012246294,0.00023437578,0.00012783219,0.00028475156],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005211622,0.00018840424,0.00037315814,0.00017975207,0.00009231955,0.00008852849,0.00014200543,0.000046410576,0.00005109595],"category_scores_gemma":[0.00069119164,0.00014886359,0.0001899331,0.00015908714,0.00019711939,0.00028035225,0.000051295072,0.00025751535,0.000027008695],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0026463228,0.00020378224,0.031063393,0.00012353355,0.0001831374,0.00021884845,0.002482729,0.0014913725,0.09840319,0.001774558,0.7896054,0.07180375],"study_design_scores_gemma":[0.021114733,0.00092523487,0.009377195,0.0008319683,0.0004409121,0.000249032,0.0009781728,0.38882637,0.0012015929,0.0006270158,0.5746279,0.0007998854],"about_ca_topic_score_codex":0.000080500155,"about_ca_topic_score_gemma":0.0000021085023,"teacher_disagreement_score":0.38733497,"about_ca_system_score_codex":0.00020184825,"about_ca_system_score_gemma":0.00022062151,"threshold_uncertainty_score":0.60704815},"labels":[],"label_agreement":null},{"id":"W2550359848","doi":"","title":"Prostate Cancer Imaging. Image Analysis and Image-Guided Interventions: International Workshop, Held in Conjunction with MICCAI 2011, Toronto, Canada, September 2011, Proceedings","year":2011,"lang":"en","type":"book","venue":"Springer eBooks","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Medical physics; Prostate cancer; Conjunction (astronomy); Medicine; Cancer; Internal medicine","score_opus":0.011431781265004009,"score_gpt":0.2800976717111162,"score_spread":0.2686658904461122,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2550359848","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02112663,0.008233575,0.0013563464,0.0035021184,0.0017288392,0.0024367615,0.00012320702,0.00024972166,0.9612428],"genre_scores_gemma":[0.013229078,0.00048434205,0.004394207,0.0010315843,0.0005978032,0.00029204576,0.0002035548,0.0001881955,0.9795792],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9971965,0.000027009073,0.00078757165,0.0008847994,0.0006047526,0.0004993436],"domain_scores_gemma":[0.9982794,0.000042926662,0.00054349547,0.00031303064,0.0005121761,0.00030897866],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00048484726,0.00054697006,0.0009011529,0.00051656266,0.000092364724,0.00014874674,0.00024759615,0.00017691297,0.0027366972],"category_scores_gemma":[0.000061180115,0.00047909297,0.00027483838,0.000062323954,0.00031870676,0.00024856196,0.00018830199,0.0010538298,0.00001656444],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016460168,0.00034765812,0.26092213,0.00410379,0.0111414,0.0013991427,0.003122093,0.0000136318195,0.002622278,0.00069521565,0.63618517,0.077801466],"study_design_scores_gemma":[0.01353075,0.0003601095,0.16253847,0.01665592,0.014711415,0.0007726399,0.0010677468,0.009172835,0.0011504405,0.00095761375,0.7749567,0.0041253716],"about_ca_topic_score_codex":0.24083193,"about_ca_topic_score_gemma":0.33604696,"teacher_disagreement_score":0.1387715,"about_ca_system_score_codex":0.0014340951,"about_ca_system_score_gemma":0.0010169678,"threshold_uncertainty_score":0.99976605},"labels":[],"label_agreement":null},{"id":"W2551588810","doi":"10.1594/ecr2013/c-2423","title":"Accuracy of a semi-automated liver segmentation method using CT scan","year":2013,"lang":"en","type":"article","venue":"Espace ÉTS (ETS)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Centre de Santé et de Services Sociaux Cavendish","funders":"","keywords":"Segmentation; Artificial intelligence; Computer vision; Computed tomography; Computer science; Image segmentation; Pattern recognition (psychology); Medicine; Radiology","score_opus":0.017007880282677412,"score_gpt":0.3447450699405835,"score_spread":0.3277371896579061,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2551588810","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9669703,0.00036173768,0.028446656,0.0022090897,0.00018228081,0.0004846482,0.0000021034925,0.00020850211,0.0011346459],"genre_scores_gemma":[0.91306764,0.00007017511,0.08522022,0.00073025835,0.00012393446,0.0000120027735,0.000018756047,0.000036515325,0.0007205086],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988115,0.00013230508,0.00026608547,0.00023129032,0.0003096437,0.00024918758],"domain_scores_gemma":[0.99901074,0.00023650524,0.0002152489,0.00024667877,0.0001178313,0.00017298835],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040240257,0.00014666197,0.00031307898,0.00015672093,0.000066480345,0.000034774115,0.00009025662,0.000046158017,0.0006161831],"category_scores_gemma":[0.00067737006,0.0001236587,0.00008408423,0.0002651838,0.000067162306,0.00018197132,0.000050232495,0.0002685671,0.00006487266],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007767264,0.00024229485,0.027530117,0.0004709947,0.0002672479,0.00012705341,0.0030425123,0.0035760233,0.802948,0.00017707612,0.014618952,0.14692207],"study_design_scores_gemma":[0.001442985,0.000084973304,0.022163302,0.00032745628,0.00015862913,0.00023860583,0.0005133701,0.9473073,0.024941424,0.000040595,0.0026063279,0.00017503672],"about_ca_topic_score_codex":0.0015258266,"about_ca_topic_score_gemma":0.0000047499075,"teacher_disagreement_score":0.94373125,"about_ca_system_score_codex":0.000089576395,"about_ca_system_score_gemma":0.00010062722,"threshold_uncertainty_score":0.67467725},"labels":[],"label_agreement":null},{"id":"W2558024855","doi":"10.1007/978-3-319-44606-6_11","title":"Observation and Inference","year":2016,"lang":"en","type":"book-chapter","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Roentgen; German; Inference; Philosophy; Medical physics; Art history; Nuclear medicine; History; Medicine; Epistemology; Archaeology","score_opus":0.02797195818044443,"score_gpt":0.2943003947548688,"score_spread":0.2663284365744244,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2558024855","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00032614067,0.00027114296,0.0031528024,0.005793837,0.00009869835,0.0001073941,0.0000015625131,0.00005829042,0.99019015],"genre_scores_gemma":[0.0038539986,0.00073563826,0.0021861724,0.0019854642,0.00026017494,0.0000014120163,0.000013838517,0.000025953064,0.99093735],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99947256,0.0000024250212,0.00013266201,0.00017100632,0.0001393304,0.00008199803],"domain_scores_gemma":[0.99958336,0.00007552355,0.00005449015,0.00013807391,0.000044732697,0.00010382556],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00008683098,0.00011495559,0.00020499688,0.00005466603,0.00002321887,0.000011336494,0.00002947334,0.00012680204,0.0010062711],"category_scores_gemma":[0.00013719845,0.00007272111,0.000033556506,0.0000048966717,0.00007915774,0.000026634316,0.0000317609,0.0002588402,0.0000800274],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001209103,0.0000036685944,0.0018799463,0.00008828957,0.00004497801,0.000029567058,0.00001819118,5.7494024e-8,0.0002454066,0.6002767,0.00406805,0.39333308],"study_design_scores_gemma":[0.0005477251,0.000078060235,0.0028569088,0.00079301855,0.00008389507,0.000050754705,0.0000010718932,0.00043828832,0.000010780282,0.032033764,0.96294105,0.00016466327],"about_ca_topic_score_codex":0.0000045561824,"about_ca_topic_score_gemma":6.92551e-7,"teacher_disagreement_score":0.95887303,"about_ca_system_score_codex":0.00002020583,"about_ca_system_score_gemma":0.000045432593,"threshold_uncertainty_score":0.99990696},"labels":[],"label_agreement":null},{"id":"W2558317280","doi":"10.1097/pai.0000000000000451","title":"Evolution of Quality Assurance for Clinical Immunohistochemistry in the Era of Precision Medicine: Part 1: Fit-for-Purpose Approach to Classification of Clinical Immunohistochemistry Biomarkers","year":2016,"lang":"en","type":"article","venue":"Applied immunohistochemistry & molecular morphology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":59,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary; Vancouver General Hospital; University of Toronto; University of British Columbia; University Health Network","funders":"","keywords":"Immunohistochemistry; Quality assurance; Medicine; Pathology; Internal medicine; External quality assessment","score_opus":0.04627317822045426,"score_gpt":0.4069085434584457,"score_spread":0.36063536523799145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2558317280","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9131701,0.0024444256,0.07751542,0.0016448954,0.00030855578,0.0018969129,0.00008296664,0.000028550257,0.0029081583],"genre_scores_gemma":[0.9828886,0.00019220884,0.015365428,0.0002800419,0.00017073988,0.00067790144,0.00024284601,0.00006027309,0.00012196852],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99360216,0.00031491913,0.003885218,0.0010395866,0.0006476997,0.0005104377],"domain_scores_gemma":[0.9928961,0.0024224436,0.0019894266,0.0019248674,0.0005913829,0.00017580563],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.007024888,0.00043076192,0.0018068871,0.00010964971,0.000084773405,0.000004810738,0.000978525,0.00072273007,0.000028201319],"category_scores_gemma":[0.008170379,0.0003178747,0.0006975801,0.00044028548,0.001985097,0.000037078742,0.00012911658,0.0008063223,0.0000015802837],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0038429298,0.00088851474,0.0017109648,0.00092606863,0.00023910655,0.0000030381862,0.00013458703,0.000012585539,0.976322,0.0008023909,0.003066728,0.012051063],"study_design_scores_gemma":[0.030670855,0.0019095258,0.09559804,0.0027646658,0.001211957,0.0002680213,0.0012753004,0.0006405499,0.85919845,0.0018459718,0.003299577,0.0013170904],"about_ca_topic_score_codex":0.000082445804,"about_ca_topic_score_gemma":4.9803894e-8,"teacher_disagreement_score":0.11712358,"about_ca_system_score_codex":0.00029866718,"about_ca_system_score_gemma":0.0006308513,"threshold_uncertainty_score":0.99992734},"labels":[],"label_agreement":null},{"id":"W2559850178","doi":"10.1200/jco.2011.29.7_suppl.124","title":"Can MRI accurately define tumor boundaries to guide focal salvage after radiotherapy?","year":2011,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; Health Sciences Centre; Sunnybrook Health Science Centre","funders":"","keywords":"Medicine; Biopsy; Radiology; Radiation therapy; Prostate cancer; Magnetic resonance imaging; Nuclear medicine; Cancer; Internal medicine","score_opus":0.10212067452287345,"score_gpt":0.4585404308136208,"score_spread":0.35641975629074735,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2559850178","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89105177,0.0015417102,0.012414756,0.08054523,0.0041208086,0.00028552618,0.000004177161,0.000035299898,0.010000717],"genre_scores_gemma":[0.81687874,0.0002562338,0.119054355,0.06017978,0.002769849,0.000006875793,0.0000013580132,0.00004560896,0.00080721214],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9961901,0.00036417352,0.0023978946,0.0002446559,0.00041544123,0.00038773924],"domain_scores_gemma":[0.9965706,0.00088604883,0.0009500256,0.0002634004,0.00035120637,0.0009787286],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004040553,0.00019007691,0.0015404079,0.00018041176,0.0000760465,0.000037407346,0.00028159583,0.00023404445,0.00109648],"category_scores_gemma":[0.007820253,0.0001300665,0.0004925697,0.00015976436,0.0005678522,0.00009397967,0.00007145344,0.001663307,0.000033684282],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.020774907,0.0028371578,0.255275,0.00010430248,0.0013383148,0.021926576,0.0030458434,0.000023203373,0.0009340375,0.0014351957,0.19702399,0.4952815],"study_design_scores_gemma":[0.0050779204,0.009916216,0.23031609,0.0001366127,0.00024244556,0.002471187,0.000100146164,0.00022162458,0.000086060834,0.00072394224,0.7505474,0.00016037162],"about_ca_topic_score_codex":0.00013773447,"about_ca_topic_score_gemma":0.000055424014,"teacher_disagreement_score":0.5535234,"about_ca_system_score_codex":0.00019283904,"about_ca_system_score_gemma":0.0024599081,"threshold_uncertainty_score":0.99981666},"labels":[],"label_agreement":null},{"id":"W2560766689","doi":"10.1002/mp.12041","title":"Multi‐site quality and variability analysis of 3D FDG PET segmentations based on phantom and clinical image data","year":2016,"lang":"en","type":"article","venue":"Medical Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"National Institute of Environmental Health Sciences; Canadian Institutes of Health Research; National Institutes of Health; National Cancer Institute; University of Washington","keywords":"Imaging phantom; Segmentation; Artificial intelligence; Feature (linguistics); Image quality; Medical imaging; Computer science; Quality assurance; Positron emission tomography; Metric (unit); Pattern recognition (psychology); Data set; Image segmentation; Radiation treatment planning; Medical physics; Medicine; Nuclear medicine; Radiology; Image (mathematics); Radiation therapy","score_opus":0.06026283636112687,"score_gpt":0.44287194260569973,"score_spread":0.38260910624457284,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2560766689","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5422863,0.00001961366,0.44874734,0.008213744,0.00009556484,0.00016716131,0.00022415101,0.000035408597,0.00021070997],"genre_scores_gemma":[0.9811901,0.00011460544,0.01619927,0.002023944,0.00017565406,0.000003198754,0.0002473401,0.0000132626665,0.000032620188],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99773175,0.00035546522,0.0005807661,0.00051541027,0.0006366673,0.00017995291],"domain_scores_gemma":[0.9963058,0.0022738604,0.00016623193,0.0007524554,0.000080613856,0.00042099383],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003461028,0.00013009811,0.0006120245,0.000068359564,0.000057124995,0.000012512042,0.00016249302,0.00006943444,0.00020374438],"category_scores_gemma":[0.0071467594,0.000083883126,0.00009394665,0.00028894874,0.0012127848,0.0000902325,0.00016926494,0.0003516164,0.000003983271],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015653478,0.0013196002,0.75586605,0.00015298175,0.0007038702,0.000036263304,0.00008833213,0.0000038021965,0.0019235555,0.00014801523,0.0005028926,0.23909809],"study_design_scores_gemma":[0.0040616523,0.00013537958,0.5765322,0.00016135744,0.0015382254,0.00000339483,0.000011935015,0.41690522,0.00008260345,0.00020838773,0.0002261885,0.00013350777],"about_ca_topic_score_codex":0.00010667933,"about_ca_topic_score_gemma":0.00000993311,"teacher_disagreement_score":0.4389038,"about_ca_system_score_codex":0.000022863367,"about_ca_system_score_gemma":0.00013600584,"threshold_uncertainty_score":0.85558546},"labels":[],"label_agreement":null},{"id":"W2561518335","doi":"10.1158/1557-3125.advbc-a124","title":"Abstract A124: Characterization of claudin-low breast cancers","year":2013,"lang":"en","type":"article","venue":"Molecular Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hamilton Health Sciences; McMaster University","funders":"","keywords":"Breast cancer; Tissue microarray; Immunohistochemistry; Cancer research; Claudin; Pathology; Cancer; Gene expression profiling; Lymph node; Biology; Gene expression; Medicine; Gene; Internal medicine","score_opus":0.021130607600725243,"score_gpt":0.36546232414979135,"score_spread":0.34433171654906614,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2561518335","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98856336,0.00025204016,0.0008013611,0.00715358,0.000112019734,0.00048737158,0.000012341671,0.000026393218,0.0025915117],"genre_scores_gemma":[0.99820894,0.0002750005,0.0001533474,0.00046846073,0.00015478556,0.00013285667,0.000043785545,0.000037108555,0.000525702],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9982253,0.00007356694,0.00023955983,0.00026277098,0.00078685913,0.0004119635],"domain_scores_gemma":[0.9989177,0.00003481543,0.00006929377,0.00029307496,0.00045113967,0.000233981],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00048414848,0.000104648425,0.00023179216,0.00021712614,0.000071934635,0.000037660764,0.00015683759,0.000075649376,0.001485263],"category_scores_gemma":[0.00012700919,0.00009113209,0.0000744632,0.0004029842,0.00021827471,0.00008497364,0.000059820493,0.0006361651,0.00006577706],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000440696,0.000046347857,0.0057959915,0.00021867461,0.000056137193,0.0000388624,0.0000850233,0.00004117634,0.93510866,0.000134186,0.0010238664,0.05740703],"study_design_scores_gemma":[0.0022966238,0.00021141556,0.71647173,0.0013110465,0.000048740316,0.00008606152,0.000118469616,0.010975129,0.2602908,0.00031649036,0.007546509,0.00032695613],"about_ca_topic_score_codex":0.0044523287,"about_ca_topic_score_gemma":0.000007766236,"teacher_disagreement_score":0.7106758,"about_ca_system_score_codex":0.0002486231,"about_ca_system_score_gemma":0.00043838585,"threshold_uncertainty_score":0.9994275},"labels":[],"label_agreement":null},{"id":"W2564219340","doi":"10.1158/1538-7445.am2015-5297","title":"Abstract 5297: Chromosomal instability as a prognostic marker in cervical cancer","year":2015,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre","funders":"","keywords":"Cervical cancer; Medicine; Hazard ratio; Cancer; Oncology; Internal medicine; Cohort; Chromosome instability; Proportional hazards model; Gastroenterology; Gene; Confidence interval; Biology; Genetics; Chromosome","score_opus":0.08298458269265552,"score_gpt":0.44804216333034846,"score_spread":0.36505758063769295,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2564219340","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9729498,0.0018365649,0.0000067197047,0.012260266,0.00021737331,0.00064575614,0.000007034202,0.000046286063,0.012030182],"genre_scores_gemma":[0.9973098,0.00022649288,0.00012532598,0.0005457216,0.00055500446,0.00038832426,0.000008636735,0.00003773985,0.0008029332],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99714106,0.00019767096,0.00031169795,0.00047398577,0.001136661,0.00073889445],"domain_scores_gemma":[0.9983239,0.0002695289,0.000036672398,0.00029434377,0.00038171114,0.0006938067],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0021141327,0.00014525693,0.0003249858,0.00022665059,0.00007452425,0.000052040916,0.00022777983,0.00013028474,0.00235565],"category_scores_gemma":[0.0028756226,0.00011871999,0.000059382815,0.0006582715,0.0003926031,0.00010201204,0.00015280419,0.0017936131,0.00012259913],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007497193,0.00036091346,0.94055665,0.00041361977,0.00004367243,0.00055927504,0.00086473225,0.000091951726,0.0063159443,0.00013558017,0.007812912,0.04209503],"study_design_scores_gemma":[0.003275321,0.00024800492,0.9504141,0.00078098726,0.000020081688,0.00004791371,0.00034851997,0.004096279,0.0007106744,0.0007629854,0.039088763,0.00020632637],"about_ca_topic_score_codex":0.01092499,"about_ca_topic_score_gemma":0.00072597,"teacher_disagreement_score":0.041888706,"about_ca_system_score_codex":0.00091744127,"about_ca_system_score_gemma":0.002289475,"threshold_uncertainty_score":0.9985563},"labels":[],"label_agreement":null},{"id":"W2565096807","doi":"10.1093/neuonc/now212.111","title":"BMET-11. DURAL METASTASES FROM BREAST CANCER - CASE SERIES","year":2016,"lang":"en","type":"article","venue":"Neuro-Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"London Health Sciences Centre; Western University","funders":"","keywords":"Medicine; Breast cancer; Headaches; Radiology; Asymptomatic; Cancer; Weakness; Surgery; Quadrantectomy; Radiation therapy; Craniotomy; Internal medicine; Mastectomy","score_opus":0.016235027392855036,"score_gpt":0.319584573768783,"score_spread":0.303349546375928,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2565096807","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89876777,0.00028648984,0.00033639057,0.09799029,0.001243605,0.00018660453,0.0002623155,0.00012707726,0.00079943193],"genre_scores_gemma":[0.98757505,0.00038207497,0.0016368342,0.008644406,0.0011995148,0.000048216065,0.000022838525,0.00004827487,0.00044281362],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.998557,0.00020930567,0.00029186803,0.00038298473,0.00018256942,0.0003762874],"domain_scores_gemma":[0.99861646,0.00058835594,0.00011835213,0.00028838028,0.00007505099,0.00031341158],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00018940489,0.00018683173,0.00047715093,0.00009100364,0.00010504403,0.000015457439,0.00010778714,0.00011223623,0.0020260199],"category_scores_gemma":[0.00050630694,0.00011570008,0.000106247615,0.000110521934,0.0003042943,0.00013155257,0.00009169585,0.0003251179,0.00007510062],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005232252,0.00018753155,0.048397467,0.00002892997,0.00014959586,0.033941135,0.00024145063,0.0000053733474,0.4910313,0.00029713436,0.0314784,0.39371848],"study_design_scores_gemma":[0.0049616373,0.0005746599,0.0105284015,0.000099020566,0.0004609935,0.08595032,0.00018464221,0.0002603243,0.0056186486,0.00023070074,0.8908513,0.00027935745],"about_ca_topic_score_codex":0.0012486491,"about_ca_topic_score_gemma":0.00031925607,"teacher_disagreement_score":0.8593729,"about_ca_system_score_codex":0.00015189595,"about_ca_system_score_gemma":0.00025871524,"threshold_uncertainty_score":0.9988863},"labels":[],"label_agreement":null},{"id":"W2565445350","doi":"10.1212/wnl.86.16_supplement.p3.025","title":"Patients Who Discontinued SC IFNB-1a and Switched to Alemtuzumab in the CARE-MS II Extension Study Show Durable Reduction in New Lesion Activity (P3.025)","year":2016,"lang":"en","type":"article","venue":"Neurology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; NeuroRx Research (Canada); Montreal Neurological Institute and Hospital","funders":"","keywords":"Alemtuzumab; Medicine; Reduction (mathematics); Lesion; Extension (predicate logic); Internal medicine; Surgery; Mathematics; Computer science","score_opus":0.014847602015065405,"score_gpt":0.2888658204393083,"score_spread":0.2740182184242429,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2565445350","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9740101,0.00004174929,0.00009122652,0.024658963,0.00029652377,0.0007749118,6.8631294e-7,0.000019773897,0.00010603156],"genre_scores_gemma":[0.9983793,0.00003702317,0.00004558447,0.0011806353,0.00013042518,0.000018893275,0.0000027216981,0.000018218772,0.00018723472],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9985191,0.0003130022,0.00021840581,0.000446685,0.00021649593,0.0002862905],"domain_scores_gemma":[0.99935836,0.00012642863,0.000069161855,0.00029821842,0.00003645411,0.00011137961],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039060356,0.00014146829,0.0003120039,0.00017522732,0.00008872264,0.000013136302,0.000103763996,0.00008738633,0.000015417678],"category_scores_gemma":[0.00045921828,0.00008251218,0.00002787974,0.00016785132,0.000057431913,0.0000942743,0.00011125435,0.0004522491,0.0000049766086],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0030166106,0.0006325796,0.64748013,0.000017527203,0.000010467289,0.00012185808,0.006786771,0.000024313826,0.05891922,0.000012785957,0.00094529224,0.28203243],"study_design_scores_gemma":[0.0048856535,0.0042078644,0.9884485,0.00006116247,0.000024059318,0.000044581648,0.00012970933,0.00034309976,0.00021128591,0.000046990575,0.0015041179,0.000092964925],"about_ca_topic_score_codex":0.0013778978,"about_ca_topic_score_gemma":0.00056527223,"teacher_disagreement_score":0.34096834,"about_ca_system_score_codex":0.00004408506,"about_ca_system_score_gemma":0.00005418443,"threshold_uncertainty_score":0.33647493},"labels":[],"label_agreement":null},{"id":"W2565812816","doi":"10.1200/jco.2015.33.15_suppl.9073","title":"Patterns of response to anti-PD1 treatment: Comparison of three radiological response criteria and effect on overall survival (OS) in metastatic melanoma patients (MM).","year":2015,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre","funders":"","keywords":"Medicine; Internal medicine; Radiological weapon; Hazard ratio; Nuclear medicine; Response Evaluation Criteria in Solid Tumors; Pembrolizumab; Oncology; Radiology; Progressive disease; Cancer; Chemotherapy; Confidence interval; Immunotherapy","score_opus":0.14473248165729216,"score_gpt":0.49835399092426463,"score_spread":0.35362150926697244,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2565812816","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99494964,0.00012545082,0.00017185637,0.0036556495,0.00067915133,0.00031024925,0.000009955515,0.0000041118597,0.000093912495],"genre_scores_gemma":[0.9974724,0.000041762847,0.0018208346,0.0004799481,0.0001393473,0.0000028641705,0.0000033887916,0.000014705311,0.000024721558],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9922377,0.0046036113,0.0022740443,0.00022137635,0.00043508454,0.00022821761],"domain_scores_gemma":[0.98485327,0.013030042,0.0011687175,0.00019814273,0.00021713931,0.00053268654],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.012242479,0.00017827652,0.0026365686,0.00028541958,0.000015475798,0.0000060376174,0.00014889971,0.00020080402,0.000030410696],"category_scores_gemma":[0.031305905,0.000110943976,0.00026014927,0.00010714702,0.00016377866,0.000047185396,0.000060441285,0.00070103916,0.000002713252],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.13255002,0.0022987283,0.82438284,0.00003109075,0.00018435236,0.00043102814,0.0003665119,0.00007342133,0.0009861668,0.000013614537,0.00023934936,0.038442872],"study_design_scores_gemma":[0.021909352,0.11667836,0.85730445,0.00021816696,0.00020225346,0.00006634334,0.00005734253,0.00081542216,0.00012585711,0.00006670032,0.0024801127,0.00007561246],"about_ca_topic_score_codex":0.000059697762,"about_ca_topic_score_gemma":0.000018646731,"teacher_disagreement_score":0.11437963,"about_ca_system_score_codex":0.00016960125,"about_ca_system_score_gemma":0.00046128116,"threshold_uncertainty_score":0.9768538},"labels":[],"label_agreement":null},{"id":"W2569634942","doi":"10.1016/j.clinbiochem.2017.01.004","title":"The future of artificial intelligence and interpretative specialization in clinical biochemistry","year":2017,"lang":"en","type":"letter","venue":"Clinical Biochemistry","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Standardization; Clinical biochemistry; Context (archaeology); Computer science; Interpretation (philosophy); Artificial intelligence; Data science; Medicine; Pathology; Biology","score_opus":0.037473730259062005,"score_gpt":0.4076623213703729,"score_spread":0.37018859111131086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2569634942","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13181223,0.007364088,0.0012356939,0.84987503,0.00468043,0.00069607585,0.00007240993,0.000066238215,0.0041978112],"genre_scores_gemma":[0.49985248,0.026030725,0.0050356486,0.32597587,0.13158864,0.00008231816,0.0018487438,0.00033999392,0.009245605],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99611384,0.00021246668,0.0020724835,0.00084699003,0.0004009096,0.00035330676],"domain_scores_gemma":[0.99553657,0.0019205236,0.0011099573,0.0010528693,0.00019233236,0.00018773318],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.0023654795,0.00033958908,0.001028457,0.000043634413,0.0001319779,0.00008539389,0.00058791507,0.0017892433,0.00004072466],"category_scores_gemma":[0.009850653,0.00024650196,0.00041598408,0.00009965198,0.0025748732,0.000028812565,0.0002596112,0.0056222198,0.0000078625235],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004508004,0.00027959593,0.016450804,0.0011215963,0.00029360116,0.0006141558,0.00008427487,6.5051404e-7,0.0005544784,0.000056543384,0.43328872,0.5468048],"study_design_scores_gemma":[0.00210984,0.00086288835,0.0069206795,0.0067155776,0.00097327377,0.0003693133,0.00078479166,0.0077356403,0.018062273,0.0068553174,0.9470011,0.0016092898],"about_ca_topic_score_codex":0.000009031795,"about_ca_topic_score_gemma":0.0000019147217,"teacher_disagreement_score":0.54519546,"about_ca_system_score_codex":0.00005733608,"about_ca_system_score_gemma":0.0004633032,"threshold_uncertainty_score":0.99999875},"labels":[],"label_agreement":null},{"id":"W2569936242","doi":"10.1016/j.jtho.2016.11.1531","title":"P2.06-038 An RCT of the Detection of Autoantibodies to Tumor Antigens in Lung Cancer Using the EarlyCDT-Lung Test in Scotland (ECLS) in 12 208 Study Subjects","year":2017,"lang":"en","type":"article","venue":"Journal of Thoracic Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Medicine; Lung cancer screening; Lung cancer; Stage (stratigraphy); Randomized controlled trial; National Lung Screening Trial; Internal medicine; Cancer; Lung; Incidence (geometry); Disease; Oncology","score_opus":0.027097108231497094,"score_gpt":0.4499857429287151,"score_spread":0.42288863469721805,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2569936242","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9959274,0.00049180683,0.000083623134,0.0023645936,0.00058277714,0.00046423983,0.0000016932514,0.000002559539,0.00008130991],"genre_scores_gemma":[0.9990868,0.00008136002,0.00041437446,0.00015287605,0.00021581353,0.0000039679207,1.6724746e-7,0.000016351743,0.00002831161],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99806404,0.0004435093,0.0007660477,0.00015631052,0.0003166981,0.00025339992],"domain_scores_gemma":[0.99818915,0.0003116577,0.0009550181,0.00032412913,0.0001359637,0.000084065134],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028842944,0.00012686536,0.0006748113,0.0003926091,0.00011821032,0.000023381119,0.00037990705,0.00007722788,0.000008613909],"category_scores_gemma":[0.0022173282,0.000075299715,0.00008262796,0.00023676235,0.0001889307,0.00015333887,0.00011564937,0.0009497061,1.5979994e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004456283,0.00048044132,0.93088657,0.00009284723,0.000041377756,0.00023259014,0.004113104,0.0013592489,0.051497713,7.889842e-7,0.000016185599,0.010833481],"study_design_scores_gemma":[0.001314809,0.0008624136,0.9715405,0.0009793505,0.00013508237,0.00023536723,0.0015188641,0.021271007,0.001978453,0.000019318679,0.00007503009,0.00006982232],"about_ca_topic_score_codex":0.00368191,"about_ca_topic_score_gemma":0.010659523,"teacher_disagreement_score":0.04951926,"about_ca_system_score_codex":0.0003237708,"about_ca_system_score_gemma":0.0004920029,"threshold_uncertainty_score":0.59482646},"labels":[],"label_agreement":null},{"id":"W2569983671","doi":"10.1016/j.jtho.2016.11.337","title":"OA19.01 A Standardized and Validation of Prognostic Gene Expression Signatures for Squamous Cell Lung Carcinoma by the SPECS Lung Consortium","year":2017,"lang":"en","type":"article","venue":"Journal of Thoracic Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre","funders":"","keywords":"Medicine; Lung cancer; Oncology; Internal medicine; Cohort; Gene signature; Pathology; Gene expression; Gene","score_opus":0.014401480905708022,"score_gpt":0.3816849195196446,"score_spread":0.3672834386139366,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2569983671","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97960734,0.003372763,0.010448561,0.0052141035,0.0005022831,0.00048033637,0.00001352742,0.00000572566,0.00035534456],"genre_scores_gemma":[0.99114203,0.00010219856,0.007962986,0.00019197873,0.00039037876,0.0000075457538,0.0000070247957,0.000018780333,0.00017708122],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99869657,0.00018962577,0.0005007492,0.0001383273,0.0002856558,0.00018910554],"domain_scores_gemma":[0.9974057,0.0007366165,0.0012195192,0.00022444593,0.00027247216,0.00014124038],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015639572,0.00011917015,0.00051540625,0.00008331306,0.00024068622,0.000043276363,0.00020679459,0.00013811117,0.000024691117],"category_scores_gemma":[0.0022254796,0.00007259218,0.00012484998,0.00002944219,0.00023904625,0.00009641294,0.000063523934,0.0005202529,1.480623e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005362176,0.00043114874,0.118406065,0.0009274624,0.00014722187,0.0002477517,0.0011998147,0.00012992838,0.80105436,0.000025166184,0.03911855,0.032950375],"study_design_scores_gemma":[0.014815437,0.0054962435,0.08136827,0.0008456622,0.0036264944,0.0023386762,0.00086520356,0.024853395,0.83691466,0.00070285646,0.027750589,0.0004225345],"about_ca_topic_score_codex":0.000009535473,"about_ca_topic_score_gemma":5.7361655e-7,"teacher_disagreement_score":0.037037805,"about_ca_system_score_codex":0.00009370375,"about_ca_system_score_gemma":0.0002796686,"threshold_uncertainty_score":0.29602233},"labels":[],"label_agreement":null},{"id":"W2570913926","doi":"10.1186/s12880-016-0172-6","title":"Dimensionality reduction-based fusion approaches for imaging and non-imaging biomedical data: concepts, workflow, and use-cases","year":2017,"lang":"en","type":"article","venue":"BMC Medical Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"U.S. Army Medical Research Acquisition Activity; Congressionally Directed Medical Research Programs; National Institute of Diabetes and Digestive and Kidney Diseases; National Institute on Aging; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; Genentech; National Institutes of Health; DOD Peer Reviewed Cancer Research Program; IXICO; Wallace H. Coulter Foundation; H. Lundbeck A/S; National Cancer Institute; Servier; Eisai; Northern California Institute for Research and Education; Pfizer; Biogen; BioClinica; National Science Foundation; Case Western Reserve University; Bristol-Myers Squibb; Cleveland Clinic; F. Hoffmann-La Roche; University of Southern California; Novartis Pharmaceuticals Corporation; U.S. Department of Defense; Eli Lilly and Company; Foundation for the National Institutes of Health; Case Comprehensive Cancer Center, Case Western Reserve University; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; Alzheimer's Association","keywords":"Computer science; Workflow; Context (archaeology); Dimensionality reduction; Sensor fusion; Artificial intelligence; Identification (biology); Data mining; Data integration; Machine learning; Modalities; Database","score_opus":0.07334934955420616,"score_gpt":0.36322643589348347,"score_spread":0.28987708633927733,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2570913926","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.58813876,0.005817421,0.32346624,0.07716132,0.0026643563,0.0017256761,0.00012413283,0.00039280002,0.00050927565],"genre_scores_gemma":[0.93476975,0.00019360722,0.060483232,0.0023556594,0.001458539,0.000046310266,0.00050337386,0.00008128179,0.00010825628],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961496,0.00014896077,0.00067134335,0.001259704,0.0010490938,0.0007212883],"domain_scores_gemma":[0.99483836,0.0021866478,0.00033656665,0.001328133,0.0001351061,0.0011751661],"candidate_categories":["metaresearch","metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.002746894,0.000410448,0.00070814206,0.00020339654,0.0013325388,0.0005365092,0.00054146163,0.00011614453,0.00007958692],"category_scores_gemma":[0.01717586,0.0003413526,0.00011828322,0.0000922274,0.0026492067,0.0008002037,0.00082867837,0.0007927487,0.0000042308466],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030704107,0.00028888293,0.5075096,0.00081156555,0.00006951345,0.00042404482,0.0001238345,0.000005345252,0.001462423,0.0003031677,0.016588463,0.47210613],"study_design_scores_gemma":[0.005420216,0.000033550896,0.12785053,0.0017589555,0.00029491787,0.0014777812,0.00034779,0.8435017,0.000062010266,0.00032652257,0.018479666,0.00044637124],"about_ca_topic_score_codex":0.00031791936,"about_ca_topic_score_gemma":0.00000824848,"teacher_disagreement_score":0.8434963,"about_ca_system_score_codex":0.00006577327,"about_ca_system_score_gemma":0.00062434026,"threshold_uncertainty_score":0.9999676},"labels":[],"label_agreement":null},{"id":"W2571825640","doi":"","title":"Integrative modelling of clinical, genomic, and microenvironmental factors for improved prediction of patient outcome in localized prostate cancer","year":2016,"lang":"en","type":"dissertation","venue":"TSpace (University of Toronto)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Prostate cancer; Outcome (game theory); Cancer; Computational biology; Medicine; Oncology; Biology; Internal medicine; Mathematics","score_opus":0.021702585627934836,"score_gpt":0.3071233222769837,"score_spread":0.2854207366490489,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2571825640","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.995543,0.0007888341,0.0019898103,0.00013462243,0.00019808867,0.0007465698,0.00021388393,0.000006456031,0.0003787485],"genre_scores_gemma":[0.99121726,0.0034884538,0.0034428677,0.000008077217,0.000017218412,0.0000015585713,0.00022114498,0.000019622683,0.0015838253],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99906105,0.000042307493,0.0003968901,0.00025582302,0.00011703765,0.00012691748],"domain_scores_gemma":[0.99889725,0.000103830374,0.00071941735,0.00012302009,0.000075206866,0.00008127293],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018077376,0.00015494492,0.0007600974,0.00006240054,0.00003394145,0.0000015923412,0.00007258865,0.00017080116,0.00029511566],"category_scores_gemma":[0.00005744527,0.0001348098,0.0001761859,0.000018685232,0.00016250658,0.000086182474,0.000027627679,0.00019066605,9.102272e-8],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.012537696,0.0007756066,0.48921353,0.003081693,0.0011600835,0.000006436199,0.0983833,0.0004424467,0.10461819,0.000046804813,0.00014133706,0.2895929],"study_design_scores_gemma":[0.011276907,0.0018706304,0.8368528,0.0022521543,0.0008988688,0.0000010897102,0.074078456,0.06948155,0.0022687786,0.000028863651,0.00065163715,0.0003383014],"about_ca_topic_score_codex":0.045823,"about_ca_topic_score_gemma":0.0034962352,"teacher_disagreement_score":0.34763923,"about_ca_system_score_codex":0.00021489394,"about_ca_system_score_gemma":0.0000989864,"threshold_uncertainty_score":0.96053094},"labels":[],"label_agreement":null},{"id":"W2578180933","doi":"10.1016/s0167-8140(15)40098-2","title":"SP-0100: Screening for metastases in high risk patients","year":2015,"lang":"en","type":"article","venue":"Radiotherapy and Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; University of Ottawa","funders":"","keywords":"Medicine; Oncology","score_opus":0.024578489286714245,"score_gpt":0.34169453459966037,"score_spread":0.3171160453129461,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2578180933","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9622954,0.0016433768,0.032183196,0.0028708638,0.00029411312,0.00041098762,0.000012158123,0.000030248948,0.00025963745],"genre_scores_gemma":[0.8885347,0.00096235797,0.10575431,0.0039546345,0.00044550622,0.000047128946,0.00006197088,0.000036448262,0.00020292494],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99913675,0.000118988304,0.00020909171,0.00020541379,0.000104648476,0.00022513299],"domain_scores_gemma":[0.99931955,0.000253477,0.00008674286,0.00010035748,0.000048452755,0.00019144625],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006986535,0.0001046185,0.00037658075,0.00012143317,0.000048463473,0.000010285187,0.000049196566,0.0000928487,0.000026110069],"category_scores_gemma":[0.00043690891,0.00008399478,0.00004444898,0.00008788019,0.000094249765,0.000046060733,0.0000122650745,0.0002490924,0.0000010350639],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00081604795,0.00021434412,0.4098353,0.000018865569,0.00007880897,0.000024982131,0.00056817086,0.000096690266,0.00008623645,0.0003185749,0.0036041539,0.58433783],"study_design_scores_gemma":[0.041406397,0.0057200175,0.27985755,0.00008350171,0.00017345835,0.000094859926,0.00024950752,0.03422464,0.00013012899,0.0012851392,0.636478,0.0002967863],"about_ca_topic_score_codex":0.00032904255,"about_ca_topic_score_gemma":0.000038008853,"teacher_disagreement_score":0.6328739,"about_ca_system_score_codex":0.00015272088,"about_ca_system_score_gemma":0.00008499947,"threshold_uncertainty_score":0.3425208},"labels":[],"label_agreement":null},{"id":"W2580425508","doi":"10.1186/s40644-017-0106-8","title":"CT texture analysis: a potential tool for prediction of survival in patients with metastatic clear cell carcinoma treated with sunitinib","year":2017,"lang":"en","type":"article","venue":"Cancer Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":95,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Sunnybrook Health Science Centre","funders":"","keywords":"Medicine; Sunitinib; Hazard ratio; Renal cell carcinoma; Proportional hazards model; Confidence interval; Internal medicine; Oncology; Progression-free survival; Clear cell renal cell carcinoma; Retrospective cohort study; Nuclear medicine; Overall survival; Urology","score_opus":0.009937996576670147,"score_gpt":0.26988570939694645,"score_spread":0.2599477128202763,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2580425508","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9935734,0.00010061657,0.0049770153,0.00034232409,0.00007337243,0.0004742876,0.0001082378,0.00002018771,0.00033053115],"genre_scores_gemma":[0.9982592,0.0000071304203,0.0012210713,0.00008567075,0.00007277099,0.00004327628,0.00015727642,0.00003354041,0.0001200728],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9988919,0.00003837843,0.0002474705,0.00028397288,0.0002844699,0.00025383345],"domain_scores_gemma":[0.999071,0.000031190008,0.00027134354,0.00034329738,0.00019809652,0.00008505684],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002232217,0.00015632136,0.00045402232,0.00021372485,0.00013648818,0.000050847135,0.00012039624,0.000015073392,0.000031982927],"category_scores_gemma":[0.00007055519,0.00011159516,0.00008816682,0.00019166594,0.00014443218,0.00015778081,0.000022453987,0.0002255367,2.9186427e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00094661437,0.00011448275,0.9900553,0.000161638,0.0002560443,0.000044151675,0.00013771569,0.0007702848,0.0002236292,0.0000038420603,0.00005671295,0.0072295414],"study_design_scores_gemma":[0.008827706,0.00024569497,0.93773735,0.00016852244,0.0018891282,0.0000046808927,0.00012852415,0.050442584,0.0003200094,0.0000038202843,0.00011886836,0.00011313794],"about_ca_topic_score_codex":0.0010401257,"about_ca_topic_score_gemma":0.000044725548,"teacher_disagreement_score":0.052318018,"about_ca_system_score_codex":0.00007552623,"about_ca_system_score_gemma":0.000111855305,"threshold_uncertainty_score":0.45507187},"labels":[],"label_agreement":null},{"id":"W2586281702","doi":"10.18383/j.tom.2016.00235","title":"Radiomics of Lung Nodules: A Multi-Institutional Study of Robustness and Agreement of Quantitative Imaging Features","year":2016,"lang":"en","type":"article","venue":"Tomography","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":125,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre","funders":"National Institute of Environmental Health Sciences; National Cancer Institute; National Heart, Lung, and Blood Institute; National Institutes of Health","keywords":"Pattern recognition (psychology); Correlation; Concordance correlation coefficient; Artificial intelligence; Feature (linguistics); Radiomics; Concordance; Segmentation; Robustness (evolution); Feature extraction; Computer science; Margin (machine learning); Mathematics; Statistics; Medicine; Machine learning","score_opus":0.013352418731822791,"score_gpt":0.30152254538886625,"score_spread":0.28817012665704345,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2586281702","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97554123,0.0014530559,0.02212784,0.00030212564,0.00008686378,0.00033075133,0.000014606268,0.000011884296,0.00013161925],"genre_scores_gemma":[0.98662734,0.000107537184,0.013176616,0.00002697091,0.000020424046,0.0000066672214,0.0000034179095,0.000009783761,0.000021243766],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99897707,0.00005286497,0.00035660667,0.0001929118,0.00028921687,0.00013136363],"domain_scores_gemma":[0.999222,0.00014021253,0.00021723492,0.00018237252,0.0001620575,0.00007612181],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034413705,0.00012191466,0.0004046774,0.00035611397,0.000037771908,0.0000033017657,0.00008346472,0.000027307276,0.0000146140055],"category_scores_gemma":[0.0001864933,0.00007551829,0.00010147926,0.00025909298,0.00047472538,0.000060664308,0.000045084875,0.00010853644,1.09512314e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030873684,0.001212229,0.9410747,0.00042616422,0.0004906601,0.000024399658,0.0025896074,0.00022610695,0.036719825,0.001583016,0.00018104998,0.0151635045],"study_design_scores_gemma":[0.010093801,0.00068962155,0.9655292,0.0011936746,0.0004086988,0.000054068794,0.0024807763,0.015260551,0.0039778305,0.00005502979,0.00006943071,0.0001873334],"about_ca_topic_score_codex":0.00015010616,"about_ca_topic_score_gemma":0.00000915351,"teacher_disagreement_score":0.032741994,"about_ca_system_score_codex":0.000013912236,"about_ca_system_score_gemma":0.000041425774,"threshold_uncertainty_score":0.30795464},"labels":[],"label_agreement":null},{"id":"W2586412306","doi":"10.1200/jco.2012.30.5_suppl.30","title":"Impact of multiparametric endorectal coil prostate MRI on disease reclassification among active surveillance candidates: A prospective cohort study.","year":2012,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto; Health Sciences Centre; University Health Network; Sunnybrook Health Science Centre","funders":"","keywords":"Medicine; Prostate cancer; Biopsy; Prospective cohort study; Radiology; Cohort; Magnetic resonance imaging; Cancer; Multiparametric MRI; Univariate analysis; Multivariate analysis; Internal medicine","score_opus":0.04596130864443774,"score_gpt":0.4580879608079175,"score_spread":0.41212665216347977,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2586412306","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99627507,0.00013425304,0.00014137028,0.0006658357,0.0007871791,0.0009431029,0.0000113737415,0.000012024265,0.0010298225],"genre_scores_gemma":[0.99816096,0.00028537904,0.000500141,0.00011850075,0.00078295456,0.000020969446,0.000008187696,0.000023919429,0.00009897291],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9961611,0.0009228742,0.0017553078,0.00024289165,0.00058900414,0.00032879997],"domain_scores_gemma":[0.9925416,0.0032356929,0.0024980356,0.00024737744,0.0005947541,0.0008825134],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005599236,0.00018117392,0.001494957,0.00028048147,0.000049071376,0.0000091261845,0.0001474625,0.00015905328,0.000050759558],"category_scores_gemma":[0.024287662,0.000115630726,0.00051094,0.00038501117,0.0003637698,0.00017337018,0.00003676684,0.0015613653,0.000007712402],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.011865884,0.006212381,0.9434031,0.00001772506,0.00084944424,0.0001192619,0.00040940542,0.00009409877,0.000042055635,0.000008072329,0.0005708359,0.036407705],"study_design_scores_gemma":[0.0067284536,0.0122128315,0.9779713,0.000078634985,0.0003356066,0.000053380754,0.00013316979,0.0020652087,0.000018487359,0.000025983803,0.00027574244,0.00010117644],"about_ca_topic_score_codex":0.00019943708,"about_ca_topic_score_gemma":0.000013920374,"teacher_disagreement_score":0.03630653,"about_ca_system_score_codex":0.0005154155,"about_ca_system_score_gemma":0.0011843663,"threshold_uncertainty_score":0.9839312},"labels":[],"label_agreement":null},{"id":"W2587481375","doi":"10.1158/1078-0432.ccr-16-1859","title":"CT Perfusion as an Early Biomarker of Treatment Efficacy in Advanced Ovarian Cancer: An ACRIN and GOG Study","year":2017,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lawson Health Research Institute; Mediprobe Research (Canada)","funders":"National Institute of General Medical Sciences; National Cancer Institute; American College of Radiology Imaging Network","keywords":"Ovarian cancer; Medicine; Biomarker; Oncology; Cancer; Internal medicine; Biology","score_opus":0.21568864824237696,"score_gpt":0.5951311830547018,"score_spread":0.3794425348123248,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2587481375","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99437946,0.0005002727,0.0000019999281,0.0031944867,0.00022247013,0.0010764824,0.0000072869466,0.000019054703,0.0005985111],"genre_scores_gemma":[0.9960714,0.002561927,0.00016674688,0.00008612682,0.00027922302,0.0001285271,0.0000059124422,0.000035437206,0.0006647059],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9969889,0.0006896972,0.00057580776,0.00070500997,0.00056947337,0.000471142],"domain_scores_gemma":[0.9975939,0.0004704679,0.00014811689,0.0010068113,0.0001924947,0.0005882231],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034786046,0.00016609342,0.0006188452,0.00018249314,0.00032196994,0.0000903499,0.00037219535,0.00008207168,0.00022837397],"category_scores_gemma":[0.0020807572,0.00012371884,0.00007810867,0.00015875288,0.0006926003,0.00018931045,0.00022081072,0.00088726106,0.0000058885357],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013051202,0.001454827,0.5464817,0.00002129492,0.000038299393,0.00014302597,0.0005171186,0.0000058946325,0.0012635702,0.000016721533,0.000020672773,0.44873175],"study_design_scores_gemma":[0.011296987,0.006889751,0.97617054,0.0002653869,0.000047548307,0.000006186234,0.00042497087,0.002856666,0.00014318169,0.000060822582,0.0017185607,0.00011939048],"about_ca_topic_score_codex":0.04620477,"about_ca_topic_score_gemma":0.0027583628,"teacher_disagreement_score":0.44861236,"about_ca_system_score_codex":0.00023041137,"about_ca_system_score_gemma":0.0006012303,"threshold_uncertainty_score":0.9601466},"labels":[],"label_agreement":null},{"id":"W2587683955","doi":"10.1097/pai.0000000000000470","title":"Evolution of Quality Assurance for Clinical Immunohistochemistry in the Era of Precision Medicine. Part 3: Technical Validation of Immunohistochemistry (IHC) Assays in Clinical IHC Laboratories","year":2017,"lang":"en","type":"article","venue":"Applied immunohistochemistry & molecular morphology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":64,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Calgary Laboratory Services; University of Calgary; Vancouver General Hospital; Canadiana.org; University Health Network; University of Toronto; University of British Columbia","funders":"American Association for Cancer Research","keywords":"Immunohistochemistry; Quality assurance; Medicine; Clinical Practice; Scope (computer science); Pathology; Medical physics; Computer science; Family medicine; External quality assessment","score_opus":0.02663656191227548,"score_gpt":0.40380860037263494,"score_spread":0.37717203846035946,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2587683955","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98695403,0.0033196518,0.004161792,0.001220432,0.00040966715,0.0009737238,0.00004243336,0.000024653467,0.002893626],"genre_scores_gemma":[0.99459404,0.00036319593,0.0041550966,0.00014872079,0.00017789197,0.00023258984,0.00023340363,0.000049344177,0.000045739904],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9936377,0.00035976365,0.0039122785,0.0008733068,0.0007380884,0.00047886296],"domain_scores_gemma":[0.9922366,0.0015316516,0.0028977306,0.0026588195,0.0005627709,0.000112394686],"candidate_categories":["metaresearch","metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.007942952,0.00042440975,0.0019131653,0.00009318609,0.00014909715,0.000013473711,0.0013463894,0.0008999034,0.000041596395],"category_scores_gemma":[0.013162398,0.00037617004,0.00048550262,0.00032084138,0.003292595,0.000070880546,0.00024486618,0.002004373,0.0000011679037],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016008336,0.00078476785,0.016748674,0.00071241945,0.000097666256,0.000026791959,0.00012315717,0.000023452516,0.9764079,0.0007041825,0.00080697564,0.0019632017],"study_design_scores_gemma":[0.013845665,0.00076144363,0.16697423,0.0018727719,0.00048119243,0.00018418452,0.0005984046,0.00015521942,0.81161916,0.0024085692,0.00041392003,0.0006852586],"about_ca_topic_score_codex":0.00027734874,"about_ca_topic_score_gemma":3.8825732e-7,"teacher_disagreement_score":0.16478874,"about_ca_system_score_codex":0.0003244577,"about_ca_system_score_gemma":0.0007271449,"threshold_uncertainty_score":0.99986905},"labels":[],"label_agreement":null},{"id":"W2587925559","doi":"10.1093/annonc/mdw376.08","title":"Development of a predictive radiomics signature for response to immune checkpoint inhibitors (ICIs) in patients with recurrent or metastatic squamous cell carcinoma of the head and neck (RM-SCCHN)","year":2016,"lang":"en","type":"article","venue":"Annals of Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; Princess Margaret Cancer Centre","funders":"","keywords":"Medicine; Radiomics; Radiology; Response Evaluation Criteria in Solid Tumors; Oncology; Clinical trial; Internal medicine; Phases of clinical research","score_opus":0.025677252376424303,"score_gpt":0.3219564177527042,"score_spread":0.2962791653762799,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2587925559","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9944279,0.00025610728,0.0003841344,0.003605739,0.00010522539,0.0011428364,0.00003241999,0.0000036797828,0.000041923395],"genre_scores_gemma":[0.992031,0.0000143471625,0.0075913914,0.00020516735,0.000014344774,0.000058171423,0.0000053282547,0.000017584463,0.000062676845],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9985104,0.0001489379,0.0006872784,0.00021085492,0.00022186596,0.00022066534],"domain_scores_gemma":[0.9984716,0.00055206363,0.0004141874,0.00019251977,0.000267054,0.00010253114],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010142504,0.00013628235,0.00057015364,0.00018069414,0.000029356186,0.0000014640262,0.000111564914,0.000078998084,0.0000075721982],"category_scores_gemma":[0.001247696,0.00006852755,0.00007325799,0.00020004541,0.0002034435,0.000031273874,0.00008409358,0.0001745375,1.8485572e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.16901128,0.005101507,0.180579,0.0015422031,0.00032309516,0.000033700046,0.018225746,0.00013911969,0.16346708,0.000037589918,0.0013279496,0.46021172],"study_design_scores_gemma":[0.018759942,0.019552024,0.8366828,0.0009173124,0.0001187796,0.000011437905,0.00044598762,0.00019345601,0.11783854,0.000050182414,0.005255603,0.00017391078],"about_ca_topic_score_codex":0.000023287244,"about_ca_topic_score_gemma":0.000028823068,"teacher_disagreement_score":0.6561038,"about_ca_system_score_codex":0.00008171926,"about_ca_system_score_gemma":0.000524447,"threshold_uncertainty_score":0.27944726},"labels":[],"label_agreement":null},{"id":"W2588483507","doi":"10.1093/eurpub/ckw174.143","title":"Personalized prostate cancer screening accounting for individual risk factors and preferences","year":2016,"lang":"en","type":"article","venue":"European Journal of Public Health","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Toronto General Hospital; Toronto Public Health","funders":"","keywords":"Prostate cancer; Medicine; Cancer; Prostate; Oncology; Internal medicine","score_opus":0.0742144597748369,"score_gpt":0.3466318645863885,"score_spread":0.27241740481155163,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2588483507","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9242324,0.0013484963,0.044829853,0.029050361,0.00019266253,0.00017251825,0.00002870974,0.000018691395,0.00012627893],"genre_scores_gemma":[0.9887068,0.0016370915,0.008078515,0.00083409745,0.0005376186,0.0000013510335,0.000003674087,0.000031985826,0.00016883091],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99785244,0.0007837877,0.00050436537,0.00015068657,0.00034491988,0.0003637726],"domain_scores_gemma":[0.9981644,0.00028285183,0.0007624606,0.00007141824,0.00020060262,0.00051826524],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010034155,0.00011896486,0.0003266631,0.00017487351,0.00019153979,0.00009156423,0.0001251569,0.000015329766,0.000048967166],"category_scores_gemma":[0.0022852605,0.00006262881,0.00008186278,0.00009008078,0.000117276606,0.00023467717,0.000038705395,0.00035701168,7.19078e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020222808,0.00001798435,0.3716068,0.00005233088,0.00009290618,0.000006957379,0.0019725503,7.344295e-7,0.000080658836,0.000024308465,0.0010292985,0.62509525],"study_design_scores_gemma":[0.0049136467,0.0009012458,0.85969573,0.0008563444,0.0000718426,0.000121607794,0.0011759959,0.00020089463,0.000015642852,0.000041684474,0.13187487,0.00013049418],"about_ca_topic_score_codex":0.000047453796,"about_ca_topic_score_gemma":0.0000020712198,"teacher_disagreement_score":0.6249648,"about_ca_system_score_codex":0.000050246617,"about_ca_system_score_gemma":0.00042218497,"threshold_uncertainty_score":0.3477658},"labels":[],"label_agreement":null},{"id":"W2589683331","doi":"10.1200/jco.2014.32.3_suppl.254","title":"Analysis of metabolic response (MR) by positron emission tomography (PET) compared with tumor response by computed tomography (CT) from MPACT, a phase III trial comparing <i>nab</i>-paclitaxel (<i>nab</i>-P) plus gemcitabine (G) versus G alone for patients (pts) with metastatic adenocarcinoma of the pancreas.","year":2014,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre","funders":"","keywords":"Medicine; Nuclear medicine; Positron emission tomography; Progressive disease; Response Evaluation Criteria in Solid Tumors; Internal medicine; Chemotherapy","score_opus":0.032710831983711136,"score_gpt":0.37477120889568666,"score_spread":0.34206037691197555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2589683331","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9896698,0.0011778703,0.0053636413,0.001942431,0.00053171464,0.0010923819,0.0001768041,0.000018430139,0.000026945454],"genre_scores_gemma":[0.990672,0.000039064067,0.008051781,0.0008259924,0.00018499869,0.000020151147,0.00013297169,0.00005214314,0.000020905536],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.9898797,0.0040601874,0.003769697,0.00053627393,0.0012310622,0.0005230672],"domain_scores_gemma":[0.97781473,0.014292409,0.0054805544,0.0006765372,0.00092079234,0.0008150019],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.008354138,0.00045354344,0.005342952,0.0007926417,0.00015117998,0.00003006508,0.00063753995,0.00012156242,0.000026465465],"category_scores_gemma":[0.0070542977,0.00026637132,0.0015362735,0.0016228234,0.00088967377,0.0001618898,0.000109691355,0.0013218519,2.9481365e-7],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.8239821,0.0054230774,0.15178043,0.000045385525,0.008505724,0.00007055147,0.0002219482,0.00037350718,0.0037947928,0.000005837503,0.0035144195,0.0022822253],"study_design_scores_gemma":[0.57797605,0.0626733,0.27777204,0.00052148855,0.026165951,0.00008705987,0.00026726726,0.043996446,0.00084427913,0.000027294387,0.009261553,0.00040726515],"about_ca_topic_score_codex":0.00035944546,"about_ca_topic_score_gemma":0.000031219315,"teacher_disagreement_score":0.24600606,"about_ca_system_score_codex":0.000117049436,"about_ca_system_score_gemma":0.00093677634,"threshold_uncertainty_score":0.99997884},"labels":[],"label_agreement":null},{"id":"W2589693254","doi":"10.1200/jco.2014.32.4_suppl.383","title":"Integrated comprehensive high-throughput kinomics profiling and whole exome sequencing of penile squamous cell cancer (PSCC).","year":2014,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency","funders":"","keywords":"Kinome; Exome sequencing; Exome; Cancer research; Computational biology; Kinase; Medicine; Biology; Genetics; Gene; Mutation","score_opus":0.07111603529556897,"score_gpt":0.421560107367877,"score_spread":0.35044407207230804,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2589693254","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9891314,0.0007658646,0.0029575895,0.0047746743,0.001296017,0.00014395316,0.0000038872113,0.0000112332145,0.00091536716],"genre_scores_gemma":[0.96537983,0.0003205398,0.030448854,0.0026065449,0.0010636037,0.0000018154379,0.0000048400734,0.000024829002,0.00014915752],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99680656,0.00042660694,0.0020164081,0.00021947727,0.0002848351,0.0002461228],"domain_scores_gemma":[0.9945013,0.0025302134,0.001834881,0.00016450386,0.0005994668,0.00036966763],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002294726,0.00015779989,0.0016326875,0.00012702041,0.00004727088,0.00001119748,0.00015689508,0.0002962998,0.000055378307],"category_scores_gemma":[0.00380376,0.000113165785,0.00023613239,0.00011708849,0.00041166064,0.00008837266,0.000076034325,0.0017539463,0.0000037633909],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0067968788,0.0023916413,0.28845,0.0015481882,0.00058450253,0.0012242249,0.001547426,0.0060008643,0.21596348,0.0015407882,0.009586252,0.46436575],"study_design_scores_gemma":[0.072138794,0.043323737,0.22135767,0.001406703,0.0035067843,0.0029980002,0.003269643,0.20757696,0.015934743,0.004257335,0.4230891,0.0011405292],"about_ca_topic_score_codex":0.0002467764,"about_ca_topic_score_gemma":0.0000120205195,"teacher_disagreement_score":0.46322522,"about_ca_system_score_codex":0.00016755315,"about_ca_system_score_gemma":0.0012385707,"threshold_uncertainty_score":0.7620121},"labels":[],"label_agreement":null},{"id":"W2589731098","doi":"10.1200/jco.2014.32.30_suppl.311","title":"Examining the use of PET scans in the diagnosis and management of non-small cell lung cancer patients.","year":2014,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Calgary; Canadian Partnership Against Cancer","funders":"","keywords":"Medicine; Lung cancer; Stage (stratigraphy); Radiology; Nuclear medicine; Internal medicine","score_opus":0.10073290450612446,"score_gpt":0.4264560150479975,"score_spread":0.3257231105418731,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2589731098","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9921083,0.00023859822,0.0004115103,0.0058856388,0.0003592701,0.00018842338,8.8597824e-7,9.094375e-7,0.0008064627],"genre_scores_gemma":[0.98911375,0.0042288294,0.003663454,0.0027436707,0.00019736921,0.0000070863384,4.9797114e-7,0.00000764904,0.00003767091],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9978136,0.00046759905,0.0012460125,0.000096131254,0.00025138666,0.00012531785],"domain_scores_gemma":[0.99418795,0.0043484364,0.0011104097,0.00014008283,0.00012544522,0.00008770235],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004087304,0.000071733615,0.00064867834,0.00006359362,0.000022733586,0.0000058945993,0.00017842017,0.000065467255,0.000017986185],"category_scores_gemma":[0.0016585813,0.000035256326,0.000117592324,0.00009592674,0.00021810338,0.000036518413,0.00006280401,0.0007263275,1.8407196e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015978755,0.00056262285,0.85704017,0.00014001201,0.000094952746,0.00004597754,0.00035831897,0.00023872427,0.000009659852,0.000036714122,0.0023083375,0.13900472],"study_design_scores_gemma":[0.0037874617,0.0021968614,0.9637795,0.00044440757,0.00040086353,0.000015772242,0.00020190295,0.0077639343,0.000008964247,0.000020235922,0.021343546,0.00003654551],"about_ca_topic_score_codex":0.00011316689,"about_ca_topic_score_gemma":0.000027077473,"teacher_disagreement_score":0.13896817,"about_ca_system_score_codex":0.000026518264,"about_ca_system_score_gemma":0.00011228866,"threshold_uncertainty_score":0.31555718},"labels":[],"label_agreement":null},{"id":"W2589753046","doi":"10.1200/jco.2016.34.4_suppl.296","title":"PET-CT compared to no PET-CT in the management of potentially resectable colorectal cancer liver metastases: The costs implications of a randomized controlled trial.","year":2016,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto General Hospital; University of Toronto; Ontario Clinical Oncology Group; McMaster University","funders":"","keywords":"Medicine; Randomized controlled trial; Randomization; Colorectal cancer; Confidence interval; Liver cancer; Christian ministry; Radiology; Nuclear medicine; Surgery; Cancer; Internal medicine","score_opus":0.04920606098488949,"score_gpt":0.44246365701602264,"score_spread":0.39325759603113314,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2589753046","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93722653,0.00059314125,0.0010895341,0.051925603,0.0010019138,0.0034212836,0.000010033156,0.000004429292,0.004727497],"genre_scores_gemma":[0.9918446,0.0024547128,0.002927767,0.0019077868,0.00036869897,0.00017011096,0.0000013915795,0.000012585845,0.00031237118],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.99255747,0.0029625143,0.0034938897,0.00017866949,0.0005655004,0.00024194094],"domain_scores_gemma":[0.9815242,0.014811302,0.0026163957,0.00028653452,0.00057303486,0.00018851421],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02133437,0.0001403057,0.0033427656,0.00015611971,0.000051391195,0.000010459758,0.00050128024,0.00002013605,0.00026580825],"category_scores_gemma":[0.012061666,0.000054168057,0.0010399086,0.00023201031,0.00048752988,0.00004934879,0.000086571374,0.0006597539,0.0000060292364],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.95433396,0.0019115604,0.0012995427,0.000048135422,0.002843893,0.0011398494,0.0000803934,0.00008828417,0.00056059164,0.0011277018,0.007489063,0.029077016],"study_design_scores_gemma":[0.96890557,0.003043305,0.009604244,0.00048904587,0.0025363602,0.0007108327,0.00019561559,0.0007459253,0.000029199218,0.00024562926,0.013415872,0.000078398436],"about_ca_topic_score_codex":0.0002399929,"about_ca_topic_score_gemma":0.00008592374,"teacher_disagreement_score":0.054618012,"about_ca_system_score_codex":0.0001292564,"about_ca_system_score_gemma":0.00078677176,"threshold_uncertainty_score":0.99626017},"labels":[],"label_agreement":null},{"id":"W2590445558","doi":"10.1200/jco.2012.30.30_suppl.40","title":"Development and validation of a digital Gleason score biomarker signature for risk stratification of patients with prostate cancer.","year":2012,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Genome British Columbia","funders":"","keywords":"Medicine; Prostate cancer; Prostatectomy; Oncology; Internal medicine; Receiver operating characteristic; Biomarker; Biochemical recurrence; Cutoff; Grading (engineering); Cancer","score_opus":0.059444363605281415,"score_gpt":0.4194303748471161,"score_spread":0.35998601124183466,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2590445558","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9966556,0.00036416188,0.0016928742,0.0007367266,0.00021977235,0.00025015115,0.000012398511,0.0000017534423,0.000066577144],"genre_scores_gemma":[0.9829864,0.00011566531,0.016652135,0.000059561444,0.00012862823,0.0000037482305,0.000022041966,0.00000795638,0.000023852213],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99851173,0.00006770395,0.0010216199,0.00007569809,0.00022053007,0.00010268882],"domain_scores_gemma":[0.99687576,0.00056182634,0.0018994752,0.000054827706,0.0004502497,0.00015783218],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015070365,0.00006439006,0.0005061885,0.00005644578,0.000020003545,0.0000045002002,0.00003851308,0.00011526507,0.000008810422],"category_scores_gemma":[0.0022826733,0.00003933051,0.000070678434,0.000061149556,0.00012999686,0.00013774823,0.000011145929,0.00031463563,1.267856e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0024526126,0.0005318169,0.64696705,0.0000732989,0.000141475,7.311067e-7,0.0002047769,0.000011837047,0.00019410612,0.000012097171,0.00018105347,0.34922916],"study_design_scores_gemma":[0.005181291,0.002476175,0.9821611,0.00020236986,0.00026315995,0.000006930641,0.00007730819,0.00020965119,0.00092478335,0.0000536892,0.008394866,0.000048695336],"about_ca_topic_score_codex":0.000003369015,"about_ca_topic_score_gemma":0.0000013343214,"teacher_disagreement_score":0.34918046,"about_ca_system_score_codex":0.000036693447,"about_ca_system_score_gemma":0.000497978,"threshold_uncertainty_score":0.2732738},"labels":[],"label_agreement":null},{"id":"W2590617369","doi":"10.1200/jco.2015.33.28_suppl.5","title":"Assessing the value of hepatic arterial phase CT imaging in patients with breast cancer.","year":2015,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Foothills Medical Centre","funders":"","keywords":"Medicine; Breast cancer; Radiology; Cancer; Liver cancer; Population; Metastasis; Internal medicine","score_opus":0.05838805657013771,"score_gpt":0.4940796037270539,"score_spread":0.43569154715691616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2590617369","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9836589,0.0000963357,0.0004931385,0.013987998,0.001221526,0.000114390736,0.0000015835082,0.0000032281716,0.00042289705],"genre_scores_gemma":[0.99532056,0.000030432318,0.002013224,0.0017331279,0.0008792508,0.000001239917,0.0000014096971,0.00001307444,0.00000768886],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99724156,0.0005053634,0.0015186685,0.00011037006,0.00044777142,0.00017628325],"domain_scores_gemma":[0.99682504,0.00090434944,0.0014632844,0.00012813367,0.0003989579,0.0002802482],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0042993585,0.00009309627,0.0009165678,0.000089169494,0.000023124188,0.00001602829,0.00015069383,0.00005063232,0.00002959144],"category_scores_gemma":[0.0031617347,0.000047952195,0.00013622016,0.0001293615,0.0003012071,0.00017276079,0.00003327829,0.000988154,8.8736385e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018683004,0.0012901106,0.75725037,0.000013140866,0.000064803746,0.00021695011,0.00009943416,0.00013196947,0.000033534172,0.000013762717,0.0005602313,0.23845737],"study_design_scores_gemma":[0.029563814,0.0026664662,0.95563537,0.00038081512,0.00025405074,0.00035229232,0.00017099646,0.008449202,0.0000060198877,0.00013317638,0.0023259614,0.00006181282],"about_ca_topic_score_codex":0.00012788828,"about_ca_topic_score_gemma":0.0000063665448,"teacher_disagreement_score":0.23839556,"about_ca_system_score_codex":0.0001345861,"about_ca_system_score_gemma":0.0017787585,"threshold_uncertainty_score":0.42930922},"labels":[],"label_agreement":null},{"id":"W2591334128","doi":"10.1200/jco.2016.34.7_suppl.93","title":"Successful completion of EGFR/ALK testing in non-squamous non-small cell lung cancer (non-sq NSCLC) with the implementation of reflex testing (RT) by pathologists.","year":2016,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Health Science Centre; North York General Hospital; University of Toronto; Health Sciences Centre; Pediatric Oncology Group","funders":"","keywords":"Medicine; Biomarker; Lung cancer; Oncology; Internal medicine; Stage (stratigraphy); Adenocarcinoma; Cancer","score_opus":0.06081244894910432,"score_gpt":0.4514777850534587,"score_spread":0.3906653361043544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2591334128","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98241836,0.00020481904,0.006783768,0.008407296,0.00029838743,0.00033695722,0.0000065938693,0.0000064331066,0.0015373896],"genre_scores_gemma":[0.9857198,0.00015632232,0.012624191,0.0009614481,0.00045293785,0.000009886063,0.000002738418,0.000025325417,0.000047367346],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99619466,0.00041247442,0.002411436,0.0002368754,0.0004217157,0.00032282315],"domain_scores_gemma":[0.9888932,0.0063705635,0.0036474047,0.00019921904,0.0007015414,0.00018804763],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005656045,0.00017268852,0.0012550656,0.00014187887,0.000054402764,0.0000075226217,0.00028409497,0.00019871163,0.000049872273],"category_scores_gemma":[0.0039766394,0.00008895222,0.00016401452,0.00031139486,0.00042910458,0.0000959072,0.00007418834,0.0010710881,9.0271595e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006234085,0.00037499543,0.7484892,0.00013659621,0.000052830554,0.00013351803,0.00025031908,0.000100878955,0.038207226,0.000003199918,0.0015096781,0.21011816],"study_design_scores_gemma":[0.014094875,0.0077098506,0.9690002,0.0011418277,0.00038157252,0.00018389105,0.0007214677,0.003968332,0.0015456671,0.00003988642,0.0010615188,0.00015090875],"about_ca_topic_score_codex":0.0010597679,"about_ca_topic_score_gemma":0.00017470129,"teacher_disagreement_score":0.220511,"about_ca_system_score_codex":0.00019961208,"about_ca_system_score_gemma":0.0012164676,"threshold_uncertainty_score":0.47606963},"labels":[],"label_agreement":null},{"id":"W2592274899","doi":"10.1158/1538-7445.sabcs16-p3-02-06","title":"Abstract P3-02-06: Magnetic resonance imaging (MRI) surveillance for patients with dense breasts and a previous breast cancer (BC) and/or high risk lesion","year":2017,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; McMaster University; University of Toronto; Sunnybrook Health Science Centre","funders":"","keywords":"Medicine; Breast cancer; Mammography; Breast MRI; Magnetic resonance imaging; Radiology; Stage (stratigraphy); Cancer; Retrospective cohort study; Breast imaging; Internal medicine","score_opus":0.022629211773663532,"score_gpt":0.3667564128170577,"score_spread":0.3441272010433941,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2592274899","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9844614,0.00797322,0.000059121787,0.005976481,0.00012010107,0.0010599042,0.00022004382,0.000032613658,0.000097092874],"genre_scores_gemma":[0.9879546,0.009714246,0.0006304892,0.0001409373,0.00036651976,0.00027798154,0.000016697655,0.00006590882,0.00083259965],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9977055,0.00009856306,0.00023634968,0.0006450129,0.00064011366,0.0006744306],"domain_scores_gemma":[0.99806094,0.00032857448,0.00016184725,0.00054847065,0.0005187123,0.00038143722],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010484073,0.00021773455,0.00038816908,0.00012390669,0.0008346101,0.00023042005,0.00023857229,0.000069555324,0.000119433236],"category_scores_gemma":[0.00060992053,0.00015104518,0.000036075224,0.00010727564,0.0007122608,0.00017601447,0.00017288026,0.00073116715,0.0000034160435],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001560314,0.00005628651,0.6266386,0.00027386268,0.00001647387,0.000038342223,0.0000814478,0.0000038179764,0.000146208,0.000007159547,0.0019843231,0.36919317],"study_design_scores_gemma":[0.0051237796,0.00030703156,0.98396474,0.0012306091,0.00003779214,0.000054976696,0.00002365357,0.0022074094,0.000033978067,0.00006800646,0.006751745,0.00019625758],"about_ca_topic_score_codex":0.013163713,"about_ca_topic_score_gemma":0.00091260875,"teacher_disagreement_score":0.36899692,"about_ca_system_score_codex":0.00016665565,"about_ca_system_score_gemma":0.00032901636,"threshold_uncertainty_score":0.9934077},"labels":[],"label_agreement":null},{"id":"W2592303973","doi":"10.1158/1538-7445.sabcs16-p1-03-01","title":"Abstract P1-03-01: An international multicenter study to evaluate reproducibility of automated scoring methods for assessment of Ki67 in breast cancer","year":2017,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Juravinski Hospital; Mount Sinai Hospital; Ontario Institute for Cancer Research","funders":"","keywords":"Reproducibility; Intraclass correlation; Medicine; Breast cancer; Nuclear proliferation; Medical physics; Cancer; Biopsy; Nuclear medicine; Pathology; Statistics; Mathematics; Internal medicine","score_opus":0.2166136544018778,"score_gpt":0.6358156388975048,"score_spread":0.419201984495627,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2592303973","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99355394,0.000054120104,0.0003048054,0.003803583,0.00045202632,0.0014472115,0.000035863035,0.000021963482,0.0003265095],"genre_scores_gemma":[0.98704946,0.000054860735,0.012198557,0.000042021155,0.00022238297,0.00032465896,0.0000059695385,0.000023645658,0.0000784452],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99743885,0.0003123266,0.00047699513,0.0007543466,0.00069440977,0.00032306535],"domain_scores_gemma":[0.9972701,0.00023222253,0.0001825186,0.0013687903,0.0007679304,0.0001784013],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015847158,0.00010290741,0.0003858974,0.0002648795,0.000113372305,0.000046812504,0.00049918337,0.00003584389,0.00026335113],"category_scores_gemma":[0.0033394767,0.00008578576,0.000058555474,0.00013595582,0.00017273746,0.0001610475,0.00023897819,0.00048979797,6.210914e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006840203,0.0009197711,0.7794078,0.00028248198,0.00012619385,0.00000708917,0.0010085677,0.0009150617,0.117513545,0.000009900622,0.0001379235,0.09898763],"study_design_scores_gemma":[0.0023624843,0.0001962763,0.8969678,0.0005192716,0.00002579257,0.0000010206762,0.0002954651,0.09409505,0.005322974,0.000021336695,0.00012777989,0.000064702486],"about_ca_topic_score_codex":0.012015209,"about_ca_topic_score_gemma":0.00037438984,"teacher_disagreement_score":0.11756002,"about_ca_system_score_codex":0.00046037167,"about_ca_system_score_gemma":0.00051520945,"threshold_uncertainty_score":0.9945639},"labels":[],"label_agreement":null},{"id":"W2593202421","doi":"10.1117/12.2255978","title":"Evaluation of an interactive ultrasound-based breast tumor contouring workflow","year":2017,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Contouring; Workflow; Computer science; Breast tumor; Ultrasound; Breast cancer; Cancer; Medicine; Radiology; Computer graphics (images); Database; Internal medicine","score_opus":0.014192085822981584,"score_gpt":0.28448490757437256,"score_spread":0.27029282175139097,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2593202421","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99334824,0.000049785154,0.00006693755,0.0028213924,0.0002771079,0.0006407249,0.000031174077,0.00004987686,0.002714731],"genre_scores_gemma":[0.93257403,0.000013235544,0.06660278,0.00012878321,0.00049051404,0.000081139806,0.000012056404,0.00005344019,0.00004400673],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972096,5.6635724e-8,0.0006590903,0.00037714397,0.0014284975,0.0003255917],"domain_scores_gemma":[0.9948266,0.00019888068,0.0008216824,0.00013065801,0.0038330199,0.00018914127],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023822787,0.00027534764,0.0005306142,0.000116081916,0.00015414853,0.00014730007,0.0008395541,0.00012596243,0.000031145333],"category_scores_gemma":[0.004265585,0.00022560821,0.00055526703,0.00011813248,0.000412241,0.0006450833,0.00010299474,0.00048745458,7.1190067e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00056098594,0.0005322608,0.0067071877,0.00081457314,0.0010841091,5.786421e-7,0.0003678564,0.0007209219,0.9378358,0.042280115,0.0007631268,0.008332489],"study_design_scores_gemma":[0.007300176,0.0007963771,0.049236007,0.0025195887,0.0015492718,0.00018322769,0.0014815144,0.7285284,0.2053198,0.002014414,0.00055138144,0.0005198275],"about_ca_topic_score_codex":0.00004273615,"about_ca_topic_score_gemma":3.213218e-7,"teacher_disagreement_score":0.732516,"about_ca_system_score_codex":0.00024664815,"about_ca_system_score_gemma":0.00012708934,"threshold_uncertainty_score":0.92000353},"labels":[],"label_agreement":null},{"id":"W2596739573","doi":"10.1182/blood.v128.22.1832.1832","title":"Texture Analysis on Computed Tomography Predicts the Outcome of Patients with Hodgkin Lymphoma","year":2016,"lang":"en","type":"article","venue":"Blood","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre","funders":"","keywords":"ABVD; Medicine; Dacarbazine; Procarbazine; Vincristine; Vinblastine; Chemotherapy regimen; Nuclear medicine; Radiology; Oncology; Chemotherapy; Internal medicine; Cyclophosphamide","score_opus":0.005148351974198391,"score_gpt":0.2320694353161337,"score_spread":0.2269210833419353,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2596739573","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99521565,0.000050186234,0.002316101,0.0014966426,0.000048629074,0.0001855951,0.000018644052,0.000040113886,0.0006284471],"genre_scores_gemma":[0.9984934,0.00000419966,0.0006342537,0.0006687718,0.000066560264,0.000004899677,0.00002077096,0.000014256681,0.00009292753],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99898237,0.000048943522,0.00021454114,0.00019231296,0.00039803822,0.00016380286],"domain_scores_gemma":[0.9991712,0.00015408068,0.00012602664,0.00036117077,0.00008746924,0.00010004556],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016714547,0.00011668792,0.00030696025,0.00019765738,0.00004748485,0.000007798636,0.00013204546,0.0000466928,0.000040166906],"category_scores_gemma":[0.00013291369,0.0000469942,0.00015006727,0.0005795052,0.00013390312,0.000021527176,0.000026349466,0.000099784105,0.0000038190337],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000089016685,0.0005911212,0.98330134,0.000017688733,0.001035981,0.000009403275,0.000061277075,0.000013974593,0.000073122304,0.00007139333,0.00019515521,0.014540515],"study_design_scores_gemma":[0.005810594,0.0004089077,0.9906931,0.000099727724,0.0015147455,0.0000031490058,0.000007123652,0.00034933144,0.00021566826,0.000015377074,0.0008127966,0.00006946778],"about_ca_topic_score_codex":0.00002150028,"about_ca_topic_score_gemma":0.000003163992,"teacher_disagreement_score":0.014471048,"about_ca_system_score_codex":0.000009337634,"about_ca_system_score_gemma":0.000018755452,"threshold_uncertainty_score":0.19163679},"labels":[],"label_agreement":null},{"id":"W2600305985","doi":"10.1016/j.ijrobp.2015.07.124","title":"Data Driven Radiogenomic Modeling of Radiation Induced Toxicities in Prostate Cancer","year":2015,"lang":"en","type":"article","venue":"International Journal of Radiation Oncology*Biology*Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre","funders":"","keywords":"Radiogenomics; Medicine; Prostate cancer; Logistic regression; Radiation therapy; Prostate; Single-nucleotide polymorphism; Internal medicine; Oncology; Receiver operating characteristic; Urology; Cancer; Radiology; Genotype","score_opus":0.05539450377262,"score_gpt":0.38078007746235193,"score_spread":0.3253855736897319,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2600305985","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97990394,0.0012154395,0.011380119,0.004903939,0.00199511,0.00020928375,0.00008031298,0.000018012148,0.0002938566],"genre_scores_gemma":[0.9928805,0.001390797,0.003096011,0.0006411424,0.0017247027,0.000006520077,0.0002142175,0.000026783928,0.000019272433],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981156,0.00020222404,0.0009190092,0.00022599573,0.00033566792,0.00020152029],"domain_scores_gemma":[0.997972,0.00017989527,0.0009487695,0.00021027218,0.00053102575,0.00015800157],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011538841,0.0001511882,0.0005286482,0.00029751434,0.000027136492,0.000018692635,0.0005146701,0.00014288793,0.000017384367],"category_scores_gemma":[0.00089692994,0.00013895123,0.00009482316,0.0001736246,0.00013536157,0.00037932096,0.00010848008,0.00061561645,0.0000039672304],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00081868184,0.0004300879,0.48455486,0.000027266597,0.0006341553,0.000071899565,0.0029028412,0.13157256,0.013060812,0.0023785736,0.0012043704,0.3623439],"study_design_scores_gemma":[0.010132544,0.00074346975,0.0076895244,0.0002052707,0.00015095373,0.00018706931,0.00040910227,0.9670361,0.0013216278,0.005550862,0.0063669668,0.00020647871],"about_ca_topic_score_codex":0.00017533061,"about_ca_topic_score_gemma":0.0000116284355,"teacher_disagreement_score":0.8354636,"about_ca_system_score_codex":0.0008358098,"about_ca_system_score_gemma":0.0013324055,"threshold_uncertainty_score":0.56662667},"labels":[],"label_agreement":null},{"id":"W2600642189","doi":"10.1038/s41598-017-10371-5","title":"Radiomics strategies for risk assessment of tumour failure in head-and-neck cancer","year":2017,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":545,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hôpital Maisonneuve-Rosemont; Jewish General Hospital; Université de Montréal; Hôpital Notre-Dame; Hôpital Fleurimont; McGill University Health Centre","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Radiomics; Medicine; Head and neck cancer; Oncology; Head and neck; Internal medicine; Radiation therapy; Risk assessment; Risk stratification; Radiology; Surgery; Computer science","score_opus":0.01897411251840962,"score_gpt":0.3615030147370685,"score_spread":0.34252890221865884,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2600642189","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99283546,0.00018039571,0.0014130225,0.002033962,0.0019505332,0.00039950188,0.0000050664908,0.00001505121,0.0011669876],"genre_scores_gemma":[0.98801625,0.00005280798,0.011133857,0.00003015485,0.00009569901,0.000034275574,0.000013864323,0.000013964715,0.00060913566],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9986078,0.0000208846,0.00041650818,0.0004340578,0.00029200938,0.00022870612],"domain_scores_gemma":[0.99856657,0.000038241014,0.000541723,0.00060562714,0.00012933937,0.0001185115],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017613783,0.000104271596,0.0003285141,0.00013106814,0.00031828496,0.00027846274,0.0001052346,0.000052826806,0.00002309753],"category_scores_gemma":[0.000619273,0.00008459455,0.00007655028,0.000070623784,0.0003881195,0.00018133786,0.000056960347,0.00024497844,2.1362591e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026066182,0.000106432235,0.9491409,0.00029738605,0.00004826322,0.00024269585,0.00044820085,0.00047013815,0.031988494,0.00083709724,0.0056486363,0.010745678],"study_design_scores_gemma":[0.0020751604,0.00013446233,0.8945228,0.0007502651,0.00014612325,0.00029584387,0.00047586675,0.053033583,0.0019984005,0.01788308,0.02844293,0.000241485],"about_ca_topic_score_codex":0.0006725205,"about_ca_topic_score_gemma":0.00030887383,"teacher_disagreement_score":0.05461811,"about_ca_system_score_codex":0.00005474182,"about_ca_system_score_gemma":0.000532482,"threshold_uncertainty_score":0.34496656},"labels":[],"label_agreement":null},{"id":"W2600850467","doi":"10.1200/jco.2012.30.15_suppl.6049","title":"Positron emission tomography/computed tomography (PET/CT) for the diagnosis of recurrent cancer (PETREC): A multicenter, prospective cohort study.","year":2012,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Hamilton Health Sciences; University of Toronto; University Health Network; Ontario Clinical Oncology Group; Thunder Bay Regional Health Sciences Centre; Sunnybrook Health Science Centre; Juravinski Cancer Centre; London Health Sciences Centre; McMaster University","funders":"","keywords":"Medicine; Positron emission tomography; Prospective cohort study; Radiology; Breast cancer; Esophageal cancer; Lymphoma; PET-CT; Lung cancer; Cancer; Nuclear medicine; Internal medicine","score_opus":0.049648685293893165,"score_gpt":0.4591316398619256,"score_spread":0.40948295456803246,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2600850467","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9825048,0.0050605596,0.00077486545,0.006024401,0.003987257,0.001472198,0.0000057429693,0.00001285184,0.00015736012],"genre_scores_gemma":[0.9918733,0.0016982828,0.003687749,0.0008251253,0.0017473495,0.000107323474,0.0000022657625,0.000023436416,0.000035131612],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9963967,0.00050065166,0.002015546,0.00021679659,0.0005175048,0.00035280516],"domain_scores_gemma":[0.9918753,0.0048781065,0.0019362858,0.0002263022,0.0005962388,0.00048777426],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005953923,0.00018085557,0.0014160647,0.00021424245,0.00009816845,0.000011083809,0.00027381655,0.00005985212,0.00006232327],"category_scores_gemma":[0.0042609563,0.00010093954,0.0009030078,0.00032263968,0.00026197082,0.00010865265,0.00007892921,0.0013317134,7.113903e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002241951,0.005824927,0.85654926,0.000049662925,0.0012984589,0.0000606763,0.00018738011,0.000012875998,0.000035118606,0.000013999353,0.005103647,0.12862203],"study_design_scores_gemma":[0.008133889,0.0075909123,0.9558063,0.000322453,0.0017698293,0.00016988027,0.00022934418,0.0016489547,0.00010692517,0.000036613674,0.024086643,0.000098224125],"about_ca_topic_score_codex":0.00010728963,"about_ca_topic_score_gemma":0.000016007172,"teacher_disagreement_score":0.1285238,"about_ca_system_score_codex":0.00012208837,"about_ca_system_score_gemma":0.0003584375,"threshold_uncertainty_score":0.5785706},"labels":[],"label_agreement":null},{"id":"W2601000485","doi":"10.1038/srep45639","title":"Multi-scale radiomic analysis of sub-cortical regions in MRI related to autism, gender and age","year":2017,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":71,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada","keywords":"Spatial normalization; Corpus callosum; White matter; Autism; Choroid plexus; Medicine; Psychology; Neuroscience; Biology; Magnetic resonance imaging; Anatomy; Developmental psychology; Radiology; Central nervous system","score_opus":0.02209642555063761,"score_gpt":0.32594937757012876,"score_spread":0.30385295201949114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2601000485","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9941965,0.000119596596,0.0021797,0.0013381008,0.0010541078,0.00024658316,0.0000011450691,0.000026046715,0.0008382546],"genre_scores_gemma":[0.9926623,0.000015507567,0.00559756,0.000064004606,0.000010643497,0.000006298364,0.000027806793,0.000013152193,0.0016027235],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9980659,0.000048897717,0.0006001661,0.0006402076,0.0003675529,0.0002772776],"domain_scores_gemma":[0.9981529,0.000039965256,0.0002717492,0.0011645743,0.00005284606,0.0003179381],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019447985,0.00011201295,0.00048910594,0.0006606555,0.00031673774,0.00012710017,0.00012039578,0.000082860635,0.000038571507],"category_scores_gemma":[0.0010677313,0.00009607308,0.00013767208,0.0005958572,0.00065556786,0.00008289575,0.00011458911,0.00031099678,0.0000036343438],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025586764,0.00022928805,0.79719466,0.000050435294,0.00034305462,0.0040450175,0.002725473,0.00061975943,0.19039835,0.00018675442,0.00226247,0.0019191823],"study_design_scores_gemma":[0.00044832716,0.00001888518,0.9419453,0.000071662,0.00046716418,0.00027009187,0.00007105733,0.054164276,0.00079146033,0.00051140925,0.0011315591,0.000108772285],"about_ca_topic_score_codex":0.00015598902,"about_ca_topic_score_gemma":0.000073042276,"teacher_disagreement_score":0.18960689,"about_ca_system_score_codex":0.00004602868,"about_ca_system_score_gemma":0.0000848801,"threshold_uncertainty_score":0.39177465},"labels":[],"label_agreement":null},{"id":"W2602288447","doi":"10.1186/s41512-017-0011-4","title":"Erratum to: Methods for evaluating medical tests and biomarkers","year":2017,"lang":"en","type":"erratum","venue":"Diagnostic and Prognostic Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University; McGill University Health Centre; University of Calgary; McGill University; South Health Campus; Jewish General Hospital; McMaster University; Population Health Research Institute","funders":"Institute of Genetics; School of Public Health, Imperial College London; Klinisk Institut, Syddansk Universitet; Medical Research Council; Institute of Psychiatry, Psychology and Neuroscience, King’s College London; Syddansk Universitet; Odense Universitetshospital; KU Leuven; iMinds; Newcastle upon Tyne Hospitals NHS Foundation Trust; Cambridge University Hospitals; Loughborough University; University of Glasgow; Warwick Medical School; Universiteit van Amsterdam; Newcastle University; Albert-Ludwigs-Universität Freiburg; King's College London; University of Oxford; University of Warwick; Vrije Universiteit Amsterdam; Imperial College London; University of Exeter; Cancer Research UK; University of Southampton; University College London; University of Cambridge; British Heart Foundation; National Institute for Health and Care Excellence; University of Leeds; National Institute for Health and Care Research; Inselspital, Universitätsspital Bern; King's College Hospital NHS Foundation Trust","keywords":"Medical physics; Computer science; Psychology; Medicine","score_opus":0.12967390453280553,"score_gpt":0.5536366208162352,"score_spread":0.4239627162834297,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2602288447","genre_codex":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026413698,0.2602126,0.085366726,0.32728618,0.06935165,0.045075893,0.00040127867,0.00086421927,0.18502775],"genre_scores_gemma":[0.036478754,0.06533086,0.5251108,0.009375921,0.02354522,0.009917744,0.003576461,0.001460301,0.32520393],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99410325,0.0009055931,0.0006495514,0.0012629272,0.0018226678,0.001255995],"domain_scores_gemma":[0.95580214,0.0401616,0.00020832186,0.00085753936,0.0009427473,0.0020276324],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.016914222,0.000480704,0.001130411,0.0006403398,0.001017786,0.0004705207,0.00054425345,0.00091899984,0.00014456698],"category_scores_gemma":[0.47610697,0.00038849912,0.00014169166,0.00025248682,0.0011971197,0.00007333883,0.00074609445,0.0036597177,0.000025590858],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000093215334,0.00006951162,0.0057847425,0.0013957422,0.00019134834,0.00018539758,0.00018674893,1.381142e-7,0.0000311206,0.00011764197,0.5358881,0.4560563],"study_design_scores_gemma":[0.0031786405,0.0035562231,0.058178794,0.012213464,0.0007721964,0.0006936663,0.00019591863,0.041571744,0.000013933133,0.0059358785,0.8728915,0.0007980636],"about_ca_topic_score_codex":0.00024819822,"about_ca_topic_score_gemma":0.000014824895,"teacher_disagreement_score":0.45919275,"about_ca_system_score_codex":0.00008879844,"about_ca_system_score_gemma":0.0020005913,"threshold_uncertainty_score":0.9998567},"labels":[],"label_agreement":null},{"id":"W2603635611","doi":"10.1161/str.47.suppl_1.161","title":"Abstract 161: Prediction of Thrombolysis-induced Parenchymal Hemorrhage in Patients With Acute Ischemic Stroke: Use of MR Perfusion and Diffusion Biomarkers","year":2016,"lang":"en","type":"article","venue":"Stroke","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Stuart Olson (Canada)","funders":"","keywords":"Medicine; Thrombolysis; Receiver operating characteristic; Effective diffusion coefficient; Infarction; Univariate analysis; Stroke (engine); Logistic regression; Internal medicine; Area under the curve; Penumbra; Perfusion scanning; Diffusion MRI; Nuclear medicine; Perfusion; Cardiology; Radiology; Multivariate analysis; Magnetic resonance imaging; Ischemia; Myocardial infarction","score_opus":0.009345268771386266,"score_gpt":0.2373500618724685,"score_spread":0.2280047931010822,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2603635611","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9989101,0.00002569508,0.00018398555,0.00018875697,0.000081940416,0.00025390866,0.00010861894,0.000018623208,0.0002283241],"genre_scores_gemma":[0.9985094,0.000066950684,0.0011930662,0.0000219458,0.0000278426,0.000004079929,0.000041953415,0.000018493578,0.00011623102],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99876773,0.000027513026,0.00035185702,0.000256614,0.00038275233,0.00021355806],"domain_scores_gemma":[0.9992806,0.00008530629,0.00020479092,0.00022614212,0.00008163445,0.0001215655],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017839562,0.00014731492,0.00035117168,0.00018387762,0.000030555217,0.0000071255913,0.00005759346,0.00009267924,0.00005670897],"category_scores_gemma":[0.00016761181,0.000089602014,0.00005576617,0.00010832156,0.00013102301,0.00015826727,0.000051805495,0.00019081778,8.334198e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034673244,0.00012019508,0.4991891,0.00004246882,0.000049626407,0.000007505328,0.00006906223,6.7364675e-7,0.48073503,0.0000010058756,0.000047671714,0.019390903],"study_design_scores_gemma":[0.00483377,0.0005324945,0.9655216,0.0004300879,0.00014277447,0.000007670254,0.000049948056,0.0009857535,0.027358871,0.0000013033468,0.00005260056,0.00008314068],"about_ca_topic_score_codex":0.00015163151,"about_ca_topic_score_gemma":0.0000051968454,"teacher_disagreement_score":0.46633247,"about_ca_system_score_codex":0.00004637211,"about_ca_system_score_gemma":0.000051734765,"threshold_uncertainty_score":0.3653864},"labels":[],"label_agreement":null},{"id":"W2603682673","doi":"10.1200/jco.2017.35.6_suppl.e590","title":"Serial FDG-PET imaging of metastatic prostate cancers reveals intrapatient intermetastases polyclonality through same patient heterogeneous responses to systemic therapy.","year":2017,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Medicine; Prostate cancer; Metastasis; Oncology; Systemic therapy; Tumour heterogeneity; Cancer; Univariate analysis; Internal medicine; Pathology; Multivariate analysis; Breast cancer","score_opus":0.09134491045388134,"score_gpt":0.4719387357795939,"score_spread":0.38059382532571256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2603682673","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98544437,0.00094338774,0.00045689978,0.009832664,0.002620181,0.00051811605,0.000041128704,0.0000104089695,0.00013284627],"genre_scores_gemma":[0.9814563,0.00081727793,0.011996731,0.00504577,0.0005891523,0.000010909834,0.0000045014594,0.000030421657,0.000048970636],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99406296,0.0012857204,0.003367582,0.00030580058,0.00061146886,0.00036643932],"domain_scores_gemma":[0.99201757,0.0016899379,0.004523652,0.00053544616,0.0007380759,0.00049529935],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0046910364,0.00023002991,0.0021192136,0.00014131989,0.00013770904,0.000045297293,0.0004312577,0.0000754208,0.00006977666],"category_scores_gemma":[0.017872544,0.00015764037,0.00053075684,0.00008754663,0.0005117989,0.0001882733,0.00015909599,0.0009253172,0.0000040006476],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.05102685,0.002185974,0.2052504,0.000387463,0.0020399631,0.005356692,0.0031465997,0.0013041251,0.011779814,0.00008244095,0.0066899983,0.7107497],"study_design_scores_gemma":[0.079502285,0.15014033,0.54457045,0.010766901,0.004523827,0.024758069,0.004229022,0.006791831,0.009712274,0.004734413,0.15821129,0.002059342],"about_ca_topic_score_codex":0.00044799357,"about_ca_topic_score_gemma":0.00001835853,"teacher_disagreement_score":0.70869035,"about_ca_system_score_codex":0.0002806056,"about_ca_system_score_gemma":0.0016868606,"threshold_uncertainty_score":0.9904003},"labels":[],"label_agreement":null},{"id":"W2603978903","doi":"10.1016/j.ijrobp.2015.07.338","title":"NRG Oncology/RTOG 0525 Role of Machine Learning Analytic Tools for Survival Prediction of GBM Patients Using Clinical Parameters","year":2015,"lang":"en","type":"article","venue":"International Journal of Radiation Oncology*Biology*Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hôtel-Dieu de Québec; Jewish General Hospital; University of Toronto; McGill University; University Health Network","funders":"National Cancer Institute; Merck Sharp and Dohme","keywords":"Medicine; Receiver operating characteristic; Machine learning; Recursive partitioning; Confidence interval; Artificial intelligence; Internal medicine; Logistic regression; Predictability; Oncology; Support vector machine; Proportional hazards model; Decision tree; Artificial neural network; Statistics; Computer science; Mathematics","score_opus":0.06910197621512155,"score_gpt":0.40156268512157856,"score_spread":0.332460708906457,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2603978903","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.930094,0.0002610014,0.064954095,0.0007380472,0.0031354793,0.00030522028,0.00009287293,0.000020691687,0.000398576],"genre_scores_gemma":[0.9782948,0.00022762993,0.01959559,0.00027816332,0.0013112917,0.0000043477967,0.00024367879,0.000030553958,0.000013932469],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968909,0.0005416756,0.0016538796,0.00023776025,0.00044935828,0.00022644688],"domain_scores_gemma":[0.99362314,0.0016397091,0.0025495603,0.00013695788,0.0018171137,0.00023352804],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027337375,0.00018183044,0.0009400468,0.00024881167,0.000048351194,0.000015801395,0.00030938836,0.00030813966,0.000012579526],"category_scores_gemma":[0.0070189033,0.00016184669,0.00041599764,0.000172555,0.0003892482,0.0002774624,0.000069940776,0.0008333499,0.0000020279247],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012668173,0.00078951684,0.77327234,0.000018049013,0.0008126723,0.0000061716137,0.00033268228,0.008176514,0.0020966104,0.0012332574,0.00018158463,0.21181376],"study_design_scores_gemma":[0.041796003,0.016703533,0.12539272,0.00036957226,0.0016216375,0.00020662705,0.000746584,0.7544871,0.0020286704,0.01649548,0.039737176,0.00041490537],"about_ca_topic_score_codex":0.00004707259,"about_ca_topic_score_gemma":0.0000015920818,"teacher_disagreement_score":0.7463106,"about_ca_system_score_codex":0.0006249345,"about_ca_system_score_gemma":0.000940403,"threshold_uncertainty_score":0.840279},"labels":[],"label_agreement":null},{"id":"W2604709294","doi":"10.1200/jco.2004.22.90140.3772","title":"Linear regression is a reproducible model of tumor response to pre-operative endorectal brachytherapy","year":2004,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; McGill University Health Centre","funders":"","keywords":"Medicine; Brachytherapy; Linear regression; Oncology; Radiology; Internal medicine; Radiation therapy; Statistics","score_opus":0.08667919022008272,"score_gpt":0.5030077746902517,"score_spread":0.41632858447016896,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2604709294","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93280435,0.00022144719,0.007442445,0.058323264,0.0005457396,0.00021732542,0.0000026452674,0.000010165716,0.0004326205],"genre_scores_gemma":[0.88912475,0.0002224039,0.0977383,0.01134518,0.00092319585,0.0000029503417,6.836721e-7,0.000024229275,0.00061829423],"study_design_codex":"design_other","study_design_gemma":"nonrandomized_trial","domain_scores_codex":[0.99636,0.0005066622,0.0021234113,0.0003111027,0.00047546646,0.00022335688],"domain_scores_gemma":[0.99607056,0.0012395193,0.001284278,0.0003413192,0.00054585555,0.0005184849],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.007975504,0.0001440041,0.0014193717,0.00019685629,0.000045315777,0.000005822326,0.00019494745,0.00019613732,0.00006972297],"category_scores_gemma":[0.02169492,0.00009184433,0.0004314843,0.00019444386,0.00021737517,0.000094907264,0.000061625884,0.0015048698,0.000009203383],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.24583137,0.008866279,0.0299094,0.00015006939,0.0011147048,0.003372355,0.013456384,0.04915484,0.31443942,0.00037304996,0.017160738,0.3161714],"study_design_scores_gemma":[0.123592764,0.2348833,0.17277204,0.0058490834,0.0015133313,0.01010036,0.0011127143,0.17077227,0.11211651,0.012835747,0.15318441,0.0012674899],"about_ca_topic_score_codex":0.000022408962,"about_ca_topic_score_gemma":0.0000020314142,"teacher_disagreement_score":0.31490391,"about_ca_system_score_codex":0.00013549668,"about_ca_system_score_gemma":0.0026355141,"threshold_uncertainty_score":0.98654574},"labels":[],"label_agreement":null},{"id":"W2606926876","doi":"10.1038/srep46349","title":"Radiomics-based Prognosis Analysis for Non-Small Cell Lung Cancer","year":2017,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":277,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; University of Toronto; Sunnybrook Health Science Centre","funders":"","keywords":"Radiomics; Feature selection; Redundancy (engineering); Random forest; Lung cancer; Feature (linguistics); Artificial intelligence; Computer science; Medicine; Pattern recognition (psychology); Oncology","score_opus":0.016836356805608986,"score_gpt":0.31903343530091777,"score_spread":0.3021970784953088,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2606926876","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95818007,0.0003044317,0.029474009,0.0033657402,0.0053053303,0.0010820021,0.0000066607913,0.00006812902,0.0022136453],"genre_scores_gemma":[0.97929317,0.000008846494,0.0111876605,0.00022501807,0.00025599345,0.0001901669,0.000097931,0.000030357456,0.008710871],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978816,0.00001597691,0.00045459814,0.0008300446,0.0004000731,0.0004176975],"domain_scores_gemma":[0.9973819,0.0000500881,0.00060631306,0.0013916031,0.0002687285,0.0003013427],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018263282,0.00016805773,0.00045135547,0.00046531897,0.000988499,0.0005762182,0.00023246698,0.000079773046,0.00012001644],"category_scores_gemma":[0.0005785862,0.00013989893,0.00043654843,0.00039906523,0.00031442987,0.000089304485,0.00005599873,0.00020206627,0.0000025461575],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027635264,0.00014252156,0.9579125,0.00028599243,0.0003264614,0.00029440958,0.00015133178,0.0011117031,0.014426946,0.000006679339,0.020022016,0.005291822],"study_design_scores_gemma":[0.0019289325,0.00007732679,0.12899147,0.00029220947,0.004482311,0.00005670454,0.000036120324,0.7388674,0.046544425,0.00023887421,0.07800521,0.00047901276],"about_ca_topic_score_codex":0.00022052058,"about_ca_topic_score_gemma":0.000036231715,"teacher_disagreement_score":0.828921,"about_ca_system_score_codex":0.000096282245,"about_ca_system_score_gemma":0.0004842303,"threshold_uncertainty_score":0.7602836},"labels":[],"label_agreement":null},{"id":"W2606954399","doi":"10.1038/srep45733","title":"A priori Prediction of Neoadjuvant Chemotherapy Response and Survival in Breast Cancer Patients using Quantitative Ultrasound","year":2017,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":71,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; University of Toronto; Sunnybrook Health Science Centre","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto; Canadian Institutes of Health Research; Terry Fox Foundation","keywords":"Breast cancer; Medicine; Chemotherapy; Neoadjuvant therapy; Oncology; Ultrasound; Breast ultrasound; Radiology; Internal medicine; Cancer; Mammography","score_opus":0.020455566620786333,"score_gpt":0.3320946141403754,"score_spread":0.31163904751958904,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2606954399","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99642164,0.00008191496,0.00008194367,0.0005967957,0.0024505497,0.0002451511,0.000011742366,0.000011612611,0.000098683566],"genre_scores_gemma":[0.9989125,0.000027163851,0.0007681934,0.00002357817,0.000038346196,0.0000037310197,0.000009988272,0.000013274954,0.00020320203],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99857825,0.00006605164,0.00038017053,0.00039254647,0.00040458565,0.000178396],"domain_scores_gemma":[0.9987662,0.00005842033,0.00043957526,0.00044724467,0.00018466174,0.00010392941],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002080377,0.000095769676,0.00025511713,0.00015434617,0.00024498207,0.00010796286,0.000060965307,0.00004690489,0.000025907739],"category_scores_gemma":[0.0010635809,0.00007956327,0.000040340572,0.0001129163,0.000505013,0.00016742169,0.000034318673,0.00016054319,2.7169432e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003691814,0.000106973624,0.89277405,0.000036544945,0.000018965631,0.000072700495,0.0008756305,0.000025088966,0.10141947,0.0000051173683,0.00014255525,0.004153737],"study_design_scores_gemma":[0.0009821167,0.000056635996,0.99147683,0.000336402,0.00002413906,0.00017488576,0.000090138994,0.005186719,0.0010187195,0.00014577586,0.00044364392,0.000064017244],"about_ca_topic_score_codex":0.0009184203,"about_ca_topic_score_gemma":0.000019223093,"teacher_disagreement_score":0.100400746,"about_ca_system_score_codex":0.000075714874,"about_ca_system_score_gemma":0.00020545088,"threshold_uncertainty_score":0.32444963},"labels":[],"label_agreement":null},{"id":"W2612844530","doi":"10.1007/978-3-319-59876-5_7","title":"Discovery Radiomics for Pathologically-Proven Computed Tomography Lung Cancer Prediction","year":2017,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":41,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Health Science Centre; Health Sciences Centre; University of Toronto; University of Waterloo","funders":"","keywords":"Radiomics; Convolutional neural network; Computer science; Artificial intelligence; Lung cancer; Data set; Ground truth; Deep learning; Pattern recognition (psychology); Machine learning; Medicine; Pathology","score_opus":0.01339840697618723,"score_gpt":0.28930340488189615,"score_spread":0.27590499790570894,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2612844530","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015597052,0.0016025314,0.9894661,0.0022646005,0.0028047448,0.0010713389,0.00006611319,0.000116106174,0.0010488066],"genre_scores_gemma":[0.47170347,0.0012550891,0.5040873,0.009590206,0.009077005,0.00019169856,0.00037083947,0.0002690867,0.0034552414],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972761,0.000017998735,0.00045864208,0.0011114603,0.0005933845,0.00054236635],"domain_scores_gemma":[0.9980877,0.00031000315,0.00037180027,0.00082110165,0.0002110604,0.00019834064],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00078265934,0.0004314553,0.0007459064,0.00053106016,0.00038212325,0.00034147096,0.00080563175,0.00038108643,0.000012389853],"category_scores_gemma":[0.00033968617,0.00034455297,0.0002837803,0.000118667886,0.0010663188,0.00025137857,0.00031083875,0.0011369622,0.0000011947263],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017955816,0.00009400477,0.009652635,0.00059012935,0.00014463428,0.00023072577,0.00038217672,0.017205862,0.0018672068,0.0014960519,0.0005616888,0.96759534],"study_design_scores_gemma":[0.001553561,0.0004029993,0.0056034247,0.00214135,0.00017915077,0.00016702063,1.5012318e-7,0.96889764,0.00036425787,0.015338423,0.004825113,0.0005269384],"about_ca_topic_score_codex":0.000024513525,"about_ca_topic_score_gemma":0.000012117836,"teacher_disagreement_score":0.9670684,"about_ca_system_score_codex":0.0002921919,"about_ca_system_score_gemma":0.00047629653,"threshold_uncertainty_score":0.99990064},"labels":[],"label_agreement":null},{"id":"W2613447076","doi":"10.1117/1.jmi.4.4.041305","title":"Discovery radiomics via evolutionary deep radiomic sequencer discovery for pathologically proven lung cancer detection","year":2017,"lang":"en","type":"preprint","venue":"Journal of Medical Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Health Science Centre; Sunnybrook Hospital; University of Toronto; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Nvidia","keywords":"Radiomics; Patient privacy; Computer science; Artificial intelligence; Deep learning; Machine learning","score_opus":0.013623607691825938,"score_gpt":0.34138648453084536,"score_spread":0.32776287683901945,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2613447076","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10883296,0.032770813,0.8139204,0.031003682,0.012220389,0.0010121211,0.000039203966,0.000070419424,0.00013000761],"genre_scores_gemma":[0.95444447,0.020901537,0.011058907,0.0015850558,0.010740973,0.00016857535,0.00007764291,0.0001971119,0.0008257395],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9942474,0.00021505343,0.001758411,0.00072038424,0.002221307,0.0008374809],"domain_scores_gemma":[0.99484766,0.0006348512,0.0024117304,0.0006751968,0.00060983,0.00082071556],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0039015694,0.00058234815,0.0015277533,0.00042805483,0.0005826772,0.00072921754,0.0011992016,0.00065831526,0.000031454794],"category_scores_gemma":[0.0069046146,0.00044526008,0.0010857891,0.000097318065,0.0007937524,0.00092056155,0.0006354471,0.0044866866,0.0000013213289],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022543592,0.00049912126,0.02660782,0.0026397738,0.0016050565,0.0040466795,0.00030495322,0.0014007128,0.021975333,0.00016160624,0.010941744,0.92756283],"study_design_scores_gemma":[0.006150073,0.00020277104,0.008329931,0.0072578024,0.0016591807,0.007112288,0.00009434957,0.95180196,0.0006732524,0.00576104,0.010143,0.00081435515],"about_ca_topic_score_codex":0.00013780227,"about_ca_topic_score_gemma":0.000014669908,"teacher_disagreement_score":0.95040125,"about_ca_system_score_codex":0.0015085898,"about_ca_system_score_gemma":0.0027462535,"threshold_uncertainty_score":0.9997999},"labels":[],"label_agreement":null},{"id":"W2615000063","doi":"10.1017/cem.2017.301","title":"P099: Age related rates of abnormal CT findings in otherwise low risk minor head injury patients over 65","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Emergency Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Interior Health","funders":"","keywords":"Medicine; Pathological; Risk factor; Retrospective cohort study; Gold standard (test); Age adjustment; Computed tomography; Head injury; Age groups; Pediatrics; Radiology; Internal medicine; Surgery; Epidemiology; Demography","score_opus":0.02761177914370302,"score_gpt":0.34689767361363777,"score_spread":0.3192858944699348,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2615000063","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9900243,0.0010216992,0.00001263602,0.0023877646,0.0037610875,0.00018180587,0.000015736186,0.0000037601628,0.0025911757],"genre_scores_gemma":[0.99751973,0.00061886106,0.00010678531,0.0001687887,0.00045639978,0.0000013758719,0.000012591826,0.00003620162,0.0010792395],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99761325,0.000091612616,0.0012388511,0.00018780639,0.00042070748,0.00044774494],"domain_scores_gemma":[0.99737316,0.000055581346,0.0009548171,0.00037167597,0.00025066928,0.000994117],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012483008,0.00021413881,0.00070972694,0.0006396049,0.00019020414,0.000009018889,0.00039526285,0.00008842741,0.0030512835],"category_scores_gemma":[0.0048034834,0.0001647011,0.0001637515,0.00021878471,0.00038628926,0.00019502762,0.000020341336,0.0009901741,0.000006737882],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000092514085,0.00006290389,0.97279686,0.00009650112,0.00010738503,0.00066631945,0.0011247998,0.000012872155,0.0006758704,0.000033991015,0.01855596,0.0057740523],"study_design_scores_gemma":[0.0041508614,0.00079468824,0.9818806,0.0016313212,0.00017187619,0.000036692752,0.00011208348,0.00038829842,0.00017258318,0.00022783865,0.010272132,0.00016100002],"about_ca_topic_score_codex":0.027906671,"about_ca_topic_score_gemma":0.0073961606,"teacher_disagreement_score":0.020510511,"about_ca_system_score_codex":0.00015004943,"about_ca_system_score_gemma":0.0005194678,"threshold_uncertainty_score":0.9978601},"labels":[],"label_agreement":null},{"id":"W2617322690","doi":"10.1002/nbm.3739","title":"DCE‐MRI prediction of survival time for patients with glioblastoma multiforme: using an adaptive neuro‐fuzzy‐based model and nested model selection technique","year":2017,"lang":"en","type":"article","venue":"NMR in Biomedicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Brain Institute","funders":"Ingeborg og Emanuel Jensens Mindelegat til Videnskabelig Forskning; Varian Medical Systems","keywords":"Adaptive neuro fuzzy inference system; Magnetic resonance imaging; Glioblastoma; Fuzzy inference system; Computer science; Nuclear medicine; Fuzzy logic; Mathematics; Artificial intelligence; Medicine; Fuzzy control system; Radiology","score_opus":0.021270329816458378,"score_gpt":0.2981373089968631,"score_spread":0.2768669791804047,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2617322690","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.71223414,0.0000073532046,0.28619772,0.0003311267,0.00005107572,0.0010096453,0.000044852524,0.00005025136,0.000073805095],"genre_scores_gemma":[0.9387676,0.0000055233963,0.060796544,0.00012027263,0.00009172462,0.000047382808,0.00009163679,0.000045900673,0.000033417175],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985753,0.000037547004,0.00036971393,0.00037643666,0.00037335238,0.00026761423],"domain_scores_gemma":[0.9988439,0.00007645497,0.00030175908,0.0003110661,0.00028763033,0.00017916334],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00051553914,0.0002074032,0.0004549622,0.0003859716,0.00018358174,0.000017511575,0.000115390394,0.00014362938,0.0000031142088],"category_scores_gemma":[0.00034474378,0.00016114462,0.00003619541,0.00017591169,0.000329849,0.00022642127,0.000032748147,0.00029292225,1.673442e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.014678566,0.0028592062,0.3467885,0.0010075025,0.0001800505,0.000028509688,0.00092693313,0.23776822,0.3764602,0.00013690219,0.00034641597,0.018818993],"study_design_scores_gemma":[0.007046883,0.0029955527,0.032825142,0.000495595,0.00012198083,0.0000151579425,0.000019371062,0.95526886,0.0009584216,0.00011935257,0.000011433712,0.00012226032],"about_ca_topic_score_codex":0.00018169527,"about_ca_topic_score_gemma":0.00002542116,"teacher_disagreement_score":0.7175006,"about_ca_system_score_codex":0.00009406705,"about_ca_system_score_gemma":0.00014978793,"threshold_uncertainty_score":0.6571287},"labels":[],"label_agreement":null},{"id":"W2617383746","doi":"10.15353/vsnl.v1i1.58","title":"Dermal Radiomics for Melanoma Screening","year":2015,"lang":"en","type":"article","venue":"Vision Letters","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Ontario Ministry of Research and Innovation; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Melanoma; Radiomics; Medicine; Cancer research; Radiology","score_opus":0.024771469473933737,"score_gpt":0.3191634294721881,"score_spread":0.2943919599982544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2617383746","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6171511,0.00013523834,0.320218,0.061077125,0.00043047708,0.00027789627,0.0000023256553,0.00009894746,0.00060890615],"genre_scores_gemma":[0.8250752,0.000007606186,0.14189108,0.031664036,0.00089083274,0.000018056657,0.000059038994,0.000052396572,0.00034175703],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990894,0.000025428493,0.0001849405,0.00020805409,0.00024121332,0.0002509476],"domain_scores_gemma":[0.9993559,0.00008875624,0.000054038963,0.00016531326,0.000047949266,0.00028801672],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044554617,0.000107244865,0.00020337256,0.00011102172,0.00006724397,0.000033339802,0.0000882437,0.000048576443,0.00001605399],"category_scores_gemma":[0.00037753116,0.00008951258,0.00009656961,0.00009447343,0.000062163264,0.000075675016,0.00003173831,0.0002051427,0.00001953909],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00067561504,0.00011598716,0.023838047,0.000112194364,0.00014020168,0.000229922,0.00071372755,0.0014728629,0.11034198,0.0005323854,0.5918479,0.26997915],"study_design_scores_gemma":[0.011045477,0.0006786365,0.012337459,0.000255998,0.00017579016,0.00054344896,0.00018596603,0.3099389,0.0030201308,0.00014992886,0.66123587,0.00043242576],"about_ca_topic_score_codex":0.000016709771,"about_ca_topic_score_gemma":2.0939937e-7,"teacher_disagreement_score":0.30846605,"about_ca_system_score_codex":0.000043912652,"about_ca_system_score_gemma":0.00003704307,"threshold_uncertainty_score":0.3650217},"labels":[],"label_agreement":null},{"id":"W2618217372","doi":"10.1200/jco.2013.31.15_suppl.1592","title":"A survey of clinical prediction tools in colorectal and lung cancers and melanoma.","year":2013,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Medicine; Colorectal cancer; Lung cancer; Oncology; Population; Disease; Internal medicine; Stage (stratigraphy); Cancer; Medical physics","score_opus":0.10146154072787807,"score_gpt":0.4793669966953422,"score_spread":0.37790545596746417,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2618217372","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99377024,0.0007389815,0.00009543613,0.0033230658,0.0009265669,0.00018861966,0.000004668279,0.0000038075345,0.0009485934],"genre_scores_gemma":[0.9948002,0.0020040898,0.0018738688,0.0007991724,0.00047164655,0.0000025722322,0.000003347118,0.000009498316,0.000035610625],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99577665,0.00089905405,0.0027692937,0.0001700675,0.00022286442,0.00016208988],"domain_scores_gemma":[0.99163395,0.006306918,0.0012740851,0.000077536926,0.0003038169,0.00040367525],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.010286231,0.00008986258,0.0014861427,0.00011085945,0.00001769727,0.0000105274885,0.0000756191,0.00033710914,0.000054102595],"category_scores_gemma":[0.02595665,0.00006376359,0.00013490806,0.000109326924,0.00046624136,0.00013484988,0.000050834722,0.0014621407,0.0000010817917],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00085879856,0.00019933908,0.77404004,0.000025312904,0.000114736315,0.00006181407,0.0000506928,0.0000087878025,0.00007705143,0.000012373293,0.001787085,0.22276394],"study_design_scores_gemma":[0.006508421,0.0050906283,0.9733465,0.00013291374,0.000112359216,0.00021500875,0.000049876104,0.013271709,0.0000050017493,0.00008162486,0.0011384219,0.000047582256],"about_ca_topic_score_codex":0.00077233784,"about_ca_topic_score_gemma":0.00016664572,"teacher_disagreement_score":0.22271636,"about_ca_system_score_codex":0.000066080866,"about_ca_system_score_gemma":0.0010703979,"threshold_uncertainty_score":0.9822481},"labels":[],"label_agreement":null},{"id":"W2618414278","doi":"10.1007/978-3-319-59876-5_6","title":"Discovery Radiomics via a Mixture of Deep ConvNet Sequencers for Multi-parametric MRI Prostate Cancer Classification","year":2017,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University of Waterloo","funders":"","keywords":"Radiomics; Computer science; Prostate cancer; Artificial intelligence; Parametric statistics; Cancer; Medicine; Internal medicine","score_opus":0.027184691720546324,"score_gpt":0.32168693436866885,"score_spread":0.2945022426481225,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2618414278","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010866942,0.0014814268,0.9926484,0.0020792454,0.0012964554,0.0011229928,0.000035333647,0.00003208147,0.00021731909],"genre_scores_gemma":[0.52429205,0.0011550487,0.47041178,0.001650312,0.0008844014,0.00007256931,0.00010480315,0.00010339793,0.0013256355],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99757576,0.0000181922,0.00050765334,0.00090150617,0.0005588847,0.00043802793],"domain_scores_gemma":[0.9977522,0.0003296789,0.0006714329,0.0007851188,0.00030232262,0.0001592792],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007189503,0.0003704866,0.00074575533,0.0006649995,0.0001889076,0.00016035067,0.00072840624,0.00031293608,0.000008436833],"category_scores_gemma":[0.000561218,0.000302156,0.00018190549,0.00019772563,0.0014308369,0.00023165977,0.00014505189,0.0009106053,0.0000015945686],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016151149,0.00006752106,0.0025385572,0.00068901305,0.00009490556,0.000046755133,0.0008974898,0.02409742,0.0058499705,0.00076605816,0.000062450315,0.96472836],"study_design_scores_gemma":[0.001264951,0.00020019329,0.0010288352,0.0008950783,0.00010223512,0.00006393779,5.419323e-7,0.9885493,0.0014077933,0.004654579,0.0014839922,0.0003485856],"about_ca_topic_score_codex":0.00010143836,"about_ca_topic_score_gemma":0.000049890852,"teacher_disagreement_score":0.96445185,"about_ca_system_score_codex":0.00044030417,"about_ca_system_score_gemma":0.00075530977,"threshold_uncertainty_score":0.9999431},"labels":[],"label_agreement":null},{"id":"W2626590690","doi":"10.1161/str.47.suppl_1.tp460","title":"Abstract TP460: Dominant Imaging Markers for Post Stroke Cognitive Performance in the TABASCO Study","year":2016,"lang":"en","type":"article","venue":"Stroke","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Titan Medical (Canada)","funders":"","keywords":"Medicine; Stroke (engine); Hyperintensity; Magnetic resonance imaging; Montreal Cognitive Assessment; Cohort; Cognition; Internal medicine; Neuroimaging; White matter; Cognitive decline; Cardiology; Prospective cohort study; Physical therapy; Dementia; Cognitive impairment; Psychiatry; Radiology","score_opus":0.009838435226285348,"score_gpt":0.29294159346420245,"score_spread":0.2831031582379171,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2626590690","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9895703,0.00012679209,0.0007306212,0.0039227316,0.00023455474,0.0011971745,0.00006946796,0.000024315212,0.0041240044],"genre_scores_gemma":[0.99734855,0.000055015953,0.00026469812,0.00085205666,0.00023906246,0.00011817203,0.000010983781,0.000029051651,0.0010824209],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9985323,0.00005923733,0.00030918003,0.00031214487,0.0003538635,0.00043328461],"domain_scores_gemma":[0.9987863,0.0006743288,0.00010141374,0.00023422735,0.000106541294,0.00009722346],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00129376,0.00017900219,0.00027346477,0.00014469822,0.00013254503,0.000034251403,0.00017716418,0.000032444226,0.00008251018],"category_scores_gemma":[0.00081494276,0.00009414923,0.000114335344,0.00008139064,0.00014119151,0.00013402144,0.00003860165,0.0003519748,0.000023178878],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011762433,0.00045633572,0.7461525,0.00011035729,0.00010351482,0.00014932649,0.0013573865,0.000002037428,0.020290548,0.00003142909,0.00050869444,0.2296616],"study_design_scores_gemma":[0.008995681,0.0006868187,0.9766742,0.00059356703,0.00014205238,0.00007051305,0.007472285,0.0012491273,0.00094693515,0.0000105639065,0.0029569839,0.00020128702],"about_ca_topic_score_codex":0.000089437315,"about_ca_topic_score_gemma":0.000020984666,"teacher_disagreement_score":0.23052165,"about_ca_system_score_codex":0.00006212615,"about_ca_system_score_gemma":0.00008805941,"threshold_uncertainty_score":0.38392943},"labels":[],"label_agreement":null},{"id":"W2692620580","doi":"10.1186/s12880-017-0209-5","title":"CT texture features are associated with overall survival in pancreatic ductal adenocarcinoma – a quantitative analysis","year":2017,"lang":"en","type":"article","venue":"BMC Medical Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":137,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University Health Network; Ontario Institute for Cancer Research; Lunenfeld-Tanenbaum Research Institute; Mount Sinai Hospital; Sunnybrook Health Science Centre","funders":"Government of Ontario; Ontario Institute for Cancer Research","keywords":"Medicine; Pancreatic ductal adenocarcinoma; Correlation; Receiver operating characteristic; Rank correlation; Tumor grade; Proportional hazards model; Survival analysis; Adenocarcinoma; Mann–Whitney U test; Pancreas; Radiology; Pancreatic cancer; Gastroenterology; Internal medicine; Mathematics; Cancer; Statistics","score_opus":0.0183835349265446,"score_gpt":0.31833538973884257,"score_spread":0.29995185481229797,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2692620580","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9820732,0.0013240431,0.0055025457,0.0077946074,0.00021073458,0.00026247578,0.000008758443,0.000095555035,0.0027280888],"genre_scores_gemma":[0.9958671,0.000060748232,0.002002421,0.0010763017,0.0002116532,0.000018695662,0.00008154513,0.000047955586,0.0006336084],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.996721,0.00029305564,0.0004313422,0.0006241968,0.0013110982,0.00061928923],"domain_scores_gemma":[0.99737144,0.0008530254,0.00042570583,0.0006611574,0.00012623904,0.000562445],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0013723578,0.00032560318,0.0010465973,0.00037483516,0.0003263741,0.00019289725,0.0004456859,0.0000935043,0.00025341008],"category_scores_gemma":[0.014931227,0.0002360509,0.0002479054,0.00038925323,0.0005931396,0.00022112926,0.00014764478,0.0013279978,0.000010285984],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015513095,0.00016241925,0.99248534,0.00008435901,0.00064448966,0.0043378742,0.00026839547,0.00005015935,0.00004639414,0.00030785255,0.00058500515,0.0008725962],"study_design_scores_gemma":[0.0033594468,0.00005216844,0.9047917,0.0010749549,0.001012332,0.0002508306,0.0004917919,0.08854506,0.000005154803,0.000103972336,0.000056872013,0.0002556872],"about_ca_topic_score_codex":0.0013134399,"about_ca_topic_score_gemma":0.0018980268,"teacher_disagreement_score":0.088494904,"about_ca_system_score_codex":0.0001530131,"about_ca_system_score_gemma":0.00040671419,"threshold_uncertainty_score":0.9933664},"labels":[],"label_agreement":null},{"id":"W2724451918","doi":"10.1149/ma2010-01/19/1033","title":"Gastrointestinal Imaging Technologies: Can We Turn the Gut Inside Out?","year":2010,"lang":"en","type":"article","venue":"ECS Meeting Abstracts","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network","funders":"","keywords":"Turn (biochemistry); Computer science; Data science; Biology","score_opus":0.01101233746847071,"score_gpt":0.2708668050449776,"score_spread":0.25985446757650693,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2724451918","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8428916,0.00019881298,0.0000484827,0.08995703,0.00074927893,0.00022941321,0.000002395316,0.00066551473,0.06525751],"genre_scores_gemma":[0.9836957,0.000022051618,0.014314204,0.0009657817,0.0005087064,0.000010805536,0.000006806992,0.000047368318,0.00042860632],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982427,0.00003271878,0.0004146615,0.00035833044,0.00038769477,0.0005639069],"domain_scores_gemma":[0.998496,0.00043799414,0.00024045806,0.00054133125,0.000108668915,0.00017554304],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0010955139,0.00023328445,0.0002660557,0.0001260488,0.00028783488,0.000110671375,0.00034026592,0.00006051875,0.000029255643],"category_scores_gemma":[0.007869996,0.00015774094,0.00010190861,0.00015092427,0.00037741012,0.000059512917,0.00013201548,0.00250674,0.00006445597],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004995274,0.00016998462,0.14130357,0.000148811,0.00005052664,0.0014495191,0.0012569473,0.0010981701,0.7797613,0.00008659481,0.009737959,0.06488664],"study_design_scores_gemma":[0.0066566216,0.00053449685,0.36026916,0.007514021,0.00066508714,0.032563467,0.012668661,0.06594943,0.13226314,0.009155178,0.36951193,0.0022488313],"about_ca_topic_score_codex":0.00028257875,"about_ca_topic_score_gemma":0.000062523904,"teacher_disagreement_score":0.6474982,"about_ca_system_score_codex":0.000042639134,"about_ca_system_score_gemma":0.00015489286,"threshold_uncertainty_score":0.99979454},"labels":[],"label_agreement":null},{"id":"W2724559516","doi":"10.1038/sdata.2017.77","title":"Matched computed tomography segmentation and demographic data for oropharyngeal cancer radiomics challenges","year":2017,"lang":"en","type":"article","venue":"Scientific Data","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":82,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Columbia College","funders":"Division of Mathematical Sciences; National Cancer Institute; National Science Foundation; National Institutes of Health; Andrew Sabin Family Foundation; National Institute of Dental and Craniofacial Research; University of Texas MD Anderson Cancer Center; Radiological Society of North America; Varian Medical Systems","keywords":"Radiomics; Head and neck cancer; Medicine; Data extraction; Workflow; Segmentation; Leverage (statistics); Radiation therapy; Medical physics; Computer science; Artificial intelligence; Radiology; MEDLINE; Database; Biology","score_opus":0.09448940482926785,"score_gpt":0.37674825807600376,"score_spread":0.28225885324673594,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2724559516","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.77799064,0.044782482,0.047226593,0.08535209,0.015092096,0.0043260613,0.023820817,0.0004084453,0.0010007658],"genre_scores_gemma":[0.8541233,0.0059711267,0.09470906,0.00088159397,0.0013393855,0.00006149003,0.04199309,0.00009815163,0.0008227955],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982206,0.000028670382,0.00021470328,0.000972508,0.00028787358,0.00027564066],"domain_scores_gemma":[0.9958059,0.00007293848,0.00017976286,0.0036602835,0.00008052671,0.00020054872],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016351898,0.00013556996,0.00029148805,0.00017628864,0.0007912761,0.0005112151,0.0015824379,0.000053928452,0.000020198542],"category_scores_gemma":[0.00038430045,0.00011653217,0.000031423337,0.00011146228,0.00063385715,0.0006070396,0.0011329748,0.00017800427,0.0000023798852],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018174564,0.00022938062,0.03498465,0.00095561094,0.0004250823,0.000032544944,0.0004903716,0.0000061262185,0.018744119,0.0004938665,0.16410421,0.7793523],"study_design_scores_gemma":[0.006485338,0.00013107811,0.21285935,0.00054791546,0.0008018622,0.0000906389,0.0004557519,0.6111767,0.00061480823,0.0009736704,0.16533661,0.0005262312],"about_ca_topic_score_codex":0.00010959691,"about_ca_topic_score_gemma":0.00009736188,"teacher_disagreement_score":0.77882606,"about_ca_system_score_codex":0.000012793372,"about_ca_system_score_gemma":0.000096831245,"threshold_uncertainty_score":0.6085936},"labels":[],"label_agreement":null},{"id":"W2726395676","doi":"10.1016/s1470-2045(17)30438-2","title":"The TNM classification of malignant tumours—towards common understanding and reasonable expectations","year":2017,"lang":"en","type":"article","venue":"The Lancet Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":286,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto","funders":"National Cancer Institute; National Institutes of Health; World Health Organization","keywords":"CLARITY; Profiling (computer programming); Disease; Medicine; Cancer; Pathology; Internal medicine; Computer science; Biology","score_opus":0.1075127998060665,"score_gpt":0.3980224307440145,"score_spread":0.290509630937948,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2726395676","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.71482635,0.0006945445,0.0017380463,0.23731676,0.00033408395,0.00026631163,0.0000032377422,0.000030458637,0.044790205],"genre_scores_gemma":[0.9980209,0.0005439545,0.0005035645,0.00030911883,0.00024264197,0.000013416022,0.000003792068,0.000008043946,0.0003545779],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99935186,0.0001182516,0.00014883235,0.00009992558,0.00011324557,0.00016789162],"domain_scores_gemma":[0.99895,0.00033630486,0.00021859856,0.00041657436,0.000032414864,0.00004609321],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00094502576,0.000056992405,0.0002397619,0.000018707755,0.0006903283,0.000038846752,0.00021101942,0.000043572843,0.000007237186],"category_scores_gemma":[0.00057767157,0.000029914068,0.00002750759,0.000028462495,0.0005848614,0.00003330339,0.00006282112,0.0002562542,0.0000024557985],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008335382,0.00019401223,0.24133655,0.0001734164,0.00023740015,0.00006617209,0.006297978,0.000017688533,0.01757106,0.52058345,0.02576925,0.18691951],"study_design_scores_gemma":[0.0029029553,0.00040001216,0.90164185,0.0001678012,0.00019694686,0.0002613093,0.007933341,0.021045603,0.0003767317,0.025796687,0.0391599,0.00011684285],"about_ca_topic_score_codex":0.00016230723,"about_ca_topic_score_gemma":0.00009306016,"teacher_disagreement_score":0.6603053,"about_ca_system_score_codex":0.00008883668,"about_ca_system_score_gemma":0.00008958207,"threshold_uncertainty_score":0.5309517},"labels":[],"label_agreement":null},{"id":"W27276676","doi":"10.1007/978-3-642-33418-4_79","title":"Registration Accuracy: How Good Is Good Enough? A Statistical Power Calculation Incorporating Image Registration Uncertainty","year":2012,"lang":"en","type":"article","venue":"Lecture notes in computer science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lawson Health Research Institute; Western University; Robarts Clinical Trials","funders":"Canadian Institutes of Health Research; Cancer Care Ontario","keywords":"Image registration; Computer science; Statistical power; Monte Carlo method; Context (archaeology); Artificial intelligence; Sample size determination; Statistical model; Sample (material); Power (physics); Algorithm; Image (mathematics); Computer vision; Statistics; Mathematics","score_opus":0.014204946502288852,"score_gpt":0.3056993930038886,"score_spread":0.2914944465015997,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W27276676","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08341283,0.000071431634,0.9027249,0.012741817,0.00045424592,0.00028326578,0.000003571772,0.00006381993,0.00024410382],"genre_scores_gemma":[0.7310148,0.0000025655943,0.2671326,0.0014089246,0.0003875432,0.000005719538,0.00003070909,0.000011549592,0.0000056156564],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978127,0.00009721925,0.00034605895,0.00049084565,0.000758514,0.0004946892],"domain_scores_gemma":[0.99847347,0.0004584212,0.00025008776,0.00039621643,0.00017473643,0.00024707886],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015435363,0.00019988704,0.00025428314,0.00017824028,0.0002301461,0.0002677103,0.00021168584,0.00010867908,0.000019416097],"category_scores_gemma":[0.002355483,0.00016783345,0.000047109595,0.00074903277,0.00044887513,0.0007258908,0.00008273794,0.0005850774,0.000007497384],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011353736,0.0005412588,0.13073057,0.00021661115,0.000036252637,0.00012028523,0.006703651,0.015600906,0.0870043,0.012734223,0.00063474395,0.7455637],"study_design_scores_gemma":[0.0008129133,0.0002585992,0.061551515,0.00017143038,0.000027170327,0.00021421816,0.0000077420045,0.9282044,0.004348338,0.0036081662,0.00050380285,0.00029169815],"about_ca_topic_score_codex":0.0001035675,"about_ca_topic_score_gemma":0.000017160592,"teacher_disagreement_score":0.9126035,"about_ca_system_score_codex":0.0002377484,"about_ca_system_score_gemma":0.00030928783,"threshold_uncertainty_score":0.68440497},"labels":[],"label_agreement":null},{"id":"W2728276326","doi":"10.1093/jnci/djx116","title":"Editorial: Radiomics: The New World or Another Road to El Dorado?","year":2017,"lang":"en","type":"editorial","venue":"JNCI Journal of the National Cancer Institute","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; University of Toronto; Princess Margaret Cancer Centre","funders":"","keywords":"Radiomics; Computer science; Artificial intelligence","score_opus":0.030601036750253215,"score_gpt":0.38604951233409257,"score_spread":0.35544847558383935,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2728276326","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00006479927,0.00086698506,0.00023795938,0.047658026,0.9483721,0.0003698251,0.0000793952,0.000014228248,0.0023366816],"genre_scores_gemma":[0.00020202677,0.0006349388,0.00071346626,0.0038679144,0.96046335,0.000014351048,0.000013324665,0.00006906528,0.034021575],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9946088,0.000096932985,0.0008322914,0.0002885239,0.003843526,0.00032990763],"domain_scores_gemma":[0.995581,0.00045080297,0.0015442045,0.0004662846,0.0016422097,0.00031553284],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0019186209,0.0003582299,0.0007635553,0.00033633717,0.00048219002,0.0002618152,0.0017331267,0.0003711165,0.00017335052],"category_scores_gemma":[0.012350692,0.00017330093,0.0004934067,0.00032335293,0.00027827028,0.00028414,0.00019089878,0.0033663872,0.000020056796],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008844943,0.000038316244,0.00003957662,0.000047775724,0.00044849346,0.000022071088,0.0001515004,0.00104835,0.00011195196,0.000060279595,0.9875088,0.009638432],"study_design_scores_gemma":[0.0023974995,0.000096388394,0.00020248591,0.0013683148,0.00040416504,0.00008335869,0.000004522129,0.00010078837,0.000035197016,0.00045294783,0.99464536,0.0002089914],"about_ca_topic_score_codex":0.0007674714,"about_ca_topic_score_gemma":0.00055173045,"teacher_disagreement_score":0.043790113,"about_ca_system_score_codex":0.0013099764,"about_ca_system_score_gemma":0.011850802,"threshold_uncertainty_score":0.9989329},"labels":[],"label_agreement":null},{"id":"W2735522662","doi":"10.1530/erc-17-0209","title":"A comprehensive review on MEN2B","year":2017,"lang":"en","type":"review","venue":"Endocrine Related Cancer","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":97,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science","score_opus":0.09907016582732375,"score_gpt":0.4699450566218236,"score_spread":0.37087489079449987,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2735522662","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[5.902579e-7,0.9747062,0.0000016008378,0.0031986427,0.0010677984,0.0014663747,0.00002461907,0.0001405354,0.019393642],"genre_scores_gemma":[5.4521064e-7,0.9798164,0.000076948614,0.0022309578,0.0005606974,0.00033350827,0.00022661328,0.00015019465,0.016604142],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973256,0.00017037858,0.00084872014,0.0006725442,0.00047560796,0.0005071345],"domain_scores_gemma":[0.9974939,0.0001818381,0.00074620463,0.0011391212,0.00011052257,0.00032839968],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00018689068,0.00061965594,0.0035077473,0.00020850814,0.00016751727,0.000033875334,0.00037820585,0.00019736601,0.0015131285],"category_scores_gemma":[0.00048124284,0.00042532015,0.0009299857,0.00021811273,0.00014659754,0.000040747127,0.000117201795,0.0026624396,0.0006251035],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000059350214,0.000036062476,0.0000017659656,0.08545897,0.0006550256,0.00069297676,0.000004550432,8.3617437e-7,1.526565e-7,0.000070231596,0.05149796,0.86157554],"study_design_scores_gemma":[0.0005373299,0.000075801654,0.0000026854846,0.27638558,0.0028338756,0.00085310475,5.1600006e-7,0.000017308514,1.9070556e-7,0.000010311704,0.7190147,0.00026855877],"about_ca_topic_score_codex":0.000096281794,"about_ca_topic_score_gemma":4.8310744e-7,"teacher_disagreement_score":0.86130697,"about_ca_system_score_codex":0.00033110668,"about_ca_system_score_gemma":0.00056911353,"threshold_uncertainty_score":0.9998199},"labels":[],"label_agreement":null},{"id":"W2736245558","doi":"10.1016/s0167-8140(17)31058-7","title":"PO-0621: Validation of tumor delineation on HE stained sections with cytokeratin staining as gold standard","year":2017,"lang":"en","type":"article","venue":"Radiotherapy and Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre","funders":"","keywords":"Gold standard (test); Cytokeratin; Staining; Pathology; Medicine; Immunohistochemistry; Internal medicine","score_opus":0.01502627732118344,"score_gpt":0.3453064289298713,"score_spread":0.33028015160868784,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2736245558","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95748997,0.00014025177,0.030299112,0.008794522,0.00014065077,0.0002966176,0.0000058246023,0.000035324832,0.002797752],"genre_scores_gemma":[0.98753047,0.00025476044,0.009521399,0.0014881801,0.00031110426,0.000016229777,0.000020029644,0.000024340476,0.00083350966],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99911064,0.00009015495,0.00023594516,0.00020911831,0.00018673479,0.00016741098],"domain_scores_gemma":[0.99912596,0.00013669704,0.0002611142,0.00024864855,0.00012026513,0.000107335036],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00049360766,0.000120957026,0.0003528532,0.00010767014,0.00027400907,0.000043206288,0.000069707996,0.00007496305,0.000085085834],"category_scores_gemma":[0.0002995757,0.00009132527,0.00003728746,0.000049922262,0.00020278512,0.00008971255,0.000011096121,0.00028651507,0.0000010532784],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.017101008,0.00088348275,0.16091944,0.0003821147,0.001102935,0.00052460504,0.0072432137,0.005783302,0.06855574,0.008215383,0.005841898,0.72344685],"study_design_scores_gemma":[0.06714957,0.07414532,0.115272336,0.001502837,0.00095393875,0.0028543703,0.0035709275,0.10831123,0.11245319,0.0016969899,0.5106515,0.0014377619],"about_ca_topic_score_codex":0.00011674056,"about_ca_topic_score_gemma":0.000019998064,"teacher_disagreement_score":0.7220091,"about_ca_system_score_codex":0.00021175075,"about_ca_system_score_gemma":0.000247605,"threshold_uncertainty_score":0.37241367},"labels":[],"label_agreement":null},{"id":"W2737453412","doi":"10.7554/elife.23421","title":"Defining the biological basis of radiomic phenotypes in lung cancer","year":2017,"lang":"en","type":"article","venue":"eLife","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":359,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto; University Health Network; Montreal Clinical Research Institute","funders":"Stichting voor de Technische Wetenschappen; National Institutes of Health; National Cancer Institute; KWF Kankerbestrijding","keywords":"Radiomics; Lung cancer; Medicine; Phenotype; Pathology; Bioinformatics; Computational biology; Oncology; Biology; Radiology; Genetics; Gene","score_opus":0.01641777494677072,"score_gpt":0.3384855564519291,"score_spread":0.3220677815051584,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2737453412","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9814972,0.0042383717,0.00017392368,0.009373268,0.00023421265,0.00011027187,0.0000022752854,0.000015068367,0.004355371],"genre_scores_gemma":[0.997114,0.0006613945,0.0009316219,0.0009939342,0.00016591132,0.00001076502,0.0000022099955,0.000008776481,0.000111363166],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9993625,0.00003621424,0.00017165557,0.00012891377,0.00014476757,0.00015592492],"domain_scores_gemma":[0.99940354,0.00011508525,0.000111785026,0.0002911063,0.000025323323,0.000053144006],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004876105,0.00006885831,0.00021502435,0.000038347724,0.00012279513,0.00001717114,0.0001957559,0.00004661703,0.00013263716],"category_scores_gemma":[0.0011884908,0.000039539573,0.000053488387,0.000040339866,0.00019145336,0.000028613518,0.00006250126,0.00028310172,0.0000052899813],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004790467,0.000029066528,0.9622284,0.000032764452,0.000037506237,0.000016662565,0.0003077342,0.000049251663,0.0021119656,0.0016943279,0.002276388,0.031168008],"study_design_scores_gemma":[0.0011265841,0.000038631402,0.9683527,0.00024946756,0.00004289821,0.0000125718025,0.000064390326,0.02297775,0.002266103,0.000060313047,0.0047275606,0.000081031074],"about_ca_topic_score_codex":0.0007233203,"about_ca_topic_score_gemma":0.00002164662,"teacher_disagreement_score":0.031086978,"about_ca_system_score_codex":0.000029316372,"about_ca_system_score_gemma":0.00006502701,"threshold_uncertainty_score":0.1612377},"labels":[],"label_agreement":null},{"id":"W2737947225","doi":"10.1200/jco.2014.32.15_suppl.e17529","title":"Pattern of use of PET/CT scanning in gastrointestinal cancers in one cancer center in Saudi Arabia.","year":2014,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre","funders":"","keywords":"Medicine; Colorectal cancer; Cancer; PET-CT; Pancreatic cancer; Radiology; Stage (stratigraphy); Esophageal cancer; Computed tomography; Nuclear medicine; Internal medicine","score_opus":0.09889790492067362,"score_gpt":0.4472949069536079,"score_spread":0.3483970020329343,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2737947225","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99282587,0.00008267386,0.0005617023,0.005815117,0.00032797796,0.000091561764,0.0000015980075,0.0000017671437,0.00029173944],"genre_scores_gemma":[0.99205506,0.0002761178,0.005757204,0.0015772892,0.00028968565,0.0000019661097,9.674757e-7,0.000013469767,0.000028224837],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9961549,0.00050940795,0.002605956,0.00015908641,0.00030619514,0.00026446857],"domain_scores_gemma":[0.99600023,0.0019642378,0.0015556032,0.00012228209,0.00016255169,0.0001951185],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0040377364,0.00010640625,0.0015167791,0.0003364992,0.0000060828606,0.000003158646,0.00014350997,0.00003780791,0.00007627907],"category_scores_gemma":[0.007915137,0.00008645893,0.0001897434,0.00019504083,0.00024708192,0.00008305023,0.00004551597,0.0017613261,6.4446147e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00087841664,0.00070550136,0.9139364,0.00008867957,0.000029157816,0.00093613256,0.000075350574,0.0027019244,0.00035251878,0.000006584824,0.00023944164,0.080049895],"study_design_scores_gemma":[0.008801081,0.0024847407,0.9655093,0.0040376806,0.000039382565,0.0007531192,0.00006135481,0.016479658,0.00002468618,0.000046707013,0.001698199,0.00006408841],"about_ca_topic_score_codex":0.003754016,"about_ca_topic_score_gemma":0.0024085222,"teacher_disagreement_score":0.079985805,"about_ca_system_score_codex":0.00031096666,"about_ca_system_score_gemma":0.00095606345,"threshold_uncertainty_score":0.94757307},"labels":[],"label_agreement":null},{"id":"W2738834107","doi":"","title":"The Implementation of 30’ Wide Undercuts at TRJV","year":2015,"lang":"en","type":"article","venue":"49th U.S. Rock Mechanics/Geomechanics Symposium","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Barrick Gold (Canada)","funders":"","keywords":"Computer science","score_opus":0.015719576795420916,"score_gpt":0.28907371976685464,"score_spread":0.27335414297143373,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2738834107","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16151817,0.0033818188,0.7634742,0.05074624,0.0085181715,0.0045367186,0.00011047706,0.0008805962,0.006833553],"genre_scores_gemma":[0.9949184,0.0007002796,0.0007363683,0.0015709772,0.00029611416,0.00006504965,0.00010786303,0.00011909502,0.0014858758],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965081,0.00016467189,0.0008889071,0.0005697618,0.0010849515,0.000783611],"domain_scores_gemma":[0.9973332,0.00026365844,0.0004955419,0.000843639,0.00044978547,0.00061415625],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0016511366,0.0003931773,0.00061770424,0.00018983812,0.00042518717,0.00006341094,0.00046691598,0.00021159333,0.00026296996],"category_scores_gemma":[0.00038988728,0.00030191336,0.0002433074,0.00044161416,0.00002051385,0.00014247291,0.00042724397,0.00057752687,0.00017300053],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002052997,0.00114689,0.0028882525,0.0010820789,0.0020350001,0.00036055216,0.0084019415,0.008963014,0.42356336,0.38892302,0.131558,0.029024912],"study_design_scores_gemma":[0.015600828,0.0040106033,0.00012324487,0.00048462843,0.0014012487,0.0009576134,0.010460387,0.5738525,0.1086127,0.078467295,0.20437405,0.0016549161],"about_ca_topic_score_codex":0.00017364189,"about_ca_topic_score_gemma":0.00006045365,"teacher_disagreement_score":0.8334002,"about_ca_system_score_codex":0.00054319686,"about_ca_system_score_gemma":0.00047807427,"threshold_uncertainty_score":0.9999433},"labels":[],"label_agreement":null},{"id":"W2739868546","doi":"10.1158/1538-7445.am2017-3952","title":"Abstract 3952: Rapid autopsy programs: A systematic review","year":2017,"lang":"en","type":"review","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Princess Margaret Cancer Centre","funders":"","keywords":"Medicine; Tissue bank; Tissue Donation; Translational research; Cancer; MEDLINE; Intensive care medicine; Oncology; Pathology; Internal medicine; Organ donation; Transplantation; Biology","score_opus":0.3031024963029514,"score_gpt":0.567224672339668,"score_spread":0.2641221760367166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2739868546","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[8.723162e-7,0.9843699,0.0000036910776,0.001319379,0.00034067236,0.007958744,0.000015923397,0.000102270315,0.0058885454],"genre_scores_gemma":[0.0000026669195,0.9867672,0.00008498274,0.0002496139,0.0008528548,0.004398904,0.00015620413,0.00015282708,0.0073347874],"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","domain_scores_codex":[0.9947299,0.0006582046,0.0012011932,0.00078345253,0.0016582648,0.00096901075],"domain_scores_gemma":[0.9957904,0.00045628648,0.00065421296,0.0020436808,0.00045063384,0.0006047749],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0071248137,0.0004811804,0.0049151694,0.00040511464,0.0003746003,0.00025290746,0.0011459012,0.0002912471,0.0006412865],"category_scores_gemma":[0.005346285,0.00030584665,0.0009286064,0.00047745724,0.00046743843,0.000078487086,0.0002553063,0.0040676044,0.00080529397],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000019607546,0.000033949316,4.811826e-7,0.51754254,0.00022726721,0.00019125202,0.000010603118,5.3738005e-9,2.2373283e-7,0.000009666427,0.006593572,0.4753885],"study_design_scores_gemma":[0.00011342399,0.000041588657,0.0000010995683,0.49790272,0.0011280825,0.0001453574,0.0000028077577,0.0000036802708,5.266218e-8,0.0000038135963,0.5005203,0.00013710077],"about_ca_topic_score_codex":0.00018617648,"about_ca_topic_score_gemma":0.0000033163024,"teacher_disagreement_score":0.4939267,"about_ca_system_score_codex":0.00067401596,"about_ca_system_score_gemma":0.0026909418,"threshold_uncertainty_score":0.9999727},"labels":[],"label_agreement":null},{"id":"W2741647816","doi":"10.1158/1538-7445.am2017-2834","title":"Abstract 2834: Metastatic colorectal cancer: characterization of distinct histological growth patterns which demonstrate different response to current treatment regimes","year":2017,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre; McGill University","funders":"","keywords":"Colorectal cancer; Medicine; Stromal cell; Metastasis; Immunohistochemistry; Bevacizumab; Angiogenesis; Cancer; Pathology; Cancer research; Parenchyma; Oncology; Internal medicine; Chemotherapy","score_opus":0.08142278276832707,"score_gpt":0.43258168008465897,"score_spread":0.3511588973163319,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2741647816","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9853881,0.00035695155,0.00020589102,0.01266338,0.0003533755,0.000732469,0.00013687406,0.000026421165,0.0001365368],"genre_scores_gemma":[0.9972886,0.0016056126,0.00004296705,0.000034525234,0.00022031163,0.0004177187,0.000055734366,0.000028882196,0.0003056386],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99775535,0.0002867885,0.00035423317,0.0004438221,0.0006625891,0.00049724086],"domain_scores_gemma":[0.9982786,0.00028154472,0.00020703912,0.00041455304,0.00040846516,0.00040978155],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00087346317,0.00020085479,0.0005125504,0.00020435883,0.00036772632,0.00008788683,0.0003109802,0.00005534347,0.00030841137],"category_scores_gemma":[0.0014340859,0.00013854347,0.00009313447,0.00014214843,0.0002826612,0.00007593977,0.00012230004,0.00054506207,0.000010260816],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004051117,0.0005157526,0.38135102,0.0003741571,0.0001668874,0.00011200542,0.00053935515,0.0000044496946,0.44328827,0.000062776446,0.0002345687,0.16929966],"study_design_scores_gemma":[0.0013719971,0.00069651136,0.9619839,0.00064745866,0.00007877702,0.000010563855,0.000030928113,0.00041837493,0.03284281,0.000030983567,0.001754623,0.00013302371],"about_ca_topic_score_codex":0.0018005576,"about_ca_topic_score_gemma":0.00023719079,"teacher_disagreement_score":0.5806329,"about_ca_system_score_codex":0.00070480705,"about_ca_system_score_gemma":0.00055321323,"threshold_uncertainty_score":0.5649639},"labels":[],"label_agreement":null},{"id":"W2747043658","doi":"10.1101/181289","title":"Prediction of early breast cancer patient survival using ensembles of hypoxia signatures","year":2017,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Ontario Institute for Cancer Research","funders":"Canadian Institutes of Health Research; National Science Foundation; Ontario Institute for Cancer Research; Cancer Research UK; BC Cancer Agency; Government of Ontario; University of Toronto","keywords":"Preprocessor; Random forest; Computer science; Artificial intelligence; Breast cancer; Classifier (UML); Biomarker discovery; Pattern recognition (psychology); Data mining; Data pre-processing; Machine learning; Cancer; Medicine; Internal medicine; Biology","score_opus":0.021035836436589784,"score_gpt":0.2601233085671878,"score_spread":0.239087472130598,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2747043658","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9937653,0.0019380491,0.0008077097,0.00023869504,0.0018798287,0.00052203663,0.00073432946,0.00009820233,0.000015838912],"genre_scores_gemma":[0.9954429,0.00044611545,0.0033125628,0.000053681797,0.0006044662,0.000028795748,7.0430644e-7,0.00010787886,0.0000028907657],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99741334,0.000120855,0.00073487026,0.00063049805,0.00071668084,0.00038378226],"domain_scores_gemma":[0.9965314,0.00006564134,0.0011909489,0.0011079686,0.00083548774,0.0002685475],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00055163517,0.00041489347,0.0009846668,0.0003009557,0.00013050815,0.00005719517,0.00035279916,0.0004925969,0.000039428825],"category_scores_gemma":[0.00037987417,0.00039344173,0.00024672764,0.00016478098,0.00031924757,0.00009952848,0.00032617553,0.0011222783,0.0000012729319],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017536867,0.00019714446,0.13035066,0.0012737999,0.00043033843,0.000043204567,0.00003591579,0.0006883618,0.8665555,0.00008301067,0.00011494917,0.0000517005],"study_design_scores_gemma":[0.0010583614,0.00014869611,0.8833607,0.0041914363,0.0006763178,1.6409652e-7,0.0000049767077,0.008380738,0.101416506,0.000002809115,0.00036952732,0.00038975326],"about_ca_topic_score_codex":0.0013331039,"about_ca_topic_score_gemma":0.0000017114203,"teacher_disagreement_score":0.76513904,"about_ca_system_score_codex":0.00019213297,"about_ca_system_score_gemma":0.0009260975,"threshold_uncertainty_score":0.99985176},"labels":[],"label_agreement":null},{"id":"W2747168886","doi":"10.1016/j.ultrasmedbio.2014.02.033","title":"Book Review","year":2014,"lang":"en","type":"article","venue":"Ultrasound in Medicine & Biology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Section (typography); Style (visual arts); Quarter (Canadian coin); Library science; Classics; Medicine; Computer science; History; Visual arts; Art","score_opus":0.010004975186077575,"score_gpt":0.3251010226009963,"score_spread":0.31509604741491876,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2747168886","genre_codex":"review","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010367699,0.69518065,0.007335173,0.17873482,0.0013210274,0.00089735765,0.0000020326213,0.00021778641,0.105943464],"genre_scores_gemma":[0.104010664,0.19718327,0.0017473737,0.6899852,0.001898261,0.000052411753,0.00024015785,0.00005506239,0.004827575],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99841803,0.00020308488,0.0004955521,0.00034992196,0.0001603347,0.00037310043],"domain_scores_gemma":[0.9984194,0.0008626061,0.00010058655,0.0003665782,0.000051440213,0.00019938019],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0013692774,0.00018053642,0.00073683757,0.00015433977,0.00004002349,0.000002799111,0.00015453124,0.00009791915,0.0033313474],"category_scores_gemma":[0.0082837045,0.00012146295,0.0000663108,0.00024560775,0.00044310023,0.0000328906,0.000023831586,0.0007045423,0.00009114877],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003175379,0.00007638645,0.032707434,0.0006971139,0.000032251435,0.000024155643,0.000113429836,0.0000012979613,0.007829464,0.0019116116,0.8583719,0.09820317],"study_design_scores_gemma":[0.0013725914,0.00050286844,0.008772555,0.0020807064,0.00007184859,0.00029467486,0.0000096692875,0.00021137965,0.000022623542,0.00067108707,0.9858708,0.00011923159],"about_ca_topic_score_codex":0.0000831863,"about_ca_topic_score_gemma":0.0000026192959,"teacher_disagreement_score":0.5112504,"about_ca_system_score_codex":0.000045391007,"about_ca_system_score_gemma":0.000043837856,"threshold_uncertainty_score":0.99757975},"labels":[],"label_agreement":null},{"id":"W2747985375","doi":"10.1016/j.nicl.2017.08.021","title":"Improved prediction of outcome in Parkinson's disease using radiomics analysis of longitudinal DAT SPECT images","year":2017,"lang":"en","type":"article","venue":"NeuroImage Clinical","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":112,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China; Michael J. Fox Foundation for Parkinson's Research","keywords":"Parkinson's disease; Spect imaging; Medicine; Putamen; Neuroimaging; Nuclear medicine; Magnetic resonance imaging; Dopamine transporter; Radiology; Psychology; Disease; Internal medicine; Dopamine; Dopaminergic","score_opus":0.0938730411228361,"score_gpt":0.42025970015663794,"score_spread":0.3263866590338018,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2747985375","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9950619,0.00008550738,0.0030614203,0.00082971604,0.00044512798,0.00022116976,0.000077717836,0.00002202961,0.00019542541],"genre_scores_gemma":[0.99598247,0.00019778713,0.003331979,0.00014661936,0.00022641692,0.000002138198,0.000033601118,0.000026455065,0.000052523454],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99746525,0.00016170819,0.0012740081,0.0005315104,0.0003204299,0.00024709964],"domain_scores_gemma":[0.9973404,0.00036593236,0.0007749791,0.0011384247,0.00009729922,0.00028300448],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014677669,0.00017256617,0.0010704816,0.00036946786,0.00008546964,0.000037914946,0.00032030177,0.000079273195,0.000044397777],"category_scores_gemma":[0.0071535422,0.00015374096,0.00055510923,0.00026325748,0.00067269587,0.00017059503,0.00017330835,0.0006785218,8.750471e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045282816,0.00037768154,0.98984265,0.000096683485,0.00026124323,0.00027781565,0.000014592604,0.00020574422,0.0045998655,0.000010067641,0.00005311724,0.0038077151],"study_design_scores_gemma":[0.0016151797,0.00012441924,0.71976733,0.000056703426,0.0015318638,0.000012406375,0.0000053181834,0.2765572,0.00009704685,0.000010893964,0.00015504782,0.00006658775],"about_ca_topic_score_codex":0.00022537004,"about_ca_topic_score_gemma":0.000008762335,"teacher_disagreement_score":0.27635145,"about_ca_system_score_codex":0.00003729138,"about_ca_system_score_gemma":0.00010492908,"threshold_uncertainty_score":0.8563975},"labels":[],"label_agreement":null},{"id":"W2750103883","doi":"10.1016/s0167-8140(15)33253-9","title":"PO-0947: Breast cancer patientsí knowledge of RT at the beginning of their RT period","year":2013,"lang":"en","type":"article","venue":"Radiotherapy and Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; Sunnybrook Health Science Centre","funders":"","keywords":"Breast cancer; Period (music); Medicine; Oncology; Internal medicine; Cancer; Art","score_opus":0.009817543406996285,"score_gpt":0.3105748514582725,"score_spread":0.3007573080512762,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2750103883","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.976627,0.008661539,0.00022814944,0.012065119,0.00026088045,0.0002981341,0.000009464676,0.000014086998,0.0018356619],"genre_scores_gemma":[0.99465394,0.002322577,0.0004274898,0.0013451659,0.00024970277,0.000032668187,0.0000051453094,0.000022547176,0.00094075425],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99915737,0.00010702422,0.00027240155,0.00017161913,0.00008819407,0.00020337763],"domain_scores_gemma":[0.99927855,0.00017852457,0.0001626106,0.00018851261,0.000094907715,0.00009687834],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00026191233,0.0001241033,0.0004445636,0.00006345629,0.000092893504,0.000005696255,0.00010132254,0.00010147448,0.0011196763],"category_scores_gemma":[0.000027430642,0.00007187285,0.00008178803,0.00010689584,0.00049579423,0.000037129856,0.000038118225,0.00024509057,0.0000028105217],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026235884,0.0002653745,0.19600391,0.0001324125,0.0002724841,0.0000041893845,0.009941675,0.000021221433,0.036066215,0.00014689309,0.0059977365,0.75088555],"study_design_scores_gemma":[0.00876444,0.0021234804,0.6485823,0.00042736012,0.00018870385,0.0010576,0.0019028237,0.013081086,0.0030208162,0.00017118847,0.32033563,0.0003445695],"about_ca_topic_score_codex":0.00046863343,"about_ca_topic_score_gemma":0.000029999299,"teacher_disagreement_score":0.750541,"about_ca_system_score_codex":0.00016019576,"about_ca_system_score_gemma":0.00013810773,"threshold_uncertainty_score":0.9997934},"labels":[],"label_agreement":null},{"id":"W2753319029","doi":"10.1088/1361-6560/aa8a49","title":"Enhancement of multimodality texture-based prediction models via optimization of PET and MR image acquisition protocols: a proof of concept","year":2017,"lang":"en","type":"article","venue":"Physics in Medicine and Biology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; McGill University Health Centre","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Computer science; Artificial intelligence; Texture (cosmology); Pattern recognition (psychology); Set (abstract data type); Data acquisition; Computer vision; Image (mathematics)","score_opus":0.08899860225068965,"score_gpt":0.40254211762372427,"score_spread":0.3135435153730346,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2753319029","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27361795,0.00015740363,0.7216328,0.0012486688,0.00005069446,0.002886413,0.000018271068,0.0000069786565,0.00038084906],"genre_scores_gemma":[0.99009997,0.000047518755,0.009403519,0.000101759455,0.00009679171,0.00016577204,0.00007454138,0.000006348055,0.000003776119],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99915695,0.0000665532,0.00038136684,0.00018511407,0.00010948707,0.000100501486],"domain_scores_gemma":[0.99910134,0.000069303984,0.00041897304,0.00021382894,0.00015224419,0.000044291704],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045305412,0.00009689222,0.00045602545,0.000058912647,0.0000383593,0.0000022315105,0.00006256479,0.00005498919,0.000012757772],"category_scores_gemma":[0.00019148798,0.000070038026,0.000025367104,0.000047277248,0.0008756953,0.00007049056,0.00003607521,0.00014597028,1.6318733e-8],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017594289,0.001598486,0.08660246,0.0035558334,0.00020221058,0.000010000328,0.0026875492,0.017276868,0.6923189,0.0036077085,0.00012839578,0.19025214],"study_design_scores_gemma":[0.004852844,0.0014539508,0.004497348,0.00095888437,0.00007408406,0.0000053008694,0.00006451008,0.9469054,0.03709027,0.0040208534,0.000012101271,0.00006445708],"about_ca_topic_score_codex":0.00020279022,"about_ca_topic_score_gemma":0.0000011935259,"teacher_disagreement_score":0.92962855,"about_ca_system_score_codex":0.000012734769,"about_ca_system_score_gemma":0.000039242455,"threshold_uncertainty_score":0.3226536},"labels":[],"label_agreement":null},{"id":"W2753633438","doi":"10.1016/j.jasc.2017.06.060","title":"Glandular Cell Abnormalities on Pap Tests: Comparing Detections Rates and Cytology-Histology Correlations of Conventional and Liquid Based (BD SurePath) Methods","year":2017,"lang":"en","type":"article","venue":"Journal of the American Society of Cytopathology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Shared Health","funders":"","keywords":"Medicine; Cytology; Histology; Statistics; Pathology; Mathematics","score_opus":0.024662786876874607,"score_gpt":0.3578867456292945,"score_spread":0.3332239587524199,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2753633438","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9828365,0.0004477275,0.011024278,0.0052046413,0.0002110106,0.00006867372,0.000004602445,0.0000047761123,0.00019783199],"genre_scores_gemma":[0.96051186,0.00022628965,0.038496807,0.0006436255,0.000069728805,0.0000014858817,0.0000011039008,0.000009319365,0.000039804865],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99882644,0.00034231442,0.00044250174,0.00011624354,0.00013684892,0.00013563369],"domain_scores_gemma":[0.9973512,0.00064776675,0.0015121674,0.00023533367,0.0001774574,0.00007604001],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011875298,0.000102633145,0.00065596617,0.000068462476,0.00027166298,0.000008434134,0.00015802152,0.00006363959,0.0000071652553],"category_scores_gemma":[0.00074990786,0.000073489406,0.00023700522,0.000056764697,0.0025566684,0.000044523313,0.00007498155,0.000521786,1.2713201e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005405628,0.00017806001,0.8980014,0.00013907922,0.0001492916,0.000021348,0.0008059664,0.00027281928,0.09699693,0.0003899735,0.00053160236,0.001972993],"study_design_scores_gemma":[0.0021943268,0.0018969141,0.976516,0.00016290788,0.0003522392,0.0018860362,0.0009989972,0.008795188,0.005579063,0.0004773613,0.0010442614,0.000096671254],"about_ca_topic_score_codex":0.000098521086,"about_ca_topic_score_gemma":0.0000042218753,"teacher_disagreement_score":0.09141787,"about_ca_system_score_codex":0.000028123437,"about_ca_system_score_gemma":0.00011541476,"threshold_uncertainty_score":0.9420151},"labels":[],"label_agreement":null},{"id":"W2757225032","doi":"10.1016/j.ijrobp.2017.06.1772","title":"Anemia and Maximum Standardized Uptake Value (SUVmax) as Predictive Factors in Lung Cancers Treated With Stereotactic Body Radiation Therapy","year":2017,"lang":"en","type":"article","venue":"International Journal of Radiation Oncology*Biology*Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; University of Ottawa","funders":"","keywords":"Medicine; Univariate analysis; Stage (stratigraphy); Lung cancer; Proportional hazards model; Adenocarcinoma; Retrospective cohort study; Internal medicine; Regimen; Survival analysis; Multivariate analysis; Radiology; Oncology; Nuclear medicine; Cancer","score_opus":0.012424554840418657,"score_gpt":0.3372604846720405,"score_spread":0.32483592983162185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2757225032","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9914622,0.0005027001,0.002941482,0.0028755446,0.00089201453,0.00031845967,0.00003161269,0.000025056313,0.00095094607],"genre_scores_gemma":[0.9956394,0.002268698,0.00055057445,0.00054164516,0.0008564786,0.000009056958,0.000065353146,0.000032498105,0.000036334986],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9983886,0.00019507496,0.0005586673,0.0002632806,0.00035756637,0.0002368231],"domain_scores_gemma":[0.9976703,0.00029971046,0.0012585163,0.00018560253,0.0004044247,0.00018147437],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006211201,0.00022118406,0.00055338495,0.00021229227,0.00016104522,0.00008858291,0.00028607025,0.00019217274,0.00004106698],"category_scores_gemma":[0.0006403401,0.00016952306,0.00010713485,0.00007351241,0.0003636403,0.000439068,0.000035414087,0.00074896746,0.0000018458614],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002380989,0.00013408498,0.8945418,0.000009113183,0.0006259412,0.00012530816,0.00075794104,0.00048168094,0.0014413005,0.0007353028,0.00013209625,0.09863446],"study_design_scores_gemma":[0.023939786,0.0033057118,0.93706316,0.00019693779,0.00024471743,0.00038975006,0.00016769514,0.021147832,0.0014188773,0.0027554554,0.009099741,0.00027034237],"about_ca_topic_score_codex":0.00030620847,"about_ca_topic_score_gemma":0.00000718426,"teacher_disagreement_score":0.098364115,"about_ca_system_score_codex":0.0012780473,"about_ca_system_score_gemma":0.0008571087,"threshold_uncertainty_score":0.69129497},"labels":[],"label_agreement":null},{"id":"W2757862658","doi":"10.1158/0008-5472.can-17-0336","title":"<i>dcmqi</i> : An Open Source Library for Standardized Communication of Quantitative Image Analysis Results Using DICOM","year":2017,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"National Institute of Biomedical Imaging and Bioengineering; National Cancer Institute; National Institutes of Health","keywords":"DICOM; Computer science; Metadata; Interoperability; Digital imaging; Open source; Information retrieval; Digital image; Software; Image (mathematics); Image processing; Artificial intelligence; World Wide Web; Operating system","score_opus":0.17938538750494795,"score_gpt":0.5412057766962901,"score_spread":0.3618203891913422,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2757862658","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9626396,0.00082295487,0.016401617,0.013916182,0.000052057392,0.0012302513,0.0003530571,0.000040751114,0.0045435773],"genre_scores_gemma":[0.92839164,0.0006366456,0.068779595,0.00015613814,0.00010055467,0.00008238624,0.00022223456,0.000057197933,0.0015735838],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99826527,0.00035546342,0.00031936503,0.00031014008,0.00046327533,0.00028649875],"domain_scores_gemma":[0.9973097,0.0004966853,0.0002516462,0.0012987697,0.00044921035,0.00019401382],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031961936,0.00008855415,0.00045114552,0.0002434738,0.00077020103,0.0003671678,0.001075278,0.000053546017,0.00006958544],"category_scores_gemma":[0.0021352198,0.00007495806,0.00009730765,0.0003291543,0.0006752035,0.0006087104,0.000617743,0.00046525517,8.78735e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.04322419,0.0015486577,0.083588354,0.001651504,0.006335629,0.00006906579,0.018783202,0.0030154504,0.57036877,0.0093036005,0.06888925,0.19322233],"study_design_scores_gemma":[0.03161113,0.0025920135,0.05409671,0.002616841,0.0023552189,0.000010427429,0.005026611,0.62333095,0.07179857,0.0046499507,0.20109989,0.0008117151],"about_ca_topic_score_codex":0.003056386,"about_ca_topic_score_gemma":0.00008162078,"teacher_disagreement_score":0.6203155,"about_ca_system_score_codex":0.00008055026,"about_ca_system_score_gemma":0.00047453304,"threshold_uncertainty_score":0.59238416},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"software","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"software","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W2758773485","doi":"10.1016/j.ijrobp.2017.06.1651","title":"Pretreatment PET SUV is Not Correlated With Tumor Growth Rate in Early Stage Non–small Cell Lung Cancer Treated With Stereotactic Radiation Therapy","year":2017,"lang":"en","type":"article","venue":"International Journal of Radiation Oncology*Biology*Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; University of Ottawa","funders":"","keywords":"Medicine; Nuclear medicine; Stage (stratigraphy); Lung cancer; Standardized uptake value; Adenocarcinoma; Log-rank test; Cancer; Radiology; Survival analysis; Positron emission tomography; Internal medicine","score_opus":0.01288724687868663,"score_gpt":0.3163509711600599,"score_spread":0.30346372428137325,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2758773485","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9918856,0.00022765,0.0023160612,0.0039829034,0.0006208873,0.0004851733,0.00003862278,0.000023446068,0.00041962753],"genre_scores_gemma":[0.9954105,0.0012457571,0.00082018186,0.0013833942,0.0007091673,0.00003168763,0.00005597539,0.00004928818,0.00029406758],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9983149,0.00019947255,0.00058223616,0.00031286437,0.00030094298,0.00028955538],"domain_scores_gemma":[0.9969584,0.00024799403,0.0017669116,0.00023315912,0.0006196045,0.00017397587],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004998369,0.0002757589,0.0005749817,0.0002219789,0.00014399271,0.000101318,0.0003723781,0.00011598294,0.00006909282],"category_scores_gemma":[0.00014756955,0.00019689486,0.00011635464,0.0001217842,0.00022669295,0.00038198498,0.000031729414,0.0008082954,0.0000062229606],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0024066991,0.0004495872,0.97477865,0.000017030115,0.0007915126,0.0006014456,0.00091872877,0.00073777663,0.001944724,0.00013443254,0.00015392351,0.01706547],"study_design_scores_gemma":[0.029009465,0.0033235112,0.91615033,0.00029396088,0.00032440075,0.00024550883,0.00005296301,0.041849814,0.006851378,0.00011156975,0.0014862136,0.00030087237],"about_ca_topic_score_codex":0.0007737012,"about_ca_topic_score_gemma":0.000030143929,"teacher_disagreement_score":0.05862833,"about_ca_system_score_codex":0.0009211704,"about_ca_system_score_gemma":0.00076057686,"threshold_uncertainty_score":0.80291396},"labels":[],"label_agreement":null},{"id":"W2759538526","doi":"10.1016/j.ijrobp.2017.06.2053","title":"A Radiomic Prognostic Index Refines Risk Models for Distant Metastasis in HPV-Related Oropharyngeal Cancer","year":2017,"lang":"en","type":"article","venue":"International Journal of Radiation Oncology*Biology*Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto","funders":"","keywords":"Medicine; Univariate; Multivariate analysis; Multivariate statistics; Proportional hazards model; Stage (stratigraphy); Receiver operating characteristic; Oncology; Internal medicine; Radiation therapy; Univariate analysis; Cancer; Chemoradiotherapy; T-stage; Nuclear medicine; Machine learning","score_opus":0.024741269059791054,"score_gpt":0.3692007564003685,"score_spread":0.3444594873405774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2759538526","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88440186,0.0017635894,0.09304948,0.015338332,0.0041868007,0.00059205847,0.00017972213,0.00003202069,0.0004561567],"genre_scores_gemma":[0.9914124,0.0021803088,0.004097676,0.0005722078,0.0015282249,0.000042929933,0.00006512927,0.00003900804,0.000062119114],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980984,0.000176067,0.0008893668,0.0002779987,0.00027188106,0.0002862912],"domain_scores_gemma":[0.99673396,0.0004869214,0.001833442,0.00022007326,0.0005633504,0.00016225217],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011018611,0.00020561223,0.00070568814,0.00023087299,0.00017135423,0.000061435974,0.0005347589,0.0002093959,0.00004436512],"category_scores_gemma":[0.0019648536,0.00017152706,0.00027676305,0.000087973305,0.00033342614,0.00038239302,0.00007121934,0.0008398065,0.0000035265289],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00093711604,0.00039340905,0.58395904,0.000023963717,0.0009869711,0.000096335156,0.00039680107,0.009940518,0.0011964333,0.0068809567,0.0008711055,0.39431736],"study_design_scores_gemma":[0.022971587,0.0012357297,0.23960038,0.00030610498,0.00075027463,0.00033330565,0.00007054527,0.63853776,0.00044998,0.083219506,0.012145175,0.00037966628],"about_ca_topic_score_codex":0.0003006656,"about_ca_topic_score_gemma":0.00002677728,"teacher_disagreement_score":0.62859726,"about_ca_system_score_codex":0.0006878344,"about_ca_system_score_gemma":0.00065607275,"threshold_uncertainty_score":0.69946706},"labels":[],"label_agreement":null},{"id":"W2759779945","doi":"10.1016/j.ijrobp.2017.06.051","title":"Head and Neck Squamous Cell Cancer Response Assessment Biomarkers: Unplanned Analysis of the NRG Oncology RTOG 0522 PET Substudy","year":2017,"lang":"en","type":"article","venue":"International Journal of Radiation Oncology*Biology*Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier de l’Université de Montréal","funders":"","keywords":"Medicine; Head and neck squamous-cell carcinoma; Head and neck cancer; Cetuximab; Radiomics; Radiology; Primary tumor; Head and neck; Nuclear medicine; Image registration; Cancer; Oncology; Radiation therapy; Internal medicine; Metastasis; Surgery; Artificial intelligence; Colorectal cancer","score_opus":0.020926020806814966,"score_gpt":0.3982198512468871,"score_spread":0.37729383044007214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2759779945","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9757753,0.00040852936,0.0017382301,0.019192811,0.0019035564,0.00019538568,0.00005659277,0.0000113107135,0.00071827957],"genre_scores_gemma":[0.99542516,0.000537583,0.0020803767,0.0011800162,0.0006315933,0.000008265181,0.000025053518,0.000019251462,0.00009267547],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.997765,0.0006166688,0.0007772784,0.00024913286,0.0003717614,0.00022017784],"domain_scores_gemma":[0.99577713,0.00095898553,0.002177691,0.00032739004,0.00060214236,0.0001566338],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017670959,0.00018191866,0.00074109,0.0002867156,0.0002221219,0.000044307402,0.00062020356,0.00015808521,0.00007194279],"category_scores_gemma":[0.0012003689,0.00013281209,0.00033387312,0.00019263964,0.0005974973,0.00015912176,0.00015894708,0.00069922174,0.0000017074487],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018695727,0.0006008058,0.9444288,0.000011970083,0.002430794,0.00010372959,0.00051866256,0.000948305,0.00888037,0.00062366546,0.0007688328,0.038814515],"study_design_scores_gemma":[0.007924573,0.0013284482,0.9477838,0.000060269445,0.0015685591,0.00017120098,0.00015669229,0.025045982,0.00059268286,0.00066191197,0.014568127,0.00013775338],"about_ca_topic_score_codex":0.00020630681,"about_ca_topic_score_gemma":0.00005129866,"teacher_disagreement_score":0.03867676,"about_ca_system_score_codex":0.00071624084,"about_ca_system_score_gemma":0.0010327239,"threshold_uncertainty_score":0.54159194},"labels":[],"label_agreement":null},{"id":"W2760330350","doi":"10.1016/j.ijrobp.2017.06.250","title":"Long-Term Results of RTOG 0617: A Randomized Phase 3 Comparison of Standard Dose Versus High Dose Conformal Chemoradiation Therapy +/- Cetuximab for Stage III NSCLC","year":2017,"lang":"en","type":"article","venue":"International Journal of Radiation Oncology*Biology*Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":48,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Regional Cancer Foundation","funders":"","keywords":"Medicine; Cetuximab; Internal medicine; Clinical endpoint; Interquartile range; Randomization; Oncology; Cumulative incidence; Radiation therapy; Randomized controlled trial; Surgery; Cancer; Colorectal cancer; Cohort","score_opus":0.03713647022066558,"score_gpt":0.41810104942083276,"score_spread":0.3809645792001672,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2760330350","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9435096,0.0004371484,0.047652956,0.0035491362,0.003269948,0.0007828507,0.00028166568,0.000019744424,0.0004970006],"genre_scores_gemma":[0.9925705,0.0008574416,0.004334256,0.00021615162,0.0015417367,0.000017648212,0.0003776469,0.000028476577,0.000056129626],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.9971111,0.00021740515,0.001712755,0.00022808326,0.0004850746,0.00024558778],"domain_scores_gemma":[0.9917198,0.0013291101,0.005089043,0.00030437802,0.0014010047,0.00015666375],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021890053,0.00023173323,0.0014850106,0.00021320292,0.00014219462,0.000046201305,0.00055677356,0.00023774676,0.000041115098],"category_scores_gemma":[0.0029355465,0.00019108842,0.0004891613,0.00006632737,0.000755269,0.00036316348,0.000059468206,0.0005446363,0.0000015512001],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.5133843,0.001619854,0.022192527,0.0000569639,0.0022129877,0.000024380286,0.0015111534,0.00074821356,0.010799153,0.007666794,0.0008258208,0.4389579],"study_design_scores_gemma":[0.93111444,0.005822816,0.008377734,0.00019058003,0.0004427949,0.00003259113,0.00009978482,0.029271465,0.018485,0.001224059,0.00470395,0.0002347747],"about_ca_topic_score_codex":0.000063043335,"about_ca_topic_score_gemma":0.0000030436313,"teacher_disagreement_score":0.43872312,"about_ca_system_score_codex":0.00033797958,"about_ca_system_score_gemma":0.0007560414,"threshold_uncertainty_score":0.77923596},"labels":[],"label_agreement":null},{"id":"W2763540369","doi":"10.1093/annonc/mdx363.031","title":"Evaluation of a predictive radiomics signature for response to immune checkpoint inhibitors (ICIs)","year":2017,"lang":"en","type":"article","venue":"Annals of Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; Princess Margaret Cancer Centre","funders":"","keywords":"Medicine; Response Evaluation Criteria in Solid Tumors; Radiomics; Pembrolizumab; Melanoma; Oncology; Internal medicine; Progressive disease; Radiology; Cancer; Disease; Immunotherapy; Cancer research","score_opus":0.07723398424837682,"score_gpt":0.43951287049092774,"score_spread":0.3622788862425509,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2763540369","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95649296,0.0006133443,0.0013641173,0.037486658,0.0004384078,0.0011266181,0.000025036912,0.000011740335,0.0024411036],"genre_scores_gemma":[0.99654835,0.000057560243,0.0022846083,0.0005601788,0.00021081258,0.000092452494,0.000014500246,0.000019039026,0.00021248114],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99838823,0.00024028831,0.00051723176,0.00021363693,0.00043537692,0.000205239],"domain_scores_gemma":[0.99724877,0.00038574918,0.000571781,0.00044032198,0.0012211922,0.0001322159],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00875549,0.00010699857,0.000512912,0.00017277896,0.00009478689,0.0000073838874,0.00018667412,0.00018393477,0.000032671393],"category_scores_gemma":[0.017544974,0.00009328384,0.00020078699,0.0000627524,0.00023386488,0.00006223083,0.00007707362,0.00025043555,0.0000017801317],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.012738042,0.00048924354,0.0009116707,0.00012287364,0.00039274746,0.000012419307,0.0019910568,0.000982268,0.39329752,0.00009326777,0.005702504,0.5832664],"study_design_scores_gemma":[0.023667715,0.026859708,0.2599651,0.001030934,0.0017085511,0.00011447222,0.00084030814,0.07984221,0.47862893,0.005555675,0.12130253,0.00048387152],"about_ca_topic_score_codex":0.00006104035,"about_ca_topic_score_gemma":0.0000049803107,"teacher_disagreement_score":0.5827825,"about_ca_system_score_codex":0.000106883366,"about_ca_system_score_gemma":0.00081306696,"threshold_uncertainty_score":0.99073064},"labels":[],"label_agreement":null},{"id":"W2766350707","doi":"10.25011/cim.v40i5.28626","title":"Scientific Overview on CSCI-CITAC Annual General Meeting and 2016 Young Investigators' Forum","year":2017,"lang":"en","type":"article","venue":"Clinical and investigative medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Toronto; Queen's University; Université de Montréal; University of Calgary","funders":"Canadian Institutes of Health Research; Wellcome Trust","keywords":"Medicine; Family medicine; Political science; Medical education","score_opus":0.12543474023720402,"score_gpt":0.394462545283355,"score_spread":0.269027805046151,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2766350707","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8529006,0.00291381,0.000035198074,0.13553292,0.0017489134,0.00033995407,0.000011019293,0.00005933693,0.006458252],"genre_scores_gemma":[0.9736849,0.0014133842,0.0024148363,0.015266741,0.0021054063,0.000015658274,0.00003519284,0.000042895343,0.005021008],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9971785,0.00020048996,0.00080064504,0.0008475177,0.00051226706,0.0004605654],"domain_scores_gemma":[0.99705356,0.000304667,0.00042546523,0.0006474023,0.0002121356,0.0013567957],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.0027713978,0.00032379862,0.00088323856,0.00013912434,0.001091623,0.00014491972,0.00025404003,0.00017183309,0.00006184111],"category_scores_gemma":[0.018587898,0.00021085629,0.00009619536,0.000120125515,0.027345207,0.00031632927,0.00029749703,0.0010082871,0.000015351407],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008084135,0.000108844084,0.83983153,0.00021445424,0.00013497524,0.00011759164,0.00093758805,9.172823e-7,0.002146012,0.03280881,0.082793355,0.040825073],"study_design_scores_gemma":[0.007583545,0.0024416526,0.7861289,0.0059360648,0.00036575666,0.00016019444,0.00062013895,0.0056153573,0.00041892313,0.06349862,0.12666865,0.0005622137],"about_ca_topic_score_codex":0.00022778622,"about_ca_topic_score_gemma":0.00001846693,"teacher_disagreement_score":0.12078427,"about_ca_system_score_codex":0.00002152216,"about_ca_system_score_gemma":0.00021511315,"threshold_uncertainty_score":0.989679},"labels":[],"label_agreement":null},{"id":"W2766426262","doi":"","title":"A New Optimization Based Method for Estimation and Spatial Localization of Lung’s Air Volume from 3D CT Images","year":2017,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Volume (thermodynamics); Computer vision; Computer science; Artificial intelligence; Computed tomography; Mathematics; Medicine; Radiology; Physics","score_opus":0.00893072606545242,"score_gpt":0.32339032836511056,"score_spread":0.31445960229965814,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2766426262","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006627915,0.00004186165,0.99436,0.0039640088,0.0001150623,0.00032014877,0.000008341908,0.00003485484,0.00049290044],"genre_scores_gemma":[0.2619258,0.000007956641,0.7369963,0.00035120157,0.00010545333,0.0000059504873,0.00014760873,0.00001455463,0.00044520953],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99936795,0.000028405502,0.00019681796,0.00017827518,0.00013754476,0.00009099187],"domain_scores_gemma":[0.99928796,0.00012395608,0.00018456594,0.00021926149,0.00008818415,0.000096091666],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002635361,0.00008484199,0.00021155419,0.000057771973,0.00012401039,0.000039579805,0.0000603465,0.000036701047,0.00017293393],"category_scores_gemma":[0.0015369959,0.000072261435,0.000038304945,0.00002456623,0.000046628258,0.00011718056,0.000021152844,0.00006900066,6.7719577e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018439486,0.000052976047,0.03861186,0.00019993605,0.000059507736,0.0000036756555,0.000098446675,0.3946566,0.00082407583,0.00008679469,0.007869241,0.5573525],"study_design_scores_gemma":[0.0021412198,0.000075915224,0.009884481,0.00010185777,0.00015722174,0.0000032716957,0.0000057382467,0.9850959,0.0016146734,0.00015609252,0.00069315743,0.00007045587],"about_ca_topic_score_codex":0.0047730696,"about_ca_topic_score_gemma":0.000016184324,"teacher_disagreement_score":0.5904393,"about_ca_system_score_codex":0.000019513951,"about_ca_system_score_gemma":0.000084819825,"threshold_uncertainty_score":0.7215485},"labels":[],"label_agreement":null},{"id":"W2766552454","doi":"10.18632/oncotarget.22251","title":"Predicting survival time of lung cancer patients using radiomic analysis","year":2017,"lang":"en","type":"article","venue":"Oncotarget","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":69,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"École de Technologie Supérieure; McGill University","funders":"","keywords":"Medicine; Lung cancer; Stage (stratigraphy); Survival analysis; Rank correlation; Proportional hazards model; Correlation; Receiver operating characteristic; Radiomics; Carcinoma; Hazard ratio; Internal medicine; Oncology; Radiology; Confidence interval; Statistics; Mathematics","score_opus":0.011651504592341957,"score_gpt":0.33153261064246253,"score_spread":0.3198811060501206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2766552454","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99605215,0.00017652902,0.0008168693,0.00036755815,0.00038741992,0.00014133357,0.000022285005,0.000027215523,0.002008634],"genre_scores_gemma":[0.99701536,0.00003489898,0.0019652508,0.0000966459,0.00028456084,0.0000029937903,0.000041183943,0.00002518976,0.0005339258],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99878913,0.000043331544,0.00031348667,0.00024198245,0.00036297803,0.00024911243],"domain_scores_gemma":[0.99884266,0.000050585822,0.00038554042,0.0004413231,0.00012236598,0.00015755596],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039587234,0.00012978,0.0005365286,0.00016438693,0.00024037485,0.000035360266,0.00020064272,0.00006635485,0.00034768364],"category_scores_gemma":[0.00052417984,0.000113050795,0.00020505842,0.00014930814,0.00012354841,0.000109358574,0.00008573577,0.00024339586,0.0000039939664],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003945743,0.00008052764,0.9931484,0.000057072044,0.0007413476,0.000008269346,0.00021315763,0.0005227713,0.0043444177,0.000004899025,0.000306701,0.0005330154],"study_design_scores_gemma":[0.0008797837,0.000028083434,0.5819279,0.00008805848,0.001051352,0.0000011230384,0.0000056384965,0.41560423,0.00014829673,0.000004919965,0.00018572976,0.000074921016],"about_ca_topic_score_codex":0.001862203,"about_ca_topic_score_gemma":0.000013398977,"teacher_disagreement_score":0.41508144,"about_ca_system_score_codex":0.00011458037,"about_ca_system_score_gemma":0.000106713225,"threshold_uncertainty_score":0.46100777},"labels":[],"label_agreement":null},{"id":"W2766656768","doi":"10.1109/access.2019.2893635","title":"Discovery Radiomics With CLEAR-DR: Interpretable Computer Aided Diagnosis of Diabetic Retinopathy","year":2019,"lang":"en","type":"preprint","venue":"IEEE Access","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph; Vector Institute; University of Waterloo","funders":"Agence Nationale de la Recherche; Canada Foundation for Innovation; Defense Advanced Research Projects Agency; Canadian Institute for Advanced Research","keywords":"Interpretability; Diabetic retinopathy; Radiomics; Grading (engineering); CAD; Computer science; Limiting; Artificial intelligence; Medicine; Medical physics; Machine learning; Diabetes mellitus; Engineering","score_opus":0.01621215197414486,"score_gpt":0.3013120529865724,"score_spread":0.2850999010124275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2766656768","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94641125,0.00039843624,0.046979804,0.0013933907,0.002685221,0.00091189146,0.00004439055,0.00009255667,0.0010830434],"genre_scores_gemma":[0.99335504,0.0005956279,0.0031457013,0.0013396279,0.0007418783,0.00008564777,0.00010272124,0.00012680574,0.00050696055],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997362,0.00012773841,0.00068204105,0.000797702,0.000572501,0.00045797988],"domain_scores_gemma":[0.9975511,0.00035798174,0.00057848677,0.0011436313,0.00017337993,0.00019545345],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00045567742,0.00045634262,0.0013474002,0.0002866286,0.000047686404,0.00028153334,0.00085474644,0.00031896317,0.0000682436],"category_scores_gemma":[0.00015599998,0.00035491234,0.00028038427,0.00021229875,0.00027758803,0.0002901327,0.00076099933,0.0017789354,0.00001802174],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013410702,0.00073025876,0.90734166,0.006642978,0.0012408999,0.00032444808,0.0009379635,0.035131704,0.0009085516,0.000091562804,0.020464927,0.024843998],"study_design_scores_gemma":[0.014296088,0.0045044706,0.23722999,0.03928297,0.004394001,0.00045664437,0.00013368974,0.64812046,0.03892675,0.0017439737,0.0072698994,0.0036410936],"about_ca_topic_score_codex":0.00040781504,"about_ca_topic_score_gemma":0.0000044495914,"teacher_disagreement_score":0.67011166,"about_ca_system_score_codex":0.00014012554,"about_ca_system_score_gemma":0.00032064054,"threshold_uncertainty_score":0.99989027},"labels":[],"label_agreement":null},{"id":"W2766776149","doi":"10.1016/j.chest.2017.08.893","title":"A Comparison of Specimen Size and Diagnostic Performance of 19G vs 22G EBUS-TBNA Needles: A Preclinical Study","year":2017,"lang":"en","type":"article","venue":"CHEST Journal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Medicine; Nuclear medicine; Biopsy; Mediastinal lymphadenopathy; Granulomatous inflammation; Sampling (signal processing); Radiology; Pathology","score_opus":0.0476111675317609,"score_gpt":0.402873566720346,"score_spread":0.3552623991885851,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2766776149","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99693567,0.0005150582,0.00007847022,0.00094997784,0.00023604253,0.00018820433,8.483586e-7,0.0000064710175,0.0010892886],"genre_scores_gemma":[0.9971494,0.00043586857,0.0017976693,0.000056878005,0.0004106335,0.0000022240033,5.128683e-7,0.000014841724,0.00013199302],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9986659,0.00005707013,0.0006118962,0.00014306586,0.00034008946,0.000181978],"domain_scores_gemma":[0.9979279,0.00082754774,0.0005961458,0.0003115778,0.0001039713,0.0002328787],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010481656,0.0001155043,0.00060467026,0.000056050732,0.00019809368,0.00005034206,0.00022574424,0.000054401826,0.00007410525],"category_scores_gemma":[0.006612225,0.00008716682,0.00007848578,0.000036574995,0.0003448313,0.00009798208,0.000097745055,0.0007895297,0.0000027960432],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024254534,0.000678983,0.98151696,0.00020920984,0.00010440751,0.000042876727,0.0027361866,0.000025729345,0.0007829884,0.0000032617324,0.00035436745,0.013302511],"study_design_scores_gemma":[0.0033317537,0.0018414712,0.9857578,0.0006230455,0.00022025697,0.00022011633,0.0010273115,0.005793875,0.0005002854,0.000021935546,0.00058131857,0.000080774626],"about_ca_topic_score_codex":0.000025767073,"about_ca_topic_score_gemma":9.330694e-7,"teacher_disagreement_score":0.013221736,"about_ca_system_score_codex":0.000020728727,"about_ca_system_score_gemma":0.000096473384,"threshold_uncertainty_score":0.79159284},"labels":[],"label_agreement":null},{"id":"W2767046341","doi":"10.1038/s41598-017-13977-x","title":"Breast-Lesion Characterization using Textural Features of Quantitative Ultrasound Parametric Maps","year":2017,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":65,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; University of Toronto; Sunnybrook Health Science Centre","funders":"Natural Sciences and Engineering Research Council of Canada; Cure Brain Cancer Foundation; Canadian Institutes of Health Research; Terry Fox Foundation; Breast Cancer Society of Canada","keywords":"Parametric statistics; Ultrasound; Breast cancer; Radiology; Pattern recognition (psychology); Biopsy; Medicine; Breast ultrasound; Homogeneity (statistics); Lesion; Computer science; Artificial intelligence; Mathematics; Cancer; Pathology; Statistics; Mammography; Internal medicine","score_opus":0.02900572441618664,"score_gpt":0.33917734432013363,"score_spread":0.310171619903947,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2767046341","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9937002,0.00008034498,0.0015553954,0.00033844783,0.0033328247,0.00021965783,0.000005935667,0.000025820777,0.00074138696],"genre_scores_gemma":[0.9937995,0.000008413072,0.0044058077,0.000024830751,0.000092132555,0.0000017845301,0.00017086751,0.000014906821,0.0014817354],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99842626,0.000037282196,0.00038487697,0.00042102492,0.00052417215,0.00020636016],"domain_scores_gemma":[0.9980052,0.000058481357,0.00077371014,0.00078185124,0.00025220227,0.00012854348],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011424776,0.000114375216,0.00027487756,0.00025567092,0.0005522183,0.0002855575,0.000117604395,0.00006109217,0.000042225285],"category_scores_gemma":[0.0019134305,0.00008866954,0.00009788209,0.0002463435,0.0005040701,0.00025487482,0.00005480971,0.00020500526,0.000003507716],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000446238,0.000101030164,0.12946664,0.00010120844,0.000037473357,0.00030969575,0.0003038819,0.0000333366,0.84925175,0.00019178496,0.0008871738,0.019271424],"study_design_scores_gemma":[0.00042783056,0.000067741414,0.96042395,0.00045475134,0.0001252387,0.007544505,0.000107676475,0.004235531,0.023145901,0.0014123376,0.0018599526,0.00019461558],"about_ca_topic_score_codex":0.00012754905,"about_ca_topic_score_gemma":0.0000017604862,"teacher_disagreement_score":0.8309573,"about_ca_system_score_codex":0.00004108498,"about_ca_system_score_gemma":0.00012806544,"threshold_uncertainty_score":0.42472726},"labels":[],"label_agreement":null},{"id":"W2767329809","doi":"10.3166/ts.33.441-460","title":"Classification automatique de la densité des tissus mammaires","year":2016,"lang":"fr","type":"article","venue":"Traitement du signal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science","score_opus":0.014087826068972896,"score_gpt":0.29568938277188755,"score_spread":0.28160155670291465,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2767329809","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7893068,0.0041496353,0.17393987,0.02406465,0.0006424055,0.0003487561,0.000014030253,0.00019345732,0.0073403656],"genre_scores_gemma":[0.9816505,0.0010623833,0.008808967,0.00085333467,0.0015148915,0.00003358289,0.000010769193,0.00005099841,0.0060146013],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99776024,0.00050492823,0.00042965554,0.00032508734,0.00036653536,0.00061355915],"domain_scores_gemma":[0.99844784,0.0007277034,0.00013841761,0.00020476103,0.00008060847,0.00040067552],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0016120665,0.00023707928,0.00028425362,0.00011441132,0.00016937933,0.00007219054,0.0001652305,0.00019626279,0.0027779844],"category_scores_gemma":[0.00047343705,0.0001757721,0.000114979994,0.00012979665,0.0008013016,0.00015009967,0.000037847203,0.00033969287,0.0002390375],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000836895,0.00031324782,0.056532755,0.0003101055,0.00016856569,0.0005095196,0.0012361654,0.000049137172,0.153849,0.023143036,0.012142005,0.7516628],"study_design_scores_gemma":[0.0049744113,0.00055011857,0.7283379,0.0038220845,0.0005092517,0.0015599373,0.00036276274,0.08374224,0.0073887543,0.0071982094,0.16103041,0.00052392756],"about_ca_topic_score_codex":0.00012940676,"about_ca_topic_score_gemma":0.000007656343,"teacher_disagreement_score":0.75113887,"about_ca_system_score_codex":0.00048038425,"about_ca_system_score_gemma":0.00025966755,"threshold_uncertainty_score":0.9981336},"labels":[],"label_agreement":null},{"id":"W2767872427","doi":"10.1093/neuonc/nox168.838","title":"QLIF-29. FUNCTIONAL AND EMPLOYMENT OUTCOMES IN IDH MUTANT GLIOBLASTOMA","year":2017,"lang":"en","type":"article","venue":"Neuro-Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary; Alberta Health Services","funders":"","keywords":"Medicine; Glioblastoma; Cohort; Internal medicine; IDH1; Confidence interval; Oncology; Performance status; Radiation therapy; Chemotherapy; Surgery; Mutation; Biology","score_opus":0.021158529618510905,"score_gpt":0.33065285029169,"score_spread":0.3094943206731791,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2767872427","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95593894,0.00006121174,0.000114862494,0.038046453,0.0009546098,0.00020922699,0.0000020058587,0.000040739393,0.0046319766],"genre_scores_gemma":[0.993123,0.00008902035,0.00034293838,0.005883223,0.00025268007,0.000021765078,0.0000028666238,0.000022487591,0.00026203156],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99884504,0.000072778144,0.0002588822,0.0003135539,0.00020159165,0.0003081421],"domain_scores_gemma":[0.99906874,0.00026335465,0.00013251352,0.00031217985,0.00003037408,0.00019286275],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034117006,0.00013707888,0.00041220651,0.0001228856,0.0001909388,0.000033789718,0.00011844234,0.00010992877,0.00012189059],"category_scores_gemma":[0.0011932139,0.00011041242,0.000055823515,0.000034875935,0.0002486505,0.00006659339,0.00016334855,0.0005910315,0.000030334531],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004844335,0.00038446163,0.73606706,0.000036085585,0.00005563332,0.0020329345,0.0002768281,0.000019312865,0.09096018,0.0007661681,0.0030331132,0.1658838],"study_design_scores_gemma":[0.005990836,0.0015284513,0.7742077,0.000043195225,0.0000628018,0.0010254327,0.00006410013,0.004112184,0.00095746975,0.0003085337,0.21154054,0.00015872986],"about_ca_topic_score_codex":0.000096335745,"about_ca_topic_score_gemma":0.00008895924,"teacher_disagreement_score":0.20850742,"about_ca_system_score_codex":0.000104744155,"about_ca_system_score_gemma":0.00013348224,"threshold_uncertainty_score":0.45024878},"labels":[],"label_agreement":null},{"id":"W2767952516","doi":"10.1093/neuonc/nox168.735","title":"PATH-45. INTEGRATION OF MULTI-REGION (EPI)GENOMICS WITH MULTIMODALITY ADVANCED IMAGING HIGHLIGHTS GLIOMA INTRATUMORAL HETEROGENEITY","year":2017,"lang":"en","type":"article","venue":"Neuro-Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hospital for Sick Children","funders":"","keywords":"Glioma; Concordance; Radiogenomics; Genetic heterogeneity; Subtyping; Tumour heterogeneity; Biopsy; Magnetic resonance imaging; DNA methylation; Medicine; Pathology; Biology; Cancer research; Bioinformatics; Radiology; Gene; Internal medicine; Genetics; Cancer; Phenotype; Computer science","score_opus":0.0239340452823193,"score_gpt":0.33150609134248915,"score_spread":0.30757204606016986,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2767952516","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9761818,0.00009364129,0.014679229,0.0072403015,0.0006861638,0.0004708865,0.000005145347,0.0000777191,0.00056508346],"genre_scores_gemma":[0.9799168,0.00008836569,0.018891605,0.0007847306,0.0002098221,0.000024402307,0.000026035352,0.000043619923,0.000014603031],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9982243,0.0001964765,0.0004702448,0.0005087891,0.0002304966,0.000369672],"domain_scores_gemma":[0.99801046,0.00015489555,0.0006272349,0.00074852235,0.00020930338,0.0002496015],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035677906,0.000256983,0.0006506983,0.00012487217,0.00029035562,0.000043806776,0.0003078795,0.00013174774,0.000008236338],"category_scores_gemma":[0.00082851277,0.0001977151,0.00012069914,0.000074742566,0.00056342076,0.00021919815,0.00012393233,0.000670466,0.000005924261],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00084110984,0.0004039058,0.0356715,0.0000764472,0.00004482163,0.0011391946,0.00040970772,0.00009196626,0.8365305,0.00028092554,0.0001140261,0.12439586],"study_design_scores_gemma":[0.0234869,0.0035967727,0.2547516,0.0004734415,0.00052185013,0.004182702,0.0003486595,0.268591,0.41403514,0.00023236634,0.028937342,0.00084224937],"about_ca_topic_score_codex":0.00027467762,"about_ca_topic_score_gemma":0.00010270863,"teacher_disagreement_score":0.4224954,"about_ca_system_score_codex":0.00021291283,"about_ca_system_score_gemma":0.00025236956,"threshold_uncertainty_score":0.8062588},"labels":[],"label_agreement":null},{"id":"W2768038963","doi":"10.1093/neuonc/nox168.736","title":"PATH-46. AUTOMATED HISTOPATHOLOGIC CLASSIFICATION OF BRAIN TUMORS USING ARTIFICIAL INTELLIGENCE","year":2017,"lang":"en","type":"article","venue":"Neuro-Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network","funders":"","keywords":"Convolutional neural network; Artificial intelligence; Classifier (UML); Computer science; Digital pathology; Glioblastoma; Brain tumor; Workflow; Pathology; Pattern recognition (psychology); Medicine; Database","score_opus":0.07108547680609452,"score_gpt":0.3889134789199807,"score_spread":0.3178280021138862,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2768038963","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9720612,0.000048560945,0.009619719,0.012579794,0.00087355694,0.00027405875,0.0000029426487,0.00019063427,0.0043495162],"genre_scores_gemma":[0.99237406,0.000019306577,0.006014154,0.0013062863,0.000221236,0.000007678502,0.000009140463,0.000023645325,0.000024466228],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99849874,0.00020267481,0.0004980203,0.00033728452,0.00019887245,0.00026440102],"domain_scores_gemma":[0.99834365,0.00029938258,0.00057036744,0.00054092734,0.00010891743,0.0001367593],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007021563,0.00013743967,0.00044569792,0.00012781497,0.00023761738,0.00002381223,0.00027748148,0.00016375004,0.00007142813],"category_scores_gemma":[0.004696674,0.00012271141,0.000087838554,0.00008434129,0.00057128497,0.000070508264,0.00009935197,0.0005182355,0.000022274608],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000101543286,0.00019190603,0.005682317,0.000052372157,0.000008032858,0.00047974085,0.00019425669,0.00008336658,0.88286597,0.0031624143,0.00062046864,0.10655759],"study_design_scores_gemma":[0.00069215975,0.0014963519,0.0716315,0.00015633166,0.0001408076,0.0013762317,0.00026278454,0.886696,0.020446153,0.0027586462,0.01408066,0.00026237313],"about_ca_topic_score_codex":0.0000701261,"about_ca_topic_score_gemma":0.0000034226855,"teacher_disagreement_score":0.88661265,"about_ca_system_score_codex":0.00016674396,"about_ca_system_score_gemma":0.00029531817,"threshold_uncertainty_score":0.5622697},"labels":[],"label_agreement":null},{"id":"W2770592529","doi":"10.1245/s10434-017-6174-y","title":"Confusion Over Differences in Registration and Randomization Criteria for the LORIS (Low-Risk DCIS) Trial","year":2017,"lang":"en","type":"letter","venue":"Annals of Surgical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Institute for Cancer Research","funders":"National Institute for Health and Care Research; Cancer Research UK","keywords":"Medicine; Confusion; Surgical oncology; Randomization; MEDLINE; Randomized controlled trial; Internal medicine; Psychology","score_opus":0.07846885737898586,"score_gpt":0.412372384338204,"score_spread":0.33390352695921816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2770592529","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.078546695,0.0008807399,0.00068848074,0.9155539,0.0011837293,0.0015344701,0.000027513519,0.000013215069,0.0015712586],"genre_scores_gemma":[0.5794166,0.10700774,0.0006264441,0.28112924,0.024753755,0.00061911205,0.0011118068,0.00012892336,0.0052063884],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981885,0.00037304068,0.0006164897,0.00031510124,0.00026122958,0.00024565333],"domain_scores_gemma":[0.99541336,0.0033735512,0.0007423078,0.0002676651,0.00014308747,0.000060007034],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019259627,0.00018543561,0.0010281771,0.00012604188,0.00013054236,0.000042476113,0.0001593162,0.00069268915,0.00011200129],"category_scores_gemma":[0.0013793005,0.00011250721,0.0001929635,0.0000464658,0.0004291967,0.000056259094,0.00004575654,0.0011466512,8.110267e-7],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.05315941,0.00016595608,0.00096822996,0.00031400562,0.000164579,0.00038584898,0.00018715915,0.0000027626943,0.00003725522,0.00013847055,0.86520565,0.0792707],"study_design_scores_gemma":[0.06564908,0.0011696598,0.0013446611,0.00021315452,0.00017851465,0.000045661538,0.000010494695,0.0053804163,0.000011737723,0.0006873189,0.9251896,0.00011968235],"about_ca_topic_score_codex":0.00029179716,"about_ca_topic_score_gemma":0.000012682922,"teacher_disagreement_score":0.6344246,"about_ca_system_score_codex":0.00001873836,"about_ca_system_score_gemma":0.00015872563,"threshold_uncertainty_score":0.5342653},"labels":[],"label_agreement":null},{"id":"W2771121563","doi":"10.1200/jco.2015.33.15_suppl.e17681","title":"Palliative chemotherapy (CT) for advanced non-small cell lung cancer (NSCLC): Investigating disparities between patients who are treated versus those who are not.","year":2015,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Ottawa Hospital","funders":"","keywords":"Medicine; Internal medicine; Lung cancer; Palliative care; Performance status; Thrombocytosis; Anemia; Proportional hazards model; Chemotherapy; Multivariate analysis; Gastroenterology; Cancer; Exact test; Demographics","score_opus":0.1220872587877821,"score_gpt":0.46518319629160665,"score_spread":0.34309593750382456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2771121563","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98330253,0.0011246366,0.0011390491,0.011807498,0.0015127636,0.0005303183,0.000028471555,0.000018565626,0.00053615967],"genre_scores_gemma":[0.97785896,0.001615852,0.011007131,0.0059744576,0.0028482175,0.000032693588,0.000021251475,0.00007284043,0.0005685908],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9965771,0.00031685666,0.0019133999,0.00031289074,0.00045519034,0.00042455315],"domain_scores_gemma":[0.99115056,0.0034810505,0.0032428126,0.00018803743,0.0010183977,0.0009191366],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002044803,0.00026504227,0.002219206,0.0001123231,0.00009484863,0.000024389,0.00026057696,0.0002762554,0.00001685803],"category_scores_gemma":[0.00985408,0.00019697416,0.0004437272,0.00015012703,0.00028211967,0.00014192387,0.000058921305,0.0015739035,0.0000018241161],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0032923468,0.00043178114,0.9013681,0.00015738666,0.00038897558,0.00005489483,0.00041510482,0.00019289635,0.00002612142,0.0000069017347,0.01022571,0.083439775],"study_design_scores_gemma":[0.068105474,0.008217342,0.88628066,0.0031628269,0.00094575726,0.0000042294137,0.00062715274,0.008534445,0.00039447134,0.00015535082,0.023240136,0.00033215797],"about_ca_topic_score_codex":0.00009063855,"about_ca_topic_score_gemma":0.00003474515,"teacher_disagreement_score":0.08310761,"about_ca_system_score_codex":0.00039456514,"about_ca_system_score_gemma":0.001241443,"threshold_uncertainty_score":0.99848634},"labels":[],"label_agreement":null},{"id":"W2773020962","doi":"10.1016/j.radonc.2017.11.023","title":"Serial 4DCT/4DPET imaging to predict and monitor response for locally-advanced non-small cell lung cancer chemo-radiotherapy","year":2017,"lang":"en","type":"article","venue":"Radiotherapy and Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre","funders":"","keywords":"Medicine; Lung cancer; Radiation therapy; Radiology; Feature (linguistics); Stage (stratigraphy); Nuclear medicine; Oncology","score_opus":0.008679170986988375,"score_gpt":0.33915040188495177,"score_spread":0.3304712308979634,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2773020962","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9359412,0.0063823615,0.030296655,0.024527049,0.0011609971,0.0013889153,0.000021771993,0.00006304057,0.00021799424],"genre_scores_gemma":[0.8363914,0.012369038,0.12635623,0.01609595,0.004888193,0.0006558876,0.000016258824,0.00023598639,0.0029910537],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99833167,0.00010045462,0.00032511746,0.0005758644,0.00014133459,0.00052555127],"domain_scores_gemma":[0.9984626,0.0003544578,0.00020740437,0.00043796806,0.00008267919,0.00045487125],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008582616,0.0002925357,0.00070506945,0.00013347711,0.00050764484,0.000118305026,0.00022816616,0.00018047569,0.000055191515],"category_scores_gemma":[0.0002211443,0.00025658018,0.0000935711,0.000051203067,0.0002882687,0.00012077981,0.000049594426,0.00036578797,5.383893e-7],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.017777147,0.00019297749,0.08333878,0.0003098162,0.00021483321,0.00013462175,0.0028480173,0.000169262,0.36879548,0.000028581544,0.0057569803,0.5204335],"study_design_scores_gemma":[0.045635983,0.0047146366,0.15036488,0.0006169398,0.00030672568,0.00039851942,0.00030544616,0.19888501,0.008104334,0.000079339385,0.58965695,0.00093123125],"about_ca_topic_score_codex":0.00016174123,"about_ca_topic_score_gemma":0.000025109843,"teacher_disagreement_score":0.5839,"about_ca_system_score_codex":0.00041717783,"about_ca_system_score_gemma":0.00032638438,"threshold_uncertainty_score":0.9999886},"labels":[],"label_agreement":null},{"id":"W2773823062","doi":"10.19080/ctoij.2017.05.555653","title":"Radiomics in Radiation Oncology Precision Medicine","year":2017,"lang":"en","type":"article","venue":"Cancer therapy & Oncology International Journal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre","funders":"","keywords":"Radiation oncology; Radiomics; Medical physics; Medicine; Precision medicine; Radiation therapy; Oncology; Internal medicine; Radiology; Pathology","score_opus":0.03888044556241093,"score_gpt":0.45921810557837617,"score_spread":0.42033766001596523,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2773823062","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.70129555,0.0054023075,0.0017850515,0.25481406,0.012259658,0.00032626686,0.0000043381706,0.000031178908,0.024081575],"genre_scores_gemma":[0.9204482,0.059429117,0.0017467431,0.010538825,0.0068793185,0.000035349287,0.000019782794,0.000035602356,0.00086708047],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983194,0.00015628968,0.0005538288,0.00024394199,0.00045887465,0.00026769252],"domain_scores_gemma":[0.9983728,0.00020739106,0.00065307325,0.00024441592,0.00029940787,0.0002229124],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001415738,0.00015622548,0.000465598,0.00035921513,0.0002448701,0.00007153241,0.0006406482,0.00021042372,0.0011240557],"category_scores_gemma":[0.00083662075,0.00011999615,0.00010711879,0.000052669,0.0003472807,0.00023339907,0.000058745944,0.0011438264,0.000012062178],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013444887,0.00018841201,0.06725631,0.0000026690334,0.00022253707,0.0007144551,0.0010326061,0.000113278475,0.0065173213,0.00021909263,0.015524293,0.9068645],"study_design_scores_gemma":[0.016992442,0.0011141978,0.17696624,0.0002619266,0.000042637268,0.0024187532,0.00019336534,0.0053042443,0.00039736956,0.0017809569,0.7943786,0.00014931615],"about_ca_topic_score_codex":0.00027321052,"about_ca_topic_score_gemma":0.00005231593,"teacher_disagreement_score":0.9067152,"about_ca_system_score_codex":0.001461368,"about_ca_system_score_gemma":0.0008278374,"threshold_uncertainty_score":0.99978906},"labels":[],"label_agreement":null},{"id":"W2774263345","doi":"10.5281/zenodo.168403","title":"tferr/hIPNAT: hIPNAT 1.0.6","year":2016,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Upload; Scripting language; Computer science; Software; World Wide Web; Programming language","score_opus":0.026432682925558955,"score_gpt":0.27334624598744334,"score_spread":0.2469135630618844,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2774263345","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21382816,0.0004278525,0.04778043,0.061676547,0.00065366866,0.0011619496,0.00012822633,0.003681178,0.670662],"genre_scores_gemma":[0.9900903,0.00017606912,0.00070545403,0.00094767107,0.00037604,2.9269831e-8,0.0002427282,0.0012202868,0.0062414357],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984779,0.00016130214,0.00022098173,0.00036039736,0.00040373974,0.00037567967],"domain_scores_gemma":[0.99883837,0.000040626073,0.0000682509,0.00041895124,0.00031452093,0.0003192859],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0006579808,0.00012729019,0.00017668858,0.00019225053,0.0008953189,0.0001965141,0.00044936768,0.000062719206,0.017538635],"category_scores_gemma":[0.00185112,0.00009268217,0.00006926505,0.0002939691,0.00021629529,0.00014453848,0.0004751772,0.00031011392,0.009123405],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009996009,0.00012383006,0.00006661432,0.00005908275,0.00005517541,0.00007189094,0.00031296542,0.0000023580674,0.030430855,0.005197064,0.2521435,0.7114367],"study_design_scores_gemma":[0.0012569515,0.0002140722,0.0028252224,0.00011044915,0.000023693196,0.0004298342,0.00005595491,0.0002696636,0.00068814406,0.00029928406,0.9936958,0.00013095532],"about_ca_topic_score_codex":0.0000070722895,"about_ca_topic_score_gemma":3.6784648e-8,"teacher_disagreement_score":0.7762621,"about_ca_system_score_codex":0.00014529405,"about_ca_system_score_gemma":0.000005304695,"threshold_uncertainty_score":0.9916481},"labels":[],"label_agreement":null},{"id":"W2780938321","doi":"10.1038/nrurol.2017.216","title":"A valuable tool for prediction of repeat biopsy pathology","year":2017,"lang":"en","type":"review","venue":"Nature Reviews Urology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Hôpital Saint-Luc","funders":"","keywords":"Medicine; Biopsy; Pathology; Medical physics","score_opus":0.06591514647525142,"score_gpt":0.42256706671454236,"score_spread":0.35665192023929093,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2780938321","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000021067794,0.99251693,0.00091648556,0.0005211374,0.0016324874,0.0031796892,0.00012900723,0.000045761124,0.001056386],"genre_scores_gemma":[0.000002648336,0.99043965,0.0054477444,0.0005753361,0.0011056858,0.00047800184,0.0007321406,0.00008129269,0.0011375101],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99672276,0.00050520804,0.0014093968,0.00073912326,0.00019536188,0.0004281547],"domain_scores_gemma":[0.996344,0.00041733735,0.0016366092,0.0013110811,0.00016664191,0.00012433983],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.0028673753,0.00047011633,0.0049630874,0.0003148895,0.00011570487,0.000012825907,0.00042654344,0.0020305885,0.00007334292],"category_scores_gemma":[0.008019735,0.0003152598,0.0014029045,0.00015163686,0.00024816341,0.00004105647,0.000105329374,0.002637678,0.000029588035],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026589474,0.000054748878,0.000031978347,0.037290104,0.00016479325,0.000065779575,0.000008418825,9.915603e-8,0.00000552894,0.00029174148,0.009941413,0.9521188],"study_design_scores_gemma":[0.0006144511,0.0003560262,0.000027107684,0.007771927,0.004260424,0.0041756555,2.84195e-7,0.000060025464,2.7074742e-7,0.00012813666,0.9824367,0.00016898147],"about_ca_topic_score_codex":0.00000197397,"about_ca_topic_score_gemma":2.3092981e-7,"teacher_disagreement_score":0.9724953,"about_ca_system_score_codex":0.000068120324,"about_ca_system_score_gemma":0.00035765953,"threshold_uncertainty_score":0.99992996},"labels":[],"label_agreement":null},{"id":"W2784295143","doi":"10.1161/circ.132.suppl_3.11695","title":"Abstract 11695: The Kinetics of Circulating Monocyte Subsets and Microbial Translocation in the Acute Phase of ST-Elevation Myocardial Infarction Reveals Prognostic Values for Cardiovascular Outcomes","year":2015,"lang":"en","type":"article","venue":"Circulation","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brandon University","funders":"","keywords":"Medicine; Myocardial infarction; Cardiology; Internal medicine; Chromosomal translocation; Monocyte; Biochemistry","score_opus":0.0441109341415583,"score_gpt":0.3314244864793603,"score_spread":0.287313552337802,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2784295143","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96473515,0.00061256695,0.032289322,0.0010503797,0.00011987384,0.0011462175,0.000009778128,0.000011425392,0.000025304105],"genre_scores_gemma":[0.99876034,0.0000458935,0.0007900524,0.00008971559,0.00011915047,0.000037338286,0.00014221502,0.0000143085745,9.755416e-7],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99880475,0.00011835744,0.00045463417,0.00015914858,0.0003442235,0.00011888959],"domain_scores_gemma":[0.9990569,0.00026311429,0.00021598273,0.00021937412,0.0002085836,0.000036043137],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015965785,0.0001026443,0.0003070713,0.00010125438,0.000046237987,0.000017932049,0.0000633805,0.00007042313,8.690298e-7],"category_scores_gemma":[0.00093167234,0.000070203176,0.00017408797,0.00018641121,0.00009005496,0.00009712365,0.0000069905973,0.00014067974,1.7700381e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003147953,0.0003621347,0.54805267,0.0005792054,0.0010580074,0.000004855815,0.010626234,0.033270136,0.2691274,0.00043801116,0.00010269974,0.13606384],"study_design_scores_gemma":[0.0038187508,0.000096929354,0.95069486,0.00013327664,0.00067927275,0.000034063443,0.0003645776,0.042166576,0.00079261773,0.0010476722,0.00008694994,0.00008445413],"about_ca_topic_score_codex":0.00006804615,"about_ca_topic_score_gemma":0.000002225008,"teacher_disagreement_score":0.4026422,"about_ca_system_score_codex":0.000045792225,"about_ca_system_score_gemma":0.000043300668,"threshold_uncertainty_score":0.28628024},"labels":[],"label_agreement":null},{"id":"W2787245360","doi":"10.5281/zenodo.1022068","title":"firedrakeproject/petsc4py: The Python interface to PETSc","year":2017,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Python (programming language); Computer science; Computer graphics (images); Programming language","score_opus":0.038153984899268745,"score_gpt":0.3205495603117031,"score_spread":0.2823955754124344,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2787245360","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33612764,0.00019497973,0.019458555,0.11108003,0.0005500559,0.0016133465,0.000055203665,0.0013403149,0.5295799],"genre_scores_gemma":[0.99306566,0.0000473512,0.0006421288,0.0010860438,0.00034171672,6.4803885e-8,0.0001116208,0.00070727104,0.0039981483],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986525,0.00014486615,0.00018280817,0.0003448929,0.00034699056,0.00032793803],"domain_scores_gemma":[0.9983857,0.00002455833,0.00010019196,0.00097400614,0.00026276396,0.00025276854],"candidate_categories":["sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0009507322,0.000120904646,0.0001586435,0.00010478437,0.0037752038,0.0010556079,0.0011395568,0.000040542458,0.003516599],"category_scores_gemma":[0.0035438472,0.00009086236,0.000060179966,0.00014503102,0.00024607594,0.00012938674,0.0012849092,0.00049171207,0.0049058963],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015544791,0.00010901408,0.000083505016,0.000066675355,0.00006632604,0.000056877812,0.0022234807,0.00004357364,0.008744503,0.0012281088,0.47830433,0.50891817],"study_design_scores_gemma":[0.00052088854,0.00022991581,0.00626152,0.000070237045,0.000023490751,0.00029655252,0.00021171178,0.0016720943,0.0004821734,0.000061229235,0.9900641,0.00010608732],"about_ca_topic_score_codex":0.00005452772,"about_ca_topic_score_gemma":3.2717844e-7,"teacher_disagreement_score":0.656938,"about_ca_system_score_codex":0.000085104846,"about_ca_system_score_gemma":0.000006490148,"threshold_uncertainty_score":0.9999814},"labels":[],"label_agreement":null},{"id":"W2788899656","doi":"10.1259/bjr.20170498","title":"Development and validation of a radiomic signature to predict HPV (p16) status from standard CT imaging: a multicenter study","year":2018,"lang":"en","type":"article","venue":"British Journal of Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":151,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto","funders":"","keywords":"Medicine; Multicenter study; Signature (topology); Nuclear medicine; Radiology; Medical physics; Pathology; Mathematics","score_opus":0.008085955393163329,"score_gpt":0.27998922729427833,"score_spread":0.271903271901115,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2788899656","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9916078,0.0022224807,0.0046813446,0.00052792573,0.00049661077,0.00032437107,0.000020207714,0.000011767019,0.00010752974],"genre_scores_gemma":[0.9734967,0.00018173078,0.025332758,0.0004440063,0.00048049056,0.0000032413845,0.000013181231,0.000021568996,0.000026357191],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9982773,0.00019129824,0.00068790995,0.00023206526,0.00032989006,0.0002815251],"domain_scores_gemma":[0.9987734,0.00012900347,0.0003377738,0.00011891844,0.00031364273,0.0003272778],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000898493,0.00013504077,0.00060021295,0.00020821966,0.00007909649,0.000034946872,0.00012722285,0.000044548146,0.0001532962],"category_scores_gemma":[0.00087822106,0.00012892592,0.00006352675,0.00011479444,0.0001895536,0.000090943235,0.00005649362,0.0004988647,0.0000021290232],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001963341,0.00047974748,0.6128682,0.000057478763,0.0007740724,0.00305196,0.0070622847,0.000029769175,0.01469742,0.0000049448718,0.020201799,0.338809],"study_design_scores_gemma":[0.016761089,0.0030484062,0.91440314,0.0009390133,0.00048259698,0.02438765,0.0022780562,0.0015901752,0.0059065875,0.000082068036,0.02979928,0.00032194782],"about_ca_topic_score_codex":0.00013756602,"about_ca_topic_score_gemma":0.00001656053,"teacher_disagreement_score":0.33848706,"about_ca_system_score_codex":0.00011893922,"about_ca_system_score_gemma":0.0002343705,"threshold_uncertainty_score":0.5257446},"labels":[],"label_agreement":null},{"id":"W2789517368","doi":"10.1016/j.ijrobp.2018.01.047","title":"How Advances in Imaging Will Affect Precision Radiation Oncology","year":2018,"lang":"en","type":"article","venue":"International Journal of Radiation Oncology*Biology*Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":43,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre","funders":"","keywords":"Precision medicine; Medical physics; Personalized medicine; Molecular imaging; Computer science; Radiation oncology; Medical imaging; Medicine; Radiation therapy; Bioinformatics; Artificial intelligence; Pathology; Radiology; Biology","score_opus":0.01108980274247466,"score_gpt":0.3611727044257421,"score_spread":0.35008290168326744,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2789517368","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.72442,0.0062582972,0.19741464,0.054032963,0.012371662,0.00063454855,0.000023491924,0.00010827496,0.00473611],"genre_scores_gemma":[0.98055845,0.0030818859,0.0074416567,0.0022799398,0.00646161,0.00000953035,0.00006122927,0.00003562102,0.00007005628],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977702,0.00041905208,0.0007667553,0.00031820245,0.00039647034,0.00032934197],"domain_scores_gemma":[0.9969847,0.00075200584,0.0011832387,0.00016469999,0.00072974287,0.00018558635],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014169047,0.00022146852,0.00061706104,0.00042607295,0.00008679653,0.00005595079,0.000397518,0.0002295117,0.00006139675],"category_scores_gemma":[0.0020557796,0.00019350987,0.00021018629,0.00027798334,0.00046308828,0.00092615327,0.0000741421,0.00090724253,0.000019891775],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004176128,0.00026506296,0.24459176,0.000008002997,0.00010664591,0.000083867446,0.00041181833,0.00020854818,0.0046029757,0.0034230356,0.0010707749,0.7448099],"study_design_scores_gemma":[0.015529184,0.0036411888,0.063534416,0.00032291652,0.000184294,0.0013030157,0.0002682017,0.05764382,0.003497295,0.022330357,0.8313267,0.00041857854],"about_ca_topic_score_codex":0.000011591426,"about_ca_topic_score_gemma":0.0000060074985,"teacher_disagreement_score":0.8302559,"about_ca_system_score_codex":0.00123489,"about_ca_system_score_gemma":0.00059447816,"threshold_uncertainty_score":0.78911036},"labels":[],"label_agreement":null},{"id":"W2790751595","doi":"10.1158/1538-7445.sabcs17-p3-08-16","title":"Abstract P3-08-16: ER, PR and HER2 biomarkers in UK and Irish clinical breast cancer testing: analysis of results from &amp;gt;168,000 patients","year":2018,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Occupational Cancer Research Centre","funders":"","keywords":"Medicine; Breast cancer; Estrogen receptor; Oncology; Cancer; Internal medicine; Immunohistochemistry; Metastasis; Pathology; Gynecology","score_opus":0.10237587191104928,"score_gpt":0.4694576276018339,"score_spread":0.3670817556907846,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2790751595","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99438244,0.0011056636,0.000012465264,0.0023297446,0.00014731007,0.00029740288,0.0003877773,0.000014531091,0.0013226588],"genre_scores_gemma":[0.99721915,0.0014125245,0.00048381364,0.00020917907,0.00037636087,0.000025659283,0.00009774797,0.000025169238,0.00015042708],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99726975,0.00021944458,0.0006944885,0.00064012123,0.0007020733,0.00047414156],"domain_scores_gemma":[0.997356,0.0012004146,0.00017777263,0.00038538215,0.00047666163,0.00040377397],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025541508,0.000152138,0.0005736659,0.0005210877,0.00010878498,0.000046546735,0.0001650243,0.00014907192,0.00046846265],"category_scores_gemma":[0.0031583766,0.00012586056,0.00007118777,0.0013449306,0.0010927833,0.00006341918,0.00015385354,0.0008259736,0.000004161867],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012070173,0.00012845935,0.8045811,0.00004642897,0.00052552327,0.000011248473,0.00028196053,0.0000065699633,0.0010620216,4.842725e-7,0.008894517,0.18325469],"study_design_scores_gemma":[0.00364559,0.00016444894,0.9886313,0.0005806401,0.00021814054,0.0000018989737,0.00007085718,0.0035637503,0.00004933132,0.00002837873,0.002924576,0.000121069344],"about_ca_topic_score_codex":0.044392504,"about_ca_topic_score_gemma":0.0028950581,"teacher_disagreement_score":0.18405023,"about_ca_system_score_codex":0.0001770366,"about_ca_system_score_gemma":0.0002833219,"threshold_uncertainty_score":0.961971},"labels":[],"label_agreement":null},{"id":"W2791051851","doi":"10.1016/j.ijrobp.2018.01.057","title":"Radiomic Biomarkers to Refine Risk Models for Distant Metastasis in HPV-related Oropharyngeal Carcinoma","year":2018,"lang":"en","type":"article","venue":"International Journal of Radiation Oncology*Biology*Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":75,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; Princess Margaret Cancer Centre; Institute of Cancer Research; Ontario Institute for Cancer Research; University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"Medicine; Concordance; Stage (stratigraphy); Proportional hazards model; Oncology; Internal medicine; Radiation therapy; T-stage; Radiology; Nuclear medicine; Cancer","score_opus":0.019567005928317987,"score_gpt":0.34223884909466185,"score_spread":0.32267184316634384,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2791051851","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8403763,0.0005249233,0.14395548,0.01071144,0.0032273557,0.00043894723,0.00010409719,0.00003440183,0.00062706345],"genre_scores_gemma":[0.97484595,0.00029691032,0.02119393,0.0015934661,0.0018676145,0.000017415172,0.00010012613,0.000042573025,0.000042011936],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977985,0.00024827704,0.0010205447,0.00032105655,0.00028208413,0.0003295572],"domain_scores_gemma":[0.9975306,0.00046456163,0.00087237393,0.00017631247,0.0006988028,0.00025737382],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014704631,0.00021483915,0.0006584285,0.00043234325,0.00008657533,0.000025863073,0.0003861623,0.0001940976,0.00007025453],"category_scores_gemma":[0.0010857211,0.00018641117,0.00027529872,0.00031373085,0.00029875585,0.00021716516,0.0000627588,0.0005847174,0.000016515265],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004130668,0.00076854345,0.20059936,0.000026498883,0.0020458186,0.00016119999,0.0017262097,0.005313303,0.012634575,0.014878698,0.007957032,0.7497581],"study_design_scores_gemma":[0.042367656,0.0091169905,0.0814127,0.00027617143,0.0011431087,0.0010740443,0.0002974151,0.6751415,0.0050387974,0.08433012,0.09894524,0.00085626036],"about_ca_topic_score_codex":0.00010991201,"about_ca_topic_score_gemma":0.000011092497,"teacher_disagreement_score":0.74890184,"about_ca_system_score_codex":0.0009382951,"about_ca_system_score_gemma":0.0004882821,"threshold_uncertainty_score":0.7601627},"labels":[],"label_agreement":null},{"id":"W2793110326","doi":"10.1111/eci.12901","title":"Role of artificial intelligence in the care of patients with nonsmall cell lung cancer","year":2018,"lang":"en","type":"review","venue":"European Journal of Clinical Investigation","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":89,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Cybernet Systems Corporation (Canada); McGill University Health Centre","funders":"","keywords":"Lung cancer; Medicine; Narrative review; Intensive care medicine; Health care; Personalized medicine; Cancer; Stage (stratigraphy); Oncology; Internal medicine; Bioinformatics","score_opus":0.07095916770317968,"score_gpt":0.40283079420546325,"score_spread":0.3318716265022836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2793110326","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.056686144,0.9403282,0.0006331972,0.0001730233,0.00043748607,0.0005796842,0.000013157021,0.0000041794856,0.0011449499],"genre_scores_gemma":[0.051912494,0.9408958,0.0054324768,0.0002761239,0.0013536185,0.0000026281598,0.000046055127,0.00006634701,0.000014450713],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99505514,0.0015279176,0.0026298454,0.00016625854,0.0004996829,0.00012117404],"domain_scores_gemma":[0.9954595,0.0005750605,0.0030771256,0.00023018249,0.0005168709,0.00014127768],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0035345475,0.00017140065,0.001198428,0.00016534422,0.000022395774,0.000012271453,0.00035861845,0.00007448134,0.000020950849],"category_scores_gemma":[0.0017194414,0.00009158721,0.0003370458,0.00028837877,0.00044995712,0.00005060339,0.00003742016,0.0012449323,0.000003008593],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000088077635,0.00016250102,0.015284299,0.0040242136,0.00009026881,0.00002359011,0.0010328384,0.000026738808,0.0000018737845,0.000035472665,0.0001741909,0.97905594],"study_design_scores_gemma":[0.0036225396,0.009510815,0.097435206,0.22554646,0.010439416,0.00009127132,0.001490999,0.0032966025,0.00008261943,0.00035284998,0.6471374,0.0009938153],"about_ca_topic_score_codex":0.000008399508,"about_ca_topic_score_gemma":0.0000024123647,"teacher_disagreement_score":0.9780621,"about_ca_system_score_codex":0.00003099221,"about_ca_system_score_gemma":0.00055220217,"threshold_uncertainty_score":0.5408681},"labels":[],"label_agreement":null},{"id":"W2794513626","doi":"10.1016/j.jmir.2017.09.006","title":"Imaging Biomarkers for Precision Medicine in Locally Advanced Breast Cancer","year":2018,"lang":"en","type":"review","venue":"Journal of medical imaging and radiation sciences","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; Sunnybrook Health Science Centre","funders":"","keywords":"Breast cancer; Medicine; Precision medicine; Neoadjuvant therapy; Chemotherapy; Personalized medicine; Cancer; Oncology; Breast imaging; Tumour heterogeneity; Clinical trial; Translational research; Pathological; Radiology; Biomarker; Medical physics; Internal medicine; Bioinformatics; Pathology; Mammography; Biology","score_opus":0.02293012045601431,"score_gpt":0.4157764810434848,"score_spread":0.39284636058747047,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2794513626","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000095676936,0.9579747,0.0040700366,0.035673548,0.0016769757,0.00036953305,0.0000071209683,0.0000136768895,0.000118740005],"genre_scores_gemma":[0.00032967608,0.99446434,0.0018475984,0.0010563348,0.0022199147,0.000015306718,0.000008079911,0.00002865834,0.000030102332],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9957586,0.00019925802,0.0014966577,0.0004388456,0.0017064327,0.00040023634],"domain_scores_gemma":[0.9966551,0.0011912471,0.0011676739,0.00013546458,0.00028242415,0.00056807784],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0076037883,0.00030378788,0.0015552811,0.0010987694,0.0001819469,0.000084209685,0.0004702539,0.00014865845,0.000119964694],"category_scores_gemma":[0.0043644155,0.00017740404,0.00026370774,0.0007691308,0.0013332301,0.00030620626,0.000067753346,0.0008076612,0.0000012558532],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003970109,0.000036162168,0.0009829445,0.0016367272,0.00005618214,0.00006491697,0.00011658098,0.0000033226124,0.0000022444806,0.00001858734,0.012411154,0.9846315],"study_design_scores_gemma":[0.0029431388,0.00015882678,0.00067354174,0.060655758,0.00054263935,0.004317149,0.00039573899,0.03257813,4.36905e-7,0.00016323099,0.897333,0.00023836631],"about_ca_topic_score_codex":0.00006228513,"about_ca_topic_score_gemma":0.0000026758553,"teacher_disagreement_score":0.9843931,"about_ca_system_score_codex":0.00018060119,"about_ca_system_score_gemma":0.0015865007,"threshold_uncertainty_score":0.72343266},"labels":[],"label_agreement":null},{"id":"W2794682008","doi":"","title":"Using Gene Expression to Predict Tumor Location in Prostate Cancer Tissue","year":2018,"lang":"en","type":"article","venue":"Research in Computational Molecular Biology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Prostate cancer; Cancer; Gene expression; Computer science; Cancer research; Gene; Oncology; Internal medicine; Medicine; Biology; Genetics","score_opus":0.05918206320353468,"score_gpt":0.482250000141232,"score_spread":0.4230679369376973,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2794682008","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8836161,0.00030447112,0.11101938,0.004315178,0.00009497087,0.0005095671,0.0000037907112,0.000013001063,0.00012352763],"genre_scores_gemma":[0.9492231,0.000008957631,0.049902827,0.0005569343,0.00017122328,0.000058920617,0.000044713404,0.000015863734,0.000017481447],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984297,0.00032951764,0.00023723194,0.00033391538,0.0003076369,0.00036200808],"domain_scores_gemma":[0.9992443,0.00012659041,0.00003119521,0.00011944649,0.00033463823,0.00014385919],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000980728,0.00008061844,0.00016333172,0.00054664275,0.000059981863,0.000013930494,0.000103783605,0.00004874621,0.0000311819],"category_scores_gemma":[0.0005120933,0.0000731556,0.000014169869,0.0007426511,0.00020430564,0.000026465228,0.000109675835,0.00038105715,0.000018383655],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003430668,0.00014301992,0.061985962,0.000082495586,0.000014240964,0.0003129978,0.00029035736,0.08115009,0.8338355,0.0011019438,0.0001738324,0.02056653],"study_design_scores_gemma":[0.0033415635,0.0017933131,0.059107944,0.0013931466,0.000008993137,0.00020640981,0.0000784068,0.8264835,0.078244604,0.026374046,0.0026656275,0.00030245833],"about_ca_topic_score_codex":0.00052446476,"about_ca_topic_score_gemma":0.000015652255,"teacher_disagreement_score":0.75559086,"about_ca_system_score_codex":0.0002247885,"about_ca_system_score_gemma":0.0004052883,"threshold_uncertainty_score":0.29831988},"labels":[],"label_agreement":null},{"id":"W2796312214","doi":"10.3389/fonc.2018.00096","title":"Radiomics Evaluation of Histological Heterogeneity Using Multiscale Textures Derived From 3D Wavelet Transformation of Multispectral Images","year":2018,"lang":"en","type":"article","venue":"Frontiers in Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":59,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Larner College of Medicine, University of Vermont; Université de Lorraine","keywords":"Radiomics; Multispectral image; Transformation (genetics); Wavelet; Artificial intelligence; Computer science; Computer vision; Pattern recognition (psychology); Radiology; Medicine; Biology","score_opus":0.033639127446058514,"score_gpt":0.3580663790709777,"score_spread":0.3244272516249192,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2796312214","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8763996,0.000669083,0.1209615,0.00033172534,0.0006961354,0.000342721,0.000014549151,0.000013349728,0.0005713701],"genre_scores_gemma":[0.77620685,0.00006124858,0.223461,0.00010011929,0.00011061473,0.0000060705233,0.000039328992,0.00000976679,0.000005030509],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99843895,0.0003283465,0.0005175679,0.00021819673,0.00028985715,0.00020708225],"domain_scores_gemma":[0.9992569,0.00008961816,0.00024777322,0.00016200692,0.00017267313,0.000071045884],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00078085106,0.00012116864,0.0005684441,0.00019404411,0.00003981985,0.0000030290132,0.00010568278,0.00021456259,0.00010588939],"category_scores_gemma":[0.0005317585,0.00010732748,0.00008758443,0.00012709235,0.00058807794,0.000068953945,0.000020559428,0.0002766681,0.000001138652],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011726453,0.000616919,0.12639569,0.000087864166,0.00022346628,0.000023914497,0.004031204,0.00072624837,0.4778346,0.000014929113,0.0015779472,0.38729456],"study_design_scores_gemma":[0.006345998,0.00061726995,0.15997678,0.00008714458,0.00035240295,0.00004826934,0.00040308107,0.74998385,0.08097966,0.00038991045,0.0006770235,0.0001386212],"about_ca_topic_score_codex":0.0003915317,"about_ca_topic_score_gemma":0.000058129648,"teacher_disagreement_score":0.74925756,"about_ca_system_score_codex":0.00043693752,"about_ca_system_score_gemma":0.0001619084,"threshold_uncertainty_score":0.43766877},"labels":[],"label_agreement":null},{"id":"W2796316889","doi":"10.1016/j.juro.2018.02.2033","title":"MP63-10 DEVELOPMENT OF A CLINICAL DECISION-SUPPORT TOOL FOR CLASSIFICATION OF RENAL MASSES","year":2018,"lang":"en","type":"article","venue":"The Journal of Urology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vancouver Coastal Health Research Institute","funders":"","keywords":"Medicine; Clinical decision support system; Renal mass; Decision support system; Intensive care medicine; Urology; Medical physics; Internal medicine; Artificial intelligence; Kidney; Nephrectomy","score_opus":0.052828376953942095,"score_gpt":0.40956939191172814,"score_spread":0.35674101495778604,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2796316889","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8239556,0.0000822999,0.17196286,0.0031799432,0.0003294761,0.00009981995,7.622141e-7,0.0000026311518,0.000386629],"genre_scores_gemma":[0.93473566,0.000060026465,0.06409106,0.0005149301,0.00046097196,0.0000010714703,0.0000015465969,0.000008560848,0.00012615274],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982993,0.00011557281,0.0011672764,0.0000694088,0.00023228643,0.00011613803],"domain_scores_gemma":[0.9972892,0.001154306,0.0008799724,0.00015596858,0.00045348486,0.00006706368],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0044416063,0.000060197443,0.0003937392,0.00009237306,0.00004140852,0.00000192625,0.00017940815,0.000078569225,0.00020760017],"category_scores_gemma":[0.003180923,0.00003441391,0.000114406575,0.00006827705,0.00030885203,0.000025609124,0.00003064381,0.00027185833,0.0000050942012],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0127304355,0.00062419527,0.049476113,0.000094707175,0.0006239323,0.000017187764,0.0015099554,0.00004311972,0.06152649,0.0006217309,0.036919646,0.8358125],"study_design_scores_gemma":[0.0074285367,0.008968787,0.4213241,0.00017350656,0.0007977973,0.0012173072,0.00018300932,0.013389912,0.00501829,0.0026968478,0.5386643,0.00013762203],"about_ca_topic_score_codex":7.594487e-7,"about_ca_topic_score_gemma":0.0000010510721,"teacher_disagreement_score":0.8356749,"about_ca_system_score_codex":0.000010977571,"about_ca_system_score_gemma":0.0004369564,"threshold_uncertainty_score":0.38080916},"labels":[],"label_agreement":null},{"id":"W2799307461","doi":"10.1200/jco.2018.36.4_suppl.562","title":"Effect of PET-CT on disease recurrence and its management in patients with potentially resectable colorectal cancer liver metastases: The long-term results of a randomized control trial.","year":2018,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Health Science Centre; Western University; University of Toronto; Mount Sinai Hospital; Princess Margaret Cancer Centre; University Health Network; Health Sciences Centre; Ottawa Hospital; Queen's University; Toronto General Hospital; McMaster University; Grand River Hospital; Hotel Dieu Hospital; Ontario Clinical Oncology Group","funders":"","keywords":"Medicine; Colorectal cancer; Hazard ratio; Randomized controlled trial; Stage (stratigraphy); Proportional hazards model; Internal medicine; Log-rank test; Cancer; Surgery; Confidence interval","score_opus":0.02291461175545683,"score_gpt":0.4076205361921019,"score_spread":0.3847059244366451,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2799307461","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99556565,0.00051519315,0.00006084164,0.0015236643,0.00057803764,0.001502148,0.000012377311,0.000002025748,0.00024003017],"genre_scores_gemma":[0.9982952,0.00089357427,0.00015157154,0.00033373173,0.00025759923,0.000019968833,0.0000027465992,0.0000094791385,0.00003613718],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.9947358,0.0025718273,0.0018203184,0.00018608388,0.00051298755,0.00017302604],"domain_scores_gemma":[0.9903067,0.006960538,0.0020076123,0.00013732881,0.00036117618,0.00022668716],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.012172017,0.00012781467,0.0018912716,0.00013811719,0.000031119867,0.0000065620197,0.00016014825,0.00003431554,0.000031572803],"category_scores_gemma":[0.015106618,0.000059916634,0.0002851075,0.00012988521,0.0005860407,0.000052513664,0.000045136,0.0006540851,7.0970356e-7],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.920232,0.0011299509,0.030280108,0.0001311431,0.0008160526,0.0006125229,0.000031352793,0.000032883352,0.0000048178367,0.000022123411,0.00020005682,0.046506967],"study_design_scores_gemma":[0.7734637,0.033803523,0.18843001,0.00081134815,0.0018639616,0.000020651638,0.000003953549,0.0013578108,0.000044371838,0.000010996556,0.00013550476,0.000054149572],"about_ca_topic_score_codex":0.00003094711,"about_ca_topic_score_gemma":0.000017351837,"teacher_disagreement_score":0.1581499,"about_ca_system_score_codex":0.00004758499,"about_ca_system_score_gemma":0.00035171976,"threshold_uncertainty_score":0.9931896},"labels":[],"label_agreement":null},{"id":"W2799976003","doi":"10.1007/s12149-018-1260-1","title":"18F-FDG PET/CT metabolic tumor parameters and radiomics features in aggressive non-Hodgkin’s lymphoma as predictors of treatment outcome and survival","year":2018,"lang":"en","type":"article","venue":"Annals of Nuclear Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":100,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; Women's College Hospital; University of Toronto; University Health Network; Mount Sinai Hospital","funders":"","keywords":"Medicine; Lymphoma; Positron emission tomography; Internal medicine; Retrospective cohort study; Aggressive lymphoma; Oncology; Radiomics; Nuclear medicine; Radiology; Rituximab","score_opus":0.02597001224701781,"score_gpt":0.33723543595977146,"score_spread":0.3112654237127537,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2799976003","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9882485,0.002517973,0.000003060017,0.0071576852,0.00032960434,0.00033233457,0.000009613226,0.000024557321,0.0013766717],"genre_scores_gemma":[0.9929383,0.0036140764,0.0006993801,0.0023107422,0.00025952098,0.0000048905504,0.000010755851,0.00005023592,0.00011213659],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99815226,0.00010372778,0.00063698436,0.00038126807,0.00037568793,0.00035006722],"domain_scores_gemma":[0.9984809,0.00026356895,0.00044189786,0.0003312205,0.00013533482,0.00034705125],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006626601,0.0002881005,0.001185768,0.00037863813,0.00005920113,0.00000963166,0.00012677559,0.000026401654,0.00006224895],"category_scores_gemma":[0.0013315893,0.00020215022,0.00009774695,0.0002465228,0.0012887563,0.00007344856,0.00007066658,0.00019739162,0.0000030937993],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004043279,0.0011740311,0.81961954,0.0010303003,0.0021634605,0.0053689703,0.0106921075,0.000023813642,0.014384143,0.0023840168,0.01135072,0.12776561],"study_design_scores_gemma":[0.013249775,0.008118285,0.9448849,0.0016778365,0.0006637047,0.004078856,0.002199127,0.0033541038,0.0019688022,0.00032707554,0.01908928,0.00038827618],"about_ca_topic_score_codex":0.0018418363,"about_ca_topic_score_gemma":0.000023338738,"teacher_disagreement_score":0.12737733,"about_ca_system_score_codex":0.00003145175,"about_ca_system_score_gemma":0.00007991213,"threshold_uncertainty_score":0.82434464},"labels":[],"label_agreement":null},{"id":"W2801459697","doi":"10.1016/j.compmedimag.2019.04.005","title":"Combo loss: Handling input and output imbalance in multi-organ segmentation","year":2019,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":23,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Artificial intelligence; Computer science; Segmentation; Deep learning; Voxel; False positive paradox; Pattern recognition (psychology); False positives and false negatives; Image segmentation; Artificial neural network; Inference; Medical imaging; Leverage (statistics); Machine learning; Autoencoder; Cross entropy; Computer vision","score_opus":0.010698468367061762,"score_gpt":0.2887381605245697,"score_spread":0.2780396921575079,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2801459697","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93416446,0.0016417917,0.054883134,0.008356346,0.00046524574,0.00029388035,0.000001475743,0.00009659835,0.00009706609],"genre_scores_gemma":[0.98068446,0.0015763432,0.011778626,0.005674955,0.000119309145,0.000006279981,0.000032191074,0.000028352337,0.00009949508],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99839854,0.000084852334,0.00036603,0.0004236751,0.00040109066,0.000325829],"domain_scores_gemma":[0.99908537,0.00019978314,0.000083110215,0.00018339722,0.0000498602,0.00039850108],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00072912156,0.00019555645,0.00045836525,0.00023721662,0.00007881365,0.000070530965,0.00010129861,0.00010146914,0.000016485728],"category_scores_gemma":[0.0002684037,0.00016992757,0.00004820757,0.00023324338,0.00033243536,0.0001064052,0.00013483656,0.0007633358,0.0000045966535],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006540472,0.00014051722,0.88535,0.00034733405,0.000037782032,0.00026085117,0.00073991576,0.000006805975,0.0019488838,0.0003093075,0.00017509749,0.110618114],"study_design_scores_gemma":[0.010608956,0.00007991639,0.23889281,0.0012479963,0.00004281099,0.00057222124,0.00014273204,0.74401414,0.00007670326,0.00025338042,0.0037932426,0.0002750916],"about_ca_topic_score_codex":0.000083443134,"about_ca_topic_score_gemma":0.0000037246248,"teacher_disagreement_score":0.74400735,"about_ca_system_score_codex":0.000022270282,"about_ca_system_score_gemma":0.00007457442,"threshold_uncertainty_score":0.6929445},"labels":[],"label_agreement":null},{"id":"W2805529185","doi":"10.1038/s41598-018-22357-y","title":"Radiomics analysis at PET/CT contributes to prognosis of recurrence and survival in lung cancer treated with stereotactic body radiotherapy","year":2018,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":155,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; University of Toronto; Sunnybrook Health Science Centre","funders":"","keywords":"Radiomics; Lung cancer; Medicine; Radiation therapy; Stereotactic radiotherapy; Survival analysis; Overall survival; Radiosurgery; Radiology; Nuclear medicine; Oncology; Internal medicine","score_opus":0.009230629689520788,"score_gpt":0.30714406992957577,"score_spread":0.297913440240055,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2805529185","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9965008,0.0008912288,0.00040691748,0.0008249822,0.0006848972,0.0005217378,0.0000038201442,0.000023563782,0.00014203413],"genre_scores_gemma":[0.9981529,0.00007678956,0.0008580544,0.00007246827,0.00004299172,0.00003276932,0.000026378304,0.000016063244,0.000721547],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9980876,0.00007059871,0.00048267256,0.0006567596,0.00040071263,0.0003016453],"domain_scores_gemma":[0.998757,0.0000768683,0.0002762608,0.0004440299,0.00024768081,0.00019817543],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014116463,0.00015249007,0.00056991936,0.0005918907,0.0001282253,0.00008157436,0.00007232235,0.000013469596,0.00008838858],"category_scores_gemma":[0.00029622033,0.00011232864,0.00006972226,0.0019475011,0.00049488136,0.00007221887,0.000039004208,0.00014028509,4.5943437e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015798434,0.00007935388,0.9857178,0.00006375185,0.00044937263,0.00083848654,0.00023112149,0.000044575077,0.010282995,0.00000583844,0.0007174317,0.0014113408],"study_design_scores_gemma":[0.0023107405,0.0004071956,0.90119123,0.00082497956,0.0017237565,0.0015982382,0.00008827771,0.06336269,0.021411028,0.000040937535,0.0066482252,0.00039268108],"about_ca_topic_score_codex":0.0007312799,"about_ca_topic_score_gemma":0.00037034,"teacher_disagreement_score":0.084526494,"about_ca_system_score_codex":0.00019189206,"about_ca_system_score_gemma":0.00016112012,"threshold_uncertainty_score":0.4580629},"labels":[],"label_agreement":null},{"id":"W2806070638","doi":"10.1016/j.jogc.2018.03.074","title":"Choosing Wisely in Low Grade, Low Risk Endometrial Cancer Patients: the Value of Pre-Operative MRI, Lymph Node Dissection, and Postoperative Detailed Pathology","year":2018,"lang":"en","type":"article","venue":"Journal of Obstetrics and Gynaecology Canada","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Medicine; Endometrial cancer; Dissection (medical); Lymphovascular invasion; Lymph node; Hysterectomy; Radiology; Stage (stratigraphy); Carcinoma; Adjuvant therapy; Cancer; Metastasis; Internal medicine","score_opus":0.005221416051923996,"score_gpt":0.257704777615473,"score_spread":0.252483361563549,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2806070638","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99134094,0.0026451864,0.00021156324,0.0011984437,0.0043006297,0.00021367196,0.000017324008,0.0000017770461,0.000070469534],"genre_scores_gemma":[0.9977401,0.00090744655,0.00035209508,0.00085675943,0.00010042848,0.000004519626,0.0000023848522,0.000012746841,0.000023520028],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9984447,0.00028616493,0.0005874146,0.00017663211,0.00027398125,0.00023114911],"domain_scores_gemma":[0.9966355,0.0019982567,0.0005239937,0.00009322442,0.0005883939,0.00016060701],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00056800095,0.0001433295,0.00050893705,0.00031705192,0.00018079921,0.000019876627,0.00009885727,0.00010337466,0.000053840304],"category_scores_gemma":[0.011144949,0.00009163634,0.00004552522,0.00049976073,0.00034882006,0.00008236114,0.00004462959,0.00058897625,7.323626e-8],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000076635966,0.0001270191,0.9771361,0.000028979068,0.00013436102,0.00023119104,0.0011502386,0.0003426805,0.00011421066,0.00003546905,0.00017706232,0.0204461],"study_design_scores_gemma":[0.006416324,0.00070196856,0.9872255,0.000048912003,0.00012982842,0.00008425737,0.00031480854,0.004433139,0.00021767542,0.000055846536,0.000280274,0.00009148733],"about_ca_topic_score_codex":0.0139179,"about_ca_topic_score_gemma":0.010179059,"teacher_disagreement_score":0.020354612,"about_ca_system_score_codex":0.00052115135,"about_ca_system_score_gemma":0.0010250536,"threshold_uncertainty_score":0.9971846},"labels":[],"label_agreement":null},{"id":"W2806274737","doi":"10.1016/j.atherosclerosissup.2018.04.242","title":"Copy Number Variation Analysis in the Diagnosis of MODY","year":2018,"lang":"en","type":"article","venue":"Atherosclerosis Supplements","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Robarts Clinical Trials; Western University","funders":"","keywords":"Variation (astronomy); Copy-number variation; Genetics; Biology; Physics; Gene","score_opus":0.022810124718670683,"score_gpt":0.3339658295422288,"score_spread":0.31115570482355814,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2806274737","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99373513,0.000010252299,0.0026799778,0.0021389062,0.000083160594,0.00026884288,0.000019263009,0.000013646982,0.001050843],"genre_scores_gemma":[0.9958713,0.00008552546,0.002448819,0.0012814094,0.00011261188,0.000065582266,0.00006674157,0.000014438565,0.0000535485],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99868023,0.000115033494,0.000358075,0.00021273068,0.00041232136,0.00022162645],"domain_scores_gemma":[0.999276,0.00012665072,0.00012524296,0.00034454843,0.00007413079,0.000053422256],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007147401,0.00010934967,0.00028246708,0.00012738297,0.000069138936,0.00002103795,0.00017712984,0.0000479989,0.002178811],"category_scores_gemma":[0.00014662792,0.000076031385,0.00013116881,0.0008654488,0.00010668425,0.00005903591,0.00003790757,0.0001536952,0.000039921288],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018894389,0.0002581709,0.9926631,0.000011162943,0.0002375192,8.435869e-7,0.0018749866,0.000012300595,0.0012842136,0.00019321535,0.0022525324,0.0011930717],"study_design_scores_gemma":[0.0013086172,0.0001393725,0.98901683,0.000045927518,0.00054795976,0.0000014245228,0.00017087751,0.003895351,0.0015911012,0.00013768404,0.0030663116,0.000078520105],"about_ca_topic_score_codex":0.0011193935,"about_ca_topic_score_gemma":0.00008077268,"teacher_disagreement_score":0.0038830505,"about_ca_system_score_codex":0.000041368774,"about_ca_system_score_gemma":0.000021477004,"threshold_uncertainty_score":0.99873334},"labels":[],"label_agreement":null},{"id":"W2806368367","doi":"10.1200/jco.2017.35.15_suppl.3601","title":"Survival prediction in patients treated by FOLFIRI and bevacizumab for metastatic colorectal cancer (PRODIGE 9) using contrast-enhanced CT texture analysis (SPECTRA).","year":2017,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre","funders":"","keywords":"Medicine; Bevacizumab; FOLFIRI; Colorectal cancer; Internal medicine; Multivariate analysis; Oncology; Nuclear medicine; Gastroenterology; Radiology; Chemotherapy; Cancer; Irinotecan","score_opus":0.05780382940564195,"score_gpt":0.4582889742829536,"score_spread":0.4004851448773117,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2806368367","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99314684,0.00025841096,0.0029318843,0.002372189,0.0007082963,0.0003709058,0.00003919176,0.0000062288127,0.000166034],"genre_scores_gemma":[0.9972911,0.00028396535,0.0016619316,0.0002807327,0.0003666258,0.000007711703,0.000018443103,0.0000168114,0.000072662064],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99735904,0.00027940754,0.0015460079,0.00025363648,0.00029972682,0.0002621865],"domain_scores_gemma":[0.9963045,0.0010616719,0.0018597363,0.00014393283,0.0003293696,0.00030078206],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002531917,0.00015077736,0.0017164664,0.00018314543,0.00014021203,0.000036044352,0.00014315992,0.00014588043,0.00004224172],"category_scores_gemma":[0.0066474024,0.00010916306,0.00037330255,0.000121085825,0.00025004882,0.00015833678,0.000029621991,0.00086447614,3.2464632e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004049487,0.000884748,0.8867348,0.000030487963,0.0017885483,0.00007310697,0.00007393425,0.00012180231,0.00093123567,0.0000064059886,0.0005396926,0.10476574],"study_design_scores_gemma":[0.022045694,0.004484478,0.9316526,0.000092707494,0.0035338684,0.000028140943,0.000036289293,0.036396217,0.00014559628,0.00007782599,0.0014045819,0.00010198062],"about_ca_topic_score_codex":0.00025923204,"about_ca_topic_score_gemma":0.00022637864,"teacher_disagreement_score":0.10466376,"about_ca_system_score_codex":0.00021064497,"about_ca_system_score_gemma":0.00044495324,"threshold_uncertainty_score":0.79580414},"labels":[],"label_agreement":null},{"id":"W2807137550","doi":"10.11159/tann18.1","title":"Non-Patchy Strategy for Interatomic Distances from Extended X-rayAbsorption Fine Structure","year":2018,"lang":"en","type":"article","venue":"Proceedings of the International Conference of Theoretical and Applied Nanoscience and Nanotechnology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Absorption (acoustics); Materials science; X-ray absorption fine structure; Interatomic potential; Optics; Physics; Molecular dynamics; Spectroscopy","score_opus":0.009693244705855572,"score_gpt":0.2659667669916715,"score_spread":0.2562735222858159,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2807137550","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99250585,0.000023260789,0.0017628907,0.0046250257,0.00010457701,0.00019278046,0.000031131654,0.00001277603,0.000741722],"genre_scores_gemma":[0.9975323,0.000038316626,0.0021688663,0.00015297136,0.000060336144,0.000008951898,0.000003046713,0.000004941226,0.000030250289],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99922955,0.0000014728022,0.00021647086,0.00025265783,0.0001743489,0.00012548541],"domain_scores_gemma":[0.99946916,0.000046711953,0.0001544234,0.000061649196,0.0002268825,0.000041162257],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014336404,0.000097540775,0.00021507515,0.00007496476,0.000070137656,0.0000292494,0.00031510947,0.00010199185,0.000050048347],"category_scores_gemma":[0.00022288867,0.000060213468,0.00003279433,0.00010399269,0.0025590223,0.00006484015,0.00015604173,0.00016406526,1.6232083e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017279561,0.000016620916,0.00061044353,0.000020424899,0.00000934628,4.839244e-8,0.000060455597,1.0265076e-7,0.5406099,0.44921586,0.000020444955,0.009263549],"study_design_scores_gemma":[0.00057589094,0.00025700824,0.0013140767,0.00015372604,0.000028041237,0.0000112963935,0.00022420344,0.00883913,0.58033174,0.4080942,0.00010727183,0.00006341746],"about_ca_topic_score_codex":0.000008058976,"about_ca_topic_score_gemma":0.000001870447,"teacher_disagreement_score":0.04112168,"about_ca_system_score_codex":0.00000953452,"about_ca_system_score_gemma":0.00003286663,"threshold_uncertainty_score":0.9428825},"labels":[],"label_agreement":null},{"id":"W2807250715","doi":"10.1200/jco.2018.36.4_suppl.591","title":"Systematic review and meta-analysis of the effect of pre-operative PET/PET-CT in the management of patients with potentially resectable colorectal cancer liver metastasis.","year":2018,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto General Hospital; University Health Network; University of Toronto; Ontario Clinical Oncology Group; McMaster University","funders":"","keywords":"Medicine; Colorectal cancer; Positron emission tomography; Metastasis; PET-CT; Radiology; Meta-analysis; Cancer; Subgroup analysis; Nuclear medicine; Internal medicine","score_opus":0.04073627842637377,"score_gpt":0.43498220910821606,"score_spread":0.39424593068184227,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2807250715","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98761994,0.008536978,0.00007578429,0.0022116883,0.00009225534,0.001154153,0.000008878634,8.9944905e-7,0.00029943747],"genre_scores_gemma":[0.995941,0.0021113174,0.0010599096,0.00077734166,0.000024752346,0.000020346468,0.0000010656321,0.00000706927,0.000057206835],"study_design_codex":"meta_analysis","study_design_gemma":"meta_analysis","domain_scores_codex":[0.99451363,0.0025711628,0.0020748964,0.00013657325,0.0005844555,0.000119309625],"domain_scores_gemma":[0.99457556,0.0020229171,0.0026658857,0.00023151693,0.00043456696,0.00006953612],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009322014,0.00012023266,0.0038854517,0.00011547938,0.000028513483,0.0000041036587,0.0002690818,0.000022275433,0.00013777218],"category_scores_gemma":[0.0021022644,0.000043325024,0.0008190361,0.00047153092,0.0004616756,0.000047269998,0.00007530509,0.0005164565,2.2573312e-7],"study_design_candidate":"meta_analysis","study_design_consensus":"meta_analysis","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008554872,0.0029025632,0.18144964,0.110116035,0.68912333,0.00093409687,0.0009167731,0.0005268648,0.00005537525,0.00021932684,0.0010338293,0.0041672923],"study_design_scores_gemma":[0.0036365835,0.010631807,0.23610643,0.0036743141,0.74486154,0.000111746645,0.00007620983,0.00065953314,0.00007418014,0.000007814908,0.000094229224,0.00006558553],"about_ca_topic_score_codex":0.00010102292,"about_ca_topic_score_gemma":0.000088562985,"teacher_disagreement_score":0.106441714,"about_ca_system_score_codex":0.000035015782,"about_ca_system_score_gemma":0.00015501078,"threshold_uncertainty_score":0.32308426},"labels":[],"label_agreement":null},{"id":"W2808749774","doi":"10.1016/j.acra.2018.05.017","title":"Interobserver Variation in Response Evaluation Criteria in Solid Tumors 1.1","year":2018,"lang":"en","type":"article","venue":"Academic Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Tellabs (Canada)","funders":"","keywords":"Medicine; Kappa; Response Evaluation Criteria in Solid Tumors; Confidence interval; Radiological weapon; Nuclear medicine; Cohen's kappa; Waiver; Clinical trial; Radiology; Internal medicine; Statistics","score_opus":0.03315993301833307,"score_gpt":0.39572721074999734,"score_spread":0.36256727773166425,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2808749774","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.988266,0.00020946779,0.00048233737,0.009611424,0.00049469905,0.00031290593,5.952011e-7,0.000029483284,0.0005930773],"genre_scores_gemma":[0.9955203,0.00009502991,0.00088151713,0.0028359788,0.00048142366,0.000035678884,0.000015679912,0.000017867633,0.000116550684],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9978033,0.00085947034,0.0005224564,0.00032645775,0.00017338654,0.00031495877],"domain_scores_gemma":[0.9992715,0.00027779516,0.000107939166,0.00019193487,0.00006967037,0.000081139224],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0049779075,0.00011604474,0.0003362827,0.0008150974,0.000026459793,0.0000048889665,0.00013566669,0.00027606293,0.00024515443],"category_scores_gemma":[0.004976932,0.00010709939,0.000032399963,0.0005390923,0.00017704105,0.000098305885,0.00004139074,0.0009592445,0.00005131963],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0048705726,0.000112233174,0.32494777,0.000050061506,0.0000496173,0.0001575219,0.010367715,0.0002914573,0.6236305,0.0007998857,0.010287138,0.02443552],"study_design_scores_gemma":[0.0024843598,0.00030668319,0.86463296,0.00018218411,0.00002168284,0.0003046304,0.000064805456,0.12779087,0.00035170684,0.0015801664,0.0021776557,0.00010227463],"about_ca_topic_score_codex":0.00015564096,"about_ca_topic_score_gemma":0.00001753165,"teacher_disagreement_score":0.6232788,"about_ca_system_score_codex":0.00024397078,"about_ca_system_score_gemma":0.0001467643,"threshold_uncertainty_score":0.5958212},"labels":[],"label_agreement":null},{"id":"W2808888481","doi":"10.1016/s0167-8140(18)31291-x","title":"PO-0981: Results from the Image Biomarker Standardisation Initiative","year":2018,"lang":"en","type":"article","venue":"Radiotherapy and Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":40,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Engineering and Physical Sciences Research Council","keywords":"Biomarker; Computer science; Chemistry","score_opus":0.02452930687874532,"score_gpt":0.3532770493852327,"score_spread":0.32874774250648736,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2808888481","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8360948,0.0020292492,0.03487551,0.10120616,0.00081811217,0.00046959505,0.00008767502,0.00009478336,0.024324114],"genre_scores_gemma":[0.96790695,0.0012942983,0.011282516,0.01743711,0.0017136028,0.00000952026,0.00007052974,0.000025542648,0.00025993536],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990404,0.000194261,0.0002198127,0.00023632191,0.00013312434,0.000176055],"domain_scores_gemma":[0.99889815,0.00064360286,0.00009852033,0.00019060721,0.000074619384,0.000094487725],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000657159,0.000105423525,0.00024240252,0.000038986986,0.00018590606,0.000026301845,0.000069992355,0.00010248279,0.00028739477],"category_scores_gemma":[0.0004122452,0.0000650136,0.000044760836,0.000098394754,0.00063818204,0.000057497873,0.00001807541,0.0002482943,0.0000126632085],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004306527,0.00014417389,0.008442754,0.000010073318,0.00041478107,0.00009698667,0.0145249795,8.863931e-7,0.025279216,0.00048004888,0.076478876,0.8698207],"study_design_scores_gemma":[0.008811915,0.0013894965,0.14128634,0.00006235449,0.00009238887,0.00013070974,0.0006529628,0.0064452565,0.0009529683,0.0010795182,0.83894026,0.00015579264],"about_ca_topic_score_codex":0.00014879875,"about_ca_topic_score_gemma":0.000034063465,"teacher_disagreement_score":0.8696649,"about_ca_system_score_codex":0.0001664253,"about_ca_system_score_gemma":0.00012988818,"threshold_uncertainty_score":0.31467712},"labels":[],"label_agreement":null},{"id":"W2809091867","doi":"10.1212/wnl.88.16_supplement.s35.006","title":"Alzheimer’s Disease: 3-Dimensional MRI-texture for Prediction of Conversion from Mild Cognitive Impairment (S35.006)","year":2017,"lang":"en","type":"article","venue":"Neurology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Cognitive impairment; Disease; Medicine; Alzheimer's disease; Cognition; Neuroscience; Psychology; Pathology","score_opus":0.020105150221762357,"score_gpt":0.3004621871653825,"score_spread":0.28035703694362013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2809091867","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97766,0.00055235333,0.0009194773,0.018632285,0.0010327786,0.0005969151,0.0003552839,0.00003803783,0.0002128964],"genre_scores_gemma":[0.994751,0.00005072657,0.00033604648,0.0039458377,0.00042181727,0.000024785153,0.00038933588,0.000020695003,0.00005979202],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9990534,0.000050523857,0.00019712857,0.00031311062,0.00019301387,0.000192813],"domain_scores_gemma":[0.9990004,0.00023255772,0.00019180603,0.00027551997,0.00010590511,0.00019383023],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013778603,0.00011960291,0.00026522088,0.000053639385,0.00018743017,0.000009345225,0.00010796835,0.00011345453,0.0001463455],"category_scores_gemma":[0.00030677312,0.00010182091,0.00011530089,0.000016666301,0.000258089,0.00005157711,0.00007462785,0.00030784545,0.000010002264],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.022887351,0.0010519541,0.8700326,0.00023037121,0.0009728347,0.00039975872,0.0004010429,0.00018318811,0.00946623,0.0002348401,0.08041652,0.013723273],"study_design_scores_gemma":[0.005537597,0.0014490183,0.93976635,0.00008468766,0.0006496898,0.000022461603,0.0000054676348,0.042547874,0.000608771,0.00037017537,0.008878422,0.00007951168],"about_ca_topic_score_codex":0.000113119626,"about_ca_topic_score_gemma":0.0000015464194,"teacher_disagreement_score":0.0715381,"about_ca_system_score_codex":0.000007648138,"about_ca_system_score_gemma":0.00007928109,"threshold_uncertainty_score":0.4152136},"labels":[],"label_agreement":null},{"id":"W2809226455","doi":"10.1007/s12149-018-1271-y","title":"Publisher Correction to: 18F-FDG PET/CT metabolic tumor parameters and radiomics features in aggressive non-Hodgkin’s lymphoma as predictors of treatment outcome and survival","year":2018,"lang":"en","type":"erratum","venue":"Annals of Nuclear Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; Women's College Hospital; University of Toronto; University Health Network; Mount Sinai Hospital","funders":"","keywords":"Medicine; Radiomics; Lymphoma; Oncology; Internal medicine; Aggressive lymphoma; Positron emission tomography; Hodgkin lymphoma; Overall survival; Radiology; Rituximab","score_opus":0.022562664438031454,"score_gpt":0.32667814407022167,"score_spread":0.3041154796321902,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2809226455","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93566704,0.0073146643,0.000004190978,0.012896683,0.030842843,0.0011464359,0.000028679593,0.0000653514,0.012034088],"genre_scores_gemma":[0.90499,0.032677542,0.0013578538,0.012434913,0.00469068,0.000067217465,0.00054152636,0.0005423732,0.042697866],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99676704,0.00018426894,0.0010533378,0.0007453519,0.0007254411,0.0005245597],"domain_scores_gemma":[0.99718606,0.0003432776,0.0009933185,0.0005577525,0.00030677734,0.0006128305],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010105824,0.00060619897,0.0023820642,0.0010159838,0.000075961274,0.000037498998,0.00023998103,0.00009811148,0.000087479566],"category_scores_gemma":[0.004216549,0.0004471437,0.0002006817,0.00046551845,0.0009340758,0.00013304448,0.00013854733,0.0007427893,0.000004306962],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008436564,0.00025010598,0.021733265,0.0004991493,0.0007661825,0.0010527775,0.0014442937,0.0000069962653,0.00011729569,0.000037772945,0.9544384,0.018810127],"study_design_scores_gemma":[0.010476921,0.011049272,0.36148092,0.008277492,0.0017213447,0.0052991766,0.002138742,0.002305537,0.0000746306,0.00016644344,0.596141,0.0008685263],"about_ca_topic_score_codex":0.00527898,"about_ca_topic_score_gemma":0.00010414342,"teacher_disagreement_score":0.35829738,"about_ca_system_score_codex":0.000108855456,"about_ca_system_score_gemma":0.00027691544,"threshold_uncertainty_score":0.99979806},"labels":[],"label_agreement":null},{"id":"W2809234664","doi":"10.1093/neuonc/noy059.228","title":"EPEN-28. HETEROGENEITY WITHIN THE PFB EPENDYMOMA SUBGROUP","year":2018,"lang":"en","type":"article","venue":"Neuro-Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; Hospital for Sick Children","funders":"","keywords":"Proportional hazards model; Oncology; Internal medicine; Survival analysis; Medicine; Biology","score_opus":0.021669296637481406,"score_gpt":0.3301284806921344,"score_spread":0.308459184054653,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2809234664","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94604534,0.00012493154,0.0008765388,0.03197949,0.0021957068,0.0003784713,0.0000023197235,0.00013640265,0.018260825],"genre_scores_gemma":[0.969233,0.000027360966,0.0014351729,0.027370913,0.0016362581,0.000024303352,0.000008915913,0.0000451808,0.00021894297],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981005,0.0003511579,0.0003788422,0.00043333432,0.00030884883,0.00042730971],"domain_scores_gemma":[0.9983989,0.00049238617,0.00018008801,0.0005556416,0.00010410957,0.00026885595],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008788437,0.00019708728,0.0004105096,0.00007959763,0.00027528647,0.000029503013,0.00032265618,0.00017547849,0.0003053823],"category_scores_gemma":[0.0012254161,0.00012849402,0.00012410127,0.00020223705,0.0006962425,0.000054002874,0.00016822289,0.0009860836,0.0003623575],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001179752,0.000847229,0.052702617,0.00009504354,0.00028417516,0.004496706,0.0028535917,0.000040654428,0.6761884,0.0061660395,0.07574182,0.17940395],"study_design_scores_gemma":[0.003913486,0.0040262993,0.021403156,0.000043479387,0.0002446146,0.008551339,0.00018021977,0.015178772,0.03160601,0.00076749997,0.9137693,0.0003157974],"about_ca_topic_score_codex":0.00008814524,"about_ca_topic_score_gemma":0.000072545896,"teacher_disagreement_score":0.83802754,"about_ca_system_score_codex":0.00010876399,"about_ca_system_score_gemma":0.00024370599,"threshold_uncertainty_score":0.5239834},"labels":[],"label_agreement":null},{"id":"W2809364338","doi":"10.1007/s11517-018-1858-4","title":"Prediction of survival with multi-scale radiomic analysis in glioblastoma patients","year":2018,"lang":"en","type":"article","venue":"Medical & Biological Engineering & Computing","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":86,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; McGill University Health Centre","funders":"","keywords":"Random forest; Radiomics; Univariate; Glioblastoma; Artificial intelligence; Fluid-attenuated inversion recovery; Correlation; Correlation coefficient; Rank correlation; Pattern recognition (psychology); Progression-free survival; Estimator; Medicine; Mathematics; Computer science; Multivariate statistics; Statistics; Magnetic resonance imaging; Oncology; Overall survival; Radiology","score_opus":0.012168336255350623,"score_gpt":0.252875117010992,"score_spread":0.2407067807556414,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2809364338","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83758074,0.000041317893,0.16168943,0.00012238424,0.00020932312,0.00014048044,0.0000033994627,0.00009747775,0.00011545482],"genre_scores_gemma":[0.9883086,0.000010395194,0.011229017,0.000118164804,0.00027304646,0.0000031440456,0.00002898391,0.000018361932,0.0000102959475],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99802804,0.00007277169,0.0005616657,0.00040416513,0.00052180514,0.0004115803],"domain_scores_gemma":[0.9990276,0.0002333665,0.00010980066,0.00019829143,0.00010915547,0.0003218022],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00081847707,0.00020328975,0.00068524084,0.00034583043,0.0000464796,0.000009319132,0.00018092457,0.00020475025,0.00015061819],"category_scores_gemma":[0.0010971846,0.00013897636,0.00013345575,0.0010920084,0.00028372306,0.000028102604,0.00010240036,0.000607529,0.0000080967075],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012346769,0.00029909637,0.9861789,0.000045929537,0.00017049213,0.000027851405,0.00015334983,0.002883962,0.0009900469,0.000016333981,0.000014068877,0.009096535],"study_design_scores_gemma":[0.0013793523,0.00050600356,0.52506185,0.00016141358,0.00006295115,0.000010853629,0.000012199564,0.47250894,0.00010682769,8.359973e-7,0.00011070189,0.00007807801],"about_ca_topic_score_codex":0.00006607215,"about_ca_topic_score_gemma":0.000010221247,"teacher_disagreement_score":0.469625,"about_ca_system_score_codex":0.000074209434,"about_ca_system_score_gemma":0.000045651406,"threshold_uncertainty_score":0.5667292},"labels":[],"label_agreement":null},{"id":"W2809639820","doi":"10.1007/978-3-319-97785-0_4","title":"Dynamic Voting in Multi-view Learning for Radiomics Applications","year":2018,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; Université du Québec à Montréal","funders":"","keywords":"Radiomics; Computer science; Random forest; Voting; Personalization; Classifier (UML); Artificial intelligence; Machine learning; World Wide Web","score_opus":0.016987406325420333,"score_gpt":0.3106549781257549,"score_spread":0.29366757180033454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2809639820","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005071304,0.00089737354,0.99584097,0.0009275987,0.00040265435,0.000998541,0.0000019706604,0.00007256608,0.00035122136],"genre_scores_gemma":[0.14235574,0.00019907276,0.8532089,0.0020103892,0.0006785236,0.000079191515,0.000059134378,0.000111091395,0.0012979356],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99773645,0.00001971516,0.00049097644,0.00089463254,0.00035819167,0.0005000275],"domain_scores_gemma":[0.99861515,0.0004646637,0.00022412823,0.00038815432,0.00015393956,0.00015398416],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011629725,0.00031998003,0.0005771609,0.0006437932,0.00019924634,0.0000929219,0.0005052074,0.00024219896,0.000025219722],"category_scores_gemma":[0.0004889008,0.00029536962,0.00012232989,0.0003184208,0.0006490545,0.00007816636,0.00019859233,0.0013577356,0.000017119688],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016965605,0.00004512158,0.0012304775,0.00032359958,0.00001643554,0.000027609429,0.00049317663,0.032880634,0.00033267375,0.0005806717,0.000010843355,0.96404177],"study_design_scores_gemma":[0.0008143313,0.00012021062,0.00033565488,0.0010945738,0.00002630162,0.00008649705,4.6650533e-7,0.9823449,0.000032407504,0.0033842563,0.01146685,0.00029351845],"about_ca_topic_score_codex":0.000015229928,"about_ca_topic_score_gemma":0.00005688002,"teacher_disagreement_score":0.9637483,"about_ca_system_score_codex":0.0003893951,"about_ca_system_score_gemma":0.00034400166,"threshold_uncertainty_score":0.9999499},"labels":[],"label_agreement":null},{"id":"W2810339171","doi":"10.1016/j.ijrobp.2018.06.023","title":"The Use of Quantitative Imaging in Radiation Oncology: A Quantitative Imaging Network (QIN) Perspective","year":2018,"lang":"en","type":"review","venue":"International Journal of Radiation Oncology*Biology*Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":43,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University Health Network","funders":"Canadian Institutes of Health Research; AbbVie; National Cancer Institute; Celgene","keywords":"Radiation oncology; Perspective (graphical); Medical physics; Medicine; Nuclear medicine; Radiology; Radiation therapy; Computer science; Artificial intelligence","score_opus":0.06095201248969996,"score_gpt":0.4374903042272815,"score_spread":0.3765382917375816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2810339171","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00064158265,0.9572228,0.028439114,0.0059623923,0.0059711738,0.0009694127,0.00008300646,0.0000414018,0.00066906924],"genre_scores_gemma":[0.0022459496,0.97464967,0.018219773,0.00089312193,0.0036152452,0.00004054729,0.00018325403,0.00010452772,0.000047898357],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9941701,0.0018282583,0.0024014919,0.00052565604,0.0005457495,0.0005287167],"domain_scores_gemma":[0.9854416,0.006494591,0.0054392456,0.00030566117,0.0021295883,0.00018931493],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0031106276,0.00051474234,0.00223821,0.0005974056,0.0001978829,0.000094162155,0.00077284145,0.00037455882,0.000024596588],"category_scores_gemma":[0.006425007,0.00038446483,0.0008699743,0.00064380775,0.0013295889,0.00053316756,0.00017116671,0.0021766864,0.00002390408],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004702736,0.00034530723,0.011150783,0.00015351076,0.0014153292,0.00015696354,0.0015528275,0.0006491384,0.000014550426,0.04412146,0.004890997,0.93507886],"study_design_scores_gemma":[0.003273108,0.0010492925,0.00076396886,0.0035119376,0.0009828438,0.0005863292,0.00061960117,0.022560086,0.000004043325,0.0087542245,0.95753896,0.0003556124],"about_ca_topic_score_codex":0.00012974904,"about_ca_topic_score_gemma":0.000016802132,"teacher_disagreement_score":0.952648,"about_ca_system_score_codex":0.0034278764,"about_ca_system_score_gemma":0.002994721,"threshold_uncertainty_score":0.9998607},"labels":[],"label_agreement":null},{"id":"W2811450527","doi":"10.6084/m9.figshare.6724625","title":"A standardised representation for non-parametric fMRI results","year":2018,"lang":"en","type":"article","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Metadata; Computer science; JSON; Representation (politics); Information retrieval; Flemish; Functional magnetic resonance imaging; Data science; Data curation; Process (computing); Neuroimaging; Data mining; World Wide Web; Programming language; Geography; Psychology","score_opus":0.015086265252169422,"score_gpt":0.2963507870041821,"score_spread":0.28126452175201266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2811450527","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27153322,0.00013622314,0.60110986,0.03599943,0.00024990266,0.00080264866,0.00003766908,0.0001934352,0.08993762],"genre_scores_gemma":[0.890982,0.00006969583,0.09939398,0.00034351173,0.00009283075,0.000037523543,0.00023824805,0.000029914745,0.008812321],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99789447,0.00069718336,0.0003749553,0.00043052976,0.0003391707,0.00026370442],"domain_scores_gemma":[0.99550575,0.0013991038,0.00021332054,0.0008916538,0.0017872266,0.00020296958],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004316584,0.00013070289,0.00023964125,0.00020186686,0.000298759,0.00011355351,0.0002442597,0.00007964369,0.000060914706],"category_scores_gemma":[0.010665367,0.00012286301,0.0001290421,0.0006121803,0.0002457142,0.00009085608,0.00009316454,0.00021998124,0.000029031611],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015948246,0.001756548,0.021604119,0.00040421964,0.00039010562,0.000029184266,0.022359248,0.000045702145,0.05084551,0.03667404,0.09464119,0.7696553],"study_design_scores_gemma":[0.015525378,0.000017338123,0.053415526,0.002111607,0.00027432712,0.000086643224,0.00044703318,0.44026673,0.21456143,0.0037960357,0.2688107,0.0006872628],"about_ca_topic_score_codex":0.00024934718,"about_ca_topic_score_gemma":0.00005694038,"teacher_disagreement_score":0.76896805,"about_ca_system_score_codex":0.00007336209,"about_ca_system_score_gemma":0.00015104664,"threshold_uncertainty_score":0.9976682},"labels":[],"label_agreement":null},{"id":"W2883180018","doi":"10.1017/cjn.2018.300","title":"46 Integration of multiple platforms to discover idh-mutant glioma subtypes","year":2018,"lang":"en","type":"article","venue":"Canadian Journal of Neurological Sciences / Journal Canadien des Sciences Neurologiques","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"ATRX; Glioma; Hox gene; Mutant; Biology; Methylation; IDH1; DNA methylation; Gene; Cancer research; Oncology; Mutation; Genetics; Gene expression; Medicine","score_opus":0.02736772545397716,"score_gpt":0.29695130598371655,"score_spread":0.2695835805297394,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2883180018","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9905778,0.00021588433,0.00046469516,0.0062549226,0.0009340863,0.00015771772,0.00000657896,0.000012008582,0.0013763175],"genre_scores_gemma":[0.9906333,0.000061067425,0.004920805,0.0038665486,0.00048744716,0.0000011714255,3.3006518e-7,0.000010774937,0.000018576093],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9967526,0.00022432298,0.0008656877,0.00039673122,0.0008252711,0.00093539373],"domain_scores_gemma":[0.9962016,0.00041031104,0.00060122437,0.00014442895,0.00062791887,0.002014569],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.003545751,0.0002445903,0.00053059653,0.0011087415,0.0012653332,0.000285653,0.0011092514,0.0001367306,0.00017190306],"category_scores_gemma":[0.006694508,0.00014409913,0.00020812589,0.0014539659,0.006238186,0.0006345473,0.00006093631,0.0010254668,0.0000052059304],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003450725,0.000051000654,0.97258824,0.000011508327,0.000023852028,0.00335213,0.0011139916,0.00079077965,0.0076937634,0.0012367761,0.000871394,0.011921472],"study_design_scores_gemma":[0.0015210253,0.2275371,0.6374789,0.00041783726,0.00015692695,0.07248857,0.0010468456,0.018118134,0.012029185,0.021502929,0.0069960565,0.0007065185],"about_ca_topic_score_codex":0.0017504073,"about_ca_topic_score_gemma":0.028280502,"teacher_disagreement_score":0.33510938,"about_ca_system_score_codex":0.00016071122,"about_ca_system_score_gemma":0.0024521076,"threshold_uncertainty_score":0.9964663},"labels":[],"label_agreement":null},{"id":"W2885002882","doi":"10.1017/cjn.2018.291","title":"51 Timing of adjuvant treatments on glioblastoma survival: A retrospective cohort analysis based on the national cancer database","year":2018,"lang":"en","type":"article","venue":"Canadian Journal of Neurological Sciences / Journal Canadien des Sciences Neurologiques","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine; Hazard ratio; Biopsy; Proportional hazards model; Cancer; Craniotomy; Surgery; Cohort; Adjuvant therapy; Internal medicine; Database; Oncology; Confidence interval","score_opus":0.04128186624863809,"score_gpt":0.33183382730921884,"score_spread":0.29055196106058073,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2885002882","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98290807,0.000110278634,0.000072851784,0.011603198,0.0005379653,0.00015955888,0.000035293728,0.000009214763,0.004563595],"genre_scores_gemma":[0.99034065,0.00008793565,0.0006359427,0.008521018,0.0003814435,0.0000036659733,6.3498743e-7,0.000009323633,0.000019369296],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99572307,0.0007506383,0.0006625554,0.0004782708,0.0016290604,0.0007564161],"domain_scores_gemma":[0.99630064,0.0009642816,0.00075830333,0.000157168,0.00071654195,0.0011030514],"candidate_categories":["sts"],"consensus_categories":["sts"],"category_scores_codex":[0.0049999934,0.00025681354,0.0006180634,0.0013418953,0.001694645,0.00020105769,0.0010098338,0.00009500426,0.00047356792],"category_scores_gemma":[0.005670255,0.00013651529,0.00031550857,0.0023662376,0.0062501994,0.00023987585,0.000033342018,0.0011087096,0.0000018669344],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025161653,0.00006301228,0.9907734,0.000003244079,0.00012935398,0.0008961608,0.00011601653,0.0056118164,0.00010943266,0.0004328143,0.00065036555,0.0009628083],"study_design_scores_gemma":[0.00046986033,0.058614116,0.8554539,0.00010736622,0.00036971434,0.0012375007,0.0000695224,0.081738375,0.0003103975,0.0010478257,0.00040490937,0.00017652141],"about_ca_topic_score_codex":0.001994081,"about_ca_topic_score_gemma":0.015081851,"teacher_disagreement_score":0.13531947,"about_ca_system_score_codex":0.00035990847,"about_ca_system_score_gemma":0.0027597018,"threshold_uncertainty_score":0.999605},"labels":[],"label_agreement":null},{"id":"W2885232520","doi":"10.1158/1538-7445.am2018-3413","title":"Abstract 3413: A pan-cancer atlas of genomic, epigenomic and transcriptomic alterations in the TGF-β pathway","year":2018,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency","funders":"","keywords":"Biology; Epigenomics; Transcriptome; Gene; Genetics; Cancer research; Gene expression; DNA methylation","score_opus":0.06552515134943829,"score_gpt":0.4167186050792456,"score_spread":0.35119345372980726,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2885232520","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9899049,0.003064661,0.00005944475,0.0051742787,0.00011829966,0.00045701533,0.000018901572,0.000009904911,0.0011926392],"genre_scores_gemma":[0.99695426,0.0014285325,0.00014143297,0.00045467765,0.00059820607,0.00013082914,0.000007669199,0.0000234569,0.00026091287],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9985491,0.00016784447,0.0002695466,0.00028130252,0.00035939485,0.0003727844],"domain_scores_gemma":[0.999218,0.00016818033,0.000042783344,0.0003004388,0.00014530546,0.00012532416],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00160416,0.00009902814,0.00022068703,0.00019462792,0.00016566066,0.00004503038,0.00022647307,0.000060743238,0.00047688565],"category_scores_gemma":[0.000098535,0.00006881339,0.00004146886,0.00021753374,0.0005682806,0.00007962897,0.000029439989,0.00072063337,0.00001765212],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031517862,0.0001469424,0.0140572665,0.00016686732,0.000047767007,0.000026383745,0.010993667,0.000027633072,0.8968726,0.00056206266,0.0015170322,0.07526664],"study_design_scores_gemma":[0.004702072,0.0009672391,0.8875936,0.00073299854,0.00006849987,0.000055681845,0.0030033125,0.007071339,0.03750867,0.0014597682,0.05648044,0.0003563665],"about_ca_topic_score_codex":0.0035938167,"about_ca_topic_score_gemma":0.0011968887,"teacher_disagreement_score":0.87353635,"about_ca_system_score_codex":0.00013225384,"about_ca_system_score_gemma":0.00045062246,"threshold_uncertainty_score":0.54328},"labels":[],"label_agreement":null},{"id":"W2885283639","doi":"10.1016/j.echo.2018.06.011","title":"Interaction with Volume-Rendered Three-Dimensional Echocardiographic Images in Virtual Reality","year":2018,"lang":"en","type":"letter","venue":"Journal of the American Society of Echocardiography","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":21,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"National Institute of Biomedical Imaging and Bioengineering; National Cancer Institute","keywords":"Medicine; Volume (thermodynamics); Virtual reality; Computer graphics (images); Computer vision; Artificial intelligence; Computer science","score_opus":0.01309520725880254,"score_gpt":0.2763963152913779,"score_spread":0.2633011080325754,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2885283639","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33046052,0.0011446833,0.010561483,0.6544454,0.0018224932,0.0008178618,0.00008282242,0.000065733075,0.0005990088],"genre_scores_gemma":[0.6759785,0.0015710327,0.01456091,0.29922688,0.008190538,0.00001550123,0.00005747612,0.00022733533,0.00017186163],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9958217,0.00043328822,0.0011033233,0.00043183178,0.0017221998,0.00048766867],"domain_scores_gemma":[0.995214,0.00029080609,0.0028952127,0.0007900949,0.000656716,0.00015317561],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0016346658,0.00047637412,0.0019912983,0.0007634689,0.00012462378,0.00004309514,0.00061297143,0.00031022457,0.000016449418],"category_scores_gemma":[0.00013258061,0.00030114653,0.00429293,0.002238181,0.002640458,0.0001588394,0.0001345457,0.0053362837,0.0000013341511],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041088118,0.00008744234,0.13710457,0.00012185984,0.002888248,0.00011366841,0.00010049105,0.0007356786,0.00030448392,3.1342944e-7,0.8547494,0.003382953],"study_design_scores_gemma":[0.0063616806,0.0058097793,0.59298366,0.0063189315,0.0048928726,0.0032830446,0.0010486955,0.004438687,0.00028040854,0.0005341741,0.37279114,0.0012569523],"about_ca_topic_score_codex":0.0004943817,"about_ca_topic_score_gemma":0.0000045398224,"teacher_disagreement_score":0.48195827,"about_ca_system_score_codex":0.00016499097,"about_ca_system_score_gemma":0.00032670904,"threshold_uncertainty_score":0.9999441},"labels":[],"label_agreement":null},{"id":"W2885350429","doi":"10.1158/1538-7445.am2018-1644","title":"Abstract 1644: Progression-free survival (PFS) as a surrogate for overall survival (OS)","year":2018,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital","funders":"","keywords":"Progression-free survival; Medicine; Internal medicine; Oncology; Surrogate endpoint; Clinical endpoint; Overall survival; Clinical trial","score_opus":0.08406891724616299,"score_gpt":0.48166759877610843,"score_spread":0.39759868152994543,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2885350429","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9443716,0.0010710236,0.000347289,0.02562759,0.0015894114,0.0013081924,0.00003262324,0.00013788638,0.025514377],"genre_scores_gemma":[0.98406035,0.00040002682,0.0012848175,0.00056462287,0.003868822,0.000336935,0.000035016645,0.0001020493,0.009347337],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9963698,0.0001607784,0.00032786606,0.0005893148,0.0015306206,0.0010216482],"domain_scores_gemma":[0.9970632,0.00072586804,0.00007785705,0.00068987976,0.00088289566,0.0005602713],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0039451327,0.00020151101,0.0004125906,0.00022387711,0.00035922122,0.00012735835,0.00051968516,0.00014968732,0.0018436926],"category_scores_gemma":[0.0036903603,0.00015929108,0.00014732014,0.00034486994,0.00069503835,0.00012078185,0.00025746837,0.001196993,0.0001985055],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008719906,0.0010882505,0.062498063,0.002172272,0.00077646156,0.00059460837,0.0022819033,0.000019701924,0.12739551,0.014099826,0.4048921,0.37546143],"study_design_scores_gemma":[0.016955642,0.0026866551,0.075976804,0.0025308337,0.00011684406,0.00006773695,0.0004209591,0.0052545494,0.021277696,0.0108102495,0.8630816,0.0008204791],"about_ca_topic_score_codex":0.001620131,"about_ca_topic_score_gemma":0.0001589011,"teacher_disagreement_score":0.4581895,"about_ca_system_score_codex":0.00025288225,"about_ca_system_score_gemma":0.00094280776,"threshold_uncertainty_score":0.99906874},"labels":[],"label_agreement":null},{"id":"W2886253811","doi":"10.1158/1538-7445.am2018-854","title":"Abstract 854: Validation of a viability assay for assessing radiation response and investigating drug/radiation combinations","year":2018,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre","funders":"","keywords":"Clonogenic assay; Viability assay; Medicine; Ionizing radiation; Radiosensitivity; Radiation therapy; Cancer; Cancer research; Radiosensitizer; Therapeutic index; Oncology; Pharmacology; Drug; Biology; In vitro; Internal medicine; Irradiation","score_opus":0.07065408337188975,"score_gpt":0.4691616969422217,"score_spread":0.39850761357033193,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2886253811","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9884173,0.00019661918,0.0021865736,0.008195076,0.00011802806,0.0005900808,0.000010252435,0.000023749593,0.00026228957],"genre_scores_gemma":[0.99745363,0.00003930373,0.0018763319,0.000102302816,0.00026310675,0.00009726421,0.000041959218,0.000017642718,0.00010846352],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99845064,0.00038302966,0.0002751954,0.00023802515,0.0004295888,0.00022350972],"domain_scores_gemma":[0.9972282,0.0016854409,0.0001231107,0.00017462563,0.0006465641,0.00014203413],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0074444916,0.00007022584,0.00016419838,0.0002476454,0.0002982093,0.00006814028,0.00006376846,0.000059994054,0.00004293129],"category_scores_gemma":[0.010284508,0.00006692703,0.000032612945,0.00035219922,0.00045375916,0.0002028959,0.000028467308,0.00032964395,0.0000013562741],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00048307705,0.00018381777,0.133084,0.0007460921,0.00005852318,0.0000014262558,0.0033747596,0.00008682188,0.6173226,0.00082588464,0.003257914,0.24057506],"study_design_scores_gemma":[0.003206577,0.00030662783,0.7887422,0.0005194638,0.00005330382,0.0000050972703,0.0005282634,0.052748356,0.14414889,0.0037797967,0.0058045005,0.00015694457],"about_ca_topic_score_codex":0.00032220111,"about_ca_topic_score_gemma":0.00000626179,"teacher_disagreement_score":0.6556582,"about_ca_system_score_codex":0.00023728484,"about_ca_system_score_gemma":0.00049488497,"threshold_uncertainty_score":0.9980523},"labels":[],"label_agreement":null},{"id":"W2886366102","doi":"10.11159/icbes18.133","title":"Detection of Hepatocellular Carcinoma in CT Images Using Deep Learning","year":2018,"lang":"en","type":"article","venue":"Proceedings of the World Congress on Electrical Engineering and Computer Systems and Science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Hepatocellular carcinoma; Artificial intelligence; Deep learning; Computer science; Medicine; Cancer research","score_opus":0.006683385258820053,"score_gpt":0.2225792031870051,"score_spread":0.21589581792818505,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2886366102","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99728036,0.00038069283,0.0017688943,0.000044121472,0.0003158827,0.00011709666,7.239088e-8,0.000016125367,0.00007674975],"genre_scores_gemma":[0.9992792,0.000011997576,0.00052665453,0.0000137823,0.00011448234,0.0000021609465,2.5892456e-8,0.000007183349,0.000044525827],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991477,0.0000058854425,0.00020494669,0.00020879105,0.00023957928,0.00019310584],"domain_scores_gemma":[0.9996058,0.000043763204,0.00009847705,0.000051930194,0.00012243619,0.000077622266],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047197004,0.00009195269,0.00022985018,0.00030754993,0.00009486461,0.000045826924,0.00011798859,0.000016231159,2.141755e-7],"category_scores_gemma":[0.00012155922,0.00006489146,0.000025363752,0.00074284856,0.00023030414,0.000072242256,0.000067778776,0.0002600285,5.5656564e-8],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006511923,0.00006308253,0.4564676,0.0006502613,0.00002565321,0.000008685111,0.00027265874,0.0034653975,0.5022815,0.0035695643,0.000010469715,0.033120025],"study_design_scores_gemma":[0.0002562393,0.00017742337,0.031019853,0.00039724552,0.00001113146,0.00010716123,0.000008232758,0.93893445,0.02893018,0.0000063537777,0.00008880509,0.00006293595],"about_ca_topic_score_codex":0.00007657965,"about_ca_topic_score_gemma":3.4704448e-7,"teacher_disagreement_score":0.93546903,"about_ca_system_score_codex":0.000033255656,"about_ca_system_score_gemma":0.00001789038,"threshold_uncertainty_score":0.26461968},"labels":[],"label_agreement":null},{"id":"W2886546589","doi":"10.1136/annrheumdis-2018-eular.6880","title":"FRI0597 Validation of web-based calibration modules for imaging scoring systems based on principles of artificial intelligence: the sparcc mri sacroiliac joint inflammation score","year":2018,"lang":"en","type":"article","venue":"Annals of the Rheumatic Diseases","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hospital for Sick Children; McMaster Children's Hospital; University of Alberta","funders":"","keywords":"Medicine; Medical physics; DICOM; Artificial intelligence; Quadrant (abdomen); Calibration; Computer science; Machine learning; Physical therapy; Radiology; Pathology; Statistics","score_opus":0.06798254035158761,"score_gpt":0.3275498075948006,"score_spread":0.259567267243213,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2886546589","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8754584,0.0001987201,0.11779825,0.005089443,0.00031404805,0.0009776596,0.000045946203,0.000028625785,0.00008886726],"genre_scores_gemma":[0.99841785,0.000027624103,0.0011704438,0.00012896757,0.00013775012,0.000046416884,0.000040716004,0.000020173058,0.000010053263],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981739,0.00016778179,0.00080544717,0.00017075341,0.00051602145,0.00016610867],"domain_scores_gemma":[0.99782395,0.0004960166,0.0007603942,0.00046625684,0.00038576947,0.000067613524],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008971728,0.00013902149,0.00035094057,0.00014648675,0.00013525579,0.000034711346,0.00017344717,0.000031946456,0.000018211293],"category_scores_gemma":[0.0026569867,0.00008383705,0.00020931462,0.00020287288,0.0003547006,0.00009682602,0.000033791654,0.000089601126,0.0000010041231],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018368851,0.0011747926,0.042806774,0.0135414265,0.00041566006,0.0000020539721,0.0015501502,0.7157467,0.032494333,0.032228805,0.0015560393,0.15664637],"study_design_scores_gemma":[0.0002426279,0.00014017687,0.006922883,0.0042872904,0.000117040196,7.9708155e-7,0.000170038,0.86264825,0.123547316,0.001824097,0.000030102407,0.00006935759],"about_ca_topic_score_codex":0.00007913632,"about_ca_topic_score_gemma":0.0000023292714,"teacher_disagreement_score":0.15657702,"about_ca_system_score_codex":0.000019549561,"about_ca_system_score_gemma":0.0002001382,"threshold_uncertainty_score":0.34187755},"labels":[],"label_agreement":null},{"id":"W2886606374","doi":"10.1002/jmri.26198","title":"Best practices for MRI systematic reviews and meta‐analyses","year":2018,"lang":"en","type":"review","venue":"Journal of Magnetic Resonance Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Public Health; Ottawa Hospital; University of Ottawa","funders":"","keywords":"Systematic review; Meta-analysis; Medical physics; Computer science; Medicine; MEDLINE; Management science; Data science; Pathology","score_opus":0.2022889902004515,"score_gpt":0.48159549893649367,"score_spread":0.2793065087360422,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2886606374","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[9.2974625e-7,0.994446,0.0013796462,0.0011981841,0.0003722026,0.0021685068,0.0000057973807,0.000010156902,0.00041860438],"genre_scores_gemma":[7.854537e-7,0.9625114,0.033323012,0.00038961854,0.0010640271,0.00013695062,0.0000038054443,0.00007901232,0.0024913491],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99532205,0.0006921526,0.0026457405,0.00040010578,0.0005654173,0.00037450704],"domain_scores_gemma":[0.9899359,0.002174117,0.006671528,0.00046162156,0.0004604775,0.00029637202],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.005532107,0.00054091454,0.0066217775,0.0004477691,0.00012222078,0.0001958537,0.0003670626,0.00011930779,0.00007557293],"category_scores_gemma":[0.013551101,0.00029977065,0.0016288206,0.00028164792,0.00022954664,0.00023901198,0.00007662843,0.0009483755,0.000016652244],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001716657,0.000052845233,0.000006278565,0.31989893,0.00088983384,0.00013017454,0.00004643668,1.1563797e-7,0.0000018750932,0.000008712714,0.0065360926,0.67241156],"study_design_scores_gemma":[0.00041428392,0.0002805273,0.0000012498277,0.12053542,0.0993214,0.0055007827,0.000031810832,0.00040142707,3.175305e-7,0.000027137976,0.7732897,0.00019594512],"about_ca_topic_score_codex":0.000018009923,"about_ca_topic_score_gemma":8.541859e-7,"teacher_disagreement_score":0.7667536,"about_ca_system_score_codex":0.000082610866,"about_ca_system_score_gemma":0.0003513277,"threshold_uncertainty_score":0.99994546},"labels":[],"label_agreement":null},{"id":"W2886752543","doi":"10.1158/1538-7445.am2018-660","title":"Abstract 660: Integration of radiomics with \"omic\" analyses to predict survival in newly diagnosed IDH-1 wild-type glioblastoma","year":2018,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Radiomics; Subtyping; IDH1; Isocitrate dehydrogenase; Glioblastoma; Computational biology; Omics; Phenotype; Biology; Transcriptome; Glioma; Proportional hazards model; Oncology; Medicine; Pathology; Bioinformatics; Internal medicine; Cancer research; Radiology; Gene; Genetics; Computer science; Gene expression; Mutation","score_opus":0.07418230351218844,"score_gpt":0.4484428351935904,"score_spread":0.37426053168140194,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2886752543","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99445754,0.00022617106,0.00073898415,0.0026615635,0.00021272998,0.00047818403,0.00000761909,0.00002795715,0.0011892425],"genre_scores_gemma":[0.99768853,0.0002448185,0.00095031224,0.0002163906,0.0005795567,0.000040630748,0.000012770449,0.00003843921,0.00022857277],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9978589,0.00013315926,0.00034675293,0.00037294332,0.0008204352,0.00046783817],"domain_scores_gemma":[0.9983293,0.00031824765,0.000072930095,0.00036844346,0.00061309803,0.00029797986],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013963068,0.00014588606,0.00040491117,0.0006625071,0.00007841125,0.0000378787,0.00023633275,0.00008760401,0.00025021622],"category_scores_gemma":[0.0014079426,0.00010935272,0.000047851507,0.0012342973,0.00043078477,0.00009697599,0.00006580328,0.0007797205,0.000023148474],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0069353776,0.00035634532,0.15178876,0.0002554941,0.00022598532,0.0002570452,0.0033104967,0.00133188,0.7399047,0.00014416683,0.009796326,0.08569344],"study_design_scores_gemma":[0.010240598,0.0069601736,0.7736779,0.0037095647,0.00013491427,0.000048347873,0.0020581572,0.022788476,0.16749316,0.00019121013,0.012130853,0.00056668255],"about_ca_topic_score_codex":0.0045555206,"about_ca_topic_score_gemma":0.0021416184,"teacher_disagreement_score":0.6218891,"about_ca_system_score_codex":0.00030607564,"about_ca_system_score_gemma":0.0006293932,"threshold_uncertainty_score":0.6886615},"labels":[],"label_agreement":null},{"id":"W2887021901","doi":"10.1007/s00330-018-5674-x","title":"Demystification of AI-driven medical image interpretation: past, present and future","year":2018,"lang":"en","type":"review","venue":"European Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":157,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre; McGill University","funders":"","keywords":"Interpretation (philosophy); Neuroradiology; Medicine; Interventional radiology; Radiology; Medical physics; Computer science; Neurology; Psychiatry; Programming language","score_opus":0.01724476556292529,"score_gpt":0.344586607164398,"score_spread":0.32734184160147267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2887021901","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000031216718,0.98266876,0.004494595,0.0048220996,0.0006911776,0.0004245292,0.000008820305,0.000056884557,0.006801902],"genre_scores_gemma":[0.00007386586,0.9865286,0.00282491,0.00047979562,0.009482581,0.000010839736,0.00025251947,0.00007719806,0.00026971687],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99719584,0.0010785026,0.00077119394,0.00048030916,0.00024977553,0.00022437946],"domain_scores_gemma":[0.99858993,0.00023780025,0.0003857464,0.0004152941,0.000098654426,0.00027258086],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00096067594,0.00027827197,0.0013200766,0.00019358727,0.00004782339,0.000014082939,0.00028369343,0.00022595355,0.00024347474],"category_scores_gemma":[0.00034029488,0.00019918194,0.00022039138,0.00013788056,0.00066559465,0.000033917797,0.00014827904,0.0010222368,0.000094712224],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019427267,0.00003300332,0.000044205637,0.004629396,0.00019979157,0.00018142862,0.00015896479,1.0380622e-7,0.0000026708244,0.00017345564,0.03986989,0.95468765],"study_design_scores_gemma":[0.00035768014,0.00019821605,0.00027744073,0.0037848768,0.0005520143,0.0026467077,0.000010369843,0.0008885499,2.680888e-7,0.0000128631345,0.99112594,0.00014505288],"about_ca_topic_score_codex":0.00000218778,"about_ca_topic_score_gemma":1.1114213e-7,"teacher_disagreement_score":0.95454264,"about_ca_system_score_codex":0.000036047317,"about_ca_system_score_gemma":0.00017245191,"threshold_uncertainty_score":0.8122404},"labels":[],"label_agreement":null},{"id":"W2887494772","doi":"10.3390/cancers10080249","title":"Multimodal Radiomic Features for the Predicting Gleason Score of Prostate Cancer","year":2018,"lang":"en","type":"article","venue":"Cancers","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":112,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; École de Technologie Supérieure; McGill University Health Centre","funders":"","keywords":"Prostate cancer; Rank correlation; Random forest; Spearman's rank correlation coefficient; Artificial intelligence; Medicine; Correlation; Pattern recognition (psychology); Cancer; Nuclear medicine; Computer science; Statistics; Mathematics; Internal medicine","score_opus":0.013081223730956916,"score_gpt":0.3140440009659139,"score_spread":0.30096277723495696,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2887494772","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9895447,0.003715722,0.0012420118,0.0030231639,0.0010642391,0.0008027386,0.000028806446,0.000046895126,0.0005317588],"genre_scores_gemma":[0.99462837,0.00031265302,0.0018193983,0.0008315135,0.0012479345,0.00010719266,0.000007663683,0.000028792303,0.0010165094],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99922454,0.0000142638655,0.00016300521,0.00018765389,0.00017356676,0.00023696468],"domain_scores_gemma":[0.9993376,0.00013703867,0.00011501901,0.00018838707,0.00013267611,0.000089246474],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002394825,0.0001026223,0.00020712761,0.000039911436,0.00017330986,0.000008805913,0.00011559162,0.000045604593,0.000058224203],"category_scores_gemma":[0.00034352887,0.00006516954,0.0000858512,0.00011584127,0.0004321242,0.00003372264,0.0000208591,0.00022163903,0.0000010293542],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0026798188,0.000040089937,0.5083772,0.0010776682,0.0008512186,0.000017523033,0.011467083,0.006391057,0.070663236,0.00037216156,0.074207984,0.32385495],"study_design_scores_gemma":[0.0100219175,0.0012440777,0.29810047,0.0021084,0.00088681653,0.00013382701,0.0013842504,0.5615074,0.04209991,0.00016405963,0.08188778,0.00046105275],"about_ca_topic_score_codex":0.0017543844,"about_ca_topic_score_gemma":0.000052478827,"teacher_disagreement_score":0.55511636,"about_ca_system_score_codex":0.0002976298,"about_ca_system_score_gemma":0.00053996244,"threshold_uncertainty_score":0.26575366},"labels":[],"label_agreement":null},{"id":"W2888001702","doi":"10.1002/jmri.26211","title":"Value of MRI in medicine: More than just another test?","year":2018,"lang":"en","type":"editorial","venue":"Journal of Magnetic Resonance Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":166,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre","funders":"National Institute of Biomedical Imaging and Bioengineering; National Cancer Institute; Rosetrees Trust","keywords":"Value (mathematics); Test (biology); Medicine; Medical physics; Radiology; Mathematics; Statistics; Geology","score_opus":0.007932809023927179,"score_gpt":0.3096566316050212,"score_spread":0.30172382258109404,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2888001702","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010086605,0.1454146,0.0010631265,0.034103435,0.7993274,0.00080874364,0.000044646586,0.000051945735,0.009099535],"genre_scores_gemma":[0.0065872986,0.0135755865,0.0133753475,0.0012443681,0.96096903,0.000008587543,0.000025951582,0.00026965913,0.0039441725],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99499,0.00015230231,0.0018282933,0.00041889382,0.0020758216,0.00053467473],"domain_scores_gemma":[0.99535,0.0014692133,0.0015087377,0.0005387543,0.0008985568,0.00023471966],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0025925115,0.0004512158,0.0016935574,0.000819259,0.000048190468,0.000032467684,0.0006281003,0.0003351732,0.00033357626],"category_scores_gemma":[0.009499757,0.00034051857,0.00029366344,0.00047636492,0.00091349334,0.00014013765,0.00010417101,0.0027489439,0.00000645078],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020660175,0.00015232485,0.022276428,0.00044143264,0.000024158293,0.00065501465,0.0007673472,0.000011414913,0.00077868387,0.0000062985932,0.9402299,0.03445039],"study_design_scores_gemma":[0.0047629527,0.0010419146,0.023291685,0.011702011,0.0003537859,0.00036003956,0.00027510143,0.0036377583,0.00005150811,0.00014544399,0.9540892,0.0002885812],"about_ca_topic_score_codex":0.00026184163,"about_ca_topic_score_gemma":0.000005067419,"teacher_disagreement_score":0.16164167,"about_ca_system_score_codex":0.00021859516,"about_ca_system_score_gemma":0.00088168937,"threshold_uncertainty_score":0.9999047},"labels":[],"label_agreement":null},{"id":"W2889279188","doi":"10.1109/jtehm.2018.2855213","title":"Image Quality Evaluation in Clinical Research: A Case Study on Brain and Cardiac MRI Images in Multi-Center Clinical Trials","year":2018,"lang":"en","type":"article","venue":"IEEE Journal of Translational Engineering in Health and Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Montreal Neurological Institute and Hospital; NeuroRx Research (Canada)","funders":"National Institute on Aging; National Institutes of Health; Norges Forskningsråd; U.S. Department of Defense","keywords":"Standard deviation; Image quality; Feature (linguistics); Artificial intelligence; Computer science; Pattern recognition (psychology); Pixel; Contrast (vision); Normal distribution; Gaussian; Mathematics; Computer vision; Image (mathematics); Statistics","score_opus":0.4361667054043206,"score_gpt":0.6219963752599054,"score_spread":0.18582966985558474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2889279188","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9671522,0.001765258,0.0021738927,0.02734243,0.0006677889,0.00087468256,0.0000028911288,0.0000052378728,0.000015612392],"genre_scores_gemma":[0.99365413,0.000941263,0.0034259432,0.0006888577,0.0012542118,0.000009764339,0.0000038914045,0.000015860414,0.0000060639222],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9918473,0.0036506369,0.0031267884,0.0002777686,0.0007981383,0.000299372],"domain_scores_gemma":[0.9907097,0.008017632,0.0003388567,0.00012901567,0.00028079833,0.0005239678],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1132711,0.00013898399,0.0011674692,0.00079739396,0.000043068867,0.000010963564,0.000055233482,0.00010561934,0.0000083529685],"category_scores_gemma":[0.026748909,0.00010363841,0.00008515641,0.00030458582,0.00025304934,0.000095055264,0.000008590572,0.0017790118,4.0664725e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018269444,0.001575654,0.920402,0.0004015561,0.00007289967,0.0011135043,0.0055586016,0.0004592963,0.00023362439,0.000027116123,0.00078348006,0.0675453],"study_design_scores_gemma":[0.038889516,0.0045997426,0.8640177,0.0020878282,0.000036377805,0.0005183089,0.0014409412,0.087678306,0.0000022583226,0.000052504405,0.0005716728,0.00010483619],"about_ca_topic_score_codex":0.00040602975,"about_ca_topic_score_gemma":0.000076513854,"teacher_disagreement_score":0.087219015,"about_ca_system_score_codex":0.00009126045,"about_ca_system_score_gemma":0.00044836273,"threshold_uncertainty_score":0.9814492},"labels":[],"label_agreement":null},{"id":"W2889506086","doi":"10.1016/j.ijrobp.2018.08.032","title":"A Deep Look Into the Future of Quantitative Imaging in Oncology: A Statement of Working Principles and Proposal for Change","year":2018,"lang":"en","type":"review","venue":"International Journal of Radiation Oncology*Biology*Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":117,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"National Cancer Institute","keywords":"Standardization; Data science; Data sharing; Computer science; Interpretability; Artificial intelligence; Field (mathematics); Precision medicine; Popularity; Big data; Medical imaging; Medical physics; Medicine; Psychology; Data mining; Pathology","score_opus":0.06351351214625009,"score_gpt":0.4243425421236295,"score_spread":0.3608290299773794,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2889506086","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022837475,0.9715934,0.016189668,0.0061824373,0.0022933574,0.0013089523,0.000026403179,0.000009838386,0.00011221264],"genre_scores_gemma":[0.005167399,0.95644736,0.03433151,0.00041321813,0.0033923658,0.000088882625,0.00010358418,0.00004644453,0.000009243498],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972015,0.00048616884,0.001585794,0.00025251586,0.00026399433,0.00020999637],"domain_scores_gemma":[0.99421453,0.0012871202,0.003590897,0.0001371715,0.00068829476,0.000081991966],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023254254,0.00025397542,0.0014726236,0.00035635778,0.0000522663,0.000014489321,0.0004076628,0.00025106157,0.000008487596],"category_scores_gemma":[0.00071613485,0.00016905354,0.0003505713,0.00018944715,0.0006583691,0.0001191742,0.00012405466,0.0007999943,9.2052295e-7],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023169736,0.00024165068,0.009582666,0.00079188036,0.0006552346,0.000020377816,0.0032620705,0.00001748356,0.000017876926,0.015566208,0.00011304116,0.9694998],"study_design_scores_gemma":[0.003677898,0.0018406999,0.00047801912,0.0052624536,0.00082232483,0.00021344982,0.0007541033,0.0082658045,0.00001313192,0.008504145,0.96997327,0.00019469945],"about_ca_topic_score_codex":0.000018389266,"about_ca_topic_score_gemma":0.000023300221,"teacher_disagreement_score":0.96986026,"about_ca_system_score_codex":0.0007254028,"about_ca_system_score_gemma":0.0015568455,"threshold_uncertainty_score":0.68938035},"labels":[],"label_agreement":null},{"id":"W2889871443","doi":"10.2172/1471213","title":"JRT (Joint Research Target) 2016 4th Quarter Report and Final Summary","year":2016,"lang":"en","type":"report","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Quarter (Canadian coin); Joint (building); Section (typography); Engineering; Computer science; History; Architectural engineering; Operating system; Archaeology","score_opus":0.08330529080593309,"score_gpt":0.4041953929235202,"score_spread":0.3208901021175871,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2889871443","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0032338456,0.0055127866,0.0022221482,0.026515415,0.0018111815,0.0009134795,0.000017437489,0.00020219141,0.95957154],"genre_scores_gemma":[0.009492253,0.012493578,0.006444384,0.000893122,0.0060250796,0.00008547407,0.00035550536,0.00019455295,0.9640161],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9943857,0.00018927555,0.0010023623,0.0010373102,0.0025250216,0.00086031324],"domain_scores_gemma":[0.99665904,0.00033348607,0.00030118067,0.0009917537,0.001043931,0.00067062525],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.007898699,0.00040842107,0.0010760947,0.00061922375,0.00020268223,0.00008166519,0.00017391739,0.00052462553,0.002145813],"category_scores_gemma":[0.003871334,0.00024882847,0.00024322829,0.00017500785,0.00054353965,0.00008799615,0.00027590952,0.002548515,0.00018374264],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000052721385,0.000074202864,0.007830814,0.00054557837,0.00017069148,0.0082002515,0.000051143536,6.877619e-8,0.00044283632,0.000067982626,0.9600407,0.022523044],"study_design_scores_gemma":[0.00093338575,0.00029615156,0.006178214,0.0025375332,0.00010879719,0.013563499,0.00006402284,0.00013488169,0.00006709777,0.0005627769,0.97521114,0.0003424956],"about_ca_topic_score_codex":0.0015179425,"about_ca_topic_score_gemma":0.000008023842,"teacher_disagreement_score":0.025622293,"about_ca_system_score_codex":0.00041147906,"about_ca_system_score_gemma":0.003738848,"threshold_uncertainty_score":0.9999964},"labels":[],"label_agreement":null},{"id":"W2890425879","doi":"10.1016/j.neuroimage.2018.09.019","title":"Corrigendum to ‘Normative morphometric data for cerebral cortical areas over the lifetime of the adult human brain’ [NeuroImage 156 (2017) 315–339]","year":2018,"lang":"en","type":"erratum","venue":"NeuroImage","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":52,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Normative; Human brain; Psychology; Neuroscience; Philosophy; Epistemology","score_opus":0.04173296702578636,"score_gpt":0.33280103710448217,"score_spread":0.2910680700786958,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2890425879","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18568102,0.0028667909,0.017707493,0.21083339,0.27171347,0.03332179,0.020366542,0.0015428759,0.25596663],"genre_scores_gemma":[0.13244969,0.00038070808,0.0041488446,0.14807783,0.028130095,0.00040499915,0.0091136815,0.001573574,0.6757206],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9945187,0.00051760796,0.0011173661,0.0013806964,0.0014904228,0.0009751929],"domain_scores_gemma":[0.9928035,0.00082372624,0.00082017935,0.004422852,0.0006044371,0.00052527647],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0012216251,0.000743593,0.0012504992,0.00048191295,0.00065702875,0.00018512181,0.0030824495,0.0003938251,0.00051871117],"category_scores_gemma":[0.018997945,0.00045160702,0.00051042007,0.0011526308,0.0011273953,0.00020341526,0.0019089656,0.0038638127,0.000111273715],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013522069,0.00021052531,0.0012503727,0.0003768601,0.00014705214,0.00008248327,0.0002453296,0.0000010963251,0.0017321563,0.00015852535,0.9948423,0.0008181004],"study_design_scores_gemma":[0.0020058225,0.0009517359,0.17637032,0.0005940727,0.00077001686,0.00028412425,0.00006411181,0.011982472,0.00007966608,0.00010723609,0.8062703,0.00052013947],"about_ca_topic_score_codex":0.0002266937,"about_ca_topic_score_gemma":0.000028147055,"teacher_disagreement_score":0.41975394,"about_ca_system_score_codex":0.00010106837,"about_ca_system_score_gemma":0.0005322202,"threshold_uncertainty_score":0.9997936},"labels":[],"label_agreement":null},{"id":"W2890978982","doi":"10.1200/jco.2018.36.15_suppl.3538","title":"Outcomes of oxaliplatin-based (Ox) chemotherapy (CT) on R0 resection of colonic liver metastases (CLM).","year":2018,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Alberta Health Services; BC Cancer Agency; University of Calgary","funders":"","keywords":"Medicine; Capecitabine; Oxaliplatin; Bevacizumab; Irinotecan; Colorectal cancer; Proportional hazards model; Perioperative; Radiology; Internal medicine; Chemotherapy; Oncology; Cancer","score_opus":0.10096094359669039,"score_gpt":0.48798117943028163,"score_spread":0.38702023583359124,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2890978982","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9849953,0.00014319658,0.0006212778,0.01116911,0.00109829,0.00013793509,0.0000029910907,0.000007317982,0.0018245463],"genre_scores_gemma":[0.9852589,0.00023470317,0.0094577605,0.0040523503,0.0008103304,0.0000010097713,0.0000017915103,0.00001847753,0.0001647211],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9965677,0.00051573553,0.0020933447,0.00015585244,0.0004881939,0.00017915027],"domain_scores_gemma":[0.99258125,0.004063431,0.002353677,0.0002203769,0.00055437087,0.0002268821],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0047073024,0.00012481051,0.0015977144,0.00021054795,0.000034605848,0.000003350659,0.00017114566,0.0001627727,0.00062555715],"category_scores_gemma":[0.01005158,0.00008259854,0.00054858834,0.00015959695,0.000644363,0.000043353448,0.00002162027,0.0009729186,0.00000839463],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.025403429,0.008041118,0.5922426,0.00026493147,0.002402391,0.00065719057,0.000248135,0.00036978335,0.0084851645,0.0012634391,0.022862857,0.337759],"study_design_scores_gemma":[0.02204222,0.07066757,0.8123657,0.00037309589,0.0007819408,0.00025353392,0.000072396164,0.006333667,0.0063731354,0.00046551423,0.0801177,0.00015348445],"about_ca_topic_score_codex":0.00006909933,"about_ca_topic_score_gemma":0.000024691393,"teacher_disagreement_score":0.3376055,"about_ca_system_score_codex":0.00007657086,"about_ca_system_score_gemma":0.0010541005,"threshold_uncertainty_score":0.9982872},"labels":[],"label_agreement":null},{"id":"W2891211750","doi":"10.1093/neuonc/noy139.025","title":"OS3.6 Development and validation of a DNA methylome-based predictor of meningioma recurrence and meningioma recurrence score","year":2018,"lang":"en","type":"article","venue":"Neuro-Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Nomogram; DNA methylation; Oncology; Internal medicine; Meningioma; Cohort; Medicine; Proportional hazards model; Microarray; Bioinformatics; Computational biology; Biology; Gene; Surgery; Genetics; Gene expression","score_opus":0.027704484369472752,"score_gpt":0.31974196413130257,"score_spread":0.2920374797618298,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2891211750","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9948934,0.0003192183,0.0019976052,0.001227485,0.0003545574,0.0003232337,0.000004762414,0.000032199274,0.00084758067],"genre_scores_gemma":[0.9771266,0.00005325441,0.02236478,0.0002838017,0.000108882254,0.00002060612,0.00001635769,0.000014819231,0.000010904218],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9983395,0.00019369,0.00054255774,0.0003871639,0.00029381338,0.00024327467],"domain_scores_gemma":[0.9984414,0.0005805482,0.00036798997,0.00020203098,0.00021218274,0.00019584768],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00079810113,0.00016691741,0.00050600915,0.00024101204,0.00007879971,0.000008648225,0.00011273227,0.00012691748,0.000032121614],"category_scores_gemma":[0.0016483282,0.00014716396,0.00003815355,0.00027077633,0.00064247387,0.000058871363,0.00009372191,0.00027787642,0.0000018104114],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00058031466,0.0002238701,0.065849744,0.0004398851,0.000080205966,0.00006381254,0.0035360982,0.0000045283377,0.6446797,0.00030434693,0.0006643507,0.28357315],"study_design_scores_gemma":[0.0059524872,0.0064002676,0.037712194,0.00089847913,0.00030888725,0.00046588818,0.00018625241,0.008576037,0.86033535,0.00023234195,0.07859025,0.0003415811],"about_ca_topic_score_codex":0.000015941474,"about_ca_topic_score_gemma":0.0000023203818,"teacher_disagreement_score":0.28323156,"about_ca_system_score_codex":0.000055952034,"about_ca_system_score_gemma":0.00043033718,"threshold_uncertainty_score":0.6001172},"labels":[],"label_agreement":null},{"id":"W2891429405","doi":"10.1200/jco.2016.34.15_suppl.6082","title":"A network meta-analysis of the sequencing and types of systemic therapies with definitive radiotherapy in locally advanced squamous cell carcinoma of head and neck (LASCCHN).","year":2016,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; Sunnybrook Health Science Centre; University of Toronto; Sunnybrook Hospital","funders":"","keywords":"Medicine; Meta-analysis; Randomized controlled trial; Oncology; Internal medicine; Radiation therapy; Taxane; Systemic therapy; Head and neck squamous-cell carcinoma; Induction chemotherapy; MEDLINE; Head and neck cancer; Cancer; Breast cancer","score_opus":0.07549374423689996,"score_gpt":0.38904257728516434,"score_spread":0.31354883304826436,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2891429405","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98276305,0.013071103,0.001236184,0.0025548723,0.000070808564,0.00014189593,0.0000022980869,0.0000013324615,0.00015847464],"genre_scores_gemma":[0.9920748,0.001642014,0.0056418832,0.0005379822,0.000065922184,0.0000016482302,1.414221e-7,0.000010522536,0.000025105312],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9973122,0.0006026791,0.0015652906,0.00013796479,0.00024614457,0.00013576123],"domain_scores_gemma":[0.9936889,0.003820162,0.0019660944,0.00015692392,0.00026841264,0.00009950594],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026407184,0.00010972386,0.002535046,0.0001423744,0.000015524985,0.0000019467927,0.000108755215,0.00012972819,0.000014884284],"category_scores_gemma":[0.0010948429,0.000046489462,0.00043100276,0.00027462022,0.0005358808,0.000048005884,0.000026067106,0.00041195672,3.7232873e-8],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0049327933,0.00037116505,0.9352134,0.00019550939,0.015682545,0.000105207146,0.0014718093,0.0030831285,0.0061996556,0.00030773962,0.000028313525,0.032408744],"study_design_scores_gemma":[0.023803774,0.019417103,0.8880732,0.0008442977,0.06102958,0.00056177075,0.0011124905,0.0035438666,0.0005061494,0.00052558305,0.00038110907,0.00020109868],"about_ca_topic_score_codex":0.000068574365,"about_ca_topic_score_gemma":0.00007331529,"teacher_disagreement_score":0.04714021,"about_ca_system_score_codex":0.000049732946,"about_ca_system_score_gemma":0.0005529794,"threshold_uncertainty_score":0.19744752},"labels":[],"label_agreement":null},{"id":"W2891772181","doi":"10.1136/jnnp-2018-abn.81","title":"THUR 174 The magnify-ms study: mavenclad® tablets in active rms","year":2018,"lang":"en","type":"article","venue":"Journal of Neurology Neurosurgery & Psychiatry","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Université de Montréal; St. Michael's Hospital","funders":"","keywords":"Medicine; Clinical trial; Clinical endpoint; Placebo; Internal medicine; Stock options; Nuclear medicine; Pathology; Alternative medicine","score_opus":0.011570069916885015,"score_gpt":0.2961322948749599,"score_spread":0.28456222495807487,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2891772181","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9252557,0.00020528323,0.000038930957,0.06502477,0.007654175,0.00028241787,0.0000013984776,0.000022201615,0.0015150835],"genre_scores_gemma":[0.96904427,0.00011814815,0.00012359157,0.02797287,0.0024762647,0.000005318112,6.9668295e-7,0.000050613253,0.00020823152],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9970457,0.0005906322,0.00096241315,0.0003628857,0.00052877294,0.0005095921],"domain_scores_gemma":[0.9979812,0.0004886833,0.0006717536,0.0004538506,0.00017383079,0.00023066933],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0014115662,0.00025789835,0.0006782817,0.00051496044,0.00020238805,0.00004784085,0.00038316372,0.00013713587,0.00017437329],"category_scores_gemma":[0.00080347114,0.00016712233,0.00026202528,0.0006612754,0.00040187547,0.00015415518,0.00009481542,0.002599298,0.000021250311],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021992943,0.0013269914,0.95302486,0.000024913712,0.00011612152,0.002010189,0.0004752971,0.000039036095,0.0020730933,0.00005246924,0.033469263,0.005188445],"study_design_scores_gemma":[0.0024990425,0.003935051,0.96054006,0.00006579427,0.00015940827,0.006865528,0.00015055222,0.00053472037,0.00004683069,0.0007678833,0.024282973,0.00015217862],"about_ca_topic_score_codex":0.000028571883,"about_ca_topic_score_gemma":0.00002415358,"teacher_disagreement_score":0.043788526,"about_ca_system_score_codex":0.000021456333,"about_ca_system_score_gemma":0.00032135716,"threshold_uncertainty_score":0.99970174},"labels":[],"label_agreement":null},{"id":"W2891830669","doi":"10.1200/jco.2016.34.15_suppl.6626","title":"FDG-PET/CT in small cell lung cancer (SCLC): A value analysis.","year":2016,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre","funders":"","keywords":"Medicine; Radiology; Lung cancer; Nuclear medicine; Oncology","score_opus":0.050245488409703463,"score_gpt":0.46887313749560877,"score_spread":0.41862764908590533,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2891830669","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95453084,0.0010855361,0.002695659,0.036503375,0.0011943526,0.00010892716,0.0000014586212,0.000009123784,0.0038707193],"genre_scores_gemma":[0.9833104,0.0024736691,0.0061335615,0.00556014,0.0012143982,0.0000033839208,6.847094e-7,0.000018901175,0.0012848574],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9962666,0.0005790739,0.0023013258,0.00023552307,0.00029341673,0.00032407718],"domain_scores_gemma":[0.99480206,0.0028837086,0.0013776693,0.00020664008,0.0002067844,0.00052313454],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0056690974,0.00013884886,0.0018470022,0.0003871399,0.000024384193,0.000008084682,0.00023521706,0.00007518607,0.00044223355],"category_scores_gemma":[0.0055273953,0.000076515025,0.0007809041,0.00039370838,0.00019269405,0.00006979178,0.000057094294,0.0014261178,0.000011479638],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007395101,0.0009117514,0.85735255,0.00003822883,0.00092337694,0.0075033405,0.000042637395,0.0003345785,0.00056368386,0.00012004992,0.0046955426,0.12677476],"study_design_scores_gemma":[0.021486802,0.0033659872,0.81791097,0.0006003636,0.0046214717,0.001451755,0.000060269176,0.017761867,0.0001226459,0.00058349816,0.13176984,0.00026456322],"about_ca_topic_score_codex":0.0001812413,"about_ca_topic_score_gemma":0.00011171792,"teacher_disagreement_score":0.12707429,"about_ca_system_score_codex":0.00025561967,"about_ca_system_score_gemma":0.0014992002,"threshold_uncertainty_score":0.66172075},"labels":[],"label_agreement":null},{"id":"W2891923862","doi":"10.1200/jco.2017.35.15_suppl.e20065","title":"Real-world data evaluating the value of PET-CT for mediastinal staging in patients diagnosed with non-small cell lung cancer in an area with high prevalence of granulomatous diseases: The LACOG-0114 study.","year":2017,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut universitaire de cardiologie et de pneumologie de Québec","funders":"","keywords":"Medicine; Lung cancer; Mediastinoscopy; Mediastinum; Radiology; Standardized uptake value; Nuclear medicine; Internal medicine; Positron emission tomography","score_opus":0.09365035847660579,"score_gpt":0.4875902462018383,"score_spread":0.3939398877252325,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2891923862","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99670744,0.000088727924,0.00014457526,0.0015735687,0.0002973667,0.0011008574,0.000035406225,0.0000027123306,0.000049349317],"genre_scores_gemma":[0.9966197,0.00025880334,0.0025475542,0.00021729457,0.00027862808,0.000030499377,0.0000062767326,0.000024633277,0.000016616588],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99617624,0.00078979606,0.0017713559,0.00030686834,0.0006813709,0.00027436134],"domain_scores_gemma":[0.98896074,0.0058233007,0.0037722744,0.0008090407,0.00043825692,0.000196409],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008139696,0.00016600156,0.0012347655,0.00012140531,0.000114231414,0.000020929649,0.0010799309,0.000027323324,0.0000117309955],"category_scores_gemma":[0.0066202506,0.000078027355,0.00009676435,0.00013276751,0.000596232,0.0001768759,0.00019208566,0.0010888315,6.1275664e-8],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0051293685,0.002501481,0.9669183,0.00029195883,0.00013076783,0.00032548935,0.0006413513,0.0015918164,0.000010256042,0.000005347494,0.00005682245,0.022397058],"study_design_scores_gemma":[0.016759612,0.011710756,0.91682774,0.001224373,0.0010125438,0.000014436687,0.00055253983,0.051774733,0.00000367166,0.000026463647,0.000011638777,0.000081489234],"about_ca_topic_score_codex":0.0019212954,"about_ca_topic_score_gemma":0.0031499192,"teacher_disagreement_score":0.050182916,"about_ca_system_score_codex":0.00009163855,"about_ca_system_score_gemma":0.0016354219,"threshold_uncertainty_score":0.79255366},"labels":[],"label_agreement":null},{"id":"W2891981628","doi":"10.1200/jco.2017.35.15_suppl.5000","title":"Development and validation of a novel clinical-genomic risk group classification for prostate cancer incorporating genomic and clinicopathologic risk.","year":2017,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Genome British Columbia","funders":"","keywords":"Medicine; Prostate cancer; Internal medicine; Prostatectomy; Oncology; Metastasis; Cancer; Retrospective cohort study; Cohort; Prostate; Prostate biopsy","score_opus":0.17988952275501133,"score_gpt":0.49409810977178814,"score_spread":0.3142085870167768,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2891981628","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98821306,0.0004526328,0.0071197147,0.0027029603,0.0009736042,0.0004256576,0.000011856136,0.000006479552,0.00009405428],"genre_scores_gemma":[0.8215416,0.005002303,0.17231132,0.00033128515,0.0007485464,0.000012003631,0.000005058595,0.000017778335,0.000030077901],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.995417,0.00042705893,0.0034810242,0.00031231533,0.00018280024,0.00017978749],"domain_scores_gemma":[0.986147,0.00265868,0.010299085,0.0002414864,0.00035195515,0.0003017825],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.018877443,0.00014258045,0.0013495785,0.00009528251,0.00026508092,0.00003435003,0.0001854417,0.00032994902,0.0000047095955],"category_scores_gemma":[0.021113407,0.00010424863,0.00022269633,0.000030573698,0.000644471,0.000124434,0.00012064965,0.0012426883,6.9924096e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009731446,0.00034070367,0.5632083,0.000048046564,0.000119963086,0.0000082884,0.00012154849,0.000020512425,0.0015016866,0.000052117983,0.000042566666,0.43356314],"study_design_scores_gemma":[0.010650565,0.0030775066,0.9641279,0.00016671684,0.0005447245,0.000072860195,0.00009788353,0.013025904,0.00003737852,0.0005150132,0.0075806202,0.00010290666],"about_ca_topic_score_codex":0.000048148475,"about_ca_topic_score_gemma":0.000025891746,"teacher_disagreement_score":0.43346024,"about_ca_system_score_codex":0.000080054655,"about_ca_system_score_gemma":0.0009772112,"threshold_uncertainty_score":0.9871322},"labels":[],"label_agreement":null},{"id":"W2892218058","doi":"10.1002/mp.13136","title":"Performance/outcomes data and physician process challenges for practical big data efforts in radiation oncology","year":2018,"lang":"en","type":"article","venue":"Medical Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"National Cancer Institute","keywords":"Radiation oncology; Big data; Data science; Medical physics; Medicine; Medical education; Computer science; Internal medicine; Radiation therapy; Data mining","score_opus":0.09679100752363538,"score_gpt":0.42643168115143126,"score_spread":0.32964067362779587,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2892218058","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.772181,0.0011235087,0.039726257,0.17441872,0.0022646384,0.0017133353,0.00008513776,0.00018502919,0.008302399],"genre_scores_gemma":[0.98994654,0.0011016882,0.0014460747,0.0033107465,0.0035421217,0.00002401102,0.00057548424,0.00003089424,0.000022411883],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982736,0.000045783294,0.00029994044,0.00054579385,0.0005054443,0.00032941342],"domain_scores_gemma":[0.9983078,0.00047208142,0.00011029709,0.0007857402,0.00006294671,0.0002611219],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012953592,0.00014862772,0.00043655542,0.000049911432,0.00009504107,0.00001523286,0.0003866911,0.00014017415,0.000011042323],"category_scores_gemma":[0.0025601673,0.000116570576,0.000020439546,0.00012978648,0.0004933162,0.00028235067,0.00034857367,0.00051488675,0.000008245185],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009343049,0.00036533907,0.019204987,0.0003063607,0.000049131995,0.000021106876,0.00035597247,4.54282e-7,0.000013193893,0.0002857581,0.0018928273,0.97741145],"study_design_scores_gemma":[0.007924777,0.0013779755,0.06778387,0.00056391524,0.00031829887,0.00011561682,0.0003202849,0.7381762,0.00022827362,0.0035960048,0.17916036,0.00043440427],"about_ca_topic_score_codex":0.000011795259,"about_ca_topic_score_gemma":0.000017444647,"teacher_disagreement_score":0.97697705,"about_ca_system_score_codex":0.00004031374,"about_ca_system_score_gemma":0.0005659185,"threshold_uncertainty_score":0.47536102},"labels":[],"label_agreement":null},{"id":"W2893210156","doi":"10.1016/j.cjca.2018.07.107","title":"MULTI-VIEW 3D FUSION ECHOCARDIOGRAPHY: ENHANCING CLINICAL FEASIBILITY WITH A NOVEL RESPIRATORY TRACKING TECHNIQUE","year":2018,"lang":"en","type":"article","venue":"Canadian Journal of Cardiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Alberta Hospital Edmonton","funders":"","keywords":"Parasternal line; Medicine; Transducer; Voxel; Artificial intelligence; Computer vision; Protocol (science); Ultrasound; Tracking (education); Radiology; Computer science; Cardiology; Acoustics; Pathology","score_opus":0.05091582749301593,"score_gpt":0.3568780958038009,"score_spread":0.305962268310785,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2893210156","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4295583,0.0011100336,0.56457174,0.0009229811,0.0010765633,0.00046178972,0.000007927275,0.000026006137,0.002264628],"genre_scores_gemma":[0.96193576,0.00006342681,0.033689983,0.0015685704,0.0026887727,0.000004403867,0.0000019507038,0.00003245965,0.000014661178],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99793303,0.00034168418,0.00078386784,0.00029444622,0.00020094632,0.00044600066],"domain_scores_gemma":[0.9975025,0.00015650831,0.0003237325,0.00035985198,0.0006392801,0.0010181149],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0040763407,0.0001821098,0.0009446633,0.00045946852,0.0001753745,0.000023168719,0.00020461733,0.00024830547,0.000016337082],"category_scores_gemma":[0.0016243935,0.00013605424,0.00040400604,0.00030555844,0.0008554453,0.00008284896,0.000017798558,0.0012924813,0.0000035429778],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025545518,0.000017336257,0.9431969,0.000067121255,0.00044104955,0.0008770829,0.00012818897,0.000104139064,0.013578772,0.000027191802,0.001764757,0.039542016],"study_design_scores_gemma":[0.004493943,0.003039507,0.7456131,0.0010624011,0.0005052664,0.005326112,0.00012727661,0.00031137248,0.0006211728,0.000031346135,0.23853782,0.0003307147],"about_ca_topic_score_codex":0.00031672182,"about_ca_topic_score_gemma":0.00055656326,"teacher_disagreement_score":0.5323775,"about_ca_system_score_codex":0.00017915208,"about_ca_system_score_gemma":0.002000071,"threshold_uncertainty_score":0.561526},"labels":[],"label_agreement":null},{"id":"W2894753707","doi":"10.1007/s00330-018-5754-y","title":"Impact of image reconstruction methods on quantitative accuracy and variability of FDG-PET volumetric and textural measures in solid tumors","year":2018,"lang":"en","type":"article","venue":"European Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":24,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Tehran University of Medical Sciences and Health Services","keywords":"Kurtosis; Nuclear medicine; Coefficient of variation; Medicine; Iterative reconstruction; Imaging phantom; Similarity (geometry); Skewness; Mathematics; Biomedical engineering; Radiology; Statistics; Artificial intelligence; Computer science; Image (mathematics)","score_opus":0.02644131493757322,"score_gpt":0.4002001680496842,"score_spread":0.373758853112111,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2894753707","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9911027,0.00019056564,0.0051145353,0.00013677275,0.000114884504,0.00014437667,0.0000043606615,0.000012632694,0.0031791546],"genre_scores_gemma":[0.94885826,0.00009840832,0.050892346,0.000047120542,0.000075067845,7.588027e-7,0.0000032928833,0.000014335271,0.00001040692],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9975088,0.0015902045,0.00040042138,0.00026208223,0.000073050105,0.00016543819],"domain_scores_gemma":[0.9985175,0.00088741875,0.00022244855,0.00017655198,0.00010687917,0.00008918],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002839451,0.0001188834,0.00048767202,0.00030508862,0.00003058508,0.0000055379746,0.00006341087,0.000028496108,0.00003366796],"category_scores_gemma":[0.008924298,0.00008780852,0.000055470744,0.00024460684,0.0011355685,0.000058639678,0.00004218986,0.00031573852,0.0000018517765],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007433001,0.0001067585,0.47362897,0.000095842945,0.00014220209,0.000058960606,0.0011377413,0.000017016991,0.1404102,0.00050360465,0.00015189122,0.3830035],"study_design_scores_gemma":[0.001159924,0.0020389,0.98401165,0.000099875346,0.000037278074,0.001001276,0.000080122794,0.010480039,0.00058551144,0.00037678884,0.000046314755,0.000082306404],"about_ca_topic_score_codex":0.00012741382,"about_ca_topic_score_gemma":0.0000015439053,"teacher_disagreement_score":0.5103827,"about_ca_system_score_codex":0.000037152342,"about_ca_system_score_gemma":0.000045507884,"threshold_uncertainty_score":0.999424},"labels":[],"label_agreement":null},{"id":"W2897043342","doi":"10.1016/j.ijrobp.2018.06.222","title":"An MRI-Based Radiomic Signature for Disease-Free Survival in Locally Advanced Cervical Cancer","year":2018,"lang":"en","type":"article","venue":"International Journal of Radiation Oncology*Biology*Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Princess Margaret Cancer Centre; University Health Network","funders":"","keywords":"Medicine; Radiomics; Cervical cancer; Stage (stratigraphy); Feature selection; Correlation; Magnetic resonance imaging; Radiology; Pearson product-moment correlation coefficient; Cancer; Nuclear medicine; Artificial intelligence; Internal medicine; Statistics","score_opus":0.012776585688523332,"score_gpt":0.35560912901008396,"score_spread":0.3428325433215606,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2897043342","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6268027,0.0010944591,0.3285284,0.036003146,0.0064923977,0.0005757281,0.0001767734,0.000062383,0.00026404904],"genre_scores_gemma":[0.97616273,0.00021715395,0.012704063,0.004817387,0.005825843,0.0000282933,0.00016804942,0.000044464305,0.000032011536],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981746,0.00021172613,0.00067145395,0.00030329576,0.00034255785,0.00029633442],"domain_scores_gemma":[0.9974945,0.00048815983,0.0006071271,0.00022614386,0.00087461364,0.0003094202],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008127861,0.00019753946,0.00050975976,0.00021831256,0.000067396424,0.000026934546,0.0005589733,0.0002240098,0.00011795013],"category_scores_gemma":[0.0008395765,0.00017429571,0.00021725707,0.00017262879,0.00038631284,0.00022065574,0.000038408656,0.0007060425,0.0000054899356],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0063112285,0.0011622688,0.5045817,0.00004486562,0.00044747707,0.00012633696,0.0002979708,0.01622639,0.014669902,0.008033586,0.0033586943,0.44473958],"study_design_scores_gemma":[0.055596042,0.0058774864,0.17481461,0.0005805804,0.00044536567,0.00011565992,0.00012104764,0.6135763,0.0032242576,0.032970794,0.11194416,0.0007336715],"about_ca_topic_score_codex":0.00002825078,"about_ca_topic_score_gemma":0.000029450348,"teacher_disagreement_score":0.59734994,"about_ca_system_score_codex":0.0007293642,"about_ca_system_score_gemma":0.0015193734,"threshold_uncertainty_score":0.71075726},"labels":[],"label_agreement":null},{"id":"W2897510230","doi":"10.1016/j.jtho.2018.08.1780","title":"P3.09-11 Genomic Organization at Large Scales (GOALS) within Nuclei and Cell Sociology for Predicting Lung Cancer Outcomes","year":2018,"lang":"en","type":"article","venue":"Journal of Thoracic Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Stromal cell; Nucleus; Medicine; Cell; Lung cancer; Stain; Pathology; Feulgen stain; Outcome (game theory); Biology; Genetics; Mathematics; Psychiatry","score_opus":0.012329085337085502,"score_gpt":0.39450659283195355,"score_spread":0.38217750749486806,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2897510230","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97925866,0.0010073124,0.007803545,0.010195064,0.001325369,0.0002174504,0.000007990884,0.000021495242,0.00016310657],"genre_scores_gemma":[0.9823002,0.00017442116,0.013157829,0.002199433,0.0014835537,0.000004070251,0.0000071826207,0.000043546734,0.00062975625],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9986418,0.00014494496,0.0005806896,0.00018643039,0.0001512015,0.00029496025],"domain_scores_gemma":[0.9982373,0.00034953226,0.00073647517,0.00010383721,0.00037696937,0.00019590203],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013027046,0.00014079052,0.0005991568,0.00014610226,0.00025090645,0.000014411021,0.00011983939,0.00021699729,0.00016715744],"category_scores_gemma":[0.0008858758,0.00010569651,0.000087028966,0.00008382844,0.0002720479,0.00007939701,0.00009751799,0.0004109032,0.000004068717],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046000638,0.00013249539,0.9528569,0.00020546543,0.00017604943,0.000043615695,0.0027634439,0.000041193027,0.027639639,0.00007601755,0.006098701,0.009506496],"study_design_scores_gemma":[0.011158516,0.0053338953,0.7784906,0.0005673535,0.0029198623,0.003198548,0.0021818602,0.1056739,0.007812577,0.00082321826,0.08119464,0.0006450268],"about_ca_topic_score_codex":0.000013533911,"about_ca_topic_score_gemma":0.000040336396,"teacher_disagreement_score":0.17436628,"about_ca_system_score_codex":0.00039265986,"about_ca_system_score_gemma":0.0002781407,"threshold_uncertainty_score":0.43101788},"labels":[],"label_agreement":null},{"id":"W2897619994","doi":"10.1016/j.jclinepi.2018.10.010","title":"Selective outcome reporting is present in randomized controlled trials in lung cancer immunotherapies","year":2018,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Medicine; Publication bias; Randomized controlled trial; Scopus; MEDLINE; Family medicine; Clinical trial; Blinding; Trial registration; Systematic review; Reporting bias; Lung cancer; Randomization; Consolidated Standards of Reporting Trials; Meta-analysis; Internal medicine","score_opus":0.24100094364110025,"score_gpt":0.5758553091539602,"score_spread":0.33485436551285996,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2897619994","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.037916802,0.017177569,0.0015121645,0.93612754,0.0047509167,0.0020096356,0.0000035757053,0.0000127379435,0.00048906944],"genre_scores_gemma":[0.014002881,0.016023386,0.0056901267,0.92945945,0.032598663,0.00016978693,0.00001259625,0.000097775206,0.0019453227],"study_design_codex":"not_applicable","study_design_gemma":"randomized_trial","domain_scores_codex":[0.86545384,0.06364415,0.0685021,0.0007313855,0.000721197,0.000947355],"domain_scores_gemma":[0.29221863,0.576464,0.12891746,0.000787592,0.0012082395,0.00040411926],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.44059506,0.00051882357,0.056168247,0.0009386146,0.00003700286,0.00001815045,0.00037387322,0.0020752696,0.00050745654],"category_scores_gemma":[0.86862737,0.0002827895,0.008267919,0.00022737985,0.00078110857,0.000069058944,0.00007378462,0.014088891,0.0000033160868],"study_design_candidate":"randomized_trial","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.107869245,0.00013614105,0.3920329,0.00029727863,0.00428098,0.0012946174,0.00020621387,0.00008817239,0.000005279252,0.000009957278,0.49068823,0.0030910054],"study_design_scores_gemma":[0.75166553,0.0007544808,0.05178219,0.0061362144,0.0035302984,0.0005544602,0.000029890605,0.02996934,0.000002639551,0.005555626,0.14952374,0.0004955889],"about_ca_topic_score_codex":0.0007336875,"about_ca_topic_score_gemma":0.000012745268,"teacher_disagreement_score":0.64379627,"about_ca_system_score_codex":0.00028053919,"about_ca_system_score_gemma":0.0011905242,"threshold_uncertainty_score":0.99996245},"labels":[],"label_agreement":null},{"id":"W2898005809","doi":"10.1016/j.jalz.2018.06.2208","title":"IC‐P‐142: SURFACE‐BASED MULTIMODAL CLUSTER ANALYSIS REVEALS TOPOGRAPHICAL HETEROGENEITY OF ALZHEIMER'S DISEASE","year":2018,"lang":"en","type":"article","venue":"Alzheimer s & Dementia","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Montreal Neurological Institute and Hospital","funders":"","keywords":"Dementia; Clinical Dementia Rating; Atrophy; Pathology; Medicine; Internal medicine; Nuclear medicine; Psychology; Disease","score_opus":0.022501095141979875,"score_gpt":0.31968929827793874,"score_spread":0.29718820313595884,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2898005809","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9611941,0.0209756,0.012072655,0.004272987,0.00036210375,0.0005699356,0.00004002653,0.00011448626,0.00039811266],"genre_scores_gemma":[0.9810961,0.000032183427,0.015137814,0.0032641124,0.00025326468,0.000013937197,0.00014984244,0.000046153036,0.0000066135617],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9972687,0.0002210455,0.00071690406,0.0006150543,0.0006579886,0.00052030716],"domain_scores_gemma":[0.9978885,0.00010891962,0.0002682428,0.0008218169,0.0002671926,0.00064534467],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007534805,0.00031439762,0.0007192985,0.00033528602,0.00016451461,0.000035877947,0.00024917987,0.00012768824,0.00074072985],"category_scores_gemma":[0.00013723952,0.00027120952,0.00067056884,0.00085548515,0.0005800694,0.000097744865,0.00012720937,0.00033083244,0.00004444831],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00057893473,0.00076025317,0.9084523,0.000028630464,0.062848374,0.000065863205,0.0001393054,0.00056532957,0.0069353385,0.00011909935,0.0030571017,0.016449502],"study_design_scores_gemma":[0.0032746946,0.0003877329,0.61842877,0.00007813914,0.20448114,0.0000078872845,0.00001955576,0.15087746,0.017576031,0.00010387289,0.004226013,0.00053872657],"about_ca_topic_score_codex":0.00023891346,"about_ca_topic_score_gemma":0.000029303284,"teacher_disagreement_score":0.2900235,"about_ca_system_score_codex":0.0000063576163,"about_ca_system_score_gemma":0.000101391546,"threshold_uncertainty_score":0.999974},"labels":[],"label_agreement":null},{"id":"W2898012179","doi":"10.1093/annonc/mdy283.105","title":"Predictive radiomics signature for treatment response to nivolumab in patients (pts) with advanced renal cell carcinoma (RCC)","year":2018,"lang":"en","type":"article","venue":"Annals of Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre","funders":"","keywords":"Medicine; Nivolumab; Renal cell carcinoma; Radiomics; Radiology; Nephrectomy; Biopsy; Imaging biomarker; Clear cell renal cell carcinoma; Oncology; Internal medicine; Magnetic resonance imaging; Immunotherapy; Kidney; Cancer","score_opus":0.018601118334254183,"score_gpt":0.3371707721320479,"score_spread":0.3185696537977937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2898012179","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99131167,0.0001121222,0.0009037425,0.0052171075,0.00014278799,0.00094671454,0.00003997099,0.000015293885,0.0013106023],"genre_scores_gemma":[0.99037665,0.00002096306,0.0068154526,0.0019112757,0.00015114514,0.0000739987,0.000047585396,0.000028337001,0.0005745787],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9987523,0.0001236273,0.00029070047,0.00032726736,0.0001623224,0.00034377063],"domain_scores_gemma":[0.99879265,0.00029421,0.00014730045,0.00022826937,0.00033600462,0.00020154989],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040109432,0.00015924225,0.0004995192,0.0002222075,0.000047286612,0.0000036599602,0.00009458048,0.00014200785,0.00002283411],"category_scores_gemma":[0.0004064127,0.0001214344,0.00007360953,0.00019286445,0.00017512054,0.00004309334,0.00002772467,0.00015474498,0.0000044121516],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.24844758,0.0047830953,0.10518144,0.00014070618,0.00025517328,0.00018917565,0.0074652173,0.0009461514,0.032339923,0.000044363722,0.026420277,0.5737869],"study_design_scores_gemma":[0.049435444,0.32599014,0.34976733,0.0002559912,0.00018885407,0.00003301012,0.00041019116,0.0034631228,0.048781592,0.00012415509,0.22114938,0.00040076996],"about_ca_topic_score_codex":0.00005819395,"about_ca_topic_score_gemma":0.000035880996,"teacher_disagreement_score":0.57338613,"about_ca_system_score_codex":0.00022038033,"about_ca_system_score_gemma":0.00039187897,"threshold_uncertainty_score":0.49519512},"labels":[],"label_agreement":null},{"id":"W2898124802","doi":"10.1016/j.jtho.2018.08.330","title":"MA02.11 Achieving Value in Cancer Diagnostics: Blood Versus Tissue Molecular Profiling - A Prospective Canadian Study (VALUE)","year":2018,"lang":"en","type":"article","venue":"Journal of Thoracic Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Juravinski Cancer Centre","funders":"","keywords":"Medicine; Oncology; Lung cancer; Genotyping; Liquid biopsy; Internal medicine; Clinical endpoint; Clinical trial; Cancer; Genotype; Gene; Genetics","score_opus":0.017977069198978256,"score_gpt":0.42881479246779763,"score_spread":0.4108377232688194,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2898124802","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9874199,0.0011537034,0.0002578114,0.0065451274,0.0016918711,0.00064435165,0.0000025489228,0.000013263875,0.0022714166],"genre_scores_gemma":[0.9896546,0.00012695004,0.008090147,0.0007367832,0.0012463244,0.000021134252,0.0000014467452,0.000039574883,0.00008301504],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99781734,0.00038611065,0.0006443679,0.0002710872,0.0003894245,0.0004916467],"domain_scores_gemma":[0.99828446,0.00033077295,0.00039007328,0.00020315082,0.00031357128,0.00047794398],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016814906,0.00019345271,0.00068610965,0.00068448443,0.00011504034,0.000029315246,0.00023668539,0.00015971319,0.00009545928],"category_scores_gemma":[0.002752999,0.00016393495,0.000088947745,0.00046879356,0.00017271357,0.000097936805,0.000061851126,0.00115837,0.000008512528],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0023478128,0.002102634,0.85857254,0.00014348797,0.00089369784,0.018738896,0.0054008625,0.0009909784,0.009394414,0.0006202548,0.00058116444,0.10021324],"study_design_scores_gemma":[0.04215441,0.081230775,0.71712106,0.0046305326,0.01027093,0.008361428,0.014112152,0.018114233,0.03279416,0.0015741533,0.06766646,0.0019697149],"about_ca_topic_score_codex":0.020396603,"about_ca_topic_score_gemma":0.0152948545,"teacher_disagreement_score":0.14145151,"about_ca_system_score_codex":0.0010348766,"about_ca_system_score_gemma":0.00167981,"threshold_uncertainty_score":0.98612666},"labels":[],"label_agreement":null},{"id":"W2898290327","doi":"10.1016/j.jtho.2018.08.424","title":"MA13.05 The Canada Lymph Node Sonographic Score: National Validation of a Sonographic Score to Determine Mediastinal Lymph Node Malignancy","year":2018,"lang":"en","type":"article","venue":"Journal of Thoracic Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Laurentian University","funders":"","keywords":"Medicine; Malignancy; Radiology; Lymph node; Receiver operating characteristic; Biopsy; Lung cancer; Internal medicine","score_opus":0.027037318132066522,"score_gpt":0.36076522510431375,"score_spread":0.33372790697224725,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2898290327","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97327536,0.00031941402,0.0033983404,0.02031839,0.0016322437,0.00020585275,0.000011864945,0.000012768121,0.00082575344],"genre_scores_gemma":[0.9799181,0.00006158662,0.010367887,0.007745696,0.001782811,0.0000104763885,0.000009248761,0.00003335669,0.00007080407],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9968507,0.00030311756,0.0010730062,0.00024913705,0.0010935366,0.0004304899],"domain_scores_gemma":[0.99660265,0.00048341698,0.0010553999,0.00026188063,0.0011855222,0.00041113107],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023078835,0.00023274551,0.0006913821,0.0006184381,0.00019341244,0.000026745602,0.00045606116,0.00015154116,0.00015421536],"category_scores_gemma":[0.0017622627,0.0001610474,0.00023094637,0.00078793435,0.0004404469,0.00012220544,0.000094896,0.00053188787,0.0000052503524],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0035410628,0.0007721839,0.7174603,0.00050645694,0.0008140919,0.0011336972,0.0014016643,0.0009637879,0.018952057,0.00030722623,0.024728328,0.22941914],"study_design_scores_gemma":[0.0069795577,0.0039025869,0.8752174,0.00384649,0.0018135225,0.0218793,0.00097615685,0.016244547,0.009075121,0.0020836906,0.05711818,0.0008634631],"about_ca_topic_score_codex":0.004262256,"about_ca_topic_score_gemma":0.002324663,"teacher_disagreement_score":0.22855568,"about_ca_system_score_codex":0.00044186143,"about_ca_system_score_gemma":0.0033611143,"threshold_uncertainty_score":0.6567322},"labels":[],"label_agreement":null},{"id":"W2898379648","doi":"10.1016/j.jtho.2018.08.981","title":"P1.16-12 Identification of a Biomarker Panel in Resected NSCLC That Predicts Patient Outcomes and Benefit from Adjuvant Chemotherapy","year":2018,"lang":"en","type":"article","venue":"Journal of Thoracic Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Medicine; Oncology; Internal medicine; Immunohistochemistry; Biomarker; Adjuvant; Tissue microarray; Adjuvant chemotherapy; Chemotherapy; Stage (stratigraphy); Multivariate analysis; Pathology; Cancer","score_opus":0.032323561277669374,"score_gpt":0.3877315770991356,"score_spread":0.3554080158214662,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2898379648","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9902744,0.00061900564,0.0008001076,0.007212375,0.0005611916,0.00017257807,0.0000063101406,0.000008189197,0.00034584152],"genre_scores_gemma":[0.9962232,0.00027807476,0.0023399007,0.0008527627,0.00015834717,0.0000026272369,0.000007787445,0.000017241202,0.000120070654],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99841195,0.00012292126,0.0007891726,0.00016625137,0.00032959323,0.00018010313],"domain_scores_gemma":[0.9983598,0.00027659617,0.0008382334,0.00018243022,0.00019405143,0.00014889694],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00090654875,0.00011960459,0.000611293,0.00031396278,0.000033623524,0.000012450773,0.00012071537,0.00014688651,0.00009846452],"category_scores_gemma":[0.00053610525,0.00008612011,0.00008783502,0.00014024132,0.0002253305,0.00009470811,0.00004108315,0.0003873271,0.0000018047597],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019102348,0.00035163978,0.17543508,0.000036308487,0.00017157891,0.00008844273,0.0016775117,0.0000024961378,0.033996202,0.000008278369,0.00079916907,0.78552306],"study_design_scores_gemma":[0.0022791794,0.0012899624,0.9824378,0.00033148009,0.00014067187,0.00024699344,0.00040713817,0.0021345655,0.0060509485,0.00092863216,0.003673103,0.00007950645],"about_ca_topic_score_codex":0.0001415073,"about_ca_topic_score_gemma":0.00004824393,"teacher_disagreement_score":0.8070027,"about_ca_system_score_codex":0.00016381491,"about_ca_system_score_gemma":0.00011834038,"threshold_uncertainty_score":0.35118762},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W2899847761","doi":"10.1016/j.radonc.2018.10.027","title":"Vulnerabilities of radiomic signature development: The need for safeguards","year":2018,"lang":"en","type":"article","venue":"Radiotherapy and Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":317,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; Princess Margaret Cancer Centre; Institute of Cancer Research; Ontario Institute for Cancer Research; University of Toronto; University Health Network","funders":"Canadian Institutes of Health Research; Terry Fox Research Institute; Ontario Institute for Cancer Research","keywords":"Voxel; Computer science; Concordance; Volume (thermodynamics); Artificial intelligence; Head and neck; Signature (topology); Concordance correlation coefficient; Pattern recognition (psychology); Index (typography); Data mining; Medicine; Medical physics; Statistics; Mathematics; Surgery","score_opus":0.012764149414445994,"score_gpt":0.32178028859215796,"score_spread":0.309016139177712,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2899847761","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94206965,0.0066459146,0.025176302,0.021446617,0.00084616477,0.00081996917,0.0000037631485,0.000051870335,0.002939734],"genre_scores_gemma":[0.9566757,0.00044616804,0.03471285,0.005651655,0.0010594968,0.00004247903,0.000009179936,0.000028683604,0.0013737794],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99922425,0.0000741108,0.00024067266,0.00016751897,0.00009516523,0.00019825998],"domain_scores_gemma":[0.9991735,0.0004410347,0.000087150744,0.00014717912,0.00007988387,0.00007121592],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00066861295,0.0001068978,0.00034664042,0.000068665606,0.00017246984,0.00000780664,0.000092575356,0.00013109278,0.0001334323],"category_scores_gemma":[0.00016244617,0.00006568729,0.00006113059,0.00008396259,0.00062952994,0.00002416852,0.0000123579575,0.00022558623,7.3061307e-7],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021202136,0.00021377529,0.0057802303,0.00026534146,0.00047196515,0.000008725527,0.015287593,0.000011253147,0.081675015,0.0071593276,0.023820972,0.8631856],"study_design_scores_gemma":[0.0039709886,0.0016630188,0.0045098932,0.00004943522,0.000059124344,0.00018195919,0.00039981835,0.0064994167,0.006030632,0.0006854701,0.9758326,0.0001176902],"about_ca_topic_score_codex":0.00001346648,"about_ca_topic_score_gemma":0.000009046217,"teacher_disagreement_score":0.9520116,"about_ca_system_score_codex":0.000117710086,"about_ca_system_score_gemma":0.0002418462,"threshold_uncertainty_score":0.267865},"labels":[],"label_agreement":null},{"id":"W2899974865","doi":"10.1109/trpms.2018.2880617","title":"An Empirical Approach for Avoiding False Discoveries When Applying High-Dimensional Radiomics to Small Datasets","year":2018,"lang":"en","type":"article","venue":"IEEE Transactions on Radiation and Plasma Medical Sciences","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Terry Fox Research Institute","keywords":"Overfitting; Feature selection; Artificial intelligence; Radiomics; Logistic regression; Computer science; Support vector machine; Feature (linguistics); Machine learning; Receiver operating characteristic; Pattern recognition (psychology)","score_opus":0.039910371036795955,"score_gpt":0.3378253655991552,"score_spread":0.29791499456235926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2899974865","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40074357,0.000017150502,0.59255797,0.0057570618,0.00038531978,0.00036473988,0.00006664346,0.000050175124,0.00005738072],"genre_scores_gemma":[0.9402468,0.000032637807,0.05465819,0.0043798164,0.00041142743,0.00008511251,0.00011063858,0.000014775152,0.000060558275],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99806905,0.000110080604,0.00029739068,0.00052803016,0.0006540946,0.00034133947],"domain_scores_gemma":[0.9985178,0.00045739659,0.00005946786,0.00016427987,0.000035330973,0.0007656963],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015118679,0.00016732948,0.00026518703,0.0002298291,0.00095135154,0.000119534336,0.000188962,0.00012791206,0.00015294917],"category_scores_gemma":[0.00029534908,0.0001271557,0.000055851706,0.00029331035,0.0006222657,0.00020757249,0.000003528602,0.00037520655,0.000008610921],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008232918,0.00091103284,0.0024374155,0.00013296932,0.00012416861,0.000018904853,0.0026866202,0.013293802,0.0029752476,0.0013029773,0.007586543,0.96770704],"study_design_scores_gemma":[0.0017389893,0.0013924944,0.0008724597,0.00007409602,0.00007960904,0.0001351095,0.00024530358,0.9816189,0.0028683573,0.00026971183,0.010447464,0.00025750097],"about_ca_topic_score_codex":0.00012037963,"about_ca_topic_score_gemma":0.00004223847,"teacher_disagreement_score":0.9683251,"about_ca_system_score_codex":0.00004912067,"about_ca_system_score_gemma":0.00022505841,"threshold_uncertainty_score":0.7317123},"labels":[],"label_agreement":null},{"id":"W2900201919","doi":"10.1016/j.jpurol.2018.10.025","title":"Authors’ reply to commentary JPUROL-D-18-00309 refers to JPUROL_2018_56","year":2018,"lang":"en","type":"letter","venue":"Journal of Pediatric Urology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hospital for Sick Children","funders":"","keywords":"Medicine; Critical appraisal; Systematic review; Publication bias; Quality of evidence; Quality (philosophy); MEDLINE; Meta-analysis; Alternative medicine; Intensive care medicine; Epistemology; Pathology","score_opus":0.022742331450526898,"score_gpt":0.31850914215534565,"score_spread":0.29576681070481875,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2900201919","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012423339,0.00060591166,0.0020578217,0.97689474,0.006225008,0.00045013175,0.00002009374,0.00004992184,0.0012730387],"genre_scores_gemma":[0.00095242535,0.0002738788,0.0072344053,0.905115,0.084702455,0.0000092971095,0.000050129634,0.00014292054,0.0015194984],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9953026,0.00045014496,0.00155154,0.0006301214,0.0011133419,0.00095221517],"domain_scores_gemma":[0.99607295,0.0005105734,0.0010983816,0.0007463739,0.00058366964,0.0009880384],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.002004277,0.00053650053,0.0014273509,0.001770242,0.00013079915,0.000053726373,0.000831617,0.0009047738,0.0008951537],"category_scores_gemma":[0.0024746172,0.00044173066,0.000477034,0.0006181646,0.00013228004,0.00008249314,0.00027731797,0.006523339,0.0003904735],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00050482433,0.00010454772,0.0020274739,0.000067359586,0.00040384554,0.004580248,0.00024118465,0.000014135694,0.000052558975,0.0000014261532,0.9904371,0.001565284],"study_design_scores_gemma":[0.0017352569,0.0051887804,0.0011723404,0.0000237439,0.0020022057,0.0028483246,0.000012518744,0.00005331478,0.0000043069367,0.000116688694,0.9864866,0.0003559222],"about_ca_topic_score_codex":0.00007714811,"about_ca_topic_score_gemma":0.0000014025219,"teacher_disagreement_score":0.07847744,"about_ca_system_score_codex":0.00024512535,"about_ca_system_score_gemma":0.000427622,"threshold_uncertainty_score":0.9998034},"labels":[],"label_agreement":null},{"id":"W2900695129","doi":"10.1109/trpms.2018.2878934","title":"Comparison of Radiomics Models Built Through Machine Learning in a Multicentric Context With Independent Testing: Identical Data, Similar Algorithms, Different Methodologies","year":2018,"lang":"en","type":"article","venue":"IEEE Transactions on Radiation and Plasma Medical Sciences","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre; McGill University","funders":"","keywords":"Radiomics; Random forest; Computer science; Machine learning; Robustness (evolution); Artificial intelligence; Classifier (UML); Feature selection; Context (archaeology); Data mining; Algorithm","score_opus":0.18208914293103123,"score_gpt":0.41214245495422824,"score_spread":0.230053312023197,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2900695129","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46763992,0.00024670555,0.5285863,0.0029638805,0.00019010136,0.00020669021,0.0000097109105,0.00004643656,0.000110206274],"genre_scores_gemma":[0.972522,0.00041923564,0.026609512,0.0003292774,0.00006528562,0.0000075731805,0.000012036586,0.000010777887,0.000024305542],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99739033,0.0002881865,0.000540708,0.0004774806,0.0009937806,0.00030950474],"domain_scores_gemma":[0.99758434,0.0017314785,0.00017664995,0.00018831185,0.00006043672,0.00025877813],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015784773,0.0001830817,0.00050002313,0.00024604276,0.00028976786,0.000045908248,0.00028259755,0.00014108284,0.00009937012],"category_scores_gemma":[0.0009928434,0.00012380905,0.000035347322,0.0005728039,0.0011671245,0.0002461071,0.000010759263,0.00081889186,0.0000022367406],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00051836186,0.0010582419,0.08650873,0.0001465088,0.0001514609,0.00005975289,0.0035904443,0.04707538,0.00040224192,0.00045338387,0.00009818479,0.8599373],"study_design_scores_gemma":[0.0022894163,0.0009915476,0.0047979797,0.00018085579,0.0000881216,0.000088310095,0.0006416859,0.9889036,0.0015051123,0.00014530166,0.00023326215,0.00013484976],"about_ca_topic_score_codex":0.00056657713,"about_ca_topic_score_gemma":0.00029638194,"teacher_disagreement_score":0.9418282,"about_ca_system_score_codex":0.000051576637,"about_ca_system_score_gemma":0.00020831407,"threshold_uncertainty_score":0.50487864},"labels":[],"label_agreement":null},{"id":"W2900949351","doi":"10.1259/bjr.20180228","title":"The use of texture-based radiomics CT analysis to predict outcomes in early-stage non-small cell lung cancer treated with stereotactic ablative radiotherapy","year":2018,"lang":"en","type":"article","venue":"British Journal of Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":51,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre","funders":"National Cancer Institute; National Institutes of Health; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Radiomics; Ablative case; Medicine; Stage (stratigraphy); Radiology; Radiation therapy; Lung cancer; SABR volatility model; Radiosurgery; Lung; Oncology; Internal medicine","score_opus":0.012084234283090535,"score_gpt":0.28429637633334315,"score_spread":0.2722121420502526,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2900949351","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97929686,0.0015271077,0.01757236,0.0009755816,0.00016090271,0.00039196288,0.000024868814,0.000009575546,0.000040766205],"genre_scores_gemma":[0.9917951,0.0011224028,0.005509273,0.00089298596,0.00018538524,0.000010826589,0.0000053580275,0.00003924658,0.0004394008],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99797547,0.00033046244,0.0007618,0.00025235038,0.00027913114,0.00040081222],"domain_scores_gemma":[0.9978056,0.00071858935,0.00063976913,0.00025593105,0.000324684,0.00025546027],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007015638,0.00020857475,0.0010826286,0.00051133416,0.000106642634,0.00006287928,0.0002615891,0.00008347637,0.00005447209],"category_scores_gemma":[0.00036370987,0.00014530796,0.00025776797,0.0007481824,0.00039521977,0.00010175961,0.000017433487,0.00070720236,3.8068632e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010962279,0.00013884572,0.97838235,0.000028521461,0.002427241,0.0013085973,0.00048055672,0.009563022,0.00072263123,0.0000022444149,0.0010759524,0.004773785],"study_design_scores_gemma":[0.006468371,0.0018071353,0.91938543,0.00034742794,0.0012807345,0.0028895598,0.00006816167,0.06533604,0.000436909,0.0000017690222,0.0017859589,0.00019250663],"about_ca_topic_score_codex":0.0026785366,"about_ca_topic_score_gemma":0.00071118964,"teacher_disagreement_score":0.058996953,"about_ca_system_score_codex":0.00023003852,"about_ca_system_score_gemma":0.00026666812,"threshold_uncertainty_score":0.59254867},"labels":[],"label_agreement":null},{"id":"W2901051058","doi":"10.1080/09553002.2019.1589013","title":"Proliferation saturation index in an adaptive Bayesian approach to predict patient-specific radiotherapy responses","year":2019,"lang":"en","type":"article","venue":"International Journal of Radiation Biology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"London Health Sciences Centre","funders":"National Cancer Institute; National Institutes of Health; Moffitt Cancer Center","keywords":"Radiation therapy; Bayesian probability; Computer science; Identifiability; Medicine; Statistics; Nuclear medicine; Medical physics; Mathematics; Artificial intelligence; Radiology; Machine learning","score_opus":0.011483801246208595,"score_gpt":0.3030673586487815,"score_spread":0.2915835574025729,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2901051058","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90261704,0.00024651844,0.092270024,0.0031178733,0.0010146486,0.00035045878,0.0000058933206,0.000012525304,0.00036504524],"genre_scores_gemma":[0.9896598,0.00013127325,0.007995483,0.0013949,0.00068374595,0.000008063621,0.00007076701,0.0000142915915,0.00004170771],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9985985,0.00023363033,0.0005255964,0.00018795769,0.0003230043,0.00013126864],"domain_scores_gemma":[0.9990355,0.000097251585,0.00031848208,0.00011020002,0.00031290334,0.00012568453],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005108171,0.00010587553,0.00023922593,0.0006887667,0.00002011002,0.000039151986,0.00016406516,0.000106125226,0.000059346487],"category_scores_gemma":[0.00022605632,0.000087403416,0.00006340156,0.00015579835,0.00003144021,0.0002715727,0.000012550204,0.0003436594,0.000005288618],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0064141285,0.0004409625,0.6812484,0.0000069141142,0.00015018864,0.000026004853,0.0022184046,0.009970147,0.031928927,0.0030491871,0.0006916615,0.263855],"study_design_scores_gemma":[0.007017558,0.004536356,0.71235174,0.0001457252,0.000019522946,0.00079877424,0.0004889764,0.24171261,0.0014016045,0.0005616287,0.030693734,0.00027176348],"about_ca_topic_score_codex":0.000010504981,"about_ca_topic_score_gemma":0.0000016253321,"teacher_disagreement_score":0.26358327,"about_ca_system_score_codex":0.00029495548,"about_ca_system_score_gemma":0.00014781904,"threshold_uncertainty_score":0.3564208},"labels":[],"label_agreement":null},{"id":"W2902029463","doi":"10.1016/s0140-6736(18)32170-6","title":"Artificial intelligence can augment global pathology initiatives – Authors' reply","year":2018,"lang":"en","type":"letter","venue":"The Lancet","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Augment; Computer science; Medicine","score_opus":0.04965424481006546,"score_gpt":0.3508445497220379,"score_spread":0.3011903049119724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2902029463","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0032838946,0.00022874169,0.0028523717,0.9812283,0.0016766363,0.0003125759,0.00008827743,0.00013272022,0.010196519],"genre_scores_gemma":[0.015403977,0.0001335614,0.0019376356,0.9411652,0.040124897,0.000031474094,0.00026734275,0.0000438738,0.0008920526],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977312,0.00033892583,0.00042452436,0.00047577318,0.00042463784,0.0006049163],"domain_scores_gemma":[0.99847835,0.00018499247,0.00023447801,0.0009190745,0.00008802558,0.0000950929],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.00093830377,0.00028941038,0.0008053713,0.000053912554,0.00015484447,0.000059246147,0.000527868,0.00034159515,0.00030892878],"category_scores_gemma":[0.00094354956,0.00018416609,0.00013583445,0.00017509771,0.0006720271,0.000023576777,0.00015500898,0.0026544132,0.00016611138],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000074519536,0.000019524658,0.00075024925,0.000103220365,0.000099012395,0.0012336583,0.00046807303,0.000002631366,0.000018338364,0.0010447357,0.98151976,0.014666308],"study_design_scores_gemma":[0.00016950023,0.00021661505,0.0020760389,0.00029336533,0.00020199736,0.00062952976,0.00006164626,0.0007750361,0.000068169364,0.017764313,0.97749126,0.00025250443],"about_ca_topic_score_codex":0.000108609616,"about_ca_topic_score_gemma":0.000009960953,"teacher_disagreement_score":0.04006308,"about_ca_system_score_codex":0.00014866974,"about_ca_system_score_gemma":0.00017485974,"threshold_uncertainty_score":0.9996465},"labels":[],"label_agreement":null},{"id":"W2902154261","doi":"10.1038/s41467-018-07619-7","title":"Why rankings of biomedical image analysis competitions should be interpreted with care","year":2018,"lang":"en","type":"article","venue":"Nature Communications","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":367,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"National Institute of Neurological Disorders and Stroke; Engineering and Physical Sciences Research Council; Medical Research Council; Ministry of Science and Technology, Taiwan; National Institute of Biomedical Imaging and Bioengineering; Grantová Agentura České Republiky; Deutsches Krebsforschungszentrum; Deutsche Forschungsgemeinschaft; Australian Research Council; Wellcome Trust; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Institutes of Health; National Science Foundation","keywords":"Ranking (information retrieval); Computer science; Rank (graph theory); Data science; Quality (philosophy); Information retrieval; Image (mathematics); Data mining; Artificial intelligence; Mathematics","score_opus":0.013589213883681997,"score_gpt":0.3453327389953813,"score_spread":0.3317435251116993,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2902154261","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30166465,0.011002501,0.13294886,0.4631781,0.00057937595,0.0016365016,0.0004329199,0.0007871509,0.08776993],"genre_scores_gemma":[0.92284393,0.000111686306,0.07021758,0.005962081,0.000074678304,0.000014371699,0.0007206883,0.000018810033,0.00003617159],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989167,0.00010144686,0.00027372068,0.0001924385,0.0003532042,0.00016249395],"domain_scores_gemma":[0.99738324,0.00023192451,0.00012592187,0.0014746638,0.0006365927,0.00014765123],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019514715,0.00012347272,0.00034847128,0.00042099893,0.00023121217,0.00002123314,0.0005924577,0.00018826868,0.00022873959],"category_scores_gemma":[0.00041978434,0.00009403636,0.00015490371,0.0014413261,0.0014623968,0.000058011756,0.00019507327,0.0013075541,0.0000041542053],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015743788,0.0051994673,0.35924911,0.0010267436,0.02293464,0.0001246649,0.067104675,0.0000465247,0.11834109,0.07568961,0.31920233,0.029506745],"study_design_scores_gemma":[0.0037656156,0.0010318593,0.06303222,0.0008407474,0.0066727977,0.00013704768,0.0040847776,0.042778086,0.0020127844,0.00015632837,0.8749477,0.0005400165],"about_ca_topic_score_codex":0.00015338071,"about_ca_topic_score_gemma":0.00042600613,"teacher_disagreement_score":0.6211793,"about_ca_system_score_codex":0.000052046584,"about_ca_system_score_gemma":0.00009537689,"threshold_uncertainty_score":0.56807446},"labels":[],"label_agreement":null},{"id":"W2902771920","doi":"10.5539/cco.v7n2p33","title":"Preoperative Staging in Women with Known Breast Cancer: Comparison between Digital Breast Tomosynthesis (DBT) and Magnetic Resonance Imaging (MRI)","year":2018,"lang":"en","type":"article","venue":"Cancer and Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"McNemar's test; Medicine; Breast cancer; Magnetic resonance imaging; Radiology; Gold standard (test); Nuclear medicine; Breast MRI; Mammography; Histology; Prospective cohort study; Cancer; Pathology; Internal medicine","score_opus":0.018302643501896868,"score_gpt":0.3752620608404163,"score_spread":0.35695941733851944,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2902771920","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9776763,0.004235103,0.00012459522,0.015937544,0.00016124416,0.0002699944,0.00009840514,0.000037079775,0.0014597359],"genre_scores_gemma":[0.9949167,0.0016247879,0.00036985462,0.0018313733,0.0009373006,0.00005741815,0.000005213361,0.000029882134,0.00022747634],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99807453,0.000122010206,0.0005839648,0.000569017,0.00016937328,0.00048113018],"domain_scores_gemma":[0.99853724,0.00061318494,0.00014434198,0.0001681712,0.00011926534,0.00041776593],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000572053,0.00021230691,0.00088452786,0.000079739766,0.0001138681,0.00006066156,0.0001040709,0.00011886957,0.0001830506],"category_scores_gemma":[0.00013290485,0.00015883651,0.000033740722,0.00018820364,0.0012473237,0.00015223518,0.00010997264,0.00070316886,0.0000035352596],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00058226543,0.000072627816,0.5106577,0.00001801515,0.000025871792,0.000024982635,0.0004979899,0.0000011857625,0.0000070599895,0.000006381596,0.0002455819,0.48786035],"study_design_scores_gemma":[0.0039660363,0.0010899263,0.969331,0.0004913694,0.00011844452,0.00013538843,0.00058025116,0.0049531567,0.000005856451,0.000043290005,0.019079685,0.00020556452],"about_ca_topic_score_codex":0.0006156328,"about_ca_topic_score_gemma":0.00020492995,"teacher_disagreement_score":0.48765478,"about_ca_system_score_codex":0.0002780928,"about_ca_system_score_gemma":0.00044349293,"threshold_uncertainty_score":0.6477165},"labels":[],"label_agreement":null},{"id":"W2903506287","doi":"10.1200/jco.2018.36.34_suppl.208","title":"FIT: Functional and imaging testing for patients with metastatic cancer.","year":2018,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Medicine; Cancer; Cachexia; Internal medicine; Clinical endpoint; Malignancy; Response Evaluation Criteria in Solid Tumors; Anorexia; Performance status; Clinical trial; Physical therapy; Oncology; Phases of clinical research","score_opus":0.1216903745679661,"score_gpt":0.4797659609511657,"score_spread":0.3580755863831996,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2903506287","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98024905,0.00020030724,0.0070419475,0.010641517,0.0010677696,0.00015442798,0.0000022516454,0.0000072242756,0.0006355322],"genre_scores_gemma":[0.92244726,0.000027262351,0.07114862,0.004340257,0.0019304941,0.0000034986933,0.0000014719666,0.000014378498,0.0000867517],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99857885,0.00008288679,0.00084548525,0.00012411913,0.00021447764,0.00015416635],"domain_scores_gemma":[0.99541116,0.0026163547,0.0008112367,0.00005757108,0.0008468089,0.0002568586],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0017875931,0.000076187695,0.0006099887,0.00006481666,0.00007117154,0.000009754383,0.000048269474,0.000044494707,0.00005159577],"category_scores_gemma":[0.01004126,0.00004643548,0.000089425586,0.00007440792,0.00033105488,0.000076551,0.000020519681,0.00049276196,0.0000011781468],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012403968,0.00026762177,0.60785884,0.000023275921,0.00013016765,0.000026693584,0.000022843815,0.0000078583735,0.000022733304,0.00002494935,0.0028697334,0.3875049],"study_design_scores_gemma":[0.012072301,0.011443995,0.9202518,0.00020328298,0.00053261995,0.00024370762,0.000033956912,0.009921742,0.0000040338473,0.0003888088,0.044830665,0.000073107854],"about_ca_topic_score_codex":0.000012157909,"about_ca_topic_score_gemma":0.0000037161321,"teacher_disagreement_score":0.3874318,"about_ca_system_score_codex":0.000044932116,"about_ca_system_score_gemma":0.00067888957,"threshold_uncertainty_score":0.9982976},"labels":[],"label_agreement":null},{"id":"W2904291170","doi":"10.3389/fonc.2018.00630","title":"Predicting Gleason Score of Prostate Cancer Patients Using Radiomic Analysis","year":2018,"lang":"en","type":"article","venue":"Frontiers in Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":93,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; École de Technologie Supérieure","funders":"","keywords":"Prostate cancer; Spearman's rank correlation coefficient; Receiver operating characteristic; Medicine; Effective diffusion coefficient; Correlation; Magnetic resonance imaging; Rank correlation; Prostate; Pearson product-moment correlation coefficient; Imaging biomarker; Diffusion MRI; Nuclear medicine; Radiology; Cancer; Mathematics; Statistics; Internal medicine","score_opus":0.012029283628677941,"score_gpt":0.32418906914838513,"score_spread":0.3121597855197072,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2904291170","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9922938,0.00057779654,0.0045054797,0.00031294415,0.0013355206,0.00028525255,0.000007681754,0.000021028953,0.0006605429],"genre_scores_gemma":[0.9723117,0.00013716609,0.026836928,0.00030623202,0.0002593101,0.000011099835,0.000021506303,0.000020094149,0.000096004995],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99870855,0.000101318146,0.00040881053,0.0002756419,0.00019689299,0.0003088115],"domain_scores_gemma":[0.9992867,0.00004124086,0.00025023802,0.00017097476,0.00013827307,0.00011256923],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037552154,0.000118264004,0.0006258994,0.0005464689,0.00005505326,0.000005192987,0.000107894564,0.00012373735,0.000059738086],"category_scores_gemma":[0.00035579258,0.00010668893,0.00010425204,0.00080299657,0.0003406545,0.000052947995,0.000048285045,0.00031596373,9.47118e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025215713,0.00014537026,0.9572565,0.00004722875,0.0003669879,0.000014632639,0.0010279769,0.00040009996,0.0008455628,0.000003592778,0.0014732452,0.038166642],"study_design_scores_gemma":[0.003467635,0.0007563987,0.53974444,0.0002169984,0.001053374,0.000008162876,0.00027480075,0.4500779,0.00044919312,0.000069304275,0.0037385726,0.00014319882],"about_ca_topic_score_codex":0.00076492893,"about_ca_topic_score_gemma":0.000056606506,"teacher_disagreement_score":0.4496778,"about_ca_system_score_codex":0.00047958037,"about_ca_system_score_gemma":0.00024457477,"threshold_uncertainty_score":0.43506482},"labels":[],"label_agreement":null},{"id":"W2904682614","doi":"10.1053/j.semnuclmed.2018.11.008","title":"Reporting Guidelines for Imaging Research","year":2018,"lang":"en","type":"review","venue":"Seminars in Nuclear Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Sunnybrook Health Science Centre; Juravinski Hospital; McMaster University; Hamilton Health Sciences; University of Toronto; Health Sciences Centre; Ottawa Hospital","funders":"","keywords":"Generalizability theory; Medicine; Transparency (behavior); Dissemination; Quality (philosophy); Research design; Variety (cybernetics); Information Dissemination; External validity; Management science; Medical physics; Data science; Computer science; World Wide Web","score_opus":0.28176403341008815,"score_gpt":0.5535519517915589,"score_spread":0.27178791838147076,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2904682614","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000018379702,0.97782093,0.000075351396,0.011193849,0.0011094445,0.0017348045,0.000004607981,0.00012700784,0.007915594],"genre_scores_gemma":[0.0000051927864,0.9760596,0.013874069,0.0016423373,0.0054626153,0.000107614,0.00014164325,0.00030310857,0.0024038225],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9924049,0.00027752775,0.004157443,0.0010794698,0.0010604452,0.0010202064],"domain_scores_gemma":[0.99444425,0.0012223405,0.0018028766,0.0010114047,0.0011193583,0.0003997877],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.01820789,0.0005416088,0.003454868,0.0013777595,0.00025403305,0.000036809375,0.00050283613,0.00037107212,0.00028869306],"category_scores_gemma":[0.080031104,0.0003861816,0.00048771215,0.0011151163,0.0009876619,0.00006237464,0.00026588843,0.0023163036,0.000076477234],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020583451,0.00003112117,0.00003814541,0.011621227,0.000047225214,0.00036486794,0.00020565059,1.155312e-7,0.000004567284,0.000095232936,0.31716347,0.6704078],"study_design_scores_gemma":[0.0007482325,0.00026692764,0.000004842782,0.17205091,0.00044076995,0.0012835533,0.00035005264,0.0014867724,1.9758244e-7,0.00023799062,0.82287484,0.00025490948],"about_ca_topic_score_codex":0.00011217814,"about_ca_topic_score_gemma":0.000002396303,"teacher_disagreement_score":0.6701529,"about_ca_system_score_codex":0.0004400191,"about_ca_system_score_gemma":0.00048138393,"threshold_uncertainty_score":0.9999854},"labels":[],"label_agreement":null},{"id":"W2905109465","doi":"10.1053/j.semnuclmed.2018.11.010","title":"Emergence of “Big Data” and Its Potential and Current Limitations in Medical Imaging","year":2018,"lang":"en","type":"review","venue":"Seminars in Nuclear Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":22,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Health Science Centre; University of Toronto; Health Sciences Centre","funders":"Ontario Institute for Cancer Research","keywords":"Medicine; Medical imaging; Digital imaging; Fluoroscopy; Pixel; Imaging technology; Multislice; Artificial intelligence; Medical physics; Image resolution; Computer vision; Digital image; Computer science; Data science; Image processing; Nuclear medicine; Radiology; Image (mathematics)","score_opus":0.08514710329052959,"score_gpt":0.39143606024922034,"score_spread":0.30628895695869074,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2905109465","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004382675,0.99429566,0.00003415582,0.0026349253,0.0010141619,0.00045608837,0.000015032218,0.000020544845,0.0010911877],"genre_scores_gemma":[0.0021258988,0.99625593,0.00028967147,0.00019811564,0.0008587459,0.000007836519,0.00014805715,0.0000667061,0.000049030386],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9969772,0.00018922711,0.0011081574,0.00068946223,0.0006881932,0.00034775038],"domain_scores_gemma":[0.998388,0.0003631918,0.0003168995,0.0005086811,0.00006651513,0.00035671974],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0019530328,0.0003372114,0.0016763129,0.0006638835,0.00004684115,0.000008080699,0.00040598155,0.00019944643,0.0002212388],"category_scores_gemma":[0.0047223,0.00025989168,0.000061961386,0.00052336295,0.00074071967,0.00007544327,0.00053354,0.001367437,0.0000069378093],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001433118,0.00007754195,0.00022451892,0.009709127,0.0000301704,0.0002673492,0.00049328397,7.8743284e-8,0.0000034231693,0.00007020921,0.00818816,0.9809218],"study_design_scores_gemma":[0.0011541182,0.0001239666,0.00020519583,0.109027185,0.00048082374,0.0008549115,0.0004304184,0.018467985,6.762077e-8,0.00006661808,0.8689724,0.0002163163],"about_ca_topic_score_codex":0.000043980683,"about_ca_topic_score_gemma":0.00001321407,"teacher_disagreement_score":0.9807055,"about_ca_system_score_codex":0.00003200924,"about_ca_system_score_gemma":0.00023145654,"threshold_uncertainty_score":0.99998534},"labels":[],"label_agreement":null},{"id":"W2906448356","doi":"10.3174/ajnr.a5918","title":"Radiomics-Based Intracranial Thrombus Features on CT and CTA Predict Recanalization with Intravenous Alteplase in Patients with Acute Ischemic Stroke","year":2018,"lang":"en","type":"article","venue":"American Journal of Neuroradiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":101,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary; Ontario Brain Institute; McMaster University","funders":"Bayer Canada; Canadian Institutes of Health Research; Alberta Innovates; Stryker; University of Calgary","keywords":"Medicine; Thrombus; Radiology; Receiver operating characteristic; Radiomics; Thrombolysis; Angiography; Internal medicine; Myocardial infarction","score_opus":0.003473966795321625,"score_gpt":0.23748064929532742,"score_spread":0.23400668250000578,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2906448356","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9960643,0.000025896576,0.0015530613,0.0018916996,0.00015178647,0.00017663414,0.00000847493,0.00001282847,0.000115340474],"genre_scores_gemma":[0.9931976,0.000065613305,0.0039942404,0.0024157185,0.00026449555,0.000001419465,0.000014612707,0.000036825342,0.000009478403],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9986603,0.00017662317,0.00034813996,0.00025816407,0.00026866506,0.00028805385],"domain_scores_gemma":[0.9988091,0.000164143,0.00046817306,0.00017514227,0.00015307819,0.00023034138],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021402132,0.00019816458,0.00062226097,0.00032915434,0.000056753903,0.000016861986,0.00012507805,0.00002964105,0.000011371232],"category_scores_gemma":[0.00019200008,0.00013094071,0.000038523678,0.00027322982,0.00094211084,0.00006664562,0.0000121943385,0.00073529646,6.8359935e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.018723208,0.0005449162,0.89472824,0.000030422541,0.00052365696,0.0030823955,0.0003934369,0.00086567126,0.0032968423,0.000024386272,0.0015356397,0.076251164],"study_design_scores_gemma":[0.01216768,0.055199448,0.91542894,0.00031029462,0.0004138953,0.010064052,0.000085328335,0.004619194,0.00049970165,0.000009911942,0.00094022875,0.00026131858],"about_ca_topic_score_codex":0.000052475916,"about_ca_topic_score_gemma":0.0000109134135,"teacher_disagreement_score":0.07598984,"about_ca_system_score_codex":0.000075934346,"about_ca_system_score_gemma":0.00022596875,"threshold_uncertainty_score":0.5339607},"labels":[],"label_agreement":null},{"id":"W2906720145","doi":"10.1109/ultsym.2018.8580090","title":"Predicting Radiotherapy Response in Head and Neck Patients Using Quantitative Ultrasound","year":2018,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Health Science Centre","funders":"","keywords":"Radiation therapy; Medicine; Head and neck cancer; Magnetic resonance imaging; Ultrasound; Lymph; Radiology; Head and neck; Nuclear medicine; Surgery; Pathology","score_opus":0.02099950571520235,"score_gpt":0.35087298612492507,"score_spread":0.3298734804097227,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2906720145","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99524355,0.00014519595,0.002881227,0.00057257083,0.00012760086,0.00019604836,0.0000011127282,0.000037887337,0.00079480914],"genre_scores_gemma":[0.9563853,0.00003307075,0.04220735,0.0011080037,0.00010530795,0.0000017738225,0.000002983358,0.000020673491,0.00013551788],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9990723,0.000115586045,0.00021267499,0.0002185423,0.00016659992,0.00021428848],"domain_scores_gemma":[0.9992872,0.00035993493,0.000051774914,0.00011770125,0.00006500872,0.00011837546],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005645358,0.00010209376,0.00020209231,0.00014409637,0.000084307074,0.000025084493,0.000038214675,0.00004929543,0.00007428155],"category_scores_gemma":[0.0014631024,0.00008287634,0.00002338076,0.00017745106,0.00019541135,0.000085734944,0.000016426282,0.0002193088,0.0000030060714],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016327035,0.0000861235,0.97828484,0.00001611139,0.000023188031,0.000011669481,0.002017849,0.000012408951,0.01547587,0.000087654706,0.00008516293,0.0022663937],"study_design_scores_gemma":[0.0039048798,0.0013295752,0.8908999,0.0002475855,0.000015652291,0.00005609121,0.00027992422,0.101806514,0.00028199912,0.000059199992,0.0010038947,0.00011480189],"about_ca_topic_score_codex":0.00032910434,"about_ca_topic_score_gemma":0.000017681328,"teacher_disagreement_score":0.1017941,"about_ca_system_score_codex":0.00007754211,"about_ca_system_score_gemma":0.000052289033,"threshold_uncertainty_score":0.3379599},"labels":[],"label_agreement":null},{"id":"W2908507660","doi":"10.1200/jco.2014.32.15_suppl.6611","title":"The impact of PET-CT on staging, management, and prognostication of small-cell lung cancer.","year":2014,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre","funders":"","keywords":"Medicine; Radiology; PET-CT; Cancer staging; Nuclear medicine; Positron emission tomography; Cancer; Internal medicine","score_opus":0.04262662154480008,"score_gpt":0.47041617589763496,"score_spread":0.4277895543528349,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2908507660","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9863895,0.00050001155,0.0009328057,0.0045391745,0.0003242285,0.00015892703,7.2230466e-7,0.000002902771,0.0071516987],"genre_scores_gemma":[0.9939334,0.0026314557,0.0025829084,0.00033509068,0.00028329136,0.0000017310844,5.7060396e-7,0.000009169049,0.00022240933],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9981335,0.00028547613,0.0011531628,0.00009595876,0.00020160437,0.00013034049],"domain_scores_gemma":[0.99530846,0.0026575148,0.0015461592,0.0001388417,0.00017833474,0.00017066576],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037763054,0.00007482636,0.0006372945,0.0000701616,0.000033278717,0.0000054082648,0.00013019648,0.000030655705,0.000016034088],"category_scores_gemma":[0.0033525382,0.000039885846,0.00021636357,0.00006770076,0.00023857811,0.00002217548,0.000035521738,0.0006317381,4.4227895e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009890548,0.00066636095,0.6202326,0.0001700695,0.0004485685,0.00008945828,0.000051383442,0.00025907782,0.00016714592,0.00068090763,0.004529126,0.3717163],"study_design_scores_gemma":[0.006373739,0.009274981,0.9393463,0.00043724457,0.0006776255,0.00016773853,0.00006841078,0.03202226,0.00007728146,0.0006720867,0.010813059,0.00006928231],"about_ca_topic_score_codex":0.000051929204,"about_ca_topic_score_gemma":0.0000024431058,"teacher_disagreement_score":0.371647,"about_ca_system_score_codex":0.000048272308,"about_ca_system_score_gemma":0.00029364764,"threshold_uncertainty_score":0.40135434},"labels":[],"label_agreement":null},{"id":"W2909341957","doi":"10.3389/fnins.2018.01045","title":"Dual-Model Radiomic Biomarkers Predict Development of Mild Cognitive Impairment Progression to Alzheimer’s Disease","year":2019,"lang":"en","type":"article","venue":"Frontiers in Neuroscience","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":68,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute on Aging; National Key Research and Development Program of China; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; University of California, San Diego; National Institutes of Health; H. Lundbeck A/S; Servier; National Natural Science Foundation of China; Eisai; Genentech; IXICO; Fudan University; Northern California Institute for Research and Education; Pfizer; Biogen; BioClinica; F. Hoffmann-La Roche; University of Southern California; Eli Lilly and Company; U.S. Department of Defense; Meso Scale Diagnostics; Alzheimer's Disease Neuroimaging Initiative; Foundation for the National Institutes of Health; Science and Technology Commission of Shanghai Municipality; Novartis Pharmaceuticals Corporation; Bristol-Myers Squibb; Alzheimer's Association","keywords":"Magnetic resonance imaging; Positron emission tomography; Neuroimaging; Alzheimer's Disease Neuroimaging Initiative; Medicine; Multivariate statistics; Proportional hazards model; Cognitive impairment; Nuclear medicine; Disease; Internal medicine; Radiology; Computer science; Machine learning","score_opus":0.017097154883304013,"score_gpt":0.3092647617298288,"score_spread":0.2921676068465248,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2909341957","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9720419,0.00038747262,0.023908444,0.00092090043,0.001151438,0.0012686222,0.000008586915,0.00004051309,0.0002720954],"genre_scores_gemma":[0.94961876,0.00003070378,0.04908537,0.001051691,0.000021240263,0.00004606383,0.000008640608,0.000021006419,0.00011654765],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9980387,0.000049072467,0.00037419584,0.00054497476,0.00060024357,0.00039280902],"domain_scores_gemma":[0.99913305,0.00002798066,0.00011016429,0.00023112209,0.000044771292,0.00045291753],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00051321805,0.00016898946,0.00030377964,0.0003636344,0.00006846933,0.000017215503,0.00018868735,0.000038216458,0.000007455745],"category_scores_gemma":[0.0002618869,0.00014233221,0.000060531944,0.00050198555,0.00021169649,0.00010402959,0.0001304262,0.00021902555,0.000005741773],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014946223,0.00064998324,0.91334313,0.00019795254,0.000039951585,0.000114391645,0.0016492703,0.0020689762,0.023752183,0.000016575434,0.006605104,0.05006785],"study_design_scores_gemma":[0.002373104,0.0003408987,0.5104469,0.0010300028,0.000072001916,0.000012497511,0.00016823225,0.48046687,0.0040411586,0.00003112035,0.00077476824,0.00024243374],"about_ca_topic_score_codex":0.000003121275,"about_ca_topic_score_gemma":1.9154953e-7,"teacher_disagreement_score":0.4783979,"about_ca_system_score_codex":0.000092514434,"about_ca_system_score_gemma":0.00046800103,"threshold_uncertainty_score":0.58041394},"labels":[],"label_agreement":null},{"id":"W2909587126","doi":"10.1109/trpms.2019.2893860","title":"Creating Robust Predictive Radiomic Models for Data From Independent Institutions Using Normalization","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Radiation and Plasma Medical Sciences","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":50,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Terry Fox Research Institute","keywords":"Normalization (sociology); Standardization; Feature selection; Artificial intelligence; Computer science; Pattern recognition (psychology); Feature (linguistics); Data mining; Logistic regression; Outlier; Machine learning","score_opus":0.08403753685768459,"score_gpt":0.3391682313430357,"score_spread":0.2551306944853511,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2909587126","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3400244,0.00006106821,0.6573608,0.0010607811,0.00051910285,0.00034267805,0.000078982586,0.00004245399,0.0005097151],"genre_scores_gemma":[0.98840344,0.0002580066,0.010382723,0.0005663773,0.00015278319,0.000014954307,0.00013176541,0.000010766482,0.00007919518],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982536,0.00006165704,0.0003037883,0.00047565057,0.00067988096,0.00022541868],"domain_scores_gemma":[0.9989163,0.00044181003,0.00009934391,0.00020443878,0.000038359118,0.00029973203],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00080876413,0.00013083815,0.00022304784,0.00019317774,0.00050929445,0.00007805599,0.0002106261,0.00014064416,0.00030039137],"category_scores_gemma":[0.00016033418,0.0001080499,0.000046254772,0.00028861238,0.00025768712,0.00054343254,0.0000051026886,0.00032558502,0.000008005579],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002223,0.00022331388,0.002758938,0.000060061222,0.000119252436,0.000007186177,0.00063024287,0.93331057,0.00055339746,0.0011457258,0.00018036869,0.06078864],"study_design_scores_gemma":[0.0017129323,0.00021877566,0.0004311544,0.0001510125,0.0001066336,0.000055317098,0.00016695469,0.9960631,0.00022561861,0.0001604927,0.0005923493,0.00011563252],"about_ca_topic_score_codex":0.0004656435,"about_ca_topic_score_gemma":0.000046533572,"teacher_disagreement_score":0.648379,"about_ca_system_score_codex":0.000082686514,"about_ca_system_score_gemma":0.0005190839,"threshold_uncertainty_score":0.4406147},"labels":[],"label_agreement":null},{"id":"W2909847169","doi":"10.21037/jmai.2019.01.01","title":"Promises and limitations of deep learning for medical image segmentation","year":2019,"lang":"en","type":"article","venue":"Journal of Medical Artificial Intelligence","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":45,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Artificial intelligence; Deep learning; Computer vision; Segmentation; Image (mathematics); Computer science","score_opus":0.043449062245623435,"score_gpt":0.36256073053461263,"score_spread":0.3191116682889892,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2909847169","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.58381057,0.000516384,0.39611408,0.018375589,0.00047514564,0.00030081332,4.918653e-7,0.000012301445,0.00039465664],"genre_scores_gemma":[0.9815713,0.0012704509,0.016209137,0.00047108968,0.0003967542,0.000004480082,0.0000043138625,0.000016036322,0.000056438013],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973783,0.00008200524,0.00089250255,0.00013836562,0.0013324188,0.0001764131],"domain_scores_gemma":[0.9971366,0.001628051,0.00038532488,0.00007666478,0.0003500252,0.00042331743],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0024094454,0.00009868558,0.0003879659,0.00015153563,0.000053590382,0.000024416742,0.00016993945,0.00013638465,0.00052844494],"category_scores_gemma":[0.018544067,0.00007399959,0.00012717405,0.00014455487,0.0002600372,0.00011666428,0.00004044278,0.0007045718,0.000009816397],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030096833,0.00023530854,0.0026913271,0.00025190116,0.00008520801,0.00005150995,0.0009134556,0.0001259567,0.012037587,0.0034931193,0.0001157906,0.9796979],"study_design_scores_gemma":[0.0020072,0.004531862,0.003989395,0.002434116,0.00044123968,0.0017213312,0.00726337,0.9093662,0.045248512,0.01281531,0.009807581,0.00037388387],"about_ca_topic_score_codex":0.00000878825,"about_ca_topic_score_gemma":0.0000048364063,"teacher_disagreement_score":0.979324,"about_ca_system_score_codex":0.00002623638,"about_ca_system_score_gemma":0.0002618643,"threshold_uncertainty_score":0.98972315},"labels":[],"label_agreement":null},{"id":"W2911605224","doi":"10.3322/caac.21552","title":"Artificial intelligence in cancer imaging: Clinical challenges and applications","year":2019,"lang":"en","type":"review","venue":"CA A Cancer Journal for Clinicians","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1829,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Medical Research Council; Natural Sciences and Engineering Research Council of Canada; Novo Nordisk Fonden; National Institute for Health and Care Research; National Institute of Biomedical Imaging and Bioengineering; Wellcome Trust; Francis Crick Institute; National Cancer Institute; National Institutes of Health; Cancer Research UK; AstraZeneca","keywords":"Medicine; Context (archaeology); Workflow; Generalizability theory; Medical physics; Precision medicine; Disease; Medical imaging; Artificial intelligence; Pathology; Radiology; Computer science; Psychology","score_opus":0.2566280228861588,"score_gpt":0.5461063273453626,"score_spread":0.28947830445920375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2911605224","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000008380654,0.98805386,0.0030426267,0.0043137297,0.0025521195,0.0016443171,0.00005628794,0.00002194239,0.0003067156],"genre_scores_gemma":[0.000023457342,0.9920671,0.0005671325,0.0009100846,0.005313571,0.0006508358,0.000019870879,0.000106213774,0.00034171145],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9962692,0.00019170478,0.0021222318,0.000665656,0.00025528757,0.0004958675],"domain_scores_gemma":[0.9968987,0.0012603696,0.00092819124,0.00034959815,0.00018035977,0.00038277084],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0022397945,0.000395377,0.0024670092,0.00034147134,0.00013014386,0.00006442105,0.00030573204,0.0003534732,0.000077296834],"category_scores_gemma":[0.00066724786,0.00031083875,0.0008260156,0.00020487132,0.00020461188,0.00007201108,0.00006764879,0.0027647996,0.00001987885],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000036974805,0.00012629486,0.00022549235,0.0071043866,0.00020227405,0.00003117471,0.00009240042,0.000007553057,9.269897e-8,0.00042775887,0.00086438836,0.9908812],"study_design_scores_gemma":[0.00028560797,0.00013431662,0.000058726022,0.017656656,0.001686895,0.0002980568,0.00012835338,0.0012985652,6.747353e-8,0.0012050762,0.9769455,0.00030213714],"about_ca_topic_score_codex":0.000041570485,"about_ca_topic_score_gemma":0.0000927782,"teacher_disagreement_score":0.99057907,"about_ca_system_score_codex":0.00028931515,"about_ca_system_score_gemma":0.0016963095,"threshold_uncertainty_score":0.9999344},"labels":[],"label_agreement":null},{"id":"W2912468918","doi":"10.1038/s41598-018-37984-8","title":"Combining Multiple Magnetic Resonance Imaging Sequences Provides Independent Reproducible Radiomics Features","year":2019,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":52,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Agence Nationale de la Recherche; McMaster University","keywords":"Magnetic resonance imaging; Concordance; Concordance correlation coefficient; Reproducibility; Coronal plane; Correlation; Hierarchical clustering; Medicine; Artificial intelligence; Radiology; Radiomics; Nuclear medicine; Computer science; Cluster analysis; Pattern recognition (psychology); Mathematics; Statistics","score_opus":0.009597508499225067,"score_gpt":0.2641475245877596,"score_spread":0.2545500160885345,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2912468918","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97427773,0.008313775,0.00008658408,0.0021043078,0.008229127,0.00084762654,0.0000011167472,0.00020733014,0.005932397],"genre_scores_gemma":[0.9780367,0.000028887085,0.0043903603,0.00037263174,0.00018218353,0.000022370652,0.00004507475,0.00004137231,0.016880397],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99629676,0.00006828454,0.00062027475,0.0015191219,0.00094500167,0.00055055413],"domain_scores_gemma":[0.99760926,0.00009835968,0.00031004558,0.0015291367,0.00019937132,0.0002538266],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031235744,0.00022945814,0.0004116768,0.00028199275,0.0003165566,0.00040538964,0.00020011704,0.00007088889,0.00017586947],"category_scores_gemma":[0.0016774687,0.0001924995,0.00013849523,0.00052691315,0.000404821,0.00025834108,0.00013995949,0.0005842608,0.000053419637],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050097624,0.000110620276,0.79359114,0.00014341495,0.000013880657,0.0016746704,0.00083846087,0.0002233342,0.11742704,0.00009610212,0.014032555,0.071798675],"study_design_scores_gemma":[0.0038953621,0.00040554127,0.2904603,0.002046002,0.00021940064,0.021260994,0.0015225065,0.060780443,0.05160061,0.010765475,0.555624,0.0014193598],"about_ca_topic_score_codex":0.00020064453,"about_ca_topic_score_gemma":0.000008797925,"teacher_disagreement_score":0.54159147,"about_ca_system_score_codex":0.00011746177,"about_ca_system_score_gemma":0.00037805858,"threshold_uncertainty_score":0.7849902},"labels":[],"label_agreement":null},{"id":"W2912777662","doi":"10.1016/j.ejrad.2019.02.006","title":"Prognostic modeling for patients with colorectal liver metastases incorporating FDG PET radiomic features","year":2019,"lang":"en","type":"article","venue":"European Journal of Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":52,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Cancer Institute; National Natural Science Foundation of China; Danmarks Frie Forskningsfond; Memorial Sloan-Kettering Cancer Center","keywords":"Medicine; Colorectal cancer; Radiology; Colonic disease; Positron emission tomography; Nuclear medicine; Oncology; Internal medicine; Cancer","score_opus":0.008174993567951507,"score_gpt":0.23797896942305338,"score_spread":0.22980397585510187,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2912777662","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9819222,0.00047546666,0.016091054,0.00027496822,0.00037722092,0.00039606914,0.0000058967976,0.00001883978,0.00043826445],"genre_scores_gemma":[0.95804536,0.000025949064,0.0410642,0.00030890663,0.0004022977,0.0000016585562,0.00003334829,0.000053770294,0.00006453704],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9985103,0.0003670494,0.00046028243,0.00019698429,0.0002098901,0.0002555044],"domain_scores_gemma":[0.9986732,0.00028458156,0.00045573665,0.0001238422,0.00028333845,0.00017928286],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011266223,0.00017293372,0.00053030445,0.00018769024,0.00008343278,0.000018232533,0.00016828679,0.00002221211,0.00002857271],"category_scores_gemma":[0.0008287632,0.000114644645,0.00014018637,0.00009127757,0.0001145475,0.00009977731,0.00003202458,0.00055081473,0.000010219667],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.006548058,0.000581795,0.9340221,0.0004043802,0.0013166971,0.0042538163,0.0010403272,0.026333638,0.0051527303,0.0006024608,0.006054692,0.013689285],"study_design_scores_gemma":[0.043031126,0.035985455,0.56266403,0.0016702653,0.00210681,0.068981886,0.0004427743,0.28016314,0.0001674032,0.00023668446,0.0034536368,0.0010967863],"about_ca_topic_score_codex":0.000002071226,"about_ca_topic_score_gemma":2.4648892e-7,"teacher_disagreement_score":0.3713581,"about_ca_system_score_codex":0.00004788158,"about_ca_system_score_gemma":0.00012481655,"threshold_uncertainty_score":0.4675073},"labels":[],"label_agreement":null},{"id":"W2912783868","doi":"","title":"Proceedings of the 14th international conference on Medical image computing and computer-assisted intervention - Volume Part III","year":2011,"lang":"en","type":"article","venue":"Medical Image Computing and Computer-Assisted Intervention","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Robarts Clinical Trials; Sunnybrook Hospital; Queen's University","funders":"","keywords":"Volume (thermodynamics); Computer science; Intervention (counseling); Medicine; Nursing","score_opus":0.0239253525846016,"score_gpt":0.3058222005788327,"score_spread":0.2818968479942311,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2912783868","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7782563,0.00013891817,0.21257305,0.003096732,0.0029153938,0.00046656444,0.000005560952,0.00025055127,0.0022969358],"genre_scores_gemma":[0.9805087,0.00006442784,0.017156161,0.0009023846,0.0010193065,0.000007947408,0.000059859052,0.00005252281,0.00022870731],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99508727,0.00027876475,0.0016056868,0.0009117013,0.0015674244,0.0005491528],"domain_scores_gemma":[0.99739665,0.00019338596,0.00087697065,0.00031046884,0.0005746525,0.0006478518],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002496479,0.00048244835,0.0008803483,0.0003010713,0.0003404631,0.0002386286,0.0007236114,0.00034922332,0.0005539866],"category_scores_gemma":[0.00066123286,0.00037491994,0.00048447298,0.00035221205,0.0010740015,0.00023345443,0.0011967531,0.0015744944,0.000010875963],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003420745,0.002593539,0.018429168,0.00109092,0.0005254964,0.00017849427,0.001545007,0.0000015583975,0.0005513796,0.0025327962,0.0071656103,0.96504396],"study_design_scores_gemma":[0.005874724,0.0013228077,0.17472942,0.01126137,0.00019209174,0.0014586935,0.0003778164,0.80304945,0.00028364357,0.0001574988,0.0009006606,0.00039183593],"about_ca_topic_score_codex":0.00022558073,"about_ca_topic_score_gemma":0.000009156841,"teacher_disagreement_score":0.9646521,"about_ca_system_score_codex":0.00011068745,"about_ca_system_score_gemma":0.000095126496,"threshold_uncertainty_score":0.9998703},"labels":[],"label_agreement":null},{"id":"W2913074424","doi":"10.3389/fneur.2019.00007","title":"Automated Generation of Radiologic Descriptions on Brain Volume Changes From T1-Weighted MR Images: Initial Assessment of Feasibility","year":2019,"lang":"en","type":"article","venue":"Frontiers in Neurology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; National Institutes of Health; Genentech; National Institute of Neurological Disorders and Stroke; IXICO; H. Lundbeck A/S; Servier; Eisai; Northern California Institute for Research and Education; Johns Hopkins University; F. Hoffmann-La Roche; University of Southern California; Pfizer; BioClinica; Biogen; U.S. Department of Defense; Eli Lilly and Company; Bristol-Myers Squibb; Meso Scale Diagnostics; Alzheimer's Disease Neuroimaging Initiative; Novartis Pharmaceuticals Corporation; National Institute on Aging; Alzheimer's Association","keywords":"Nuclear medicine; Medicine; Volume (thermodynamics); Neuroimaging; Radiology; Artificial intelligence; Medical physics; Computer science; Neuroscience; Psychology; Physics","score_opus":0.027071484326484936,"score_gpt":0.3210304032517301,"score_spread":0.29395891892524517,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2913074424","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98356813,0.00011337256,0.0075128824,0.006253412,0.0015267659,0.0004875099,0.000030045336,0.000076210934,0.0004316847],"genre_scores_gemma":[0.9839867,0.000042433207,0.01305329,0.0024985587,0.00013595777,0.000014930141,0.00018386103,0.000017029843,0.00006728117],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984138,0.0004569771,0.00037178892,0.0003635328,0.00017977112,0.00021414399],"domain_scores_gemma":[0.99918556,0.00016678445,0.00019502413,0.00032778,0.00006057142,0.0000643025],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004190058,0.00013582341,0.00055718503,0.00027583036,0.000023825916,0.0000047657904,0.00012154529,0.0001721279,0.00012312435],"category_scores_gemma":[0.00039405748,0.000120629906,0.000067505985,0.0001863951,0.00020320345,0.000037818765,0.000036235688,0.0004970839,0.0000029196772],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033561085,0.0003188935,0.8582282,0.0000556865,0.00006382118,0.00004267714,0.00015788023,0.0007025924,0.11277544,0.00007143299,0.02446385,0.002783888],"study_design_scores_gemma":[0.002063484,0.0014889333,0.46797413,0.000027152182,0.000035626985,0.000012172806,0.000024783543,0.5263722,0.0012300301,0.00019605855,0.0004968272,0.00007862809],"about_ca_topic_score_codex":0.0001441979,"about_ca_topic_score_gemma":0.000009585496,"teacher_disagreement_score":0.5256696,"about_ca_system_score_codex":0.00005961179,"about_ca_system_score_gemma":0.00008748799,"threshold_uncertainty_score":0.49191448},"labels":[],"label_agreement":null},{"id":"W2913197325","doi":"10.1007/s11307-018-01304-3","title":"Radiomics Analysis of PET and CT Components of PET/CT Imaging Integrated with Clinical Parameters: Application to Prognosis for Nasopharyngeal Carcinoma","year":2019,"lang":"en","type":"article","venue":"Molecular Imaging and Biology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":98,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Key Research and Development Program of China; China Scholarship Council; Natural Science Foundation of Guangdong Province; National Natural Science Foundation of China","keywords":"Medicine; Nasopharyngeal carcinoma; Positron emission tomography; Nuclear medicine; Concordance; PET-CT; Stage (stratigraphy); Radiomics; Radiology; Proportional hazards model; Radiation therapy; Internal medicine","score_opus":0.015128507289440941,"score_gpt":0.3188585228828143,"score_spread":0.30373001559337337,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2913197325","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9772673,0.00045769336,0.020112028,0.001517439,0.00004536041,0.0005336024,0.000022967279,0.000017344826,0.000026235706],"genre_scores_gemma":[0.9790926,0.00003553417,0.01983095,0.0007291749,0.000011964408,0.000023983557,0.00025291965,0.00001811045,0.0000047596877],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99879026,0.00009742173,0.00040481007,0.00042250252,0.00007993101,0.00020505626],"domain_scores_gemma":[0.999175,0.00017567528,0.00018788522,0.00021523095,0.000114582705,0.00013162552],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004891676,0.00015162349,0.0006852428,0.00030278508,0.000028759308,0.000012433708,0.00008575302,0.000008249547,0.0000023111497],"category_scores_gemma":[0.00013626747,0.00011427819,0.00012213617,0.0003056621,0.00026152428,0.000025213565,0.000051467658,0.0001759817,3.6365026e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002345159,0.00007942988,0.909546,0.00009929622,0.00045439426,0.00005518639,0.00003320718,0.00004520485,0.06842017,0.000073863055,0.000021293528,0.02093745],"study_design_scores_gemma":[0.00405782,0.0006705121,0.32705596,0.00016693567,0.0023482493,0.0009611725,0.00020558792,0.65689534,0.0063403775,0.00008184434,0.00093218236,0.00028401052],"about_ca_topic_score_codex":0.00039351173,"about_ca_topic_score_gemma":0.0000023133784,"teacher_disagreement_score":0.65685016,"about_ca_system_score_codex":0.000016228749,"about_ca_system_score_gemma":0.000033903892,"threshold_uncertainty_score":0.46601295},"labels":[],"label_agreement":null},{"id":"W2913972996","doi":"10.1158/1538-7445.sabcs18-p4-02-01","title":"Abstract P4-02-01: Analytical validation of an automated digital scoring protocol for Ki67: International multicenter collaboration study","year":2019,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sinai Health System; University of Toronto; University of British Columbia","funders":"","keywords":"Reproducibility; Breast cancer; Protocol (science); Medicine; Standardization; Medical physics; Tissue microarray; Digital image analysis; Cancer; Pathology; Artificial intelligence; Computer science; Internal medicine; Statistics; Mathematics; Computer vision","score_opus":0.07730096198235493,"score_gpt":0.5323393647668984,"score_spread":0.45503840278454344,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2913972996","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9503605,0.0000013388985,0.000086786975,0.00074996165,0.0001368046,0.047746666,0.000016378037,0.000058486316,0.0008430825],"genre_scores_gemma":[0.9761319,5.772079e-7,0.0002661141,0.000024419272,0.00023571783,0.02294205,0.00006188017,0.000022808472,0.00031450493],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99838495,0.000052556068,0.0003042127,0.00027759248,0.0007534065,0.0002272655],"domain_scores_gemma":[0.99874383,0.00013763053,0.00008060385,0.00020767454,0.00070175907,0.00012852336],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009795689,0.00008236805,0.00018304036,0.00022425514,0.000055902132,0.000133993,0.00015320565,0.000046986726,0.00031135252],"category_scores_gemma":[0.00066594646,0.00006891265,0.00003882141,0.00026417998,0.000067069486,0.00032724597,0.000050592666,0.00030303877,0.00001605582],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0057637473,0.003695283,0.8455542,0.0013127255,0.0004546356,0.000039653256,0.002387745,0.0035386584,0.0996901,0.00021904307,0.0028622907,0.034481943],"study_design_scores_gemma":[0.01682967,0.0021716522,0.2539874,0.0007833054,0.000042384363,0.0000052370056,0.0019176282,0.6916401,0.02459361,0.000057543362,0.007738072,0.00023340927],"about_ca_topic_score_codex":0.00012414559,"about_ca_topic_score_gemma":0.0000066609214,"teacher_disagreement_score":0.6881014,"about_ca_system_score_codex":0.00021716417,"about_ca_system_score_gemma":0.00028344698,"threshold_uncertainty_score":0.34090918},"labels":[],"label_agreement":null},{"id":"W2913985588","doi":"10.2967/jnumed.118.223495","title":"Machine Learning in Nuclear Medicine: Part 1—Introduction","year":2019,"lang":"en","type":"review","venue":"Journal of Nuclear Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":61,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Health Sciences Centre; Montreal Neurological Institute and Hospital; University of Toronto; Sunnybrook Health Science Centre; University of Waterloo; University of British Columbia; McGill University","funders":"Society of Nuclear Medicine and Molecular Imaging","keywords":"Context (archaeology); Field (mathematics); Computer science; Artificial intelligence; Machine learning; Data science; Medical physics; Medicine; History; Mathematics","score_opus":0.03646419099408104,"score_gpt":0.347644446213445,"score_spread":0.31118025521936393,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2913985588","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000042266627,0.95787024,0.0000143681555,0.032787696,0.0037798225,0.0005308752,0.0000017960385,0.00006829746,0.004904613],"genre_scores_gemma":[0.000060869806,0.9816027,0.00039449232,0.001971294,0.013866924,0.0000019467013,0.000059146532,0.00028566827,0.0017569509],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99391335,0.0005700969,0.0029155447,0.00058270106,0.0014140843,0.0006042158],"domain_scores_gemma":[0.9955536,0.00045852482,0.0025024859,0.0005989746,0.0003017799,0.0005846451],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0038387717,0.0007215467,0.00557932,0.0017388222,0.000111807036,0.000024878747,0.0005381451,0.0005157561,0.004294192],"category_scores_gemma":[0.0048571937,0.00045597422,0.0006910061,0.00095043326,0.0005036264,0.00018003749,0.000119747885,0.006293191,0.0002373255],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001921156,0.00016117992,0.0000645303,0.011962543,0.000490771,0.0010323495,0.00059998885,0.000023180612,0.000027709984,0.00038075203,0.1709527,0.8141122],"study_design_scores_gemma":[0.0032103807,0.0021505347,0.0000362396,0.053282082,0.0028168003,0.0069877575,0.00025169435,0.0007317246,3.555564e-8,0.000028936562,0.93019146,0.0003123599],"about_ca_topic_score_codex":0.00006902341,"about_ca_topic_score_gemma":0.0000011007468,"teacher_disagreement_score":0.81379986,"about_ca_system_score_codex":0.0005195008,"about_ca_system_score_gemma":0.00033023814,"threshold_uncertainty_score":0.9997892},"labels":[],"label_agreement":null},{"id":"W2915596936","doi":"10.1186/s41077-018-0066-5","title":"Selected abstracts from the 24th Annual Meeting of the Society in Europe for the Simulation Applied to Medicine","year":2018,"lang":"en","type":"article","venue":"Advances in Simulation","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Queen's University; Hospital for Sick Children; Queen's University Belfast","keywords":"Process (computing); Clinical Practice; 3d model; Medicine; Medical education; Computer science; Artificial intelligence; Nursing","score_opus":0.012345640291266655,"score_gpt":0.3373355585946099,"score_spread":0.32498991830334323,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2915596936","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9283846,0.0008075076,0.05926737,0.007681827,0.00048828038,0.0016754686,0.000009627078,0.000035852696,0.0016494431],"genre_scores_gemma":[0.9961905,0.00003961735,0.0015609458,0.0015643159,0.0005744483,0.000014169867,0.000016385971,0.000015664345,0.000023956574],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989608,0.000056360477,0.00037922192,0.00018201236,0.00026527594,0.00015632705],"domain_scores_gemma":[0.99645746,0.0028566592,0.00018385699,0.0002198818,0.0002552328,0.000026927659],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00082677574,0.00009397275,0.0001702535,0.000028045833,0.0001243227,0.0000066290017,0.00015357182,0.000042358926,0.0000098936935],"category_scores_gemma":[0.0036085781,0.0000460788,0.000036386602,0.00070938177,0.00016848763,0.00008298812,0.000036736343,0.00023575629,0.0000013353506],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014602975,0.000019506568,0.017018074,0.0000141602695,0.000012082432,1.447315e-7,0.0040598246,0.9410516,0.0016351843,0.00008537851,0.0000963919,0.0358616],"study_design_scores_gemma":[0.0010979414,0.0000618839,0.26254115,0.00018460785,0.000033210876,2.1056611e-7,0.00042457084,0.7176456,0.00020081067,0.00037482096,0.017386153,0.00004907716],"about_ca_topic_score_codex":0.00013252569,"about_ca_topic_score_gemma":0.00010677379,"teacher_disagreement_score":0.24552307,"about_ca_system_score_codex":0.00004164019,"about_ca_system_score_gemma":0.00003775688,"threshold_uncertainty_score":0.43200657},"labels":[],"label_agreement":null},{"id":"W2916358664","doi":"10.6084/m9.figshare.c.3900712.v1","title":"OHBM 2011 Courses: Introduction to Imaging Genetics","year":2017,"lang":"en","type":"article","venue":"Figshare","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Imaging genetics; Biology; Neuroscience; Neuroimaging","score_opus":0.022780964802005633,"score_gpt":0.32636274549964905,"score_spread":0.3035817806976434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2916358664","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.098121576,0.0056448444,0.0012226063,0.7023976,0.00756663,0.004298326,0.049879957,0.0015542296,0.12931427],"genre_scores_gemma":[0.9199251,0.000042314576,0.007826762,0.010366928,0.017629934,0.00016558505,0.032834996,0.00015968361,0.0110486755],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992061,0.000010968913,0.000121637764,0.00025144115,0.00019244848,0.00021739406],"domain_scores_gemma":[0.9989614,0.00001827325,0.00008530006,0.00060183957,0.000112979345,0.00022020703],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00008036473,0.000100676785,0.00014906575,0.00006025836,0.00025134618,0.00012253156,0.00021278035,0.00003395975,0.06173594],"category_scores_gemma":[0.0023793508,0.00009171029,0.00005097142,0.000023789156,0.000014932533,0.00008334504,0.00012938581,0.00025402446,0.0034329742],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010055577,0.00001795816,0.0030200959,0.00005572472,0.000010963499,0.000045186254,0.00005561483,0.000020247297,0.00065393606,0.0000069288676,0.9330574,0.06304588],"study_design_scores_gemma":[0.0004304177,0.000039767565,0.052893464,0.0004908751,0.000024332743,0.00011099343,0.000023822311,0.0054826303,0.0007062539,0.000025265064,0.9396453,0.00012689359],"about_ca_topic_score_codex":0.000016494772,"about_ca_topic_score_gemma":0.0000012756012,"teacher_disagreement_score":0.82180357,"about_ca_system_score_codex":0.000036622092,"about_ca_system_score_gemma":0.000054821274,"threshold_uncertainty_score":0.99734294},"labels":[],"label_agreement":null},{"id":"W2918339201","doi":"","title":"Dependency of a validated radiomics signature on tumor volume and potential corrections","year":2018,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Radiomics; Cancer; Concordance; Lung cancer; Medicine; Nuclear medicine; Radiology; Oncology; Internal medicine","score_opus":0.006335193978469401,"score_gpt":0.26458932258251644,"score_spread":0.25825412860404706,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2918339201","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9724304,0.00006273051,0.015370418,0.0016971896,0.000595439,0.00017416464,0.0000040032014,0.00007597654,0.009589653],"genre_scores_gemma":[0.9913617,0.000019177694,0.0042207637,0.001003551,0.000305099,0.000002001893,0.0000107358,0.000016504755,0.0030604794],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992885,0.000027598388,0.00017226466,0.00018563145,0.00017850003,0.0001475103],"domain_scores_gemma":[0.9995218,0.000030311716,0.000058891525,0.00015574704,0.00010014245,0.00013309663],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001605877,0.00009306448,0.00019936515,0.000113554,0.000077319695,0.000013162625,0.000052203763,0.00006142138,0.00049959874],"category_scores_gemma":[0.00025718944,0.00007243813,0.00004869596,0.00014141256,0.00018003547,0.000032522363,0.00002566872,0.0003230917,0.000020800444],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0020984756,0.0016141138,0.12782049,0.00040801783,0.0007804113,0.00060087006,0.0018246549,0.00025861242,0.59527826,0.0066296603,0.105611205,0.15707524],"study_design_scores_gemma":[0.013372955,0.007244324,0.16187619,0.00083778764,0.0010752574,0.003314617,0.00092790416,0.68716055,0.07302178,0.00219299,0.04792326,0.001052369],"about_ca_topic_score_codex":0.00008438618,"about_ca_topic_score_gemma":0.0000028864254,"teacher_disagreement_score":0.686902,"about_ca_system_score_codex":0.000018433135,"about_ca_system_score_gemma":0.000051949894,"threshold_uncertainty_score":0.54702556},"labels":[],"label_agreement":null},{"id":"W2921423014","doi":"10.1200/jco.2019.37.7_suppl.126","title":"Radiogenomic characterization of multifocal prostate cancer.","year":2019,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Genome British Columbia","funders":"","keywords":"Prostate cancer; Medicine; Magnetic resonance imaging; Radiogenomics; Prostatectomy; ATRX; Prostate; Cancer; Pathology; Radiology; Internal medicine; Gene; Mutation; Biology; Radiomics","score_opus":0.04538494451729355,"score_gpt":0.4470190684444935,"score_spread":0.4016341239272,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2921423014","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9885032,0.00017530471,0.00029469814,0.008175604,0.001984816,0.00016541698,0.0000025383476,0.000004853148,0.0006935743],"genre_scores_gemma":[0.99326843,0.00129787,0.0022188225,0.0016807299,0.00091694505,0.0000010997752,0.0000044387957,0.00001463252,0.00059705676],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99759346,0.00019454942,0.0017211153,0.00011399912,0.00023690362,0.00013995651],"domain_scores_gemma":[0.9971334,0.0005080978,0.0017455949,0.00011602807,0.00026926745,0.00022761119],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022995002,0.00007703287,0.0011058747,0.00009462728,0.0000121536805,0.0000035637383,0.00011002986,0.00017479794,0.0002462684],"category_scores_gemma":[0.0014918181,0.00005389226,0.00029061103,0.0000837379,0.0001322543,0.00006948308,0.000026058322,0.00083505723,0.000016092623],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002055856,0.0005088647,0.48513508,0.00008111536,0.00022298373,0.00009755395,0.00014930656,0.000071284965,0.09742376,0.00005604298,0.00033942904,0.4138587],"study_design_scores_gemma":[0.009530398,0.005743276,0.86255884,0.0002602293,0.00024910909,0.00028805653,0.000037644433,0.0075925956,0.0008578284,0.000054492208,0.11274211,0.00008544403],"about_ca_topic_score_codex":0.000017021564,"about_ca_topic_score_gemma":8.895517e-7,"teacher_disagreement_score":0.41377327,"about_ca_system_score_codex":0.000075962904,"about_ca_system_score_gemma":0.0010224625,"threshold_uncertainty_score":0.36279547},"labels":[],"label_agreement":null},{"id":"W2921622031","doi":"10.1117/12.2512550","title":"PI-RADS guided discovery radiomics for characterization of prostate lesions with diffusion-weighted MRI","year":2019,"lang":"en","type":"article","venue":"Medical Imaging 2019: Computer-Aided Diagnosis","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Radiomics; Diffusion MRI; Prostate; BI-RADS; Multiparametric MRI; Magnetic resonance imaging; Medicine; Computer science; Radiology; Internal medicine","score_opus":0.0068312632274489605,"score_gpt":0.2622688284657198,"score_spread":0.2554375652382708,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2921622031","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.73859715,0.00017049098,0.23933205,0.019254431,0.0009623564,0.0014094438,0.000047328962,0.00015344525,0.000073306175],"genre_scores_gemma":[0.9425539,0.001651157,0.04350962,0.008023763,0.0012694269,0.00032681244,0.001306304,0.00023156012,0.0011274884],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99645823,0.00013123953,0.0009257819,0.00076816464,0.0010706146,0.0006459527],"domain_scores_gemma":[0.9972554,0.00072554924,0.0004413067,0.0006747802,0.00031461928,0.00058838824],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00079548906,0.00042206308,0.0010058546,0.0003612143,0.00014781172,0.0001136828,0.00035114927,0.00015752525,0.00016552127],"category_scores_gemma":[0.00048415686,0.0003156725,0.00026238326,0.00044846433,0.0003362282,0.00044279595,0.00022206797,0.0005848897,0.000025741241],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00081060635,0.0021076328,0.7189893,0.001469754,0.0005008037,0.0002693802,0.00086613593,0.0001579055,0.018605981,0.0010185231,0.03290808,0.2222959],"study_design_scores_gemma":[0.016758023,0.0010114023,0.12354681,0.005657802,0.00054190226,0.0005393953,0.00005938917,0.8110763,0.005047464,0.0002618702,0.034573738,0.00092594075],"about_ca_topic_score_codex":0.00012035823,"about_ca_topic_score_gemma":0.0000014045116,"teacher_disagreement_score":0.81091833,"about_ca_system_score_codex":0.000114892995,"about_ca_system_score_gemma":0.0003956832,"threshold_uncertainty_score":0.99992955},"labels":[],"label_agreement":null},{"id":"W2921843095","doi":"10.1136/ijgc-00009577-200303001-00029","title":"Prognostic Precision With Sentinel Node Localization (SNL) in Cancer of the Cervix, Stage 1B1","year":2003,"lang":"en","type":"article","venue":"International Journal of Gynecological Cancer","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier de l’Université de Montréal","funders":"","keywords":"Medicine; Sentinel node; Stage (stratigraphy); Cervix; Node (physics); Oncology; Cancer; Gynecology; Internal medicine; Breast cancer","score_opus":0.018078548027772617,"score_gpt":0.3338803823247408,"score_spread":0.3158018342969682,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2921843095","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98636115,0.0005598115,0.004324911,0.006845685,0.0007342967,0.00017659784,0.0000045698894,0.00000490398,0.0009880894],"genre_scores_gemma":[0.9967701,0.0004173394,0.0006118961,0.0017876233,0.00013182356,0.000011077988,0.0000013245276,0.000010270161,0.0002585628],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9985316,0.0001045188,0.00045244093,0.000118560216,0.0006592214,0.00013369371],"domain_scores_gemma":[0.99866813,0.00023498233,0.000424792,0.00007816599,0.00052091305,0.00007298261],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043926435,0.00009402894,0.00024341568,0.000106691834,0.000026104934,0.000016261329,0.00021182757,0.000061785046,0.0008985152],"category_scores_gemma":[0.0016395244,0.000049224735,0.00008691963,0.00019769096,0.000107627886,0.000073382624,0.000034319568,0.00040757534,7.3854426e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025510704,0.00025219514,0.96857136,0.00002745665,0.000095468575,0.00008648188,0.000104873754,0.023626978,0.0010546932,0.00033808887,0.0004255249,0.005161755],"study_design_scores_gemma":[0.0037440166,0.00026405844,0.9576033,0.00099902,0.000103538245,0.00014108387,0.00009252294,0.013785472,0.0016131856,0.0003532676,0.021185402,0.0001151615],"about_ca_topic_score_codex":0.000086398286,"about_ca_topic_score_gemma":0.000059534184,"teacher_disagreement_score":0.020759877,"about_ca_system_score_codex":0.00024679565,"about_ca_system_score_gemma":0.0003220809,"threshold_uncertainty_score":0.9838112},"labels":[],"label_agreement":null},{"id":"W2923027365","doi":"10.1038/s41598-019-39206-1","title":"Deep learning in head &amp; neck cancer outcome prediction","year":2019,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":200,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds de recherche du Québec – Nature et technologies; Canadian Institutes of Health Research","keywords":"Radiomics; Convolutional neural network; Artificial intelligence; Computer science; Head and neck cancer; Head and neck squamous-cell carcinoma; Outcome (game theory); Appropriate Use Criteria; Head and neck; Basal cell; Deep learning; Medical imaging; Machine learning; Medicine; Pattern recognition (psychology); Radiology; Radiation therapy; Internal medicine; Surgery; Mathematics","score_opus":0.017976302208352953,"score_gpt":0.3243917913262709,"score_spread":0.30641548911791794,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2923027365","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98463804,0.00033437184,0.00040471135,0.0010082686,0.007976825,0.0003221056,2.426565e-7,0.0001167827,0.0051986566],"genre_scores_gemma":[0.9646564,0.000015716094,0.00089340965,0.00019989505,0.0001450358,0.00001773837,0.00005528873,0.000022466631,0.033994015],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99792844,0.000040452713,0.00054400525,0.0006063731,0.00054230675,0.00033844338],"domain_scores_gemma":[0.99907565,0.000027054446,0.00017411688,0.00047588302,0.000081374244,0.00016593428],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015500865,0.00011903218,0.00028144152,0.00025679468,0.00011508808,0.000096236996,0.000060362694,0.00007315354,0.00077197823],"category_scores_gemma":[0.0005546977,0.00010122392,0.00008603614,0.00045606485,0.00009949032,0.0001227668,0.000047080463,0.000593093,0.00012371497],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011737351,0.000044085155,0.9739534,0.00006891937,0.000009917097,0.00018033781,0.0003242197,0.004134229,0.0077607175,0.000010350938,0.0015234118,0.011978669],"study_design_scores_gemma":[0.00084128097,0.000053687418,0.53912264,0.00034869873,0.000036019283,0.00059276354,0.00008673031,0.047650803,0.00019704309,0.00037829575,0.41050768,0.00018433435],"about_ca_topic_score_codex":0.0002646379,"about_ca_topic_score_gemma":0.0000846452,"teacher_disagreement_score":0.43483075,"about_ca_system_score_codex":0.00014180627,"about_ca_system_score_gemma":0.00012394697,"threshold_uncertainty_score":0.845262},"labels":[],"label_agreement":null},{"id":"W2923943486","doi":"10.1016/j.radonc.2019.03.001","title":"Repeatability and reproducibility of MRI-based radiomic features in cervical cancer","year":2019,"lang":"en","type":"article","venue":"Radiotherapy and Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":168,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Princess Margaret Cancer Centre; University Health Network","funders":"","keywords":"Reproducibility; Repeatability; Intraclass correlation; Medicine; Radiomics; Cohort; Magnetic resonance imaging; Radiology; Stage (stratigraphy); Nuclear medicine; Statistics; Mathematics; Pathology","score_opus":0.010470522464677508,"score_gpt":0.3332591124720611,"score_spread":0.3227885900073836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2923943486","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9829428,0.006094816,0.000111767076,0.0098807085,0.0002181987,0.0004001959,0.0000031124403,0.00001791758,0.0003304637],"genre_scores_gemma":[0.9937382,0.0010990964,0.0030617851,0.0017421917,0.00010207367,0.000012760171,0.000004327461,0.000013377291,0.00022623144],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9985755,0.00018041639,0.00029058158,0.00067265506,0.000103337254,0.00017747552],"domain_scores_gemma":[0.99893355,0.00027081434,0.00008572065,0.00057623815,0.000029415765,0.00010424412],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015477818,0.00011070497,0.0005779268,0.00009208366,0.000025278981,0.0000036307754,0.0000547444,0.00014650803,0.00019933598],"category_scores_gemma":[0.00025446495,0.000087641274,0.000047590493,0.000115662304,0.00033219156,0.000029835695,0.00001780949,0.00038204057,3.390818e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00090655254,0.00017863585,0.9439105,0.00027186953,0.000032948297,0.000020976202,0.0005155164,0.00007154337,0.011913873,0.00010946302,0.0001442284,0.041923944],"study_design_scores_gemma":[0.0044134357,0.000644434,0.9761001,0.0000685968,0.0000253438,0.00012422768,0.00003421469,0.007791709,0.00081614335,0.00013021988,0.00975698,0.00009459803],"about_ca_topic_score_codex":0.0007269209,"about_ca_topic_score_gemma":0.00009938809,"teacher_disagreement_score":0.041829344,"about_ca_system_score_codex":0.00020764346,"about_ca_system_score_gemma":0.00021740678,"threshold_uncertainty_score":0.35739073},"labels":[],"label_agreement":null},{"id":"W2931569196","doi":"10.1109/access.2019.2907564","title":"Quantification of Full Left Ventricular Metrics via Deep Regression Learning With Contour-Guidance","year":2019,"lang":"en","type":"article","venue":"IEEE Access","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":83,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Science Foundation of Tianjin City; Natural Science Foundation of Beijing Municipality; Department of Education of Hebei Province; National Natural Science Foundation of China; National Science Foundation","keywords":"Segmentation; Artificial intelligence; Ventricle; Regression; Computer science; Pattern recognition (psychology); Component (thermodynamics); Image segmentation; Regression analysis; Deep learning; Cardiac magnetic resonance; Magnetic resonance imaging; Computer vision; Machine learning; Mathematics; Statistics; Cardiology; Medicine; Radiology","score_opus":0.01608091908371773,"score_gpt":0.3147499362919007,"score_spread":0.29866901720818295,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2931569196","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8155696,0.00063188974,0.18193719,0.00046671295,0.00029761027,0.00027170216,4.5898258e-7,0.00005003707,0.0007747942],"genre_scores_gemma":[0.9972098,0.00006718154,0.001983468,0.00014976799,0.00010888208,0.0000042873944,0.000019312776,0.000028013537,0.0004293204],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99868834,0.000073728625,0.00029121578,0.00027925163,0.00046096783,0.00020649142],"domain_scores_gemma":[0.9989266,0.000119382436,0.00031993655,0.00031777218,0.00020796232,0.000108369124],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047212068,0.00013158684,0.00034153776,0.00020802967,0.00005922072,0.000037572816,0.00021780883,0.00007671928,0.00010777159],"category_scores_gemma":[0.0003363052,0.000092129936,0.00006382175,0.00043176446,0.000060489627,0.00018270742,0.00003242117,0.00042301524,0.000029443703],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003564015,0.00017111529,0.8297715,0.00049833854,0.00010784304,0.00010700733,0.00020396298,0.008445604,0.11445261,0.00010230782,0.00042985595,0.04535346],"study_design_scores_gemma":[0.0073385774,0.0016572161,0.25481856,0.0024056216,0.00048189747,0.0007576331,0.0002742363,0.60904396,0.10811549,0.00016742671,0.014202414,0.00073698774],"about_ca_topic_score_codex":0.000068674504,"about_ca_topic_score_gemma":0.0000026382677,"teacher_disagreement_score":0.60059834,"about_ca_system_score_codex":0.000043878394,"about_ca_system_score_gemma":0.00004671436,"threshold_uncertainty_score":0.37569496},"labels":[],"label_agreement":null},{"id":"W2936340812","doi":"10.1007/s00330-019-06159-y","title":"Head and neck squamous cell carcinoma: prediction of cervical lymph node metastasis by dual-energy CT texture analysis with machine learning","year":2019,"lang":"en","type":"article","venue":"European Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":119,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Royal Victoria Hospital; Jewish General Hospital; Université de Montréal; Royal Victoria Regional Health Centre; McGill University Health Centre","funders":"Fonds de Recherche du Québec - Santé; Réseau de cancérologie Rossy","keywords":"Medicine; Neuroradiology; Head and neck squamous-cell carcinoma; Lymph node metastasis; Cervical lymph nodes; Radiology; Interventional radiology; Head and neck; Basal cell; Lymph node; Ultrasound; Head and neck cancer; Metastasis; Radiation therapy; Pathology; Internal medicine; Surgery; Cancer; Neurology","score_opus":0.005765094514935071,"score_gpt":0.22013333593738327,"score_spread":0.2143682414224482,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2936340812","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9840962,0.0027465364,0.004218102,0.000603942,0.0000874198,0.00010706972,0.000034422428,0.00007098665,0.008035264],"genre_scores_gemma":[0.9960978,0.00012304704,0.0009728752,0.00061365386,0.0001214545,0.0000022477066,0.00040240114,0.000060613318,0.0016059233],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.997949,0.0005966928,0.00038782103,0.00051579124,0.00021934626,0.0003313724],"domain_scores_gemma":[0.9990234,0.00014759983,0.00020820311,0.0003372415,0.00005741592,0.00022615904],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047230508,0.00024574122,0.00073454616,0.0002653985,0.0000789423,0.000014421921,0.0001079704,0.00005507819,0.000194192],"category_scores_gemma":[0.00009643396,0.00018241018,0.00013775597,0.0004012495,0.00018279329,0.000047218407,0.000079056794,0.0005226294,0.000013162017],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002795409,0.00015258571,0.98277885,0.00015650959,0.00041905418,0.00032851569,0.00021449126,0.003009042,0.008629673,0.000060103433,0.0009071265,0.003064511],"study_design_scores_gemma":[0.007448563,0.0016932262,0.8314276,0.000037478992,0.0023347158,0.0018021284,0.00012011196,0.13392864,0.0003867879,0.0000052700498,0.02050493,0.00031059602],"about_ca_topic_score_codex":0.00038609054,"about_ca_topic_score_gemma":0.0000046976716,"teacher_disagreement_score":0.15135129,"about_ca_system_score_codex":0.000039788156,"about_ca_system_score_gemma":0.0000342094,"threshold_uncertainty_score":0.74384713},"labels":[],"label_agreement":null},{"id":"W2937582454","doi":"10.1007/s00330-019-06169-w","title":"Image-based biomarkers for solid tumor quantification","year":2019,"lang":"en","type":"review","venue":"European Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":40,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Jewish General Hospital; McGill University Health Centre; McGill University","funders":"","keywords":"Medicine; Clinical Practice; Personalized medicine; Biomarker; Artificial intelligence; Radiomics; Precision medicine; Medical physics; Image processing; Computer science; Data science; Pathology; Image (mathematics); Bioinformatics","score_opus":0.05823360293449027,"score_gpt":0.3810091473915019,"score_spread":0.3227755444570116,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2937582454","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000008709557,0.9744451,0.015478672,0.0005518406,0.001275859,0.0017056959,0.00004382516,0.00015609454,0.006334204],"genre_scores_gemma":[0.000026158676,0.98083025,0.0134968,0.0011707116,0.0011422521,0.00007255701,0.0018387886,0.0002818404,0.0011406589],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9971705,0.0007622501,0.0007773263,0.00071589067,0.00012781599,0.00044622208],"domain_scores_gemma":[0.997859,0.0006108748,0.00053056784,0.00072497234,0.00008534566,0.00018921368],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0014676024,0.0004124725,0.0018903548,0.00034324045,0.00008468803,0.000033427972,0.0003456213,0.00013340366,0.00008494789],"category_scores_gemma":[0.0012688751,0.00031718623,0.0007301636,0.00017831114,0.00024479537,0.000025687095,0.000044889257,0.0006511454,0.0008300441],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000064940934,0.000071790884,0.00001377506,0.022114858,0.00044259857,0.00020042386,0.000014141313,0.0000035455662,0.00013410351,0.00013941666,0.042110804,0.9346896],"study_design_scores_gemma":[0.0009775759,0.00025675862,0.000034502376,0.0038123657,0.001338115,0.00072439073,0.0000033396732,0.0026955782,0.0000016128498,0.0000046044624,0.9898552,0.00029598034],"about_ca_topic_score_codex":0.0000026212515,"about_ca_topic_score_gemma":7.756065e-8,"teacher_disagreement_score":0.94774437,"about_ca_system_score_codex":0.00010952402,"about_ca_system_score_gemma":0.00037146255,"threshold_uncertainty_score":0.9999479},"labels":[],"label_agreement":null},{"id":"W2941261582","doi":"10.1097/01.ju.0000556876.83918.db","title":"PD50-01 ASSESSMENT OF MRI PERFORMANCE IN THE CANARY PROSTATE ACTIVE SURVEILLANCE STUDY (PASS)","year":2019,"lang":"en","type":"article","venue":"The Journal of Urology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Medicine; Prostate; Medical physics; Radiology; Internal medicine","score_opus":0.0079218639893252,"score_gpt":0.3051100528449437,"score_spread":0.2971881888556185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2941261582","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9864672,0.00013096131,0.00006265426,0.011197964,0.000205582,0.00031862216,7.060027e-7,0.0000020040522,0.001614352],"genre_scores_gemma":[0.9985922,0.00022934962,0.00007393435,0.00094889523,0.00008183914,0.0000018012694,6.118868e-7,0.000007836003,0.00006351229],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9985758,0.0005356477,0.0003519502,0.00006849468,0.00030315382,0.00016493264],"domain_scores_gemma":[0.9988967,0.00043246537,0.0003476378,0.00020401679,0.00008336747,0.00003578421],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031115043,0.00007655451,0.00031804235,0.00008817497,0.00003220449,0.0000036503243,0.00025246944,0.000028018683,0.000039335475],"category_scores_gemma":[0.00011217918,0.00003649782,0.00004110994,0.00013971068,0.000091514295,0.000044102482,0.000036341913,0.00089728786,0.0000020894336],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006786613,0.00027151973,0.9879285,0.000024687855,0.00010365693,0.00006571078,0.0033461011,0.0027520866,0.0008643121,0.000023746636,0.00021286003,0.0037281173],"study_design_scores_gemma":[0.001794308,0.002823785,0.9830587,0.000019593068,0.00005555461,0.00054155453,0.0014129002,0.009030245,0.0000109447965,0.00003526898,0.0011822028,0.000034968274],"about_ca_topic_score_codex":0.00012015805,"about_ca_topic_score_gemma":0.000038575334,"teacher_disagreement_score":0.012125066,"about_ca_system_score_codex":0.000036541493,"about_ca_system_score_gemma":0.0001644726,"threshold_uncertainty_score":0.3898319},"labels":[],"label_agreement":null},{"id":"W2942237787","doi":"10.1016/j.ejmp.2019.04.009","title":"Stability of radiomic features of apparent diffusion coefficient (ADC) maps for locally advanced rectal cancer in response to image pre-processing","year":2019,"lang":"en","type":"article","venue":"Physica Medica","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":65,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre","funders":"","keywords":"Effective diffusion coefficient; Histogram; Resampling; Artificial intelligence; Pattern recognition (psychology); Computer science; Reproducibility; Image processing; Pixel; Computer vision; Mathematics; Medicine; Image (mathematics); Radiology; Statistics; Magnetic resonance imaging","score_opus":0.0065736685103552185,"score_gpt":0.30635924446887186,"score_spread":0.2997855759585166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2942237787","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.990303,0.00039901648,0.0045258873,0.0030632508,0.0002238706,0.001175049,0.00004119068,0.000026705946,0.00024204391],"genre_scores_gemma":[0.9960108,0.000036580088,0.00339963,0.00020177396,0.000087705914,0.00008569502,0.000022012247,0.000031566044,0.00012424096],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99811846,0.00011045271,0.00047872163,0.0004083345,0.0005638135,0.00032021123],"domain_scores_gemma":[0.9986644,0.00038424332,0.00022129924,0.0003499687,0.00016945227,0.00021067582],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008894805,0.00017597813,0.0006652518,0.0001509841,0.00003709575,0.0000050684293,0.00018889403,0.00006263479,0.00006454568],"category_scores_gemma":[0.0011380796,0.00014085823,0.00012512291,0.0003322577,0.00022069293,0.00005321032,0.00008224705,0.00033010132,0.0000017064954],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008021169,0.00056271884,0.0040837307,0.0012690496,0.000026960182,0.0000052136,0.003581811,0.00029573793,0.9028337,0.000015483709,0.00064481585,0.07865961],"study_design_scores_gemma":[0.02304838,0.004062027,0.5224463,0.009904385,0.00029315188,0.000030440015,0.0019488432,0.14635096,0.28508607,0.00024310917,0.0057356367,0.000850679],"about_ca_topic_score_codex":0.00013334004,"about_ca_topic_score_gemma":0.000008153581,"teacher_disagreement_score":0.6177476,"about_ca_system_score_codex":0.00016017588,"about_ca_system_score_gemma":0.0004383833,"threshold_uncertainty_score":0.5744032},"labels":[],"label_agreement":null},{"id":"W2943568147","doi":"","title":"Pondération dynamique en apprentissage multi-vues pour des applications radiomics","year":2018,"lang":"fr","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Radiomics; Computer science; Artificial intelligence; Random forest; Personalization; Voting; Machine learning; Classifier (UML)","score_opus":0.013628284281500537,"score_gpt":0.27135537516024727,"score_spread":0.25772709087874673,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2943568147","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06246909,0.0045384215,0.8859859,0.016897589,0.0007225781,0.0015077842,0.00010781877,0.00039527635,0.027375558],"genre_scores_gemma":[0.4034275,0.0057315473,0.5237064,0.0003002548,0.00066699873,0.0004858523,0.002562925,0.00023006494,0.06288848],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9879997,0.007679442,0.0012446092,0.0014875128,0.0006690892,0.00091967493],"domain_scores_gemma":[0.98999023,0.0027798736,0.0009339574,0.0027641642,0.0027825418,0.0007492558],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.010627799,0.0007528883,0.0008958627,0.00039418053,0.0009740386,0.0005674083,0.0015955048,0.0007753652,0.00070289284],"category_scores_gemma":[0.005404686,0.00083106937,0.0004731388,0.00065879175,0.0015025267,0.00027296104,0.0012323878,0.002065477,0.0004749679],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000078161494,0.004625965,0.02482273,0.002543954,0.00096303667,0.0000697154,0.029951181,0.0008781261,0.041729968,0.21516915,0.0042616096,0.67490643],"study_design_scores_gemma":[0.0031630683,0.000003467688,0.026934458,0.009618856,0.00069600804,0.00030825307,0.00083278085,0.8212552,0.021589456,0.009918555,0.10431473,0.0013651754],"about_ca_topic_score_codex":0.0013524385,"about_ca_topic_score_gemma":0.0007858967,"teacher_disagreement_score":0.82037705,"about_ca_system_score_codex":0.00076370686,"about_ca_system_score_gemma":0.0008121739,"threshold_uncertainty_score":0.999414},"labels":[],"label_agreement":null},{"id":"W2943578454","doi":"10.18383/j.tom.2018.00026","title":"[18F] FDG Positron Emission Tomography (PET) Tumor and Penumbra Imaging Features Predict Recurrence in Non–Small Cell Lung Cancer","year":2019,"lang":"en","type":"article","venue":"Tomography","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Cancer Institute; Natural Sciences and Engineering Research Council of Canada; Carestream Health","keywords":"Positron emission tomography; Lung cancer; Penumbra; Medicine; Nuclear medicine; Brain positron emission tomography; Positron emission; Radiology; Preclinical imaging; Pathology; Internal medicine; Biology","score_opus":0.0027213513204185458,"score_gpt":0.2468464905776685,"score_spread":0.24412513925724996,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2943578454","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98211795,0.009820262,0.00009637885,0.0011828917,0.00045008954,0.0007768731,0.000012239426,0.00010918908,0.005434152],"genre_scores_gemma":[0.99601793,0.00061945885,0.0015766069,0.0010520717,0.00017826636,0.000049125043,0.00003251349,0.000052777308,0.00042126025],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99794024,0.000078620906,0.00035939683,0.0006605175,0.00037771426,0.00058348547],"domain_scores_gemma":[0.9989312,0.000103529965,0.0001534539,0.0003818126,0.0000671187,0.0003628462],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00044789058,0.0003265977,0.0004856933,0.00075538404,0.000099638964,0.0000878786,0.0002231536,0.000055611083,0.00012825223],"category_scores_gemma":[0.00005036312,0.0002810525,0.00019924506,0.00086341356,0.00014105244,0.0001668989,0.000114269365,0.0010039017,0.0000041771295],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001262901,0.00011191019,0.9704315,0.00055777834,0.000036750247,0.00018716748,0.00040719932,0.000017768401,0.015878767,0.0000124067965,0.0039994996,0.008232983],"study_design_scores_gemma":[0.003233279,0.00017287135,0.9722405,0.0021476191,0.00019273254,0.00025650894,0.0001986361,0.016330747,0.00209886,0.00008314767,0.0025788303,0.00046627707],"about_ca_topic_score_codex":0.000620508,"about_ca_topic_score_gemma":0.0000131723145,"teacher_disagreement_score":0.01631298,"about_ca_system_score_codex":0.000044589415,"about_ca_system_score_gemma":0.00008590615,"threshold_uncertainty_score":0.9999642},"labels":[],"label_agreement":null},{"id":"W2944104881","doi":"10.1161/str.48.suppl_1.tp245","title":"Abstract TP245: Prediction of Hemorrhagic Transformation in Patients With Acute Ischaemic Stroke and Atrial Fibrillation With Ct Perfusion Aspects Scores","year":2017,"lang":"en","type":"article","venue":"Stroke","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Medicine; Atrial fibrillation; Cardiology; Stroke (engine); Internal medicine; Perfusion scanning; Receiver operating characteristic; Perfusion; Infarction; Logistic regression; Acute stroke; Area under the curve; Radiology; Myocardial infarction; Tissue plasminogen activator","score_opus":0.006659888045837248,"score_gpt":0.24612801026929096,"score_spread":0.2394681222234537,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2944104881","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9963575,0.000048331265,0.00031872402,0.00041668653,0.00010262905,0.00043542642,0.00005021849,0.000021895956,0.0022485917],"genre_scores_gemma":[0.99894786,0.000060110262,0.0006093679,0.00001184263,0.00018084326,0.0000017249091,0.00009248594,0.000015949974,0.00007981634],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9990365,0.000015419246,0.00023816328,0.00018664647,0.00036551536,0.0001577632],"domain_scores_gemma":[0.9993993,0.000024779496,0.00022203852,0.00020599701,0.0000667921,0.00008109022],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017226742,0.00012614194,0.00024971514,0.00013495702,0.00013195073,0.000036580746,0.000056248962,0.000043040836,0.000023567916],"category_scores_gemma":[0.000063493106,0.00008890702,0.000041851083,0.00003850469,0.00012255336,0.00032512666,0.000015524924,0.00024795468,0.0000012925005],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015719617,0.000020816311,0.9445623,0.000106242594,0.000058808666,0.000018697427,0.00032754033,0.00025112947,0.0027708048,0.000028049266,0.000012918467,0.050270732],"study_design_scores_gemma":[0.0074757896,0.0008335678,0.9819912,0.00034796575,0.00013417173,0.000034233384,0.000048472975,0.008081619,0.0008633914,0.000012654227,0.00009522119,0.0000817543],"about_ca_topic_score_codex":0.00018340416,"about_ca_topic_score_gemma":0.000027206659,"teacher_disagreement_score":0.050188977,"about_ca_system_score_codex":0.00004065899,"about_ca_system_score_gemma":0.000061252074,"threshold_uncertainty_score":0.36255231},"labels":[],"label_agreement":null},{"id":"W2944900917","doi":"10.1016/s0167-8140(19)31153-3","title":"PO-0733 Non-invasive imaging for tumor hypoxia: a novel validated CT and FDG-PET-based Radiomic signature.","year":2019,"lang":"en","type":"article","venue":"Radiotherapy and Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre","funders":"","keywords":"Signature (topology); Medicine; Hypoxia (environmental); Nuclear medicine; Pet imaging; Radiology; Positron emission tomography; Chemistry; Oxygen","score_opus":0.00861927694884308,"score_gpt":0.2929993021061408,"score_spread":0.2843800251572977,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2944900917","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9602871,0.003704464,0.023641601,0.009913987,0.0006111197,0.0012738999,0.000020553565,0.00009137196,0.00045590242],"genre_scores_gemma":[0.9515458,0.0004445865,0.03137138,0.01565555,0.00041532176,0.00006108774,0.00005393986,0.00008259793,0.00036975637],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984021,0.00007139602,0.00033574353,0.0005614316,0.00015165447,0.0004776607],"domain_scores_gemma":[0.9984057,0.0008250564,0.00017215009,0.0002523901,0.00007020437,0.0002745163],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00057281,0.00028939,0.00077843183,0.00022539808,0.00013773584,0.000044462642,0.00011729705,0.00007029362,0.000102261016],"category_scores_gemma":[0.00018421275,0.0002436515,0.00012624143,0.00014504208,0.0002545764,0.000084752246,0.000022801489,0.0005206159,0.0000041242],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0020765632,0.0005082281,0.038697086,0.0006482042,0.00045526747,0.00079784205,0.00062926917,0.00015956975,0.8793849,0.00043683616,0.0053534587,0.070852794],"study_design_scores_gemma":[0.09281715,0.0061400905,0.031057637,0.0008700394,0.0007540609,0.014854313,0.00061874726,0.52035683,0.029601298,0.00052940706,0.30078772,0.0016126864],"about_ca_topic_score_codex":0.00006004439,"about_ca_topic_score_gemma":0.000006234327,"teacher_disagreement_score":0.8497836,"about_ca_system_score_codex":0.0002576853,"about_ca_system_score_gemma":0.00038819804,"threshold_uncertainty_score":0.993582},"labels":[],"label_agreement":null},{"id":"W2945281393","doi":"10.1007/s11548-019-02000-5","title":"IJCARS—IPCAI 2019 special issue: conference information processing for computer-assisted interventions, 10th international conference 2019—part 1","year":2019,"lang":"en","type":"editorial","venue":"International Journal of Computer Assisted Radiology and Surgery","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Health informatics; Psychological intervention; Multimedia; Medical education; Medicine; Nursing; Public health","score_opus":0.022465404691079383,"score_gpt":0.32613673209514554,"score_spread":0.30367132740406616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2945281393","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016589469,0.0007632833,0.18844259,0.007081805,0.8006909,0.0004066539,0.00030083087,0.00005015854,0.00060486275],"genre_scores_gemma":[0.004500296,0.0029437519,0.021764273,0.0015204533,0.9622451,0.000018801673,0.005322027,0.00006685062,0.0016184667],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99565583,0.00026359348,0.0021379918,0.0004269486,0.0011353379,0.0003802692],"domain_scores_gemma":[0.99140835,0.0018169422,0.0025077118,0.00022256926,0.00378951,0.000254931],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0018086103,0.00047164594,0.0014954444,0.0011567876,0.00012560561,0.00048991153,0.0007303358,0.00076847157,0.000343672],"category_scores_gemma":[0.0010128784,0.00041613975,0.00081285613,0.00011734931,0.0002989654,0.00077272585,0.00020500852,0.0017352079,0.000026302712],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008038544,0.00016665732,0.0007862623,0.00029276885,0.0011197571,0.00010269308,0.00016071933,0.00006558278,0.00001224099,0.000067334855,0.77431685,0.22210526],"study_design_scores_gemma":[0.0031340704,0.00041790516,0.0048099137,0.0042565875,0.00032421734,0.0022263255,0.00003848249,0.025150971,0.0000041329326,0.00008009038,0.95916253,0.00039475987],"about_ca_topic_score_codex":0.000016082622,"about_ca_topic_score_gemma":0.000002401263,"teacher_disagreement_score":0.2217105,"about_ca_system_score_codex":0.00030066248,"about_ca_system_score_gemma":0.0014661546,"threshold_uncertainty_score":0.99982905},"labels":[],"label_agreement":null},{"id":"W2945306163","doi":"10.1016/s0167-8140(19)30794-7","title":"OC-0374 GWAS identifies new susceptibility loci for late toxicity following prostate cancer radiotherapy","year":2019,"lang":"en","type":"article","venue":"Radiotherapy and Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Prostate cancer; Oncology; Medicine; Internal medicine; Cancer","score_opus":0.013293521266556372,"score_gpt":0.34413222509044217,"score_spread":0.3308387038238858,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2945306163","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96393,0.010438147,0.005884142,0.016859151,0.0011246046,0.0013403388,0.000008061576,0.00010535676,0.0003101827],"genre_scores_gemma":[0.90038276,0.012062315,0.025273856,0.019872144,0.0022409149,0.00015121211,0.000058269943,0.00017698678,0.039781526],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982201,0.00011501407,0.00039714167,0.00056552707,0.00019720267,0.0005050264],"domain_scores_gemma":[0.99889517,0.00029611087,0.00015204777,0.00030933646,0.00005161778,0.00029571366],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007787116,0.000261086,0.00081619556,0.00011274742,0.00014941003,0.00004850669,0.00013273231,0.00023171744,0.00052060926],"category_scores_gemma":[0.00007866891,0.00021658035,0.00025235597,0.00014623013,0.00015653373,0.0001332748,0.0000209071,0.00040796312,0.0000039303113],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002442628,0.0003105387,0.21011809,0.00047219,0.0009793747,0.000060203598,0.0064484035,0.0004248347,0.29048625,0.0003042276,0.011443758,0.4765095],"study_design_scores_gemma":[0.028478615,0.0042421464,0.039088495,0.00027516505,0.00032118673,0.0001602446,0.0003236976,0.05630943,0.003687418,0.0016090154,0.86467475,0.00082985533],"about_ca_topic_score_codex":0.00069123047,"about_ca_topic_score_gemma":0.00016165031,"teacher_disagreement_score":0.85323095,"about_ca_system_score_codex":0.0005293033,"about_ca_system_score_gemma":0.00040204191,"threshold_uncertainty_score":0.883189},"labels":[],"label_agreement":null},{"id":"W2945521800","doi":"10.1016/s0167-8140(19)30431-1","title":"SP-0011 Unified Radiogenomic Prediction of Late Radiotherapy Toxicities","year":2019,"lang":"en","type":"article","venue":"Radiotherapy and Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Radiation therapy; Medicine; Radiology","score_opus":0.011723162960766878,"score_gpt":0.2851383697724851,"score_spread":0.2734152068117182,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2945521800","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9841236,0.0061411094,0.0027972644,0.0024987771,0.0006112671,0.00045623435,0.000009748483,0.0000721082,0.0032899035],"genre_scores_gemma":[0.97081745,0.01263047,0.009475507,0.0029060955,0.0005554899,0.0000136794015,0.000029042241,0.000064256834,0.0035080381],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987443,0.00012461073,0.00038582526,0.0003036953,0.00016000791,0.000281532],"domain_scores_gemma":[0.9992037,0.00017902903,0.00016215134,0.0002627211,0.00004049647,0.00015189976],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047403265,0.00018239916,0.0006737134,0.00020013712,0.00006146342,0.000011612787,0.000098700046,0.00021134605,0.0006386313],"category_scores_gemma":[0.000027006034,0.00015465647,0.0001117823,0.00013383162,0.00027458766,0.00006946395,0.000013291424,0.00034152844,0.0000056286935],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018005366,0.0003449256,0.16259602,0.00030290597,0.00071038114,0.000058113506,0.003467028,0.00040035154,0.6604194,0.0035827963,0.0018088712,0.16450866],"study_design_scores_gemma":[0.027172323,0.010052037,0.19594589,0.00030840482,0.00026480015,0.0014973659,0.00052580994,0.09743052,0.00702909,0.00085505174,0.65832365,0.0005950492],"about_ca_topic_score_codex":0.000063836065,"about_ca_topic_score_gemma":0.0000024214362,"teacher_disagreement_score":0.6565148,"about_ca_system_score_codex":0.00028443846,"about_ca_system_score_gemma":0.00016014432,"threshold_uncertainty_score":0.6992565},"labels":[],"label_agreement":null},{"id":"W2945596785","doi":"","title":"Accurate characterization of in vivo bone deposition and b-TCP scaffold resorption using X-ray micro-computed tomography and image processing","year":2016,"lang":"en","type":"article","venue":"Knowledge UdeS (Institutional Deposit of the University of Sherbrooke)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Characterization (materials science); X-ray microtomography; Deposition (geology); In vivo; Materials science; X-ray; Computed tomography; Biomedical engineering; Resorption; Tomography; Nuclear medicine; Computer science; Medicine; Radiology; Optics; Pathology; Nanotechnology; Geology; Physics; Biology","score_opus":0.008643613301768152,"score_gpt":0.2205634343715491,"score_spread":0.21191982106978094,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2945596785","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9099996,0.00080387376,0.08860274,0.00019687066,0.00004830927,0.00016885226,0.00000461889,0.000010795913,0.00016430648],"genre_scores_gemma":[0.9883605,0.00025826506,0.011289003,0.000012476146,0.000022888004,1.4923381e-7,0.00000419886,0.0000061756514,0.000046301036],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9993092,0.000055162753,0.00021737878,0.00017086047,0.00014616565,0.00010125117],"domain_scores_gemma":[0.99956334,0.000025690682,0.00014230523,0.00009519185,0.000118673546,0.00005482754],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016695324,0.000097640564,0.00023251688,0.00022339278,0.0001295587,0.000007645377,0.00008008882,0.000069437905,0.000004529689],"category_scores_gemma":[0.000034952147,0.00007563354,0.00006240539,0.00023562026,0.00054953754,0.0002458116,0.00008626966,0.00008580011,2.2950563e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018953317,0.00011417126,0.030536197,0.0013937587,0.000028100394,0.0000063602565,0.0007403527,0.000143931,0.9608709,0.0001221967,0.000005750809,0.0058487267],"study_design_scores_gemma":[0.002329173,0.0000800454,0.5929847,0.010674843,0.000162039,0.000098154924,0.00005024761,0.084342435,0.30895266,0.000041290594,0.00015570593,0.00012874842],"about_ca_topic_score_codex":0.0001477464,"about_ca_topic_score_gemma":0.00006682588,"teacher_disagreement_score":0.65191823,"about_ca_system_score_codex":0.00013883847,"about_ca_system_score_gemma":0.000059689308,"threshold_uncertainty_score":0.30842465},"labels":[],"label_agreement":null},{"id":"W2946086971","doi":"10.3389/fonc.2019.00374","title":"Radiomics in Glioblastoma: Current Status and Challenges Facing Clinical Implementation","year":2019,"lang":"en","type":"review","venue":"Frontiers in Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":190,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre; McGill University","funders":"","keywords":"Radiomics; Computer science; Segmentation; Glioblastoma; Medical imaging; Redundancy (engineering); Data extraction; Artificial intelligence; Feature extraction; Medical physics; Data mining; Medicine; Machine learning; MEDLINE","score_opus":0.09798999134276305,"score_gpt":0.47325028508889955,"score_spread":0.3752602937461365,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2946086971","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00054569816,0.99297786,0.00029331396,0.0005017825,0.0043158582,0.0010973096,0.000009184098,0.000021961952,0.00023703386],"genre_scores_gemma":[0.000033958768,0.9959149,0.0033643602,0.00010128365,0.00036556763,0.00006625002,0.000075882235,0.000051632967,0.00002619082],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9967161,0.0006551193,0.0012642862,0.0006433131,0.00017310075,0.0005480878],"domain_scores_gemma":[0.99865043,0.00042106243,0.00043491178,0.00025942625,0.000022712406,0.00021146557],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0015777971,0.00032697932,0.0029091104,0.0007876876,0.000023674946,0.0000131909,0.00013596924,0.00049529236,0.000016902992],"category_scores_gemma":[0.00038028316,0.00028693074,0.00021404907,0.00022376042,0.00017084806,0.000054177293,0.0001260242,0.00200889,0.000009169943],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000047648144,0.00012733592,0.010042588,0.008291012,0.000083387036,0.0000863964,0.00028820077,0.0000010560199,2.6685452e-8,0.00005832488,0.0022167594,0.97875726],"study_design_scores_gemma":[0.0029405183,0.0005553032,0.00087754044,0.004120363,0.00038969066,0.00009273022,0.00044297078,0.00050448376,2.6256236e-8,0.00006862425,0.98978233,0.00022541732],"about_ca_topic_score_codex":0.000029924595,"about_ca_topic_score_gemma":0.000054584754,"teacher_disagreement_score":0.9875656,"about_ca_system_score_codex":0.00095942226,"about_ca_system_score_gemma":0.000912531,"threshold_uncertainty_score":0.9999583},"labels":[],"label_agreement":null},{"id":"W2946182886","doi":"10.1136/gutjnl-2018-316407","title":"Early evaluation using a radiomic signature of unresectable hepatic metastases to predict outcome in patients with colorectal cancer treated with FOLFIRI and bevacizumab","year":2019,"lang":"en","type":"article","venue":"Gut","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":138,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre","funders":"","keywords":"FOLFIRI; Bevacizumab; Medicine; Colorectal cancer; Internal medicine; Oncology; Signature (topology); Cancer; Radiology; Gastroenterology; Chemotherapy; Oxaliplatin","score_opus":0.011104749878831454,"score_gpt":0.2917095296524945,"score_spread":0.28060477977366305,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2946182886","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9982222,0.0001977713,0.00012024869,0.00009118169,0.000041663858,0.0012204126,0.000020116786,0.000015219574,0.00007119341],"genre_scores_gemma":[0.99840474,0.0000035565415,0.0013608721,0.000083280924,0.000017887167,0.000028543764,0.000036527388,0.000025426105,0.0000391403],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99876434,0.00007935277,0.00022622844,0.00025098925,0.000471521,0.00020756423],"domain_scores_gemma":[0.9994361,0.00006419394,0.00010710769,0.00013800604,0.00014405895,0.000110562185],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030166187,0.0001407342,0.0004004695,0.00020458,0.000026442216,0.000014633977,0.000050506438,0.0000505974,0.000060232407],"category_scores_gemma":[0.00014187032,0.00009341303,0.00002243335,0.00033312946,0.000046512778,0.00009355883,0.000021623902,0.00021402982,0.000001383545],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016014404,0.00008447489,0.9879504,0.00009915616,0.00010853407,0.000006778929,0.0003754538,0.002881498,0.0046783895,0.0000023228904,0.0000130542385,0.0021985099],"study_design_scores_gemma":[0.008768982,0.0013931374,0.9238072,0.00048691887,0.00032844846,0.0000075801704,0.000037491507,0.064644344,0.0003953789,0.000004018019,0.000012083969,0.000114408576],"about_ca_topic_score_codex":0.0017992731,"about_ca_topic_score_gemma":0.00006986975,"teacher_disagreement_score":0.06414317,"about_ca_system_score_codex":0.00016881344,"about_ca_system_score_gemma":0.00014766285,"threshold_uncertainty_score":0.3809273},"labels":[],"label_agreement":null},{"id":"W2946893408","doi":"10.1007/s11255-019-02178-2","title":"Correction to: The clinical utility of prostate cancer heterogeneity using texture analysis of multiparametric MRI","year":2019,"lang":"en","type":"erratum","venue":"International Urology and Nephrology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network","funders":"","keywords":"Medicine; Multiparametric MRI; Prostate cancer; Nephrology; Internal medicine; Prostate; Texture (cosmology); Medical physics; Oncology; Cancer; Radiology; Artificial intelligence","score_opus":0.025959430712591203,"score_gpt":0.3848303461040629,"score_spread":0.3588709153914717,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2946893408","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92624897,0.0038058304,0.0037267916,0.012722669,0.05120868,0.000673263,0.00020085837,0.000019911467,0.0013930234],"genre_scores_gemma":[0.9872335,0.0017515295,0.00023500815,0.0059523196,0.00084987475,0.000013720718,0.00022603698,0.000018393508,0.0037196064],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99810874,0.00031348254,0.00068959675,0.00045376184,0.00024410599,0.00019029882],"domain_scores_gemma":[0.99798185,0.0007452888,0.0005742703,0.0003030244,0.00031444166,0.00008115021],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009128219,0.00017772379,0.00095179805,0.00065773295,0.000041546013,0.0000052898436,0.00022800291,0.00052364083,0.00019755583],"category_scores_gemma":[0.0012213474,0.00012584851,0.00030661759,0.00048018488,0.00046267206,0.000021371765,0.00015381972,0.0015032284,0.0000024086646],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001547954,0.00020281451,0.7408479,0.00006022243,0.0069343476,0.000014578493,0.00017016975,0.004134573,0.00013398322,0.00003107974,0.22804151,0.017880885],"study_design_scores_gemma":[0.00045594567,0.0002636007,0.43607387,0.000023043498,0.002099096,0.00004582875,0.0000062432723,0.4092605,0.0000069386765,0.000016779451,0.15168163,0.000066512315],"about_ca_topic_score_codex":0.00086119346,"about_ca_topic_score_gemma":0.000376414,"teacher_disagreement_score":0.40512592,"about_ca_system_score_codex":0.000026983564,"about_ca_system_score_gemma":0.00022204031,"threshold_uncertainty_score":0.6530863},"labels":[],"label_agreement":null},{"id":"W2947071545","doi":"10.1200/jco.2019.37.15_suppl.e18096","title":"Generating real-world evidence: Using automated data extraction to replace manual chart review.","year":2019,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Roche (Canada); Princess Margaret Cancer Centre; University of Toronto; University Health Network","funders":"","keywords":"Medicine; Data extraction; Medical record; Clinical trial; Lung cancer; Cancer; MEDLINE; Internal medicine; Intensive care medicine","score_opus":0.25496319891806163,"score_gpt":0.6008652848898383,"score_spread":0.34590208597177663,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2947071545","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9404155,0.002671642,0.0014586322,0.047911085,0.004743379,0.00047629818,0.0000020080322,0.00006570965,0.0022557455],"genre_scores_gemma":[0.5105413,0.034410406,0.34902254,0.08610604,0.013457843,0.0000045420425,0.000040339084,0.0001172044,0.006299751],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9954269,0.00070760545,0.0027101838,0.0003503943,0.00054816867,0.00025676363],"domain_scores_gemma":[0.9941992,0.002208248,0.0020449301,0.0006299045,0.00039762605,0.0005200538],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.014941928,0.00013691872,0.001473815,0.0001686929,0.000053543907,0.000019366073,0.00037122006,0.00017962653,0.0003533532],"category_scores_gemma":[0.02353619,0.00010123796,0.00021777324,0.00027834816,0.00006296164,0.00034383644,0.00018497343,0.0017146659,0.000082396495],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0027598087,0.0009361392,0.15593933,0.001117125,0.00053848926,0.0017274143,0.00011983885,0.0017378984,0.023047138,0.00005841351,0.402748,0.40927044],"study_design_scores_gemma":[0.0035366442,0.004338375,0.07074504,0.010347668,0.0009385188,0.0026213839,0.000069429196,0.5050103,0.00005175074,0.000015431151,0.40208736,0.0002380854],"about_ca_topic_score_codex":0.000085469146,"about_ca_topic_score_gemma":0.000013554242,"teacher_disagreement_score":0.5032724,"about_ca_system_score_codex":0.00021112089,"about_ca_system_score_gemma":0.0013833215,"threshold_uncertainty_score":0.984689},"labels":[],"label_agreement":null},{"id":"W2947287592","doi":"10.1200/jco.2019.37.15_suppl.3561","title":"Utilization and reach of the Fight Colorectal Cancer Late Stage MSS CRC Clinical Trial Finder.","year":2019,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Medicine; Clinical trial; Colorectal cancer; Cancer; Stage (stratigraphy); Oncology; Internal medicine","score_opus":0.1663466852735201,"score_gpt":0.5275581294484417,"score_spread":0.3612114441749216,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2947287592","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9794995,0.00043185268,0.000081029575,0.013040696,0.0044752797,0.00040029243,0.000003084209,0.0000050991803,0.0020631363],"genre_scores_gemma":[0.99020696,0.002109546,0.00073992147,0.0034999393,0.0015452921,0.0000028897412,0.0000016242278,0.000016227126,0.0018776169],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99588114,0.0008571301,0.002503075,0.00018731072,0.00039956742,0.0001717565],"domain_scores_gemma":[0.9939149,0.0031912744,0.0021801903,0.00017166196,0.00028696744,0.00025502016],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00651961,0.000106233485,0.0013311177,0.000057284426,0.000036366895,0.000008155188,0.00018814193,0.00040727603,0.00034222216],"category_scores_gemma":[0.010352555,0.000059498823,0.0004589128,0.00011904035,0.00037241206,0.00006525782,0.00008850407,0.0018308742,0.0000039658407],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.03923713,0.0012052252,0.6351526,0.000076222736,0.00041163975,0.00007189151,0.0001306934,0.00010030541,0.00036975383,0.00022015821,0.0074171275,0.31560728],"study_design_scores_gemma":[0.0825749,0.012090654,0.6390816,0.00025923495,0.00047252138,0.000077700075,0.000061853665,0.009086396,0.00009803093,0.00021065758,0.25588194,0.00010452899],"about_ca_topic_score_codex":0.000027771921,"about_ca_topic_score_gemma":0.000015312831,"teacher_disagreement_score":0.31550273,"about_ca_system_score_codex":0.000052257798,"about_ca_system_score_gemma":0.0013843126,"threshold_uncertainty_score":0.9979837},"labels":[],"label_agreement":null},{"id":"W2949977288","doi":"10.1007/s00261-019-02089-x","title":"The use of PET/MRI for imaging rectal cancer","year":2019,"lang":"en","type":"review","venue":"Abdominal Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":31,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"National Cancer Institute","keywords":"Medicine; Colorectal cancer; Correction for attenuation; Radiology; Hepatology; Positron emission tomography; Magnetic resonance imaging; Cancer; Pelvis; Nuclear medicine; Internal medicine","score_opus":0.07413345802603809,"score_gpt":0.40437132919660623,"score_spread":0.33023787117056813,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2949977288","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000040285962,0.99425644,0.0015139774,0.0012321507,0.0014811723,0.0012340273,0.00003269287,0.000021184274,0.00018807533],"genre_scores_gemma":[0.000016718694,0.9930105,0.0034976501,0.00034826435,0.0007610776,0.00021165909,0.000076856915,0.000078999714,0.001998229],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99799997,0.0002265478,0.0007270794,0.000423812,0.00015427264,0.00046831992],"domain_scores_gemma":[0.99537325,0.0033548889,0.00055505056,0.0004860153,0.00011431263,0.00011647185],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006779737,0.00032741483,0.0021042586,0.00013906814,0.000115934374,0.000022290056,0.0002874611,0.00013269148,0.00004650618],"category_scores_gemma":[0.0014622653,0.00019080006,0.0007514262,0.00012901104,0.0004097208,0.000037497997,0.00007227053,0.0007740645,0.000014341797],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011589554,0.000015822567,0.000080767255,0.005877692,0.00034876386,0.00004988559,0.000022860315,0.000007759363,0.000007040349,0.0002629894,0.019758277,0.97345227],"study_design_scores_gemma":[0.00058419624,0.00013367241,0.000015296528,0.004361822,0.002008184,0.0029095046,0.000010687716,0.003756761,7.6538123e-7,0.000025881667,0.98601794,0.00017525633],"about_ca_topic_score_codex":0.00011193101,"about_ca_topic_score_gemma":0.0000038946005,"teacher_disagreement_score":0.973277,"about_ca_system_score_codex":0.00013754395,"about_ca_system_score_gemma":0.00059692346,"threshold_uncertainty_score":0.7780601},"labels":[],"label_agreement":null},{"id":"W2951883912","doi":"10.1053/j.semnuclmed.2019.06.005","title":"Radiomics Analysis for Clinical Decision Support in Nuclear Medicine","year":2019,"lang":"en","type":"review","venue":"Seminars in Nuclear Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":58,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Radiomics; Medicine; Workflow; Standardization; Decision support system; Clinical decision support system; Medical imaging; Medical physics; Personalized medicine; Precision medicine; Decision analysis; Artificial intelligence; Bioinformatics; Computer science; Pathology; Radiology","score_opus":0.06988569294152833,"score_gpt":0.4473506359476946,"score_spread":0.3774649430061663,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2951883912","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00041660754,0.9852506,0.00029686792,0.004662929,0.002342708,0.002745836,0.000025152955,0.00012554238,0.0041337647],"genre_scores_gemma":[0.00011944939,0.9867552,0.0056086597,0.0035743257,0.0018824227,0.00004081523,0.00066004845,0.0003826342,0.00097642356],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9912507,0.0004613807,0.0043049734,0.0017501687,0.001166684,0.0010660829],"domain_scores_gemma":[0.99257344,0.003703487,0.0011662828,0.0016735732,0.00015717388,0.00072605396],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.008192899,0.0010296768,0.009718036,0.0035478068,0.00009665832,0.000023922135,0.00096516445,0.0013051103,0.0019895902],"category_scores_gemma":[0.008595433,0.0007447851,0.0014726368,0.0032079332,0.0010134128,0.00010186682,0.00027462884,0.0035072886,0.00018426971],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035019335,0.00025597797,0.0015217795,0.007831925,0.0008935386,0.00055785244,0.00057689415,0.000010928715,0.0000014036378,0.0002491441,0.08925353,0.8984968],"study_design_scores_gemma":[0.00612971,0.001706381,0.00046819207,0.05521782,0.009066031,0.00031771706,0.00031234347,0.0062907087,1.3795056e-8,0.00010233783,0.9198277,0.00056104065],"about_ca_topic_score_codex":0.00014496299,"about_ca_topic_score_gemma":0.000018558865,"teacher_disagreement_score":0.8979358,"about_ca_system_score_codex":0.0006840107,"about_ca_system_score_gemma":0.00039436202,"threshold_uncertainty_score":0.9999914},"labels":[],"label_agreement":null},{"id":"W2953216366","doi":"10.1007/s00259-019-04382-9","title":"Why imaging data alone is not enough: AI-based integration of imaging, omics, and clinical data","year":2019,"lang":"en","type":"review","venue":"European Journal of Nuclear Medicine and Molecular Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":140,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; Krembil Foundation; University of Toronto; University Health Network","funders":"","keywords":"Computer science; Radiomics; Artificial intelligence; Data science; Domain (mathematical analysis); Machine learning; Quality (philosophy); Data quality; Data mining","score_opus":0.10168172379972272,"score_gpt":0.4105108725437765,"score_spread":0.30882914874405376,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2953216366","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00005883264,0.9410837,0.013078616,0.043790884,0.00075797417,0.0004131203,0.0000816754,0.00003058911,0.0007045506],"genre_scores_gemma":[0.0012516088,0.9359344,0.010105214,0.050764732,0.0010756835,2.5082912e-7,0.0005700783,0.00028279237,0.000015227404],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9942898,0.0010561395,0.002494894,0.000968977,0.000788325,0.00040186007],"domain_scores_gemma":[0.99464357,0.00038007624,0.0020551041,0.0020467099,0.0003542383,0.0005202813],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0064398013,0.0005995697,0.0028250886,0.0006899511,0.000098295815,0.00011729459,0.0013654173,0.00006514726,0.000057546702],"category_scores_gemma":[0.0029732129,0.0004417147,0.0003178039,0.00025301825,0.00087253645,0.00043547357,0.0011234866,0.0024354681,0.000009290543],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007243745,0.00008553773,0.00024190279,0.003162403,0.00033905412,0.00205604,0.00016977818,2.9189448e-7,0.00030886094,0.000015017398,0.1150884,0.8784603],"study_design_scores_gemma":[0.003121566,0.00021682034,0.00007014015,0.02624933,0.005091082,0.003193237,0.00019463587,0.022639105,0.0000036979502,0.000005037898,0.9388787,0.00033664284],"about_ca_topic_score_codex":0.00004997371,"about_ca_topic_score_gemma":2.6559744e-7,"teacher_disagreement_score":0.87812364,"about_ca_system_score_codex":0.000046496447,"about_ca_system_score_gemma":0.00034800926,"threshold_uncertainty_score":0.99986595},"labels":[],"label_agreement":null},{"id":"W2953430427","doi":"10.1016/j.phro.2019.05.001","title":"Automatic recognition and analysis of metal streak artifacts in head and neck computed tomography for radiomics modeling","year":2019,"lang":"en","type":"article","venue":"Physics and Imaging in Radiation Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre","funders":"National Cancer Institute; National Institutes of Health","keywords":"Streak; Radiomics; Artifact (error); Artificial intelligence; Receiver operating characteristic; Random forest; Computer science; Hough transform; Computed tomography; Test set; Pattern recognition (psychology); Data set; Computer vision; Radiology; Medicine; Machine learning; Image (mathematics)","score_opus":0.020455605873936824,"score_gpt":0.3167414912519355,"score_spread":0.2962858853779987,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2953430427","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98983955,0.000500051,0.008617368,0.00059766066,0.000059089485,0.00030161545,0.0000096920585,0.000012254374,0.000062713356],"genre_scores_gemma":[0.99245226,0.0001844256,0.006934064,0.00023322445,0.000030499732,0.000011389335,0.0001424897,0.00001033339,0.0000013165957],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991937,0.00005096222,0.00031254438,0.00022349576,0.00007133616,0.00014790965],"domain_scores_gemma":[0.99947375,0.00022012778,0.00012481373,0.000074958996,0.00004410014,0.00006225547],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033594045,0.0000968469,0.00047769235,0.00045870262,0.000023218849,0.000015842876,0.000022298776,0.000042025604,0.0000034883333],"category_scores_gemma":[0.00007263247,0.000096930125,0.000050676575,0.0004008755,0.00005654903,0.00011601571,0.000018174642,0.00014477487,2.1356988e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005527834,0.00012329008,0.5063909,0.00016252331,0.00015029593,0.0000023382395,0.00082035305,0.006875455,0.0017668694,0.00019051114,0.0000039192637,0.48345825],"study_design_scores_gemma":[0.0022620114,0.00010242295,0.18230826,0.000069708876,0.000254069,0.000006270709,0.00008060076,0.8132112,0.000037090373,0.0015685395,0.00002738747,0.000072414725],"about_ca_topic_score_codex":0.00016458039,"about_ca_topic_score_gemma":0.000016386546,"teacher_disagreement_score":0.80633575,"about_ca_system_score_codex":0.00004449227,"about_ca_system_score_gemma":0.000040647563,"threshold_uncertainty_score":0.39526957},"labels":[],"label_agreement":null},{"id":"W2953494215","doi":"","title":"Radiolabeled Bombesin Analogs to Improve Prostate Cancer Diagnosis by PET Imaging","year":2019,"lang":"en","type":"article","venue":"Knowledge UdeS (Institutional Deposit of the University of Sherbrooke)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Fonds de Recherche du Québec - Santé; Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Université de Sherbrooke","keywords":"Prostate cancer; Medicine; Bombesin; Prostate; Cancer; Internal medicine","score_opus":0.004686694729184059,"score_gpt":0.22239625121220538,"score_spread":0.21770955648302132,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2953494215","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.984224,0.00446939,0.0028471432,0.002352342,0.00047238375,0.0005807038,0.000029121811,0.00003212522,0.0049927807],"genre_scores_gemma":[0.992794,0.000595807,0.0024572886,0.0002141883,0.00004993765,0.000002815427,0.000012397158,0.000014359742,0.0038592054],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9988906,0.00005267262,0.0002144287,0.00029920225,0.000308642,0.00023449308],"domain_scores_gemma":[0.99924356,0.000053796783,0.000089415335,0.0002860834,0.00015524043,0.00017191062],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018820619,0.0001621141,0.00036135493,0.000121328274,0.00018705231,0.000010620976,0.0003525385,0.00004248681,0.00013643802],"category_scores_gemma":[0.00009021577,0.00013807563,0.00019425983,0.00028536865,0.0003181891,0.00012451467,0.00019450793,0.0002733812,0.00003520718],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036024064,0.00043738636,0.5822174,0.0021763751,0.00028568885,0.000034926972,0.002437334,0.0036933408,0.3658238,0.00063053117,0.025356201,0.01654675],"study_design_scores_gemma":[0.009648531,0.000502085,0.4036965,0.012355133,0.001033162,0.00018258949,0.00046295708,0.1356011,0.16019735,0.0001254138,0.27536416,0.00083102664],"about_ca_topic_score_codex":0.002354238,"about_ca_topic_score_gemma":0.0003860627,"teacher_disagreement_score":0.25000796,"about_ca_system_score_codex":0.0006282411,"about_ca_system_score_gemma":0.00019442079,"threshold_uncertainty_score":0.5630561},"labels":[],"label_agreement":null},{"id":"W2954014370","doi":"","title":"Lung cancer detected through CT surveillance of incidental lung nodules","year":2019,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Lung; Lung cancer; Medicine; Radiology; Cancer; Pathology; Nuclear medicine; Internal medicine","score_opus":0.005997088991027615,"score_gpt":0.301398798895382,"score_spread":0.2954017099043544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2954014370","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98452544,0.00040140128,0.0011796149,0.0009116627,0.00033271257,0.0013684648,0.0000038874896,0.00007604882,0.011200743],"genre_scores_gemma":[0.9952251,0.00006865584,0.0019766137,0.0005884331,0.000118505304,0.000073787916,0.000010439259,0.000024303952,0.001914193],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9989881,0.000035487796,0.00026053927,0.00021645411,0.00028596204,0.00021347486],"domain_scores_gemma":[0.9994274,0.000091320326,0.00009981144,0.00023532525,0.00007020299,0.00007596635],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00019242318,0.00011785534,0.00031962857,0.000047309994,0.000027705599,0.000009447098,0.00009968166,0.00003249762,0.0017528805],"category_scores_gemma":[0.00014636772,0.000088861976,0.00008259254,0.00015633623,0.00006580606,0.000072306175,0.000054288754,0.00025769178,0.000017463242],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000056973102,0.00003774594,0.97531515,0.0003253367,0.00008116291,0.000020134095,0.00011778128,0.00008448744,0.017604316,0.00019184966,0.0029688699,0.0031962055],"study_design_scores_gemma":[0.0036642312,0.00009589055,0.8464971,0.0003681407,0.00006648261,0.00012026219,0.000112718175,0.1316628,0.010137374,0.000040840332,0.006979649,0.00025452295],"about_ca_topic_score_codex":0.0018899979,"about_ca_topic_score_gemma":0.000051636805,"teacher_disagreement_score":0.13157831,"about_ca_system_score_codex":0.00006965544,"about_ca_system_score_gemma":0.000077266224,"threshold_uncertainty_score":0.99915963},"labels":[],"label_agreement":null},{"id":"W2954275934","doi":"10.1158/1538-7445.am2019-1184","title":"Abstract 1184: Comprehensive analysis with interactive exploration of immune response signatures in 10,000 tumor samples","year":2019,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mount Sinai Hospital","funders":"","keywords":"Immune system; Tumor microenvironment; Biology; Tumor-infiltrating lymphocytes; Cancer; Epigenetics; Cell type; Cancer research; Immunology; Cell; Immunotherapy; Genetics; Gene","score_opus":0.05782837659817464,"score_gpt":0.41904750903052923,"score_spread":0.3612191324323546,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2954275934","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99625534,0.00079732854,0.000089459914,0.0015313013,0.000039471324,0.00041548954,0.0000123779955,0.000012662053,0.0008465924],"genre_scores_gemma":[0.99860436,0.0001034041,0.00027054,0.000072979565,0.000049128073,0.00005561593,0.00002439666,0.000019979405,0.00079957827],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9982291,0.00028799902,0.0002850859,0.00029093528,0.0006225327,0.00028437667],"domain_scores_gemma":[0.99798274,0.0010158506,0.000107427375,0.00030874752,0.0004887226,0.00009653318],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0011082629,0.00010595125,0.00042648189,0.00086351513,0.00004018356,0.000024598034,0.00013967333,0.000045597415,0.0014741635],"category_scores_gemma":[0.0005346435,0.00007916805,0.00008015126,0.0011790277,0.00019257613,0.00017661929,0.000052431074,0.00090211356,0.000016216603],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.03180594,0.00032223316,0.059014186,0.0004558006,0.0010877106,0.00025731273,0.00479386,0.025933977,0.8664385,0.00008427199,0.0012634994,0.008542677],"study_design_scores_gemma":[0.002877468,0.0007580308,0.95167065,0.0009595491,0.00012227161,0.0000046832915,0.004087923,0.0058631063,0.029053632,0.00008882942,0.0043367282,0.00017711631],"about_ca_topic_score_codex":0.0026638985,"about_ca_topic_score_gemma":0.00009600698,"teacher_disagreement_score":0.8926565,"about_ca_system_score_codex":0.00020510267,"about_ca_system_score_gemma":0.0002909603,"threshold_uncertainty_score":0.99943864},"labels":[],"label_agreement":null},{"id":"W2954503654","doi":"10.1007/s11307-020-01487-8","title":"Next-Generation Radiogenomics Sequencing for Prediction of EGFR and KRAS Mutation Status in NSCLC Patients Using Multimodal Imaging and Machine Learning Algorithms","year":2020,"lang":"en","type":"article","venue":"Molecular Imaging and Biology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":163,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency; University of British Columbia Hospital; University of British Columbia","funders":"Shaheed Rajaei Cardiovascular Medical and Research Center; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Radiogenomics; KRAS; Machine learning; Computer science; Artificial intelligence; Mutation; Algorithm; Radiomics; Biology; Genetics; Gene","score_opus":0.0341848152830091,"score_gpt":0.28360218257359165,"score_spread":0.24941736729058256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2954503654","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8975608,0.0025813042,0.09852718,0.0009194153,0.00007288683,0.00028219618,0.000023768478,0.000023340626,0.000009159827],"genre_scores_gemma":[0.9758544,0.00021402263,0.022870801,0.00062144577,0.000083815525,0.0000058320866,0.00032537853,0.000023408888,9.152618e-7],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99896425,0.00009767643,0.00029777217,0.00034433667,0.00006451844,0.0002314421],"domain_scores_gemma":[0.9995759,0.000053246564,0.00012364202,0.00005360822,0.00006728464,0.00012627765],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025828308,0.00014164599,0.00026934152,0.00013867221,0.000096145915,0.00003190302,0.000024304984,0.00004970733,0.000001088662],"category_scores_gemma":[0.00041085188,0.00013624722,0.000029858475,0.00009195939,0.00013620187,0.00009713383,0.00004374163,0.0002275845,5.433471e-8],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005460778,0.000013997757,0.3813446,0.00008610129,0.000021249905,0.000011939674,0.0007159275,0.0006057943,0.50699514,0.000023233268,0.0000025505378,0.110124886],"study_design_scores_gemma":[0.0029212986,0.00016175154,0.013575461,0.000061550665,0.00007447817,0.000069780894,0.00022244734,0.97877836,0.0038033514,0.00005152206,0.00017189974,0.000108102875],"about_ca_topic_score_codex":0.00036782585,"about_ca_topic_score_gemma":0.000001962166,"teacher_disagreement_score":0.97817254,"about_ca_system_score_codex":0.000062094936,"about_ca_system_score_gemma":0.000043812837,"threshold_uncertainty_score":0.5556001},"labels":[],"label_agreement":null},{"id":"W2955164461","doi":"10.1007/s00259-019-04395-4","title":"EJNMMI supplement: bringing AI and radiomics to nuclear medicine","year":2019,"lang":"en","type":"editorial","venue":"European Journal of Nuclear Medicine and Molecular Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Women's College Hospital; University of Toronto","funders":"","keywords":"Radiomics; Medicine; Medical physics; Nuclear medicine; Radiology","score_opus":0.006140260064794959,"score_gpt":0.2749790751018757,"score_spread":0.26883881503708074,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2955164461","genre_codex":"commentary","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012050745,0.020441383,0.006289557,0.4691264,0.46825907,0.0013702338,0.000034869583,0.00022701034,0.02220072],"genre_scores_gemma":[0.07724084,0.010314418,0.012553872,0.12431266,0.773464,0.0000014658401,0.00016333743,0.0014331342,0.0005162803],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9953575,0.00041321773,0.0014019521,0.00069305697,0.0014912796,0.00064297376],"domain_scores_gemma":[0.9967001,0.00031131253,0.0008108484,0.00053731416,0.0005265801,0.0011138158],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0035763392,0.00065487943,0.0016773416,0.0010737594,0.00019293057,0.00012394709,0.00046556164,0.00012851045,0.00022832885],"category_scores_gemma":[0.0040376964,0.00051977695,0.00019999825,0.00028495103,0.0005414069,0.00017234946,0.00040413084,0.0030196635,0.000029405333],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024316987,0.000031161784,0.000081835824,0.00048402228,0.00028462088,0.004710472,0.0025807794,0.000006354838,0.011094474,0.0000923664,0.95909023,0.021300517],"study_design_scores_gemma":[0.0061237086,0.0014842841,0.00011855559,0.0062805046,0.001059821,0.0021058898,0.0009748242,0.001621763,0.000009609234,0.000021630176,0.97976726,0.00043213862],"about_ca_topic_score_codex":0.000053423508,"about_ca_topic_score_gemma":2.4935412e-7,"teacher_disagreement_score":0.34481376,"about_ca_system_score_codex":0.00014151032,"about_ca_system_score_gemma":0.0001491755,"threshold_uncertainty_score":0.9997254},"labels":[],"label_agreement":null},{"id":"W2955212995","doi":"","title":"Refined estimates of local recurrence risks by DCIS score adjusting for clinicopathological features: a combined analysis of ECOG-ACRIN E5194 and Ontario DCIS cohort studies","year":2018,"lang":"en","type":"article","venue":"Publisher","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Cohort; Medicine; Internal medicine","score_opus":0.06718568760883135,"score_gpt":0.3850498065682052,"score_spread":0.31786411895937383,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2955212995","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9891554,0.001491542,0.006375583,0.0013023717,0.00036495648,0.0004075741,0.000028291865,0.000045647088,0.0008286453],"genre_scores_gemma":[0.9851131,0.00012370011,0.01355701,0.00043218635,0.00009084243,0.000044576253,0.00014285832,0.000020401705,0.00047535068],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.998174,0.000063229636,0.00065830944,0.0004741988,0.0003150483,0.00031518636],"domain_scores_gemma":[0.9977977,0.0007677848,0.00036277337,0.00031681516,0.0005882363,0.0001666884],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001483462,0.00020703,0.0010996487,0.00019968707,0.00009901355,0.000046340974,0.00017109656,0.00014462623,0.00009644774],"category_scores_gemma":[0.005878836,0.00015243735,0.0001848916,0.00053553755,0.00089272443,0.00015058513,0.0001409558,0.00041315128,5.9856325e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045065323,0.00021118367,0.9231749,0.00023023583,0.001233957,0.000008242206,0.0008820311,0.000014073474,0.00028078456,0.00008087185,0.03610426,0.03732878],"study_design_scores_gemma":[0.0027540876,0.0016937038,0.96997154,0.0004336591,0.0049111457,0.000022868873,0.00072281505,0.015271945,0.0003809378,0.0005467043,0.0030177706,0.00027281887],"about_ca_topic_score_codex":0.0024610825,"about_ca_topic_score_gemma":0.0013415302,"teacher_disagreement_score":0.046796616,"about_ca_system_score_codex":0.00007337999,"about_ca_system_score_gemma":0.00010517324,"threshold_uncertainty_score":0.70379406},"labels":[],"label_agreement":null},{"id":"W2955569215","doi":"10.1016/j.wneu.2019.08.232","title":"Noninvasive O6 Methylguanine-DNA Methyltransferase Status Prediction in Glioblastoma Multiforme Cancer Using Magnetic Resonance Imaging Radiomics Features: Univariate and Multivariate Radiogenomics Analysis","year":2019,"lang":"en","type":"article","venue":"World Neurosurgery","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":100,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Kermanshah University of Medical Sciences; Iran University of Medical Sciences","keywords":"Radiogenomics; Univariate; Medicine; Magnetic resonance imaging; Feature selection; Receiver operating characteristic; Artificial intelligence; Univariate analysis; Multivariate analysis; Oncology; Multivariate statistics; Radiology; Radiomics; Internal medicine; Machine learning; Computer science","score_opus":0.009762077671919188,"score_gpt":0.26773922021066243,"score_spread":0.25797714253874326,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2955569215","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99024624,0.00588049,0.0010426692,0.0008951352,0.0008693093,0.00069093873,0.000114321214,0.000114655195,0.0001462156],"genre_scores_gemma":[0.992574,0.0014991146,0.0030571755,0.0017260045,0.00020460875,0.000027859585,0.00004160561,0.00012432312,0.00074531767],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965452,0.0003208762,0.00083108933,0.0009780816,0.00043296773,0.0008917742],"domain_scores_gemma":[0.9979923,0.0007173997,0.00023396089,0.00052616966,0.00009969351,0.0004305079],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008093159,0.00047634498,0.001092051,0.0019955954,0.00015149347,0.00011508876,0.00014384188,0.00011080272,0.00013723026],"category_scores_gemma":[0.00036215608,0.00046897779,0.00030231386,0.0025272428,0.00017701703,0.00028705143,0.000073183655,0.0010110954,0.0000053766516],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009219479,0.00013282166,0.7510489,0.00012760682,0.00024574436,0.0007965399,0.0008334719,0.012836175,0.21238668,0.000071454415,0.000078754325,0.020519879],"study_design_scores_gemma":[0.0044439933,0.000103559396,0.46867624,0.00038438383,0.0013883956,0.00033341732,0.00012526836,0.514495,0.005739571,0.00002980592,0.0037403766,0.0005399656],"about_ca_topic_score_codex":0.0016321745,"about_ca_topic_score_gemma":0.0002875335,"teacher_disagreement_score":0.50165886,"about_ca_system_score_codex":0.0003936689,"about_ca_system_score_gemma":0.00028035603,"threshold_uncertainty_score":0.9997762},"labels":[],"label_agreement":null},{"id":"W2955781876","doi":"10.1016/j.ijrobp.2019.06.2504","title":"Computed Tomography-based Radiomics for Risk Stratification in Prostate Cancer","year":2019,"lang":"en","type":"article","venue":"International Journal of Radiation Oncology*Biology*Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":63,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Queen's University; Queen's University Belfast; Prostate Cancer UK; Movember Foundation","keywords":"Radiomics; Risk stratification; Prostate cancer; Computed tomography; Medicine; Stratification (seeds); Prostate; Radiology; Cancer; Medical physics; Internal medicine; Biology","score_opus":0.012181149990554849,"score_gpt":0.3375739603794908,"score_spread":0.3253928103889359,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2955781876","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91358143,0.0005409751,0.07517537,0.0069344495,0.0028465434,0.00064942794,0.00007860938,0.000032585427,0.00016059136],"genre_scores_gemma":[0.9821507,0.00033716415,0.014874966,0.0012522269,0.0011182952,0.000025792793,0.00018338469,0.000027860675,0.000029651996],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984733,0.00015892765,0.00071709236,0.00022460941,0.00021930103,0.0002067572],"domain_scores_gemma":[0.9975942,0.0004810217,0.0010757326,0.00012817458,0.0006138186,0.00010708985],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00086936634,0.00015120172,0.00044039078,0.0002944306,0.000040829116,0.000028010363,0.000252668,0.00014287536,0.000034030003],"category_scores_gemma":[0.00032596284,0.00013690317,0.00021712689,0.00021751231,0.0001310887,0.00015314153,0.000016380636,0.0006110914,0.0000063499806],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00063150126,0.0003052938,0.7808869,0.000024281844,0.00026564044,0.00001060682,0.00023249946,0.018331666,0.0045368606,0.003558319,0.0004674715,0.19074897],"study_design_scores_gemma":[0.025787834,0.0019723035,0.23734725,0.00031242493,0.0002511455,0.000108285494,0.00010698732,0.67775977,0.003399939,0.015083569,0.03750022,0.0003702753],"about_ca_topic_score_codex":0.00004075704,"about_ca_topic_score_gemma":0.000004703477,"teacher_disagreement_score":0.6594281,"about_ca_system_score_codex":0.00049095025,"about_ca_system_score_gemma":0.0006967412,"threshold_uncertainty_score":0.5582749},"labels":[],"label_agreement":null},{"id":"W2956136536","doi":"","title":"Quantitative renal PET imaging with Rubidium-82 can discriminate individuals with different degrees of renal impairment","year":2019,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Medicine; Renal function; Renal blood flow; Cardiology; Kidney; Perfusion; Creatinine; Ejection fraction; Internal medicine; Nuclear medicine; Cardiac PET; Blood flow; Diabetes mellitus; Kidney disease; Urology; Heart failure; Endocrinology","score_opus":0.010354211622141998,"score_gpt":0.27470290047804535,"score_spread":0.26434868885590335,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2956136536","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98799556,0.00007746709,0.00378991,0.0034755128,0.000054505785,0.00047664,0.000013074052,0.000056819455,0.0040605203],"genre_scores_gemma":[0.97951776,0.000018367662,0.018641956,0.00033168658,0.000039770213,0.000016539623,0.00005617612,0.000042968844,0.001334782],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9981652,0.00007170311,0.00033167598,0.00038050045,0.0006572575,0.00039366455],"domain_scores_gemma":[0.9989966,0.00012098378,0.00020975138,0.0003249316,0.00010938588,0.00023832185],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030904845,0.0002717183,0.00055383454,0.00018415478,0.000060213206,0.000033855627,0.00014380294,0.000023542385,0.00031400178],"category_scores_gemma":[0.000044257995,0.00014538015,0.00007703832,0.0001470506,0.00024103362,0.00008676918,0.00007202658,0.00040907864,0.0000072940047],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001012953,0.00047428953,0.96867704,0.0003351615,0.000545421,0.0002780503,0.002390259,0.00079188467,0.017900659,0.003952499,0.000899918,0.002741872],"study_design_scores_gemma":[0.011752829,0.007211097,0.9022075,0.003024859,0.0008638101,0.0010005026,0.005217335,0.055841386,0.011105599,0.0001812488,0.0008016147,0.0007922123],"about_ca_topic_score_codex":0.0005755673,"about_ca_topic_score_gemma":0.00009917554,"teacher_disagreement_score":0.06646953,"about_ca_system_score_codex":0.000073242045,"about_ca_system_score_gemma":0.00014032534,"threshold_uncertainty_score":0.59284306},"labels":[],"label_agreement":null},{"id":"W2958287596","doi":"10.1016/j.ctro.2019.07.003","title":"Learning from scanners: Bias reduction and feature correction in radiomics","year":2019,"lang":"en","type":"article","venue":"Clinical and Translational Radiation Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":79,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre","funders":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","keywords":"Scanner; Imaging phantom; Standard deviation; Feature (linguistics); Artificial intelligence; Region of interest; Pattern recognition (psychology); Signal-to-noise ratio (imaging); Computer science; Nuclear medicine; Medicine; Mathematics; Statistics","score_opus":0.03024073712173539,"score_gpt":0.36250060890022084,"score_spread":0.3322598717784855,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2958287596","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.982161,0.00059330725,0.00047624495,0.014360695,0.00094680046,0.00029395943,0.0000018256943,0.000028561135,0.0011376434],"genre_scores_gemma":[0.99563384,0.0010645506,0.0015667408,0.00053483614,0.00049811223,0.000008081509,0.00016026707,0.000011223816,0.00052232004],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9989245,0.00019348307,0.00034761807,0.00030037167,0.000117265125,0.000116767325],"domain_scores_gemma":[0.99893934,0.00073857367,0.00010613505,0.000057814235,0.000034184093,0.00012398031],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006105766,0.00008847496,0.00030413773,0.0001161613,0.000052676292,0.00001554098,0.000022294702,0.00024609666,0.00007439265],"category_scores_gemma":[0.00038039376,0.00008317512,0.00005168073,0.00012229707,0.00013650095,0.00010097998,0.000007256297,0.000765017,0.000010685653],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002801557,0.00006637349,0.68827516,0.000009729316,0.000025445588,0.0000043965583,0.00027738968,0.00072278373,0.0001886725,0.00018928539,0.00026237933,0.30969825],"study_design_scores_gemma":[0.0039203744,0.0003818753,0.8202925,0.00005207554,0.000040013423,0.00008098232,0.00010515463,0.14107417,0.000007485092,0.0007429252,0.033219837,0.00008264891],"about_ca_topic_score_codex":0.00006465634,"about_ca_topic_score_gemma":0.000010957619,"teacher_disagreement_score":0.30961558,"about_ca_system_score_codex":0.000029138468,"about_ca_system_score_gemma":0.000117000855,"threshold_uncertainty_score":0.3391783},"labels":[],"label_agreement":null},{"id":"W2958498622","doi":"10.1200/jco.2019.37.15_suppl.9087","title":"Pembrolizumab alone or with chemotherapy for PD-L1 positive NSCLC: A network meta-analysis of randomized trials.","year":2019,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; Sunnybrook Hospital; University of Toronto; Sunnybrook Health Science Centre","funders":"","keywords":"Medicine; Pembrolizumab; Internal medicine; Hazard ratio; Lung cancer; Chemotherapy; Oncology; Meta-analysis; Subgroup analysis; Progression-free survival; Adverse effect; Randomized controlled trial; Cancer; Confidence interval; Immunotherapy","score_opus":0.17338429771949004,"score_gpt":0.5051865838041146,"score_spread":0.3318022860846246,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2958498622","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.73260266,0.006726552,0.12074488,0.12741838,0.0022967928,0.0049537253,0.000028888337,0.00003163135,0.0051964847],"genre_scores_gemma":[0.90128523,0.0011655673,0.078323275,0.015431506,0.0018602045,0.000030761024,0.000015543976,0.000049488226,0.0018383985],"study_design_codex":"randomized_trial","study_design_gemma":"meta_analysis","domain_scores_codex":[0.99081856,0.002832336,0.0052437773,0.0002573974,0.00056123844,0.0002866858],"domain_scores_gemma":[0.9468725,0.04486155,0.0067376303,0.0002741157,0.00089665496,0.0003575606],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.039864756,0.00021103182,0.017494034,0.00028231865,0.000031326825,0.000011810351,0.00020788994,0.0003251082,0.0010908906],"category_scores_gemma":[0.027840834,0.00009659092,0.0076237586,0.0004594757,0.00035419982,0.00006604054,0.000023202469,0.0010264504,0.0000027766014],"study_design_candidate":"randomized_trial","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.6411333,0.0007756676,0.0013144747,0.000033940938,0.33550772,0.0000935268,0.00011296084,0.0013536674,0.000048480826,0.00026598407,0.0027982288,0.01656206],"study_design_scores_gemma":[0.44006914,0.013945986,0.004639001,0.000070970666,0.51454425,0.00020761252,0.000049887312,0.0150381,0.00002597609,0.00041185113,0.0108550275,0.00014219631],"about_ca_topic_score_codex":0.000025456115,"about_ca_topic_score_gemma":0.000009986642,"teacher_disagreement_score":0.20106415,"about_ca_system_score_codex":0.000058185327,"about_ca_system_score_gemma":0.0012567332,"threshold_uncertainty_score":0.99982226},"labels":[],"label_agreement":null},{"id":"W2960473173","doi":"10.1016/j.csbj.2019.07.001","title":"Radiomics and Artificial Intelligence for Biomarker and Prediction Model Development in Oncology","year":2019,"lang":"en","type":"review","venue":"Computational and Structural Biotechnology Journal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":202,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Royal Victoria Hospital; Jewish General Hospital; McGill University Health Centre; Royal Victoria Regional Health Centre","funders":"Fonds de Recherche du Québec - Santé","keywords":"Radiomics; Biomarker; Artificial intelligence; Predictive modelling; Computer science; Medical physics; Medicine; Machine learning; Biology","score_opus":0.06691848413472225,"score_gpt":0.37560191680804683,"score_spread":0.3086834326733246,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2960473173","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0105465185,0.8988759,0.08715827,0.0024930832,0.00030222998,0.0005725614,0.000018788172,0.000024664107,0.000007989639],"genre_scores_gemma":[0.003317243,0.92077094,0.07556703,0.00011769999,0.00009437449,0.000011905282,0.00008633175,0.000019059777,0.00001541456],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987387,0.00003790132,0.0006211558,0.00030312096,0.0001031477,0.00019596076],"domain_scores_gemma":[0.99934727,0.00020956558,0.00023521869,0.00005197302,0.000052586565,0.000103368286],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035982783,0.00021036953,0.00080005935,0.00047013626,0.00015176242,0.000039254486,0.00006850566,0.00050307286,0.0000027056583],"category_scores_gemma":[0.00015288315,0.00015511658,0.000060477698,0.00010745465,0.00028839317,0.00004507122,0.00007627699,0.000915075,4.4756396e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003819166,0.000007643456,0.000040990413,0.0011141644,0.000089075016,0.0000147778655,0.000062313025,0.00029984707,0.0000060484967,0.0024482904,0.000023688379,0.995855],"study_design_scores_gemma":[0.0005872758,0.0002433306,0.00034635747,0.0020568876,0.00029931526,0.012788191,0.000041366657,0.844804,0.0000027913004,0.03302353,0.10556054,0.00024640025],"about_ca_topic_score_codex":8.2980387e-7,"about_ca_topic_score_gemma":6.737619e-7,"teacher_disagreement_score":0.99560857,"about_ca_system_score_codex":0.0001350757,"about_ca_system_score_gemma":0.00041103814,"threshold_uncertainty_score":0.6325471},"labels":[],"label_agreement":null},{"id":"W2961784244","doi":"10.13140/rg.2.2.28400.51204","title":"END-TO-END DISCRIMINATIVE DEEP NETWORK FOR LIVER LESION CLASSIFICATION","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier de l’Université de Montréal; Polytechnique Montréal","funders":"","keywords":"Discriminative model; Artificial intelligence; Computer science; Deep learning; Lesion; Colorectal cancer; Radiology; Contextual image classification; Medicine; Residual; Probabilistic logic; Pattern recognition (psychology); Cancer; Image (mathematics); Pathology; Internal medicine","score_opus":0.09797159266163005,"score_gpt":0.2534858767203372,"score_spread":0.15551428405870713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2961784244","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21852371,0.0001775024,0.7702953,0.0014951566,0.0010876528,0.0016283821,0.000027976543,0.00013609619,0.0066282097],"genre_scores_gemma":[0.98731655,0.0002651219,0.005174317,0.00062850077,0.00054938527,0.000005757809,0.0003215058,0.000047286067,0.0056915707],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998184,0.000106195526,0.00022686663,0.00093195617,0.00014291673,0.00040806123],"domain_scores_gemma":[0.99831915,0.00023639698,0.00024196328,0.00065784797,0.00024232177,0.00030234866],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000455776,0.0003038565,0.0004985815,0.00022118035,0.00015707854,0.000038585575,0.0003490398,0.0003369444,0.00013009885],"category_scores_gemma":[0.0002615566,0.000307404,0.00028136355,0.00026209847,0.00012814885,0.000082350685,0.0004049693,0.0009667152,0.00010651705],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021699984,0.0006918429,0.053320825,0.0024105932,0.0009913484,0.000592415,0.0026561087,0.6500986,0.0010514344,0.18864828,0.02574554,0.07162296],"study_design_scores_gemma":[0.0013581995,0.00023303753,0.034404676,0.0005885586,0.00069065765,0.000008963621,0.00034886852,0.94170785,0.00003854209,0.004955855,0.015232603,0.00043218202],"about_ca_topic_score_codex":0.00011970231,"about_ca_topic_score_gemma":0.000021853344,"teacher_disagreement_score":0.76879287,"about_ca_system_score_codex":0.00034908328,"about_ca_system_score_gemma":0.00019347631,"threshold_uncertainty_score":0.99993783},"labels":[],"label_agreement":null},{"id":"W2962866587","doi":"10.2196/14310","title":"A Good Practice–Compliant Clinical Trial Imaging Management System for Multicenter Clinical Trials: Development and Validation Study","year":2019,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Workflow; Clinical trial; Protocol (science); Harmonization; Audit; Process management; Good laboratory practice; Medicine; Medical physics; Computer science; Quality assurance; Database; Engineering; Business","score_opus":0.10680611792971861,"score_gpt":0.49050197898477843,"score_spread":0.3836958610550598,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2962866587","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94240075,0.00006481429,0.03634128,0.002313543,0.0030324173,0.012245782,0.000003856924,0.00020791597,0.003389639],"genre_scores_gemma":[0.8927571,0.000089460926,0.10037197,0.004218207,0.0013635114,0.0006699958,0.00009343219,0.000059198028,0.00037709167],"study_design_codex":"design_other","study_design_gemma":"randomized_trial","domain_scores_codex":[0.99237156,0.000858222,0.004646824,0.00035800782,0.001334922,0.0004304435],"domain_scores_gemma":[0.99380213,0.003728797,0.0011400919,0.00039812832,0.00019670618,0.00073415524],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.031732734,0.00027754146,0.0013322104,0.0001668166,0.00013157864,0.00013954297,0.0002432162,0.00021334298,0.000047266436],"category_scores_gemma":[0.0073757106,0.00019814036,0.00029194393,0.00013215121,0.00012557866,0.00029528362,0.00024707007,0.0009958171,0.000115383205],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.018858202,0.003921213,0.051119693,0.0025074692,0.0013633528,0.00011558013,0.003908473,0.000003534578,0.0000014222609,0.0006638937,0.0033273834,0.9142098],"study_design_scores_gemma":[0.33420792,0.0030708592,0.012873951,0.0022127202,0.0015278495,0.00023129047,0.03900361,0.3128869,0.000010181642,0.000016262766,0.29335815,0.0006002906],"about_ca_topic_score_codex":0.0000035927137,"about_ca_topic_score_gemma":2.9655413e-7,"teacher_disagreement_score":0.9136095,"about_ca_system_score_codex":0.00011543994,"about_ca_system_score_gemma":0.00024936072,"threshold_uncertainty_score":0.9970349},"labels":[],"label_agreement":null},{"id":"W2963464382","doi":"10.1007/s11307-019-01411-9","title":"Machine Learning Methods for Optimal Radiomics-Based Differentiation Between Recurrence and Inflammation: Application to Nasopharyngeal Carcinoma Post-therapy PET/CT Images","year":2019,"lang":"en","type":"article","venue":"Molecular Imaging and Biology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":74,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Natural Science Foundation of China","keywords":"Nasopharyngeal carcinoma; Radiomics; Random forest; Artificial intelligence; Support vector machine; Medicine; Feature selection; Positron emission tomography; Magnetic resonance imaging; Machine learning; Receiver operating characteristic; Pattern recognition (psychology); Nuclear medicine; Radiology; Computer science; Radiation therapy","score_opus":0.011023351139088153,"score_gpt":0.32934326380011086,"score_spread":0.3183199126610227,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963464382","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6782906,0.0015756914,0.31359905,0.0058978265,0.00006202799,0.0005036455,0.000007937992,0.000040661456,0.000022554597],"genre_scores_gemma":[0.92388266,0.00007280387,0.07454468,0.00083954755,0.00009716052,0.000051447358,0.00046440912,0.000025511763,0.000021747222],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988434,0.00018218494,0.00023502087,0.00043568312,0.00006120406,0.00024252266],"domain_scores_gemma":[0.99927974,0.0002141825,0.000106691616,0.00016041772,0.00009644314,0.00014253905],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00055541785,0.00017897754,0.00033806328,0.00017497178,0.00011061664,0.000044808647,0.00007521813,0.000021349753,0.0000074073],"category_scores_gemma":[0.00022895544,0.00015549884,0.000060790753,0.00009990106,0.00008350925,0.000046485806,0.00004436949,0.00026658695,0.000002227739],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011200057,0.000011805626,0.30467966,0.0000703434,0.000030144762,0.0000069782254,0.000048052145,0.000057699584,0.33889169,0.00009387683,0.000008871749,0.35598886],"study_design_scores_gemma":[0.0063994043,0.0011515836,0.17514455,0.000106951,0.00018498935,0.00042726134,0.000053483658,0.7162393,0.07968716,0.00040719484,0.019643938,0.0005542113],"about_ca_topic_score_codex":0.000079148056,"about_ca_topic_score_gemma":2.2160177e-7,"teacher_disagreement_score":0.7161816,"about_ca_system_score_codex":0.000028289682,"about_ca_system_score_gemma":0.000036921636,"threshold_uncertainty_score":0.63410586},"labels":[],"label_agreement":null},{"id":"W2963465156","doi":"10.1016/j.artmed.2019.101769","title":"Fully-automated deep learning-powered system for DCE-MRI analysis of brain tumors","year":2019,"lang":"en","type":"preprint","venue":"Artificial Intelligence in Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Future Earth","funders":"Narodowe Centrum Badań i Rozwoju; Silesian University of Technology","keywords":"Computer science; Segmentation; Magnetic resonance imaging; Artificial intelligence; Grading (engineering); Glioma; Deep learning; Brain tumor; Pattern recognition (psychology); Radiology; Medicine; Pathology","score_opus":0.031645882989533206,"score_gpt":0.3635783111487204,"score_spread":0.3319324281591872,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963465156","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4732184,0.0035184224,0.4933113,0.016762331,0.0041788113,0.004709762,0.000058266327,0.0010686014,0.003174126],"genre_scores_gemma":[0.99404067,0.00023574756,0.0034623821,0.00049172813,0.00055234134,0.00011913033,0.00074424344,0.00009520302,0.00025856114],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9943762,0.00033046582,0.0025168008,0.0011189351,0.00094269204,0.00071492593],"domain_scores_gemma":[0.9953583,0.0016899679,0.0011079512,0.00096889446,0.0005543864,0.00032050107],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.003639132,0.0005885165,0.0030327057,0.0022756066,0.00008833546,0.00003457824,0.0005917376,0.0005512872,0.00027305106],"category_scores_gemma":[0.0060292426,0.0005005953,0.0006076624,0.0019349249,0.0005599704,0.000049160768,0.00026226544,0.0020202864,0.000032258635],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021396168,0.00079226756,0.03967189,0.008988543,0.0054110982,0.00046134225,0.010814316,0.76980644,0.012135845,0.008852083,0.0018204272,0.13910612],"study_design_scores_gemma":[0.00038001715,0.00068162795,0.0030126197,0.0038191353,0.0024542802,0.000023147455,0.004218635,0.98221636,0.0012670865,0.0008455121,0.00068045687,0.000401126],"about_ca_topic_score_codex":0.0015392824,"about_ca_topic_score_gemma":0.00015649504,"teacher_disagreement_score":0.5208223,"about_ca_system_score_codex":0.00036150328,"about_ca_system_score_gemma":0.0002938614,"threshold_uncertainty_score":0.9997446},"labels":[],"label_agreement":null},{"id":"W2963910535","doi":"10.1109/access.2019.2930238","title":"Deep Radiomic Analysis Based on Modeling Information Flow in Convolutional Neural Networks","year":2019,"lang":"en","type":"article","venue":"IEEE Access","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; Université du Québec à Montréal; McGill University","funders":"McGill University","keywords":"Softmax function; Convolutional neural network; Artificial intelligence; Pattern recognition (psychology); Computer science; Binary classification; Feature extraction; Conditional entropy; Feature (linguistics); Entropy (arrow of time); Contextual image classification; Histogram; Wilcoxon signed-rank test; Local binary patterns; Mann–Whitney U test; Mathematics; Principle of maximum entropy; Image (mathematics); Statistics; Support vector machine","score_opus":0.011031429614248524,"score_gpt":0.2892656213452136,"score_spread":0.2782341917309651,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963910535","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5469597,0.000025500152,0.45112532,0.00063251186,0.00034170924,0.00016378246,0.0000011080961,0.00003156956,0.00071881287],"genre_scores_gemma":[0.9953958,0.000008237293,0.00081283686,0.003453371,0.00014574811,0.000010251562,0.00014670861,0.000010183258,0.000016909027],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99894005,0.000043771084,0.00031283533,0.00016969415,0.00029991334,0.00023376314],"domain_scores_gemma":[0.99945706,0.00008893157,0.00007593295,0.00022080158,0.000057009333,0.00010025948],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033676435,0.00011639107,0.00028691473,0.00053015567,0.000039591294,0.00007457927,0.00016256631,0.00007800084,0.00015641833],"category_scores_gemma":[0.00007999204,0.00010248022,0.00012016685,0.00065261853,0.000022190978,0.00039978174,0.000018121771,0.00044092353,0.000023739562],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000107608816,0.000026332144,0.081394605,0.00002055502,0.000048125596,0.0000055625446,0.000033016666,0.9104351,0.000009750853,0.000015707565,0.00007060091,0.007833084],"study_design_scores_gemma":[0.001563208,0.000040372517,0.01898795,0.000040030358,0.00010984296,0.0000037224809,0.000009174419,0.9790628,0.0000047505255,0.000024548513,0.000050122526,0.000103458726],"about_ca_topic_score_codex":0.00016046822,"about_ca_topic_score_gemma":0.000010922235,"teacher_disagreement_score":0.4503125,"about_ca_system_score_codex":0.00010975461,"about_ca_system_score_gemma":0.00004589198,"threshold_uncertainty_score":0.4179022},"labels":[],"label_agreement":null},{"id":"W2964166134","doi":"10.1016/j.compbiomed.2019.04.018","title":"Deep learning for identifying radiogenomic associations in breast cancer","year":2019,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":163,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of Biomedical Imaging and Bioengineering; National Institutes of Health; Canadian Institute for Advanced Research; North Carolina Biotechnology Center","keywords":"Artificial intelligence; Deep learning; Transfer of learning; Computer science; Artificial neural network; Receiver operating characteristic; Magnetic resonance imaging; Breast cancer; Machine learning; Support vector machine; Pattern recognition (psychology); Cancer; Medicine; Radiology; Internal medicine","score_opus":0.015875686455081445,"score_gpt":0.34889873667946286,"score_spread":0.3330230502243814,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964166134","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96836513,0.0029595708,0.013571297,0.013278018,0.0010602222,0.00041434588,0.0000018908088,0.000028621256,0.00032092704],"genre_scores_gemma":[0.9947057,0.000965222,0.0020170584,0.001803261,0.0003193098,0.000020250316,0.000056702407,0.000012345199,0.00010015117],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9991355,0.0000631356,0.0002549842,0.00025240978,0.000050120732,0.00024383796],"domain_scores_gemma":[0.9994086,0.00033338153,0.000076823395,0.00007922623,0.000026429096,0.000075558295],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00058645627,0.00010035133,0.00039278524,0.00024339525,0.000047972055,0.000004216171,0.00006265805,0.00010177552,0.000042730455],"category_scores_gemma":[0.00014135963,0.00008168886,0.000029941531,0.00014393298,0.00011463922,0.00002898561,0.000032909113,0.00039191282,0.0000022338559],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000058483132,0.000022461401,0.95211804,0.000073658135,0.00003385603,0.000007883086,0.00065866,0.00032743695,0.0038477462,0.0009097221,0.00016848525,0.041773595],"study_design_scores_gemma":[0.0051394096,0.00015132398,0.8705946,0.00048621395,0.00003463146,0.00007807334,0.00016931356,0.12017013,0.0000066531748,0.0009770981,0.0020863963,0.00010611886],"about_ca_topic_score_codex":0.0002128746,"about_ca_topic_score_gemma":0.00002166884,"teacher_disagreement_score":0.11984269,"about_ca_system_score_codex":0.000108155415,"about_ca_system_score_gemma":0.000031311072,"threshold_uncertainty_score":0.33311749},"labels":[],"label_agreement":null},{"id":"W2968081492","doi":"10.2196/13476","title":"A Machine Learning Method for Identifying Lung Cancer Based on Routine Blood Indices: Qualitative Feasibility Study","year":2019,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":55,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Lung cancer; Medicine; Cancer; Lung; Internal medicine; Oncology; Intensive care medicine","score_opus":0.04071611167170215,"score_gpt":0.4582163525879367,"score_spread":0.41750024091623456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2968081492","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8308773,0.00015545766,0.1595291,0.0018750745,0.000501489,0.0045386087,0.00003049793,0.00026225846,0.0022301793],"genre_scores_gemma":[0.93978196,0.00002086764,0.054016177,0.0046088593,0.00024900047,0.00044638506,0.00018023794,0.00006431113,0.0006321865],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99574333,0.00044162737,0.0011682907,0.00033819198,0.0017445146,0.0005640368],"domain_scores_gemma":[0.99655515,0.0017045762,0.00049809745,0.0004519368,0.00020493666,0.00058528833],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0057933447,0.00034340008,0.0008581863,0.00029347604,0.00019690626,0.00008028787,0.0003208179,0.00022553545,0.0010247187],"category_scores_gemma":[0.0026666354,0.00025852807,0.00023577084,0.000423823,0.00008781185,0.00019679818,0.00011662262,0.0018025519,0.000027920141],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002270799,0.0051022926,0.7281245,0.0102170985,0.001586185,0.00010196027,0.18981135,0.0030082043,0.0002066059,0.0007384562,0.0017473644,0.0570852],"study_design_scores_gemma":[0.013028678,0.0016557156,0.006568933,0.0010947606,0.00039065428,0.00002059115,0.0142310485,0.961184,0.00004954837,0.000048047834,0.001413357,0.0003146449],"about_ca_topic_score_codex":0.00020196871,"about_ca_topic_score_gemma":0.000014213012,"teacher_disagreement_score":0.95817584,"about_ca_system_score_codex":0.00017979703,"about_ca_system_score_gemma":0.00039455076,"threshold_uncertainty_score":0.9999867},"labels":[],"label_agreement":null},{"id":"W2968456576","doi":"10.4103/jpi.jpi_31_19","title":"2020 Vision of Digital Pathology in Action","year":2019,"lang":"en","type":"editorial","venue":"Journal of Pathology Informatics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network","funders":"","keywords":"Digital pathology; Computer science; Action (physics); Pathology; Artificial intelligence; Medicine","score_opus":0.00748709512679094,"score_gpt":0.3229791782215725,"score_spread":0.31549208309478155,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2968456576","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24731933,0.00041549472,0.002646314,0.0007464598,0.7466198,0.0002681474,0.000050671195,0.000013261414,0.0019204809],"genre_scores_gemma":[0.09848572,0.008994028,0.02000507,0.0007968976,0.86913514,0.0000056719896,0.0007590717,0.0001771548,0.0016412478],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9970205,0.00007837094,0.0018953792,0.00008625637,0.0006786014,0.00024093792],"domain_scores_gemma":[0.9962218,0.0006329797,0.0023255663,0.0002482158,0.0004600176,0.00011141584],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0012485168,0.00021183936,0.001183391,0.0005877475,0.000017191764,0.0000231985,0.00023273018,0.00093739334,0.000027684833],"category_scores_gemma":[0.0047563007,0.000163721,0.00024405368,0.00016819489,0.00016809502,0.0003349573,0.00008768212,0.0030867134,0.000023163675],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00048092753,0.000238404,0.0038489134,0.0014249308,0.00010176773,0.0024682323,0.0018063802,0.00025935596,0.00043546595,0.000013104807,0.963683,0.025239527],"study_design_scores_gemma":[0.0091637615,0.005463332,0.0027625978,0.003244814,0.00053101184,0.012540094,0.0012101432,0.004744287,0.00007287986,0.00039390087,0.95945346,0.00041971478],"about_ca_topic_score_codex":0.0000010904336,"about_ca_topic_score_gemma":5.025551e-7,"teacher_disagreement_score":0.14883362,"about_ca_system_score_codex":0.00014516669,"about_ca_system_score_gemma":0.00060184684,"threshold_uncertainty_score":0.9992132},"labels":[],"label_agreement":null},{"id":"W2968538884","doi":"","title":"Evaluation of MRI to ultrasound registration methods for brain shift correction: The CuRIOUS2018 Challenge","year":2019,"lang":"en","type":"article","venue":"Duo Research Archive (University of Oslo)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":72,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Engineering and Physical Sciences Research Council; Deutsche Forschungsgemeinschaft","keywords":"Computer science; Benchmark (surveying); Artificial intelligence; Image registration; Medical physics; Annotation; Ground truth; Plan (archaeology); Midline shift; Computer vision; Radiology; Medicine; Image (mathematics); Computed tomography","score_opus":0.06116782952778539,"score_gpt":0.4055102622676365,"score_spread":0.3443424327398511,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2968538884","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21767594,0.0002214096,0.6920296,0.055350345,0.000347995,0.0032697977,0.000023069533,0.000028140892,0.031053707],"genre_scores_gemma":[0.93812853,0.00012979493,0.05880951,0.0001444378,0.00013621457,0.0000066528323,0.00006557411,0.000018219747,0.0025610705],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973649,0.0011068357,0.00013117246,0.00025327812,0.00091527717,0.00022857219],"domain_scores_gemma":[0.9961384,0.0026112269,0.0001008813,0.0003644969,0.00065313507,0.00013188127],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011339852,0.0000717161,0.0002122003,0.00026019136,0.00020924772,0.000010296928,0.0002455624,0.00004507664,0.00025448707],"category_scores_gemma":[0.0038059368,0.00006398846,0.00010836715,0.0002854096,0.00031854806,0.00007892258,0.00008090416,0.0004008326,0.000017818144],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002475022,0.0006863351,0.005056186,0.0007722656,0.000644352,0.000008600706,0.04460439,0.0017632452,0.1440982,0.022563485,0.12756948,0.6497584],"study_design_scores_gemma":[0.007005141,0.0047479654,0.13219547,0.0006186509,0.0003912726,0.000042016305,0.016989987,0.5866427,0.0015254886,0.034223128,0.21530455,0.00031363586],"about_ca_topic_score_codex":0.000516583,"about_ca_topic_score_gemma":0.0001634963,"teacher_disagreement_score":0.7204526,"about_ca_system_score_codex":0.00009465515,"about_ca_system_score_gemma":0.00034750055,"threshold_uncertainty_score":0.45563367},"labels":[],"label_agreement":null},{"id":"W2969294044","doi":"10.1016/j.jmir.2019.07.010","title":"Personalized Breast Cancer Treatments Using Artificial Intelligence in Radiomics and Pathomics","year":2019,"lang":"en","type":"article","venue":"Journal of medical imaging and radiation sciences","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":94,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; York University; University of Toronto; Sunnybrook Health Science Centre","funders":"Natural Sciences and Engineering Research Council of Canada; Terry Fox Research Institute","keywords":"Radiomics; Breast cancer; Medical physics; Cancer; Medicine; Artificial intelligence; Computer science; Internal medicine","score_opus":0.022467705017157828,"score_gpt":0.3660068508425579,"score_spread":0.34353914582540007,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2969294044","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96782327,0.005239893,0.0032726678,0.023103168,0.0004392066,0.00007392329,0.0000015876383,0.0000044365975,0.00004186226],"genre_scores_gemma":[0.9883339,0.0070213107,0.0033421412,0.00096894143,0.00031494055,5.4647603e-7,5.6909505e-7,0.000006326905,0.000011343448],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984723,0.00006753953,0.00040590056,0.00016750203,0.00071238587,0.00017438129],"domain_scores_gemma":[0.99926925,0.00016145036,0.00021578763,0.00004374337,0.000055204968,0.00025457368],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018515683,0.00008968489,0.00028672256,0.00027466821,0.00008102558,0.00007774522,0.00009843378,0.000049031027,0.00008111173],"category_scores_gemma":[0.00035266197,0.00006158432,0.00004235962,0.0002518801,0.00042217757,0.00021757484,0.000025795707,0.00033600032,6.3459197e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006583815,0.00007287943,0.27424258,0.000034920806,0.000024203384,0.0000820764,0.0008026108,0.0002764268,0.0013172581,0.0007942199,0.000040406838,0.7222466],"study_design_scores_gemma":[0.001163695,0.00007991937,0.06894551,0.00048916176,0.000068354784,0.003384718,0.0021876858,0.9222229,0.000055427277,0.000945135,0.00035200582,0.000105488914],"about_ca_topic_score_codex":0.000109890905,"about_ca_topic_score_gemma":0.0000014552812,"teacher_disagreement_score":0.92194647,"about_ca_system_score_codex":0.00007612409,"about_ca_system_score_gemma":0.00035793133,"threshold_uncertainty_score":0.25113356},"labels":[],"label_agreement":null},{"id":"W2969964521","doi":"10.1002/jmri.26904","title":"Reliability of 3D texture analysis: A multicenter MRI study of the brain","year":2019,"lang":"en","type":"article","venue":"Journal of Magnetic Resonance Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Women and Children’s Health Research Institute; University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Fondation Brain Canada; ALS Society of Canada","keywords":"Intraclass correlation; Reliability (semiconductor); Neuroimaging; Voxel; Nuclear medicine; Computer science; Psychology; Reproducibility; Medicine; Artificial intelligence; Mathematics; Statistics; Neuroscience; Physics","score_opus":0.004461918603934783,"score_gpt":0.2722354442724372,"score_spread":0.2677735256685024,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2969964521","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9905384,0.0037954273,0.00032133254,0.0042449557,0.00024524107,0.00036668137,0.0000015471738,0.000004327867,0.00048205754],"genre_scores_gemma":[0.9965276,0.000056360983,0.0023503697,0.0005177818,0.00008305404,0.0000013322096,3.0464426e-7,0.000014446148,0.00044875528],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99769413,0.00023167567,0.00092776446,0.00019095073,0.00076096243,0.0001945192],"domain_scores_gemma":[0.9979027,0.00027925606,0.0007769692,0.00054287334,0.00041040275,0.000087821776],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015233917,0.00013551004,0.0006871895,0.0002214864,0.00003198806,0.000014339342,0.0003304007,0.00003327824,0.00018475839],"category_scores_gemma":[0.0011636409,0.00008001301,0.00031855208,0.00060548336,0.0001465464,0.000094278555,0.00008956652,0.0006792052,0.0000014362607],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021954864,0.000540909,0.95610833,0.000098184966,0.000090293484,0.000027295018,0.001522428,0.00094002404,0.0052836863,0.0000031656716,0.0006653733,0.034500755],"study_design_scores_gemma":[0.0035581603,0.0004874791,0.94242287,0.00041679209,0.0007800064,0.00006744298,0.0011377104,0.046457715,0.00010849579,0.000022663055,0.0044673616,0.00007331221],"about_ca_topic_score_codex":0.00008963938,"about_ca_topic_score_gemma":0.0000045081665,"teacher_disagreement_score":0.04551769,"about_ca_system_score_codex":0.00004405175,"about_ca_system_score_gemma":0.00010214362,"threshold_uncertainty_score":0.32628357},"labels":[],"label_agreement":null},{"id":"W2970283707","doi":"10.1007/s12072-019-09973-0","title":"Radiomics in hepatocellular carcinoma: a quantitative review","year":2019,"lang":"en","type":"review","venue":"Hepatology International","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":131,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Horizon 2020 Framework Programme; European Commission","keywords":"Radiomics; Medicine; Hepatocellular carcinoma; Radiology; Magnetic resonance imaging; Medical physics; Positron emission tomography; Internal medicine","score_opus":0.07115902956135728,"score_gpt":0.4004379783425816,"score_spread":0.3292789487812243,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2970283707","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001111862,0.99093086,0.00019222072,0.0018866445,0.00144669,0.0010705221,0.00002889468,0.000037063597,0.004295908],"genre_scores_gemma":[0.00009120602,0.9942902,0.0013435784,0.002060405,0.00017047663,0.00012563047,0.0008420937,0.00007039372,0.0010060514],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99742985,0.0002579328,0.0010226952,0.00060156133,0.00035158388,0.0003364056],"domain_scores_gemma":[0.99855036,0.0003682123,0.00044153814,0.00040245778,0.00011248599,0.0001249588],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005825342,0.00040042706,0.0026711388,0.0005650702,0.000023466724,0.00001409309,0.00041199298,0.00035798346,0.00050246256],"category_scores_gemma":[0.00088129455,0.00033410345,0.0006076303,0.0003016229,0.000137766,0.000054731074,0.00012624048,0.0014519879,0.00051802816],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005971955,0.00037918598,0.061472125,0.12849268,0.0011195529,0.0042651016,0.000103607315,9.2992406e-7,0.0000010210064,0.011890176,0.023688165,0.76852775],"study_design_scores_gemma":[0.0006238507,0.000058064583,0.00004846551,0.040418826,0.0007871168,0.0024095192,0.000004126767,0.005442877,1.1863292e-7,0.00004411304,0.9499111,0.00025179333],"about_ca_topic_score_codex":0.00007533751,"about_ca_topic_score_gemma":0.0000034551565,"teacher_disagreement_score":0.926223,"about_ca_system_score_codex":0.0004413933,"about_ca_system_score_gemma":0.0007782986,"threshold_uncertainty_score":0.9999111},"labels":[],"label_agreement":null},{"id":"W2970394565","doi":"10.1164/ajrccm-conference.2019.199.1_meetingabstracts.a5167","title":"An Individual Patient Data Meta-Analysis to Estimate the Diagnostic Accuracy of a Machine Learning-Based Software for Analyzing Chest X-Rays of Persons with Symptoms of Pulmonary Tuberculosis: Preliminary Findings","year":2019,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre","funders":"","keywords":"Pulmonary tuberculosis; Patient data; Software; Meta-analysis; Computer science; Medicine; Machine learning; Artificial intelligence; Data mining; Tuberculosis; Internal medicine; Programming language; Pathology; Database","score_opus":0.02753823538583563,"score_gpt":0.3244169623306955,"score_spread":0.2968787269448599,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2970394565","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95601726,0.0007933646,0.039499037,0.0017485525,0.00002336216,0.0013565555,0.0004903282,0.000046620917,0.00002490619],"genre_scores_gemma":[0.97090584,0.000006975519,0.027374957,0.00028660853,0.000014154547,0.00007566568,0.0012537703,0.000045172423,0.000036881604],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99759686,0.00015586316,0.0006920848,0.0005652276,0.0006776091,0.00031236833],"domain_scores_gemma":[0.99450505,0.0033194572,0.00049272104,0.0012102295,0.00027535233,0.00019716784],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010932569,0.00028375312,0.0013382614,0.00044494888,0.00009405551,0.000022821718,0.0006467277,0.00007250124,0.0002082755],"category_scores_gemma":[0.004261147,0.00016181912,0.0004551585,0.0010059908,0.00016151402,0.00016459839,0.00020911454,0.00036958797,0.0000012592936],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00074248994,0.0009636896,0.7411469,0.00088417187,0.05244333,0.000015651724,0.0019397229,0.19101697,0.0014955126,0.000021327194,0.00011759905,0.009212619],"study_design_scores_gemma":[0.0010485963,0.0041367593,0.11371479,0.00017550145,0.17430277,0.000019504008,0.00055252423,0.70430964,0.0013479752,0.0000049662676,0.00012293157,0.00026401214],"about_ca_topic_score_codex":0.0005775561,"about_ca_topic_score_gemma":0.000025111256,"teacher_disagreement_score":0.6274321,"about_ca_system_score_codex":0.000019643488,"about_ca_system_score_gemma":0.0001498522,"threshold_uncertainty_score":0.6598792},"labels":[],"label_agreement":null},{"id":"W2970612217","doi":"10.1016/j.radonc.2019.08.008","title":"Sensitivity of radiomic features to inter-observer variability and image pre-processing in Apparent Diffusion Coefficient (ADC) maps of cervix cancer patients","year":2019,"lang":"en","type":"article","venue":"Radiotherapy and Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":73,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Princess Margaret Cancer Centre","funders":"Princess Margaret Cancer Foundation","keywords":"Effective diffusion coefficient; Sensitivity (control systems); Cervix; Medicine; Observer (physics); Diffusion MRI; Diffusion imaging; Nuclear medicine; Cancer; Radiology; Artificial intelligence; Computer science; Internal medicine; Magnetic resonance imaging; Physics; Engineering","score_opus":0.0065371825723880015,"score_gpt":0.3033597934002563,"score_spread":0.2968226108278683,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2970612217","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9953394,0.00063034106,0.0023741738,0.0008527465,0.00018523297,0.0004915327,0.0000142913,0.000009220887,0.00010307971],"genre_scores_gemma":[0.99625134,0.00034009054,0.0027420109,0.00054045784,0.000041392268,0.000008126076,0.000010351176,0.000014578139,0.00005162216],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99883085,0.00023954634,0.0003148363,0.0002971862,0.00013621524,0.00018135025],"domain_scores_gemma":[0.9993391,0.00018911452,0.0001446683,0.00014511606,0.00007097317,0.00011102858],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00078123587,0.000129952,0.00058975635,0.00012359816,0.00002822986,0.0000052995524,0.00004722753,0.00010993876,0.00004922613],"category_scores_gemma":[0.0001231747,0.00010307354,0.000040969608,0.00012945605,0.0001860488,0.00004067843,0.000052442494,0.00024804095,1.8572909e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009933216,0.00056998816,0.7537464,0.0005277869,0.000026770638,0.000008842728,0.003680468,0.00012535567,0.12562822,0.000018649498,0.00016862254,0.11450557],"study_design_scores_gemma":[0.004025492,0.0009105692,0.9691894,0.00032006027,0.000031537533,0.00002950507,0.000072278235,0.02253755,0.0013428784,0.000021758253,0.0014071753,0.00011181843],"about_ca_topic_score_codex":0.0007289249,"about_ca_topic_score_gemma":0.00007504964,"teacher_disagreement_score":0.21544297,"about_ca_system_score_codex":0.00022493051,"about_ca_system_score_gemma":0.00009505309,"threshold_uncertainty_score":0.42032167},"labels":[],"label_agreement":null},{"id":"W2972168296","doi":"10.1016/j.jmir.2019.09.005","title":"Machine Learning and Deep Learning in Medical Imaging: Intelligent Imaging","year":2019,"lang":"en","type":"review","venue":"Journal of medical imaging and radiation sciences","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":447,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Deep learning; Artificial intelligence; Perspective (graphical); Computer science; Medical imaging; Quality (philosophy); Foundation (evidence); Craft; Artificial neural network; Machine learning; Engineering management; Engineering; Political science","score_opus":0.0252816267536549,"score_gpt":0.39032798294840293,"score_spread":0.365046356194748,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2972168296","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00020785819,0.9796531,0.00241042,0.015969845,0.0010246477,0.0002302237,7.4795713e-7,0.000041077335,0.00046208248],"genre_scores_gemma":[0.0040936843,0.99332416,0.0004621392,0.0009378344,0.0009894966,0.000004285554,0.000015052631,0.000052606487,0.00012074468],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9929221,0.0006143641,0.001891256,0.0006554601,0.0032748415,0.0006419731],"domain_scores_gemma":[0.9955042,0.0017836756,0.0013033451,0.00013829638,0.00014814353,0.0011223439],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.011314742,0.00049007393,0.0021327373,0.0015248994,0.00031478988,0.0003282562,0.0005582689,0.00024048898,0.0002997827],"category_scores_gemma":[0.01147999,0.0003332779,0.00034425725,0.00081083085,0.0011366212,0.0003955679,0.00028554397,0.004972932,0.000010166817],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009444876,0.00005545928,0.034923237,0.0018479218,0.00005104475,0.00080060586,0.0002836724,0.000025606798,6.00146e-7,0.0000631856,0.0002730338,0.96166617],"study_design_scores_gemma":[0.0009884165,0.00006358982,0.00031085094,0.012412597,0.00032152678,0.00919052,0.00070066674,0.30557644,2.0091902e-7,0.000037866626,0.67013574,0.00026158674],"about_ca_topic_score_codex":0.000084693675,"about_ca_topic_score_gemma":0.0000026923344,"teacher_disagreement_score":0.9614046,"about_ca_system_score_codex":0.00017428001,"about_ca_system_score_gemma":0.0014524884,"threshold_uncertainty_score":0.9999119},"labels":[],"label_agreement":null},{"id":"W2972617274","doi":"10.1016/j.ijrobp.2019.06.548","title":"Comparisons of Outcome Prediction Performance between Radiomics Features and Clinical Features Based on NRG Oncology/ RTOG-0522","year":2019,"lang":"en","type":"article","venue":"International Journal of Radiation Oncology*Biology*Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Radiomics; Medicine; Univariate; Proportional hazards model; Multivariate statistics; Cetuximab; Clinical trial; Radiation therapy; Feature (linguistics); Feature selection; Head and neck cancer; Multivariate analysis; Stage (stratigraphy); Oncology; Artificial intelligence; Radiology; Internal medicine; Cancer; Machine learning; Computer science","score_opus":0.02618661391524823,"score_gpt":0.38193886833451957,"score_spread":0.35575225441927133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2972617274","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9820194,0.00023506001,0.005906353,0.0068172277,0.003281442,0.00028707093,0.000059530823,0.000034122062,0.0013597629],"genre_scores_gemma":[0.988264,0.00053366314,0.0064812466,0.0020441671,0.0024303896,0.0000026319822,0.0001284674,0.000028779874,0.000086636064],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9975042,0.00034512323,0.0012338285,0.00028499617,0.000403981,0.0002279122],"domain_scores_gemma":[0.99630874,0.001386294,0.001424081,0.00019870156,0.000475359,0.00020681313],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016325789,0.00021689823,0.0009597084,0.00027281992,0.000065947876,0.000020189686,0.00033831253,0.0004315491,0.000034431636],"category_scores_gemma":[0.000796404,0.00017991468,0.00029682717,0.00013747795,0.000433749,0.00016196152,0.000059450802,0.0016241603,0.000010989974],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000744283,0.00036701316,0.8668043,0.00002454712,0.0004213773,0.0000109992,0.00009922932,0.0020969363,0.0003920272,0.00091593456,0.002724651,0.12539871],"study_design_scores_gemma":[0.009275492,0.0038073838,0.9240535,0.0001497826,0.00030128335,0.00020836329,0.000048871017,0.03774918,0.0003294334,0.00036903447,0.02355517,0.00015251679],"about_ca_topic_score_codex":0.000013483882,"about_ca_topic_score_gemma":0.0000010172832,"teacher_disagreement_score":0.12524618,"about_ca_system_score_codex":0.00045998624,"about_ca_system_score_gemma":0.00048145422,"threshold_uncertainty_score":0.7336708},"labels":[],"label_agreement":null},{"id":"W2972654566","doi":"10.1016/j.ijrobp.2019.06.2477","title":"Towards Improved Medical Imaging Analysis for Oncology Care: Clinical Experience with Simulation Platform for Brain Tumors","year":2019,"lang":"en","type":"article","venue":"International Journal of Radiation Oncology*Biology*Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Fraser Health; Simon Fraser University","funders":"","keywords":"Benchmark (surveying); Medicine; Ground truth; Magnetic resonance imaging; Identification (biology); Artificial intelligence; Machine learning; Medical physics; Computer science; Glioblastoma; Feature (linguistics); Radiology","score_opus":0.022532095778114807,"score_gpt":0.4134035363868805,"score_spread":0.39087144060876566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2972654566","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43888786,0.00015300502,0.54872906,0.009544723,0.001839481,0.0005415244,0.000026705291,0.00003161585,0.0002460253],"genre_scores_gemma":[0.9703707,0.00007360972,0.021513762,0.00489839,0.0027758214,0.00003910725,0.00025104822,0.000036808207,0.000040728108],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99746746,0.00015757255,0.0012366622,0.0003787496,0.00043758214,0.0003219786],"domain_scores_gemma":[0.9942412,0.0025280076,0.0013699188,0.00018351257,0.0013854477,0.00029196066],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00189551,0.00021452073,0.00095340126,0.00028955424,0.00008472221,0.000033240787,0.00043243848,0.00029711818,0.000079053716],"category_scores_gemma":[0.003214468,0.00016944508,0.0005610656,0.00024759615,0.00034265613,0.0002657503,0.00005675545,0.0007091582,0.000004071807],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001962429,0.0003004379,0.48230276,0.00002559094,0.0014827197,0.000027400054,0.0010949519,0.00813767,0.0005327987,0.0028108642,0.00027404004,0.5010483],"study_design_scores_gemma":[0.018152803,0.0037399293,0.03080375,0.00009317123,0.00074678275,0.00019543813,0.00073298544,0.8624887,0.00022564398,0.0018676624,0.0806792,0.00027393427],"about_ca_topic_score_codex":0.000020854424,"about_ca_topic_score_gemma":0.0000058962537,"teacher_disagreement_score":0.85435104,"about_ca_system_score_codex":0.0007554184,"about_ca_system_score_gemma":0.0016849225,"threshold_uncertainty_score":0.690977},"labels":[],"label_agreement":null},{"id":"W2972983521","doi":"10.1016/j.carj.2019.06.009","title":"Magnetic Resonance Imaging Texture Analysis Predicts Recurrence in Patients with Nasopharyngeal Carcinoma","year":2019,"lang":"en","type":"article","venue":"Canadian Association of Radiologists Journal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; McMaster University; McGill University Health Centre","funders":"","keywords":"Medicine; Nasopharyngeal carcinoma; Magnetic resonance imaging; Confidence interval; Receiver operating characteristic; Proportional hazards model; Logistic regression; Hazard ratio; Retrospective cohort study; Radiology; Nuclear medicine; Internal medicine; Radiation therapy","score_opus":0.003711328461689621,"score_gpt":0.21889519930110649,"score_spread":0.21518387083941687,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2972983521","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99452764,0.0013664808,0.00007411198,0.0020036194,0.00024078743,0.00021519413,0.000027414599,0.000008352438,0.0015364062],"genre_scores_gemma":[0.9982076,0.000053887186,0.00051499147,0.0005794929,0.00009525737,0.0000020453908,0.000052830128,0.000012672042,0.00048121615],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99844706,0.0001438156,0.00037836013,0.0002216068,0.000390382,0.0004187606],"domain_scores_gemma":[0.9986911,0.00010294166,0.0003652788,0.00016961787,0.0002788576,0.00039224996],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00080814614,0.00013264394,0.00045624626,0.00064584275,0.00006390053,0.00003080153,0.0001549115,0.000098846314,0.00017815281],"category_scores_gemma":[0.0007684019,0.000109446955,0.00010378962,0.0006910617,0.0000608997,0.00010956721,0.000009870699,0.0007669503,0.000006042281],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005929639,0.000024479108,0.98530066,0.000012032997,0.000059063626,0.0000639614,0.00013336087,0.00020082253,0.0000049273176,0.000019572655,0.0018925742,0.01222927],"study_design_scores_gemma":[0.0026832211,0.00021586199,0.9889054,0.00009695246,0.00015713561,0.00003307219,0.000029677161,0.005654046,0.0000011983825,0.000019599667,0.0020977894,0.00010606134],"about_ca_topic_score_codex":0.0025230905,"about_ca_topic_score_gemma":0.0025405018,"teacher_disagreement_score":0.012123209,"about_ca_system_score_codex":0.001251972,"about_ca_system_score_gemma":0.0006285204,"threshold_uncertainty_score":0.4463117},"labels":[],"label_agreement":null},{"id":"W2973045916","doi":"10.1016/j.ijrobp.2019.06.1563","title":"Predicting Recurrence for Patients with Head-Neck Squamous Cell Carcinoma Using Quantitative Ultrasound Based Radiomic Signatures Integrated with Machine Learning","year":2019,"lang":"en","type":"article","venue":"International Journal of Radiation Oncology*Biology*Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Health Sciences Centre; Sunnybrook Health Science Centre","funders":"","keywords":"Medicine; Head and neck squamous-cell carcinoma; Radiation therapy; Ultrasound; Head and neck cancer; Radiology; Linear discriminant analysis; Head and neck; Concomitant; Oncology; Internal medicine; Surgery; Artificial intelligence","score_opus":0.012847657991616898,"score_gpt":0.30863148367151094,"score_spread":0.29578382567989403,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2973045916","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9225012,0.0003009713,0.07523857,0.0003748194,0.0008966495,0.00049673254,0.000060764978,0.000033277982,0.00009700851],"genre_scores_gemma":[0.9594535,0.000021529964,0.039162718,0.00041938122,0.00046327818,0.000007841291,0.00039299877,0.000054202952,0.000024553141],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99812484,0.00024523656,0.00061032013,0.0003267403,0.00039078124,0.00030208332],"domain_scores_gemma":[0.99566984,0.0014411184,0.0013307546,0.00012532505,0.0012755492,0.0001574151],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005575815,0.00027060646,0.0005822385,0.00024671905,0.00012301485,0.00004391398,0.0002823118,0.00017879967,0.000035790334],"category_scores_gemma":[0.0009911718,0.00019890549,0.00015238408,0.00022366513,0.00021819051,0.0002537943,0.00002256877,0.0011725005,0.0000033698682],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0028648,0.0004463029,0.9504175,0.000044915218,0.00020761586,0.000018950925,0.0003939507,0.0348779,0.004337893,0.00032747063,0.000051954008,0.006010738],"study_design_scores_gemma":[0.037323568,0.01592219,0.14146532,0.000509,0.00049603765,0.00021250176,0.000301336,0.7968191,0.0021552218,0.00038791823,0.0038870056,0.00052082783],"about_ca_topic_score_codex":0.00006578219,"about_ca_topic_score_gemma":0.0000042043857,"teacher_disagreement_score":0.8089522,"about_ca_system_score_codex":0.000648357,"about_ca_system_score_gemma":0.00082679006,"threshold_uncertainty_score":0.811113},"labels":[],"label_agreement":null},{"id":"W2973179191","doi":"10.1016/j.carj.2019.06.002","title":"Sample-Size Determination Methodologies for Machine Learning in Medical Imaging Research: A Systematic Review","year":2019,"lang":"en","type":"review","venue":"Canadian Association of Radiologists Journal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":298,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Francis Xavier University; Hospital for Sick Children; University of Toronto","funders":"","keywords":"Sample size determination; Sample (material); Medicine; Machine learning; Computer science; Artificial intelligence; Data mining; Data science; Medical physics; Statistics","score_opus":0.15210933942869703,"score_gpt":0.46918625880969084,"score_spread":0.3170769193809938,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2973179191","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000017622611,0.98882025,0.002940688,0.0049401745,0.000507429,0.0024934271,0.000054655586,0.000024228613,0.00021739007],"genre_scores_gemma":[0.00002455619,0.9906147,0.0071840947,0.0007974238,0.00031405987,0.00014823824,0.00014161761,0.00006623227,0.0007090827],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9902382,0.0051759374,0.0021694358,0.00041106986,0.0011336849,0.0008716546],"domain_scores_gemma":[0.964917,0.03079964,0.002491015,0.00033290102,0.0007803949,0.00067901687],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03976215,0.00036094713,0.004391814,0.0013278753,0.00020706872,0.000073334,0.0005746174,0.00058840215,0.00012597951],"category_scores_gemma":[0.44601047,0.00027547346,0.0008250656,0.00069374,0.00013824945,0.00009448436,0.00005197186,0.004046754,0.000009895908],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007519538,0.000016230171,0.0009317398,0.6241889,0.00028090557,0.00022120062,0.00005956295,0.0000032332555,1.8068755e-7,0.00007880402,0.0034723165,0.3707394],"study_design_scores_gemma":[0.00096435554,0.00014165042,0.000077550634,0.62421185,0.001998827,0.0025271953,0.000055037304,0.004190386,6.14052e-8,0.00031346723,0.36521077,0.00030885046],"about_ca_topic_score_codex":0.0019475803,"about_ca_topic_score_gemma":0.001208652,"teacher_disagreement_score":0.40624833,"about_ca_system_score_codex":0.004940921,"about_ca_system_score_gemma":0.005078908,"threshold_uncertainty_score":0.9999697},"labels":[],"label_agreement":null},{"id":"W2974585575","doi":"10.1148/radiol.2019190357","title":"Bone Marrow and Tumor Radiomics at <sup>18</sup>F-FDG PET/CT: Impact on Outcome Prediction in Non–Small Cell Lung Cancer","year":2019,"lang":"en","type":"article","venue":"Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":64,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Cancer Institute; Natural Sciences and Engineering Research Council of Canada","keywords":"Medicine; Bone marrow; Proportional hazards model; Penumbra; Radiology; Nuclear medicine; Cancer; Lung cancer; Cohort; Standardized uptake value; Primary tumor; Concordance; Positron emission tomography; Oncology; Internal medicine; Metastasis","score_opus":0.008121937660733807,"score_gpt":0.2841735014077314,"score_spread":0.2760515637469976,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2974585575","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9936299,0.0011300932,0.00006184675,0.00162585,0.0004954474,0.0007589151,0.000029444318,0.00006300199,0.002205501],"genre_scores_gemma":[0.99370605,0.00032695133,0.00044481608,0.0016832188,0.00037027927,0.00004407947,0.00006352906,0.000062311694,0.0032987844],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980061,0.00013475996,0.0005052221,0.0005761101,0.00017689893,0.00060090364],"domain_scores_gemma":[0.9988835,0.000253672,0.00015131845,0.000380563,0.000029650659,0.0003012991],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00060318183,0.00031678414,0.00083922414,0.00031655977,0.00006934824,0.000016739868,0.00012549026,0.00006387508,0.0007397191],"category_scores_gemma":[0.00015891608,0.00025150552,0.000143105,0.00016946116,0.00013226538,0.000059219168,0.00007680279,0.0008874276,0.000063424646],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004135269,0.00008250803,0.97799736,0.00024570184,0.00006767386,0.0009827918,0.00022546425,0.007580502,0.006073575,0.000027517555,0.0052992976,0.0010040889],"study_design_scores_gemma":[0.0062707746,0.0006538877,0.4677097,0.00018982014,0.00014132008,0.0064453967,0.00006710072,0.5147343,0.00017883192,0.000021012931,0.0032896455,0.0002981997],"about_ca_topic_score_codex":0.00043647224,"about_ca_topic_score_gemma":0.0000132636205,"teacher_disagreement_score":0.51028764,"about_ca_system_score_codex":0.0006428513,"about_ca_system_score_gemma":0.00011287695,"threshold_uncertainty_score":0.99999374},"labels":[],"label_agreement":null},{"id":"W2974630971","doi":"10.21037/jmai.2019.09.04","title":"Artificial intelligence and colorectal polyp detection","year":2019,"lang":"en","type":"article","venue":"Journal of Medical Artificial Intelligence","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vancouver General Hospital; University of British Columbia","funders":"","keywords":"Colorectal cancer; Colonoscopy; Incidence (geometry); Medicine; Cancer; Cause of death; Internal medicine; Oncology; General surgery; Disease","score_opus":0.028525185784608133,"score_gpt":0.33072993466385864,"score_spread":0.30220474887925053,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2974630971","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8253472,0.0004291079,0.16056728,0.011419946,0.0016523533,0.00019409935,7.4535575e-7,0.000028204338,0.0003610656],"genre_scores_gemma":[0.9958224,0.0004273437,0.0016671653,0.0008222405,0.0011838304,0.000002011689,0.0000011349061,0.000024445673,0.000049398583],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964459,0.00011638704,0.0012191423,0.00028237386,0.0015701094,0.00036609266],"domain_scores_gemma":[0.99803203,0.00045713357,0.00038314672,0.00016922934,0.0002540701,0.00070438796],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0024912078,0.00020052391,0.00055216294,0.00029209102,0.000096543234,0.000079962294,0.00030368587,0.00025585745,0.0012513429],"category_scores_gemma":[0.0031592401,0.00015473191,0.00018815346,0.00037888592,0.000386127,0.00016320778,0.00009887455,0.0015530711,0.00015845505],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005808212,0.00026462472,0.0018017483,0.000073101975,0.00007215658,0.00029602743,0.00042051557,0.00012043459,0.01612269,0.007306185,0.000051350034,0.9728903],"study_design_scores_gemma":[0.00031593684,0.006140815,0.004463661,0.0017796321,0.0003835228,0.0105067175,0.004005126,0.5681772,0.32524076,0.071750954,0.00641401,0.00082165183],"about_ca_topic_score_codex":0.00006613024,"about_ca_topic_score_gemma":0.000017263977,"teacher_disagreement_score":0.97206867,"about_ca_system_score_codex":0.00008182642,"about_ca_system_score_gemma":0.0002910991,"threshold_uncertainty_score":0.9996616},"labels":[],"label_agreement":null},{"id":"W2975022009","doi":"","title":"Training of deep convolutional neural nets to extract radiomic signatures of tumors","year":2019,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Convolutional neural network; Artificial intelligence; Voxel; Pattern recognition (psychology); Computer science; Histogram; Radiomics; Feature (linguistics); Minimum bounding box; Deep learning; Image (mathematics); Process (computing)","score_opus":0.013733800990688829,"score_gpt":0.2902369975954875,"score_spread":0.27650319660479866,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2975022009","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98608994,0.00026378332,0.00319769,0.0014175029,0.00021106306,0.00023328762,0.0000021690967,0.00002702204,0.008557556],"genre_scores_gemma":[0.9908038,0.0000032710107,0.00733783,0.0011845675,0.000077865305,0.0000021431817,0.000011281875,0.000016246304,0.0005630454],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99897707,0.00002890951,0.00032165728,0.00017651405,0.0002945317,0.00020134106],"domain_scores_gemma":[0.99935305,0.00016149458,0.0000992221,0.00016267526,0.00006568096,0.00015789804],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027823975,0.000102307946,0.00037376615,0.00014786782,0.000015825459,0.0000040077402,0.000104303435,0.0000522089,0.00083051826],"category_scores_gemma":[0.00027226334,0.00008130255,0.000105253726,0.0001406412,0.0000775538,0.000041958887,0.00002638081,0.0002781367,0.00001357415],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00054566487,0.00023697666,0.09437341,0.0003430202,0.00019891927,0.000056019122,0.00248153,0.017852979,0.7424634,0.0067403256,0.0024828492,0.13222487],"study_design_scores_gemma":[0.004149566,0.0010967638,0.3660833,0.00043093576,0.000107430984,0.00029507573,0.000998628,0.610443,0.010979631,0.00029773006,0.0047618398,0.0003560767],"about_ca_topic_score_codex":0.00005665175,"about_ca_topic_score_gemma":0.0000014458586,"teacher_disagreement_score":0.7314838,"about_ca_system_score_codex":0.000022603892,"about_ca_system_score_gemma":0.00007899402,"threshold_uncertainty_score":0.9093593},"labels":[],"label_agreement":null},{"id":"W2977457995","doi":"10.1016/j.media.2019.101568","title":"Segmentation and quantification of infarction without contrast agents via spatiotemporal generative adversarial learning","year":2019,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":71,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Western University","keywords":"Artificial intelligence; Computer science; Segmentation; Pattern recognition (psychology); Discriminator; Encoder; Generator (circuit theory); Centroid; Contrast (vision); Feature (linguistics); Power (physics)","score_opus":0.008969040013805935,"score_gpt":0.3076035449077018,"score_spread":0.29863450489389587,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2977457995","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6496129,0.00005924918,0.348339,0.0014155863,0.0000913229,0.00018554651,0.000001607543,0.000024982151,0.00026981038],"genre_scores_gemma":[0.9937786,0.00009070695,0.00482224,0.00036210977,0.00012278023,0.0000066355424,0.00029413486,0.000013450829,0.000509333],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982617,0.00017518531,0.0004278276,0.00029900693,0.0006830102,0.00015329057],"domain_scores_gemma":[0.9991493,0.00008412681,0.00025029664,0.00015606458,0.00015401216,0.00020616857],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007782631,0.00012268109,0.00046096116,0.0002940273,0.00006726745,0.000025136636,0.000057679263,0.000102111146,0.0012117189],"category_scores_gemma":[0.00069156324,0.000103826664,0.00013309564,0.0004750632,0.00016684581,0.00014661887,0.000030876232,0.00037274839,0.000020657037],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017204089,0.0001377869,0.82943213,0.000112043024,0.0017537898,0.000011117142,0.00072213187,0.00085836183,0.10922062,0.000048634556,0.00011006834,0.05742126],"study_design_scores_gemma":[0.0020479457,0.00014955428,0.16635124,0.000050545514,0.0018181397,0.000012552517,0.0002454051,0.82505447,0.0036709832,0.000020740812,0.00046684692,0.00011157113],"about_ca_topic_score_codex":0.0005269399,"about_ca_topic_score_gemma":0.000015046445,"teacher_disagreement_score":0.8241961,"about_ca_system_score_codex":0.000033688153,"about_ca_system_score_gemma":0.00006456335,"threshold_uncertainty_score":0.9997013},"labels":[],"label_agreement":null},{"id":"W2978236883","doi":"10.1109/access.2019.2945524","title":"SISC: End-to-End Interpretable Discovery Radiomics-Driven Lung Cancer Prediction via Stacked Interpretable Sequencing Cells","year":2019,"lang":"en","type":"article","venue":"IEEE Access","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Nvidia","keywords":"Interpretability; Radiomics; Discriminative model; Computer science; Lung cancer; Artificial intelligence; Pipeline (software); Machine learning; Medicine; Pathology","score_opus":0.010658166018932278,"score_gpt":0.3067761257050322,"score_spread":0.29611795968609994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2978236883","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90798134,0.00027193208,0.08259533,0.00087297463,0.0040907376,0.00092332216,0.0000666579,0.00016997111,0.0030277392],"genre_scores_gemma":[0.9917053,0.00019006783,0.0011486331,0.002495741,0.00068632973,0.00008441284,0.000050352803,0.00009766652,0.0035414938],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973954,0.000092623566,0.0005685899,0.00073072076,0.00053748826,0.00067517767],"domain_scores_gemma":[0.9984991,0.00015332206,0.0002113023,0.000638209,0.0001206435,0.00037743928],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000448518,0.00034709784,0.00066407106,0.00032824758,0.00012384912,0.00037157498,0.0005587179,0.00015113068,0.000940157],"category_scores_gemma":[0.000093271075,0.00030667306,0.00018536267,0.00043192867,0.000090841255,0.0013515335,0.00022592983,0.0008235918,0.000082148814],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00049765,0.00012647067,0.18124975,0.00084273756,0.00047774074,0.00008802123,0.0020318748,0.054874618,0.73052925,0.00004445668,0.011738617,0.017498834],"study_design_scores_gemma":[0.0025478727,0.00031992633,0.0078073726,0.0020486545,0.00050840684,0.00009516107,0.00018923628,0.90334404,0.07663303,0.00008391525,0.005780672,0.00064170954],"about_ca_topic_score_codex":0.0024293577,"about_ca_topic_score_gemma":0.000046126792,"teacher_disagreement_score":0.84846944,"about_ca_system_score_codex":0.0008575959,"about_ca_system_score_gemma":0.00034792506,"threshold_uncertainty_score":0.9999731},"labels":[],"label_agreement":null},{"id":"W2979332613","doi":"10.1007/978-3-030-32692-0_61","title":"Renal Cell Carcinoma Staging with Learnable Image Histogram-Based Deep Neural Network","year":2019,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; University of British Columbia","funders":"","keywords":"Computer science; Artificial intelligence; Artificial neural network; Histogram; Renal cell carcinoma; Image (mathematics); Pattern recognition (psychology); Pathology; Medicine","score_opus":0.0073384954432499615,"score_gpt":0.22901550894328337,"score_spread":0.2216770135000334,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2979332613","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0033890794,0.00073333073,0.984005,0.0014804497,0.0008411341,0.00048014033,0.0000016702747,0.00009804865,0.008971162],"genre_scores_gemma":[0.61795014,0.000010705375,0.37144363,0.0061457185,0.0013794563,0.0000056395634,0.00004503446,0.00013880029,0.0028808636],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99674284,0.00003399729,0.00037717717,0.0010640997,0.0009382068,0.0008436491],"domain_scores_gemma":[0.9981942,0.00028805356,0.00026044517,0.0007844239,0.0001796564,0.0002932237],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00066828076,0.0004929372,0.0006881054,0.00042561797,0.00022273691,0.00018318971,0.0006221374,0.00019787019,0.00011029272],"category_scores_gemma":[0.00006285717,0.00038444786,0.00014003903,0.00034695675,0.0008997475,0.00013154127,0.00021640434,0.002074878,0.00003240814],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015805753,0.000052791605,0.008616701,0.00035871708,0.000018106875,0.0012176457,0.00026987196,0.7458614,0.0011356481,0.0002010663,0.00021223702,0.24189772],"study_design_scores_gemma":[0.0012421842,0.00045980597,0.00061545323,0.00054324797,0.00006447141,0.00013604497,3.132911e-7,0.9913526,0.00028298172,0.0006235542,0.0041867355,0.00049256836],"about_ca_topic_score_codex":0.00008332328,"about_ca_topic_score_gemma":0.000019244995,"teacher_disagreement_score":0.6145611,"about_ca_system_score_codex":0.000339347,"about_ca_system_score_gemma":0.00077434204,"threshold_uncertainty_score":0.99986076},"labels":[],"label_agreement":null},{"id":"W2979373743","doi":"10.1007/978-3-030-32251-9_63","title":"Unsupervised Clustering of Quantitative Imaging Phenotypes Using Autoencoder and Gaussian Mixture Model","year":2019,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":19,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Hospital; University of Toronto","funders":"","keywords":"Overfitting; Autoencoder; Computer science; Cluster analysis; Artificial intelligence; Pipeline (software); Pattern recognition (psychology); Mixture model; Machine learning; Medical imaging; Probabilistic logic; Unsupervised learning; Deep learning; Artificial neural network","score_opus":0.020617912216807945,"score_gpt":0.2942916779446181,"score_spread":0.27367376572781016,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2979373743","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003332279,0.0012344307,0.9920864,0.00085373316,0.0003899063,0.0002998123,0.000005671926,0.00003399741,0.0017637872],"genre_scores_gemma":[0.33902812,0.000061166465,0.65930974,0.0012161417,0.00014382895,7.3591315e-7,0.000004912209,0.00005316036,0.00018221208],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997967,0.000018799723,0.00039793696,0.0007266449,0.0005289433,0.0003606511],"domain_scores_gemma":[0.99887586,0.00020859859,0.00021027421,0.0004144526,0.00014868376,0.00014215206],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004971514,0.00033967843,0.0006628457,0.000520846,0.00010158728,0.000073519994,0.0003087274,0.00015511557,0.000016150047],"category_scores_gemma":[0.00014686876,0.0002827751,0.00008676592,0.00017107405,0.00078346377,0.00015684575,0.00033002545,0.00088988093,0.0000017199786],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006113808,0.000026645701,0.0013438915,0.0006391841,0.00004422216,0.0000817826,0.0028262504,0.7734945,0.007296693,0.002878916,0.0000048647717,0.21130192],"study_design_scores_gemma":[0.00050573575,0.000071341005,0.00021600586,0.0017423106,0.000054453907,0.000114299524,0.0000016892894,0.9882282,0.00014739698,0.008612648,0.000037170452,0.00026876753],"about_ca_topic_score_codex":0.000042840893,"about_ca_topic_score_gemma":0.000010127506,"teacher_disagreement_score":0.33569583,"about_ca_system_score_codex":0.00012339564,"about_ca_system_score_gemma":0.0005052879,"threshold_uncertainty_score":0.99996245},"labels":[],"label_agreement":null},{"id":"W2979469225","doi":"10.1245/s10434-019-07896-6","title":"ASO Author Reflections: HCC in LIRADS Lesions—Neither the Exception nor the Rule","year":2019,"lang":"en","type":"article","venue":"Annals of Surgical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; Kingston General Hospital; Western University","funders":"","keywords":"Surgical oncology; Medicine; General surgery; Internal medicine","score_opus":0.08008038442012015,"score_gpt":0.4401368768113348,"score_spread":0.3600564923912146,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2979469225","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.664931,0.00048003215,0.00006454394,0.3006231,0.00034876642,0.00032022235,0.0000012946883,0.00002253024,0.03320853],"genre_scores_gemma":[0.9862787,0.0016555559,0.00021203097,0.005800231,0.00031484227,0.00002923606,0.000007021821,0.000017156208,0.005685202],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986263,0.00032796222,0.00036796049,0.00019397381,0.00022608145,0.00025771454],"domain_scores_gemma":[0.99857044,0.0008417854,0.00013176465,0.00028489876,0.00008904709,0.00008204612],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016325022,0.00010123589,0.00036409692,0.00009212144,0.00008077411,0.000009251719,0.00016369132,0.00015262277,0.00073887577],"category_scores_gemma":[0.00019647065,0.000050950217,0.00013969322,0.00029816228,0.00023974311,0.00004283081,0.000060525897,0.0007112952,0.00014799809],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019195434,0.0018935357,0.09363534,0.00014638693,0.0002723842,0.00036789058,0.0038804067,0.0006976663,0.010171594,0.017443111,0.059634116,0.809938],"study_design_scores_gemma":[0.0009895317,0.00049905636,0.05137211,0.000067940164,0.000023160304,0.0001565447,0.00021304704,0.001154616,0.00013474857,0.0009884784,0.94433725,0.00006352476],"about_ca_topic_score_codex":0.00017827206,"about_ca_topic_score_gemma":0.00001615349,"teacher_disagreement_score":0.8847031,"about_ca_system_score_codex":0.000033864555,"about_ca_system_score_gemma":0.00011987077,"threshold_uncertainty_score":0.8090172},"labels":[],"label_agreement":null},{"id":"W2979779808","doi":"10.1016/j.acra.2019.09.001","title":"PET-MR Imaging and MR Texture Analysis in the Diagnosis of Pancreatic Cysts: A Prospective Preliminary Study","year":2019,"lang":"en","type":"article","venue":"Academic Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Research and Development; Capital Health","keywords":"Medicine; Nuclear medicine; Effective diffusion coefficient; Receiver operating characteristic; Positron emission tomography; Standardized uptake value; Mann–Whitney U test; Radiology; Coefficient of variation; Pancreas; Skewness; Magnetic resonance imaging; Internal medicine; Mathematics","score_opus":0.007215919470808679,"score_gpt":0.2982990195403054,"score_spread":0.2910831000694967,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2979779808","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9895551,0.0040144417,0.000049890223,0.0046965494,0.00006599382,0.0009850357,0.0000024778676,0.00002024179,0.00061022147],"genre_scores_gemma":[0.9973795,0.0010092106,0.00017035456,0.0010549601,0.00010514185,0.00016235928,0.000010105136,0.000016137028,0.000092273935],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9982651,0.00038499097,0.00043466393,0.0004190791,0.00020827098,0.00028791904],"domain_scores_gemma":[0.9984353,0.0009414043,0.00017596956,0.00034289848,0.000035525918,0.00006885693],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012063328,0.0001711823,0.0007445396,0.0006580983,0.000041942803,0.0000061986552,0.00023025114,0.0000985522,0.000055043398],"category_scores_gemma":[0.00074454537,0.00011013525,0.00009695793,0.0011267165,0.00021640249,0.000062653824,0.00007278885,0.0013101529,0.0000047069534],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000136446,0.000116338146,0.9906696,0.000052263982,0.00041823828,0.00013771794,0.0055557354,0.000076742464,0.00036059492,0.0001785944,0.0005788497,0.001718899],"study_design_scores_gemma":[0.0017536931,0.00058396196,0.9788658,0.00008392135,0.0011841683,0.00070689025,0.00504816,0.011050486,0.000016746737,0.00026126415,0.0003357741,0.00010913736],"about_ca_topic_score_codex":0.00030409964,"about_ca_topic_score_gemma":0.000005832766,"teacher_disagreement_score":0.011803783,"about_ca_system_score_codex":0.000048455233,"about_ca_system_score_gemma":0.000037170274,"threshold_uncertainty_score":0.56920356},"labels":[],"label_agreement":null},{"id":"W2980534287","doi":"10.1200/jgo.2019.5.suppl.78","title":"A phase I study of MR-HIFU hyperthermia (HT) with radiation (RT) and chemotherapy (CT) for recurrent rectal cancer.","year":2019,"lang":"en","type":"article","venue":"Journal of Global Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Profound Medical (Canada); University of Calgary; Health Sciences Centre; Sunnybrook Health Science Centre","funders":"","keywords":"Medicine; Capecitabine; Hyperthermia; Adverse effect; Radiation therapy; Colorectal cancer; Nuclear medicine; Radiology; Quality of life (healthcare); Sedation; Toxicity; Cancer; Surgery; Internal medicine","score_opus":0.011656984713668472,"score_gpt":0.3749669855702899,"score_spread":0.3633100008566214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2980534287","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9934444,0.0011438009,0.00019315211,0.00396111,0.00042581957,0.0004984454,0.0000044768103,0.000004750952,0.00032403643],"genre_scores_gemma":[0.9975365,0.0003650694,0.0012477982,0.000520144,0.00027540594,0.0000061309534,0.0000013775256,0.000010811168,0.000036766327],"study_design_codex":"design_other","study_design_gemma":"nonrandomized_trial","domain_scores_codex":[0.9990942,0.00006567881,0.00037606942,0.0001213325,0.00020081046,0.00014193435],"domain_scores_gemma":[0.9990251,0.00010123579,0.0004999631,0.0000799926,0.00016535065,0.00012833928],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004212504,0.00009816164,0.00053187495,0.000049444563,0.000024879855,0.000006116414,0.000068734225,0.000041546253,0.000040717267],"category_scores_gemma":[0.000112204725,0.00006569864,0.00006200579,0.00010689555,0.000051804975,0.000051926545,0.0000101167,0.00023167208,4.7401954e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.011356911,0.00319053,0.2008691,0.00009595085,0.00051105494,0.00012350168,0.0007255267,0.00009924829,0.0025290865,0.000050867464,0.0034612915,0.77698696],"study_design_scores_gemma":[0.239076,0.27781913,0.25591278,0.00088699744,0.0016404997,0.0074789855,0.00330536,0.017797334,0.0004238325,0.0002889939,0.19489451,0.00047559573],"about_ca_topic_score_codex":0.00006588953,"about_ca_topic_score_gemma":0.000029989127,"teacher_disagreement_score":0.7765113,"about_ca_system_score_codex":0.0003072223,"about_ca_system_score_gemma":0.0003881696,"threshold_uncertainty_score":0.2679113},"labels":[],"label_agreement":null},{"id":"W2980641956","doi":"10.1016/j.jalz.2019.06.2815","title":"P2‐408: DEFICIT ACCUMULATION IN THE BRAIN MEDIATES THE EFFECT OF AGE ON COGNITION: AN APPLICATION OF THE BRAIN ATROPHY AND LESION INDEX USING CLINICAL ROUTINE MRI","year":2019,"lang":"en","type":"article","venue":"Alzheimer s & Dementia","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Nova Scotia Health Authority; Dalhousie University; Surrey Memorial Hospital; Fraser Health","funders":"","keywords":"Cognition; Montreal Cognitive Assessment; Cognitive decline; Atrophy; Dementia; Effects of sleep deprivation on cognitive performance; Audiology; Psychology; Medicine; Lesion; Internal medicine; Disease; Neuroscience; Cognitive impairment; Psychiatry","score_opus":0.03575233028439126,"score_gpt":0.3687080625536699,"score_spread":0.33295573226927866,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2980641956","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9917106,0.0015144971,0.0012963718,0.0042944704,0.00011296608,0.00094697863,0.000001997618,0.000009128393,0.000113000766],"genre_scores_gemma":[0.99825674,0.000023067045,0.00021465578,0.0013128722,0.00012278109,0.000012758923,0.00004004552,0.000015708496,0.000001385284],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9981895,0.00065808767,0.00043940294,0.00022532468,0.00035126923,0.00013638756],"domain_scores_gemma":[0.99805593,0.0012149103,0.0002754517,0.00038150718,0.000035133857,0.0000370803],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020962171,0.00012283199,0.00026471535,0.000056552526,0.00008060379,0.000017553237,0.00017967525,0.00008277596,0.00001475877],"category_scores_gemma":[0.00030808532,0.00006168563,0.00008709169,0.00020821042,0.00017762856,0.00006178943,0.000061221224,0.00037163368,0.0000028499476],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003437613,0.00014319642,0.89129186,0.000043813732,0.0006920804,0.0000025440966,0.0005919258,0.00088900083,0.013094108,0.0003600184,0.00017969402,0.092368014],"study_design_scores_gemma":[0.0029008063,0.00069941476,0.8623563,0.0001543598,0.0026175634,0.0000118482185,0.00011655356,0.12808691,0.0022347367,0.0002456673,0.00047416383,0.000101650556],"about_ca_topic_score_codex":0.00016309721,"about_ca_topic_score_gemma":0.000014644489,"teacher_disagreement_score":0.1271979,"about_ca_system_score_codex":0.000004169392,"about_ca_system_score_gemma":0.000021980599,"threshold_uncertainty_score":0.25154668},"labels":[],"label_agreement":null},{"id":"W2981137639","doi":"10.1200/jgo.2019.5.suppl.77","title":"Magnetic resonance-guided high intensity focused ultrasound (MR-HIFU) hyperthermia for primary rectal cancer: A virtual feasibility analysis.","year":2019,"lang":"en","type":"article","venue":"Journal of Global Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Calgary; Profound Medical (Canada); Health Sciences Centre; Sunnybrook Health Science Centre","funders":"","keywords":"Medicine; Magnetic resonance imaging; High-intensity focused ultrasound; Ultrasound; Radiology; Nuclear medicine; Colorectal cancer; Radiation therapy; Hyperthermia; Cancer","score_opus":0.016076401611926677,"score_gpt":0.32887845804022103,"score_spread":0.31280205642829434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2981137639","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9868548,0.0019790428,0.0008598914,0.00679614,0.0015226041,0.00045833245,0.00003232932,0.000021922933,0.0014749587],"genre_scores_gemma":[0.9859571,0.00028986274,0.008282058,0.004361195,0.0006725189,0.0000067784,0.000012895294,0.000018738,0.00039886285],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99774444,0.00018637822,0.0008823421,0.00033626982,0.00044134035,0.00040920655],"domain_scores_gemma":[0.99764675,0.00048249363,0.0005957732,0.00029360576,0.0006482537,0.00033313458],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012608025,0.0002143646,0.0014677517,0.00013221854,0.000067638335,0.000022311631,0.00025415278,0.00023091574,0.00027068114],"category_scores_gemma":[0.0013339033,0.00016423633,0.00056709355,0.0005224771,0.00019928944,0.000097273434,0.000055027227,0.0006656137,0.000009653799],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0059594675,0.00056955364,0.84707195,0.00007106123,0.00087638915,0.0002664583,0.00012355791,0.00028574752,0.009909949,0.00021097713,0.016265027,0.11838984],"study_design_scores_gemma":[0.009134486,0.0065250043,0.9338225,0.000107957705,0.0021346232,0.0018695596,0.00008695519,0.001443286,0.00008671899,0.0005603858,0.04401945,0.00020908155],"about_ca_topic_score_codex":0.00032970787,"about_ca_topic_score_gemma":0.00010489508,"teacher_disagreement_score":0.11818076,"about_ca_system_score_codex":0.001815436,"about_ca_system_score_gemma":0.0011361035,"threshold_uncertainty_score":0.6697363},"labels":[],"label_agreement":null},{"id":"W2981472215","doi":"10.1016/j.jtho.2019.08.1233","title":"P1.16-07 Real World Evidence of the Impact of Immunotherapy in Patients with Advanced Lung Cancer","year":2019,"lang":"en","type":"article","venue":"Journal of Thoracic Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Roche (Canada)","funders":"","keywords":"Medicine; Lung cancer; Immunotherapy; Oncology; Internal medicine; Population; Cancer; Performance status; Targeted therapy; Biomarker; Stage (stratigraphy); Chemotherapy","score_opus":0.01055610398592287,"score_gpt":0.4332620181733169,"score_spread":0.422705914187394,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2981472215","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9963185,0.0012582822,0.00004669357,0.001160849,0.00033588381,0.000251881,0.0000012168874,0.0000020012083,0.0006246862],"genre_scores_gemma":[0.99803305,0.0005631416,0.0009583681,0.00015785752,0.000065592445,0.0000017529841,3.8701387e-7,0.00001458205,0.0002052486],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9986829,0.00017796387,0.00055355555,0.00009287682,0.00032460986,0.00016810215],"domain_scores_gemma":[0.9982194,0.00025336078,0.0010169714,0.000203331,0.00024016053,0.000066795255],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00072818855,0.00009996217,0.00061114173,0.00019063104,0.000014316006,0.0000029196005,0.00020633415,0.00005509938,0.00022653746],"category_scores_gemma":[0.00017764966,0.000051563427,0.00016264751,0.0002967672,0.00010929223,0.0001131914,0.000029210169,0.000626417,5.7690477e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005592878,0.00022889787,0.8821926,0.00009390747,0.00014757055,0.000008531904,0.00030701957,0.0017240571,0.004731163,0.0000038096764,0.00018990823,0.10477967],"study_design_scores_gemma":[0.0024275214,0.0026832395,0.99063796,0.0027283242,0.00008343551,0.000025113546,0.00004204009,0.0006601336,0.00042865227,0.000026010935,0.00020246819,0.000055093173],"about_ca_topic_score_codex":0.00041679104,"about_ca_topic_score_gemma":0.00004214393,"teacher_disagreement_score":0.108445376,"about_ca_system_score_codex":0.0005769109,"about_ca_system_score_gemma":0.00071044953,"threshold_uncertainty_score":0.2721505},"labels":[],"label_agreement":null},{"id":"W2981759705","doi":"10.1016/j.jtho.2019.08.1710","title":"P2.11-10 Discovery of Potential Biomarkers That Discriminate Early Stage NSCLC from Controls by Non-Targeted Metabolomics Profiling","year":2019,"lang":"en","type":"article","venue":"Journal of Thoracic Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Medicine; Metabolomics; Metabolome; Lung cancer; Oncology; Stage (stratigraphy); Adenocarcinoma; Carcinoma; Internal medicine; Concordance; Metabolite; Cancer; Bioinformatics; Biology","score_opus":0.010663085844505609,"score_gpt":0.3424001193653149,"score_spread":0.3317370335208093,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2981759705","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9829232,0.0011438768,0.010011411,0.0030482884,0.0017788031,0.00037109616,0.00007604651,0.0000126444465,0.0006346076],"genre_scores_gemma":[0.9857457,0.00018679137,0.011600033,0.0004163261,0.00036104044,0.0000028442153,0.000053307354,0.00004477847,0.0015891661],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99752593,0.0003122965,0.00094512606,0.00027561162,0.000545526,0.0003955132],"domain_scores_gemma":[0.9974474,0.00037243098,0.001418162,0.00028849914,0.00022162909,0.0002519248],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014161221,0.00024552856,0.001318877,0.00026869038,0.000050545583,0.00004701578,0.0003213376,0.00025058383,0.000224851],"category_scores_gemma":[0.00042050082,0.00018067153,0.0004098152,0.00015146566,0.00021622043,0.00038970704,0.00009310614,0.0008830985,0.00001235818],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0072518913,0.00053601875,0.057155505,0.00018248902,0.0013237415,0.00048009574,0.00039354563,0.0001418597,0.8983665,0.000035097415,0.0024993496,0.03163389],"study_design_scores_gemma":[0.042205907,0.015161446,0.30383748,0.0027474384,0.011113834,0.0017159834,0.008307197,0.06850041,0.47922584,0.0012941441,0.06386687,0.0020234606],"about_ca_topic_score_codex":0.00021123854,"about_ca_topic_score_gemma":0.0000033108934,"teacher_disagreement_score":0.41914067,"about_ca_system_score_codex":0.0001607838,"about_ca_system_score_gemma":0.00042255557,"threshold_uncertainty_score":0.7367571},"labels":[],"label_agreement":null},{"id":"W2981907877","doi":"10.29173/aar98","title":"On-unit CT measures as tools for artificial intelligence to identify random vs. systematic anatomical changes in radiotherapy patients","year":2019,"lang":"en","type":"article","venue":"Alberta Academic Review","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Medicine; Tomotherapy; Radiation therapy; Chin; Head and neck cancer; Nuclear medicine; Dosimetry; Radiology; Anatomy","score_opus":0.04501397797228483,"score_gpt":0.3913531502911383,"score_spread":0.34633917231885347,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2981907877","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8714058,0.061889198,0.0034490211,0.043670725,0.0011158603,0.017709466,0.000006577261,0.000061329134,0.0006920522],"genre_scores_gemma":[0.86658907,0.07190164,0.00060998934,0.058435526,0.00032536132,0.0010534485,0.00007231984,0.00011676757,0.0008958595],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.9973126,0.00029481435,0.0009713628,0.00048581357,0.00051997055,0.0004154069],"domain_scores_gemma":[0.99631315,0.002675568,0.0002434265,0.0004231763,0.00008553517,0.00025913696],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0020646574,0.00027465844,0.0013974115,0.00020395142,0.000041961866,0.000040115105,0.00037664452,0.00011741738,0.00024410583],"category_scores_gemma":[0.011187675,0.0002013767,0.00020411971,0.00037639675,0.000039646977,0.000105393396,0.0000382911,0.0007883258,0.00042441656],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003116627,0.0007104949,0.03326684,0.2337496,0.00081245945,0.00004755286,0.0019076514,0.00019212306,0.0028053173,0.023830866,0.014054004,0.68550646],"study_design_scores_gemma":[0.01019761,0.0036917217,0.0055135237,0.7364378,0.0019285753,0.00033583044,0.0002611014,0.024565974,0.0024150761,0.0074528037,0.20462334,0.0025766576],"about_ca_topic_score_codex":0.00010929987,"about_ca_topic_score_gemma":0.000016383516,"teacher_disagreement_score":0.6829298,"about_ca_system_score_codex":0.00012326574,"about_ca_system_score_gemma":0.00006922327,"threshold_uncertainty_score":0.99714154},"labels":[],"label_agreement":null},{"id":"W2981946351","doi":"10.1093/eurheartj/ehz747.0001","title":"29Prognostic safety of automatic cancellation of rest myocardial perfusion scan by machine learning: a report from multicenter REFINE SPECT registry of new generation SPECT","year":2019,"lang":"en","type":"article","venue":"European Heart Journal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Medicine; SSS*; Myocardial perfusion imaging; Receiver operating characteristic; Revascularization; Myocardial infarction; Population; Nuclear medicine; Perfusion scanning; Cutoff; Stress testing (software); Perfusion; Radiology; Artificial intelligence; Internal medicine; Computer science","score_opus":0.01863755320107973,"score_gpt":0.2818984532114607,"score_spread":0.26326090001038094,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2981946351","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.993201,0.0008077269,0.0011796845,0.001158717,0.00045793815,0.0002162631,0.000010117635,0.000021301943,0.0029472183],"genre_scores_gemma":[0.99199075,0.0002662113,0.0050401944,0.00007625523,0.0008613228,1.961042e-7,0.00012260856,0.00004457822,0.0015979173],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99769145,0.00039178797,0.00094213174,0.00023725102,0.00056001125,0.0001773856],"domain_scores_gemma":[0.99834585,0.00011942618,0.0008872184,0.00032212815,0.00012756496,0.0001978231],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013308385,0.00015344015,0.0005251911,0.00012257311,0.00006671777,0.000019083565,0.00010089961,0.000033049062,0.0005559641],"category_scores_gemma":[0.0013524216,0.00012872006,0.00017895148,0.00013828713,0.00007349275,0.000068892485,0.000048685077,0.00069291954,0.000013409607],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032799377,0.00012231957,0.4765272,0.00011473443,0.00010885496,0.00022015334,0.00045894107,0.0020257393,0.49883673,0.0000029313649,0.010701721,0.010552667],"study_design_scores_gemma":[0.0062966486,0.0011693605,0.7530145,0.002147311,0.0003520401,0.0017488993,0.00010785278,0.18145227,0.017905418,0.000007948541,0.0355236,0.00027412124],"about_ca_topic_score_codex":0.00047099777,"about_ca_topic_score_gemma":0.0000056265967,"teacher_disagreement_score":0.4809313,"about_ca_system_score_codex":0.000080130456,"about_ca_system_score_gemma":0.00018840795,"threshold_uncertainty_score":0.60874176},"labels":[],"label_agreement":null},{"id":"W2981959691","doi":"10.1038/s41597-019-0241-0","title":"Distributed radiomics as a signature validation study using the Personal Health Train infrastructure","year":2019,"lang":"en","type":"article","venue":"Scientific Data","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":67,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre","funders":"","keywords":"Radiomics; Computer science; Signature (topology); Data mining; Artificial intelligence; Mathematics","score_opus":0.03081040018237908,"score_gpt":0.3496671711163765,"score_spread":0.31885677093399745,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2981959691","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9862325,0.00021105795,0.0037925413,0.005996808,0.0016996618,0.001002716,0.00093225844,0.000049958307,0.00008249212],"genre_scores_gemma":[0.9894462,0.0000039557663,0.0016186654,0.00085547246,0.0002062373,0.000002129399,0.0071744337,0.00001997035,0.0006729092],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979259,0.0001654135,0.00025952494,0.0006559868,0.0006765973,0.00031661478],"domain_scores_gemma":[0.9982662,0.000066275345,0.00014803166,0.0012777119,0.00007077002,0.00017097099],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025835575,0.00014012464,0.00024673477,0.00010022425,0.00041751724,0.00030229113,0.00067791773,0.000053575983,0.0002974921],"category_scores_gemma":[0.00047828618,0.000090742826,0.00004430022,0.00057515537,0.00019419493,0.00020277454,0.0002972491,0.00066376553,0.000030922503],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004658319,0.0015624494,0.15839916,0.00057591853,0.0007796686,0.00015964732,0.03421872,0.0035055531,0.05066663,0.0007462182,0.599594,0.14932624],"study_design_scores_gemma":[0.0038830764,0.00036800976,0.04885384,0.00023380465,0.00023396582,0.0004283161,0.011524812,0.7690376,0.000105439,0.00034853895,0.16461317,0.0003694101],"about_ca_topic_score_codex":0.00009771962,"about_ca_topic_score_gemma":0.0000063772018,"teacher_disagreement_score":0.7655321,"about_ca_system_score_codex":0.00012111847,"about_ca_system_score_gemma":0.0005761002,"threshold_uncertainty_score":0.3700385},"labels":[],"label_agreement":null},{"id":"W2982239275","doi":"10.1016/j.jtho.2019.08.2370","title":"EP1.16-05 Real World Outcomes of Advanced NSCLC Patients with Liver Metastases","year":2019,"lang":"en","type":"article","venue":"Journal of Thoracic Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Roche (Canada)","funders":"","keywords":"Medicine; Oncology; Lung cancer; Internal medicine; Metastasis; Clinical endpoint; Systemic therapy; Cohort; Population; Performance status; Stage (stratigraphy); Cancer; Clinical trial","score_opus":0.011515542800591949,"score_gpt":0.3777532496586298,"score_spread":0.3662377068580378,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2982239275","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9911448,0.00019783717,0.0002786813,0.0021092657,0.000638319,0.00020352352,0.000004043067,0.000009108664,0.005414467],"genre_scores_gemma":[0.97985786,0.00009322498,0.017407106,0.00083884055,0.00011503952,0.0000012867648,0.0000072128564,0.000022741326,0.0016566636],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99846166,0.00015976375,0.00058771967,0.00013614036,0.0004375917,0.00021710584],"domain_scores_gemma":[0.99803495,0.00037304248,0.0008637229,0.0001938052,0.00034599728,0.00018847879],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006583671,0.00014166911,0.0009057497,0.0003152565,0.000025720306,0.0000062823847,0.00015449127,0.00006204612,0.00033100208],"category_scores_gemma":[0.0003332044,0.00008677635,0.00016822947,0.00019500009,0.00011672758,0.00013533047,0.000043295964,0.00059489626,0.000012819057],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0032072342,0.00069183647,0.65964055,0.00012705699,0.0004446127,0.0002411322,0.00019994909,0.00013833269,0.0006194184,0.00008200872,0.0020588401,0.33254904],"study_design_scores_gemma":[0.0059509454,0.00621442,0.93447477,0.00049398065,0.0008970438,0.00029642845,0.0002692983,0.00019699673,0.0005402375,0.00009781396,0.050387315,0.00018078045],"about_ca_topic_score_codex":0.000035768953,"about_ca_topic_score_gemma":0.000015380127,"teacher_disagreement_score":0.33236825,"about_ca_system_score_codex":0.00018433346,"about_ca_system_score_gemma":0.00025330635,"threshold_uncertainty_score":0.36242408},"labels":[],"label_agreement":null},{"id":"W2982258259","doi":"10.1016/j.jmir.2019.09.002","title":"Preparing for Artificial Intelligence: Systems-Level Implications for the Medical Imaging and Radiation Therapy Professions","year":2019,"lang":"en","type":"article","venue":"Journal of medical imaging and radiation sciences","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":17,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency","funders":"","keywords":"Transformational leadership; Medical radiation; Health care; Medical imaging; Field (mathematics); Medical education; Medicine; Engineering ethics; Psychology; Computer science; Medical physics; Artificial intelligence; Political science; Engineering","score_opus":0.0457468151492713,"score_gpt":0.4098765493419587,"score_spread":0.3641297341926874,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2982258259","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12665546,0.030563625,0.46468663,0.37379813,0.002883793,0.001237732,0.0000086938035,0.000034221408,0.00013169924],"genre_scores_gemma":[0.9879223,0.0068857344,0.0016987522,0.001983776,0.001409975,0.000037006266,0.0000051703832,0.0000136159215,0.000043688477],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977516,0.000092767776,0.00067716715,0.00024574177,0.0009674659,0.00026525074],"domain_scores_gemma":[0.99663144,0.0022400294,0.00041790734,0.00011830285,0.00022474915,0.0003675605],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0063666063,0.00012121823,0.00030147147,0.00021241044,0.0005604064,0.00020803756,0.00028311525,0.000076157834,0.00002449851],"category_scores_gemma":[0.0045949416,0.000068869835,0.000093806804,0.00023137942,0.00046848707,0.00027358573,0.000041826886,0.00042049048,7.2146497e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051177398,0.000055053533,0.0335253,0.00007133784,0.000042242114,0.0000017540175,0.00061349827,0.00011482292,0.0002899359,0.005273501,0.0042334716,0.95572793],"study_design_scores_gemma":[0.0011957916,0.0001406246,0.031176137,0.00042516532,0.000085459964,0.00081198267,0.0039343312,0.9283693,0.00005214193,0.0027666322,0.03091422,0.00012821033],"about_ca_topic_score_codex":0.000027406284,"about_ca_topic_score_gemma":0.0000011470371,"teacher_disagreement_score":0.9555997,"about_ca_system_score_codex":0.000038642807,"about_ca_system_score_gemma":0.0006291547,"threshold_uncertainty_score":0.5500906},"labels":[],"label_agreement":null},{"id":"W2982503154","doi":"","title":"Evaluation of Processing Software for SPECT Myocardial Blood Flow","year":2019,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Correction for attenuation; Nuclear medicine; Software; Blood flow; Coronary artery disease; Cardiac PET; Iterative reconstruction; Single-photon emission computed tomography; Medicine; Artificial intelligence; Positron emission tomography; Radiology","score_opus":0.019316889048662456,"score_gpt":0.3219077464938343,"score_spread":0.30259085744517183,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2982503154","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94124997,0.00044225785,0.044043288,0.00089715037,0.00031685823,0.0010158041,0.0000026549549,0.00007413335,0.011957905],"genre_scores_gemma":[0.9481433,0.0000047662907,0.05077303,0.00026570327,0.00023536729,0.000015854643,0.00002173129,0.000017100769,0.000523162],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990233,0.000028350782,0.0001597508,0.00014893986,0.0005180736,0.00012154345],"domain_scores_gemma":[0.99929905,0.00006011358,0.000058026097,0.00012708401,0.00040323497,0.000052499945],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013357842,0.000064638014,0.00019859843,0.000053748376,0.00002388214,0.0000091318525,0.00004009518,0.00003159831,0.0002794803],"category_scores_gemma":[0.0013068301,0.00004980787,0.00007356797,0.00009171596,0.000023189554,0.000042767842,0.000011647075,0.00009933607,0.000009773512],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000092341084,0.00016946091,0.042401906,0.00051468157,0.00020713806,0.0000020220127,0.00031072917,0.0016706006,0.012663302,0.00014184444,0.0014495739,0.9403764],"study_design_scores_gemma":[0.008004567,0.0004508943,0.015236512,0.0002870198,0.0015578428,0.000052677166,0.000119539145,0.9643249,0.0064988714,0.0010062468,0.0023124514,0.00014848438],"about_ca_topic_score_codex":0.000008772747,"about_ca_topic_score_gemma":4.792613e-7,"teacher_disagreement_score":0.9626543,"about_ca_system_score_codex":0.000025275933,"about_ca_system_score_gemma":0.00025998618,"threshold_uncertainty_score":0.30601132},"labels":[],"label_agreement":null},{"id":"W2982595270","doi":"10.5414/np301234","title":"Brain tumor disparities: From biology to social determinants - The 2019 Brain Tumor Epidemiology Consortium meeting report","year":2019,"lang":"en","type":"article","venue":"Clinical Neuropathology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Cancer Institute; Brain Tumour Foundation of Canada","keywords":"Epidemiology; Brain research; Theme (computing); Brain tumor; Library science; Medicine; Gerontology; Psychology; Pathology; Neuroscience","score_opus":0.04804466565417129,"score_gpt":0.4161799189142296,"score_spread":0.36813525326005836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2982595270","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.869111,0.00015029748,0.0007331151,0.12506099,0.003353094,0.00059729826,0.000045997826,0.00011993963,0.00082824565],"genre_scores_gemma":[0.7854638,0.000023332677,0.0014460228,0.20955983,0.0019193626,0.00003150895,0.00007817254,0.00007577601,0.0014021727],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9917687,0.0036645678,0.0021535794,0.0012910131,0.00017331264,0.0009488177],"domain_scores_gemma":[0.9795001,0.018263467,0.00076778664,0.00093480624,0.00011256062,0.00042127777],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0074113156,0.00035254392,0.0017352693,0.000112090325,0.00022235292,0.000018939043,0.0005436229,0.00028895898,0.00021655414],"category_scores_gemma":[0.07929916,0.00024679725,0.00042461656,0.00019014787,0.00128193,0.000042875476,0.00051156693,0.0019613903,0.0005852742],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031521643,0.00014032605,0.94252706,0.000023703169,0.00004019232,0.004105715,0.000102888494,0.000007240308,0.006013618,0.00056229887,0.03874459,0.0074171824],"study_design_scores_gemma":[0.0020088363,0.0011813954,0.87481487,0.000092229806,0.000110948924,0.004412764,0.000057940488,0.0021270153,0.00005185317,0.001978745,0.112824716,0.00033871806],"about_ca_topic_score_codex":0.000305938,"about_ca_topic_score_gemma":0.000015795638,"teacher_disagreement_score":0.08449884,"about_ca_system_score_codex":0.00003205274,"about_ca_system_score_gemma":0.00020165178,"threshold_uncertainty_score":0.99999845},"labels":[],"label_agreement":null},{"id":"W2982804252","doi":"10.1136/jnnp-2019-abn-2.148","title":"161 Qualitative aspects of cognition in MS &amp; audit of MoCA in LTHTR natalizumab cohort","year":2019,"lang":"en","type":"article","venue":"Journal of Neurology Neurosurgery & Psychiatry","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Natalizumab; Cohort; Cognition; Audit; Montreal Cognitive Assessment; Medicine; Psychology; Internal medicine; Multiple sclerosis; Psychiatry; Business; Cognitive impairment; Accounting","score_opus":0.013284492096923116,"score_gpt":0.31974830476046606,"score_spread":0.30646381266354294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2982804252","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98546803,0.00042375657,0.000049993574,0.009393077,0.002725304,0.0002318837,0.0000055565447,0.000007646571,0.0016947326],"genre_scores_gemma":[0.9961218,0.00027775657,0.00028186673,0.003069423,0.00016955657,0.0000023028083,0.000006843003,0.000033103126,0.00003735116],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9968219,0.00063601864,0.0014897109,0.0002725416,0.00048556185,0.00029429857],"domain_scores_gemma":[0.99739015,0.00081215164,0.0012464701,0.00025557625,0.00016782952,0.00012784392],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016304627,0.00018670458,0.0010243146,0.0009309826,0.00001700632,0.0000052248765,0.00016278181,0.00016114536,0.00012372177],"category_scores_gemma":[0.0010815935,0.00016803142,0.00025496376,0.0004725414,0.0001970208,0.00012971123,0.000036436933,0.0014741888,0.000008138282],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0023268147,0.0008008769,0.9772363,0.00030290612,0.00009149576,0.00035929913,0.0005401683,0.00038032176,0.015087276,0.00042621332,0.002050126,0.00039823557],"study_design_scores_gemma":[0.0043869694,0.0018062507,0.9847161,0.0005091581,0.00010702101,0.0021308872,0.00013206077,0.00046767536,0.00028319607,0.0033331425,0.001967255,0.00016025847],"about_ca_topic_score_codex":0.000037363163,"about_ca_topic_score_gemma":0.000022770884,"teacher_disagreement_score":0.014804079,"about_ca_system_score_codex":0.00002164951,"about_ca_system_score_gemma":0.00038293592,"threshold_uncertainty_score":0.68521225},"labels":[],"label_agreement":null},{"id":"W2983101271","doi":"10.1093/neuonc/noz175.328","title":"EPID-28. WHAT DO PATTERNS OF “UNCLASSIFIED” BRAIN TUMORS TELL US ABOUT INCIDENCE RATES OF NON-MALIGNANT BRAIN TUMORS IN CANADA?","year":2019,"lang":"en","type":"article","venue":"Neuro-Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Western University; University of Alberta","funders":"","keywords":"Incidence (geometry); Medicine; Population; Demography; Epidemiology; Disease; Pathology; Environmental health","score_opus":0.010641020316094056,"score_gpt":0.29376110912570885,"score_spread":0.2831200888096148,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2983101271","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98345244,0.00031979984,0.00010583772,0.014009369,0.0008114523,0.0005645053,0.000010990632,0.000014960391,0.0007106219],"genre_scores_gemma":[0.9863545,0.0002873526,0.0002034482,0.012848811,0.00010734164,0.000017577244,0.000015862584,0.000047728492,0.00011741286],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9969822,0.0003860034,0.0010020084,0.0005416908,0.00049680047,0.00059128966],"domain_scores_gemma":[0.99604905,0.002487939,0.00055354397,0.0005089506,0.00011771507,0.00028279726],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010137196,0.00027566202,0.0011694187,0.0002786235,0.000031359126,0.0000162322,0.00038123757,0.0001450965,0.0002755262],"category_scores_gemma":[0.0021238842,0.00023938803,0.000114575916,0.0003206004,0.00018921492,0.00015153777,0.00017141677,0.00092168985,0.000014635616],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016204438,0.00012866955,0.70813,0.00032699195,0.00002332201,0.0011697034,0.00061933894,0.0005069587,0.26573685,0.000058722224,0.0020871358,0.02105029],"study_design_scores_gemma":[0.0052087526,0.0021589447,0.8986819,0.0026149272,0.00006249823,0.00075093313,0.0022045472,0.019457357,0.046606243,0.000079061174,0.02171879,0.00045604468],"about_ca_topic_score_codex":0.2422176,"about_ca_topic_score_gemma":0.093245745,"teacher_disagreement_score":0.2191306,"about_ca_system_score_codex":0.000502889,"about_ca_system_score_gemma":0.002956314,"threshold_uncertainty_score":0.976196},"labels":[],"label_agreement":null},{"id":"W2985286907","doi":"10.18280/ts.360406","title":"Lung Cancer Detection Based on CT Scan Images by Using Deep Transfer Learning","year":2019,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":118,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Artificial intelligence; Transfer of learning; Lung cancer; Computed tomography; Computer science; Cancer detection; Lung; Cancer; Deep learning; Radiology; Computer vision; Medicine; Pattern recognition (psychology); Pathology; Internal medicine","score_opus":0.006955440247937681,"score_gpt":0.2715386440194762,"score_spread":0.2645832037715385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2985286907","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9148384,0.000262579,0.082285896,0.0008172071,0.00021090596,0.00041134347,0.000004157012,0.00009519227,0.0010743489],"genre_scores_gemma":[0.99773395,0.000021624304,0.0003525967,0.0012681128,0.00021924944,0.000020948877,0.000026469108,0.000047006703,0.00031004322],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99856037,0.00009005963,0.0002462147,0.00032710948,0.00044595508,0.00033030257],"domain_scores_gemma":[0.99956185,0.00007436228,0.000047168603,0.00011501429,0.000041801643,0.0001598188],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00037097864,0.00019193077,0.00026343914,0.00013345665,0.00013645536,0.000042971715,0.000071933275,0.00004018327,0.0022521622],"category_scores_gemma":[0.00002517132,0.00016813783,0.00011620803,0.00014568507,0.000045499095,0.00007846117,0.000007886858,0.00054220675,0.000013626336],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003479333,0.00019642737,0.071259886,0.0002553875,0.0001251606,0.000038646907,0.00021072726,0.11067504,0.66460055,0.000010050332,0.00040512314,0.1518751],"study_design_scores_gemma":[0.0029857175,0.00034209975,0.0048545133,0.0002868853,0.00016672538,0.00001710644,0.00006503394,0.95792216,0.028869208,0.0000018421247,0.004282358,0.0002063784],"about_ca_topic_score_codex":0.00024561808,"about_ca_topic_score_gemma":0.0000043783175,"teacher_disagreement_score":0.8472471,"about_ca_system_score_codex":0.0002126885,"about_ca_system_score_gemma":0.00006701679,"threshold_uncertainty_score":0.9986599},"labels":[],"label_agreement":null},{"id":"W2987983801","doi":"10.1088/1361-6560/ab5427","title":"Automatic classification of dental artifact status for efficient image veracity checks: effects of image resolution and convolutional neural network depth","year":2019,"lang":"en","type":"article","venue":"Physics in Medicine and Biology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; Princess Margaret Cancer Centre; Institute of Cancer Research; Ontario Institute for Cancer Research; University of Toronto; University Health Network","funders":"Canadian Institutes of Health Research; Terry Fox Research Institute; Ontario Institute for Cancer Research","keywords":"Convolutional neural network; Artificial intelligence; Computer science; Resampling; Image quality; Robustness (evolution); Pattern recognition (psychology); Quality assurance; Grid; Visualization; Artifact (error); Computer vision; Image (mathematics); Mathematics; Medicine","score_opus":0.051464698553344755,"score_gpt":0.3661720179653029,"score_spread":0.3147073194119582,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2987983801","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99012905,0.0007091662,0.007933841,0.00042066345,0.00019524347,0.00047191553,0.0000045631737,0.000011262018,0.00012426895],"genre_scores_gemma":[0.9963181,0.00011601954,0.003144331,0.00013310056,0.00017405457,0.00001257406,0.000088318535,0.000007871325,0.0000056576673],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999118,0.000075018535,0.0003055457,0.00019841902,0.00009443313,0.00020859658],"domain_scores_gemma":[0.9990662,0.00051917403,0.00017379317,0.00010669549,0.00006685022,0.000067323126],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037983488,0.0001017923,0.0004115745,0.0000605931,0.000027636876,0.0000021348967,0.00003507504,0.000058684545,0.000007367796],"category_scores_gemma":[0.0003920984,0.000075614,0.00003527279,0.00011503614,0.00047225496,0.00003039222,0.00002976376,0.00018140771,5.899859e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030467883,0.0002144511,0.31712207,0.0016686358,0.00006883402,0.000002305649,0.0004840237,0.00022531193,0.63357806,0.0051906537,0.0002424849,0.040898487],"study_design_scores_gemma":[0.0030223236,0.0007034837,0.43797457,0.00031181905,0.00007654593,0.000010534127,0.00010923933,0.55510265,0.0011425104,0.0014256875,0.000055883433,0.00006476072],"about_ca_topic_score_codex":0.00006533747,"about_ca_topic_score_gemma":0.0000025517086,"teacher_disagreement_score":0.63243556,"about_ca_system_score_codex":0.000029509247,"about_ca_system_score_gemma":0.00003473943,"threshold_uncertainty_score":0.30834493},"labels":[],"label_agreement":null},{"id":"W2988677670","doi":"10.1093/neuonc/noz175.644","title":"PATH-48. THE DNA METHYLATION LANDSCAPE OF CORE AND PERIPHERAL DIFFUSE GLIOMA REGIONS SHOWS LITTLE SPATIAL SUBTYPE HETEROGENEITY AFTER CONSIDERING TUMOR PURITY","year":2019,"lang":"en","type":"article","venue":"Neuro-Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Glioma; DNA methylation; Methylation; Epigenetics; DNA; Biology; Brain tumor; Pathology; Molecular biology; Cancer research; Gene; Genetics; Medicine; Gene expression","score_opus":0.01777987691746194,"score_gpt":0.28961814237103917,"score_spread":0.27183826545357725,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2988677670","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9943691,0.00032740485,0.00028370475,0.003614167,0.0005332434,0.00036308682,0.0000064942747,0.000034458415,0.000468361],"genre_scores_gemma":[0.9975558,0.000048713635,0.00038551606,0.0017247803,0.0002068166,0.000019556332,0.000009674022,0.000023440913,0.000025699323],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99883777,0.00019532035,0.0002809138,0.00028181987,0.0001785818,0.00022559831],"domain_scores_gemma":[0.9989441,0.00041400094,0.00015472676,0.00029606797,0.000063146304,0.00012792806],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027435922,0.00013985379,0.00039087207,0.00006272063,0.000067333014,0.000015687776,0.00008454767,0.00009898555,0.00019668204],"category_scores_gemma":[0.00050195935,0.00009895186,0.0000835582,0.000087275635,0.000219218,0.000046759735,0.000104078325,0.00046546926,0.00000806287],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00064199703,0.00020094194,0.42108116,0.00013562385,0.000056309244,0.0003863734,0.0010616925,0.000020477037,0.56660324,0.00016545373,0.00078715663,0.00885961],"study_design_scores_gemma":[0.016073797,0.0039842995,0.7287223,0.00022503811,0.00065931125,0.0052181,0.00082392944,0.1052749,0.03741039,0.0009319356,0.09994979,0.0007262286],"about_ca_topic_score_codex":0.000086030785,"about_ca_topic_score_gemma":0.00006335083,"teacher_disagreement_score":0.5291928,"about_ca_system_score_codex":0.000038678103,"about_ca_system_score_gemma":0.0001127679,"threshold_uncertainty_score":0.40351397},"labels":[],"label_agreement":null},{"id":"W2990040492","doi":"10.1148/rycan.2019190031","title":"Imaging-based Biomarkers for Predicting and Evaluating Cancer Immunotherapy Response","year":2019,"lang":"en","type":"review","venue":"Radiology Imaging Cancer","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":57,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"National Natural Science Foundation of China; Ministry of Science and Innovation, New Zealand","keywords":"Immunotherapy; Molecular imaging; Medicine; Cancer immunotherapy; Functional imaging; Cancer; Modalities; Biomarker; Oncology; Medical physics; Internal medicine; Radiology; Biology; In vivo","score_opus":0.04577564204199543,"score_gpt":0.43882385040370264,"score_spread":0.39304820836170723,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2990040492","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00055078074,0.9876768,0.0021920796,0.00447323,0.0020224624,0.0025907184,0.00013284618,0.0003109678,0.000050100145],"genre_scores_gemma":[0.0001831634,0.98908615,0.0041622287,0.003127569,0.0010443055,0.0014943135,0.00014226073,0.0004277237,0.00033229016],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9957329,0.00074727397,0.0010102472,0.0012357639,0.00032872878,0.0009451088],"domain_scores_gemma":[0.9955844,0.0024600257,0.00082991977,0.0006622185,0.00020791331,0.00025549866],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.003092483,0.00079184514,0.0027465008,0.00060196983,0.00024266874,0.00008478053,0.00032354306,0.00028323472,0.00010369194],"category_scores_gemma":[0.0013391837,0.00065148296,0.00066552224,0.00032443614,0.00053965347,0.000100176454,0.00007947221,0.0011847683,0.0000044818935],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007632633,0.000025445155,0.012270123,0.010428129,0.000887629,0.00002827836,0.000087673216,0.000050374834,0.0002311123,0.0000049362184,0.003652031,0.971571],"study_design_scores_gemma":[0.003894026,0.00014425114,0.0006040279,0.02047945,0.0031242673,0.0006144994,0.000024086343,0.09517748,0.0000041264047,0.000015276468,0.87526464,0.0006538823],"about_ca_topic_score_codex":0.00033090962,"about_ca_topic_score_gemma":0.0000026810708,"teacher_disagreement_score":0.9709171,"about_ca_system_score_codex":0.00085723767,"about_ca_system_score_gemma":0.002623799,"threshold_uncertainty_score":0.9995936},"labels":[],"label_agreement":null},{"id":"W2990990887","doi":"10.1038/s41746-019-0196-8","title":"Publisher Correction: Development and validation of a deep learning algorithm for improving Gleason scoring of prostate cancer","year":2019,"lang":"en","type":"erratum","venue":"npj Digital Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University Health Network","funders":"","keywords":"Prostate cancer; Algorithm; Computer science; Artificial intelligence; Machine learning; Cancer; Medicine; Internal medicine","score_opus":0.010074030973793646,"score_gpt":0.27254625596355025,"score_spread":0.2624722249897566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2990990887","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12561248,0.08656862,0.2374015,0.01000405,0.32910427,0.016270844,0.0001411247,0.0009363868,0.19396073],"genre_scores_gemma":[0.3232026,0.0023818382,0.022746952,0.0005737788,0.009671469,0.00053847954,0.00646706,0.0006449039,0.6337729],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99768585,0.000023228156,0.0007983137,0.0004903406,0.00066508545,0.00033719247],"domain_scores_gemma":[0.99808365,0.00020828999,0.0008001736,0.00020710909,0.00051164255,0.00018911628],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005554267,0.0003341236,0.0010353765,0.0003596524,0.000073266456,0.00005352842,0.000114719456,0.00026131407,0.00003584367],"category_scores_gemma":[0.0020353796,0.00026893336,0.00009178784,0.0002556713,0.00020993267,0.00028865488,0.00008925072,0.0009905,9.716035e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008689236,0.00004933899,0.0060420237,0.0029949227,0.00017089643,0.000005837737,0.001176825,0.000025869407,0.00014876387,0.0000050494127,0.05076277,0.9385308],"study_design_scores_gemma":[0.009214288,0.0030155638,0.0060305423,0.020311983,0.0011240053,0.00018864611,0.0023499883,0.12336182,0.0010324462,0.000090466165,0.83233696,0.00094330206],"about_ca_topic_score_codex":0.00015535337,"about_ca_topic_score_gemma":0.0000030653441,"teacher_disagreement_score":0.9375875,"about_ca_system_score_codex":0.00016378722,"about_ca_system_score_gemma":0.00043194942,"threshold_uncertainty_score":0.9999763},"labels":[],"label_agreement":null},{"id":"W2990999174","doi":"10.48550/arxiv.1911.10657","title":"Reducing the Human Effort in Developing PET-CT Registration","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; University of Victoria","funders":"","keywords":"Medical physics; Business; Medicine","score_opus":0.055025210406946266,"score_gpt":0.2414717033797318,"score_spread":0.18644649297278554,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2990999174","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9782381,0.00005238291,0.008405383,0.0017047996,0.0003920475,0.00046357015,0.0000011840822,0.00007042349,0.010672079],"genre_scores_gemma":[0.99483097,0.00016501734,0.0003903818,0.00038987093,0.0001512015,9.69316e-7,0.00006481104,0.000028693516,0.0039781113],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99864894,0.00008222754,0.00026084244,0.000617842,0.00011193147,0.00027822782],"domain_scores_gemma":[0.9988853,0.0000756484,0.00022800133,0.00066648924,0.000060104176,0.00008449273],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00064936193,0.0002196816,0.00035822825,0.00021267908,0.0001440864,0.000045393488,0.00035123856,0.000060322185,0.00003491464],"category_scores_gemma":[0.00012853529,0.00019278708,0.0001403186,0.0002737587,0.00012596884,0.00006937808,0.0003170103,0.0014272388,0.000026627793],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014362419,0.00019953151,0.44798595,0.0015340863,0.00038054556,0.008936193,0.0008381153,0.41399595,0.0007861481,0.11991971,0.003371728,0.0019084408],"study_design_scores_gemma":[0.0038036727,0.00013655728,0.20390148,0.0044676256,0.00055459485,0.0006209117,0.0007759907,0.75951326,0.00029754505,0.0139708575,0.01079253,0.001164969],"about_ca_topic_score_codex":0.00093690946,"about_ca_topic_score_gemma":0.000047916623,"teacher_disagreement_score":0.34551734,"about_ca_system_score_codex":0.00039574498,"about_ca_system_score_gemma":0.00035633027,"threshold_uncertainty_score":0.78616285},"labels":[],"label_agreement":null},{"id":"W2991835787","doi":"10.1182/blood-2019-123450","title":"A Prognostic Model Integrating PET-Derived Quantitative Parameters and Image Texture Analyses Using Radiomics in a Large Prospective Phase III Trial, GOYA","year":2019,"lang":"en","type":"article","venue":"Blood","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency","funders":"","keywords":"Medicine; Proportional hazards model; Logistic regression; Progression-free survival; Oncology; Nuclear medicine; Internal medicine; Radiology; Overall survival","score_opus":0.0341315135952375,"score_gpt":0.3748559315591447,"score_spread":0.3407244179639072,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2991835787","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9808241,0.00045560166,0.016554374,0.0001804668,0.00007400088,0.0015782447,0.00001268877,0.00005067594,0.00026983808],"genre_scores_gemma":[0.9251461,0.00004699592,0.07446563,0.00017080319,0.000042866755,0.00003486047,0.000022325929,0.000038943497,0.000031453845],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983839,0.00010976858,0.00042001918,0.00046938026,0.00023514057,0.0003818259],"domain_scores_gemma":[0.99907684,0.00027567663,0.0001965547,0.00020972124,0.00008691336,0.00015429217],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005303871,0.0002472221,0.00068244885,0.00024727982,0.00008340315,0.00007761914,0.000085278094,0.000071891,0.000012977097],"category_scores_gemma":[0.001553862,0.00019866074,0.00010941742,0.0003333877,0.000121568366,0.00017180985,0.00005909857,0.0006891169,0.0000026866264],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.020141011,0.0070865564,0.08416638,0.00068027386,0.001433358,0.0011923151,0.016274974,0.0028033722,0.8610701,0.0017713921,0.000038820748,0.0033414387],"study_design_scores_gemma":[0.11858049,0.0008384365,0.000728662,0.00043850564,0.0005277538,0.00013268468,0.002128794,0.8752552,0.0007664291,0.00037375005,0.0000031330176,0.00022615088],"about_ca_topic_score_codex":0.00009896498,"about_ca_topic_score_gemma":0.000012133565,"teacher_disagreement_score":0.87245184,"about_ca_system_score_codex":0.00006751658,"about_ca_system_score_gemma":0.0001790606,"threshold_uncertainty_score":0.810115},"labels":[],"label_agreement":null},{"id":"W2992918713","doi":"10.1007/s10278-019-00290-4","title":"A Comparison of the Efficiency of Using a Deep CNN Approach with Other Common Regression Methods for the Prediction of EGFR Expression in Glioblastoma Patients","year":2019,"lang":"en","type":"article","venue":"Journal of Digital Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Winnipeg; University of Manitoba; CancerCare Manitoba","funders":"","keywords":"Elastic net regularization; Lasso (programming language); Convolutional neural network; Artificial intelligence; Overfitting; Regression; Feature selection; Linear regression; Deep learning; Regression analysis; Computer science; Regularization (linguistics); Pattern recognition (psychology); Artificial neural network; Machine learning; Statistics; Mathematics","score_opus":0.020176894112262592,"score_gpt":0.35806397776435445,"score_spread":0.33788708365209186,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2992918713","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86330456,0.00035221927,0.13555047,0.00009763232,0.00012962845,0.0003262307,0.0000030621195,0.0000025504505,0.00023362247],"genre_scores_gemma":[0.98028064,0.0000027729782,0.019633627,0.000023224542,0.000031191586,0.0000013224662,8.5704943e-7,0.00001792099,0.0000084559515],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985851,0.00008849115,0.0006870801,0.00010069079,0.00040650027,0.00013210729],"domain_scores_gemma":[0.99808574,0.00031709083,0.0011390446,0.00019196101,0.00022415862,0.000042000313],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00061992113,0.00010561927,0.0004607697,0.00015791232,0.000036998616,0.000017146805,0.00018696113,0.000031411826,0.0000023895236],"category_scores_gemma":[0.00034681533,0.000048537375,0.00014434908,0.0002464183,0.00014711851,0.0002205956,0.0000597603,0.00032943138,3.6942392e-8],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00071830745,0.0005538032,0.90686643,0.0002470202,0.000037506106,4.2049993e-7,0.0016266108,0.004473525,0.05374386,0.000006152949,0.000019387968,0.03170698],"study_design_scores_gemma":[0.005500345,0.0008972611,0.060219143,0.0047310423,0.00019683733,0.000087389504,0.0021683201,0.86931676,0.056506123,0.00008761577,0.00019355476,0.00009561741],"about_ca_topic_score_codex":0.000008612393,"about_ca_topic_score_gemma":2.0195057e-7,"teacher_disagreement_score":0.86484325,"about_ca_system_score_codex":0.000047899306,"about_ca_system_score_gemma":0.000057978963,"threshold_uncertainty_score":0.19792968},"labels":[],"label_agreement":null},{"id":"W2994263048","doi":"10.1002/jso.25783","title":"A clinical‐radiomic model for improved prognostication of surgical candidates with colorectal liver metastases","year":2019,"lang":"en","type":"article","venue":"Journal of Surgical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mount Sinai Hospital; Women's College Hospital; University of Toronto; University Health Network","funders":"","keywords":"Medicine; Colorectal cancer; General surgery; Radiology; Internal medicine; Cancer","score_opus":0.020844448575782448,"score_gpt":0.3526661528887494,"score_spread":0.331821704312967,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2994263048","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98794186,0.0005776711,0.0045112856,0.0050519877,0.0002777278,0.0006610936,0.000015837495,0.000012719627,0.0009497961],"genre_scores_gemma":[0.97171426,0.0015390728,0.02587594,0.00017817329,0.0003620236,0.000011102453,0.000020161386,0.000025535632,0.00027375895],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99799955,0.00018215904,0.0010728189,0.00021678187,0.00025559927,0.00027307068],"domain_scores_gemma":[0.9960428,0.0021589154,0.0008711837,0.00013720065,0.00047466313,0.00031524655],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018869747,0.00015427668,0.0011873038,0.0001574906,0.000031278374,0.000009867501,0.00015002902,0.0001870871,0.000101487196],"category_scores_gemma":[0.00032779144,0.00009535499,0.00035690566,0.00014065781,0.0003036131,0.000093719005,0.00003361872,0.0006389236,0.000004314981],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.117620535,0.010490902,0.30142015,0.001376386,0.0046941326,0.0049808575,0.0010203737,0.0046669287,0.017690256,0.0064280117,0.012121368,0.5174901],"study_design_scores_gemma":[0.026786078,0.017071543,0.0034442905,0.0002994014,0.0011505863,0.00804028,0.00006874665,0.77862495,0.00048809094,0.0002365963,0.16355583,0.00023359002],"about_ca_topic_score_codex":0.000011476601,"about_ca_topic_score_gemma":0.0000029645896,"teacher_disagreement_score":0.773958,"about_ca_system_score_codex":0.00010509612,"about_ca_system_score_gemma":0.0007952003,"threshold_uncertainty_score":0.38884637},"labels":[],"label_agreement":null},{"id":"W2995016195","doi":"10.1038/s42256-019-0133-1","title":"Publisher Correction: Intelligent feature engineering and ontological mapping of brain tumour histomorphologies by deep learning","year":2019,"lang":"en","type":"article","venue":"Nature Machine Intelligence","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; Princess Margaret Cancer Centre; University of Toronto","funders":"","keywords":"Feature (linguistics); Computer science; Feature engineering; Artificial intelligence; Deep learning; Philosophy; Linguistics","score_opus":0.0057446667449439675,"score_gpt":0.2530969551124466,"score_spread":0.24735228836750264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995016195","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.63763136,0.057853863,0.25364047,0.027047193,0.009842518,0.0014450805,0.000006372689,0.00084122096,0.01169195],"genre_scores_gemma":[0.9869564,0.00036813834,0.0049688774,0.0011182611,0.00010977714,0.000007911524,0.000051183368,0.00003742524,0.0063819797],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982696,0.00007650647,0.00038704017,0.0005088612,0.00039505961,0.00036291574],"domain_scores_gemma":[0.99870455,0.00054006145,0.00018334278,0.00024304805,0.00014212879,0.00018688203],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.00062337064,0.00029411333,0.00056329055,0.00023138792,0.000069196336,0.000055547243,0.00023563321,0.00044146573,0.0002351301],"category_scores_gemma":[0.003142198,0.00023502651,0.00012540804,0.00039343757,0.0001382025,0.00012631225,0.00014686717,0.003517491,0.000014268698],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00050946156,0.00041012466,0.29750404,0.001130931,0.00038948434,0.00029706224,0.0020744808,0.0077147656,0.08535393,0.0028029282,0.1003305,0.5014823],"study_design_scores_gemma":[0.0011030388,0.0013568276,0.044325463,0.0011659701,0.00014258458,0.0026984627,0.0014183449,0.6036455,0.011918304,0.0003668191,0.33074504,0.0011136704],"about_ca_topic_score_codex":0.00007811144,"about_ca_topic_score_gemma":0.000003830664,"teacher_disagreement_score":0.5959307,"about_ca_system_score_codex":0.0001055056,"about_ca_system_score_gemma":0.00003279245,"threshold_uncertainty_score":0.99878144},"labels":[],"label_agreement":null},{"id":"W2995847542","doi":"10.23736/s1824-4785.19.03222-9","title":"Radiomics in nuclear medicine and hybrid imaging: current standings on clinical applicability","year":2019,"lang":"en","type":"article","venue":"The Quarterly Journal of Nuclear Medicine and Molecular Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sinai Health System; Women's College Hospital","funders":"National Cancer Institute","keywords":"Medicine; Radiomics; Medical physics; Radiology; Nuclear medicine imaging; Nuclear medicine","score_opus":0.01737626690817911,"score_gpt":0.33824288524411716,"score_spread":0.32086661833593805,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995847542","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8972836,0.004410353,0.0004884945,0.09578686,0.0005652634,0.00036487778,8.7890845e-7,0.000025094332,0.0010745326],"genre_scores_gemma":[0.9841087,0.0012037558,0.0003665977,0.013715132,0.0005302408,9.5171197e-7,0.0000021016663,0.00006612216,0.0000063988823],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99709576,0.0002882175,0.0011503508,0.00041539865,0.00065601955,0.00039427663],"domain_scores_gemma":[0.99807346,0.00042287563,0.00049526495,0.00042965813,0.00014130988,0.0004374315],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037601918,0.00030355548,0.0009671265,0.00037507786,0.00010479325,0.000043943124,0.00026397454,0.000037977024,0.000094132556],"category_scores_gemma":[0.00055723963,0.00018671129,0.00014708619,0.00019717579,0.0009870436,0.00014316132,0.00005712874,0.0017187719,0.000008676017],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0023585428,0.0005775993,0.09606176,0.00060225965,0.0003116313,0.0022543797,0.01359449,0.0000132031555,0.032143928,0.0056838337,0.03680239,0.809596],"study_design_scores_gemma":[0.054475453,0.015867488,0.08010283,0.013566831,0.0019588156,0.022228746,0.028730111,0.08945317,0.00006147117,0.013804433,0.6782524,0.001498237],"about_ca_topic_score_codex":0.000044232704,"about_ca_topic_score_gemma":2.911672e-7,"teacher_disagreement_score":0.8080978,"about_ca_system_score_codex":0.00008424462,"about_ca_system_score_gemma":0.00005559532,"threshold_uncertainty_score":0.7613865},"labels":[],"label_agreement":null},{"id":"W2997061028","doi":"10.1002/9780471420194.tnmc36.pub2","title":"Fallopian Tube","year":2010,"lang":"en","type":"other","venue":"TNM Online","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Grading (engineering); Pathological; Distant metastasis; Lymph node metastasis; Stage (stratigraphy); Metastasis; Medicine; Lymph node; Lymph; Pathology; Cancer; Internal medicine; Biology","score_opus":0.009454986042878229,"score_gpt":0.30721801855115854,"score_spread":0.2977630325082803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2997061028","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002864935,0.00057004625,0.0002324808,0.0052854912,0.0009759337,0.0002696643,0.00035941548,0.00051648205,0.991504],"genre_scores_gemma":[0.00010536321,0.0002439881,0.019967819,0.0030592328,0.0038195231,0.000006065016,0.0022337271,0.0005766357,0.96998763],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99900895,0.000015350079,0.00018103071,0.00028953212,0.00025492968,0.00025019137],"domain_scores_gemma":[0.9991689,0.000026770065,0.000099035744,0.00044358417,0.00002190674,0.00023982748],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000085198306,0.00022617452,0.00044814468,0.00020196209,0.000022410322,0.000012515912,0.0001468154,0.00038288336,0.03860349],"category_scores_gemma":[0.0002849961,0.00017988823,0.000113448106,0.0000920378,0.00011123028,0.000007844821,0.000049021797,0.001449365,0.00033019827],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000074938935,0.00012196304,0.00031871992,0.00011814629,0.0000693507,0.0001316912,0.000014599635,1.3447331e-7,0.000247086,0.0001169076,0.9484926,0.050361328],"study_design_scores_gemma":[0.00065643725,0.00005096377,0.0005341897,0.00045403006,0.00009458017,0.00010520263,0.0000052482646,0.00069881644,0.0000050049302,0.000025700623,0.9971941,0.00017572551],"about_ca_topic_score_codex":0.00019910533,"about_ca_topic_score_gemma":0.00014857335,"teacher_disagreement_score":0.050185602,"about_ca_system_score_codex":0.00001799895,"about_ca_system_score_gemma":0.00011179956,"threshold_uncertainty_score":0.9622754},"labels":[],"label_agreement":null},{"id":"W2997449172","doi":"10.1148/radiol.2019192515","title":"Assessing Radiology Research on Artificial Intelligence: A Brief Guide for Authors, Reviewers, and Readers—From the <i>Radiology</i> Editorial Board","year":2019,"lang":"en","type":"editorial","venue":"Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":334,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Cancer Research UK","keywords":"Medicine; General hospital; Library science; Radiology; Family medicine; Computer science","score_opus":0.07186118850790842,"score_gpt":0.43659368792783737,"score_spread":0.36473249941992897,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2997449172","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009472191,0.009343187,0.0042765494,0.017501453,0.96466345,0.0022332647,0.00020528237,0.00012653836,0.00070307194],"genre_scores_gemma":[0.0004257521,0.0070418767,0.0040100766,0.0017280171,0.98318744,0.0002484638,0.0021233857,0.00019203029,0.0010429565],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99036145,0.0031165662,0.0015867443,0.002068511,0.0012570709,0.0016096452],"domain_scores_gemma":[0.9643269,0.032231078,0.0006411527,0.0014946222,0.00084942905,0.00045678014],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.012492668,0.0007999318,0.0026390224,0.00042038554,0.00068764045,0.00024121522,0.0010412713,0.0038440872,0.000076075],"category_scores_gemma":[0.048606705,0.00056661735,0.00046364387,0.00038551973,0.002360888,0.00011730422,0.0002998096,0.0088676335,0.00007535272],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001041303,0.000069659196,0.00009371317,0.00027306462,0.00040326588,0.0000746455,0.00034198374,0.000023442162,0.00038266697,0.0018147201,0.972885,0.022596518],"study_design_scores_gemma":[0.001119637,0.0018150331,0.0000703701,0.0008591818,0.0004816361,0.00021724573,0.00044283905,0.0011924319,0.000018371107,0.0043546506,0.9889256,0.0005030198],"about_ca_topic_score_codex":0.0006690903,"about_ca_topic_score_gemma":0.000023943965,"teacher_disagreement_score":0.036114037,"about_ca_system_score_codex":0.0005495137,"about_ca_system_score_gemma":0.0019836542,"threshold_uncertainty_score":0.99967855},"labels":[],"label_agreement":null},{"id":"W2997729525","doi":"10.1002/9780471420194.tnmc04.pub2","title":"Pharynx","year":2010,"lang":"en","type":"other","venue":"TNM Online","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Grading (engineering); Distant metastasis; Pathological; Lymph node metastasis; Stage (stratigraphy); Lymph node; Metastasis; Medicine; Lymph; Cancer; Pathology; Internal medicine; Biology; Paleontology; Ecology","score_opus":0.010117314765426674,"score_gpt":0.32292380146933164,"score_spread":0.312806486703905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2997729525","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00018944855,0.0009070618,0.00020659111,0.004283855,0.0009499957,0.00023669432,0.00041606938,0.00050121854,0.9923091],"genre_scores_gemma":[0.0000720487,0.0002815372,0.01844993,0.002857362,0.004116378,0.0000052239648,0.002344778,0.00054330216,0.97132945],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99915344,0.000012401549,0.00015208618,0.00024994073,0.00022329135,0.00020884961],"domain_scores_gemma":[0.9992852,0.000025760206,0.000100146506,0.00037151534,0.00001774499,0.00019961136],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000075494965,0.00019367466,0.00039777864,0.00017821888,0.000017873424,0.000009037345,0.00012011005,0.00029983805,0.06210227],"category_scores_gemma":[0.0002334458,0.00015302534,0.00009933096,0.000080305435,0.00009404538,0.0000071943546,0.00004056699,0.0012914201,0.00044995346],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007011169,0.00011977325,0.000121443874,0.000094032854,0.000055889555,0.00011854206,0.000008324103,4.9413014e-8,0.00039274292,0.000037063586,0.9333215,0.065723665],"study_design_scores_gemma":[0.0006767591,0.000040573985,0.00023163341,0.00037810626,0.0001010827,0.000110782785,0.0000028795714,0.00053265877,0.000009391733,0.000021004258,0.99774843,0.0001466907],"about_ca_topic_score_codex":0.00011131172,"about_ca_topic_score_gemma":0.000040096056,"teacher_disagreement_score":0.06557697,"about_ca_system_score_codex":0.00001341151,"about_ca_system_score_gemma":0.00009171417,"threshold_uncertainty_score":0.9387551},"labels":[],"label_agreement":null},{"id":"W2998471640","doi":"10.1038/s41598-019-56185-5","title":"Quantitative MRI Biomarkers of Stereotactic Radiotherapy Outcome in Brain Metastasis","year":2019,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":69,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; York University; University of Toronto; Sunnybrook Health Science Centre","funders":"Canadian Institutes of Health Research; Terry Fox Foundation; Natural Sciences and Engineering Research Council of Canada; Government of Canada; Lotte and John Hecht Memorial Foundation","keywords":"Brain metastasis; Medicine; Radiation therapy; Stereotactic radiotherapy; Metastasis; Radiology; Magnetic resonance imaging; Radiosurgery; Oncology; Internal medicine; Cancer","score_opus":0.02182523726732469,"score_gpt":0.3437085832338464,"score_spread":0.3218833459665217,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2998471640","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99052787,0.00043165163,0.0008227801,0.002953592,0.0029871205,0.00046073826,0.0000010796211,0.000026215166,0.0017889555],"genre_scores_gemma":[0.98665553,0.000008559922,0.009774713,0.00026832035,0.000016614484,0.00000569812,0.000018543,0.000021810358,0.0032301957],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9978504,0.00009854332,0.0007227814,0.0005339832,0.0005301788,0.00026408947],"domain_scores_gemma":[0.9985907,0.00018076386,0.00036371587,0.00065271684,0.00008820023,0.00012390885],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0033292454,0.00012798858,0.0004683734,0.00047645427,0.00003965886,0.000049517163,0.00008755338,0.000047240377,0.00041742894],"category_scores_gemma":[0.00079696125,0.000102059246,0.00014503801,0.00068712374,0.00024881389,0.0001224435,0.000029324734,0.00022254114,0.000016516986],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011529792,0.0001776212,0.86809963,0.00021674058,0.00019254086,0.0007141509,0.0009293602,0.0001281108,0.11863562,0.00025452932,0.0048841583,0.00565223],"study_design_scores_gemma":[0.011148339,0.0020734542,0.61975825,0.0019662285,0.0004898958,0.0046878285,0.0036977842,0.08841826,0.029919205,0.006493756,0.22968265,0.0016643202],"about_ca_topic_score_codex":0.00012293631,"about_ca_topic_score_gemma":0.000006229214,"teacher_disagreement_score":0.24834137,"about_ca_system_score_codex":0.00007952474,"about_ca_system_score_gemma":0.00014289978,"threshold_uncertainty_score":0.45705542},"labels":[],"label_agreement":null},{"id":"W2999697937","doi":"10.1016/s0923-7534(20)30087-9","title":"P-0164 Online System For Decentralized Review of Digital Medical Images And its Use in Multicenter Clinical Trials","year":2012,"lang":"en","type":"article","venue":"Annals of Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital","funders":"","keywords":"Medicine; Clinical trial; Medical physics; Multicenter study; Internal medicine; Randomized controlled trial","score_opus":0.2944690035533987,"score_gpt":0.5582311128523553,"score_spread":0.26376210929895655,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2999697937","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92117727,0.04867699,0.00041482138,0.02745331,0.00057070766,0.0013509123,0.000114025446,0.000021832358,0.00022015237],"genre_scores_gemma":[0.94073105,0.05316888,0.001717956,0.003931672,0.00031535418,0.000017688884,0.000059808564,0.00001723967,0.000040328086],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99704444,0.0006035755,0.0016538063,0.00016790252,0.00023543889,0.00029480908],"domain_scores_gemma":[0.99455935,0.0041568,0.00055380404,0.00012272174,0.00024302052,0.00036431634],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008801619,0.00011075472,0.0015603935,0.00008293999,0.000010642211,0.0000044445205,0.00009006689,0.0001831901,0.000041112606],"category_scores_gemma":[0.05709548,0.00007809284,0.0002400211,0.00007630129,0.00016000218,0.00013222148,0.000058216945,0.00028738167,0.000002068412],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0032620828,0.005254304,0.34552145,0.024350978,0.0006388739,0.000098776814,0.00019831567,8.2518494e-7,0.00090757327,0.0013838258,0.029350601,0.5890324],"study_design_scores_gemma":[0.05608589,0.0065266816,0.2056599,0.056927186,0.0015742822,0.00071852497,0.00037674326,0.011452402,0.0019247142,0.00007899088,0.65804064,0.00063408195],"about_ca_topic_score_codex":0.000016368112,"about_ca_topic_score_gemma":0.0000016021132,"teacher_disagreement_score":0.62869,"about_ca_system_score_codex":0.000016433965,"about_ca_system_score_gemma":0.00014249096,"threshold_uncertainty_score":0.950847},"labels":[],"label_agreement":null},{"id":"W2999878794","doi":"","title":"2019 November Top 100 REMAX REALTOR in Western Canada – Lotus Yuen PREC","year":2020,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Geography","score_opus":0.011751659394178873,"score_gpt":0.2735837939006291,"score_spread":0.2618321345064502,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2999878794","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7667428,0.00035853908,0.000808833,0.16637078,0.0004633878,0.00043713962,0.0000064785463,0.000115079914,0.06469695],"genre_scores_gemma":[0.93699956,0.000048829254,0.0014782839,0.04184193,0.0004999721,0.000006203626,0.00003070073,0.00003660355,0.019057943],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988594,0.000033033797,0.00026354607,0.00026900362,0.000294864,0.0002801417],"domain_scores_gemma":[0.99929845,0.00006726941,0.000045047793,0.00018996083,0.000030794323,0.00036848383],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016179425,0.00012021939,0.00028521544,0.00003678035,0.000022683698,0.0000153013,0.00010748518,0.000052832456,0.0006238338],"category_scores_gemma":[0.00035034254,0.00009628363,0.000043175372,0.00016870906,0.000027040704,0.000042300442,0.000051856132,0.00042808722,0.000052878655],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017837946,0.00008875894,0.544268,0.00023725297,0.000076983226,0.0008722307,0.00078420603,0.00019607936,0.002477989,0.00020997168,0.42240018,0.028209997],"study_design_scores_gemma":[0.003271936,0.00022758875,0.17326933,0.00020502899,0.000059347247,0.0001062253,0.00015647181,0.019384049,0.0005492959,0.000024096546,0.8024064,0.000340287],"about_ca_topic_score_codex":0.54484344,"about_ca_topic_score_gemma":0.21270621,"teacher_disagreement_score":0.3800062,"about_ca_system_score_codex":0.00013332114,"about_ca_system_score_gemma":0.00054341916,"threshold_uncertainty_score":0.8016599},"labels":[],"label_agreement":null},{"id":"W3000524228","doi":"10.1016/j.media.2020.101636","title":"Improving cardiac MRI convolutional neural network segmentation on small training datasets and dataset shift: A continuous kernel cut approach","year":2020,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":64,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Sunnybrook Health Science Centre","funders":"Engineering and Physical Sciences Research Council; Canadian Institutes of Health Research; British Heart Foundation; Medical Research Council; National Institute for Health and Care Research","keywords":"Segmentation; Convolutional neural network; Computer science; Artificial intelligence; Pattern recognition (psychology); Deep learning; Kernel (algebra); Market segmentation; Image segmentation; Scale-space segmentation; Machine learning; Mathematics","score_opus":0.01914023953641023,"score_gpt":0.28293529042554033,"score_spread":0.2637950508891301,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3000524228","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21046858,0.0015610098,0.73701406,0.044861104,0.0003704427,0.0010563389,0.0035020744,0.00032484496,0.0008415798],"genre_scores_gemma":[0.8799027,0.00016450323,0.032353893,0.026155606,0.0020883891,0.00005047893,0.059174564,0.00006510387,0.00004471323],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970945,0.00024446222,0.0005237873,0.00074191164,0.0008993943,0.0004959598],"domain_scores_gemma":[0.9981671,0.0002830682,0.0001784091,0.00032665653,0.00003807357,0.0010067153],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011115432,0.00027303197,0.0008517423,0.00014450823,0.0001923666,0.00011051384,0.00021614756,0.00013017122,0.00029107372],"category_scores_gemma":[0.0013927196,0.00022966045,0.00022858374,0.0006954712,0.0003390982,0.0001645117,0.000174732,0.00092439086,0.000016414158],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017802066,0.0012606126,0.1854486,0.0014617585,0.01719297,0.004374256,0.0078949295,0.010828523,0.0046362765,0.0009145208,0.29736468,0.46684265],"study_design_scores_gemma":[0.0018553822,0.00018572003,0.009304385,0.00004845737,0.003329467,0.0000410517,0.00044246885,0.97924787,0.0000228272,0.000019018353,0.00521603,0.00028731377],"about_ca_topic_score_codex":0.0002908823,"about_ca_topic_score_gemma":0.000009709991,"teacher_disagreement_score":0.9684194,"about_ca_system_score_codex":0.00004241976,"about_ca_system_score_gemma":0.000121191166,"threshold_uncertainty_score":0.93652815},"labels":[],"label_agreement":null},{"id":"W3001067515","doi":"10.1016/j.ejmp.2020.01.009","title":"Overlooked pitfalls in multi-class machine learning classification in radiation oncology and how to avoid them","year":2020,"lang":"en","type":"article","venue":"Physica Medica","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Surrogate endpoint; Correlation; Clinical endpoint; Statistical significance; Ordinal Scale; Medicine; Radiation oncology; Statistics; Machine learning; Artificial intelligence; Radiation therapy; Clinical trial; Mathematics; Computer science; Internal medicine","score_opus":0.037609382590694795,"score_gpt":0.3165520865646233,"score_spread":0.2789427039739285,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3001067515","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7345054,0.00023974566,0.0033435535,0.25938904,0.00011316251,0.0005548339,0.0000025393615,0.000092139635,0.0017595647],"genre_scores_gemma":[0.9925804,0.00031292185,0.0015672267,0.0049976474,0.00026466628,0.000040454906,0.00004951375,0.000029488594,0.00015765871],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99854594,0.00020329788,0.0002472158,0.00040705863,0.00030613283,0.00029032148],"domain_scores_gemma":[0.9990854,0.00025386518,0.0001119189,0.00013313994,0.000028187007,0.0003874859],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00049050624,0.00015888942,0.00043235935,0.00012689049,0.000047390462,0.000021449256,0.000107889486,0.00009830233,0.000036170077],"category_scores_gemma":[0.0022333178,0.00014312494,0.000041537256,0.000396449,0.00009010662,0.000085998596,0.00006356373,0.000992299,0.000035155692],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005636145,0.0008447346,0.22091627,0.00040641642,0.00008462868,0.00022681372,0.021031557,0.0004702137,0.17257488,0.0011446781,0.004737816,0.5769984],"study_design_scores_gemma":[0.0056828815,0.00043009056,0.17694949,0.0001855952,0.000039719984,0.00001636833,0.0005892932,0.70956063,0.00043032132,0.000060439783,0.105827704,0.00022746724],"about_ca_topic_score_codex":0.00009667935,"about_ca_topic_score_gemma":0.000018350305,"teacher_disagreement_score":0.7090904,"about_ca_system_score_codex":0.00015360014,"about_ca_system_score_gemma":0.00011752431,"threshold_uncertainty_score":0.58364654},"labels":[],"label_agreement":null},{"id":"W3001157157","doi":"10.3389/fcvm.2020.00001","title":"Image-Based Cardiac Diagnosis With Machine Learning: A Review","year":2020,"lang":"en","type":"review","venue":"Frontiers in Cardiovascular Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":245,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Circle Cardiovascular Imaging; Servier; European Commission; British Heart Foundation; Engineering and Physical Sciences Research Council; National Institute for Health and Care Research","keywords":"Artificial intelligence; Computer science; Big data; Machine learning; Deep learning; Presentation (obstetrics); Field (mathematics); Data science; Disease; Cardiac imaging; Medicine; Pathology; Data mining; Cardiology; Radiology","score_opus":0.01635311578946379,"score_gpt":0.2895553287678998,"score_spread":0.273202212978436,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3001157157","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.1234816e-7,0.9784982,0.01123346,0.0042026388,0.0013986622,0.0031219784,0.000023797644,0.00023161437,0.0012895045],"genre_scores_gemma":[0.0000011667481,0.977912,0.016628463,0.0015418029,0.0013753828,0.0009639385,0.0010858184,0.000357679,0.00013374262],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9927493,0.0014060884,0.0014743357,0.0015547844,0.0019675244,0.00084797037],"domain_scores_gemma":[0.99648285,0.00041356464,0.0005046697,0.0015711815,0.0001867643,0.0008409936],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.003068934,0.0012644127,0.013059788,0.00081627344,0.000116244206,0.000028220225,0.0005522407,0.00043951266,0.00015398918],"category_scores_gemma":[0.003957863,0.00083478936,0.0036275468,0.002213062,0.00065262726,0.000077314246,0.00012249144,0.0042572487,0.000043870965],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003592454,0.000054257816,0.001522331,0.10933077,0.004749879,0.0029242814,0.000032717726,0.000010851479,5.048176e-8,0.0000015401383,0.043572523,0.83776486],"study_design_scores_gemma":[0.0020961496,0.0004226903,0.00002614277,0.19553344,0.023107518,0.00031445024,0.000020285672,0.0006725849,1.5886779e-7,0.000001981069,0.77720195,0.00060265407],"about_ca_topic_score_codex":0.00015332189,"about_ca_topic_score_gemma":7.443239e-7,"teacher_disagreement_score":0.8371622,"about_ca_system_score_codex":0.0006096766,"about_ca_system_score_gemma":0.0009071719,"threshold_uncertainty_score":0.9994103},"labels":[],"label_agreement":null},{"id":"W3001828378","doi":"10.1093/neuonc/noaa007","title":"Use of radiomics for the prediction of local control of brain metastases after stereotactic radiosurgery","year":2020,"lang":"en","type":"article","venue":"Neuro-Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":97,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; Sunnybrook Health Science Centre; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Sunnybrook Research Institute","keywords":"Radiosurgery; Radiomics; Medicine; Stereotactic radiotherapy; Medical physics; Radiology; Radiation therapy","score_opus":0.032448662517219236,"score_gpt":0.29534824347099187,"score_spread":0.26289958095377264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3001828378","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6881218,0.00074931624,0.26459876,0.044229858,0.0007709688,0.0011875792,0.0002611417,0.00003556202,0.000044986722],"genre_scores_gemma":[0.9907152,0.00010583482,0.0011723982,0.007732025,0.00019454907,0.000034895158,0.0000135765285,0.000025366237,0.0000061317974],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99858767,0.0002510982,0.000593883,0.00019583399,0.00019414748,0.00017739792],"domain_scores_gemma":[0.9938409,0.005329205,0.00036333993,0.00021385754,0.00012884058,0.00012389949],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004586755,0.00011791483,0.0006844525,0.00008127092,0.000022988375,0.000003912221,0.00009691118,0.00009035435,0.000040838648],"category_scores_gemma":[0.003213594,0.0000830361,0.00021991269,0.00014651967,0.00041038354,0.00006121845,0.000030283907,0.00030745732,5.7147616e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.011110544,0.00059771544,0.036494315,0.0010000777,0.0010424001,0.00016197508,0.001252867,0.0029435828,0.75907826,0.00044934909,0.020645624,0.16522332],"study_design_scores_gemma":[0.014574604,0.0083149895,0.01658322,0.00014838643,0.0026352885,0.00051522726,0.00041699247,0.49029627,0.04746094,0.00005574583,0.41879377,0.00020456975],"about_ca_topic_score_codex":0.00002799596,"about_ca_topic_score_gemma":0.0000011336717,"teacher_disagreement_score":0.7116173,"about_ca_system_score_codex":0.000034544664,"about_ca_system_score_gemma":0.0002109722,"threshold_uncertainty_score":0.38472044},"labels":[],"label_agreement":null},{"id":"W3002402144","doi":"10.1088/1361-6560/ab6e54","title":"Data clustering to select clinically-relevant test cases for algorithm benchmarking and characterization","year":2020,"lang":"en","type":"article","venue":"Physics in Medicine and Biology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Lethbridge; University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Medoid; Benchmarking; Cluster analysis; Algorithm; Computer science; Workflow; Data mining; Ground truth; Statistical hypothesis testing; Artificial intelligence; Statistics; Mathematics; Database","score_opus":0.23639643577115818,"score_gpt":0.4405806988614017,"score_spread":0.20418426309024354,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3002402144","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35684198,0.00042567894,0.573612,0.067610644,0.0003386885,0.00086947886,0.00013157695,0.000059227696,0.00011074266],"genre_scores_gemma":[0.9289647,0.0013844671,0.039113913,0.024997687,0.0040812995,0.000024264995,0.0013893606,0.000030066956,0.000014249557],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999003,0.000032739947,0.00031315317,0.00040128976,0.000056330813,0.00019350043],"domain_scores_gemma":[0.9988045,0.0007612127,0.000072444716,0.00014466964,0.000038080016,0.00017908924],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045065247,0.0001164177,0.0003952131,0.000042816086,0.000050071834,0.000008156939,0.00009090531,0.00005659866,0.000005906351],"category_scores_gemma":[0.0021462047,0.000086719505,0.000013315555,0.00014553631,0.0001220223,0.000042984087,0.00016804357,0.0002411958,6.315617e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001035098,0.00004583546,0.046632115,0.00018535763,0.000029097313,0.000023615034,0.00052287785,0.00000377277,0.05107417,0.000097014905,0.00051216147,0.9007705],"study_design_scores_gemma":[0.003544849,0.0041960394,0.019680299,0.000535761,0.00015467832,0.00012776307,0.0001785571,0.92784554,0.000083497165,0.00043539496,0.042962227,0.00025539927],"about_ca_topic_score_codex":0.00003147591,"about_ca_topic_score_gemma":0.0000036836627,"teacher_disagreement_score":0.9278418,"about_ca_system_score_codex":0.00000871827,"about_ca_system_score_gemma":0.00002832047,"threshold_uncertainty_score":0.35363188},"labels":[],"label_agreement":null},{"id":"W3002900120","doi":"10.1259/bjr.20190855","title":"Artificial Intelligence: reshaping the practice of radiological sciences in the 21st century","year":2020,"lang":"en","type":"review","venue":"British Journal of Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":100,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; University of Toronto","funders":"National Cancer Institute","keywords":"Applications of artificial intelligence; Data science; Artificial intelligence; Computer science; Analytics; Health care; Entertainment; Engineering ethics; Medicine; Engineering; Political science","score_opus":0.06705026402170557,"score_gpt":0.3947881149658452,"score_spread":0.32773785094413965,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3002900120","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00008193827,0.989963,0.00030571502,0.007331228,0.0005933989,0.00035303607,0.0000043202367,0.0000050102103,0.0013623688],"genre_scores_gemma":[0.00092657306,0.9940397,0.0014852056,0.0021458678,0.0013730029,0.000005877659,0.0000053216063,0.000015769416,0.0000026764167],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9949856,0.002368194,0.0016039667,0.00025637477,0.00046690303,0.0003189693],"domain_scores_gemma":[0.9942387,0.0039673042,0.0014198743,0.00015929813,0.00012586422,0.00008895548],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.007218542,0.00020050658,0.001805157,0.00018555789,0.0001563442,0.000063631924,0.00096587656,0.00025087278,0.000042732358],"category_scores_gemma":[0.01441975,0.00010840628,0.00051842054,0.0006582559,0.0014579669,0.000077993034,0.00008028886,0.0033922994,0.0000039648353],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003705989,0.000075999305,0.000011234124,0.0005969828,0.00012728531,0.0028698188,0.0002602768,0.000015519901,0.0000015006217,0.0025202415,0.002428182,0.9910559],"study_design_scores_gemma":[0.00007713005,0.00046798243,0.000018175853,0.005183201,0.00045687496,0.26493698,0.0012000322,0.000072611074,1.9891333e-7,0.00033063165,0.7271758,0.0000803826],"about_ca_topic_score_codex":0.000035906534,"about_ca_topic_score_gemma":0.0000016493104,"teacher_disagreement_score":0.9909755,"about_ca_system_score_codex":0.00007199364,"about_ca_system_score_gemma":0.00064722117,"threshold_uncertainty_score":0.9989069},"labels":[],"label_agreement":null},{"id":"W3003771908","doi":"10.1016/j.jogc.2019.12.003","title":"Le JOGC adopte la révision par les pairs à double insu","year":2020,"lang":"fr","type":"editorial","venue":"Journal of Obstetrics and Gynaecology Canada","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Humanities; Art; Philosophy","score_opus":0.00862529808754013,"score_gpt":0.243161267719157,"score_spread":0.23453596963161688,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3003771908","genre_codex":"editorial","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01817806,0.050134584,0.00024883586,0.0092961695,0.91476804,0.00023421521,0.000052474967,0.000011586626,0.0070760217],"genre_scores_gemma":[0.8727562,0.0100753335,0.0016486858,0.0012536348,0.11303891,0.0000044929207,0.00007625481,0.00013137957,0.0010151447],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.995847,0.0003649515,0.0014001185,0.00042585962,0.0012711554,0.00069094554],"domain_scores_gemma":[0.98352766,0.012801829,0.0014538891,0.00022936976,0.00075688533,0.0012303831],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0013088143,0.00048184427,0.0015712763,0.00041644892,0.00042482937,0.00011242536,0.00047801534,0.0010693553,0.00033142898],"category_scores_gemma":[0.035047993,0.0004301868,0.0002562342,0.0005431185,0.00043473503,0.0001223344,0.00020250861,0.0052883043,0.0000030482809],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006584756,0.00018346743,0.019133475,0.00067744433,0.00067146047,0.021063466,0.00017767736,0.00028003077,0.000015704918,0.0010752358,0.7113112,0.24534498],"study_design_scores_gemma":[0.008082517,0.0009428012,0.02121183,0.00019678012,0.00061483175,0.00021188895,0.00034542492,0.0009476709,0.000011557802,0.00013142424,0.9669461,0.00035714995],"about_ca_topic_score_codex":0.054712623,"about_ca_topic_score_gemma":0.0072586355,"teacher_disagreement_score":0.8545781,"about_ca_system_score_codex":0.0016110217,"about_ca_system_score_gemma":0.018145164,"threshold_uncertainty_score":0.999815},"labels":[],"label_agreement":null},{"id":"W3003922976","doi":"10.1016/j.ejmp.2020.01.027","title":"User-controlled pipelines for feature integration and head and neck radiation therapy outcome predictions","year":2020,"lang":"en","type":"article","venue":"Physica Medica","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":20,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; Princess Margaret Cancer Centre; Ontario Institute for Cancer Research; University of Toronto; University Health Network","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Terry Fox Research Institute; Ontario Institute for Cancer Research","keywords":"Outcome (game theory); Pipeline transport; Radiation therapy; Head and neck; Feature (linguistics); Head (geology); Computer science; Medicine; Engineering; Geology; Internal medicine; Surgery; Mechanical engineering; Mathematics","score_opus":0.018216211186738725,"score_gpt":0.317211722944433,"score_spread":0.2989955117576943,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3003922976","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.64585155,0.0026063158,0.038651805,0.30968165,0.00038044344,0.0018974224,0.000030311921,0.00023698791,0.00066351896],"genre_scores_gemma":[0.9869317,0.0007811696,0.0032874981,0.006927697,0.0016126375,0.000094125346,0.00012222686,0.000026437452,0.00021655418],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991335,0.000033050535,0.0002230563,0.00025485922,0.000202937,0.00015255662],"domain_scores_gemma":[0.9992812,0.00019193892,0.00009311466,0.00009928815,0.00006111397,0.0002733093],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016758886,0.00014094285,0.0004234192,0.000044604043,0.000118886914,0.000032824206,0.000045603025,0.00006849208,0.00001095976],"category_scores_gemma":[0.0010207432,0.00009896823,0.000081117876,0.000106088126,0.000089719935,0.00008955729,0.0000152020175,0.0003132057,0.0000016501806],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0032518117,0.00038874758,0.06012222,0.00038497004,0.00052423845,0.000012638409,0.005581329,0.000032474672,0.03397709,0.0023300773,0.0939435,0.7994509],"study_design_scores_gemma":[0.045578457,0.0017467693,0.13759497,0.00022926013,0.00050612603,0.0000343707,0.0003114435,0.62882996,0.0007053807,0.00063585833,0.18346414,0.0003632538],"about_ca_topic_score_codex":0.000014502567,"about_ca_topic_score_gemma":0.0000011340247,"teacher_disagreement_score":0.79908764,"about_ca_system_score_codex":0.00001460574,"about_ca_system_score_gemma":0.000045915964,"threshold_uncertainty_score":0.40358075},"labels":[],"label_agreement":null},{"id":"W3004670172","doi":"10.1016/j.critrevonc.2020.102896","title":"A novel, more reliable approach to use of progression-free survival as a predictor of gain in overall survival: The Ottawa PFS Predictive Model","year":2020,"lang":"en","type":"review","venue":"Critical Reviews in Oncology/Hematology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Ottawa Hospital; University of Ottawa","funders":"","keywords":"Predictive modelling; Progression-free survival; Overall survival; Oncology; Computer science; Medicine; Machine learning","score_opus":0.09157622534961121,"score_gpt":0.4323188863312236,"score_spread":0.34074266098161243,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3004670172","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000046337555,0.97097254,0.011836802,0.007239685,0.0005381086,0.0058688438,0.0001201882,0.000053357122,0.0033241254],"genre_scores_gemma":[0.00021017929,0.9464504,0.049559418,0.0016817609,0.00016131012,0.0016092921,0.00010968986,0.0001394648,0.000078486344],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99121433,0.001898921,0.003859701,0.0012565004,0.0008188986,0.0009516634],"domain_scores_gemma":[0.9902807,0.0064331046,0.00090633245,0.0014938504,0.0002938563,0.0005921845],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0045876936,0.00081559963,0.0093628615,0.00051056297,0.000054390035,0.000017637449,0.0012656404,0.0011743493,0.000036221536],"category_scores_gemma":[0.07529307,0.0005213533,0.0008162903,0.0011752577,0.0014038936,0.00010282765,0.0009208144,0.003395687,0.00001758174],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011646518,0.008627247,0.0019849862,0.1763745,0.0007902876,0.0011667839,0.0026094893,0.00038080703,0.00002365012,0.24252248,0.034174636,0.53018045],"study_design_scores_gemma":[0.0020467862,0.0009295366,0.000032370514,0.0560394,0.0011460405,0.00083526055,0.00008645995,0.030010441,0.0000015855276,0.0012781908,0.9071428,0.00045113973],"about_ca_topic_score_codex":0.0001013396,"about_ca_topic_score_gemma":0.000016917436,"teacher_disagreement_score":0.87296814,"about_ca_system_score_codex":0.00045152596,"about_ca_system_score_gemma":0.0019717875,"threshold_uncertainty_score":0.9997238},"labels":[],"label_agreement":null},{"id":"W3005813709","doi":"10.1161/str.51.suppl_1.wp406","title":"Abstract WP406: Training and Validation of Deepmedic Machine Learning Tool for Automated Hematoma Segmentation and Volume Analysis on CT Using Multicenter Data","year":2020,"lang":"en","type":"article","venue":"Stroke","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen Elizabeth II Health Sciences Centre; University of Calgary; Sunnybrook Health Science Centre; University of Ottawa; Dalhousie University","funders":"","keywords":"Medicine; Segmentation; Intraclass correlation; Sørensen–Dice coefficient; Confidence interval; Cohort; Artificial intelligence; Nuclear medicine; Radiology; Image segmentation; Internal medicine; Computer science","score_opus":0.042516807009308884,"score_gpt":0.3403180001635956,"score_spread":0.2978011931542867,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3005813709","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9746474,0.00012128078,0.023952603,0.00079405087,0.00003611776,0.00027018427,0.00006794229,0.00008523113,0.000025162532],"genre_scores_gemma":[0.979123,0.000027779868,0.01984879,0.0002524551,0.00007471545,0.0000035025948,0.0006292995,0.000019376273,0.000021057795],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989717,0.000036709607,0.00031456124,0.0003081553,0.00021689893,0.00015198988],"domain_scores_gemma":[0.99937755,0.0001357051,0.00018676656,0.00013998887,0.000038470364,0.00012151003],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042655854,0.000118215714,0.00034765573,0.00013578674,0.000085201085,0.00003284802,0.00006238713,0.00003103971,0.000035775534],"category_scores_gemma":[0.00076027197,0.000106567844,0.00004975593,0.0001549033,0.00005520715,0.00012536706,0.00004913186,0.00021138378,6.446672e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005266225,0.0001412258,0.66210485,0.0012749514,0.0018978472,0.000056673678,0.0044647334,0.011411665,0.19907922,0.000020017831,0.00019965015,0.11882253],"study_design_scores_gemma":[0.0018752532,0.00014282514,0.02729275,0.000091546775,0.00081583543,0.00001330248,0.0004269132,0.9676249,0.0014129422,0.0000017366914,0.00021468889,0.00008732515],"about_ca_topic_score_codex":0.000047674595,"about_ca_topic_score_gemma":0.000001426162,"teacher_disagreement_score":0.95621324,"about_ca_system_score_codex":0.000018645249,"about_ca_system_score_gemma":0.000028012813,"threshold_uncertainty_score":0.43457106},"labels":[],"label_agreement":null},{"id":"W3006101259","doi":"","title":"Deep Convolutional Networks for Automated Detection of Epileptogenic Brain Malformations","year":2018,"lang":"en","type":"article","venue":"Lecture notes in computer science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Montreal Neurological Institute and Hospital","funders":"","keywords":"Convolutional neural network; Computer science; Cortical dysplasia; Artificial intelligence; Voxel; Pattern recognition (psychology); Magnetic resonance imaging; Medicine; Radiology","score_opus":0.008580735068186154,"score_gpt":0.28663051307550913,"score_spread":0.278049778007323,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3006101259","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.098284595,0.000056822737,0.8994829,0.0013373398,0.0005494395,0.00020162316,6.3324933e-7,0.00007725898,0.000009397177],"genre_scores_gemma":[0.8322881,0.000001661635,0.16611494,0.0012458457,0.00033172956,0.000006727691,0.0000051076186,0.0000051966463,7.073921e-7],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990988,0.000022198876,0.00022276989,0.0002092582,0.00020506061,0.00024190683],"domain_scores_gemma":[0.9991799,0.00030963146,0.00007931951,0.00015904313,0.0001986763,0.000073456424],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006393767,0.000076781595,0.00014554091,0.00020119963,0.00015360344,0.000022228889,0.00015462041,0.000055806246,0.000010716548],"category_scores_gemma":[0.0006398524,0.00006492476,0.000045922683,0.00068356737,0.00057948,0.000099984325,0.000050671242,0.00016953092,0.0000022040617],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000070032474,0.00007646704,0.0069184196,0.000054416887,0.00001790761,0.0000022080467,0.00065115246,0.3189104,0.03098621,0.00019122216,0.00007911171,0.64204246],"study_design_scores_gemma":[0.0005465561,0.00024926546,0.017644918,0.000054675562,0.000007672479,0.00005554673,5.435703e-7,0.9756004,0.004960141,0.0007165515,0.00010091743,0.00006277917],"about_ca_topic_score_codex":0.000016049957,"about_ca_topic_score_gemma":0.000016797798,"teacher_disagreement_score":0.7340035,"about_ca_system_score_codex":0.00006947046,"about_ca_system_score_gemma":0.00011266972,"threshold_uncertainty_score":0.2647555},"labels":[],"label_agreement":null},{"id":"W3006651584","doi":"10.1016/j.jacr.2020.01.007","title":"Patient Perspectives and Priorities Regarding Artificial Intelligence in Radiology: Opportunities for Patient-Centered Radiology","year":2020,"lang":"en","type":"article","venue":"Journal of the American College of Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":61,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Saskatchewan Health Authority; Saskatchewan Health; Saskatoon Medical Imaging; University of Saskatchewan","funders":"University of Saskatchewan","keywords":"Workflow; Triage; Radiology; Patient care; Medicine; Medical physics; Computer science; Medical emergency; Nursing","score_opus":0.035701389088750944,"score_gpt":0.2956942958709268,"score_spread":0.2599929067821759,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3006651584","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9598014,0.0023538368,0.002297468,0.034766503,0.00035833998,0.00032748262,0.000028328705,0.000007290894,0.000059390768],"genre_scores_gemma":[0.99151087,0.0015567023,0.004714279,0.0019056335,0.00027864485,0.0000064731785,0.000001047226,0.000018681283,0.000007661485],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9981134,0.00042709112,0.00082708715,0.00020910765,0.0001484768,0.0002748533],"domain_scores_gemma":[0.99792796,0.0005998269,0.0009832216,0.00014066754,0.00018264604,0.00016567537],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046377748,0.00016369855,0.0010310925,0.00022236664,0.0000738391,0.0000053819385,0.00019225314,0.000063994645,0.000005644714],"category_scores_gemma":[0.002215108,0.00011376712,0.00021633432,0.00021723121,0.0013974456,0.00005699667,0.00008597723,0.0005182687,1.18510485e-7],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.03297297,0.00094074465,0.12231705,0.0008530612,0.00280985,0.0027014043,0.054086473,0.003177134,0.12422744,0.03739945,0.033900127,0.5846143],"study_design_scores_gemma":[0.012661668,0.083284825,0.053901196,0.002155543,0.0017207625,0.08797955,0.6004911,0.08192597,0.016806798,0.017612856,0.039455287,0.0020044306],"about_ca_topic_score_codex":0.000010774534,"about_ca_topic_score_gemma":0.0000020542532,"teacher_disagreement_score":0.58260983,"about_ca_system_score_codex":0.00009938235,"about_ca_system_score_gemma":0.00024210052,"threshold_uncertainty_score":0.5148946},"labels":[],"label_agreement":null},{"id":"W3006982737","doi":"10.1088/1361-6560/ab8535","title":"A physics-guided modular deep-learning based automated framework for tumor segmentation in PET","year":2020,"lang":"en","type":"article","venue":"Physics in Medicine and Biology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":57,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Institute of Biomedical Imaging and Bioengineering","keywords":"Segmentation; Dice; Context (archaeology); Modular design; Generalizability theory; Positron emission tomography; Pattern recognition (psychology); Similarity (geometry); Image segmentation","score_opus":0.11093126330568423,"score_gpt":0.41319998532128666,"score_spread":0.3022687220156024,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3006982737","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.63927954,0.00036068857,0.33921278,0.020002708,0.00015828069,0.00065998494,0.000003146386,0.00017647633,0.00014635344],"genre_scores_gemma":[0.96029794,0.000072205425,0.028444465,0.010180641,0.00074134517,0.00005511663,0.00017790704,0.000026292782,0.0000040758105],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99879,0.00011650454,0.00034397643,0.00036034928,0.000101964404,0.00028716112],"domain_scores_gemma":[0.9991654,0.00043002624,0.00011848174,0.000100484,0.000050325358,0.00013525935],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003742204,0.00017197238,0.0005316075,0.00007312178,0.000048593814,0.000006611934,0.000072696916,0.00006179738,0.000018116234],"category_scores_gemma":[0.0013186135,0.00013735359,0.000045634082,0.00035464286,0.00017520835,0.00003810489,0.000028855806,0.0006070872,0.0000021671906],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001493342,0.0008321023,0.45108938,0.0027643112,0.0002880017,0.00048648252,0.013018041,0.034671508,0.23716167,0.039188292,0.0019934138,0.21701348],"study_design_scores_gemma":[0.0045184223,0.0007140082,0.003946935,0.0003405101,0.000055596844,0.000012966761,0.00047613314,0.9772838,0.0004665177,0.011384558,0.0006526622,0.00014791895],"about_ca_topic_score_codex":0.00007502231,"about_ca_topic_score_gemma":0.0000018300823,"teacher_disagreement_score":0.9426123,"about_ca_system_score_codex":0.00003854986,"about_ca_system_score_gemma":0.000046143217,"threshold_uncertainty_score":0.5601117},"labels":[],"label_agreement":null},{"id":"W3007455870","doi":"10.1186/s13244-019-0832-5","title":"Deep learning workflow in radiology: a primer","year":2020,"lang":"en","type":"review","venue":"Insights into Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":179,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal; Centre Hospitalier de l’Université de Montréal; Centre intégré de santé et de services sociaux de Chaudière-Appalaches; Centre Intégré de Santé et de Services Sociaux des Laurentides; Université de Montréal; Université Laval; Cegep regional de Lanaudiere","funders":"Fonds de Recherche du Québec - Santé; Fondation de l'Association des radiologistes du Québec; Institut de Valorisation des Données","keywords":"Workflow; Neuroradiology; Medicine; Interventional radiology; Primer (cosmetics); Radiology; Medical physics; Computer science; Neurology; Database","score_opus":0.018752069411409323,"score_gpt":0.3295022001419946,"score_spread":0.31075013073058527,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3007455870","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000010518445,0.98974746,0.0032147472,0.0010425057,0.000582289,0.00069837895,1.9841744e-7,0.0002432866,0.0044605862],"genre_scores_gemma":[0.00019653498,0.9899898,0.0071457103,0.0009732075,0.0009850592,0.000085118074,0.00010620819,0.00019683356,0.00032150163],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9964503,0.00047434078,0.0010804774,0.0009852598,0.00038532287,0.00062427996],"domain_scores_gemma":[0.9982681,0.0004207801,0.0003938479,0.00045479086,0.00005779069,0.00040465393],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.00042783597,0.0006942483,0.0029610733,0.00078319566,0.00015059106,0.00008946025,0.00039544053,0.00030811393,0.00011092179],"category_scores_gemma":[0.0013623737,0.0005392594,0.00057598995,0.00087816024,0.00025980815,0.00013384226,0.00024218141,0.0042985505,0.0002679154],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011507502,0.00004165499,0.00046510986,0.004530748,0.00014771007,0.0023307535,0.000912305,0.000019442654,0.000004427436,0.00011786203,0.0002799533,0.9911385],"study_design_scores_gemma":[0.0006439958,0.00004408663,0.000024817422,0.0164805,0.0005928837,0.00095858227,0.00004221235,0.017048726,6.0212164e-7,0.00023138219,0.9634386,0.0004936488],"about_ca_topic_score_codex":0.00009474809,"about_ca_topic_score_gemma":0.0000044778308,"teacher_disagreement_score":0.9906449,"about_ca_system_score_codex":0.00048016838,"about_ca_system_score_gemma":0.00043260332,"threshold_uncertainty_score":0.9997059},"labels":[],"label_agreement":null},{"id":"W3007643597","doi":"10.1200/jco.2020.38.6_suppl.20","title":"Multiparametric magnetic resonance imaging of multifocal prostate cancer to reveal intra-prostatic genomic heterogeneity and novel radio-genomic correlates: Results of the Smarter Prostate Interventions and Therapeutics (SPIRIT) study.","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St Joseph's Health Care; Ontario Institute for Cancer Research; London Health Sciences Centre; Lawson Health Research Institute; Western University","funders":"","keywords":"Medicine; Prostate cancer; Prostatectomy; Prostate; Histopathology; Magnetic resonance imaging; Cancer; Gold standard (test); Pathology; Nuclear medicine; Radiology; Internal medicine","score_opus":0.07987718340682844,"score_gpt":0.4291617750754897,"score_spread":0.34928459166866127,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3007643597","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97616947,0.005766223,0.0005613088,0.015998594,0.00044621615,0.0010021381,0.00003953641,0.0000058501932,0.000010676723],"genre_scores_gemma":[0.9898438,0.0009631911,0.006498743,0.0024477236,0.00017405703,0.000010016624,9.891744e-7,0.00002679162,0.000034722827],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99575603,0.0004787879,0.002883429,0.00032860113,0.00030209048,0.00025103692],"domain_scores_gemma":[0.99607867,0.001357103,0.0016726742,0.00019042501,0.0003220915,0.00037906147],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028512834,0.00018597613,0.0012699338,0.00014057544,0.0000611663,0.000017344451,0.00022354198,0.00010760528,0.0000045340325],"category_scores_gemma":[0.004192784,0.00012245742,0.00029035722,0.00030148824,0.0005817987,0.00006306831,0.00019971657,0.0012019469,7.1128204e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004202219,0.000950729,0.7122265,0.00019704056,0.00019514652,0.00005430851,0.0027531192,0.00032818023,0.00869861,0.0000028490438,0.0001622732,0.270229],"study_design_scores_gemma":[0.014289349,0.0077014407,0.9550702,0.0005066802,0.00064166676,0.00018933807,0.00043787525,0.018411143,0.00008659434,0.00002467817,0.0025263533,0.00011467125],"about_ca_topic_score_codex":0.00009368693,"about_ca_topic_score_gemma":0.000032860844,"teacher_disagreement_score":0.27011433,"about_ca_system_score_codex":0.0000830191,"about_ca_system_score_gemma":0.00045700575,"threshold_uncertainty_score":0.5221928},"labels":[],"label_agreement":null},{"id":"W3007657137","doi":"10.1117/12.2560146","title":"Non-invasive prediction of lymph node risk in oral cavity cancer patients using a combination of supervised and unsupervised machine learning algorithms","year":2020,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre","funders":"","keywords":"Machine learning; Radiomics; Artificial intelligence; Medicine; Lymph node; Occult; Algorithm; Dimensionality reduction; Cancer imaging; Cancer; Radiology; Computer science; Internal medicine; Pathology","score_opus":0.018003944264977326,"score_gpt":0.2706560972858094,"score_spread":0.2526521530208321,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3007657137","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9957546,0.00012506881,0.0031405415,0.00046548204,0.000068193745,0.00030005616,0.000040526298,0.000024548433,0.00008095659],"genre_scores_gemma":[0.99567497,0.00030340295,0.003652502,0.00021811285,0.00003261961,0.0000055504775,0.00008100295,0.000021209224,0.00001060355],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987699,0.00009980913,0.0004219383,0.0002446071,0.00030165282,0.00016212137],"domain_scores_gemma":[0.9993409,0.00008122785,0.00018370914,0.00008340541,0.00016738425,0.00014341007],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002757183,0.00013509704,0.0004246662,0.00013364581,0.00005369664,0.000007138808,0.000054555218,0.000077117904,0.000048842812],"category_scores_gemma":[0.00059626927,0.000118500386,0.000054275577,0.00030970978,0.00010003262,0.00010435138,0.00005612055,0.00033457982,3.3804713e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014669762,0.00019149625,0.96633303,0.0003155801,0.000047877475,0.0000039361216,0.0015023577,0.0017385285,0.017078755,0.000004489069,0.000007802712,0.0126294345],"study_design_scores_gemma":[0.0048409277,0.00017958399,0.40895033,0.00016045845,0.00007906037,0.0000014131723,0.00012196496,0.5834475,0.002151291,0.000007901495,0.0000057369143,0.000053811145],"about_ca_topic_score_codex":0.0076775355,"about_ca_topic_score_gemma":0.000025871997,"teacher_disagreement_score":0.58170897,"about_ca_system_score_codex":0.000072926785,"about_ca_system_score_gemma":0.000102908,"threshold_uncertainty_score":0.99893045},"labels":[],"label_agreement":null},{"id":"W3007666443","doi":"10.1200/jco.2020.38.6_suppl.291","title":"GLUT1 expression in high-risk prostate cancer: Correlation with 18F-FDG-PET/CT and clinical outcome.","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Medicine; Prostatectomy; Prostate cancer; Standardized uptake value; GLUT1; Positron emission tomography; Biochemical recurrence; Metastasis; Cancer; Biopsy; Stage (stratigraphy); Oncology; Nuclear medicine; Internal medicine; Urology; Glucose transporter","score_opus":0.06061232942779081,"score_gpt":0.4620119878217214,"score_spread":0.4013996583939306,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3007666443","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95463437,0.00043437182,0.0009991438,0.042499676,0.0009723944,0.00021044692,0.0000022330164,0.000013451086,0.00023393407],"genre_scores_gemma":[0.9745977,0.0044599907,0.013426698,0.006252877,0.0011534333,0.000002701146,0.0000026816392,0.00002297499,0.00008097674],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99531966,0.00075410894,0.003049419,0.00028294095,0.0003702645,0.0002235839],"domain_scores_gemma":[0.9937346,0.0030330566,0.0022367856,0.00012012111,0.00017322734,0.0007022326],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0046906695,0.000147586,0.0015788906,0.00008374956,0.00004466188,0.00001380066,0.0001223018,0.000065367196,0.000062699764],"category_scores_gemma":[0.014318515,0.00009131572,0.00020702837,0.00015790036,0.0003176984,0.00012715562,0.000065962995,0.0033809657,0.0000062403456],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0034701051,0.0003422956,0.8352251,0.00003092566,0.000091245696,0.0039038993,0.000060671704,0.00036097234,0.000016801783,0.000014409027,0.0014416205,0.15504195],"study_design_scores_gemma":[0.018891837,0.010006828,0.9138933,0.00034833723,0.0004195669,0.0012535725,0.000116069416,0.018273773,0.0000075713824,0.00013115654,0.0365289,0.00012908461],"about_ca_topic_score_codex":0.00009932431,"about_ca_topic_score_gemma":0.00003640461,"teacher_disagreement_score":0.15491287,"about_ca_system_score_codex":0.00007291123,"about_ca_system_score_gemma":0.0007741016,"threshold_uncertainty_score":0.9989183},"labels":[],"label_agreement":null},{"id":"W3007829463","doi":"10.1177/0846537119899526","title":"Radiogenomic Models Using Machine Learning Techniques to Predict EGFR Mutations in Non-Small Cell Lung Cancer","year":2020,"lang":"en","type":"article","venue":"Canadian Association of Radiologists Journal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":89,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Jewish General Hospital; McMaster University; McGill University Health Centre; University of Calgary","funders":"Réseau de cancérologie Rossy; McGill University","keywords":"Radiogenomics; Medicine; Lung cancer; Epidermal growth factor receptor; Contouring; Nuclear medicine; Exon; Logistic regression; Cancer; Radiology; Radiomics; Oncology; Internal medicine; Gene; Biology","score_opus":0.01758956021471287,"score_gpt":0.28065112892397814,"score_spread":0.2630615687092653,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3007829463","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94271624,0.001053609,0.036186047,0.018020494,0.00025207942,0.00057780294,0.000057528407,0.00004845453,0.001087727],"genre_scores_gemma":[0.9796526,0.0005190779,0.016443064,0.0026559378,0.00044815723,0.000011402058,0.000029541872,0.000037186164,0.00020305236],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983405,0.00018013667,0.0005502574,0.00022971033,0.00023432662,0.00046508654],"domain_scores_gemma":[0.9983132,0.000103773775,0.00042595586,0.0000860441,0.00018287293,0.00088816846],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009628803,0.00016543803,0.00046905375,0.000478418,0.00016602328,0.000042898886,0.0001805144,0.00016914072,0.000057782036],"category_scores_gemma":[0.0010060408,0.00016643714,0.00012468838,0.00040439708,0.000037892052,0.000102798374,0.000020680163,0.0011173795,0.0000015840676],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000429876,0.00002427787,0.83872885,0.00007662439,0.00012477917,0.00017661907,0.0023704432,0.13937557,0.012880061,0.00002492371,0.0027987983,0.003376097],"study_design_scores_gemma":[0.0017627417,0.00023661499,0.031909253,0.00027965303,0.00019279694,0.00016269257,0.00021819721,0.9593205,0.0008610845,0.000067363,0.0047096442,0.0002794626],"about_ca_topic_score_codex":0.018324867,"about_ca_topic_score_gemma":0.004500303,"teacher_disagreement_score":0.8199449,"about_ca_system_score_codex":0.0029007585,"about_ca_system_score_gemma":0.0012439416,"threshold_uncertainty_score":0.98821217},"labels":[],"label_agreement":null},{"id":"W3007977432","doi":"10.1200/jco.2020.38.6_suppl.296","title":"Comparison of micro-ultrasound and multiparametric MRI imaging for prostate cancer: A multicenter prospective analysis.","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; University of Toronto; Sunnybrook Health Science Centre","funders":"","keywords":"Medicine; Ultrasound; Biopsy; Radiology; Magnetic resonance imaging; Prostate cancer; Multiparametric MRI; Prospective cohort study; Prostate; Nuclear medicine; Cancer; Pathology; Internal medicine","score_opus":0.06834707980865913,"score_gpt":0.49947789382797514,"score_spread":0.431130814019316,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3007977432","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.967955,0.0024793458,0.010023049,0.018607719,0.0003635158,0.0004596305,0.00000951442,0.000007955556,0.000094284485],"genre_scores_gemma":[0.95535016,0.00074778975,0.040713526,0.0026377845,0.00050428335,0.000006031158,0.000002974925,0.000014357447,0.000023077057],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9971431,0.00018172458,0.0020072786,0.00023089696,0.00023754436,0.00019946357],"domain_scores_gemma":[0.99358,0.0034155047,0.0019468409,0.000086812826,0.00053991383,0.00043095974],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0018295278,0.00012130676,0.002030469,0.00021173862,0.000037084526,0.000012900787,0.000112764705,0.0001115327,0.000023091141],"category_scores_gemma":[0.0119962245,0.00008690875,0.00051092426,0.00042039866,0.00029986777,0.00006906899,0.000039281793,0.000964092,6.017843e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002910537,0.0006189957,0.9281254,0.000103195256,0.0013731915,0.000036018802,0.0010318618,0.00041888186,0.001874083,0.00000821982,0.0014461023,0.06205352],"study_design_scores_gemma":[0.014557081,0.0043691783,0.8208048,0.000100015925,0.004113856,0.000050164825,0.00064631354,0.13864806,0.0004893087,0.000052425967,0.016051086,0.00011770967],"about_ca_topic_score_codex":0.000039460647,"about_ca_topic_score_gemma":0.0000070921215,"teacher_disagreement_score":0.13822918,"about_ca_system_score_codex":0.000066349094,"about_ca_system_score_gemma":0.00039479978,"threshold_uncertainty_score":0.99632615},"labels":[],"label_agreement":null},{"id":"W3008753367","doi":"10.1016/j.media.2020.101668","title":"Contrast agent-free synthesis and segmentation of ischemic heart disease images using progressive sequential causal GANs","year":2020,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":85,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Segmentation; Computer science; Artificial intelligence; Regularization (linguistics); Pixel; Pattern recognition (psychology); Leverage (statistics); Computer vision","score_opus":0.014827723108367795,"score_gpt":0.3162005930765553,"score_spread":0.3013728699681875,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3008753367","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87127286,0.001238983,0.09591488,0.03094203,0.000046774276,0.00029112995,0.0000622376,0.00006812285,0.0001629682],"genre_scores_gemma":[0.9835736,0.00009767387,0.013121478,0.002785939,0.00027343503,0.000015271613,0.00007917359,0.000026715597,0.000026697198],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978128,0.00014590069,0.00047342532,0.00040810413,0.00088424375,0.0002755299],"domain_scores_gemma":[0.99824595,0.0001898429,0.00017374479,0.0002705933,0.00012715999,0.0009927227],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00038931565,0.0001888793,0.0006758359,0.00017872121,0.000083723906,0.000044457236,0.0001597941,0.000076092234,0.0011429851],"category_scores_gemma":[0.0049720006,0.00015695684,0.000260463,0.00059744244,0.00054400193,0.00013150719,0.00013999673,0.00034637435,0.00000452166],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007960108,0.00058587146,0.25335577,0.0013459368,0.0055872253,0.003184073,0.0012229424,0.00013320184,0.69638443,0.000023335431,0.016832288,0.020548912],"study_design_scores_gemma":[0.0063708387,0.0002799791,0.05453964,0.00078598777,0.035100464,0.0001981503,0.0009813018,0.80797714,0.091905266,0.00007185413,0.0010010626,0.00078832335],"about_ca_topic_score_codex":0.00014226144,"about_ca_topic_score_gemma":0.000001708691,"teacher_disagreement_score":0.8078439,"about_ca_system_score_codex":0.000036452388,"about_ca_system_score_gemma":0.00017815779,"threshold_uncertainty_score":0.9997701},"labels":[],"label_agreement":null},{"id":"W3008840315","doi":"10.1016/j.ejmp.2020.02.010","title":"Machine learning helps identifying volume-confounding effects in radiomics","year":2020,"lang":"en","type":"article","venue":"Physica Medica","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":79,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre","funders":"","keywords":"Radiomics; Bootstrapping (finance); Artificial intelligence; Computer science; Logistic regression; Cluster analysis; Machine learning; Robustness (evolution); Pairwise comparison; Confounding; Data mining; Statistics; Mathematics; Econometrics","score_opus":0.01534044335997121,"score_gpt":0.29319542781515145,"score_spread":0.27785498445518025,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3008840315","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86628735,0.0033988429,0.04287381,0.069889806,0.0014339127,0.0013168677,0.0000042029724,0.0008726971,0.013922497],"genre_scores_gemma":[0.99126065,0.00023376606,0.0025110273,0.0042168493,0.0011841104,0.000025923271,0.00005680022,0.00007799341,0.00043285618],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976537,0.0001610659,0.0004385045,0.0005316705,0.0006466503,0.00056839985],"domain_scores_gemma":[0.998641,0.00029820917,0.00015523813,0.0002300966,0.00003820253,0.0006372669],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005337046,0.00027727394,0.00070175837,0.00016562812,0.0001474817,0.00005787688,0.00024387149,0.00009883907,0.00014443828],"category_scores_gemma":[0.002637751,0.0002598449,0.00017369761,0.00059669436,0.0001633665,0.00015094201,0.0001334043,0.0017320223,0.00019093732],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00081865385,0.00091463164,0.35835597,0.0052370387,0.00076040794,0.004067146,0.02251735,0.0019261537,0.1555107,0.0041146684,0.01713973,0.42863756],"study_design_scores_gemma":[0.0070372485,0.00054731924,0.023453059,0.0011880234,0.0002662973,0.00013162616,0.00035197218,0.8546204,0.0017611086,0.0005277194,0.10949117,0.00062408554],"about_ca_topic_score_codex":0.0001239095,"about_ca_topic_score_gemma":0.0000018344127,"teacher_disagreement_score":0.8526942,"about_ca_system_score_codex":0.00012217989,"about_ca_system_score_gemma":0.00013031597,"threshold_uncertainty_score":0.9999854},"labels":[],"label_agreement":null},{"id":"W3009334705","doi":"10.3390/cancers12030578","title":"Glioma Grading via Analysis of Digital Pathology Images Using Machine Learning","year":2020,"lang":"en","type":"article","venue":"Cancers","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":69,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Digital pathology; Gray level; Glioma; Grading (engineering); Artificial intelligence; Medicine; Random forest; Digital image analysis; Pathology; Atypia; Support vector machine; Computer science; Computer vision; Cancer research; Biology","score_opus":0.01852469626171952,"score_gpt":0.2985756986660744,"score_spread":0.2800510024043549,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3009334705","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95471025,0.00088674284,0.042469513,0.0011076723,0.00008905832,0.00007459701,0.0000130722165,0.000063527055,0.00058556977],"genre_scores_gemma":[0.9969916,0.000050544757,0.0022188853,0.0005027062,0.00012591899,0.0000015296308,0.00005115272,0.00002371518,0.00003397599],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990474,0.00003466934,0.00025987334,0.00025497904,0.00018826114,0.00021479215],"domain_scores_gemma":[0.99941796,0.000062218845,0.00014554326,0.000116395546,0.000051377705,0.00020649403],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012540718,0.00012166376,0.0004918134,0.00024433955,0.00006133799,0.000019475883,0.00008562655,0.000047440742,0.00011550901],"category_scores_gemma":[0.0004527802,0.000110839916,0.0001972936,0.0009641986,0.00014891331,0.00007894976,0.000046611018,0.00035934892,0.000002757881],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020474153,0.00002290287,0.50186896,0.00021469987,0.002029057,0.0010602956,0.0019059111,0.07254492,0.38693014,0.000061976665,0.00018660608,0.03296979],"study_design_scores_gemma":[0.00073762215,0.00016305823,0.0033165338,0.00004795825,0.0014577379,0.00010083549,0.00014448285,0.98948455,0.0032468722,0.000022397911,0.0011360121,0.00014196851],"about_ca_topic_score_codex":0.00019403444,"about_ca_topic_score_gemma":0.0000015175865,"teacher_disagreement_score":0.9169396,"about_ca_system_score_codex":0.00019501646,"about_ca_system_score_gemma":0.00011458061,"threshold_uncertainty_score":0.45199206},"labels":[],"label_agreement":null},{"id":"W3009472179","doi":"10.1002/jmri.27110","title":"Editorial for \"Quantitative MRCP Imaging: Accuracy, Repeatability, Reproducibility, and Cohort‐Derived Normative Ranges","year":2020,"lang":"en","type":"article","venue":"Journal of Magnetic Resonance Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; University of Ottawa; Women's College Hospital; University of Toronto; University Health Network; Mount Sinai Hospital","funders":"","keywords":"Reproducibility; Repeatability; Normative; Magnetic resonance imaging; Medicine; Medical physics; Radiology; Statistics; Mathematics","score_opus":0.018982220158315483,"score_gpt":0.3175794045196611,"score_spread":0.29859718436134564,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3009472179","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.69078815,0.073356904,0.02160039,0.18979035,0.02040394,0.0026782271,0.00005276355,0.00014410398,0.0011851997],"genre_scores_gemma":[0.8777035,0.0021361148,0.07826417,0.005372299,0.036280602,0.000036740676,0.000015344145,0.00010815574,0.00008306518],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9969727,0.00019642434,0.0010315607,0.00073355174,0.0006870704,0.00037868464],"domain_scores_gemma":[0.9963539,0.0011380053,0.000666598,0.0004936252,0.0009358612,0.00041199228],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003470194,0.0002658221,0.00079345587,0.00012156165,0.00014910268,0.00012597574,0.00024764397,0.000048783302,0.000044417808],"category_scores_gemma":[0.027100049,0.00021805873,0.00022158823,0.00021582752,0.00046407405,0.00045690036,0.00015254528,0.0008341555,0.0000026317848],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0037963516,0.00024152207,0.44573182,0.000698871,0.000097186385,0.0002214934,0.0056563322,0.000032320037,0.03798313,0.00013722635,0.15153204,0.3538717],"study_design_scores_gemma":[0.016994594,0.0026279266,0.3226348,0.0013429583,0.0009513812,0.0015862051,0.0030942918,0.08265052,0.0039601433,0.003248134,0.56005466,0.0008543882],"about_ca_topic_score_codex":0.000027104521,"about_ca_topic_score_gemma":7.397678e-7,"teacher_disagreement_score":0.40852264,"about_ca_system_score_codex":0.00008149034,"about_ca_system_score_gemma":0.00024717127,"threshold_uncertainty_score":0.9810951},"labels":[],"label_agreement":null},{"id":"W3010660902","doi":"10.3390/app10061903","title":"Multimodal Ensemble-Based Segmentation of White Matter Lesions and Analysis of Their Differential Characteristics across Major Brain Regions","year":2020,"lang":"en","type":"article","venue":"Applied Sciences","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Artificial intelligence; Pattern recognition (psychology); Segmentation; Computer science; Hyperintensity; Fluid-attenuated inversion recovery; Voxel; White matter; False positive paradox; Magnetic resonance imaging; Medicine; Radiology","score_opus":0.020961760219583715,"score_gpt":0.3039733390713485,"score_spread":0.28301157885176476,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3010660902","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9443173,0.000008661028,0.04767862,0.007650668,0.000019476465,0.000121345256,0.000029132927,0.000010475111,0.00016431525],"genre_scores_gemma":[0.994311,0.0000041238395,0.004010381,0.0015659503,0.000027515078,0.0000052386567,0.000053488217,0.000004912465,0.00001739784],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99918896,0.000023599223,0.00023491059,0.00020512727,0.00021603318,0.00013136808],"domain_scores_gemma":[0.99949175,0.00013844931,0.00015192585,0.00008939458,0.000028497441,0.000099951925],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020253893,0.00007886186,0.00029747107,0.000095839816,0.0001578508,0.000016725831,0.00008799516,0.00003013384,0.000072289564],"category_scores_gemma":[0.00005567847,0.000056544985,0.00006426795,0.00050591794,0.00045647522,0.000025323307,0.000048922037,0.000099507095,0.0000010246332],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009903624,0.00008946617,0.4757989,0.0001096223,0.00018526235,0.0000019800946,0.005715561,0.00025666243,0.5094648,0.00034119526,0.00022264129,0.0077148774],"study_design_scores_gemma":[0.00093295064,0.00010420559,0.7868467,0.00002900175,0.00040942928,0.0000013609673,0.0011468916,0.1995624,0.01078795,0.000033943925,0.000050849478,0.000094300834],"about_ca_topic_score_codex":0.000020505902,"about_ca_topic_score_gemma":0.000003107094,"teacher_disagreement_score":0.49867684,"about_ca_system_score_codex":0.000005351572,"about_ca_system_score_gemma":0.0000330686,"threshold_uncertainty_score":0.23058376},"labels":[],"label_agreement":null},{"id":"W3011129081","doi":"10.1117/1.jmi.7.4.042803","title":"Quantitative imaging feature pipeline: a web-based tool for utilizing, sharing, and building image-processing pipelines","year":2020,"lang":"en","type":"article","venue":"Journal of Medical Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Cancer Institute; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health","keywords":"Upload; Computer science; Software; Pipeline (software); Graphical user interface; Segmentation; Feature (linguistics); Interface (matter); Image processing; Application programming interface; Image file formats; Source code; Machine learning; Artificial intelligence; Image (mathematics); World Wide Web","score_opus":0.021337683740427126,"score_gpt":0.3554667564339915,"score_spread":0.3341290726935644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3011129081","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.088153884,0.00971834,0.6483252,0.2527357,0.00044623498,0.00031250555,0.000005297023,0.000115742085,0.00018710423],"genre_scores_gemma":[0.79102015,0.00035436635,0.18113527,0.024874669,0.0024226494,0.000008567374,0.000011064185,0.0001234285,0.000049815666],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964514,0.00008011952,0.0010055624,0.00049064093,0.0014115724,0.00056072883],"domain_scores_gemma":[0.997037,0.0004560091,0.0006841172,0.0001671178,0.00067003537,0.0009857535],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0026949467,0.00035297914,0.00087236555,0.00030872566,0.00023710477,0.0002862839,0.00044646187,0.00011415739,0.000083376966],"category_scores_gemma":[0.011892565,0.0002789439,0.00032330572,0.00034953956,0.000387773,0.00048012927,0.00015772326,0.0017666903,0.0000020770194],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018148357,0.00030598306,0.12408111,0.003170288,0.0002049505,0.0032149446,0.0019211664,0.00011979268,0.076852255,0.0006612067,0.09524999,0.6924035],"study_design_scores_gemma":[0.0066569843,0.00011124252,0.0006083429,0.0024189504,0.0003325493,0.0013314411,0.0008290157,0.96249646,0.00058869517,0.00022309477,0.024121108,0.00028210747],"about_ca_topic_score_codex":0.000010494089,"about_ca_topic_score_gemma":4.083893e-7,"teacher_disagreement_score":0.96237665,"about_ca_system_score_codex":0.00007522858,"about_ca_system_score_gemma":0.00067419745,"threshold_uncertainty_score":0.99996626},"labels":[],"label_agreement":null},{"id":"W3011518098","doi":"10.1158/1538-7445.sabcs19-p5-02-01","title":"Abstract P5-02-01: Analytical validation and prognostic potential of an automated digital scoring protocol for Ki67: An International Ki67 Working Group study","year":2020,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; University of Toronto; Sunnybrook Health Science Centre; Ottawa Hospital; University of Ottawa; University of Alberta; Ontario Institute for Cancer Research; Queen's University; McMaster University; Juravinski Hospital; University of British Columbia","funders":"","keywords":"Medicine; Breast cancer; Reproducibility; Protocol (science); Cancer; Medical physics; Core biopsy; Biomarker; Biopsy; Guideline; Pathology; Internal medicine; Statistics; Mathematics","score_opus":0.12751611688142872,"score_gpt":0.5013966937374744,"score_spread":0.3738805768560457,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3011518098","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9697118,0.0000046001887,0.0006095997,0.0010949128,0.00006190985,0.028249921,0.000008779719,0.000098265526,0.00016024266],"genre_scores_gemma":[0.984557,0.0000015830176,0.0005141841,0.00004269076,0.0006270447,0.014157323,0.000056077293,0.0000304123,0.000013698797],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981894,0.00007152955,0.00031402486,0.00039635695,0.0007389346,0.00028975424],"domain_scores_gemma":[0.9990861,0.00012610665,0.000074154996,0.00014524526,0.0002338072,0.00033460656],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00085304095,0.000106736436,0.00021850204,0.00015864022,0.00011107413,0.00021326847,0.0001890076,0.000050211765,0.00007372272],"category_scores_gemma":[0.0010554038,0.00009211816,0.000038941398,0.00024189397,0.00014141561,0.00032934838,0.00009773648,0.00046731232,0.0000014101511],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0047804574,0.002485142,0.71670985,0.0013812922,0.0004532334,0.00024244218,0.0026914903,0.0014554134,0.04161078,0.00027259337,0.00041704864,0.22750029],"study_design_scores_gemma":[0.00640529,0.002916537,0.3306357,0.0005711497,0.00006238063,0.00001784652,0.00096006674,0.65612006,0.0010258214,0.0000804615,0.0010161003,0.00018860197],"about_ca_topic_score_codex":0.000078432844,"about_ca_topic_score_gemma":0.0000031203087,"teacher_disagreement_score":0.65466464,"about_ca_system_score_codex":0.00008175762,"about_ca_system_score_gemma":0.00015573078,"threshold_uncertainty_score":0.37564698},"labels":[],"label_agreement":null},{"id":"W3011720109","doi":"10.1038/s41598-020-61297-4","title":"Privacy-preserving distributed learning of radiomics to predict overall survival and HPV status in head and neck cancer","year":2020,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":80,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto","funders":"National Institute of Biomedical Imaging and Bioengineering; Stichting voor de Technische Wetenschappen; National Institute of Dental and Craniofacial Research; Center for Translational Molecular Medicine; National Cancer Institute; KWF Kankerbestrijding; National Institutes of Health; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Health Foundation Limburg; National Science Foundation; Eurostars; Horizon 2020 Framework Programme; Cancer Research UK; Andrew Sabin Family Foundation; Division of Mathematical Sciences; University of Texas MD Anderson Cancer Center; Interreg; Elekta","keywords":"Radiomics; Feature selection; Logistic regression; Computer science; Workflow; Feature (linguistics); Artificial intelligence; Cluster analysis; Machine learning; Receiver operating characteristic; Head and neck cancer; Data mining; Cancer; Medicine; Database; Internal medicine","score_opus":0.017762623576485382,"score_gpt":0.2961112534293367,"score_spread":0.2783486298528513,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3011720109","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99308926,0.00066154904,0.0009482949,0.0039050847,0.00074391015,0.00031610922,0.0000070566443,0.00003960308,0.00028915372],"genre_scores_gemma":[0.9978401,0.0001081162,0.0015507574,0.0001480942,0.00008306437,0.000007428434,0.00005888794,0.000019086981,0.0001844541],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9980863,0.00005762597,0.00048804286,0.0005982284,0.00042206387,0.00034775957],"domain_scores_gemma":[0.99887824,0.00006258334,0.00018153447,0.00028385344,0.00008502779,0.00050874345],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009062895,0.00013153661,0.00039201565,0.00012684223,0.00010005175,0.00009570921,0.00007695366,0.00005167912,0.00005453054],"category_scores_gemma":[0.0028012127,0.00011932363,0.000036846897,0.00042637647,0.0001740139,0.000103986604,0.00027335802,0.00037058373,4.6151501e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008766112,0.000032924174,0.96734196,0.00023704751,0.000025643738,0.0003283704,0.001846794,0.0017888331,0.01827269,0.000021047403,0.002365182,0.007651844],"study_design_scores_gemma":[0.0018558827,0.00023436619,0.8104051,0.0005229705,0.000064416476,0.00015865963,0.0003534996,0.120273665,0.001294391,0.0003333336,0.06424458,0.00025914446],"about_ca_topic_score_codex":0.0005898404,"about_ca_topic_score_gemma":0.00002351598,"teacher_disagreement_score":0.15693687,"about_ca_system_score_codex":0.000055713914,"about_ca_system_score_gemma":0.00018082466,"threshold_uncertainty_score":0.48658764},"labels":[],"label_agreement":null},{"id":"W3011724586","doi":"10.1117/12.2549749","title":"Automated segmentation of computed tomography colonography images using a 3D U-Net","year":2020,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Segmentation; Computer science; Artificial intelligence; Standard deviation; Pooling; Metric (unit); Cross entropy; Pattern recognition (psychology); Mathematics; Statistics","score_opus":0.01595989950550039,"score_gpt":0.3017560007201432,"score_spread":0.28579610121464283,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3011724586","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9028889,0.00016966648,0.089747235,0.0036354754,0.00010595497,0.0003546964,0.000007033078,0.0006431751,0.0024478494],"genre_scores_gemma":[0.8044129,0.000007181582,0.19303204,0.0024245738,0.000061824605,0.0000018383788,0.0000369878,0.00001399189,0.000008662114],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991755,0.000049342667,0.000260231,0.00017152181,0.00020097394,0.0001424589],"domain_scores_gemma":[0.9995262,0.000046100944,0.000100690406,0.00009185713,0.00007046221,0.00016467346],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012863678,0.00009968999,0.00025808284,0.00015083917,0.000045995785,0.000014764112,0.00006009558,0.00004049812,0.000093252216],"category_scores_gemma":[0.000075077594,0.000084668194,0.0001003325,0.0004550791,0.00010212682,0.000054518445,0.000028944674,0.00018444151,0.0000029811558],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031095606,0.0003509249,0.23806514,0.0007112817,0.0005679488,0.00009191207,0.00144805,0.0019281204,0.71106493,0.00033592517,0.025586529,0.019538295],"study_design_scores_gemma":[0.0017462764,0.00033784035,0.030966017,0.00009609111,0.00014883612,0.000029243667,0.0001294018,0.95379275,0.011783833,0.000016074006,0.0008370431,0.00011659298],"about_ca_topic_score_codex":0.00007555918,"about_ca_topic_score_gemma":2.1397126e-7,"teacher_disagreement_score":0.95186466,"about_ca_system_score_codex":0.000009453438,"about_ca_system_score_gemma":0.000033161996,"threshold_uncertainty_score":0.34526688},"labels":[],"label_agreement":null},{"id":"W3011824971","doi":"10.1158/1538-7445.sabcs19-p6-10-12","title":"Abstract P6-10-12: Texture heterogeneity of breast tumour in magnetic resonance imaging can be explained by differentially regulated genes","year":2020,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; Sunnybrook Health Science Centre; University of Toronto","funders":"","keywords":"Magnetic resonance imaging; Breast cancer; False discovery rate; Breast MRI; Tumour heterogeneity; Medicine; Multiple comparisons problem; Cancer; Pathology; Radiology; Gene; Biology; Mammography; Internal medicine; Genetics","score_opus":0.03404167046317556,"score_gpt":0.3504769301410093,"score_spread":0.3164352596778337,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3011824971","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95729816,0.011167285,0.000022926202,0.030657835,0.00005915302,0.0003826337,0.00010073941,0.000040963034,0.00027033204],"genre_scores_gemma":[0.9978374,0.00061847677,0.000087450826,0.00061290985,0.0002433606,0.00004756819,0.00006704029,0.00005281831,0.00043292326],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9973965,0.00017382414,0.0004231189,0.0005240098,0.00085149327,0.00063104095],"domain_scores_gemma":[0.99885917,0.00011259308,0.00008012999,0.00029828874,0.0002248887,0.00042491476],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005895129,0.00019622296,0.00044740454,0.00017279634,0.0000941549,0.000042029507,0.00032637364,0.00008623151,0.00087628997],"category_scores_gemma":[0.00033374285,0.0001727021,0.00008618605,0.00050130556,0.00033057356,0.000058950514,0.00014510176,0.0010109588,0.000005116941],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00061625685,0.00011137086,0.05845163,0.00033048703,0.000018872546,0.00020245777,0.0006313024,0.00003718238,0.8436178,0.000009104707,0.013803273,0.08217024],"study_design_scores_gemma":[0.0069327145,0.00038977992,0.8215806,0.0013975333,0.000054497323,0.000106749154,0.00043338767,0.019245595,0.12965119,0.000059224087,0.019634683,0.0005140568],"about_ca_topic_score_codex":0.0022703079,"about_ca_topic_score_gemma":0.00025663967,"teacher_disagreement_score":0.76312894,"about_ca_system_score_codex":0.00017088614,"about_ca_system_score_gemma":0.0003474367,"threshold_uncertainty_score":0.95947605},"labels":[],"label_agreement":null},{"id":"W3011844005","doi":"10.1007/s10278-020-00332-2","title":"Predicting the Response to FOLFOX-Based Chemotherapy Regimen from Untreated Liver Metastases on Baseline CT: a Deep Neural Network Approach","year":2020,"lang":"en","type":"article","venue":"Journal of Digital Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":26,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Polytechnique Montréal; Centre Hospitalier de l’Université de Montréal","funders":"Fonds de Recherche du Québec - Santé","keywords":"FOLFOX; Medicine; Regimen; Chemotherapy; Colorectal cancer; Radiology; Chemotherapy regimen; Oxaliplatin; Bevacizumab; Oncology; Internal medicine; Cancer","score_opus":0.01570369011507139,"score_gpt":0.26349445778627884,"score_spread":0.24779076767120745,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3011844005","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8591799,0.0011064286,0.048022617,0.09041345,0.00019134258,0.0003667414,0.000023573448,0.00008519498,0.00061070855],"genre_scores_gemma":[0.9672344,0.000010960744,0.0074599204,0.023912247,0.0012634059,0.00000304562,0.000025154965,0.000057483583,0.000033406457],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979661,0.00023136391,0.00057791494,0.0002751415,0.0005909529,0.00035851263],"domain_scores_gemma":[0.99773973,0.0010290489,0.00036336802,0.00023428358,0.00015073123,0.0004828173],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010156292,0.0002463902,0.00048558574,0.000115029616,0.00013063324,0.00026713958,0.0002760964,0.000021127358,0.000038184324],"category_scores_gemma":[0.0025602633,0.00015570885,0.00026113665,0.00041650631,0.00008855873,0.00026975392,0.000052970052,0.0007812865,0.00000847984],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.034909006,0.001159246,0.19525255,0.00014115844,0.0014740403,0.006600535,0.0055967453,0.2093298,0.008886771,0.00002495017,0.039028306,0.4975969],"study_design_scores_gemma":[0.004506405,0.00075369346,0.007100701,0.0003379067,0.00030954197,0.0005162137,0.0004729327,0.9736887,0.0005583279,0.000036290578,0.0114967255,0.00022253758],"about_ca_topic_score_codex":0.000021358092,"about_ca_topic_score_gemma":2.1383092e-7,"teacher_disagreement_score":0.76435894,"about_ca_system_score_codex":0.000075792836,"about_ca_system_score_gemma":0.00011071376,"threshold_uncertainty_score":0.6349623},"labels":[],"label_agreement":null},{"id":"W3012448416","doi":"","title":"Analytical validation of a standardised scoring protocol for Ki67 immunohistochemistry on breast cancer excision whole sections: an international multicentre collaboration","year":2019,"lang":"en","type":"book-chapter","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; University of Toronto; Sunnybrook Health Science Centre; Ottawa Hospital; University of Ottawa; University of Alberta; Institute of Cancer Research; Ontario Institute for Cancer Research; McMaster University; University of British Columbia","funders":"","keywords":"Concordance; Intraclass correlation; Breast cancer; Medicine; Reproducibility; Confidence interval; Nuclear proliferation; Concordance correlation coefficient; Protocol (science); Nuclear medicine; Cancer; Pathology; Internal medicine; Statistics; Mathematics","score_opus":0.02100851844806706,"score_gpt":0.38832968684028923,"score_spread":0.3673211683922222,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3012448416","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025727978,0.000053420747,0.023725512,0.01039116,0.003183946,0.36634314,0.0027647074,0.00047999556,0.5673301],"genre_scores_gemma":[0.062792644,0.00006944477,0.009741237,0.0009927744,0.0045809452,0.07262755,0.0045204936,0.0004856464,0.8441893],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983468,0.000013490766,0.0005032183,0.00041208082,0.000584401,0.00014003096],"domain_scores_gemma":[0.9983399,0.00008017578,0.0003585816,0.00033496573,0.00076892524,0.000117447984],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002587476,0.00023428552,0.00040761032,0.00018510302,0.00006869182,0.00005062577,0.0001187368,0.00019507638,0.0008883275],"category_scores_gemma":[0.00016326614,0.00020206858,0.0001515991,0.000044471548,0.000064930755,0.00013930585,0.000029900368,0.0003854907,0.000007740499],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.10896172,0.0067210025,0.029031191,0.024621032,0.009054257,0.00017550742,0.0037106555,0.06434155,0.22000125,0.11367872,0.08602424,0.33367887],"study_design_scores_gemma":[0.03774796,0.0021831372,0.0025245564,0.017907826,0.0013897796,0.00015733766,0.00046674104,0.4814003,0.015227922,0.0010653224,0.43822908,0.0017000289],"about_ca_topic_score_codex":0.000022195274,"about_ca_topic_score_gemma":0.0000020568616,"teacher_disagreement_score":0.41705877,"about_ca_system_score_codex":0.0005496808,"about_ca_system_score_gemma":0.0005293894,"threshold_uncertainty_score":0.9726563},"labels":[],"label_agreement":null},{"id":"W3013393667","doi":"10.22038/ijmp.2018.12974","title":"Advanced quantitative MRI radiomics features for recurrence prediction in glioblastoma multiform patients","year":2018,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Radiomics; Fluid-attenuated inversion recovery; Random forest; Magnetic resonance imaging; Receiver operating characteristic; Glioblastoma; Medicine; Gray level; Nuclear medicine; Radiology; Artificial intelligence; Computer science; Pixel; Internal medicine","score_opus":0.010370581022722621,"score_gpt":0.314476535434762,"score_spread":0.30410595441203936,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3013393667","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96288365,0.00008531815,0.031695403,0.0011242132,0.0008842422,0.00094351603,0.000024149833,0.00009394034,0.0022655556],"genre_scores_gemma":[0.92521197,0.000048799873,0.07288938,0.0006806477,0.0002100899,0.00005734184,0.00005638557,0.000026545416,0.00081884913],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99897635,0.000021246771,0.00026279403,0.00028734608,0.00018749844,0.00026475338],"domain_scores_gemma":[0.9992977,0.00014279221,0.000081511906,0.00015273155,0.00020865117,0.00011665984],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025570014,0.00012898426,0.00022446013,0.0001688048,0.00008054077,0.000015544356,0.0000795053,0.00007532547,0.000039617604],"category_scores_gemma":[0.0010967712,0.000103690836,0.00005858487,0.00021387018,0.00013992035,0.0001362637,0.000023682232,0.0002463821,0.000016443943],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0063732653,0.0012145643,0.3287912,0.00038280306,0.000145401,0.000014958707,0.005481505,0.00032599128,0.0060962676,0.00606313,0.044895556,0.6002154],"study_design_scores_gemma":[0.024003366,0.010742949,0.35617435,0.001044574,0.00011120937,0.000043631408,0.0012844017,0.5365756,0.010865168,0.0013329528,0.057225574,0.0005961977],"about_ca_topic_score_codex":0.00003897692,"about_ca_topic_score_gemma":0.000062071354,"teacher_disagreement_score":0.59961915,"about_ca_system_score_codex":0.00010384203,"about_ca_system_score_gemma":0.000047770598,"threshold_uncertainty_score":0.42283896},"labels":[],"label_agreement":null},{"id":"W3013419627","doi":"10.1158/1538-7445.sabcs19-p5-02-04","title":"Abstract P5-02-04: Upfront dichotomous histopathological assessment of ductal carcinoma in situ of the breast to reduce inter-observer variability: The DCISion study","year":2020,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Sunnybrook Health Science Centre","funders":"","keywords":"Medicine; Breast cancer; Ductal carcinoma; Concordance; Intraclass correlation; Radiology; Oncology; Internal medicine; Pathology; Cancer","score_opus":0.08109260586593608,"score_gpt":0.43570941266165214,"score_spread":0.35461680679571606,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3013419627","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9734287,0.000110514084,0.00007307315,0.024039447,0.00015696825,0.0012213698,0.000010590394,0.000009263392,0.00095003133],"genre_scores_gemma":[0.9991774,0.000013774648,0.00011720156,0.00034922073,0.00016412606,0.000095835756,0.0000020119605,0.000016930007,0.00006348919],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9971611,0.0006542269,0.00045496091,0.0004127707,0.0009949106,0.00032205155],"domain_scores_gemma":[0.99856055,0.00035219974,0.00008755829,0.00055086345,0.0002502998,0.00019850722],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036065895,0.0001199275,0.00037903077,0.00008221568,0.00008266143,0.000017269782,0.0005495838,0.000057069577,0.00023574101],"category_scores_gemma":[0.0014533947,0.000064359774,0.000093715564,0.00056364626,0.00034043036,0.00003536054,0.0004889306,0.0014084135,0.0000026206965],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005489441,0.0007859058,0.75233716,0.00018223174,0.000032008586,0.0001980877,0.0043664854,0.00022160506,0.226104,0.000060397764,0.0015488684,0.013614325],"study_design_scores_gemma":[0.00096604764,0.0005566024,0.9939661,0.00015862971,0.000022479051,0.00003166579,0.0012851264,0.0010390365,0.001582183,0.000042996584,0.00028770577,0.00006142072],"about_ca_topic_score_codex":0.0015230547,"about_ca_topic_score_gemma":0.00007463081,"teacher_disagreement_score":0.24162897,"about_ca_system_score_codex":0.00038267937,"about_ca_system_score_gemma":0.0004648297,"threshold_uncertainty_score":0.6118934},"labels":[],"label_agreement":null},{"id":"W3014785343","doi":"10.1148/rycan.2020190079","title":"Decoding and Systematization of Medical Imaging Features of Multiple Human Malignancies","year":2020,"lang":"en","type":"article","venue":"Radiology Imaging Cancer","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"China Scholarship Council; China Postdoctoral Science Foundation","keywords":"Malignancy; Feature (linguistics); Medical imaging; Cluster analysis; Medicine; Feature selection; Computer science; Pattern recognition (psychology); Artificial intelligence; Pathology","score_opus":0.013609783254060946,"score_gpt":0.3196896325571045,"score_spread":0.30607984930304355,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3014785343","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9301043,0.017807066,0.016516527,0.03408925,0.00031949428,0.00034999946,0.000011130899,0.00009613878,0.0007061039],"genre_scores_gemma":[0.9960199,0.00044452236,0.0013145233,0.0019112481,0.00024228031,0.000011215305,0.000012928771,0.000023706993,0.000019664276],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986725,0.0000927938,0.00044176812,0.00026149317,0.00032331416,0.00020817122],"domain_scores_gemma":[0.9991655,0.00017635504,0.00024093715,0.00012926954,0.000099597426,0.0001883484],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004683557,0.00013633927,0.00056606275,0.00010463338,0.00006711416,0.000009487548,0.0001351087,0.0000612525,0.000076722485],"category_scores_gemma":[0.0011620324,0.00011422696,0.00006785109,0.00014381803,0.0003990496,0.00006458584,0.0000735572,0.00030404032,4.960159e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041667194,0.000020759839,0.8725601,0.0017209919,0.000096279815,0.00004670214,0.0014691108,0.0000661806,0.10331849,0.0013453031,0.0035924327,0.015722001],"study_design_scores_gemma":[0.00824621,0.00016716009,0.41391683,0.006206884,0.0006855108,0.0020747723,0.0020518505,0.54356027,0.019253157,0.00030510954,0.0029145102,0.0006177232],"about_ca_topic_score_codex":0.00030688551,"about_ca_topic_score_gemma":0.0000051457923,"teacher_disagreement_score":0.5434941,"about_ca_system_score_codex":0.00003433118,"about_ca_system_score_gemma":0.000102786216,"threshold_uncertainty_score":0.465804},"labels":[],"label_agreement":null},{"id":"W3015214387","doi":"10.2196/18960","title":"Application of Magnetic Resonance Image Intelligent Data Acquisition in Ovarian Cancer (Preprint)","year":2020,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Preprint; Magnetic resonance imaging; Computer science; Medicine; Computer vision; Medical physics; Radiology; World Wide Web","score_opus":0.017990239895881686,"score_gpt":0.33287669092613387,"score_spread":0.3148864510302522,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3015214387","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3971941,0.0034879684,0.52278394,0.065184675,0.00032806766,0.0031753352,0.000095693176,0.00023482814,0.0075154095],"genre_scores_gemma":[0.96372044,0.0013613182,0.023148004,0.011030113,0.00031837367,0.00010323033,0.00026747235,0.00002463263,0.000026441809],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998146,0.000031111074,0.0007901949,0.00016542726,0.0006686533,0.00019863958],"domain_scores_gemma":[0.99887556,0.00007274256,0.00016428337,0.00048067368,0.00006580327,0.0003409635],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005607144,0.000112300964,0.00030762755,0.00007238721,0.00002016401,0.000013140592,0.00042073842,0.000115873896,0.0004888164],"category_scores_gemma":[0.00058441394,0.000095911244,0.000035623212,0.00033131088,0.00016317378,0.0001729283,0.00028998687,0.0005817583,0.00004973524],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000178055,0.00021695394,0.02280813,0.0012953436,0.000018514296,0.00003308003,0.006470452,0.000058876667,0.0014938436,0.00072777807,0.005155794,0.9615432],"study_design_scores_gemma":[0.0014624939,0.0001301417,0.024526488,0.0005100485,0.000025682652,0.000018304429,0.0005887303,0.92465717,0.0005476297,0.00009185506,0.047319632,0.00012183321],"about_ca_topic_score_codex":0.00010000777,"about_ca_topic_score_gemma":0.0000036597346,"teacher_disagreement_score":0.9614214,"about_ca_system_score_codex":0.00004840631,"about_ca_system_score_gemma":0.00019055359,"threshold_uncertainty_score":0.5352197},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W3015481932","doi":"10.1016/j.ejmp.2020.03.018","title":"Bridging the gap between micro- and macro-scales in medical imaging with textural analysis – A biological basis for CT radiomics classifiers?","year":2020,"lang":"en","type":"article","venue":"Physica Medica","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":23,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; Hospital for Sick Children; Princess Margaret Cancer Centre; Ontario Institute for Cancer Research; University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"Radiomics; Digital pathology; Attenuation; Artificial intelligence; Pattern recognition (psychology); Pixel; Feature (linguistics); Computer science; Nuclear medicine; Medicine; Physics; Optics","score_opus":0.023756445552523455,"score_gpt":0.29938920274851677,"score_spread":0.27563275719599334,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3015481932","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.76810336,0.00062373973,0.024541704,0.20582141,0.000050428505,0.000488219,0.000026012012,0.00009160315,0.0002535074],"genre_scores_gemma":[0.98827237,0.0002474693,0.0023643794,0.007831481,0.0010938271,0.000048170245,0.000095597796,0.000035546484,0.000011178687],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99764025,0.00014403198,0.00044072806,0.0006184977,0.000608178,0.0005483019],"domain_scores_gemma":[0.99792516,0.0009563517,0.00014802083,0.00025567433,0.000048749036,0.0006660674],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007888588,0.00028438572,0.0008745581,0.00015064831,0.00018185504,0.000058037705,0.00031568005,0.00006709095,0.00004362847],"category_scores_gemma":[0.0013897257,0.00016436737,0.00023485628,0.00084763614,0.00087926775,0.000072889736,0.0001285586,0.00094530935,0.0000033986744],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004616704,0.00016399188,0.678277,0.0002600036,0.0017360195,0.0005290448,0.002262977,0.00003362948,0.006085199,0.0004272208,0.007121527,0.3026417],"study_design_scores_gemma":[0.0066521727,0.000397492,0.34174895,0.0005130751,0.0025253617,0.0003243837,0.0014418573,0.628993,0.00064081163,0.00029942335,0.01574797,0.00071550027],"about_ca_topic_score_codex":0.000080417114,"about_ca_topic_score_gemma":0.000009719728,"teacher_disagreement_score":0.62895936,"about_ca_system_score_codex":0.000059497874,"about_ca_system_score_gemma":0.00014721515,"threshold_uncertainty_score":0.6702707},"labels":[],"label_agreement":null},{"id":"W3016291997","doi":"10.1016/j.ejca.2020.02.050","title":"The European Organisation for Research and Treatment of Cancer, State of Science in radiation oncology and priorities for clinical trials meeting report","year":2020,"lang":"en","type":"article","venue":"European Journal of Cancer","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":35,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; Health Sciences Centre; Sunnybrook Health Science Centre","funders":"Novo Nordisk Fonden; Ferring; Roche; Merck; Bayer","keywords":"Radiation oncology; Medicine; Medical physics; Clinical trial; Cancer; Clinical Oncology; Oncology; State (computer science); Radiation therapy; Internal medicine; Computer science","score_opus":0.25181968435030094,"score_gpt":0.5496809856460632,"score_spread":0.2978613012957622,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3016291997","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9786579,0.0075662276,0.00062710576,0.0121157905,0.00027396425,0.0004021837,0.0000051458687,0.0000019739016,0.0003497135],"genre_scores_gemma":[0.9739723,0.02349498,0.0016181374,0.00009020734,0.00073788234,0.0000033517972,5.608275e-7,0.000015190713,0.000067373],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9975123,0.0009900846,0.0010165928,0.00012144104,0.00023618809,0.00012340993],"domain_scores_gemma":[0.9970992,0.0015273602,0.00082170434,0.000056537992,0.00038308586,0.000112104965],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.026614744,0.000048751204,0.00035365552,0.00008038699,0.00009445763,0.000019006633,0.00006891044,0.000007899727,0.0000017627788],"category_scores_gemma":[0.008966955,0.000029830691,0.00004649169,0.00009855633,0.0005179468,0.000047201647,0.000022161163,0.0001457763,3.6806885e-8],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009089025,0.000026944097,0.045085095,0.000057355162,0.000049445574,0.000035958994,0.0030367642,0.000059002832,0.010891454,0.00001534239,0.00030778506,0.93952596],"study_design_scores_gemma":[0.022180269,0.014930266,0.63717496,0.00083959225,0.00035606985,0.0001240763,0.0023277716,0.008913145,0.009090898,0.0002671839,0.3036412,0.00015459325],"about_ca_topic_score_codex":0.00003323496,"about_ca_topic_score_gemma":0.0000109487055,"teacher_disagreement_score":0.93937135,"about_ca_system_score_codex":0.00009345033,"about_ca_system_score_gemma":0.00055306806,"threshold_uncertainty_score":0.99938095},"labels":[],"label_agreement":null},{"id":"W3016685740","doi":"10.1096/fasebj.2020.34.s1.07506","title":"A study on Morphometric Features of Esophagus","year":2020,"lang":"en","type":"article","venue":"The FASEB Journal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Esophagus; Correlation; Medicine; Body weight; Anatomy; Mathematics; Internal medicine; Geometry","score_opus":0.02748039804232747,"score_gpt":0.30647939780787964,"score_spread":0.27899899976555215,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3016685740","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98545325,0.0012647394,0.00035278883,0.011301936,0.0002046963,0.00015300277,9.691365e-7,0.00001508707,0.0012535616],"genre_scores_gemma":[0.9963605,0.000030894065,0.00020854305,0.0027134481,0.00048588772,9.318954e-7,5.4463464e-7,0.00001209436,0.00018720099],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9990968,0.00008723245,0.0001891633,0.000085099324,0.00041418488,0.00012752002],"domain_scores_gemma":[0.99940705,0.00011995168,0.00011254581,0.00012338813,0.00004520844,0.0001918763],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046647416,0.00007731577,0.00021010684,0.000113090166,0.00009040912,0.000021436894,0.00015832193,0.000018803396,0.00009043503],"category_scores_gemma":[0.000832005,0.000040931896,0.00009056241,0.00038251973,0.00005025726,0.000018859839,0.000028646442,0.0008569385,0.000015677791],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0026189436,0.0026117763,0.62050366,0.00013349454,0.0015640926,0.0058063045,0.022944687,0.0016680441,0.10500907,0.0004772462,0.08134271,0.15531994],"study_design_scores_gemma":[0.007844636,0.006627366,0.9555386,0.00016862807,0.0005397487,0.0030377354,0.005346467,0.002179769,0.017660568,0.00016147223,0.0007038341,0.00019122659],"about_ca_topic_score_codex":0.000007748948,"about_ca_topic_score_gemma":7.440563e-8,"teacher_disagreement_score":0.33503485,"about_ca_system_score_codex":0.000017075594,"about_ca_system_score_gemma":0.00004735774,"threshold_uncertainty_score":0.37230188},"labels":[],"label_agreement":null},{"id":"W3017370325","doi":"10.20944/preprints202004.0354.v1","title":"Comparative Analysis of Machine Learning Algorithms for Computer-Assisted Reporting Based on Fully Automated Cross-Lingual RadLex® Mappings","year":2020,"lang":"en","type":"preprint","venue":"Preprints.org","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Bundesministerium für Wirtschaft und Energie; Bundesministerium für Bildung und Forschung","keywords":"Support vector machine; Machine learning; Random forest; Artificial intelligence; Brier score; Computer science; Confusion matrix; Cross-validation; F1 score; Algorithm; Classifier (UML); Context (archaeology); Natural language processing","score_opus":0.15691511639050304,"score_gpt":0.44062043724893335,"score_spread":0.2837053208584303,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3017370325","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94716454,0.00007370591,0.04671343,0.001566538,0.0005806046,0.0015098423,0.000130008,0.0011494579,0.0011118933],"genre_scores_gemma":[0.9611711,0.00001267054,0.034688585,0.0006794359,0.00037650493,0.0001191311,0.0026718436,0.00008712098,0.00019360591],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99336743,0.0003447625,0.0029466087,0.0018121116,0.0009340567,0.00059504726],"domain_scores_gemma":[0.99228114,0.00076476665,0.004638698,0.0011063423,0.0007611235,0.00044793647],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0029792665,0.0007078096,0.003101002,0.00093065604,0.00025758526,0.000073717165,0.0005382705,0.0004556056,0.00020818363],"category_scores_gemma":[0.005321366,0.0006885416,0.0013665624,0.0010080743,0.00029863085,0.00004917383,0.00084539625,0.0029142913,0.000020627596],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008224393,0.0005528341,0.5759474,0.0014396654,0.0052692816,0.00020640386,0.0020620713,0.40005666,0.010561435,0.000021871063,0.000079017365,0.0029809081],"study_design_scores_gemma":[0.001548013,0.00019515096,0.33115566,0.00061761617,0.0018862282,0.00001456922,0.000041574192,0.65920085,0.004152973,0.000018411316,0.00081333943,0.0003556622],"about_ca_topic_score_codex":0.00041320597,"about_ca_topic_score_gemma":0.0000047466046,"teacher_disagreement_score":0.25914416,"about_ca_system_score_codex":0.00028129388,"about_ca_system_score_gemma":0.00051841995,"threshold_uncertainty_score":0.9995566},"labels":[],"label_agreement":null},{"id":"W3018162543","doi":"10.1007/s00259-020-04821-y","title":"A case of COVID-19 lung infection first detected by [18F]FDG PET-CT","year":2020,"lang":"en","type":"article","venue":"European Journal of Nuclear Medicine and Molecular Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":19,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hospital for Sick Children","funders":"","keywords":"Coronavirus disease 2019 (COVID-19); Medicine; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); 2019-20 coronavirus outbreak; Positron Emission Tomography-Computed Tomography; Lung; PET-CT; Nuclear medicine; Positron emission tomography; Radiology; Coronavirus Infections; Pathology; Internal medicine; Infectious disease (medical specialty)","score_opus":0.01228234155926469,"score_gpt":0.27655334477738375,"score_spread":0.2642710032181191,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3018162543","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8630094,0.0031435771,0.020448864,0.11051274,0.00019587125,0.00018746128,0.0000029328598,0.000064069434,0.002435065],"genre_scores_gemma":[0.9737292,0.00046358607,0.0013899206,0.024082728,0.00025828523,1.7885073e-7,0.000004248315,0.000065970315,0.000005879566],"study_design_codex":"case_report","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983773,0.00028299305,0.00061784795,0.0002079071,0.00031435548,0.0001995792],"domain_scores_gemma":[0.9983931,0.000081032544,0.0004306797,0.00014091107,0.00013772311,0.00081652944],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009488539,0.00018013293,0.0004477951,0.00019571956,0.00012241738,0.000022723267,0.00010071749,0.0000061932355,0.00011298007],"category_scores_gemma":[0.002766932,0.00014383196,0.00012327736,0.000238168,0.0002558127,0.000090276364,0.0000712752,0.0006694575,0.0000028565858],"study_design_candidate":"case_report","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00056097424,0.0001573204,0.010874946,0.0014610548,0.0004791208,0.49024326,0.0065710586,0.00013542254,0.23177901,0.00008704369,0.22959676,0.028054032],"study_design_scores_gemma":[0.0128789125,0.0020777576,0.0012659689,0.0012831347,0.0012906939,0.3751828,0.002272598,0.046989165,0.000813133,0.000021114933,0.55550516,0.00041956297],"about_ca_topic_score_codex":0.00008245925,"about_ca_topic_score_gemma":3.5725944e-7,"teacher_disagreement_score":0.3259084,"about_ca_system_score_codex":0.000041418498,"about_ca_system_score_gemma":0.00006386089,"threshold_uncertainty_score":0.58652973},"labels":[],"label_agreement":null},{"id":"W3018177167","doi":"10.1016/j.media.2020.101667","title":"Tripartite-GAN: Synthesizing liver contrast-enhanced MRI to improve tumor detection","year":2020,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":111,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Western University","funders":"Primary Research and Development Plan of Zhejiang Province; Taishan Scholar Project of Shandong Province; China Scholarship Council; National Natural Science Foundation of China","keywords":"Computer science; Discriminator; Convolutional neural network; Context (archaeology); Generator (circuit theory); Detector; Materials science; Artificial intelligence; Power (physics)","score_opus":0.007824679294856297,"score_gpt":0.272096335132687,"score_spread":0.2642716558378307,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3018177167","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22829929,0.00019581911,0.7413446,0.028058965,0.0001491707,0.00034079433,0.0000052314417,0.00022255824,0.0013836053],"genre_scores_gemma":[0.97288346,0.000063590756,0.004463241,0.02146962,0.00081317016,0.00003993434,0.000017202723,0.000037934416,0.00021184674],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970677,0.00014049925,0.0005826138,0.0006626237,0.0010447897,0.00050178025],"domain_scores_gemma":[0.9974511,0.0002771214,0.00013358553,0.00033192744,0.00016515778,0.0016410751],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007687132,0.00024891863,0.0008752788,0.00029497402,0.000112859816,0.00007767453,0.00023973155,0.000115383875,0.0022622603],"category_scores_gemma":[0.0069976114,0.00020479078,0.00047536538,0.0016337881,0.00015695508,0.00012363636,0.00008196335,0.00079636206,0.0003389165],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006047975,0.00034241402,0.0020062109,0.0002636143,0.002968987,0.0022393137,0.0020258091,0.0003118586,0.66164017,0.000018622924,0.0033381674,0.32424003],"study_design_scores_gemma":[0.0023996597,0.0005045576,0.0035014371,0.00012885155,0.0048381975,0.000047273137,0.00038658094,0.82196283,0.15132791,0.000013087007,0.014435712,0.0004539028],"about_ca_topic_score_codex":0.0002106934,"about_ca_topic_score_gemma":0.000033640827,"teacher_disagreement_score":0.821651,"about_ca_system_score_codex":0.000079500925,"about_ca_system_score_gemma":0.00011096966,"threshold_uncertainty_score":0.99864984},"labels":[],"label_agreement":null},{"id":"W3018713651","doi":"10.1038/s41467-019-08563-w","title":"Author Correction: Why rankings of biomedical image analysis competitions should be interpreted with care","year":2019,"lang":"en","type":"erratum","venue":"Nature Communications","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Science and Engineering Faculty, Queensland University of Technology; Institut National de la Santé et de la Recherche Médicale; Engineering and Physical Sciences Research Council; Medical Research Council; Haute école Spécialisée de Suisse Occidentale; Masarykova Univerzita; Technische Universität München; Technische Universiteit Eindhoven; Radboud Universiteit; Queensland University of Technology; Massachusetts General Hospital; McGill University; University of Leeds; National Taiwan University; University of Warwick; University of Oxford; University College London; Universität zu Lübeck; Deutsches Krebsforschungszentrum; Johns Hopkins University; National Taiwan University of Science and Technology; Vanderbilt University; Technische Universität Wien; University of Bern","keywords":"Column (typography); Table (database); Computer science; Image (mathematics); Information retrieval; Artificial intelligence; Data mining; Telecommunications","score_opus":0.0152416473435611,"score_gpt":0.342140772325349,"score_spread":0.3268991249817879,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3018713651","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010374378,0.075822085,0.05195933,0.42648825,0.05181404,0.004776035,0.0024580737,0.0014176843,0.38422707],"genre_scores_gemma":[0.6537097,0.004828897,0.09200851,0.016577544,0.0020800151,0.00029201954,0.100584716,0.00044900452,0.12946957],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99734604,0.00027137628,0.0006613227,0.0005031869,0.0009105966,0.00030746634],"domain_scores_gemma":[0.9942266,0.0005342643,0.00054531026,0.0033352207,0.0011053705,0.00025324686],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.00036154495,0.00039838874,0.0012295867,0.0012101902,0.0003078101,0.00006199062,0.0013073871,0.0013411638,0.0003903889],"category_scores_gemma":[0.00095228513,0.00032308,0.00056513323,0.0023276596,0.0010871334,0.00008217697,0.0004270929,0.009497886,0.00001108966],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000070656555,0.00025191216,0.0016281388,0.00030743936,0.0025576018,0.000012664501,0.001462416,0.000011445821,0.00012192763,0.0004201473,0.992254,0.00090160954],"study_design_scores_gemma":[0.00080125284,0.00023559696,0.0026376368,0.0014361042,0.0059123198,0.00008024204,0.0010419502,0.019673213,0.000013416186,0.000009023554,0.967837,0.00032224614],"about_ca_topic_score_codex":0.0002754571,"about_ca_topic_score_gemma":0.0005394927,"teacher_disagreement_score":0.6526723,"about_ca_system_score_codex":0.00024062309,"about_ca_system_score_gemma":0.0006880971,"threshold_uncertainty_score":0.9999553},"labels":[],"label_agreement":null},{"id":"W3019779044","doi":"10.1007/s12350-020-02109-0","title":"Cardiac SPECT radiomic features repeatability and reproducibility: A multi-scanner phantom study","year":2020,"lang":"en","type":"article","venue":"Journal of Nuclear Cardiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":55,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Repeatability; Reproducibility; Imaging phantom; Radiomics; Cardiac imaging","score_opus":0.027726888769440614,"score_gpt":0.3075255445659917,"score_spread":0.27979865579655105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3019779044","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9872083,0.0016228518,0.00009181024,0.009719431,0.00066693616,0.00033321415,0.000003681949,0.00003528191,0.00031846948],"genre_scores_gemma":[0.9949144,0.00020397949,0.0019397441,0.0012620862,0.0015820268,0.0000010079593,0.0000013529682,0.000035180852,0.000060184386],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9977819,0.00052219897,0.0005580039,0.0006327596,0.00027233278,0.00023284361],"domain_scores_gemma":[0.99846584,0.00011911167,0.00025019748,0.00062730187,0.00015033253,0.00038722335],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027902622,0.00017262615,0.0011677847,0.000093509516,0.00009083242,0.000019085412,0.0001489997,0.00007993591,0.000029050248],"category_scores_gemma":[0.0046215947,0.00012759026,0.00034347925,0.00014285414,0.00026626824,0.00007576061,0.000119360164,0.0010328034,0.000005578609],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015899005,0.0002687023,0.943706,0.00012367596,0.0014539931,0.003351214,0.0048553566,0.00010215341,0.018054232,0.000018946475,0.016744716,0.009731127],"study_design_scores_gemma":[0.0034367996,0.00221024,0.96044487,0.00003100225,0.0006560172,0.0054478077,0.0016557842,0.00064589694,0.000046312914,0.000023834647,0.02524046,0.00016096952],"about_ca_topic_score_codex":0.000033046053,"about_ca_topic_score_gemma":4.3196496e-7,"teacher_disagreement_score":0.01800792,"about_ca_system_score_codex":0.00007153767,"about_ca_system_score_gemma":0.000095083116,"threshold_uncertainty_score":0.5532814},"labels":[],"label_agreement":null},{"id":"W3020867332","doi":"10.1016/j.ijrobp.2016.06.127","title":"Detection of Local Cancer Recurrence After Stereotactic Ablative Radiation Therapy (SABR) for Lung Cancer: Physician Performance Versus Radiomic Assessment","year":2016,"lang":"en","type":"article","venue":"International Journal of Radiation Oncology*Biology*Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"London Health Sciences Centre; Western University","funders":"","keywords":"Medicine; SABR volatility model; Radiology; Radiation therapy; Lung cancer; Medical imaging; Radiation treatment planning; Nuclear medicine; Internal medicine","score_opus":0.017274459103208923,"score_gpt":0.3752484401396082,"score_spread":0.35797398103639927,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3020867332","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7826924,0.0015614484,0.20791018,0.0030293039,0.004303292,0.0003552568,0.000059355312,0.000018128178,0.0000706598],"genre_scores_gemma":[0.98830426,0.007586874,0.0011417316,0.0005422894,0.0022569152,0.00009413881,0.000020128233,0.000030162853,0.00002352329],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99834913,0.00016871694,0.0006846524,0.00024238203,0.00031809037,0.00023701583],"domain_scores_gemma":[0.99698687,0.00063666643,0.0013400012,0.00012457996,0.0008009352,0.00011097546],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005520565,0.00019596361,0.0004825028,0.0001809774,0.000068560585,0.000015287182,0.00022867706,0.0001545005,0.00004754685],"category_scores_gemma":[0.00015690824,0.00014557916,0.00022353028,0.00014824898,0.00028235113,0.00040166156,0.000024514642,0.00039813816,0.0000015444821],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0027709354,0.00017902517,0.14206201,0.000023979148,0.00086240977,0.0000033557592,0.00025006427,0.00075055397,0.01813739,0.00032661617,0.00015099515,0.83448267],"study_design_scores_gemma":[0.06847872,0.00935248,0.443261,0.0015312976,0.0011597583,0.00013098854,0.00020769471,0.35252392,0.0842232,0.002024269,0.03618854,0.00091812795],"about_ca_topic_score_codex":0.000042542582,"about_ca_topic_score_gemma":0.00000476581,"teacher_disagreement_score":0.8335645,"about_ca_system_score_codex":0.0017057076,"about_ca_system_score_gemma":0.0007735045,"threshold_uncertainty_score":0.59365463},"labels":[],"label_agreement":null},{"id":"W3021673644","doi":"10.1016/j.rpor.2020.03.015","title":"Artificial intelligence in radiotherapy","year":2020,"lang":"en","type":"review","venue":"Reports of Practical Oncology & Radiotherapy","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":112,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto; University Health Network; Toronto Metropolitan University","funders":"","keywords":"Radiation therapy; Computer science; Quality assurance; Artificial intelligence; Applications of artificial intelligence; Medical physics; Artificial neural network; Field (mathematics); Medicine; Radiology; Pathology","score_opus":0.0715469436238749,"score_gpt":0.4729590458363885,"score_spread":0.40141210221251356,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3021673644","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000015596772,0.9722395,0.0150283985,0.0090037845,0.0007913676,0.0013579528,0.0000028149673,0.000080003585,0.0014805868],"genre_scores_gemma":[0.000030931053,0.9358581,0.061601557,0.001124829,0.0010421666,0.00007729484,0.000032708773,0.00014430306,0.00008812876],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9942356,0.00069446274,0.0029397637,0.0009744563,0.000595737,0.00055999384],"domain_scores_gemma":[0.99499947,0.0018564889,0.0018379521,0.0007371326,0.00009428865,0.00047467795],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0021110293,0.00059920334,0.005177233,0.00051218155,0.000046337445,0.000028387183,0.0002189272,0.0009737636,0.0007190554],"category_scores_gemma":[0.002715061,0.00047895528,0.000905967,0.00080533145,0.0005576019,0.00011760088,0.000049534498,0.0030125543,0.000013404499],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001891206,0.0008074674,0.000051710318,0.00297551,0.00061598123,0.017106459,0.0001638429,0.0000053504923,0.000052372776,0.0010670527,0.0007720582,0.9761931],"study_design_scores_gemma":[0.00020533982,0.001216022,0.000008534785,0.003303151,0.00064597814,0.016354686,0.00002128785,0.0010717845,0.000007652511,0.00033062662,0.9764872,0.00034771443],"about_ca_topic_score_codex":0.00005218101,"about_ca_topic_score_gemma":0.0000035008836,"teacher_disagreement_score":0.97584534,"about_ca_system_score_codex":0.001019628,"about_ca_system_score_gemma":0.003625778,"threshold_uncertainty_score":0.99976623},"labels":[],"label_agreement":null},{"id":"W3022777305","doi":"10.1200/cci.19.00165","title":"Quantitative Imaging Informatics for Cancer Research","year":2020,"lang":"en","type":"article","venue":"JCO Clinical Cancer Informatics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"National Institutes of Health; Leidos; University of Arkansas for Medical Sciences; National Cancer Institute; University of Arkansas","keywords":"DICOM; Standardization; Health informatics; Informatics; Computer science; Health informatics tools; Data science; Implementation; Interface (matter); Medical physics; Medicine; Software engineering; Engineering; Artificial intelligence","score_opus":0.24694347748817752,"score_gpt":0.5583108190181661,"score_spread":0.31136734152998863,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3022777305","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5259241,0.0041342266,0.23765229,0.19415858,0.0039275996,0.0056409794,0.00039277461,0.0007465629,0.027422898],"genre_scores_gemma":[0.48541,0.009788866,0.31569663,0.18042316,0.0058547985,0.00106818,0.00025074714,0.0002412596,0.001266334],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963889,0.00008640301,0.0019093528,0.00016765912,0.0008092736,0.0006384187],"domain_scores_gemma":[0.9962145,0.0015505179,0.0004413796,0.00029589527,0.0008022036,0.0006954811],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00276295,0.00021517581,0.0006904707,0.00013193281,0.00023944219,0.00011459336,0.00032812273,0.00014276689,0.00018232696],"category_scores_gemma":[0.0059374454,0.00017323707,0.00027096,0.00051588065,0.0004497913,0.0003840967,0.00017859794,0.0016332705,0.00008688487],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002102164,0.00025406678,0.11140567,0.00476859,0.0004918822,0.0000188312,0.027410181,0.002302773,0.00014351726,0.00654144,0.3518665,0.49269438],"study_design_scores_gemma":[0.002852924,0.00053440157,0.0016443569,0.00035600734,0.00013206612,0.000005927873,0.0039555626,0.58031684,0.000069131995,0.00026093866,0.40965146,0.00022036159],"about_ca_topic_score_codex":0.00008785977,"about_ca_topic_score_gemma":0.000008594436,"teacher_disagreement_score":0.5780141,"about_ca_system_score_codex":0.00013751014,"about_ca_system_score_gemma":0.0007980912,"threshold_uncertainty_score":0.71081054},"labels":[],"label_agreement":null},{"id":"W3023252280","doi":"10.1155/2020/8153295","title":"Fusion of FDG-PET Image and Clinical Features for Prediction of Lung Metastasis in Soft Tissue Sarcomas","year":2020,"lang":"en","type":"article","venue":"Computational and Mathematical Methods in Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Natural Science Foundation of China; McGill University; Natural Science Foundation of Shanghai","keywords":"Computer science; Artificial intelligence; Feature (linguistics); Positron emission tomography; Feature extraction; Metastasis; Pattern recognition (psychology); Random forest; Artificial neural network; Sensitivity (control systems); Radiology; Medicine; Cancer","score_opus":0.061080396855601446,"score_gpt":0.46927945457138803,"score_spread":0.4081990577157866,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3023252280","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07393518,0.0010809137,0.9125456,0.011640456,0.000059525795,0.0004848392,0.00001190044,0.00001339985,0.00022818442],"genre_scores_gemma":[0.11179682,0.00014461782,0.88728416,0.0006081227,0.00010606111,0.000007858177,0.00002800365,0.000012092955,0.000012247493],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984722,0.00020631234,0.00074506237,0.00023268007,0.00022771383,0.00011603501],"domain_scores_gemma":[0.99648005,0.0030527955,0.00015011553,0.0000708037,0.00008820181,0.00015801968],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023724174,0.00010984259,0.0007491167,0.00010938588,0.000021090833,0.0000032453586,0.000051898518,0.000057489968,0.00005523274],"category_scores_gemma":[0.006358088,0.00008064824,0.00004592006,0.00016089306,0.00043053934,0.00003508423,0.000055078206,0.00028560753,1.9665148e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011360479,0.0008582537,0.03217889,0.010888873,0.0002748808,0.0000852301,0.0058504734,0.00034035975,0.030357227,0.022594536,0.0031821835,0.89225304],"study_design_scores_gemma":[0.0055347434,0.0009856543,0.09842118,0.0012418501,0.00027075413,0.00012978484,0.00037459476,0.7885184,0.00025369468,0.10386214,0.00031171503,0.00009548938],"about_ca_topic_score_codex":0.000010578185,"about_ca_topic_score_gemma":4.9616244e-7,"teacher_disagreement_score":0.89215755,"about_ca_system_score_codex":0.000008498956,"about_ca_system_score_gemma":0.00003255982,"threshold_uncertainty_score":0.7611685},"labels":[],"label_agreement":null},{"id":"W3023894570","doi":"10.1016/j.jmpt.2006.12.003","title":"","year":2007,"lang":"en","type":"article","venue":"Journal of Manipulative and Physiological Therapeutics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Memorial Chiropractic College","funders":"","keywords":"Medicine; Quality (philosophy); ROWE; Inclusion (mineral); Medical physics; Radiology; Epistemology; Management","score_opus":0.2660539991437601,"score_gpt":0.40633500364705105,"score_spread":0.14028100450329095,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3023894570","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97104466,0.0011936408,0.024973243,0.0024040882,0.00012486584,0.000118662836,3.145488e-7,0.000013286807,0.00012721772],"genre_scores_gemma":[0.9842522,0.00081512996,0.0077838544,0.006524943,0.00058910676,3.1272583e-7,0.000001391649,0.000014037761,0.00001899791],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9982189,0.000113159396,0.0007687861,0.00017024098,0.00038767216,0.00034123543],"domain_scores_gemma":[0.998218,0.0005059442,0.000503055,0.00011883617,0.00031142787,0.00034273858],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017425244,0.0002008465,0.0006736304,0.00013280763,0.00012332712,0.000023093022,0.00011490003,0.00013202801,0.00001012187],"category_scores_gemma":[0.00022868367,0.000116239964,0.00022727149,0.00018584244,0.00032451353,0.00012316041,0.000050833092,0.0010025805,3.561588e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0042989687,0.00077299564,0.21958196,0.000073810384,0.00079489616,0.00076730736,0.0015590645,0.0001667195,0.6461069,0.0038009065,0.000035024044,0.122041434],"study_design_scores_gemma":[0.0028899887,0.0038329083,0.97265255,0.00012776883,0.00024469616,0.0013237209,0.00065385527,0.0020124028,0.0030147466,0.011143615,0.0019466918,0.00015704909],"about_ca_topic_score_codex":0.0000032942771,"about_ca_topic_score_gemma":3.1214617e-7,"teacher_disagreement_score":0.7530706,"about_ca_system_score_codex":0.00003966218,"about_ca_system_score_gemma":0.000030722596,"threshold_uncertainty_score":0.4740128},"labels":[],"label_agreement":null},{"id":"W3024076615","doi":"10.2196/19113","title":"Study on Measurement Information of Bladder Tumor Measurement Based on Ultrasound Imaging Measurement Technology (Preprint)","year":2020,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Preprint; Ultrasound; Medicine; Bladder tumor; Ultrasound imaging; Medical physics; Computer science; Biomedical engineering; Radiology; Bladder cancer; World Wide Web; Internal medicine; Cancer","score_opus":0.030224296968083503,"score_gpt":0.2946633328678176,"score_spread":0.2644390358997341,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3024076615","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7234609,0.00018561236,0.15007287,0.07213783,0.0012073579,0.011368358,0.000021095037,0.0014465058,0.040099435],"genre_scores_gemma":[0.9823247,0.0000063413427,0.001473577,0.01588001,0.00011742559,0.0001578071,0.000010988616,0.000027624752,0.0000015097835],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9893368,0.00011164516,0.001666756,0.00023428368,0.008172195,0.00047832177],"domain_scores_gemma":[0.9969191,0.00008916632,0.0005651228,0.00062263885,0.0011106143,0.00069334457],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.004155346,0.00037385477,0.0006865739,0.00046286546,0.000119502976,0.000053342144,0.00044022783,0.00013577293,0.00027920306],"category_scores_gemma":[0.008167014,0.000293292,0.00016544951,0.00059063215,0.00021863489,0.00022315563,0.00011303488,0.0013287765,0.0001954488],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005361119,0.01923675,0.1542719,0.009286644,0.0032727518,0.00065995654,0.07097675,0.0076825377,0.012355652,0.002331976,0.086540855,0.6280231],"study_design_scores_gemma":[0.054434538,0.016687457,0.06877487,0.010562695,0.0012250035,0.00034974547,0.07725362,0.6581223,0.02447508,0.0002380104,0.08527821,0.002598437],"about_ca_topic_score_codex":0.000009697221,"about_ca_topic_score_gemma":0.0000013382232,"teacher_disagreement_score":0.6504398,"about_ca_system_score_codex":0.00056066725,"about_ca_system_score_gemma":0.0008136551,"threshold_uncertainty_score":0.9999519},"labels":[],"label_agreement":null},{"id":"W3024083990","doi":"10.1038/s41598-020-64824-5","title":"3D-MCN: A 3D Multi-scale Capsule Network for Lung Nodule Malignancy Prediction","year":2020,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":63,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; University of Toronto; Sunnybrook Health Science Centre; Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Canada","keywords":"Malignancy; Nodule (geology); Convolutional neural network; Computer science; Lung cancer; Interpretability; Artificial intelligence; Scale (ratio); Artificial neural network; Machine learning; Medicine; Pathology; Biology; Cartography","score_opus":0.016252673432930676,"score_gpt":0.27987516342414864,"score_spread":0.26362248999121796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3024083990","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44483083,0.0022680399,0.50622666,0.011382292,0.027659379,0.003300181,0.000032749158,0.00083765754,0.0034622015],"genre_scores_gemma":[0.7328082,0.000029166371,0.2476085,0.0027110197,0.0035523411,0.00019915456,0.00075132964,0.00012423928,0.012216103],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975486,0.000033256656,0.00058840547,0.0008606415,0.0004883085,0.00048079112],"domain_scores_gemma":[0.99859524,0.00002699138,0.00025286342,0.00051038497,0.00018187509,0.00043262244],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012751595,0.00017008578,0.00033506873,0.00006774354,0.0004042529,0.00014163433,0.000095345735,0.00009306381,0.0001585434],"category_scores_gemma":[0.0007206694,0.00014870943,0.00015850311,0.00044082387,0.0001815076,0.00012049277,0.00006480944,0.0002881279,0.00001527026],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000112399306,0.0003849918,0.13611236,0.00091873045,0.00017690468,0.001414068,0.0034542237,0.008832168,0.101827554,0.000041391864,0.71767867,0.029046515],"study_design_scores_gemma":[0.0010820158,0.00011822862,0.0048481626,0.00025571973,0.00017693189,0.00044982467,0.000057535923,0.72119194,0.0014247476,0.00014112788,0.27005,0.00020378333],"about_ca_topic_score_codex":0.00002208585,"about_ca_topic_score_gemma":0.0000033447727,"teacher_disagreement_score":0.7123598,"about_ca_system_score_codex":0.000057374218,"about_ca_system_score_gemma":0.0001744009,"threshold_uncertainty_score":0.60641944},"labels":[],"label_agreement":null},{"id":"W3024460317","doi":"10.1016/j.jval.2020.04.046","title":"MS3 PREDICTING OPTIMAL TREATMENT REGIMENS FOR HR+/HER2- BREAST CANCER BASED ON ELECTRONIC HEALTH RECORDS USING RANDOM FOREST","year":2020,"lang":"en","type":"article","venue":"Value in Health","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Eli Lilly (Canada)","funders":"","keywords":"Regimen; Medicine; Cohort; Proportional hazards model; Breast cancer; Oncology; Random forest; Internal medicine; Cancer; Machine learning; Computer science","score_opus":0.03991685157468309,"score_gpt":0.35201333159086773,"score_spread":0.3120964800161846,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3024460317","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6946063,0.0025987008,0.04747404,0.25035033,0.0005806348,0.003909273,0.0001313701,0.00022424156,0.00012510185],"genre_scores_gemma":[0.9690816,0.0010055908,0.012017891,0.016388882,0.0011317456,0.0001482876,0.000075327465,0.00009781266,0.00005287612],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99728847,0.0002793386,0.00064945826,0.00052941387,0.00030758575,0.0009457659],"domain_scores_gemma":[0.9984792,0.0003611699,0.00029198625,0.00022662643,0.00004448707,0.00059656193],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011940632,0.00025526574,0.0007391843,0.0001458469,0.00022946752,0.000022332664,0.00009218541,0.00007509416,0.00003141337],"category_scores_gemma":[0.0002729619,0.00021595618,0.00014996708,0.00030031096,0.0000454335,0.000043198856,0.000014702772,0.0005492008,0.0000017991465],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004629133,0.00048257006,0.112579376,0.0014608692,0.000104337254,0.000029148843,0.001829588,0.8057403,0.00008170919,0.0002027518,0.001670314,0.07118991],"study_design_scores_gemma":[0.0110032195,0.003262615,0.0032455176,0.0011424326,0.000036112437,0.00004102331,0.00009869775,0.9749967,0.000013553298,0.000025462978,0.0059916815,0.00014298875],"about_ca_topic_score_codex":0.020719867,"about_ca_topic_score_gemma":0.00016063251,"teacher_disagreement_score":0.27447528,"about_ca_system_score_codex":0.0021631138,"about_ca_system_score_gemma":0.0031325987,"threshold_uncertainty_score":0.9858012},"labels":[],"label_agreement":null},{"id":"W3024703185","doi":"10.1007/s00259-020-04839-2","title":"PET/CT radiomics signature of human papilloma virus association in oropharyngeal squamous cell carcinoma","year":2020,"lang":"en","type":"article","venue":"European Journal of Nuclear Medicine and Molecular Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":63,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre","funders":"","keywords":"Radiomics; Human papilloma virus; Medicine; Basal cell; Human papillomavirus; Oncology; Head and neck squamous-cell carcinoma; Pathology; Papilloma; Papillomaviridae; Internal medicine; Head and neck cancer; Radiology; Cancer; Cervical cancer","score_opus":0.008886595689837512,"score_gpt":0.2442828280403073,"score_spread":0.23539623235046978,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3024703185","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9715037,0.00295555,0.00017134233,0.020743432,0.00012670462,0.00010508529,0.0000014363694,0.000015495552,0.0043772613],"genre_scores_gemma":[0.9861129,0.00014003602,0.00094849314,0.01235544,0.00035521528,1.11680464e-7,0.00000516276,0.00006999016,0.000012648913],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980145,0.00033574938,0.0007214266,0.0002053823,0.00047810242,0.00024482823],"domain_scores_gemma":[0.9987245,0.00007001179,0.00058322144,0.00012702175,0.00014392739,0.00035129327],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011496859,0.00018476084,0.00059227186,0.00023604694,0.00005469223,0.000018511004,0.00017196767,0.000010203057,0.000056293502],"category_scores_gemma":[0.0008091389,0.00015384881,0.00012674573,0.00021760381,0.00011628663,0.00009155865,0.00006817432,0.0010034768,0.0000029574294],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001766595,0.00010181508,0.017640134,0.00025794367,0.000043447035,0.03478167,0.0028412773,0.000031983538,0.9279057,0.000045005494,0.011339206,0.004835207],"study_design_scores_gemma":[0.13984463,0.022520253,0.2957722,0.0058411276,0.00522147,0.037257016,0.0226154,0.06829428,0.07115122,0.00026619312,0.3280016,0.003214647],"about_ca_topic_score_codex":0.000027268374,"about_ca_topic_score_gemma":1.4540797e-7,"teacher_disagreement_score":0.8567544,"about_ca_system_score_codex":0.000073677824,"about_ca_system_score_gemma":0.000046811965,"threshold_uncertainty_score":0.6273773},"labels":[],"label_agreement":null},{"id":"W3024830673","doi":"10.1016/j.acra.2020.03.039","title":"The Role of Imaging in Health Screening: Screening for Specific Conditions","year":2020,"lang":"en","type":"review","venue":"Academic Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Institute of Biomedical Imaging and Bioengineering; National Institutes of Health","keywords":"Medicine; Context (archaeology); Magnetic resonance imaging; Cancer screening; Lung cancer screening; Breast cancer screening; Medical physics; Radiology; Task force; Hepatocellular carcinoma; Cancer; Mammography; Breast cancer; Computed tomography; Internal medicine","score_opus":0.047937351971119646,"score_gpt":0.3996546660165365,"score_spread":0.35171731404541684,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3024830673","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000005090527,0.9841915,0.005453623,0.008324736,0.0001936325,0.0013811017,0.000033762382,0.00004734482,0.00036922406],"genre_scores_gemma":[0.00009269317,0.993321,0.004275413,0.00080070284,0.0008552521,0.00016534395,0.00031901587,0.00008466081,0.00008590272],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9966219,0.0004478896,0.0015579421,0.00053546584,0.00018784776,0.00064895116],"domain_scores_gemma":[0.99625206,0.0022006212,0.0009146669,0.00033587092,0.000042022923,0.00025474545],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0017847153,0.00034803475,0.0023104271,0.000603601,0.00019375149,0.000009990693,0.00049126684,0.00036157432,0.00001462872],"category_scores_gemma":[0.001269542,0.0002473532,0.00048195096,0.0006856702,0.00044617406,0.000038967777,0.00009783274,0.0029312044,0.000005660115],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025164694,0.000007753899,0.00037230397,0.0016399971,0.00009883303,0.000013959778,0.00009751641,0.000008737656,0.000009858266,0.0042929184,0.00895831,0.98447466],"study_design_scores_gemma":[0.0006542107,0.00008944929,0.00006762507,0.006942036,0.00016175865,0.0008319307,0.00014782445,0.0023558624,9.0417e-7,0.0006824332,0.9878941,0.0001718271],"about_ca_topic_score_codex":0.000049938648,"about_ca_topic_score_gemma":8.376155e-7,"teacher_disagreement_score":0.9843028,"about_ca_system_score_codex":0.00010868303,"about_ca_system_score_gemma":0.00040911164,"threshold_uncertainty_score":0.99999785},"labels":[],"label_agreement":null},{"id":"W3025036301","doi":"10.1002/mp.13678","title":"Machine and deep learning methods for radiomics","year":2020,"lang":"en","type":"review","venue":"Medical Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":583,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"National Cancer Institute","keywords":"Radiomics; Artificial intelligence; Computer science; Deep learning; Machine learning; Medical imaging; Standardization; Data science; Translational research; Precision medicine; Big data; Medical physics; Medicine; Data mining; Pathology","score_opus":0.0355448319793312,"score_gpt":0.4180000261170838,"score_spread":0.38245519413775264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3025036301","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.02099165e-7,0.61350733,0.38438427,0.0008283174,0.00025498882,0.0005504936,0.000004742065,0.00009694989,0.00037281486],"genre_scores_gemma":[0.0000021867259,0.9534328,0.042237174,0.0011811412,0.0022592475,0.000101637015,0.0003711193,0.00018117994,0.00023350117],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972717,0.0003216332,0.0007330046,0.00069582753,0.00050402066,0.0004738095],"domain_scores_gemma":[0.99661005,0.0016928394,0.00031636783,0.00028693912,0.000057527697,0.0010362896],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0013141251,0.00053032336,0.0030375125,0.00008467665,0.00016013179,0.000048417845,0.0002807901,0.00049172994,0.00007926852],"category_scores_gemma":[0.0056443443,0.00040922855,0.00068168924,0.00032455934,0.0003927562,0.000040585288,0.00021175355,0.0029232027,0.000020055917],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014155583,0.00005007934,0.000007508946,0.015265432,0.00032463617,0.00006507595,0.000072874405,4.0003238e-7,3.9505403e-7,0.0006150854,0.00032777272,0.9832566],"study_design_scores_gemma":[0.0009511053,0.00019602846,5.9469505e-7,0.0050684772,0.0019468841,0.00036278644,0.0000049790647,0.03131346,0.0000010819535,0.0008413038,0.95896804,0.00034528313],"about_ca_topic_score_codex":0.0000060721377,"about_ca_topic_score_gemma":1.2902005e-7,"teacher_disagreement_score":0.9829113,"about_ca_system_score_codex":0.000102453494,"about_ca_system_score_gemma":0.000457246,"threshold_uncertainty_score":0.99983597},"labels":[],"label_agreement":null},{"id":"W3025618867","doi":"10.1097/rlu.0000000000003145","title":"FDG PET/CT Findings in an Asymptomatic Case of Confirmed COVID-19","year":2020,"lang":"en","type":"article","venue":"Clinical Nuclear Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Research Institute in Oncology and Hematology; University of Manitoba; Health Sciences Centre; BC Cancer Agency","funders":"","keywords":"Medicine; Coronavirus disease 2019 (COVID-19); Asymptomatic; 2019-20 coronavirus outbreak; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Nuclear medicine; Positron Emission Tomography-Computed Tomography; Positron emission tomography; Coronavirus Infections; Betacoronavirus; Radiology; Virology; Internal medicine; Infectious disease (medical specialty); Disease; Outbreak","score_opus":0.07828845123697388,"score_gpt":0.4364279640885408,"score_spread":0.3581395128515669,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3025618867","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.906133,0.0001061819,0.00018497353,0.09151334,0.00024592303,0.00036812658,0.000003220599,0.000121859965,0.001323387],"genre_scores_gemma":[0.93637335,0.00010370594,0.0013910447,0.06151139,0.0004997845,0.0000031451598,0.00002273311,0.000053692256,0.000041151365],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99706084,0.0002985129,0.0014053677,0.0005169766,0.00038411614,0.00033418208],"domain_scores_gemma":[0.9963424,0.001189352,0.00023394033,0.00041397128,0.000071716306,0.0017485737],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0019902198,0.00021533857,0.0011549578,0.00014850798,0.00006605717,0.000009311889,0.00023419279,0.000047525056,0.0020179658],"category_scores_gemma":[0.021338997,0.00016623997,0.00015193693,0.000416406,0.00096921495,0.00007335509,0.00008666332,0.0011306888,0.00006362986],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003434186,0.0027526277,0.45732042,0.0046117725,0.00051920605,0.325153,0.013332125,0.00019750312,0.006840637,0.0052363635,0.11728082,0.06332136],"study_design_scores_gemma":[0.06748299,0.01952978,0.09513361,0.002926806,0.0014358613,0.056669284,0.0131857805,0.4891138,0.000050245548,0.0011272104,0.25203893,0.0013056817],"about_ca_topic_score_codex":0.00026154923,"about_ca_topic_score_gemma":0.000012701268,"teacher_disagreement_score":0.4889163,"about_ca_system_score_codex":0.000056488287,"about_ca_system_score_gemma":0.00019024519,"threshold_uncertainty_score":0.99889433},"labels":[],"label_agreement":null},{"id":"W3025639393","doi":"10.1002/mp.14224","title":"Comparison of robust to standardized CT radiomics models to predict overall survival for non‐small cell lung cancer patients","year":2020,"lang":"en","type":"article","venue":"Medical Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung","keywords":"Radiomics; Lung cancer; Medicine; Computed tomography; Cancer; Medical imaging; Radiology; Medical physics; Nuclear medicine; Oncology; Internal medicine","score_opus":0.0326943239640338,"score_gpt":0.3225880767256473,"score_spread":0.2898937527616135,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3025639393","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42322165,0.00006392078,0.570206,0.004466948,0.0004243134,0.0010102494,0.00011298738,0.000047389418,0.0004465316],"genre_scores_gemma":[0.9851428,0.0000341636,0.0074841822,0.0059485724,0.0010459833,0.00008196082,0.000119248885,0.00007734485,0.00006573799],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972278,0.000048020007,0.00062403595,0.00046813898,0.0011616587,0.00047035958],"domain_scores_gemma":[0.9977446,0.00022639336,0.00015740139,0.0002454012,0.00026216212,0.0013640191],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038705784,0.00025735493,0.0010073447,0.00004879376,0.00007332419,0.00001999639,0.00032451676,0.00008586587,0.00005924335],"category_scores_gemma":[0.00069549173,0.00022922907,0.00021640272,0.00027409126,0.00009270146,0.00005792963,0.00015862822,0.0005501172,0.0000040532573],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004691993,0.004229783,0.30119446,0.005218354,0.00091690745,0.000060133698,0.015100092,0.283026,0.0046539144,0.0006062335,0.26777127,0.11253083],"study_design_scores_gemma":[0.008737142,0.001017579,0.0013138803,0.0005075616,0.0003242299,6.7048046e-7,0.00006733721,0.9763712,0.0058600833,0.00014420565,0.0053173,0.00033878154],"about_ca_topic_score_codex":0.00010169265,"about_ca_topic_score_gemma":0.0000041604208,"teacher_disagreement_score":0.6933452,"about_ca_system_score_codex":0.00014045353,"about_ca_system_score_gemma":0.00043247288,"threshold_uncertainty_score":0.934769},"labels":[],"label_agreement":null},{"id":"W3026076968","doi":"10.1016/j.annonc.2020.03.205","title":"71P Role of radiomics in predicting molecular phenotypes of female breast cancer","year":2020,"lang":"en","type":"article","venue":"Annals of Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre","funders":"","keywords":"Medicine; Radiomics; Breast cancer; Kappa; Biomarker; Population; Imaging biomarker; Artificial intelligence; False positive paradox; Categorization; Breast MRI; Feature selection; Oncology; Cancer; Radiology; Mammography; Internal medicine; Magnetic resonance imaging; Computer science","score_opus":0.029265435920107632,"score_gpt":0.3594159296272463,"score_spread":0.33015049370713867,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3026076968","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98022336,0.001595323,0.00016372441,0.014788858,0.000052136893,0.000121939076,0.000017140166,0.000009203933,0.003028343],"genre_scores_gemma":[0.99650246,0.00041740897,0.0011712854,0.0017863223,0.000091339236,0.0000041546878,0.000005061737,0.000014208287,0.0000077586665],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9990389,0.00006647952,0.0004269572,0.00014791108,0.00015105965,0.00016869055],"domain_scores_gemma":[0.9992943,0.00009908621,0.00025787382,0.000110015455,0.00013187606,0.00010686219],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030607075,0.00007985696,0.00053728203,0.00008696283,0.000008184368,9.955535e-7,0.00010894154,0.000089276175,0.00007262046],"category_scores_gemma":[0.00037538973,0.00007399706,0.000084828214,0.00020305239,0.00015344008,0.000027347529,0.000048578564,0.00024421973,7.478718e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00073689426,0.00039451753,0.4552543,0.0005080141,0.00020671256,0.00006698072,0.003423005,0.0023995435,0.3226412,0.0008427857,0.0004167754,0.21310928],"study_design_scores_gemma":[0.011488314,0.006205724,0.49310103,0.0014765341,0.00046577808,0.00022218958,0.003519075,0.1552557,0.30499446,0.0014645217,0.021297727,0.0005089362],"about_ca_topic_score_codex":0.00048719102,"about_ca_topic_score_gemma":0.0000079746615,"teacher_disagreement_score":0.21260035,"about_ca_system_score_codex":0.000015777146,"about_ca_system_score_gemma":0.00022285385,"threshold_uncertainty_score":0.30175126},"labels":[],"label_agreement":null},{"id":"W3027243780","doi":"10.3389/fnins.2020.00480","title":"Editorial: Artificial Intelligence for Medical Image Analysis of Neuroimaging Data","year":2020,"lang":"en","type":"editorial","venue":"Frontiers in Neuroscience","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Fundamental Research Funds for the Central Universities; Korea Foundation for Advanced Studies; Wuyi University","keywords":"Library science; Intelligence analysis; Computer science; China; Data science; Artificial intelligence; Political science; Law; Computer security","score_opus":0.028313317362950948,"score_gpt":0.3586980649348805,"score_spread":0.33038474757192954,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3027243780","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000016354406,0.00015894021,0.24907392,0.0022245306,0.74773467,0.00035525646,0.0003273278,0.000046710556,0.000062293744],"genre_scores_gemma":[0.0004231518,0.0006255109,0.02368299,0.0005692022,0.9735797,0.000024745534,0.0009670078,0.00007801485,0.000049680293],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99357533,0.00014909408,0.0011820049,0.0016300105,0.0028812203,0.00058233505],"domain_scores_gemma":[0.9964121,0.0010932245,0.0004883704,0.0012511502,0.00027708072,0.0004780576],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0020949238,0.0003619473,0.0014924605,0.0010124298,0.00009739809,0.00011325076,0.0024529588,0.00046938748,0.000015690368],"category_scores_gemma":[0.06956165,0.00034517495,0.000287498,0.0026551865,0.00096286717,0.00024064339,0.000727566,0.0023464214,0.0000012335137],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014245701,0.000112978894,0.00052706304,0.00025912788,0.00007433398,0.00010486601,0.000071202914,0.00007551315,0.00050641655,0.000022167951,0.98337084,0.014733052],"study_design_scores_gemma":[0.00018234704,0.00011798784,0.000055305285,0.00017738246,0.00076061103,0.0000014801335,0.000026674374,0.44296083,0.000025899039,0.00014885548,0.5553627,0.00017993797],"about_ca_topic_score_codex":0.000076197684,"about_ca_topic_score_gemma":0.000006855145,"teacher_disagreement_score":0.4428853,"about_ca_system_score_codex":0.00008524506,"about_ca_system_score_gemma":0.0013631232,"threshold_uncertainty_score":0.9999552},"labels":[],"label_agreement":null},{"id":"W3029487762","doi":"10.1200/jco.2020.38.15_suppl.9600","title":"Physiologic colonic uptake of <sup>18</sup>F-FDG on PET/CT predicts immunotherapy response and gut microbiome diversity in patients with advanced non-small cell lung cancer (NSCLC).","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Centre intégré universitaire de santé et de services sociaux de la Mauricie-et-du-Centre-du-Québec; Centre Hospitalier de l’Université de Montréal","funders":"","keywords":"Medicine; Colorectal cancer; Internal medicine; Lung cancer; Gastroenterology; Oncology; Microbiome; Immune system; Cancer; Dysbiosis; Immunology; Bioinformatics; Disease","score_opus":0.03424917432139452,"score_gpt":0.36954572707612704,"score_spread":0.3352965527547325,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3029487762","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9938764,0.00042928767,0.00004208985,0.0049189925,0.00021078231,0.00038570474,0.000010278662,0.0000075974363,0.000118879616],"genre_scores_gemma":[0.99170846,0.0010109072,0.0022498327,0.0047977674,0.00016841223,0.0000027876076,0.000003446253,0.000019704672,0.00003868229],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9973648,0.00050428725,0.0013009233,0.0002792397,0.00028538215,0.00026534544],"domain_scores_gemma":[0.99663925,0.0014049745,0.0012434325,0.00014952905,0.00022798868,0.00033480625],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001750394,0.00018214661,0.001374651,0.00013031413,0.000059523627,0.0000054059856,0.00023312106,0.00008299159,0.00007571749],"category_scores_gemma":[0.0016037829,0.000124285,0.00020276199,0.0001900116,0.0002939326,0.00006894453,0.0001323003,0.0014377317,0.0000015980892],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.09517804,0.0021819388,0.85764086,0.00017180879,0.00036503933,0.0012661282,0.0008072049,0.0025021548,0.0055881804,0.0000018782015,0.0015625634,0.032734197],"study_design_scores_gemma":[0.029110659,0.02508551,0.9376596,0.00040967073,0.00017216528,0.000045769728,0.00009798993,0.003696423,0.00006422646,0.000007666851,0.0035314052,0.00011888998],"about_ca_topic_score_codex":0.000027252927,"about_ca_topic_score_gemma":0.0000029292796,"teacher_disagreement_score":0.08001876,"about_ca_system_score_codex":0.00014658115,"about_ca_system_score_gemma":0.00083825254,"threshold_uncertainty_score":0.62463087},"labels":[],"label_agreement":null},{"id":"W3029860013","doi":"10.1200/jco.2020.38.15_suppl.6545","title":"Radiomic response evaluation of recurrent or metastatic head and neck squamous cell cancer (R/M HNSCC) patients receiving pembrolizumab on KEYNOTE-012 study.","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; Princess Margaret Cancer Centre","funders":"Merck","keywords":"Medicine; Pembrolizumab; Concordance; Response Evaluation Criteria in Solid Tumors; Cancer; Target lesion; Nuclear medicine; Head and neck cancer; Radiology; Head and neck squamous-cell carcinoma; Feature (linguistics); Oncology; Internal medicine; Clinical trial; Immunotherapy; Phases of clinical research","score_opus":0.174651997589594,"score_gpt":0.5075316327907415,"score_spread":0.33287963520114755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3029860013","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98688096,0.0006522574,0.00006893517,0.01053708,0.0010616458,0.00058253505,0.0000033907902,0.00000766514,0.00020555043],"genre_scores_gemma":[0.9952507,0.00039478508,0.0014109303,0.0023554822,0.00051477243,0.000007809648,0.0000019007308,0.00002587155,0.000037757003],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9931844,0.0029275753,0.0023581788,0.0002819056,0.0010241601,0.00022377835],"domain_scores_gemma":[0.99198085,0.0045974855,0.0020254904,0.00016201784,0.00067609194,0.0005580464],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009281175,0.00017408303,0.0015222882,0.0001622759,0.00004847796,0.000010309268,0.0001579766,0.00013534902,0.0001705273],"category_scores_gemma":[0.038628507,0.00011555907,0.00024293733,0.00020248382,0.00014520025,0.000081197286,0.000057871806,0.0014128343,0.000004279649],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.13107064,0.006232047,0.23017591,0.00017971409,0.0003738541,0.000279137,0.0021815274,0.00094813836,0.0004087407,0.000002425185,0.003585148,0.62456274],"study_design_scores_gemma":[0.062222797,0.07496081,0.8339535,0.00029857783,0.0019038484,0.0000631968,0.000321681,0.020739272,0.00004809795,0.00003107634,0.0053165033,0.0001406373],"about_ca_topic_score_codex":0.000030016387,"about_ca_topic_score_gemma":0.000016582275,"teacher_disagreement_score":0.6244221,"about_ca_system_score_codex":0.00025745694,"about_ca_system_score_gemma":0.002034491,"threshold_uncertainty_score":0.96946955},"labels":[],"label_agreement":null},{"id":"W3031347985","doi":"10.3877/cma.j.issn.1674-0785.2018.03.002","title":"Effect of narrow-banding imaging on detection rate of ascending colon polyps in patients with different intestinal cleanliness","year":2018,"lang":"en","type":"article","venue":"Chin J Clinicians(Electronic Edition)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Ascending colon; Medicine; Subgroup analysis; Colonoscopy; Gastroenterology; Internal medicine; Diarrhea; Nuclear medicine; Colorectal cancer; Confidence interval","score_opus":0.003973947333400162,"score_gpt":0.2834677713236304,"score_spread":0.2794938239902302,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3031347985","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9963263,0.000043715838,0.0017663755,0.00033502062,0.00072613126,0.00044731007,0.000003817755,0.00004534515,0.00030596452],"genre_scores_gemma":[0.99888587,0.000010989086,0.000053911146,0.00021786286,0.0006963476,0.000016962718,0.00006115636,0.00004346129,0.000013444195],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9979274,0.0002791583,0.0006444882,0.00036833575,0.00032260307,0.00045801164],"domain_scores_gemma":[0.99832565,0.00076125446,0.00043540247,0.0002408639,0.00013938187,0.00009742974],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012173229,0.00024852515,0.0006058379,0.00036389008,0.00010260786,0.000011730109,0.00012407912,0.00007817026,0.000047527657],"category_scores_gemma":[0.0010542147,0.000185276,0.00011412365,0.00038843675,0.0002824059,0.0001034946,0.000026258163,0.00087771734,0.0000044020667],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00680356,0.00067206373,0.9136015,0.00042498106,0.00009118778,0.000011988487,0.00025233914,0.000072547366,0.004213623,0.00021072346,0.000081442566,0.073564045],"study_design_scores_gemma":[0.015735283,0.021485599,0.841951,0.0038774246,0.00031856733,0.000022999538,0.00007740272,0.01933172,0.09625499,0.00042212196,0.000120022785,0.00040287225],"about_ca_topic_score_codex":0.00003712274,"about_ca_topic_score_gemma":0.00003364511,"teacher_disagreement_score":0.092041366,"about_ca_system_score_codex":0.00026696824,"about_ca_system_score_gemma":0.000090666865,"threshold_uncertainty_score":0.7555336},"labels":[],"label_agreement":null},{"id":"W3031359424","doi":"10.48550/arxiv.2005.14017","title":"A Normalized Fully Convolutional Approach to Head and Neck Cancer Outcome Prediction","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Preprocessor; Computer science; Artificial intelligence; Deep learning; Feature extraction; Feature (linguistics); Modalities; Residual; Convolutional neural network; Head and neck; Pattern recognition (psychology); Medicine","score_opus":0.08422657778240779,"score_gpt":0.24854095793657574,"score_spread":0.16431438015416794,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3031359424","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89731604,0.00015179203,0.09307393,0.0026969074,0.0004704036,0.0006545873,0.000085334585,0.00019444745,0.0053565525],"genre_scores_gemma":[0.99326295,0.00021335429,0.0025563713,0.0016758282,0.00035746756,0.000005376649,0.00013017567,0.000031878295,0.0017665754],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99845946,0.00006330172,0.00024436493,0.000813822,0.00013982289,0.00027921036],"domain_scores_gemma":[0.9988844,0.00003537029,0.00011846662,0.00030460075,0.00011125009,0.0005459229],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00017632185,0.00026298885,0.00050873123,0.00018136045,0.00011435004,0.000033850458,0.00019223752,0.00022016975,0.00006563838],"category_scores_gemma":[0.00014727119,0.0002755782,0.00015016111,0.00026564617,0.00013269033,0.00006647947,0.0004845166,0.0010657576,0.000020238205],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012301628,0.00031947807,0.8695519,0.0013316838,0.0006524005,0.00037448533,0.00068597205,0.10070699,0.0005270884,0.018132424,0.005347033,0.0011403926],"study_design_scores_gemma":[0.0034017342,0.00015556067,0.18341784,0.0003240576,0.00055206724,0.000047151927,0.00009543366,0.8017033,0.000007828073,0.00090476475,0.009020173,0.00037009086],"about_ca_topic_score_codex":0.00059848296,"about_ca_topic_score_gemma":0.000009024227,"teacher_disagreement_score":0.70099634,"about_ca_system_score_codex":0.00024908132,"about_ca_system_score_gemma":0.00023753749,"threshold_uncertainty_score":0.99996966},"labels":[],"label_agreement":null},{"id":"W3031823049","doi":"10.1200/jco.2020.38.15_suppl.7019","title":"Predictive survival ability of patient-reported in comparison to physician-reported performance status in solid malignancies.","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Ontario Institute for Cancer Research; Sunnybrook Health Science Centre; Cancer Care Ontario; Health Sciences Centre; Baker Hughes (Canada)","funders":"","keywords":"Medicine; Performance status; Internal medicine; Cancer; Hazard ratio; Proportional hazards model; Oncology; Confidence interval","score_opus":0.0888066843451651,"score_gpt":0.4491425284582962,"score_spread":0.36033584411313113,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3031823049","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9907336,0.00009802516,0.0004953779,0.006485471,0.00073414424,0.00028914105,0.0000020330517,0.000008267243,0.0011539012],"genre_scores_gemma":[0.99450403,0.00011671389,0.0019321886,0.003085019,0.00033720487,0.0000031996385,0.0000032505739,0.000013847681,0.000004511452],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99393576,0.00045776437,0.004471713,0.00025686898,0.00055029534,0.00032760715],"domain_scores_gemma":[0.9952066,0.0011411186,0.002452918,0.00017577065,0.00045684463,0.00056674884],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0033845631,0.0001389832,0.0021274977,0.00014941901,0.000014825853,0.000003952938,0.00013934581,0.00020409096,0.000027402266],"category_scores_gemma":[0.017504182,0.0001096923,0.00024641235,0.000449595,0.0002185115,0.00009565221,0.000078076504,0.0017622496,0.0000026852724],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004619906,0.0016505772,0.888864,0.000070968286,0.00014899943,0.00051781983,0.0012355057,0.004147529,0.0016420181,0.000005403033,0.00044831444,0.09664899],"study_design_scores_gemma":[0.005841911,0.011025959,0.9478483,0.00026155362,0.000119346856,0.000033882363,0.0005402472,0.0292732,0.0002755713,0.000038639973,0.0046528173,0.00008857751],"about_ca_topic_score_codex":0.00009123968,"about_ca_topic_score_gemma":0.000022948823,"teacher_disagreement_score":0.09656041,"about_ca_system_score_codex":0.00019006037,"about_ca_system_score_gemma":0.0014703812,"threshold_uncertainty_score":0.9907718},"labels":[],"label_agreement":null},{"id":"W3032299426","doi":"10.1016/j.adro.2020.05.011","title":"In regard to “Radiation for glioblastoma in the era of COVID-19: Patient selection and hypofractionation to maximize benefit and minimize risk”","year":2020,"lang":"en","type":"article","venue":"Advances in Radiation Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"CancerCare Manitoba; University of Manitoba","funders":"","keywords":"Medicine; Coronavirus disease 2019 (COVID-19); Glioblastoma; Radiation oncology; Radiation therapy; 2019-20 coronavirus outbreak; Selection (genetic algorithm); Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Medical physics; Disease; Oncology; Internal medicine; Pathology; Infectious disease (medical specialty); Cancer research; Outbreak","score_opus":0.010229175217832311,"score_gpt":0.34118639861642913,"score_spread":0.33095722339859684,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3032299426","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90623176,0.000701441,0.0146351,0.0771036,0.00015682772,0.0010679896,0.000008325633,0.0000109517305,0.00008397762],"genre_scores_gemma":[0.97477573,0.0012886957,0.010729261,0.012874397,0.00010921776,0.00019604557,0.000013585471,0.000009039934,0.000004022223],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99900466,0.00013536034,0.0003578031,0.00024198797,0.00013111475,0.00012909331],"domain_scores_gemma":[0.9987287,0.00087527325,0.0001722982,0.000054697943,0.000039595558,0.0001294484],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000511908,0.00008097339,0.0002343787,0.00023428541,0.000041223688,0.000007762556,0.000040964034,0.000071880524,0.0000094145635],"category_scores_gemma":[0.004457171,0.000072247065,0.000017233067,0.0004569021,0.000026492808,0.00016819988,0.0000139883,0.0002503813,7.401162e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021308004,0.00013431799,0.11108258,0.00010644785,0.000009027232,0.0000079714,0.01081571,0.09182584,0.00053768064,0.00085656217,0.0005852792,0.7819078],"study_design_scores_gemma":[0.01047272,0.0048571955,0.31560972,0.0000732008,0.000049184207,0.00006289545,0.002058652,0.24491096,0.00044104396,0.0036641094,0.41756502,0.00023531776],"about_ca_topic_score_codex":0.00016512227,"about_ca_topic_score_gemma":0.000527033,"teacher_disagreement_score":0.7816725,"about_ca_system_score_codex":0.00027951962,"about_ca_system_score_gemma":0.0000981031,"threshold_uncertainty_score":0.53359723},"labels":[],"label_agreement":null},{"id":"W3032403368","doi":"10.1200/jco.2020.38.15_suppl.tps1597","title":"ECOG-ACRIN tomosynthesis mammographic imaging screening trial (EA1151).","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Health Sciences Centre; Sunnybrook Health Science Centre","funders":"National Institutes of Health","keywords":"Medicine; Breast cancer; Mammography; Population; Oncology; Internal medicine; Randomized controlled trial; Breast cancer screening; Clinical endpoint; Randomization; Biopsy; Cancer; Atypia; Gynecology; Pathology","score_opus":0.12401787704730786,"score_gpt":0.4636063458305183,"score_spread":0.3395884687832104,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3032403368","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.78891987,0.0008387999,0.02191075,0.17944254,0.0025774804,0.0003082774,0.0000016174223,0.000055850687,0.0059448145],"genre_scores_gemma":[0.94161016,0.000487906,0.031173592,0.020835705,0.005792459,0.0000021749754,0.0000016801125,0.000037107086,0.00005924068],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9955255,0.00063543126,0.002689282,0.00027162043,0.0005386347,0.00033956132],"domain_scores_gemma":[0.99418217,0.002677944,0.0016222054,0.00017363379,0.00025983813,0.0010841799],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.005400339,0.00017523655,0.0017696988,0.00016413917,0.00006910349,0.000027181448,0.00029520635,0.00022645123,0.0003782649],"category_scores_gemma":[0.021669395,0.00013003468,0.0009886296,0.0002602024,0.00028839582,0.00013926109,0.000090575144,0.0024643417,0.000024219145],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.038170602,0.0005682568,0.08683164,0.000039424845,0.0003928761,0.0024144857,0.00011729066,0.000034013843,0.0003144276,0.00008419757,0.008719172,0.8623136],"study_design_scores_gemma":[0.15861893,0.017532088,0.07042734,0.00038020866,0.0015492559,0.0017435469,0.0003961856,0.025241997,0.00009106609,0.00042371443,0.7232,0.00039566247],"about_ca_topic_score_codex":0.000013478554,"about_ca_topic_score_gemma":0.0000014419741,"teacher_disagreement_score":0.861918,"about_ca_system_score_codex":0.00003941027,"about_ca_system_score_gemma":0.0007452677,"threshold_uncertainty_score":0.99983704},"labels":[],"label_agreement":null},{"id":"W3032882035","doi":"10.1200/jco.2020.38.15_suppl.2044","title":"Improved prognostication for lung cancer patients from computed tomography imaging using deep learning.","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto","funders":"","keywords":"Medicine; Concordance; Lung cancer; Stage (stratigraphy); Rank correlation; Cancer staging; TNM staging system; Radiology; Cancer; Computed tomography; Correlation; Survival analysis; Internal medicine; Oncology; Neoplasm staging; Machine learning","score_opus":0.04989980656603694,"score_gpt":0.44028108604561444,"score_spread":0.3903812794795775,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3032882035","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.82131004,0.0011623864,0.15844688,0.01703684,0.0014944834,0.00043776527,0.0000045064544,0.00002821159,0.0000788667],"genre_scores_gemma":[0.92314696,0.000117818585,0.06688103,0.007138249,0.0026565061,0.0000051566158,0.000020802278,0.00002830792,0.0000051882885],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997481,0.00023999118,0.0015825082,0.00022699025,0.00024709527,0.00022243649],"domain_scores_gemma":[0.9952348,0.001850848,0.0016357638,0.00007191045,0.00070202316,0.00050466036],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0010817244,0.00012591065,0.0009595273,0.00008569599,0.00007369052,0.000019475197,0.00014871516,0.00015598824,0.00004156129],"category_scores_gemma":[0.010028348,0.00009834479,0.00042082838,0.00016373479,0.00012878081,0.00010153675,0.000047021407,0.0012495462,5.5836097e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012161057,0.00040913845,0.6961747,0.000051938798,0.00030592628,0.000026970058,0.0001727833,0.0004396374,0.00096983986,0.0000066935368,0.00081431674,0.29941198],"study_design_scores_gemma":[0.007647896,0.0020898606,0.17504513,0.00013476651,0.00071701704,0.000010101941,0.000037244245,0.80124366,0.000038039547,0.000034082397,0.012909417,0.00009280361],"about_ca_topic_score_codex":0.00004104878,"about_ca_topic_score_gemma":0.0000016385263,"teacher_disagreement_score":0.800804,"about_ca_system_score_codex":0.00007619508,"about_ca_system_score_gemma":0.0005061198,"threshold_uncertainty_score":0.9983106},"labels":[],"label_agreement":null},{"id":"W3033172521","doi":"10.18383/j.tom.2019.00030","title":"Stanford DRO Toolkit: Digital Reference Objects for Standardization of Radiomic Features","year":2020,"lang":"en","type":"article","venue":"Tomography","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"National Cancer Institute","keywords":"Computer science; DICOM; Software; Parameterized complexity; Margin (machine learning); Standardization; Object (grammar); Feature (linguistics); Sample (material); Implementation; Glyph (data visualization); Data mining; Artificial intelligence; Computer vision; Software engineering; Visualization; Programming language; Machine learning; Algorithm","score_opus":0.015253830131718013,"score_gpt":0.2785525934290258,"score_spread":0.2632987632973078,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3033172521","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7476829,0.0016609941,0.21898381,0.0058408105,0.00031758065,0.0014163738,0.00040315554,0.00035970073,0.023334641],"genre_scores_gemma":[0.99383456,0.000047645382,0.004974734,0.0007192561,0.00014266602,0.000009957865,0.00014653936,0.000022622751,0.00010202623],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99911124,0.00001142097,0.00022914377,0.00020601753,0.00026289007,0.00017929201],"domain_scores_gemma":[0.99938786,0.000076651195,0.000099841156,0.00014269487,0.00011549026,0.00017746446],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001152052,0.00011640468,0.00029924023,0.00012279137,0.00005486657,0.000026612128,0.000094893294,0.0000600962,0.000037638496],"category_scores_gemma":[0.00041796637,0.000098502605,0.0001568096,0.0003553636,0.00011703995,0.00010289681,0.000021910982,0.00019180377,0.0000014539362],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00908637,0.00083919923,0.29739085,0.0059521873,0.002166112,0.00022320743,0.016787875,0.0012522012,0.09810147,0.018739047,0.19154537,0.35791612],"study_design_scores_gemma":[0.039744537,0.01349194,0.2818603,0.0019746288,0.0019522263,0.00045847916,0.003515734,0.047989722,0.0671456,0.0074172346,0.5315543,0.0028953168],"about_ca_topic_score_codex":0.0000057333855,"about_ca_topic_score_gemma":4.6189965e-7,"teacher_disagreement_score":0.35502082,"about_ca_system_score_codex":0.000013684113,"about_ca_system_score_gemma":0.00008022138,"threshold_uncertainty_score":0.40168196},"labels":[],"label_agreement":null},{"id":"W3033672396","doi":"10.18383/j.tom.2020.00004","title":"Multisite Technical and Clinical Performance Evaluation of Quantitative Imaging Biomarkers from 3D FDG PET Segmentations of Head and Neck Cancer Images","year":2020,"lang":"en","type":"article","venue":"Tomography","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"National Center for Advancing Translational Sciences; National Institute of Biomedical Imaging and Bioengineering; National Cancer Institute; Holden Comprehensive Cancer Center, University of Iowa; National Institutes of Health","keywords":"Segmentation; Robustness (evolution); Positron emission tomography; Artificial intelligence; Computer science; Medicine; Medical physics; Pattern recognition (psychology); Radiology","score_opus":0.0361437175790271,"score_gpt":0.39472977103358503,"score_spread":0.3585860534545579,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3033672396","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9933508,0.002839677,0.0009833606,0.002230252,0.000051271705,0.00027697883,0.000044742133,0.000023735403,0.00019918766],"genre_scores_gemma":[0.9595224,0.0010262883,0.03903659,0.0003216558,0.00003932679,0.000010785113,0.000030258117,0.0000114012655,0.0000012890432],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9988606,0.00010196992,0.00038306945,0.00024170203,0.00030713313,0.000105509476],"domain_scores_gemma":[0.9992268,0.00021350932,0.00016931305,0.00010094948,0.00015575264,0.00013368196],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005561271,0.00009700697,0.0002997067,0.00011526983,0.000042989974,0.0000092086975,0.000045743775,0.000027101592,0.000045920126],"category_scores_gemma":[0.0003477231,0.000084681946,0.00007355422,0.00026708958,0.00044778266,0.000094647505,0.000040013023,0.00020375337,4.1710888e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015246117,0.00005621262,0.89809567,0.000073584575,0.00014886419,0.0000030957235,0.00033068622,0.000018519948,0.013265617,0.000008066498,0.00020700521,0.08764022],"study_design_scores_gemma":[0.0022613124,0.00020344651,0.8389128,0.00025325827,0.00041723307,0.0000059278755,0.00020965726,0.15698086,0.00061571685,0.00002112022,0.000047536763,0.00007113151],"about_ca_topic_score_codex":0.00046002175,"about_ca_topic_score_gemma":0.00001389457,"teacher_disagreement_score":0.15696234,"about_ca_system_score_codex":0.000009172571,"about_ca_system_score_gemma":0.00003972172,"threshold_uncertainty_score":0.34532297},"labels":[],"label_agreement":null},{"id":"W3033844338","doi":"10.18383/j.tom.2019.00031","title":"Standardization in Quantitative Imaging: A Multicenter Comparison of Radiomic Features from Different Software Packages on Digital Reference Objects and Patient Data Sets","year":2020,"lang":"en","type":"article","venue":"Tomography","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":75,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"David Geffen School of Medicine, University of California, Los Angeles; Massachusetts General Hospital; National Institute of Neurological Disorders and Stroke; Natural Sciences and Engineering Research Council of Canada; School of Medicine, Stanford University; National Cancer Institute; National Institutes of Health; Moffitt Cancer Center; University of South Florida; University of Washington; University of Pennsylvania; University of California, San Francisco","keywords":"Feature (linguistics); Standardization; Software; Artificial intelligence; Computer science; Data set; Pattern recognition (psychology); Object (grammar); Nuclear medicine; Computer vision; Data mining; Medicine","score_opus":0.03209305775068186,"score_gpt":0.3287904808228918,"score_spread":0.2966974230722099,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3033844338","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.992773,0.0013506623,0.0038371156,0.0011117529,0.00005663643,0.0002702166,0.00042953042,0.00004532915,0.00012573905],"genre_scores_gemma":[0.9958737,0.000060426733,0.0028876958,0.0004570385,0.000017495327,0.0000034242555,0.000681635,0.00001754702,0.0000010223156],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9988456,0.000055875193,0.00027739178,0.00037195458,0.00030009108,0.00014909748],"domain_scores_gemma":[0.99921983,0.0002085213,0.00013199037,0.0002533259,0.000041607786,0.00014469055],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000049619888,0.00015561818,0.0003922402,0.00015108968,0.00003567351,0.000035747235,0.00012033154,0.000037380472,0.000014162897],"category_scores_gemma":[0.00048232757,0.00012110556,0.000041292813,0.00017312738,0.00014300024,0.000121955316,0.00010999943,0.00033553262,9.584667e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00067110406,0.0002539212,0.9578864,0.00010106356,0.00008792107,0.0000393027,0.007102596,0.000056024583,0.0013461553,0.000020646321,0.0018005284,0.03063431],"study_design_scores_gemma":[0.0034194589,0.00075514545,0.9480948,0.00072304363,0.000103210565,0.000004625584,0.0021400515,0.042231735,0.0015184768,0.00010305264,0.0006641854,0.00024225048],"about_ca_topic_score_codex":0.00007287643,"about_ca_topic_score_gemma":0.000010043427,"teacher_disagreement_score":0.04217571,"about_ca_system_score_codex":0.000015526597,"about_ca_system_score_gemma":0.000019373778,"threshold_uncertainty_score":0.4938541},"labels":[],"label_agreement":null},{"id":"W3033949602","doi":"10.1016/j.ymeth.2020.05.023","title":"2-[18F]FDG PET/CT radiomics in lung cancer: An overview of the technical aspect and its emerging role in management of the disease","year":2020,"lang":"en","type":"review","venue":"Methods","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":43,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; SickKids Foundation; Hospital for Sick Children","funders":"Medizinische Fakultät, RWTH Aachen University","keywords":"Radiomics; Lung cancer; Medicine; Disease; Positron emission tomography; Lung disease; Cancer; Medical physics; Radiology; Lung; Pathology; Internal medicine","score_opus":0.05955049064367402,"score_gpt":0.47562584572725997,"score_spread":0.41607535508358595,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3033949602","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005718248,0.9963951,0.00021026118,0.0010806907,0.00020793655,0.0012108171,0.000013734443,0.000013596705,0.00029604963],"genre_scores_gemma":[0.0005130513,0.9869146,0.012170226,0.00012975287,0.00006105696,0.00008720143,0.0000055490195,0.000049278977,0.000069285954],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99686193,0.0013687682,0.00079018006,0.0004164285,0.0003268705,0.00023579151],"domain_scores_gemma":[0.9986215,0.00024441825,0.0003960947,0.00057108526,0.000019563658,0.00014733349],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00222333,0.00028079952,0.0015553212,0.00014560584,0.000037903945,0.000010018037,0.0005036819,0.000029048648,0.000028116172],"category_scores_gemma":[0.0005195831,0.00016073495,0.00036182924,0.00089347496,0.0001124065,0.000032864766,0.00043558786,0.0010642526,1.6195148e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014797037,0.0000713716,0.0014373421,0.03833179,0.000121873185,0.00021266645,0.000053686857,0.000041957916,0.000013271024,0.0010988622,0.000031322033,0.9585711],"study_design_scores_gemma":[0.0015158929,0.00005328022,0.014089753,0.11308463,0.0046829046,0.00037665086,0.00009360152,0.041457728,0.00002105907,0.00047936107,0.8236392,0.0005059255],"about_ca_topic_score_codex":0.000120095494,"about_ca_topic_score_gemma":0.000011305972,"teacher_disagreement_score":0.95806515,"about_ca_system_score_codex":0.00019799662,"about_ca_system_score_gemma":0.00023259934,"threshold_uncertainty_score":0.65545815},"labels":[],"label_agreement":null},{"id":"W3034203354","doi":"10.1016/j.ymeth.2020.06.008","title":"Artificial intelligence and radiomics in pediatric molecular imaging","year":2020,"lang":"en","type":"review","venue":"Methods","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":21,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hospital for Sick Children","funders":"","keywords":"Computer science; Radiomics; Artificial intelligence; Medical imaging; Dictation; Artificial neural network; Machine learning; Deep learning; Pattern recognition (psychology)","score_opus":0.0664160961612034,"score_gpt":0.45303180008569294,"score_spread":0.3866157039244895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3034203354","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000045541065,0.7678542,0.2304829,0.00065906416,0.00023918574,0.00035075744,0.000001391056,0.000040109215,0.0003678343],"genre_scores_gemma":[0.000004589747,0.7497173,0.24946827,0.0003194577,0.00038338816,0.000020032192,0.000013910664,0.00006118273,0.000011886184],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974687,0.00069338817,0.000765372,0.0005675034,0.00018728041,0.00031776863],"domain_scores_gemma":[0.99867696,0.0005652803,0.00020027423,0.00027064732,0.000021555605,0.00026526177],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0018721491,0.00034669237,0.0017559084,0.00043788744,0.000034248915,0.00005055844,0.00017869944,0.00016592923,0.00002247677],"category_scores_gemma":[0.0021352915,0.0002947841,0.0002576162,0.0007333059,0.00009321393,0.000032534925,0.00014659048,0.0015062635,0.000013953784],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004369919,0.00002025798,0.00007288977,0.005977028,0.000025390373,0.0005778491,0.00006358224,0.0000024143803,0.0000044076987,0.00047323748,0.0000333231,0.9927452],"study_design_scores_gemma":[0.00007169412,0.0000329323,0.00001137962,0.002257052,0.0011283427,0.0005445928,0.000015496335,0.0120510645,0.000008803916,0.0014308207,0.9821143,0.00033350545],"about_ca_topic_score_codex":0.000013141873,"about_ca_topic_score_gemma":1.9144467e-7,"teacher_disagreement_score":0.99241173,"about_ca_system_score_codex":0.000100070705,"about_ca_system_score_gemma":0.0002627474,"threshold_uncertainty_score":0.9999504},"labels":[],"label_agreement":null},{"id":"W3034497617","doi":"10.1158/1557-3265.aacrahns19-a35","title":"Abstract A35: Diagnostic performance and timing of post-treatment 18F-FDG PET/CT for head and neck cancer surveillance: A meta-analysis of reported studies","year":2020,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Medicine; Head and neck cancer; Head and neck; Nuclear medicine; Meta-analysis; Cancer; Internal medicine; Confidence interval; Oncology; Surgery","score_opus":0.46416252462490215,"score_gpt":0.5781511218199314,"score_spread":0.1139885971950293,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3034497617","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95923305,0.026207749,0.000008315875,0.013710763,0.00005774783,0.0006201296,0.0000956415,0.000012571064,0.000054057007],"genre_scores_gemma":[0.96402854,0.034671385,0.00042048388,0.00038709014,0.00013259576,0.0001974954,0.000021659165,0.00002162337,0.000119122924],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99746776,0.00016258628,0.0009758992,0.00053365825,0.00052836095,0.00033172162],"domain_scores_gemma":[0.9926109,0.0056836926,0.000306438,0.00028063657,0.00079957064,0.00031881902],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0025653935,0.00016717608,0.0018163493,0.00016499554,0.000107784486,0.00001556352,0.0000977811,0.00002222925,0.00017263301],"category_scores_gemma":[0.010725668,0.00011253602,0.00044648856,0.00054219225,0.00067960104,0.000047822392,0.00010863777,0.00046427842,5.244013e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001366869,0.00030053186,0.8716874,0.0020451313,0.08337262,0.0002885161,0.00075159076,0.0005729383,0.00049426575,0.000010673644,0.001149105,0.037960358],"study_design_scores_gemma":[0.0039530685,0.003111511,0.90765536,0.0002622299,0.041485608,0.000032378408,0.0005738795,0.0381606,0.00038643245,0.000021572732,0.004120469,0.00023689265],"about_ca_topic_score_codex":0.0021949355,"about_ca_topic_score_gemma":0.000347872,"teacher_disagreement_score":0.04188701,"about_ca_system_score_codex":0.000067904395,"about_ca_system_score_gemma":0.00034273264,"threshold_uncertainty_score":0.9976074},"labels":[],"label_agreement":null},{"id":"W3034614593","doi":"10.1016/j.nic.2020.04.005","title":"Patient-Centric Head and Neck Cancer Radiation Therapy","year":2020,"lang":"en","type":"review","venue":"Neuroimaging Clinics of North America","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre","funders":"GE Healthcare","keywords":"Radiogenomics; Medicine; Radiation therapy; Head and neck cancer; Radioresistance; Radiomics; Head and neck; Personalized medicine; Precision medicine; Modalities; Cancer; Medical physics; Radiology; Bioinformatics; Pathology; Internal medicine; Surgery; Biology","score_opus":0.03501507224030336,"score_gpt":0.3717797346304144,"score_spread":0.33676466239011105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3034614593","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028030064,0.9943692,0.000057001813,0.0012417537,0.00051884097,0.0007457948,0.000049295406,0.00007965181,0.00013545218],"genre_scores_gemma":[0.00028734194,0.99486816,0.00076932873,0.003382558,0.0003713069,0.000031270745,0.00015511762,0.00011206901,0.00002284382],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973797,0.00018231502,0.0010351563,0.00066408166,0.00040245702,0.00033624808],"domain_scores_gemma":[0.9976559,0.00044466587,0.0010592402,0.0003951111,0.00009097472,0.00035407994],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00009986451,0.00042545112,0.0021337073,0.00023627385,0.00007166463,0.000031817064,0.00017971241,0.000090405854,0.000030335488],"category_scores_gemma":[0.0007585181,0.00035143257,0.00043304768,0.00069012295,0.00022145291,0.00006222945,0.000102562306,0.0012948816,0.000013536038],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002847525,0.00008926307,0.015178478,0.0026675318,0.0001354655,0.00007720462,0.00007742127,0.000005626824,1.5301451e-7,8.319928e-7,0.0008954343,0.98084414],"study_design_scores_gemma":[0.0007897812,0.00043315862,0.0031192051,0.0024802054,0.0005661386,0.00005760411,0.0000025689642,0.0017063626,8.348063e-8,0.0000023033203,0.99059707,0.00024551945],"about_ca_topic_score_codex":0.00008202278,"about_ca_topic_score_gemma":6.8316274e-7,"teacher_disagreement_score":0.9897016,"about_ca_system_score_codex":0.00004957109,"about_ca_system_score_gemma":0.00051132636,"threshold_uncertainty_score":0.9998938},"labels":[],"label_agreement":null},{"id":"W3035665735","doi":"10.1007/s10462-020-09854-1","title":"Deep semantic segmentation of natural and medical images: a review","year":2020,"lang":"en","type":"review","venue":"PolyPublie (École Polytechnique de Montréal)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":849,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal; Université de Montréal; Simon Fraser University","funders":"","keywords":"Computer science; Artificial intelligence; Segmentation; Image segmentation; Categorization; Context (archaeology); Task (project management); Image (mathematics); Segmentation-based object categorization; Deep learning; Pattern recognition (psychology); Scale-space segmentation; Computer vision; Geography","score_opus":0.011373909986624664,"score_gpt":0.30680030991558843,"score_spread":0.29542639992896375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3035665735","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000006649717,0.9520087,0.03895105,0.0067609237,0.00011742875,0.0017831749,0.00001543885,0.00021333112,0.00014326234],"genre_scores_gemma":[0.00008860459,0.9707069,0.022991225,0.0051803878,0.00023309524,0.00028958137,0.00025014929,0.00011711196,0.00014297555],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99650085,0.0003179964,0.0012429758,0.00060056435,0.00086801685,0.00046960928],"domain_scores_gemma":[0.9976418,0.00031539006,0.00068518583,0.00055778964,0.00010435867,0.0006954491],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011049618,0.000555778,0.0028440128,0.00036297613,0.00008185377,0.00004374073,0.00036810842,0.00042307106,0.00013395777],"category_scores_gemma":[0.002641668,0.0004354071,0.00058027887,0.00063601526,0.00023317263,0.000101137506,0.00026328934,0.0018626523,0.000010962277],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012802938,0.000068828806,0.00011277396,0.0640107,0.00021801032,0.0003931567,0.00003382871,5.6153124e-7,0.0000135547525,0.00024371875,0.0027350874,0.932157],"study_design_scores_gemma":[0.0010280589,0.00028600826,0.00014104946,0.16295753,0.004247904,0.006048081,0.000026775293,0.03665087,0.000024200528,0.000096654374,0.78774613,0.00074671645],"about_ca_topic_score_codex":0.0006695197,"about_ca_topic_score_gemma":0.000035321336,"teacher_disagreement_score":0.93141025,"about_ca_system_score_codex":0.00026388638,"about_ca_system_score_gemma":0.00078564393,"threshold_uncertainty_score":0.99980974},"labels":[],"label_agreement":null},{"id":"W3035761137","doi":"10.1016/j.ijrobp.2020.06.004","title":"Recent Developments in the Prediction of Clinical Outcomes Data in Radiation Oncology","year":2020,"lang":"en","type":"letter","venue":"International Journal of Radiation Oncology*Biology*Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto; University Health Network","funders":"","keywords":"Radiation oncology; Precision oncology; Medical physics; Medicine; Oncology; Clinical Oncology; Clinical Practice; Radiation therapy; Internal medicine; Data science; Computer science; Family medicine; Cancer","score_opus":0.07685070036712044,"score_gpt":0.4286660720433939,"score_spread":0.35181537167627347,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3035761137","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.038497694,0.0007764302,0.0034179382,0.9452628,0.009916765,0.00071696466,0.00026306635,0.000028425246,0.0011199104],"genre_scores_gemma":[0.22505683,0.022688976,0.009832377,0.71051174,0.024363525,0.00003836054,0.0073271426,0.000114490096,0.00006657959],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9940777,0.0014942698,0.0029030235,0.00046765181,0.0007559728,0.00030142558],"domain_scores_gemma":[0.99338496,0.0024811865,0.003143398,0.00039092163,0.00049868406,0.00010086576],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0033906961,0.00029272263,0.0013988585,0.00042334027,0.000038142512,0.000023518904,0.0013990783,0.00092817005,0.000044152577],"category_scores_gemma":[0.0058547086,0.00022233142,0.00026661626,0.0003407643,0.00034798685,0.0002507653,0.00020110692,0.0049702995,0.000013420479],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021991736,0.0003813733,0.5131483,0.000021926271,0.0004983722,0.00042711754,0.00044406287,0.00007394251,0.000020427417,0.00017023945,0.12186545,0.36272886],"study_design_scores_gemma":[0.006454974,0.0007443068,0.165453,0.00013319774,0.0001816212,0.00019793274,0.00006232577,0.0048019867,0.00000757394,0.0012462354,0.820584,0.00013285624],"about_ca_topic_score_codex":0.00004063293,"about_ca_topic_score_gemma":0.000007722711,"teacher_disagreement_score":0.69871855,"about_ca_system_score_codex":0.0009660449,"about_ca_system_score_gemma":0.0023917712,"threshold_uncertainty_score":0.9973253},"labels":[],"label_agreement":null},{"id":"W3036537095","doi":"10.1007/978-3-030-50516-5_18","title":"Enhancing the Prediction of Lung Cancer Survival Rates Using 2D Features from 3D Scans","year":2020,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Lung cancer; Artificial intelligence; Oncology; Medicine","score_opus":0.01874421086188993,"score_gpt":0.29953462889484733,"score_spread":0.2807904180329574,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3036537095","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008101733,0.002560824,0.9831793,0.0025662158,0.0024483884,0.00037554296,0.000035109537,0.00005213877,0.0006807913],"genre_scores_gemma":[0.8920847,0.00037384755,0.09859878,0.0040473416,0.004542287,0.000007723446,0.000047514302,0.0000951951,0.00020260594],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99783015,0.000038419133,0.0004134687,0.0006508361,0.0007741508,0.00029299507],"domain_scores_gemma":[0.99855834,0.0005069633,0.00025835572,0.00039800932,0.00014741592,0.00013088745],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048592547,0.0002924707,0.0005512303,0.00019750674,0.00017959924,0.000083098,0.00047834724,0.00018302801,0.000057921567],"category_scores_gemma":[0.0003088659,0.00020005307,0.000110274224,0.00026895112,0.00068361283,0.00008692828,0.00024385689,0.0013160512,9.1448567e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021552727,0.00007584069,0.029650921,0.00089789875,0.0005087043,0.00025467598,0.008725897,0.25037083,0.1105912,0.0009255566,0.00029204675,0.5974909],"study_design_scores_gemma":[0.00045934707,0.00008065692,0.0038940578,0.0024691315,0.00019221882,0.00003433459,0.0000017907824,0.9836674,0.006512141,0.0020177593,0.00043423704,0.00023692855],"about_ca_topic_score_codex":0.0008517137,"about_ca_topic_score_gemma":0.00013151752,"teacher_disagreement_score":0.8845805,"about_ca_system_score_codex":0.0002160701,"about_ca_system_score_gemma":0.0006199665,"threshold_uncertainty_score":0.8157927},"labels":[],"label_agreement":null},{"id":"W3037080441","doi":"10.2196/21025","title":"Analysis and Research of Subclinical Diabetic Peripheral Vascular Lesions Based on Mutual Information-based Medical Image Registration Algorithm and Colour Ultrasound Imaging (Preprint)","year":2020,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Preprint; Subclinical infection; Image registration; Medicine; Ultrasound; Computer science; Ultrasound imaging; Medical imaging; Artificial intelligence; Computer vision; Radiology; Image (mathematics); Pathology; World Wide Web","score_opus":0.018598382511505925,"score_gpt":0.3552703716223436,"score_spread":0.3366719891108377,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3037080441","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.62293315,0.00006158096,0.34444603,0.030059949,0.000078249235,0.00088948006,0.000025463498,0.00012395106,0.0013821743],"genre_scores_gemma":[0.9621713,0.00011382344,0.027491208,0.0097865155,0.00014358229,0.00004461613,0.00022373072,0.00001798766,0.0000072289617],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9946525,0.00027340066,0.0013483333,0.00023074173,0.0030793683,0.0004156314],"domain_scores_gemma":[0.9955433,0.0020219572,0.00027307688,0.00036969455,0.00034969,0.001442307],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0038115496,0.00022223627,0.00068504835,0.00041579772,0.0001888163,0.00012090242,0.0002609849,0.00027962567,0.00057674473],"category_scores_gemma":[0.013493036,0.00018065616,0.00019541613,0.0009088529,0.0012795806,0.0003064978,0.00012575062,0.0017529163,0.000015566906],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009102279,0.0014555473,0.303502,0.0047940863,0.0012582118,0.00034116674,0.017834924,0.0014982832,0.0002441761,0.0010038781,0.010149848,0.6570077],"study_design_scores_gemma":[0.0031122076,0.00041083663,0.029236114,0.00031612624,0.00020366655,0.000024405264,0.0012262673,0.9635218,0.00006069739,0.000031350057,0.0016933925,0.00016317547],"about_ca_topic_score_codex":0.00005033538,"about_ca_topic_score_gemma":0.0000028292277,"teacher_disagreement_score":0.9620235,"about_ca_system_score_codex":0.00006521963,"about_ca_system_score_gemma":0.0010098969,"threshold_uncertainty_score":0.9948167},"labels":[],"label_agreement":null},{"id":"W3038062368","doi":"10.1038/s41598-020-66110-w","title":"Performance comparison of modified ComBat for harmonization of radiomic features for multicenter studies","year":2020,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":193,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre","funders":"Horizon 2020 Framework Programme; Agence Nationale de la Recherche","keywords":"Robustness (evolution); Computer science; Harmonization; Data mining; Artificial intelligence; Pooling; Context (archaeology); Radiomics; Medical physics; Machine learning; Medicine","score_opus":0.05472248690862956,"score_gpt":0.36104427993952287,"score_spread":0.3063217930308933,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3038062368","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9841421,0.0008131754,0.011103754,0.0012537518,0.0017213512,0.0008710859,0.000004075818,0.000024006176,0.000066648696],"genre_scores_gemma":[0.9898901,0.000014180285,0.009417435,0.00008929572,0.00007684694,0.000025228406,0.00008182212,0.000013770413,0.0003913415],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987394,0.000012897524,0.000543495,0.0003009311,0.00026100097,0.00014222602],"domain_scores_gemma":[0.99878114,0.00009355592,0.00042555772,0.00021274,0.00040379248,0.00008318301],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006223807,0.00008782888,0.00042985278,0.00007679441,0.00012439961,0.000012384368,0.00006135833,0.00003493416,0.0000049680607],"category_scores_gemma":[0.0012984908,0.00006952021,0.00011074909,0.00016333415,0.00028093613,0.000054403106,0.000027414168,0.00008407989,2.3022575e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011764715,0.00049684296,0.23633364,0.007256458,0.00048038867,0.000021970787,0.0150504755,0.008363462,0.5512027,0.00013800894,0.15441552,0.025064018],"study_design_scores_gemma":[0.0023430255,0.0004198469,0.009804677,0.00032980696,0.0002774472,0.000035655547,0.0005982616,0.77410483,0.20616084,0.00015738155,0.0056303344,0.00013790367],"about_ca_topic_score_codex":0.0000027042115,"about_ca_topic_score_gemma":3.0620353e-7,"teacher_disagreement_score":0.76574135,"about_ca_system_score_codex":0.000019323194,"about_ca_system_score_gemma":0.00006887598,"threshold_uncertainty_score":0.2834952},"labels":[],"label_agreement":null},{"id":"W3038195328","doi":"10.1017/s1431927600037545","title":"Detection of Early Cancers by Quantitative Cytology","year":2000,"lang":"en","type":"article","venue":"Microscopy and Microanalysis","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency","funders":"","keywords":"Medicine; Incidence (geometry); Cervical cancer; Cytology; Cervix; Uterine cervix; Gynecology; Malignancy; Cancer; Obstetrics; Population; Stage (stratigraphy); Internal medicine; Pathology; Carcinoma; Biology; Environmental health","score_opus":0.00697862535777627,"score_gpt":0.29826178541931525,"score_spread":0.291283160061539,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3038195328","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99199533,0.0028690333,0.00399725,0.00037405052,0.00002984333,0.00007174239,0.000009729076,0.000016348768,0.0006366392],"genre_scores_gemma":[0.9940693,0.0009891688,0.0025346512,0.00035314402,0.00001709544,0.0000037351513,0.000017596567,0.000011963887,0.0020033438],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992687,0.00004388216,0.00022427714,0.00021904088,0.00007890606,0.00016517844],"domain_scores_gemma":[0.999637,0.00004087742,0.00007104014,0.00012294325,0.000041120333,0.0000870103],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014083505,0.000102500206,0.00034613736,0.00010407013,0.00007465915,0.000011623276,0.000044702883,0.00006637913,0.00025619223],"category_scores_gemma":[0.000031519747,0.000089877474,0.00009234061,0.00023149067,0.00022309176,0.000038123424,0.000009194767,0.00018292251,0.000009578635],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020345207,0.000030044583,0.008231572,0.000031734144,0.000224079,0.0000049718833,0.0004079577,0.000009130052,0.9408674,0.000012144997,0.00036635212,0.049611107],"study_design_scores_gemma":[0.002910777,0.0010713468,0.018382635,0.00014681388,0.0016752455,0.0001430016,0.00041600704,0.0045691445,0.92217284,0.00012417829,0.048018403,0.00036957458],"about_ca_topic_score_codex":0.001724415,"about_ca_topic_score_gemma":0.00003620709,"teacher_disagreement_score":0.04924153,"about_ca_system_score_codex":0.000039492956,"about_ca_system_score_gemma":0.000034271903,"threshold_uncertainty_score":0.3665097},"labels":[],"label_agreement":null},{"id":"W3038503126","doi":"10.1007/s12021-020-09475-7","title":"DeepDicomSort: An Automatic Sorting Algorithm for Brain Magnetic Resonance Imaging Data","year":2020,"lang":"en","type":"article","venue":"Neuroinformatics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute on Aging; Canadian Institutes of Health Research; KWF Kankerbestrijding","keywords":"Computer science; Convolutional neural network; Data curation; Artificial intelligence; Pattern recognition (psychology); Magnetic resonance imaging; Contrast (vision); Sorting; Metadata; sort; Data mining; Information retrieval; Algorithm; Radiology; Medicine","score_opus":0.030434322757303178,"score_gpt":0.3135303376829426,"score_spread":0.2830960149256394,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3038503126","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.076407626,0.0017586044,0.84766877,0.065342456,0.0007282842,0.0024554434,0.00016116923,0.0013655823,0.0041120695],"genre_scores_gemma":[0.0505489,0.00006924042,0.86132115,0.08570896,0.001116738,0.00003242175,0.00079939724,0.00016717924,0.00023602071],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981522,0.00003816714,0.00069133926,0.00030404053,0.0003865603,0.00042769613],"domain_scores_gemma":[0.9983195,0.00025565614,0.00019847302,0.00073156785,0.00006454314,0.00043022525],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00053871836,0.00020270952,0.00036294814,0.000069639755,0.00016507514,0.00011823623,0.00050303974,0.000042288582,0.000058883845],"category_scores_gemma":[0.0024444617,0.0001870305,0.00006595848,0.00020521421,0.00009052961,0.00054441474,0.00022267335,0.00045850873,0.000040321374],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010461833,0.000035816192,0.0013948098,0.00029962132,0.000005608432,0.00004361005,0.0008533637,0.000031536616,0.0002067914,0.00006872058,0.013262257,0.9837874],"study_design_scores_gemma":[0.0014150376,0.00026964422,0.0019068056,0.000093741975,0.00007144842,0.0001996563,0.00022974328,0.9206797,0.00002708541,0.00007308035,0.074865595,0.00016846898],"about_ca_topic_score_codex":0.000005398507,"about_ca_topic_score_gemma":4.7326623e-7,"teacher_disagreement_score":0.9836189,"about_ca_system_score_codex":0.000020006899,"about_ca_system_score_gemma":0.00012255552,"threshold_uncertainty_score":0.7626882},"labels":[],"label_agreement":null},{"id":"W3038620230","doi":"10.48550/arxiv.2007.02319","title":"Medical Imaging with Deep Learning: MIDL 2020 -- Short Paper Track","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Compendium; Track (disk drive); Deep learning; Artificial intelligence; Library science; Computer science; Data science; History; Archaeology","score_opus":0.026018415193169976,"score_gpt":0.21330720742941842,"score_spread":0.18728879223624845,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3038620230","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7868355,0.0010778586,0.1522745,0.023393221,0.0008987851,0.0010551657,0.000008801935,0.0011648388,0.033291336],"genre_scores_gemma":[0.99312514,0.000964484,0.00078064925,0.002650214,0.000675551,0.0000018446566,0.00014371828,0.00011109668,0.001547285],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969896,0.0001931508,0.00035123952,0.001421766,0.0004607694,0.000583437],"domain_scores_gemma":[0.9976871,0.00016467397,0.00017453395,0.000638094,0.00016455342,0.001171033],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00044293056,0.0005268651,0.0008515157,0.00017218504,0.0001884399,0.00007158027,0.00062743714,0.00038324585,0.001171939],"category_scores_gemma":[0.0006088699,0.0004889619,0.00033372315,0.00046405935,0.000457299,0.0001425271,0.00070051185,0.0046063717,0.00011700943],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022495924,0.0009058518,0.7085395,0.002178773,0.0024035238,0.09283789,0.001865007,0.09879019,0.000899987,0.007797831,0.011471497,0.070060395],"study_design_scores_gemma":[0.0024991278,0.00021132267,0.016702496,0.00094294595,0.0010854078,0.00051108503,0.0005704084,0.9450213,0.000031545722,0.0011028929,0.030449713,0.00087177946],"about_ca_topic_score_codex":0.00013045255,"about_ca_topic_score_gemma":0.000021276863,"teacher_disagreement_score":0.8462311,"about_ca_system_score_codex":0.00020632082,"about_ca_system_score_gemma":0.00050293363,"threshold_uncertainty_score":0.9997562},"labels":[],"label_agreement":null},{"id":"W3038855643","doi":"10.21873/anticanres.14350","title":"Review of the Role of Radiomics in Tumour Risk Classification and Prognosis of Cancer","year":2020,"lang":"en","type":"review","venue":"Anticancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Trinity College","funders":"","keywords":"Radiomics; Medicine; Prostate cancer; Discriminative model; Disease; Oncology; Cancer; Breast cancer; Internal medicine; Machine learning; Radiology; Computer science","score_opus":0.09135065635705054,"score_gpt":0.4776273313926602,"score_spread":0.3862766750356097,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3038855643","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005596899,0.9962138,0.000002370229,0.0014498087,0.000034309247,0.0013355081,0.000034484874,0.000003200277,0.00036681793],"genre_scores_gemma":[0.0049157296,0.9946412,0.00014534812,0.00005003078,0.00007425694,0.00011933769,0.000007716364,0.0000296607,0.000016736043],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974728,0.00060053024,0.00080266705,0.00028974478,0.00061805,0.00021616275],"domain_scores_gemma":[0.99834967,0.0004311673,0.00053715747,0.0003401047,0.00025337408,0.00008854264],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020502906,0.00014217499,0.0015511708,0.000198656,0.000029386354,0.000004619484,0.00030729343,0.00010217141,0.000033302338],"category_scores_gemma":[0.0021648952,0.000087659864,0.00022113822,0.0011695753,0.0005606054,0.000020261732,0.00015667219,0.0012895862,8.682933e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000121108005,0.00005046605,0.014055649,0.14247406,0.000096972064,0.0000013782411,0.000059192826,1.18021745e-7,0.000075463795,0.00019137756,0.00025312518,0.8427301],"study_design_scores_gemma":[0.00025979275,0.00007864435,0.003990588,0.28181827,0.00065847556,0.0000079435695,0.0000384857,0.00076693104,0.00009609743,0.000066850684,0.7121378,0.000080104495],"about_ca_topic_score_codex":0.0012697655,"about_ca_topic_score_gemma":0.000016372667,"teacher_disagreement_score":0.84265,"about_ca_system_score_codex":0.00010913841,"about_ca_system_score_gemma":0.0011563296,"threshold_uncertainty_score":0.56026816},"labels":[],"label_agreement":null},{"id":"W3039188410","doi":"10.1002/cam4.3255","title":"Quantitative ultrasound radiomics in predicting response to neoadjuvant chemotherapy in patients with locally advanced breast cancer: Results from multi‐institutional study","year":2020,"lang":"en","type":"article","venue":"Cancer Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":78,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Hospital; Institute for Clinical Evaluative Sciences; Princess Margaret Cancer Centre; London Health Sciences Centre; University of Toronto; Western University; Sunnybrook Health Science Centre; St. Michael's Hospital; University Health Network; Toronto Metropolitan University; Health Sciences Centre; York University","funders":"Canadian Institutes of Health Research; Terry Fox Foundation","keywords":"Radiomics; Medicine; Breast cancer; Ultrasound; Neoadjuvant therapy; Cross-validation; Radiology; Cancer; Artificial intelligence; Internal medicine; Computer science","score_opus":0.01544054674262504,"score_gpt":0.31635583780244975,"score_spread":0.30091529105982473,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3039188410","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9605699,0.00052438845,0.0018230606,0.034880694,0.00030265894,0.0015724517,0.00023251743,0.00005950473,0.00003481045],"genre_scores_gemma":[0.98910356,0.0001992616,0.0028524268,0.0071861865,0.0003547857,0.00012192292,0.000104045204,0.000052169104,0.000025648305],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.997198,0.00017735758,0.00074846984,0.00076941965,0.0006873075,0.00041944842],"domain_scores_gemma":[0.998285,0.00054614723,0.00020359072,0.0002682444,0.00020426999,0.000492778],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006955043,0.00033640486,0.0008187883,0.00024025593,0.00007710455,0.000013041602,0.00020367563,0.00007468348,0.000088145694],"category_scores_gemma":[0.0022253958,0.00023978096,0.00003610013,0.00089883694,0.00024241622,0.00012681971,0.00003723742,0.00076802017,0.0000035160997],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.077441424,0.0005299933,0.8589428,0.000035290297,0.00013060788,0.00019094671,0.019152008,0.01580051,0.003867984,0.0000046925597,0.0002546418,0.023649082],"study_design_scores_gemma":[0.06292183,0.0022868002,0.9104858,0.0020408777,0.000066625056,0.0000059623358,0.0023926774,0.018962301,0.000039399547,0.0000031714978,0.00055639545,0.0002381314],"about_ca_topic_score_codex":0.004598844,"about_ca_topic_score_gemma":0.0007767372,"teacher_disagreement_score":0.051543005,"about_ca_system_score_codex":0.00064395915,"about_ca_system_score_gemma":0.00055622566,"threshold_uncertainty_score":0.9777984},"labels":[],"label_agreement":null},{"id":"W3039670270","doi":"10.3390/cancers12071778","title":"Potential Added Value of PET/CT Radiomics for Survival Prognostication beyond AJCC 8th Edition Staging in Oropharyngeal Squamous Cell Carcinoma","year":2020,"lang":"en","type":"article","venue":"Cancers","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":61,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre","funders":"National Center for Advancing Translational Sciences","keywords":"Medicine; Radiomics; Positron emission tomography; AJCC staging system; PET-CT; Oncology; Radiology; Cancer staging; Cancer; Internal medicine","score_opus":0.010900890494378205,"score_gpt":0.2638365611343678,"score_spread":0.2529356706399896,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3039670270","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9829034,0.00027943676,0.012098764,0.0025649434,0.0007580302,0.00071865314,0.00005723103,0.000039390783,0.00058010686],"genre_scores_gemma":[0.9946463,0.000033697335,0.0034457422,0.00069762283,0.0008109525,0.000041840878,0.00025198102,0.000038364742,0.00003347914],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99876183,0.000051892075,0.0003420705,0.0003090043,0.00026136264,0.0002738613],"domain_scores_gemma":[0.9993039,0.00012186386,0.00015349135,0.00013347784,0.00008720041,0.0002001017],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002579691,0.00014094531,0.00035238854,0.00009597474,0.00005037435,0.000013641199,0.00010836033,0.000018628718,0.000036131525],"category_scores_gemma":[0.00039782803,0.00014351076,0.00009610936,0.00020783191,0.00009659542,0.000077617566,0.000024313693,0.0002931952,0.0000017730457],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008208389,0.0007621712,0.30679607,0.0121519165,0.00030921446,0.0032886753,0.009452971,0.14702928,0.39843833,0.0044754297,0.041285604,0.06780195],"study_design_scores_gemma":[0.010059323,0.0008973758,0.022984887,0.000112051486,0.00032978388,0.00007319076,0.00090265746,0.9450219,0.017373798,0.00018579415,0.0017231582,0.00033603344],"about_ca_topic_score_codex":0.00039303934,"about_ca_topic_score_gemma":0.0000046940013,"teacher_disagreement_score":0.79799265,"about_ca_system_score_codex":0.00043368328,"about_ca_system_score_gemma":0.00062396686,"threshold_uncertainty_score":0.58521986},"labels":[],"label_agreement":null},{"id":"W3039802208","doi":"10.1002/mp.14368","title":"Repeatability of radiomic features in magnetic resonance imaging of glioblastoma: Test–retest and image registration analyses","year":2020,"lang":"en","type":"article","venue":"Medical Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":73,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"BC Cancer Foundation; Swiss Cancer Research Foundation; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Repeatability; Magnetic resonance imaging; Glioblastoma; Image registration; Medical imaging; Medical physics; Nuclear medicine; Artificial intelligence; Medicine; Computer science; Radiology; Image (mathematics); Mathematics; Statistics","score_opus":0.01246669645454345,"score_gpt":0.30596367923613843,"score_spread":0.293496982781595,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3039802208","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98310316,0.0042103757,0.0037342873,0.007888733,0.00004030744,0.00021853953,0.000010902742,0.000037122103,0.0007565903],"genre_scores_gemma":[0.9975927,0.00012254978,0.0015410094,0.0005383795,0.00015986423,0.0000032866649,0.000010617212,0.000015285324,0.000016318734],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9984471,0.00006233481,0.00047234667,0.00030127767,0.0005457603,0.00017115477],"domain_scores_gemma":[0.998942,0.0003666836,0.00015148704,0.00022838531,0.00007815433,0.00023329863],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004197298,0.00012818196,0.0005003247,0.000045952434,0.000024619669,0.00000612555,0.000116520605,0.00005673309,0.00004292665],"category_scores_gemma":[0.005623994,0.00011150596,0.00007210757,0.00038694713,0.00090937957,0.00007708786,0.00006037911,0.00048931665,7.9090455e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030700833,0.0004115035,0.82832074,0.0010131983,0.0000159038,0.0002835266,0.0010914461,0.000009694566,0.05576325,0.00018199478,0.0014887911,0.111112945],"study_design_scores_gemma":[0.004116272,0.0008563952,0.882195,0.00088469527,0.00015976351,0.00014496244,0.00014586942,0.07438505,0.03511204,0.0015150897,0.00023094914,0.00025391582],"about_ca_topic_score_codex":0.00013509295,"about_ca_topic_score_gemma":0.0000043791138,"teacher_disagreement_score":0.11085903,"about_ca_system_score_codex":0.000022862809,"about_ca_system_score_gemma":0.00015660141,"threshold_uncertainty_score":0.6732852},"labels":[],"label_agreement":null},{"id":"W3040329659","doi":"10.1038/s41598-020-67823-8","title":"A priori prediction of tumour response to neoadjuvant chemotherapy in breast cancer patients using quantitative CT and machine learning","year":2020,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; York University; University of Waterloo; University of Toronto; Sunnybrook Health Science Centre","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Terry Fox Foundation","keywords":"Breast cancer; Neoadjuvant therapy; Chemotherapy; Oncology; Computer science; A priori and a posteriori; Medicine; Cancer; Internal medicine; Machine learning","score_opus":0.021048559928047838,"score_gpt":0.30313573481318,"score_spread":0.2820871748851322,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3040329659","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9944056,0.00018361869,0.0003179037,0.004055093,0.0006087779,0.00036716115,0.000009724102,0.00002965669,0.000022434584],"genre_scores_gemma":[0.9978951,0.000019435522,0.0016495503,0.00027644637,0.000036277073,0.0000056834397,0.000016877662,0.000020693642,0.00007990759],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99829996,0.00010461913,0.0004712538,0.0004940073,0.00042783664,0.00020230714],"domain_scores_gemma":[0.999186,0.000038946087,0.00024430235,0.00014332366,0.0001477412,0.00023970421],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001279783,0.00011828103,0.0003009232,0.00021480481,0.000098092125,0.00004273048,0.0000422909,0.00002081368,0.000039204708],"category_scores_gemma":[0.0009349594,0.000101641905,0.00004359961,0.0005766207,0.00013018837,0.000091879454,0.00004941819,0.00027736014,8.9909935e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008106599,0.00008920937,0.6693227,0.000074206146,0.000019440855,0.00026101607,0.0029998405,0.0009787171,0.31715667,0.0000017218658,0.00024297845,0.008042806],"study_design_scores_gemma":[0.0017037105,0.00034083612,0.8479075,0.0005589328,0.000042196727,0.00037147512,0.00025342545,0.13994963,0.004444258,0.000032385575,0.0042517963,0.00014385169],"about_ca_topic_score_codex":0.00046175843,"about_ca_topic_score_gemma":0.000005224716,"teacher_disagreement_score":0.31271243,"about_ca_system_score_codex":0.00007919547,"about_ca_system_score_gemma":0.00017474516,"threshold_uncertainty_score":0.41448367},"labels":[],"label_agreement":null},{"id":"W3040698806","doi":"10.2174/1573405616666200712181135","title":"FDG-PET/CT Radiomics Models for The Early Prediction of Locoregional Recurrence in Head and Neck Cancer","year":2020,"lang":"en","type":"article","venue":"Current Medical Imaging Formerly Current Medical Imaging Reviews","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Guangxi Key Laboratory of Automatic Detection Technology and Instrument Foundation; Guilin University of Electronic Technology; National Natural Science Foundation of China; Natural Science Foundation of Guangxi Zhuang Autonomous Region","keywords":"Radiomics; Medicine; Head and neck cancer; Head and neck; Radiology; Artificial intelligence; Radiation therapy; Nuclear medicine; Computer science; Surgery","score_opus":0.0581821192958965,"score_gpt":0.36776885149841354,"score_spread":0.30958673220251703,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3040698806","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.061053846,0.61364645,0.20825975,0.10540857,0.0062677353,0.004795933,0.00014530018,0.00024429616,0.00017811726],"genre_scores_gemma":[0.55808234,0.42311895,0.0029774413,0.009379949,0.004295758,0.0014408743,0.00043986793,0.00023563899,0.000029150962],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9927646,0.00028622427,0.0023235222,0.0011516624,0.0023831513,0.0010908524],"domain_scores_gemma":[0.99562496,0.0009302966,0.0006942849,0.00053401466,0.0002768399,0.0019396303],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.003374015,0.00068132847,0.0016431379,0.00027462398,0.00024002569,0.00009209733,0.00089582324,0.00005462523,0.00022719863],"category_scores_gemma":[0.008109168,0.0004685225,0.0005350699,0.0008544858,0.0014848936,0.000554041,0.0003170551,0.003017705,0.000011859233],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001245496,0.00033426372,0.073153585,0.0025673013,0.000050111114,0.00008507812,0.00049257086,0.000017101629,0.000019918407,0.00054226536,0.020162677,0.90245056],"study_design_scores_gemma":[0.0044206497,0.00009265931,0.004931004,0.011409595,0.00031190764,0.000615116,0.00005694499,0.68558866,0.000008036257,0.00049267925,0.29171446,0.00035827907],"about_ca_topic_score_codex":0.00014659589,"about_ca_topic_score_gemma":0.000008670109,"teacher_disagreement_score":0.9020923,"about_ca_system_score_codex":0.00019225315,"about_ca_system_score_gemma":0.0011028952,"threshold_uncertainty_score":0.99977666},"labels":[],"label_agreement":null},{"id":"W3040918722","doi":"10.1164/ajrccm-conference.2020.201.1_meetingabstracts.a1046","title":"Deep Learning-Based A.I. Software for Chest X-Ray Analysis to Detect Microbiologically-Confirmed Tuberculosis: A Prospective Study of Diagnostic Accuracy","year":2020,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre","funders":"","keywords":"Computer science; Tuberculosis; Software; Artificial intelligence; Medicine; Medical physics; Radiology; Pathology; Programming language","score_opus":0.014004096944480935,"score_gpt":0.2903867862003323,"score_spread":0.27638268925585135,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3040918722","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.66524285,0.00010377532,0.32854202,0.003519486,0.000031813222,0.0023181937,0.000005227359,0.00018706381,0.00004957222],"genre_scores_gemma":[0.97210956,0.0000086792115,0.024179809,0.0031323323,0.00009700192,0.00034745317,0.00004874129,0.000034991728,0.0000414589],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99804443,0.00013900653,0.0005422429,0.00065322,0.00025451212,0.00036657928],"domain_scores_gemma":[0.99559915,0.0031703012,0.00017899733,0.00026350995,0.00036404366,0.00042402072],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00040341358,0.00026442276,0.00090239453,0.00021705589,0.00011849591,0.00003183795,0.00021856313,0.000096921554,0.00027871737],"category_scores_gemma":[0.045596145,0.00019413985,0.0003102023,0.0013368193,0.000078625744,0.00003496455,0.00007567938,0.00045715238,0.000015311778],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015591531,0.0016568447,0.8304099,0.00044277598,0.0046580136,0.000089099056,0.004735258,0.102692224,0.016643286,0.000009636371,0.0005491498,0.03655469],"study_design_scores_gemma":[0.011384229,0.015284675,0.79240644,0.00013712468,0.0076143565,0.000006560556,0.0033659474,0.16277702,0.0040211184,0.00002710373,0.002260478,0.00071493286],"about_ca_topic_score_codex":0.000114823,"about_ca_topic_score_gemma":0.000046624595,"teacher_disagreement_score":0.30686668,"about_ca_system_score_codex":0.000050820996,"about_ca_system_score_gemma":0.000078151956,"threshold_uncertainty_score":0.9624432},"labels":[],"label_agreement":null},{"id":"W3041319720","doi":"10.1101/2020.07.09.20137240","title":"The impact of the variation of imaging factors on the robustness of Computed Tomography Radiomic Features: A review","year":2020,"lang":"en","type":"review","venue":"medRxiv","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; Princess Margaret Cancer Centre; Ontario Institute for Cancer Research; University of Toronto; University Health Network","funders":"","keywords":"Robustness (evolution); Radiomics; Computer science; Computed tomography; Scanner; Data mining; Artificial intelligence; Histogram; Medical imaging; Pattern recognition (psychology); Medical physics; Medicine; Radiology; Image (mathematics)","score_opus":0.021619429802839568,"score_gpt":0.32780639782386406,"score_spread":0.3061869680210245,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3041319720","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015824701,0.99438006,0.00028682087,0.0017788647,0.00035322813,0.0014434678,0.000026767197,0.000018939909,0.00012935471],"genre_scores_gemma":[0.0114720715,0.9880638,0.00006537449,0.00012654175,0.00014879627,0.000020357662,0.00002783352,0.00005283801,0.000022388711],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9970487,0.00083746074,0.0010026712,0.00028571754,0.0005967655,0.00022870101],"domain_scores_gemma":[0.9956162,0.0016743481,0.001545785,0.00091463065,0.000154449,0.000094607334],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014719353,0.00038309157,0.0020404067,0.00013535171,0.00013952512,0.000012146466,0.00082532846,0.00009940777,0.000026282274],"category_scores_gemma":[0.0020777346,0.00013686498,0.0018117179,0.0012194072,0.00041712917,0.000022291697,0.000115758776,0.0011596931,7.19349e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009683903,0.00037525038,0.013015171,0.1141849,0.0048626545,0.000026189302,0.001029212,0.0003471697,0.00013647905,0.00093821145,0.013677551,0.8513104],"study_design_scores_gemma":[0.0015699215,0.00054445036,0.10244206,0.41135722,0.011399514,0.00044814733,0.00008498982,0.009697362,0.00005213975,0.00008919579,0.46144843,0.0008665528],"about_ca_topic_score_codex":0.00008282415,"about_ca_topic_score_gemma":5.10792e-7,"teacher_disagreement_score":0.85044384,"about_ca_system_score_codex":0.00007023017,"about_ca_system_score_gemma":0.00043847456,"threshold_uncertainty_score":0.5581192},"labels":[],"label_agreement":null},{"id":"W3042511599","doi":"10.1055/s-0040-1711024","title":"Devising novel imaging biomarkers for Human Papillomavirus (HPV) status in oropharyngeal squamous cell carcinoma (OPSCC): applying radiomics and machine learning algorithms","year":2020,"lang":"en","type":"article","venue":"Laryngo-Rhino-Otologie","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Radiomics; Human papillomavirus; Artificial intelligence; Basal cell; Computer science; Medicine; Machine learning; Algorithm; Oncology; Internal medicine","score_opus":0.034728054600616017,"score_gpt":0.2941329573429818,"score_spread":0.2594049027423658,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3042511599","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96058726,0.008385964,0.023282662,0.0036892465,0.00032589375,0.0020802,0.000062583116,0.00043951906,0.001146662],"genre_scores_gemma":[0.9677855,0.00025095552,0.027891338,0.002977549,0.0003957703,0.00014164584,0.00030696712,0.0001766334,0.000073689145],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99573743,0.00017553491,0.00095048785,0.0012380678,0.00046498256,0.0014334898],"domain_scores_gemma":[0.9977356,0.00061221106,0.0003456562,0.00039643585,0.00010030617,0.00080975186],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00088436593,0.00065758906,0.0012108934,0.0003877411,0.00053574576,0.00017639672,0.00035915905,0.00024339509,0.000051567073],"category_scores_gemma":[0.0012398928,0.00063499244,0.00024702656,0.0005378998,0.0003222745,0.00029011501,0.0003446463,0.0015526032,0.00000816055],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00078703655,0.00033010732,0.6729556,0.0014422374,0.000110399706,0.0013534273,0.002016566,0.00051479106,0.17628677,0.00017804315,0.00044015894,0.14358489],"study_design_scores_gemma":[0.027576318,0.0014491582,0.10075355,0.0002848507,0.00058831414,0.00065791723,0.0016663366,0.8257628,0.010640492,0.00025413276,0.028479563,0.0018865304],"about_ca_topic_score_codex":0.0015827293,"about_ca_topic_score_gemma":0.000031393007,"teacher_disagreement_score":0.82524806,"about_ca_system_score_codex":0.0003034717,"about_ca_system_score_gemma":0.00020140354,"threshold_uncertainty_score":0.9996101},"labels":[],"label_agreement":null},{"id":"W3044073468","doi":"10.1038/s41598-020-69106-8","title":"$$\\text {DRTOP}$$: deep learning-based radiomics for the time-to-event outcome prediction in lung cancer","year":2020,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":45,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; Sunnybrook Health Science Centre; University of Toronto; Toronto General Hospital; Concordia University","funders":"University of Toronto; Natural Sciences and Engineering Research Council of Canada; Mitacs; Government of Canada; Sunnybrook Research Institute","keywords":"Concordance correlation coefficient; Concordance; Artificial intelligence; Radiomics; Computer science; Hazard ratio; Algorithm; Machine learning; Lung cancer; Event (particle physics); Positron emission tomography; Proportional hazards model; Medicine; Nuclear medicine; Mathematics; Statistics; Internal medicine; Confidence interval; Physics","score_opus":0.01351538231969917,"score_gpt":0.3053651834387694,"score_spread":0.2918498011190702,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3044073468","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6487914,0.0024109827,0.20642138,0.12292568,0.01242636,0.0053941025,0.000013728562,0.00048477124,0.0011316137],"genre_scores_gemma":[0.9868904,0.000008508312,0.0013427853,0.003332983,0.0005104152,0.00021828378,0.00008386169,0.00005147522,0.0075613055],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977522,0.00005252549,0.0006366959,0.00066390046,0.000521163,0.00037351393],"domain_scores_gemma":[0.9987977,0.00015413214,0.0002091558,0.00039482745,0.0001225992,0.0003215519],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020107024,0.00015796103,0.00031331196,0.00015399948,0.0002971351,0.00013281184,0.00013716075,0.00006769198,0.000507181],"category_scores_gemma":[0.0020471136,0.00011415478,0.00016373231,0.00060963107,0.00013688262,0.00006011302,0.000049757684,0.00046234461,0.000035568897],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026189408,0.00016080811,0.3704627,0.00047764662,0.000116179064,0.0005116175,0.00202973,0.4571681,0.014756764,0.00001598778,0.09841495,0.055623632],"study_design_scores_gemma":[0.00060324516,0.0000668017,0.007882864,0.000086978886,0.000090957685,0.00004742352,0.000041041378,0.7910806,0.0004116055,0.000025648413,0.1995577,0.00010514694],"about_ca_topic_score_codex":0.000043885997,"about_ca_topic_score_gemma":0.000007371665,"teacher_disagreement_score":0.36257982,"about_ca_system_score_codex":0.00017774836,"about_ca_system_score_gemma":0.00023120978,"threshold_uncertainty_score":0.5553276},"labels":[],"label_agreement":null},{"id":"W3044795341","doi":"","title":"Medical Image Segmentation by Deep Convolutional Neural Networks","year":2019,"lang":"en","type":"dissertation","venue":"Spectrum Research Repository (Concordia University)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"McGill University","keywords":"Segmentation; Artificial intelligence; Convolutional neural network; Computer science; Deep learning; Image segmentation; Scale-space segmentation; Task (project management); Pattern recognition (psychology); Segmentation-based object categorization; Computer vision; Engineering","score_opus":0.01096096328986024,"score_gpt":0.2988526307904836,"score_spread":0.28789166750062334,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3044795341","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86349934,0.0012723767,0.0029263548,0.003081793,0.003123183,0.0012545257,0.000014266397,0.00021375166,0.12461443],"genre_scores_gemma":[0.89222676,0.00051736145,0.000077201665,0.00012597117,0.0009903527,0.0000060516472,0.0022207801,0.00009573951,0.10373981],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9951531,0.00058416656,0.00039640127,0.00083987333,0.0021402915,0.0008861297],"domain_scores_gemma":[0.99767375,0.00041080258,0.00022075635,0.0004812443,0.00037436993,0.0008390711],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0008699706,0.0003530734,0.00060338975,0.0007975963,0.0005558036,0.00013164699,0.00055882515,0.0006526782,0.00065603084],"category_scores_gemma":[0.0003771184,0.00037402115,0.00029905635,0.0007465141,0.0004582727,0.00023957118,0.00013187308,0.0038040609,0.0000726056],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.016578106,0.002934457,0.44516486,0.0050537973,0.005076147,0.037385687,0.0024893228,0.001060097,0.111701444,0.007940605,0.2916023,0.07301317],"study_design_scores_gemma":[0.013144479,0.0025620032,0.13561547,0.0015882176,0.0010055989,0.0012135577,0.007331843,0.73386323,0.0076949545,0.00018212578,0.09365526,0.0021432363],"about_ca_topic_score_codex":0.0037751817,"about_ca_topic_score_gemma":0.0005495913,"teacher_disagreement_score":0.73280317,"about_ca_system_score_codex":0.0009659764,"about_ca_system_score_gemma":0.0013507829,"threshold_uncertainty_score":0.9998712},"labels":[],"label_agreement":null},{"id":"W3045374016","doi":"10.1088/1361-6560/aba8b5","title":"Impact of image reconstruction method on dose distributions derived from <sup>90</sup> Y PET images: phantom and liver radioembolization patient studies","year":2020,"lang":"en","type":"article","venue":"Physics in Medicine and Biology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"British Columbia Institute of Technology; University of British Columbia","funders":"Canadian Institutes of Health Research","keywords":"Imaging phantom; Nuclear medicine; Iterative reconstruction; Physics; Medicine; Radiology","score_opus":0.09957968888513344,"score_gpt":0.41530765062175684,"score_spread":0.31572796173662343,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3045374016","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9742942,0.0014924997,0.020767324,0.002981769,0.000063316475,0.00021117422,0.000057078894,0.000020201122,0.000112435],"genre_scores_gemma":[0.98748326,0.003885672,0.00740986,0.0006196705,0.00037649702,0.000007898675,0.00020523714,0.000010622215,0.0000012735402],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989547,0.00017975854,0.0003153045,0.00030571123,0.000083884464,0.0001606059],"domain_scores_gemma":[0.9990984,0.00042771752,0.00013987886,0.00010639221,0.00009972168,0.00012788178],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019067973,0.00016636662,0.0006062778,0.00006796639,0.00005319243,0.0000045663623,0.000039723258,0.00004829906,0.000027171933],"category_scores_gemma":[0.0009629057,0.000109851644,0.000052701438,0.0001879552,0.00051476137,0.00005687446,0.000047742247,0.00030411404,9.1926125e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008039728,0.00029573473,0.1064287,0.00028878113,0.0007810856,0.00008809075,0.011264561,0.00026013836,0.31700996,0.001120906,0.0014252799,0.5602328],"study_design_scores_gemma":[0.030009285,0.01700903,0.30183163,0.0030613742,0.002046013,0.00063886744,0.013474307,0.58399147,0.018004581,0.02783346,0.0008680266,0.0012319821],"about_ca_topic_score_codex":0.00032779304,"about_ca_topic_score_gemma":0.0000011392692,"teacher_disagreement_score":0.5837313,"about_ca_system_score_codex":0.000041157247,"about_ca_system_score_gemma":0.000034541645,"threshold_uncertainty_score":0.447962},"labels":[],"label_agreement":null},{"id":"W3046278830","doi":"10.1053/j.semnuclmed.2020.07.003","title":"Multimodality Imaging and Artificial Intelligence for Tumor Characterization: Current Status and Future Perspective","year":2020,"lang":"en","type":"article","venue":"Seminars in Nuclear Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Agence Nationale de la Recherche","keywords":"Interpretability; Artificial intelligence; Medicine; Deep learning; Machine learning; Standardization; Medical imaging; Medical physics; Computer science","score_opus":0.017866760070910016,"score_gpt":0.3196566954485773,"score_spread":0.30178993537766724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3046278830","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7099907,0.009392928,0.0054226415,0.2728193,0.0007490958,0.0010458239,0.000021775162,0.00011909202,0.0004386343],"genre_scores_gemma":[0.9848427,0.0036975706,0.0032617582,0.0058496506,0.0022364988,0.000012107633,0.000045672783,0.000046570156,0.0000074748223],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99878556,0.00003864285,0.00031255875,0.00040539968,0.00019139053,0.00026648017],"domain_scores_gemma":[0.9992849,0.00009433067,0.00008905789,0.00010959201,0.00008910546,0.0003329727],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032567227,0.0001623071,0.00036171137,0.00009343861,0.00008761804,0.00001999248,0.000056536253,0.000034974935,0.00007916076],"category_scores_gemma":[0.0009033142,0.00013540171,0.000027646804,0.00019196725,0.00033609767,0.00007855678,0.00005859956,0.0004531919,0.0000018400618],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006876897,0.000107311535,0.019252667,0.00055956875,0.000026832106,0.00008634886,0.027399562,0.0000021208027,0.013854523,0.011579208,0.000681929,0.92576224],"study_design_scores_gemma":[0.004245451,0.0015698253,0.112718195,0.0026789934,0.00032741713,0.0002977989,0.059072625,0.53987813,0.0002631131,0.0055585937,0.2726227,0.0007671655],"about_ca_topic_score_codex":0.000035430967,"about_ca_topic_score_gemma":8.940803e-7,"teacher_disagreement_score":0.92499506,"about_ca_system_score_codex":0.00006612163,"about_ca_system_score_gemma":0.000035852718,"threshold_uncertainty_score":0.55215216},"labels":[],"label_agreement":null},{"id":"W3046538241","doi":"10.1177/0846537120942134","title":"Utilizing Artificial Intelligence for Head and Neck Cancer Outcomes Prediction From Imaging","year":2020,"lang":"en","type":"review","venue":"Canadian Association of Radiologists Journal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Medicine; Radiomics; Head and neck cancer; Medical physics; Head and neck; Clinical trial; Radiology; Radiation therapy; Pathology; Surgery","score_opus":0.058313227300536855,"score_gpt":0.3742050824103124,"score_spread":0.3158918551097756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3046538241","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00021575563,0.9867249,0.0031993168,0.0072754505,0.0013376749,0.00052579155,0.00057330064,0.00002542197,0.00012236575],"genre_scores_gemma":[0.0010503771,0.99420017,0.002469757,0.0005956596,0.0013479788,0.000026242857,0.00018312884,0.00004411741,0.000082592785],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979671,0.00015820948,0.00093704276,0.000306993,0.00024332949,0.00038731442],"domain_scores_gemma":[0.99742126,0.00056798325,0.0010802975,0.00011241093,0.00018461044,0.00063346175],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00083099573,0.00026404005,0.0015243511,0.00030440092,0.00020109149,0.000088422756,0.00015274668,0.0002734576,0.000051832358],"category_scores_gemma":[0.0032487768,0.00022078454,0.00040156976,0.00016157291,0.00008224277,0.00007587415,0.000017347369,0.0010777848,0.0000023899506],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008460671,0.000007663162,0.022446042,0.00060902844,0.00042887856,0.000039297804,0.000102481514,0.0000061332194,9.782431e-7,0.00012722693,0.003421744,0.97280204],"study_design_scores_gemma":[0.0002952584,0.00007431661,0.0038274282,0.00429703,0.0012775015,0.0001754365,0.00006990585,0.0033211934,5.202555e-7,0.0005985718,0.9858603,0.00020256398],"about_ca_topic_score_codex":0.0048581753,"about_ca_topic_score_gemma":0.0021544422,"teacher_disagreement_score":0.9824385,"about_ca_system_score_codex":0.0019287739,"about_ca_system_score_gemma":0.0018269412,"threshold_uncertainty_score":0.9003332},"labels":[],"label_agreement":null},{"id":"W3046599714","doi":"10.1148/rycan.2020190047","title":"Precision Digital Oncology: Emerging Role of Radiomics-based Biomarkers and Artificial Intelligence for Advanced Imaging and Characterization of Brain Tumors","year":2020,"lang":"en","type":"review","venue":"Radiology Imaging Cancer","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":50,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre","funders":"Fonds de Recherche du Québec - Santé","keywords":"Informatics; Radiomics; Artificial intelligence; Computer science; Medical imaging; Medical physics; Brain tumor; Medicine; Deep learning; Neuroimaging; Personalized medicine; Biomarker; Precision medicine; Machine learning; Pathology; Bioinformatics","score_opus":0.016663009954028793,"score_gpt":0.3601563416758399,"score_spread":0.34349333172181107,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3046599714","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0038891397,0.9666153,0.024104055,0.0033780236,0.00037211983,0.0013458472,0.0002045867,0.00005156195,0.000039346738],"genre_scores_gemma":[0.014783823,0.97867936,0.00493799,0.0004295227,0.00035863818,0.00016341465,0.00050928636,0.00012779704,0.0000101856],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975665,0.00013997033,0.0011123727,0.0006756623,0.0001533624,0.0003520923],"domain_scores_gemma":[0.99762374,0.00086543435,0.00097430125,0.00022507324,0.000119637,0.0001918311],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00055214466,0.0004020315,0.00215411,0.0004329038,0.0000799879,0.000028558587,0.00016697303,0.00014962304,0.000011286328],"category_scores_gemma":[0.00095737114,0.0003585784,0.0002584839,0.00029858536,0.00067303726,0.00014289143,0.00008726383,0.0004603136,3.7889603e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021763558,0.000033603166,0.00092056487,0.004737755,0.0001857704,0.000015447853,0.00018947372,0.000009671758,0.007042317,0.000076471064,0.000041666095,0.98652965],"study_design_scores_gemma":[0.0015884908,0.00043627864,0.00026310203,0.020081978,0.0019054752,0.000848815,0.00030547436,0.17247364,0.00091774866,0.0006298014,0.79971707,0.00083215017],"about_ca_topic_score_codex":0.000016961914,"about_ca_topic_score_gemma":4.999462e-7,"teacher_disagreement_score":0.98569745,"about_ca_system_score_codex":0.00019482696,"about_ca_system_score_gemma":0.00063766836,"threshold_uncertainty_score":0.99988663},"labels":[],"label_agreement":null},{"id":"W3046896154","doi":"10.1177/0846537120941434","title":"Artificial Intelligence in Lung Cancer: Bridging the Gap Between Computational Power and Clinical Decision-Making","year":2020,"lang":"en","type":"review","venue":"Canadian Association of Radiologists Journal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":48,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Lawson Health Research Institute","keywords":"Medicine; Lung cancer; Intensive care medicine; Standardization; Cancer; Bridging (networking); Medical physics; Pathology; Internal medicine; Computer science","score_opus":0.046687415465580785,"score_gpt":0.4202256669377138,"score_spread":0.373538251472133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3046896154","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005674387,0.9783747,0.011850686,0.0076717045,0.00084513036,0.00045133446,0.0000807944,0.0000118284515,0.00014638295],"genre_scores_gemma":[0.019538967,0.9762134,0.0021456773,0.0006194185,0.0014023758,0.000005352599,0.000029298926,0.000031479707,0.000014020804],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99681634,0.0005829444,0.0015490315,0.0002878019,0.00039253704,0.0003713396],"domain_scores_gemma":[0.9945423,0.0033893958,0.0013409845,0.00011279484,0.00015465822,0.00045987603],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0036546034,0.0002229614,0.0014985747,0.00038060054,0.00018925051,0.00009045963,0.00026839017,0.0003504207,0.00006223155],"category_scores_gemma":[0.008925647,0.00016149701,0.0003695278,0.00038726482,0.00017094963,0.000051237475,0.000039030136,0.0025313664,0.0000032349567],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005834919,0.000006752029,0.043008838,0.00023624429,0.0003064095,0.0001346791,0.000086018845,0.00015953953,7.859003e-9,0.00014711471,0.002881499,0.95302707],"study_design_scores_gemma":[0.0005043988,0.00021480181,0.061213512,0.028435653,0.0023273162,0.0013190361,0.00011772135,0.040999364,2.4969657e-8,0.003526756,0.86068094,0.00066046644],"about_ca_topic_score_codex":0.0007112667,"about_ca_topic_score_gemma":0.0011784026,"teacher_disagreement_score":0.9523666,"about_ca_system_score_codex":0.00190381,"about_ca_system_score_gemma":0.0030475867,"threshold_uncertainty_score":0.9997698},"labels":[],"label_agreement":null},{"id":"W3047633099","doi":"10.1002/mp.14437","title":"Technical Note: Synthesizing of lung tumors in computed tomography images","year":2020,"lang":"en","type":"article","venue":"Medical Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Computer science; Artificial intelligence; Graphical user interface; Computed tomography; Histogram; Lung cancer; Set (abstract data type); Computer vision; Pattern recognition (psychology); Radiology; Image (mathematics); Medicine; Pathology","score_opus":0.009487384914947473,"score_gpt":0.2835005047912786,"score_spread":0.2740131198763311,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3047633099","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12848577,0.0008236987,0.8135646,0.049816348,0.0002616265,0.000653136,0.000009166129,0.0003979937,0.0059876977],"genre_scores_gemma":[0.99116725,0.000024802519,0.0048288056,0.0034903502,0.00043711095,0.0000057201464,0.0000134188385,0.00002794869,0.00000457046],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99817544,0.000059406535,0.00044404145,0.00028346793,0.0007590343,0.00027861263],"domain_scores_gemma":[0.99892116,0.00030639934,0.00009483907,0.00018044726,0.00004578793,0.00045135268],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038057368,0.00014829564,0.0005530336,0.000069793634,0.000027857983,0.00000820923,0.0002213539,0.00011129566,0.00007966532],"category_scores_gemma":[0.0017375194,0.00012790631,0.0001563447,0.0006488775,0.00042738102,0.00004683565,0.0001125356,0.0009993027,0.0000067008586],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039713574,0.0015863618,0.2845901,0.002461633,0.00011633471,0.0019277243,0.0013587706,0.00024947416,0.048144046,0.0022107125,0.0148767615,0.64208096],"study_design_scores_gemma":[0.011731125,0.0011989695,0.20722412,0.007556261,0.00047462794,0.0002881433,0.00017021506,0.6583467,0.104097515,0.0035712065,0.0039625317,0.0013785654],"about_ca_topic_score_codex":0.000027347507,"about_ca_topic_score_gemma":4.5571952e-7,"teacher_disagreement_score":0.8626815,"about_ca_system_score_codex":0.000028824645,"about_ca_system_score_gemma":0.00014918756,"threshold_uncertainty_score":0.52158684},"labels":[],"label_agreement":null},{"id":"W3047861159","doi":"10.21037/tlcr-19-577","title":"Radiomics nomogram for prediction disease-free survival and adjuvant chemotherapy benefits in patients with resected stage I lung adenocarcinoma","year":2020,"lang":"en","type":"article","venue":"Translational Lung Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":48,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"CancerCare Manitoba; University of Manitoba","funders":"Shanghai Pulmonary Hospital; Natural Science Foundation of Shanghai","keywords":"Nomogram; Medicine; Radiomics; Radiogenomics; Stage (stratigraphy); Proportional hazards model; Oncology; Adenocarcinoma; Internal medicine; Lung cancer; Radiology; Cohort; Lasso (programming language); Cancer","score_opus":0.03250252776826584,"score_gpt":0.34786606854957564,"score_spread":0.3153635407813098,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3047861159","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96825117,0.004266072,0.0022862288,0.022507574,0.00006475855,0.001917912,0.000571768,0.0000491176,0.00008540184],"genre_scores_gemma":[0.9971911,0.00032562995,0.0011543902,0.00026890673,0.00031172458,0.00017392695,0.0004440338,0.000056276967,0.000074032905],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99782836,0.00009346124,0.00026610406,0.000445156,0.00096963224,0.00039728315],"domain_scores_gemma":[0.998844,0.00023850559,0.00004101133,0.00018282935,0.0002836039,0.00041000367],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00054475793,0.0001479623,0.00027458978,0.00019214556,0.00014209123,0.000042293337,0.00014391314,0.00006689012,0.000066564426],"category_scores_gemma":[0.00019860646,0.00012722095,0.00004860116,0.00044421735,0.00015375792,0.000121212,0.000023426493,0.0005765279,3.1679133e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0070832283,0.00011302297,0.9798477,0.0004997423,0.00010066261,0.000007640476,0.00054226414,0.0016998147,0.00011520175,0.00045530367,0.00056534,0.008970058],"study_design_scores_gemma":[0.010734624,0.00029919873,0.787238,0.00022646076,0.000041864794,5.0347415e-7,0.000020647934,0.20069245,0.000017452632,0.000045662004,0.0005828854,0.000100258025],"about_ca_topic_score_codex":0.0001338451,"about_ca_topic_score_gemma":0.000054409036,"teacher_disagreement_score":0.19899262,"about_ca_system_score_codex":0.00013608555,"about_ca_system_score_gemma":0.00037573455,"threshold_uncertainty_score":0.518792},"labels":[],"label_agreement":null},{"id":"W3048306659","doi":"10.1101/2020.08.06.20169516","title":"A hybrid algorithm for dental artifact detection in large computed tomography datasets","year":2020,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; Ontario Institute for Cancer Research; University of Toronto; Princess Margaret Cancer Centre; University Health Network","funders":"Canadian Institutes of Health Research; University of Toronto; University Health Network","keywords":"Artifact (error); Computed tomography; Artificial intelligence; Voxel; Computer science; Pattern recognition (psychology); Computer vision; Radiology; Medicine","score_opus":0.015325928499074526,"score_gpt":0.29777785826482284,"score_spread":0.2824519297657483,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3048306659","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.53125054,0.00033802426,0.46352357,0.0015390317,0.0011938408,0.0011714571,0.00074932945,0.0001861721,0.000048015172],"genre_scores_gemma":[0.9704871,0.00004060067,0.02316186,0.0012141118,0.0006563869,0.00012455261,0.0042352434,0.00006638847,0.000013755697],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99804676,0.000087069966,0.00045901598,0.0006828998,0.00032254853,0.00040169916],"domain_scores_gemma":[0.99900764,0.00010444127,0.00016716993,0.0003973377,0.000042922387,0.00028048048],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000586811,0.00029038207,0.00061024405,0.00033421215,0.00006941723,0.000053557826,0.0002267226,0.00014846098,0.0000348653],"category_scores_gemma":[0.00032723488,0.00027900093,0.00027106865,0.00019539347,0.000057490877,0.000041056588,0.0003323709,0.001419739,0.000016721751],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004037708,0.0010791059,0.16882023,0.002060054,0.00070472463,0.0019529648,0.00041854838,0.00022018375,0.009614398,0.00004099979,0.006918046,0.807767],"study_design_scores_gemma":[0.0030705975,0.0001930754,0.07631814,0.00049273676,0.00019153424,0.00014226191,0.000027197113,0.8932048,0.0042853863,0.00055240374,0.021157825,0.00036404093],"about_ca_topic_score_codex":0.00008214086,"about_ca_topic_score_gemma":0.000021934244,"teacher_disagreement_score":0.8929846,"about_ca_system_score_codex":0.00007968446,"about_ca_system_score_gemma":0.00008366419,"threshold_uncertainty_score":0.9999662},"labels":[],"label_agreement":null},{"id":"W3048331484","doi":"10.1002/mp.14427","title":"Deep learning segmentation of general interventional tools in two‐dimensional ultrasound images","year":2020,"lang":"en","type":"article","venue":"Medical Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Artificial intelligence; Segmentation; Imaging phantom; Deep learning; Computer vision; Medicine; Radiology","score_opus":0.018961188768082827,"score_gpt":0.3291332140006695,"score_spread":0.3101720252325867,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3048331484","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8822489,0.00023326022,0.1099753,0.0057918527,0.00017477534,0.00018308054,0.0000033213082,0.00005108566,0.0013384585],"genre_scores_gemma":[0.99406713,0.000018838755,0.0030413037,0.0020143935,0.00060039875,0.000006412343,0.00016396373,0.000017962073,0.00006960256],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984143,0.00008513132,0.00037274478,0.00021118,0.0007365619,0.00018012642],"domain_scores_gemma":[0.99926835,0.00024973365,0.000100887155,0.00006902325,0.000056364308,0.00025562075],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033330836,0.000107646236,0.00029002188,0.00003433694,0.000032563257,0.000012517303,0.00009131568,0.00004302686,0.0006099508],"category_scores_gemma":[0.0016878268,0.00009702708,0.000119222605,0.00019712908,0.00019833898,0.00009343007,0.000053883832,0.00068523444,0.000018919081],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004220746,0.0013164738,0.31481573,0.0006996135,0.00026847475,0.00040030884,0.0018930914,0.027316133,0.12686302,0.0017714947,0.0037809452,0.5204526],"study_design_scores_gemma":[0.023163226,0.0017640748,0.1952245,0.0018083528,0.00032427436,0.00028408243,0.0003983893,0.674973,0.093660556,0.006165086,0.0013047649,0.00092966633],"about_ca_topic_score_codex":0.00003944488,"about_ca_topic_score_gemma":0.0000010524154,"teacher_disagreement_score":0.6476569,"about_ca_system_score_codex":0.00003615531,"about_ca_system_score_gemma":0.00008652174,"threshold_uncertainty_score":0.66785336},"labels":[],"label_agreement":null},{"id":"W3048997450","doi":"10.1158/1538-7445.am2020-5489","title":"Abstract 5489: The cost of delaying therapy for advanced non-small cell lung cancer (NSCLC): a population kinetics assessment","year":2020,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Medicine; Placebo; Subgroup analysis; Population; Internal medicine; Lung cancer; Oncology; Survival analysis; Surgery; Confidence interval; Pathology","score_opus":0.0680414398346201,"score_gpt":0.46058110527279855,"score_spread":0.3925396654381784,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3048997450","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96648926,0.0037147598,0.008672819,0.017881796,0.00018277214,0.0021927946,0.000025195217,0.00002273662,0.0008178603],"genre_scores_gemma":[0.9933624,0.002326669,0.0019118624,0.0011207924,0.00048420148,0.00058998284,0.00002874248,0.000046197056,0.00012914857],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9984041,0.00006381366,0.0002936568,0.0002877414,0.0005528196,0.0003978776],"domain_scores_gemma":[0.9987824,0.00033845007,0.00011426099,0.0002244384,0.00034317403,0.00019730916],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007360483,0.0001217871,0.00026286935,0.00007089957,0.00015986935,0.00003454937,0.00022633112,0.00006158834,0.00014907547],"category_scores_gemma":[0.00018413718,0.00008430428,0.00009282957,0.0003072993,0.000098009135,0.000043519754,0.000053590877,0.00075588125,0.0000010211052],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00084601896,0.0001677891,0.083579704,0.0012387164,0.00013795492,0.000011401485,0.0016203345,0.00993144,0.5952956,0.00008738639,0.005346402,0.30173722],"study_design_scores_gemma":[0.015965268,0.0015211034,0.48359704,0.001939818,0.00019733502,0.000004787331,0.0014653623,0.36552435,0.080270275,0.00014440606,0.048793633,0.0005766304],"about_ca_topic_score_codex":0.0008859796,"about_ca_topic_score_gemma":0.00002562783,"teacher_disagreement_score":0.5150254,"about_ca_system_score_codex":0.0002259943,"about_ca_system_score_gemma":0.0004166625,"threshold_uncertainty_score":0.34378287},"labels":[],"label_agreement":null},{"id":"W3080245372","doi":"","title":"BIAS: Transparent reporting of biomedical image analysis challenges","year":2020,"lang":"en","type":"article","venue":"Veřejné služby Informačního systému (Masarykiana Brunensis Universitas)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":129,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; University of Toronto; Sunnybrook Health Science Centre","funders":"NIH Clinical Center; National Science Foundation; European Research Council; Natural Sciences and Engineering Research Council of Canada; Ministerstvo Školství, Mládeže a Tělovýchovy; Canadian Cancer Society","keywords":"Interpretability; Benchmarking; Checklist; Computer science; Data science; Image quality; Set (abstract data type); Quality (philosophy); Process (computing); Image (mathematics); Artificial intelligence; Psychology","score_opus":0.069861126523536,"score_gpt":0.2925615362881141,"score_spread":0.2227004097645781,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3080245372","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.80057466,0.006110651,0.05482971,0.07043261,0.0007417999,0.0017048419,0.00021063566,0.0011435642,0.06425155],"genre_scores_gemma":[0.99138975,0.0011606945,0.00532126,0.0014776035,0.00022058125,0.0000032108433,0.0002786549,0.0000477779,0.000100442696],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99510777,0.000111919966,0.0023383312,0.0006287724,0.0011362282,0.00067694846],"domain_scores_gemma":[0.99593794,0.00015711042,0.0018466853,0.00065281085,0.00038573536,0.0010196919],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011587228,0.0004522581,0.0017701398,0.001041044,0.0001884846,0.000037012756,0.00042007197,0.00026443184,0.0005776756],"category_scores_gemma":[0.0017774643,0.0004110516,0.00097460544,0.0022423163,0.0004304887,0.00044585962,0.00017092313,0.00075506774,0.000056963196],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.006094315,0.0035053315,0.22233026,0.0210223,0.052986138,0.022013338,0.12851103,0.012875684,0.06554795,0.011882431,0.10973145,0.34349978],"study_design_scores_gemma":[0.018798115,0.0042498056,0.19256741,0.0024957687,0.027732963,0.0011662685,0.08834955,0.35113266,0.0063046124,0.00009551566,0.30336386,0.0037434935],"about_ca_topic_score_codex":0.00023481953,"about_ca_topic_score_gemma":0.000008017393,"teacher_disagreement_score":0.33975628,"about_ca_system_score_codex":0.00015538785,"about_ca_system_score_gemma":0.00031811764,"threshold_uncertainty_score":0.9998341},"labels":[],"label_agreement":null},{"id":"W3081423662","doi":"10.1038/s41571-020-0417-8","title":"Artificial intelligence in radiation oncology","year":2020,"lang":"en","type":"review","venue":"Nature Reviews Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":401,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"National Cancer Institute; CARIM School for Cardiovascular Diseases, Universiteit Maastricht; Universiteit Maastricht; National Institutes of Health; Brigham and Women's Hospital","keywords":"Radiation oncology; Medical physics; Medicine; Oncology; Computer science; Radiation therapy; Internal medicine","score_opus":0.1720944463343659,"score_gpt":0.574027760237618,"score_spread":0.40193331390325215,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3081423662","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[5.392799e-7,0.978197,0.0005101008,0.009845248,0.0030717675,0.002586323,0.0000058737783,0.00006389765,0.0057192505],"genre_scores_gemma":[0.0000035386424,0.9783366,0.007939078,0.0088059,0.004314022,0.0001915654,0.00022247504,0.00008007106,0.00010677787],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9886686,0.0038033943,0.005458813,0.0011823494,0.0003300534,0.00055674923],"domain_scores_gemma":[0.99167705,0.0049094944,0.002059899,0.00060692703,0.000080264166,0.00066636526],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.0075738765,0.00061394693,0.0103288675,0.0003610957,0.000048614624,0.000018324366,0.00055495364,0.0048805266,0.0003026053],"category_scores_gemma":[0.02993352,0.00043128757,0.0019079476,0.0011104957,0.00034836648,0.00004982791,0.00020116617,0.0160539,0.0011064935],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005972353,0.00049432734,0.00002260378,0.0063391663,0.00011128853,0.0009249211,0.000023866069,2.3202334e-7,7.8863174e-8,0.0011772178,0.0063835564,0.98446304],"study_design_scores_gemma":[0.00026628276,0.0013619721,0.000013661268,0.00868973,0.0015308603,0.00040561412,0.0000049591013,0.00033001657,5.185244e-8,0.00035692385,0.9867149,0.0003250318],"about_ca_topic_score_codex":0.000007599236,"about_ca_topic_score_gemma":0.000016285201,"teacher_disagreement_score":0.984138,"about_ca_system_score_codex":0.0010766281,"about_ca_system_score_gemma":0.003303877,"threshold_uncertainty_score":0.9998139},"labels":[],"label_agreement":null},{"id":"W3082023277","doi":"10.1109/embc44109.2020.9175489","title":"A Cascaded Deep-Learning Framework for Segmentation of Metastatic Brain Tumors Before and After Stereotactic Radiation Therapy","year":2020,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; Sunnybrook Health Science Centre; York University","funders":"","keywords":"Segmentation; Computer science; Context (archaeology); Radiation treatment planning; Radiation therapy; Artificial intelligence; Image segmentation; Deep learning; Magnetic resonance imaging; Medical imaging; Computer vision; Radiology; Medicine","score_opus":0.01450571880648044,"score_gpt":0.3106224994656707,"score_spread":0.2961167806591903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3082023277","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7869893,0.00033586076,0.19896065,0.013082293,0.00003277966,0.00051881565,0.0000013995024,0.000037385173,0.00004153257],"genre_scores_gemma":[0.9467444,0.000054343644,0.047493964,0.0054450682,0.00010986343,0.000041841526,0.000023532077,0.000023400384,0.00006358238],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999247,0.000060987324,0.00023278633,0.0001743867,0.00015364267,0.00013117334],"domain_scores_gemma":[0.9993537,0.0002971244,0.00011607552,0.00006150319,0.00003755961,0.00013402163],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022048634,0.000098679135,0.0002415158,0.000055467204,0.000039103794,0.000019729945,0.000028789602,0.0000351417,0.00012075908],"category_scores_gemma":[0.00095587195,0.00007657851,0.000057534562,0.00011622591,0.000041207062,0.00007790842,0.00001094955,0.00023570082,0.0000014659813],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013635685,0.000107906395,0.1664208,0.00077686406,0.00041211492,0.000037548416,0.019704144,0.00012730001,0.010793537,0.0016265963,0.00024050889,0.79838914],"study_design_scores_gemma":[0.01585661,0.0061176373,0.2984927,0.0005533932,0.0006026242,0.00014316398,0.0052119354,0.651592,0.011214902,0.005308642,0.0043320577,0.00057432486],"about_ca_topic_score_codex":0.000013439184,"about_ca_topic_score_gemma":0.0000012152984,"teacher_disagreement_score":0.7978148,"about_ca_system_score_codex":0.00001695012,"about_ca_system_score_gemma":0.000023951432,"threshold_uncertainty_score":0.3122781},"labels":[],"label_agreement":null},{"id":"W3082115943","doi":"10.1109/embc44109.2020.9176099","title":"Machine Learning-Based A Priori Chemotherapy Response Prediction in Breast Cancer Patients using Textural CT Biomarkers","year":2020,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Health Science Centre; York University; University of Toronto","funders":"","keywords":"Breast cancer; A priori and a posteriori; Oncology; Computer science; Chemotherapy; Machine learning; Medicine; Artificial intelligence; Cancer; Internal medicine","score_opus":0.01163692005091752,"score_gpt":0.2815023521942921,"score_spread":0.26986543214337455,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3082115943","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9703991,0.00010282149,0.0013092115,0.027398827,0.00012949179,0.00034614562,0.000018292327,0.00014401981,0.00015208585],"genre_scores_gemma":[0.9920156,0.000023804943,0.0010613503,0.00652855,0.00013430964,0.00000862639,0.000045317338,0.000043923545,0.0001384945],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985641,0.00017054605,0.00031232167,0.00033699296,0.00033095814,0.0002850597],"domain_scores_gemma":[0.9993872,0.00008009738,0.00009716268,0.00010914813,0.00006228671,0.0002641226],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036196454,0.00018345116,0.0002846737,0.00015340414,0.00007443921,0.000025646246,0.00007872639,0.000049917537,0.0006567483],"category_scores_gemma":[0.00031148433,0.00014747887,0.00008631179,0.00043321616,0.00007376095,0.00008001066,0.000023102364,0.0005318739,0.0000084478215],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004887653,0.00015129313,0.96468425,0.00006210543,0.000059456648,0.000046796227,0.00026401068,0.0034045365,0.009912488,0.0000011701586,0.0005541721,0.015972063],"study_design_scores_gemma":[0.0047194804,0.00017968944,0.37416032,0.00011364869,0.000028064826,0.00002012137,0.000026298992,0.61734563,0.00019983186,9.936751e-7,0.0031015186,0.00010437217],"about_ca_topic_score_codex":0.0008626547,"about_ca_topic_score_gemma":0.000005673729,"teacher_disagreement_score":0.61394113,"about_ca_system_score_codex":0.00022081181,"about_ca_system_score_gemma":0.00018842926,"threshold_uncertainty_score":0.7190934},"labels":[],"label_agreement":null},{"id":"W3082976134","doi":"10.1109/embc44109.2020.9175746","title":"Predicting Local Failure after Stereotactic Radiation Therapy in Brain Metastasis using Quantitative CT and Machine Learning","year":2020,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University; Health Sciences Centre; Sunnybrook Health Science Centre","funders":"","keywords":"Radiation therapy; Medicine; Brain metastasis; Metastasis; Radiation treatment planning; Radiosurgery; Biomarker; Cancer; Radiology; Internal medicine","score_opus":0.02871268401844837,"score_gpt":0.30749398999013844,"score_spread":0.27878130597169004,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3082976134","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95634824,0.0015724833,0.026088918,0.015509571,0.000034885885,0.00025708563,0.0000020282414,0.00007201822,0.000114775976],"genre_scores_gemma":[0.9876628,0.00015801635,0.007931477,0.0040717092,0.000089529785,0.000007234031,0.000014285384,0.00003389965,0.000031049312],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987231,0.0002078412,0.00028935255,0.00031953052,0.0002238375,0.00023636046],"domain_scores_gemma":[0.9993291,0.0002739495,0.00009083236,0.000077117154,0.000028898157,0.00020009953],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045054578,0.00016696082,0.00033168853,0.00013061846,0.00006983762,0.000048694485,0.000042850734,0.000030866435,0.00016762689],"category_scores_gemma":[0.00081167405,0.00013479943,0.00005426032,0.00028189668,0.00008230476,0.00018612624,0.000039530005,0.0007091961,0.00000419352],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005326287,0.00005994613,0.8444228,0.00013317578,0.00017317082,0.00039594984,0.004064677,0.0018616293,0.005573788,0.00012651562,0.00006876471,0.14258693],"study_design_scores_gemma":[0.0029497924,0.00052386173,0.02747946,0.00010281981,0.000059833612,0.00014416578,0.0012183547,0.96368676,0.00045020768,0.000023756282,0.0031899314,0.00017104673],"about_ca_topic_score_codex":0.0004822647,"about_ca_topic_score_gemma":0.00003271954,"teacher_disagreement_score":0.96182513,"about_ca_system_score_codex":0.000052083233,"about_ca_system_score_gemma":0.000046676916,"threshold_uncertainty_score":0.5496961},"labels":[],"label_agreement":null},{"id":"W3083034492","doi":"10.2144/fsoa-2020-0073","title":"Quantitative Ultrasound Delta-Radiomics During Radiotherapy for Monitoring Treatment Responses in Head and Neck Malignancies","year":2020,"lang":"en","type":"article","venue":"Future Science OA","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University; Health Sciences Centre; York University; University of Toronto; Sunnybrook Health Science Centre","funders":"","keywords":"Radiomics; Medicine; Radiation therapy; Head and neck; Ultrasound; Naive Bayes classifier; Bayes' theorem; Radiology; Lymph node; Pathology; Artificial intelligence; Surgery; Computer science; Support vector machine; Bayesian probability","score_opus":0.027207901661829372,"score_gpt":0.3436316676486708,"score_spread":0.31642376598684147,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3083034492","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9867033,0.0020891542,0.00081086264,0.009594542,0.00033056477,0.00037633913,0.00000719131,0.00004078649,0.00004728765],"genre_scores_gemma":[0.94129616,0.0010507158,0.056279235,0.00047091334,0.0007731288,0.000028820108,0.000002952095,0.000020315154,0.0000777817],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99879676,0.000028498833,0.00019177684,0.00040275278,0.00023186489,0.00034834692],"domain_scores_gemma":[0.99932295,0.00018829464,0.00005736555,0.00012904493,0.000052937867,0.000249427],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034409604,0.00015077098,0.0002834821,0.00015016756,0.0002393107,0.00008188039,0.00011931578,0.000043437783,0.000005393479],"category_scores_gemma":[0.00071954634,0.000116192365,0.000050132858,0.00045668634,0.00031725943,0.00017634664,0.00001758202,0.00015891639,9.2617813e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014646724,0.00008277573,0.23189433,0.00012804964,0.000038969018,0.00008455182,0.014901135,0.00023930463,0.7366806,0.0008787405,0.000061787265,0.013545046],"study_design_scores_gemma":[0.010294741,0.0038038776,0.87901014,0.0004882571,0.000076873235,0.0003731529,0.008082592,0.03165085,0.05156581,0.00016298951,0.013907741,0.0005829574],"about_ca_topic_score_codex":0.00004097782,"about_ca_topic_score_gemma":0.0000050623757,"teacher_disagreement_score":0.68511486,"about_ca_system_score_codex":0.00019964909,"about_ca_system_score_gemma":0.0001742553,"threshold_uncertainty_score":0.47381872},"labels":[],"label_agreement":null},{"id":"W3083182284","doi":"10.14740/jnr.v0i0.628","title":"Approach to Brain Magnetic Resonance Imaging for Non-Radiologists","year":2020,"lang":"en","type":"article","venue":"Journal of Neurology Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine; Fluid-attenuated inversion recovery; Magnetic resonance imaging; Radiology; White matter; Diffusion MRI; Brain tumor; Neuroimaging; Effective diffusion coefficient; Nuclear medicine; Pathology","score_opus":0.06751092235776236,"score_gpt":0.3977471692544479,"score_spread":0.33023624689668557,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3083182284","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42413566,0.0022193047,0.015921017,0.5540249,0.00025034454,0.0006872268,0.0000027560523,0.000020178664,0.002738639],"genre_scores_gemma":[0.9419059,0.00008591726,0.013103647,0.042991478,0.0015429946,0.0000190928,0.0000020207005,0.000041667052,0.00030727612],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980428,0.0002836311,0.00040109752,0.00028834294,0.0004767155,0.0005073619],"domain_scores_gemma":[0.99790937,0.0008833501,0.00008734851,0.00016706181,0.00039842314,0.0005544702],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026124883,0.0001039415,0.00040983793,0.00027898152,0.00010513049,0.000028590583,0.00036453866,0.000070972215,0.000018275516],"category_scores_gemma":[0.007935023,0.00008099357,0.00012571801,0.000386115,0.0002492537,0.00004923493,0.00010735962,0.0017645021,0.000012409149],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.007577995,0.00039914603,0.097202815,0.00033676033,0.00004875115,0.0022061947,0.0019347139,0.00047069095,0.081392534,0.00046036323,0.626353,0.181617],"study_design_scores_gemma":[0.006040722,0.011632956,0.14170256,0.00008575941,0.00004534897,0.0052214297,0.00013509432,0.15100342,0.00025529705,0.0005391961,0.6831428,0.00019543714],"about_ca_topic_score_codex":0.00000473264,"about_ca_topic_score_gemma":1.260926e-7,"teacher_disagreement_score":0.51777023,"about_ca_system_score_codex":0.000023605711,"about_ca_system_score_gemma":0.0001992697,"threshold_uncertainty_score":0.9499537},"labels":[],"label_agreement":null},{"id":"W3083422982","doi":"10.1158/1538-7445.am2020-3935","title":"Abstract 3935: Runt related transcription factor-1 (runx1) plays a central role in vessel co-option of colorectal cancer liver metastases","year":2020,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Occupational Cancer Research Centre; McGill University Health Centre; McGill University","funders":"","keywords":"RUNX1; Colorectal cancer; Angiogenesis; Metastasis; Cancer research; Transcription factor; Liver cancer; Medicine; Cancer; Cancer cell; Transforming growth factor; Gene knockdown; Transforming growth factor beta; Pathology; Internal medicine; Biology; Cell culture","score_opus":0.05653761840472124,"score_gpt":0.3865931099863259,"score_spread":0.33005549158160463,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3083422982","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9912674,0.0037567115,0.0000440756,0.003700446,0.000104686915,0.0005239725,0.000111877765,0.000034725,0.00045613773],"genre_scores_gemma":[0.9961482,0.0032167349,0.00008255265,0.00016488715,0.00015792431,0.0000817751,0.0000640345,0.000032036958,0.000051824783],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9978538,0.00015892346,0.00038243877,0.0003499867,0.00072699715,0.0005278487],"domain_scores_gemma":[0.9992016,0.000121665376,0.00007915353,0.000112484726,0.00014613781,0.0003389424],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005263446,0.00014042131,0.00037725075,0.00020215403,0.000073140945,0.000023972032,0.0001465225,0.00011540486,0.0013970841],"category_scores_gemma":[0.00028151917,0.00012407146,0.00009549567,0.0004929048,0.00022297255,0.00012925148,0.000026336122,0.0012473756,0.000015332675],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011517714,0.00017517571,0.03723481,0.00048338692,0.00012223974,0.000122030775,0.005637259,0.0013045574,0.9344667,0.00010730734,0.0013008093,0.017893905],"study_design_scores_gemma":[0.0052184165,0.0005930328,0.7894245,0.00087265304,0.00009003141,0.000014719379,0.0011093583,0.03182433,0.1595111,0.00006439524,0.010986444,0.0002910292],"about_ca_topic_score_codex":0.0047963345,"about_ca_topic_score_gemma":0.00011545531,"teacher_disagreement_score":0.77495563,"about_ca_system_score_codex":0.00036693682,"about_ca_system_score_gemma":0.00049377506,"threshold_uncertainty_score":0.9995158},"labels":[],"label_agreement":null},{"id":"W3087403136","doi":"10.1038/s41598-020-71364-5","title":"Convolutional neural networks versus radiologists in characterization of small hypoattenuating hepatic nodules on CT: a critical diagnostic challenge in staging of colorectal carcinoma","year":2020,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; Sinai Health System; Princess Margaret Cancer Centre; Women's College Hospital; University of Toronto","funders":"University of Toronto","keywords":"Medicine; Confidence interval; Radiology; Nodule (geology); Receiver operating characteristic; Convolutional neural network; Colorectal cancer; Hepatocellular carcinoma; Internal medicine; Cancer; Machine learning; Computer science","score_opus":0.0280924226107033,"score_gpt":0.2808138689858188,"score_spread":0.2527214463751155,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3087403136","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9953541,0.00012294181,0.00068871333,0.0018459354,0.0015808614,0.0002959981,0.0000027416295,0.000017390721,0.00009132421],"genre_scores_gemma":[0.9993378,0.00000879832,0.0003488069,0.000078314086,0.00008511331,0.000014563869,0.000109119515,0.000013169353,0.0000043110726],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980782,0.00012029427,0.0007301296,0.00045770826,0.0003408656,0.00027275603],"domain_scores_gemma":[0.9985393,0.00078627525,0.00026494448,0.00018258773,0.00009689451,0.00012994133],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00097437477,0.00012179062,0.00039735332,0.00018625605,0.00004741587,0.000019182313,0.00007308979,0.000044281438,0.000019572106],"category_scores_gemma":[0.009026417,0.00011452757,0.000065444794,0.0004044518,0.0004026863,0.00005824959,0.00005110852,0.00036227013,5.732949e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029645575,0.00027487677,0.954354,0.00033888101,0.000015042252,0.0025098245,0.00111794,0.007699257,0.027579673,0.00024820986,0.000023754796,0.005542115],"study_design_scores_gemma":[0.00084817153,0.00025879103,0.40954417,0.00028961225,0.000021061169,0.000063905456,0.00008633682,0.5880402,0.00067777216,0.00006731419,0.000014248873,0.00008844275],"about_ca_topic_score_codex":0.00008410731,"about_ca_topic_score_gemma":0.000013354184,"teacher_disagreement_score":0.5803409,"about_ca_system_score_codex":0.000070210976,"about_ca_system_score_gemma":0.00011373683,"threshold_uncertainty_score":0.999321},"labels":[],"label_agreement":null},{"id":"W3087474631","doi":"10.1177/0846537120959875","title":"Radiology Artificial Intelligence: Bringing Theory to Clinical Practice","year":2020,"lang":"en","type":"article","venue":"Canadian Association of Radiologists Journal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Western University","funders":"","keywords":"Medicine; Clinical Practice; Medical physics; Radiology; Family medicine","score_opus":0.04133454104387329,"score_gpt":0.37068230959979864,"score_spread":0.32934776855592535,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3087474631","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16877677,0.0009281196,0.25780997,0.5540381,0.0039234073,0.0006458144,0.000026729633,0.00014384964,0.013707209],"genre_scores_gemma":[0.9334866,0.00024477925,0.029372174,0.03375402,0.0028852443,0.0000021189853,0.000009875766,0.000023771912,0.00022143456],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99753183,0.0006633905,0.0008468147,0.00023197851,0.00028768188,0.0004382735],"domain_scores_gemma":[0.9963027,0.0011832502,0.00055312493,0.00011881146,0.00037146662,0.00147063],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0055111065,0.00012341511,0.0004960341,0.00020454849,0.00014807869,0.000043241645,0.00020730673,0.00021366797,0.00021671057],"category_scores_gemma":[0.0628281,0.00011356071,0.00018949642,0.00029116913,0.000104787534,0.000085882355,0.000022097327,0.0012767869,0.000061619794],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00084050966,0.00012605301,0.22803241,0.000052752053,0.0011411491,0.0015155515,0.0033322899,0.002328891,0.0005478058,0.023849735,0.20159204,0.5366408],"study_design_scores_gemma":[0.0018477404,0.0032164154,0.15186669,0.00024447628,0.0007955029,0.0062568667,0.0033436392,0.033456277,0.00017497197,0.009897792,0.78808224,0.0008173921],"about_ca_topic_score_codex":0.00040659274,"about_ca_topic_score_gemma":0.0001476466,"teacher_disagreement_score":0.76470983,"about_ca_system_score_codex":0.00065312645,"about_ca_system_score_gemma":0.0010312136,"threshold_uncertainty_score":0.9450661},"labels":[],"label_agreement":null},{"id":"W3087560109","doi":"10.1016/j.nicl.2020.102437","title":"A Bayesian 2D functional linear model for gray-level co-occurrence matrices in texture analysis of lower grade gliomas","year":2020,"lang":"en","type":"article","venue":"NeuroImage Clinical","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"National Cancer Institute; Natural Sciences and Engineering Research Council of Canada; University of Michigan; American Cancer Society","keywords":"Gray level; Bayesian probability; Artificial intelligence; Computer science; Radiomics; Pattern recognition (psychology); Statistics; Isocitrate dehydrogenase; Realization (probability); Mathematics; Image (mathematics)","score_opus":0.12681888396749566,"score_gpt":0.41511870998582884,"score_spread":0.28829982601833315,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3087560109","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.505072,0.00017972398,0.47599974,0.017044835,0.00036527828,0.0005710615,0.0004789715,0.00009110755,0.0001972828],"genre_scores_gemma":[0.9821862,0.000089436726,0.010935507,0.006057097,0.00034824363,0.000013790954,0.0002694047,0.00002524535,0.00007505812],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976281,0.000111372756,0.00095022505,0.00061768154,0.00041257692,0.0002800262],"domain_scores_gemma":[0.9981149,0.00087295746,0.00024305137,0.00029620057,0.00011517913,0.0003577551],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00069076335,0.0001912732,0.00083236845,0.00029334554,0.000044818582,0.000017307786,0.00019709895,0.00015535193,0.00008845917],"category_scores_gemma":[0.0037754145,0.00016281892,0.00058705575,0.0009994743,0.00022324837,0.000075753895,0.000057368303,0.00092452817,0.0000064176],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005163389,0.0033655178,0.8463902,0.0008573898,0.0015584303,0.0009494628,0.00080936926,0.056795537,0.0060171024,0.00036003173,0.046228662,0.031504903],"study_design_scores_gemma":[0.0020595456,0.00040800316,0.07336458,0.000031514304,0.0007864821,0.000010163031,0.0000146887105,0.9209442,0.000017956327,0.000056189252,0.0021798972,0.00012676549],"about_ca_topic_score_codex":0.000009600463,"about_ca_topic_score_gemma":0.000004660879,"teacher_disagreement_score":0.8641487,"about_ca_system_score_codex":0.000014294438,"about_ca_system_score_gemma":0.0001643317,"threshold_uncertainty_score":0.6639563},"labels":[],"label_agreement":null},{"id":"W3087577741","doi":"10.1245/s10434-020-09134-w","title":"Differences in Liver Parenchyma are Measurable with CT Radiomics at Initial Colon Resection in Patients that Develop Hepatic Metastases from Stage II/III Colon Cancer","year":2020,"lang":"en","type":"article","venue":"Annals of Surgical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":25,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"National Cancer Institute; National Institutes of Health","keywords":"Medicine; Surgical oncology; Liver parenchyma; Colorectal cancer; Radiomics; Stage (stratigraphy); Hepatectomy; Radiology; Retrospective cohort study; Parenchyma; Cancer; Cohort; Resection; Internal medicine; Gastroenterology; Surgery; Pathology","score_opus":0.1008672061480325,"score_gpt":0.3521929790452156,"score_spread":0.2513257728971831,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3087577741","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9892572,0.0007104516,0.000013965406,0.008907915,0.0001340956,0.00039778528,0.00006109527,0.000019615716,0.0004978868],"genre_scores_gemma":[0.99485433,0.0032187873,0.00019949194,0.0014076984,0.00008096333,0.000049383227,0.00010569503,0.000018135728,0.0000655231],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9978901,0.00039415053,0.0005175555,0.00039704554,0.000429575,0.0003715798],"domain_scores_gemma":[0.99854755,0.00057109515,0.00034554192,0.00011770784,0.00017570962,0.00024237452],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045696725,0.00020223213,0.001013932,0.00015057453,0.00007576531,0.00000958723,0.00013140283,0.00012440125,0.0003980989],"category_scores_gemma":[0.0003038701,0.00015409489,0.00006440227,0.00044688297,0.00023632811,0.00010469533,0.00011353057,0.00054940657,0.000003001721],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00805782,0.0006818222,0.97407883,0.0001044958,0.00014359117,0.0015478692,0.0013062528,0.00016785169,0.00012305396,0.000014487894,0.0015731574,0.012200768],"study_design_scores_gemma":[0.021494843,0.0073738466,0.8848406,0.001003848,0.00017773709,0.000039555627,0.0005795369,0.010196461,0.005601164,0.000052978445,0.068121195,0.0005182307],"about_ca_topic_score_codex":0.0050253496,"about_ca_topic_score_gemma":0.003270626,"teacher_disagreement_score":0.08923822,"about_ca_system_score_codex":0.00020573135,"about_ca_system_score_gemma":0.00030877383,"threshold_uncertainty_score":0.75968593},"labels":[],"label_agreement":null},{"id":"W3087931875","doi":"10.1016/j.annonc.2020.08.1708","title":"1394P Deep learning model to predict clinical outcomes in patients with advanced non-small cell lung cancer treated with immune checkpoint inhibitors","year":2020,"lang":"en","type":"article","venue":"Annals of Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Medicine; Lung cancer; Receiver operating characteristic; Hazard ratio; Internal medicine; Oncology; Machine learning; Progression-free survival; Cancer; Artificial intelligence; Overall survival; Confidence interval","score_opus":0.027858380045234825,"score_gpt":0.3607937644516039,"score_spread":0.33293538440636905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3087931875","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.988398,0.00012893524,0.0016481661,0.007979333,0.00006304853,0.00068060856,0.0000038771195,0.000042174754,0.0010558157],"genre_scores_gemma":[0.99033624,0.0001340289,0.0056778654,0.0035149094,0.000075466494,0.0000497552,0.000025473657,0.00004753964,0.0001387259],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99805784,0.00011077398,0.00075514946,0.00041673743,0.00026129308,0.00039820667],"domain_scores_gemma":[0.99871624,0.00015853881,0.0003346724,0.00017639191,0.00023039333,0.00038378467],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040376958,0.00022372352,0.0009795676,0.00012506757,0.00003892966,0.0000058616124,0.00014028112,0.00012632339,0.000024958068],"category_scores_gemma":[0.00042535708,0.00015619154,0.00011814396,0.00028754378,0.00011829549,0.00006145057,0.00008174125,0.0008588389,0.0000031548864],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022972934,0.000551292,0.91671735,0.00010242884,0.0001313828,0.000046863956,0.0009771293,0.044779055,0.0003908118,0.0000013106591,0.00013944886,0.03386565],"study_design_scores_gemma":[0.01235536,0.010621423,0.8155739,0.00033361913,0.0001521311,0.0000018861102,0.00015566939,0.15863682,0.0009179518,0.0000023682162,0.0010091069,0.00023979263],"about_ca_topic_score_codex":0.00018748411,"about_ca_topic_score_gemma":0.000044258595,"teacher_disagreement_score":0.11385776,"about_ca_system_score_codex":0.000058840975,"about_ca_system_score_gemma":0.00027028765,"threshold_uncertainty_score":0.6369306},"labels":[],"label_agreement":null},{"id":"W3088345887","doi":"10.1101/2020.09.19.20198077","title":"Testing the Ability of Convolutional Neural Networks to Learn Radiomic Features","year":2020,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; University of British Columbia","funders":"Canadian Institutes of Health Research; National Institutes of Health; University of British Columbia","keywords":"Convolutional neural network; Artificial intelligence; Computer science; Pattern recognition (psychology); Deep learning; Feature (linguistics); Radiomics; Artificial neural network; Image (mathematics); Machine learning; Sphericity; Mathematics","score_opus":0.030912302495169488,"score_gpt":0.30184059753124,"score_spread":0.2709282950360705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3088345887","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95946366,0.001003606,0.0072648316,0.029647961,0.0010171793,0.0006892778,0.000010557948,0.000115824434,0.00078712445],"genre_scores_gemma":[0.99181354,0.000013407973,0.004120785,0.0026028461,0.001236343,0.000030847423,0.00004205199,0.00004399352,0.000096197124],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9979086,0.00021764777,0.0004997022,0.0005553326,0.0004906458,0.00032805433],"domain_scores_gemma":[0.9979951,0.0006723658,0.00024202629,0.00060447695,0.00017939169,0.00030664212],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0009986904,0.00027599646,0.00066373666,0.00007615277,0.00013317008,0.000025929312,0.0004523631,0.00019216651,0.000059151454],"category_scores_gemma":[0.0049794544,0.00018927919,0.00024276994,0.00028094192,0.00037412607,0.000016540234,0.0005953896,0.0026159864,0.000006930297],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032962856,0.00012964942,0.8166012,0.00083661714,0.00033042734,0.00016267481,0.0009215488,0.123301424,0.027358413,0.00036303606,0.009667876,0.019997472],"study_design_scores_gemma":[0.0003254085,0.000083840045,0.7043641,0.00019153189,0.00012510715,0.00010876858,0.000019001976,0.29340506,0.000049368755,0.00029489887,0.0008944966,0.0001383884],"about_ca_topic_score_codex":0.00021410991,"about_ca_topic_score_gemma":0.0000016598841,"teacher_disagreement_score":0.17010362,"about_ca_system_score_codex":0.00007672189,"about_ca_system_score_gemma":0.0002331823,"threshold_uncertainty_score":0.999685},"labels":[],"label_agreement":null},{"id":"W3089756171","doi":"10.2196/25337","title":"Correction: A Novel Approach to Assessing Differentiation Degree and Lymph Node Metastasis of Extrahepatic Cholangiocarcinoma: Prediction Using a Radiomics-Based Particle Swarm Optimization and Support Vector Machine Model","year":2021,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Baidu","keywords":"Radiomics; Particle swarm optimization; Support vector machine; Computer science; Lymph node metastasis; Degree (music); Node (physics); Medicine; Metastasis; Artificial intelligence; Machine learning; Cancer; Internal medicine; Engineering","score_opus":0.03569403278292189,"score_gpt":0.30055182228466265,"score_spread":0.26485778950174077,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3089756171","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4374322,0.000059496953,0.5617945,0.00022662776,0.000104135586,0.00018786898,0.000010635718,0.000033497956,0.00015101976],"genre_scores_gemma":[0.8079106,0.000028945127,0.19104832,0.000708689,0.000058824673,0.000022689159,0.00017602845,0.00002167291,0.000024207306],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981545,0.000047250196,0.0007128481,0.00019104706,0.0006527377,0.00024159424],"domain_scores_gemma":[0.998861,0.000105279134,0.00022054576,0.00020676042,0.00016215809,0.00044421744],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005190112,0.00018228931,0.00042903586,0.00015615756,0.000120596495,0.000082601066,0.00006295775,0.00014316698,0.000024181101],"category_scores_gemma":[0.00059509015,0.00016114686,0.000067417204,0.00034779237,0.00011500436,0.00028557077,0.0000736261,0.00030805077,4.2200077e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004051789,0.0028564008,0.1513964,0.0051908563,0.0006089702,0.000041824947,0.012136146,0.73887575,0.013522351,0.00037363652,0.00047457678,0.074117884],"study_design_scores_gemma":[0.002620438,0.000061281826,0.015700296,0.0002965981,0.00027352164,0.00034975522,0.00035227195,0.97925174,0.00094611873,0.0000041576163,0.000013451458,0.00013037902],"about_ca_topic_score_codex":0.000022189077,"about_ca_topic_score_gemma":7.5426817e-7,"teacher_disagreement_score":0.37074617,"about_ca_system_score_codex":0.00010903065,"about_ca_system_score_gemma":0.00037609087,"threshold_uncertainty_score":0.6571379},"labels":[],"label_agreement":null},{"id":"W3091991241","doi":"10.3389/frai.2020.550890","title":"Prognostic Value of Transfer Learning Based Features in Resectable Pancreatic Ductal Adenocarcinoma","year":2020,"lang":"en","type":"article","venue":"Frontiers in Artificial Intelligence","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hospital for Sick Children; Sinai Health System; Sunnybrook Health Science Centre; Health Sciences Centre; Lunenfeld-Tanenbaum Research Institute; University of Alberta; University Health Network; University of Toronto","funders":"Canadian Cancer Society Research Institute; Terry Fox Research Institute; Pancreatic Cancer Canada Foundation; Hebrew University of Jerusalem; Government of Ontario; Ontario Institute for Cancer Research; Princess Margaret Cancer Foundation","keywords":"Pancreatic ductal adenocarcinoma; Value (mathematics); Medicine; Pancreatic carcinoma; Internal medicine; Oncology; Pancreatic cancer; Computer science; Cancer; Machine learning","score_opus":0.02112175603968496,"score_gpt":0.2777843000506922,"score_spread":0.25666254401100724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3091991241","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8435221,0.0015900709,0.15016001,0.0034051922,0.0002834484,0.00047546718,0.0000023127077,0.000046046865,0.00051537686],"genre_scores_gemma":[0.98631954,0.00006353453,0.0129682645,0.00042617947,0.00012268183,0.000019334157,0.000015655707,0.000029900282,0.000034886732],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99814785,0.00017761499,0.0005716776,0.00038637873,0.0003388821,0.00037762796],"domain_scores_gemma":[0.99940675,0.00016344037,0.000055048888,0.00014801066,0.000049252994,0.00017748406],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047223383,0.00017455092,0.0005110829,0.00027086402,0.000043495853,0.000021500246,0.00018223675,0.0001088704,0.00006718047],"category_scores_gemma":[0.0021447095,0.0001672086,0.000095997435,0.00078196416,0.00020835319,0.00007189927,0.000024567269,0.00097869,0.000005659018],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008923824,0.00017654792,0.9244406,0.000393537,0.00003597315,0.00037536645,0.003588503,0.04797846,0.0064780307,0.0010458048,0.0002708506,0.01432394],"study_design_scores_gemma":[0.00037514078,0.00066271593,0.09432697,0.0006669737,0.0000893544,0.000020725605,0.0022522197,0.8790003,0.020491347,0.0015775702,0.00026140944,0.00027525637],"about_ca_topic_score_codex":0.00025426823,"about_ca_topic_score_gemma":0.000017322533,"teacher_disagreement_score":0.83102185,"about_ca_system_score_codex":0.00007002355,"about_ca_system_score_gemma":0.00015672791,"threshold_uncertainty_score":0.6818568},"labels":[],"label_agreement":null},{"id":"W3092138439","doi":"10.1200/jco.2020.38.29_suppl.268","title":"Readiness of health care systems to generate RWE: Frequency of radiographic imaging of metastatic disease during first-line systemic therapy.","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency","funders":"","keywords":"Medicine; Metastatic breast cancer; Systemic therapy; Cohort; Breast cancer; Clinical trial; Internal medicine; Population; Cancer; Lung cancer; Oncology; Radiology","score_opus":0.08282330971798137,"score_gpt":0.43865604401145425,"score_spread":0.3558327342934729,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3092138439","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94847304,0.028272588,0.0034936303,0.018369403,0.0008848991,0.00044048313,0.000018103285,0.0000102160775,0.000037635462],"genre_scores_gemma":[0.9912831,0.0035775925,0.0031231625,0.0013233895,0.0006434928,0.0000047397643,0.000005559919,0.000031663476,0.000007280265],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99353963,0.00089080975,0.0045245555,0.00023880598,0.00054683624,0.0002593865],"domain_scores_gemma":[0.99308777,0.00092236826,0.004022069,0.00025906652,0.000842074,0.0008666784],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0033279995,0.00018154627,0.0028600313,0.00031164987,0.00004210197,0.0000056978834,0.00028696549,0.0000716986,0.000016552955],"category_scores_gemma":[0.0045517245,0.00013052158,0.00060496,0.00047552743,0.00020187312,0.00007164644,0.000048494265,0.0007669507,7.9289134e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005772865,0.0015135753,0.8917128,0.013464155,0.0018381474,0.0015809508,0.002883383,0.011734879,0.010692552,0.0002875134,0.0009042807,0.057614937],"study_design_scores_gemma":[0.07532879,0.04403456,0.7841142,0.026167605,0.004667136,0.0035316176,0.0067333253,0.045443293,0.0014636344,0.00032752246,0.006981076,0.0012072729],"about_ca_topic_score_codex":0.00014219045,"about_ca_topic_score_gemma":0.0000029855967,"teacher_disagreement_score":0.107598595,"about_ca_system_score_codex":0.00009164479,"about_ca_system_score_gemma":0.0014777782,"threshold_uncertainty_score":0.5449168},"labels":[],"label_agreement":null},{"id":"W3092408429","doi":"10.1016/j.nic.2020.08.003","title":"Machine Learning Applications for Head and Neck Imaging","year":2020,"lang":"en","type":"review","venue":"Neuroimaging Clinics of North America","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":17,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Jewish General Hospital; Royal Victoria Hospital; McGill University; Centre Hospitalier de l’Université de Montréal; Polytechnique Montréal; Royal Victoria Regional Health Centre; McGill University Health Centre","funders":"Fonds de Recherche du Québec - Santé; Fondation de l'Association des radiologistes du Québec; Fondation de l’Ordre des dentistes du Québec","keywords":"Medicine; Head and neck; Deep learning; Medical physics; Software deployment; Focus (optics); Artificial intelligence; Radiology; Computer science; Surgery; Software engineering","score_opus":0.035357636824676984,"score_gpt":0.37901146223914195,"score_spread":0.343653825414465,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3092408429","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00002147635,0.9840735,0.0118093975,0.0015139102,0.00016696512,0.0017603232,0.0001079945,0.00018787885,0.00035852546],"genre_scores_gemma":[0.00007696262,0.98105097,0.015752064,0.0015181163,0.00045240374,0.0001855182,0.00064593076,0.00020405304,0.00011399184],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9968636,0.00013861629,0.0012857673,0.0009382648,0.00031937327,0.00045436338],"domain_scores_gemma":[0.99655443,0.0012390435,0.0011143195,0.00050283177,0.00015171089,0.0004376873],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00026054474,0.00054445636,0.0027038048,0.00028620486,0.00019467573,0.000052859727,0.0003251318,0.00008082995,0.000009938602],"category_scores_gemma":[0.0016329308,0.00049646624,0.0007079553,0.0005762319,0.000384807,0.00007071633,0.00022678664,0.0019070265,0.000015539634],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022001921,0.00007263573,0.008027267,0.010742324,0.00011516738,0.000034504894,0.000030706804,0.00001052818,3.1026386e-7,0.000014625524,0.00023816759,0.98069173],"study_design_scores_gemma":[0.0007394118,0.00023093831,0.00023774944,0.0024749404,0.0015145272,0.00019757023,0.0000055652945,0.021139825,3.934177e-8,0.000020814236,0.97310495,0.00033364992],"about_ca_topic_score_codex":0.000028195032,"about_ca_topic_score_gemma":8.0600825e-7,"teacher_disagreement_score":0.9803581,"about_ca_system_score_codex":0.00003898584,"about_ca_system_score_gemma":0.00036775682,"threshold_uncertainty_score":0.9997487},"labels":[],"label_agreement":null},{"id":"W3092481189","doi":"10.1007/s11307-020-01550-4","title":"Integration of PET/CT Radiomics and Semantic Features for Differentiation between Active Pulmonary Tuberculosis and Lung Cancer","year":2020,"lang":"en","type":"article","venue":"Molecular Imaging and Biology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":66,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Occupational Cancer Research Centre; University of British Columbia","funders":"Guangdong Province Higher Vocational Colleges and Schools Pearl River Scholar Funded Scheme; Natural Science Foundation of Guangdong Province; National Natural Science Foundation of China","keywords":"Medicine; Nomogram; Radiomics; Cohort; Lung cancer; Radiology; Logistic regression; Positron emission tomography; Nuclear medicine; Internal medicine","score_opus":0.010522059800330845,"score_gpt":0.3030913755544985,"score_spread":0.29256931575416767,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3092481189","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96531606,0.0042106174,0.015851868,0.01432657,0.000036128,0.00020336075,0.000018296729,0.000015075037,0.000022031467],"genre_scores_gemma":[0.9969623,0.0006276618,0.0013596653,0.00085526943,0.00007031295,0.000010580449,0.000097993936,0.0000116257825,0.000004555993],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99946976,0.00004161458,0.00012387602,0.00021827723,0.000035951154,0.00011052085],"domain_scores_gemma":[0.999709,0.000068878864,0.00006104869,0.000046824884,0.000033112334,0.000081118524],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000075063486,0.00009769023,0.0002448671,0.000054373068,0.000048206643,0.000012895146,0.000023476767,0.000014469676,0.000001611647],"category_scores_gemma":[0.00014155028,0.000076746604,0.000032139706,0.000048119913,0.00011923414,0.000028449089,0.000031959196,0.00014817383,2.4655707e-8],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008546964,0.000013260218,0.25264734,0.00029597865,0.00016430832,0.000023720595,0.0002710983,0.0000025176678,0.59115946,0.0001758005,0.00008207461,0.15507898],"study_design_scores_gemma":[0.002709001,0.00029940179,0.52994275,0.00036240864,0.0014001244,0.0006634775,0.0003562812,0.3988544,0.063469894,0.0009883196,0.0006007362,0.00035322612],"about_ca_topic_score_codex":0.00012285651,"about_ca_topic_score_gemma":0.0000010931323,"teacher_disagreement_score":0.5276896,"about_ca_system_score_codex":0.000010726114,"about_ca_system_score_gemma":0.00001355835,"threshold_uncertainty_score":0.31296358},"labels":[],"label_agreement":null},{"id":"W3092600108","doi":"10.1016/j.nic.2020.08.008","title":"Artificial Intelligence Applications for Workflow, Process Optimization and Predictive Analytics","year":2020,"lang":"en","type":"review","venue":"Neuroimaging Clinics of North America","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":72,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre; Royal Victoria Hospital; Royal Victoria Regional Health Centre; Jewish General Hospital; McGill University; Centre Hospitalier de l’Université de Montréal","funders":"Fonds de Recherche du Québec - Santé; Fondation de l'Association des radiologistes du Québec","keywords":"Workflow; Predictive analytics; Medicine; Analytics; Informatics; Artificial intelligence; Process (computing); Applications of artificial intelligence; Decision support system; Data science; Computer science","score_opus":0.05516516281025739,"score_gpt":0.3995003959787761,"score_spread":0.3443352331685187,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3092600108","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000023334526,0.42897156,0.56877667,0.00047986826,0.000094273884,0.0014650144,0.000105809624,0.0000566569,0.00004783265],"genre_scores_gemma":[0.000086529515,0.95704114,0.041169655,0.00045431184,0.00040412546,0.0002005536,0.00054185867,0.000090859736,0.000010958775],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99759233,0.00006505223,0.0011489176,0.0006674604,0.0002738859,0.00025234575],"domain_scores_gemma":[0.99731904,0.0008864644,0.0009299581,0.00034796016,0.00025602963,0.00026055076],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00018104585,0.00033427207,0.0016364969,0.0002106491,0.00009974665,0.000036196907,0.00024594128,0.00009529231,0.0000057545417],"category_scores_gemma":[0.00156954,0.00030494324,0.00033631237,0.00080253725,0.00037632475,0.000057173453,0.000082082624,0.00085508346,0.0000033397391],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002853487,0.00009043301,0.00022597982,0.007131827,0.0001186504,0.000007076862,0.00004569074,0.007244803,2.0150933e-8,0.000009269427,0.000061766434,0.98503596],"study_design_scores_gemma":[0.00007141447,0.00026721891,0.000011492508,0.0016094384,0.0019996858,0.00002748395,0.000014868897,0.39135975,1.3889844e-7,0.00011062511,0.6043271,0.0002007925],"about_ca_topic_score_codex":0.0000018026399,"about_ca_topic_score_gemma":1.89733e-7,"teacher_disagreement_score":0.98483515,"about_ca_system_score_codex":0.000029231363,"about_ca_system_score_gemma":0.00043397114,"threshold_uncertainty_score":0.9999403},"labels":[],"label_agreement":null},{"id":"W3092651983","doi":"10.1177/0846537120967720","title":"Imaging Database Preparation for Machine Learning","year":2020,"lang":"en","type":"article","venue":"Canadian Association of Radiologists Journal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier de l’Université de Montréal; McMaster University; Hamilton Health Sciences; Juravinski Hospital","funders":"","keywords":"Medicine; Medical physics; Database","score_opus":0.017086243319813815,"score_gpt":0.2945726153428971,"score_spread":0.27748637202308324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3092651983","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3529864,0.004365415,0.2527014,0.37550402,0.0020603372,0.0018293292,0.0003744113,0.00025259785,0.009926097],"genre_scores_gemma":[0.9869052,0.00017341085,0.007532272,0.003989918,0.00071671646,0.0000046362015,0.00019768429,0.000020673551,0.00045945894],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988863,0.00011099754,0.00035353928,0.00015376025,0.00020144835,0.0002939913],"domain_scores_gemma":[0.9984637,0.00017961032,0.00042288058,0.00006826382,0.0002423339,0.0006232168],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011064177,0.000097522476,0.00027945446,0.00013540364,0.00019754667,0.00004048911,0.00009770016,0.000065729524,0.000086341446],"category_scores_gemma":[0.008223436,0.000091188536,0.00012433091,0.00012800642,0.000036248795,0.000112890884,0.000009030305,0.00058158487,0.0000052409086],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024756635,0.000028512211,0.8525344,0.00012587069,0.00026466476,0.000116590934,0.00101303,0.0019821848,0.0062516825,0.0006333201,0.11582937,0.020972772],"study_design_scores_gemma":[0.0050440542,0.00064137386,0.03423576,0.00013333399,0.00027969573,0.0006131906,0.00023185961,0.46125615,0.0003633592,0.00023936103,0.49665093,0.00031092818],"about_ca_topic_score_codex":0.0008980077,"about_ca_topic_score_gemma":0.0004412388,"teacher_disagreement_score":0.8182987,"about_ca_system_score_codex":0.00056232885,"about_ca_system_score_gemma":0.000561857,"threshold_uncertainty_score":0.98448145},"labels":[],"label_agreement":null},{"id":"W3092853699","doi":"10.3390/cancers12102978","title":"Implementing Systems Modelling and Molecular Imaging to Predict the Efficacy of BCL-2 Inhibition in Colorectal Cancer Patient-Derived Xenograft Models","year":2020,"lang":"en","type":"article","venue":"Cancers","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"H2020 Societal Challenges; European Regional Development Fund; Science Foundation Ireland; Queen's University Belfast; Queen's University; European Commission; Royal College of Surgeons in Ireland; KWF Kankerbestrijding; Irish Cancer Society; H2020 Research Infrastructures; Health Research Board","keywords":"Colorectal cancer; Chemotherapy; Positron emission tomography; Medicine; Apoptosis; Cancer; Cancer research; Oncology; Internal medicine; Nuclear medicine; Biology","score_opus":0.014359258898078637,"score_gpt":0.27183947560847455,"score_spread":0.2574802167103959,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3092853699","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9547536,0.0020665408,0.03906172,0.0032146443,0.000091445945,0.0006161513,0.000010187261,0.00002858189,0.00015714906],"genre_scores_gemma":[0.99779284,0.00012844152,0.00050883676,0.0013855766,0.000084853826,0.00006473051,0.000009303979,0.000024447636,9.532982e-7],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988558,0.00004966963,0.00032127864,0.0002493209,0.00023013196,0.00029378632],"domain_scores_gemma":[0.9995366,0.00005225033,0.00010703604,0.000081188446,0.000055598397,0.0001673289],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021506046,0.00011769277,0.00025157008,0.00006976199,0.000066967485,0.000024559875,0.0000480598,0.000025351756,0.000005377985],"category_scores_gemma":[0.00007334166,0.000093566996,0.000043722834,0.00023947775,0.00006948793,0.00006826268,0.0000690435,0.00024085255,2.8143984e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013980291,0.0000070395076,0.003694513,0.00016217247,0.000039707847,0.000030681393,0.005328117,0.86733484,0.116170235,0.00007701107,0.00018781245,0.006828038],"study_design_scores_gemma":[0.00124766,0.00008169104,0.00021148393,0.00045959087,0.000052318846,0.000008283142,0.0012912655,0.9882663,0.007859759,0.00001889921,0.00040884595,0.00009388826],"about_ca_topic_score_codex":0.0017741064,"about_ca_topic_score_gemma":0.000010824066,"teacher_disagreement_score":0.12093144,"about_ca_system_score_codex":0.00023393732,"about_ca_system_score_gemma":0.00017116863,"threshold_uncertainty_score":0.3815551},"labels":[],"label_agreement":null},{"id":"W3093025058","doi":"10.1016/j.radonc.2020.09.054","title":"From multisource data to clinical decision aids in radiation oncology: The need for a clinical data science community","year":2020,"lang":"en","type":"review","venue":"Radiotherapy and Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre","funders":"University of Texas MD Anderson Cancer Center","keywords":"Radiation oncology; Big data; Metadata; Interoperability; Data science; Medicine; Computer science; Obstacle; Medical physics; Internal medicine; Radiation therapy; World Wide Web; Data mining","score_opus":0.29949733082312296,"score_gpt":0.5846014159161492,"score_spread":0.28510408509302626,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3093025058","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013228817,0.97187275,0.013266371,0.008591094,0.0019091616,0.0025909892,0.0003310596,0.000046139456,0.000069547845],"genre_scores_gemma":[0.000060958842,0.92511183,0.06202354,0.008674257,0.0028665697,0.000052179475,0.0011421099,0.000053652922,0.000014917974],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99314827,0.0030548328,0.0018419327,0.0012281742,0.0003016587,0.00042510618],"domain_scores_gemma":[0.97198117,0.023858596,0.0006268613,0.0029081937,0.00006333051,0.0005618688],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.01982557,0.0003448286,0.0031724523,0.00023295036,0.0003629075,0.00007069429,0.0031861188,0.0007414957,0.000027910237],"category_scores_gemma":[0.017663093,0.00022227303,0.00020655268,0.00064268796,0.0012269202,0.00017262422,0.001388627,0.0036637865,0.000008789626],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004836788,0.0003886957,0.00094485603,0.00024633625,0.00018035475,0.000036771416,0.00046207395,0.0000010317717,0.0000015000459,0.000015734868,0.011016789,0.98622215],"study_design_scores_gemma":[0.0041720537,0.0023697824,0.001216532,0.0012555653,0.000602748,0.00010443681,0.00014105251,0.024304433,2.3344423e-8,0.000039645856,0.96558905,0.00020467286],"about_ca_topic_score_codex":0.00043400328,"about_ca_topic_score_gemma":0.00016400545,"teacher_disagreement_score":0.9860175,"about_ca_system_score_codex":0.00058367813,"about_ca_system_score_gemma":0.0028448056,"threshold_uncertainty_score":0.9986348},"labels":[],"label_agreement":null},{"id":"W3093315369","doi":"10.1016/j.tranon.2020.100906","title":"Prediction of post-radiotherapy locoregional progression in HPV-associated oropharyngeal squamous cell carcinoma using machine-learning analysis of baseline PET/CT radiomics","year":2020,"lang":"en","type":"article","venue":"Translational Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre","funders":"National Center for Advancing Translational Sciences; Fonds de Recherche du Québec - Santé","keywords":"Medicine; Radiomics; Interquartile range; Oncology; Radiation therapy; Lymph node; Radiology; Internal medicine","score_opus":0.02766428694063654,"score_gpt":0.3124142368143861,"score_spread":0.2847499498737496,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3093315369","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9863651,0.00084715406,0.008607407,0.0034713754,0.00007311763,0.0003362033,0.00010325326,0.00003261464,0.00016377267],"genre_scores_gemma":[0.98782355,0.0000476084,0.010458066,0.00050395436,0.000105168525,0.000005715246,0.0010143258,0.000030678755,0.000010949702],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977905,0.00037442744,0.00082413637,0.00032358567,0.0004565786,0.000230765],"domain_scores_gemma":[0.998631,0.00047833976,0.00042350244,0.00009860733,0.00019822257,0.00017033945],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00065645913,0.00018238877,0.0008750048,0.0005184968,0.00005341778,0.0000040929467,0.000106573505,0.000061458835,0.00030170113],"category_scores_gemma":[0.00026091505,0.00017064714,0.00027347516,0.0010348422,0.00016017284,0.00007114752,0.000013159851,0.00059909653,5.2630304e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001766128,0.0008130677,0.8130874,0.00018245478,0.0003677161,0.0003880763,0.0011122121,0.10762152,0.06714909,0.00006357996,0.000023516013,0.007425261],"study_design_scores_gemma":[0.0047274353,0.0009976432,0.17993627,0.00002358209,0.00075093994,0.00007585582,0.00004597342,0.8126377,0.00041234156,0.000007756199,0.0002931714,0.00009131299],"about_ca_topic_score_codex":0.00029457334,"about_ca_topic_score_gemma":0.000034745313,"teacher_disagreement_score":0.7050162,"about_ca_system_score_codex":0.00017476734,"about_ca_system_score_gemma":0.0004786647,"threshold_uncertainty_score":0.69587886},"labels":[],"label_agreement":null},{"id":"W3093420264","doi":"10.48083/akui6936","title":"Classification of Molecular Biomarkers","year":2020,"lang":"en","type":"article","venue":"Société Internationale d’Urologie Journal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Biomarker; Disease; Biomarker discovery; Medicine; Malignancy; Context (archaeology); Oncology; Bioinformatics; Internal medicine; Biology; Proteomics","score_opus":0.040227691569884885,"score_gpt":0.3442319046386999,"score_spread":0.30400421306881503,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3093420264","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8861907,0.00042124462,0.024465512,0.07654846,0.00034970426,0.000102293234,0.0000036254924,0.000040245115,0.011878217],"genre_scores_gemma":[0.99034107,0.00013457591,0.0042810002,0.004819713,0.00029416423,0.0000023214232,0.000018353834,0.000010681308,0.000098106015],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9989383,0.000059099188,0.00034213142,0.00013584095,0.00039442276,0.0001301843],"domain_scores_gemma":[0.99918705,0.00009953226,0.00025456122,0.00008069258,0.00020610695,0.00017203434],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032662257,0.000083914594,0.00018964952,0.00008173265,0.000043121814,0.000020584193,0.00017686353,0.00006444343,0.00038434667],"category_scores_gemma":[0.0015486722,0.00007062464,0.00017542647,0.000111400295,0.00010896207,0.00006481003,0.000037907776,0.0004979966,0.000010036032],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007402393,0.00029364708,0.29920593,0.00011702463,0.0013331401,0.00042998363,0.0007956952,0.0005308482,0.5454913,0.0062609403,0.02437351,0.12042777],"study_design_scores_gemma":[0.009891454,0.0018319244,0.6987722,0.00023086423,0.0005383869,0.0019034288,0.0018528975,0.1645947,0.01735925,0.008203373,0.09427093,0.00055061135],"about_ca_topic_score_codex":0.00000245792,"about_ca_topic_score_gemma":5.577592e-8,"teacher_disagreement_score":0.528132,"about_ca_system_score_codex":0.000053246884,"about_ca_system_score_gemma":0.00011945844,"threshold_uncertainty_score":0.42083266},"labels":[],"label_agreement":null},{"id":"W3093607327","doi":"10.1016/j.ijrobp.2020.07.306","title":"Convolutionally Normalized Survival Prediction of Head and Neck Cancer Using Planning CT","year":2020,"lang":"en","type":"article","venue":"International Journal of Radiation Oncology*Biology*Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Upsampling; Convolutional neural network; Artificial intelligence; Medicine; Feature (linguistics); Deep learning; Preprocessor; Computer science; Pattern recognition (psychology); Radiation treatment planning; Image quality; Radiology; Radiation therapy; Image (mathematics)","score_opus":0.03948425177002169,"score_gpt":0.37022805638922496,"score_spread":0.3307438046192033,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3093607327","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9498604,0.0009922932,0.041331973,0.0059051765,0.0015177098,0.000109288,0.000057195863,0.000021504122,0.00020445124],"genre_scores_gemma":[0.9896483,0.00051879993,0.0058125146,0.001521882,0.0024170782,0.0000020751245,0.000052565803,0.000018574985,0.000008220403],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99861944,0.00013446105,0.00064971956,0.00016039879,0.00029042602,0.0001455686],"domain_scores_gemma":[0.9982199,0.00021614895,0.0008346484,0.000053912463,0.00050453714,0.00017086182],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041218396,0.00012583828,0.0004505295,0.00009692708,0.0000540412,0.000013334032,0.00015142022,0.000087418935,0.000046557558],"category_scores_gemma":[0.0005360319,0.00011523882,0.00012517087,0.00011710554,0.00022840344,0.00018371879,0.000047849662,0.000500823,0.0000013107019],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005514051,0.00011703516,0.934005,0.000028030443,0.00056281977,0.000048425547,0.00052803627,0.0072986656,0.024509689,0.0025569056,0.00032748966,0.029466476],"study_design_scores_gemma":[0.020833375,0.0021229303,0.42317584,0.00053975027,0.0005578333,0.00093593105,0.0002281554,0.5099341,0.002450736,0.0027230813,0.036203865,0.00029437387],"about_ca_topic_score_codex":0.000050713857,"about_ca_topic_score_gemma":5.758795e-7,"teacher_disagreement_score":0.5108292,"about_ca_system_score_codex":0.0002421843,"about_ca_system_score_gemma":0.0005222668,"threshold_uncertainty_score":0.4699303},"labels":[],"label_agreement":null},{"id":"W3093691058","doi":"10.1016/j.ijrobp.2020.07.2497","title":"Tumor Target Delineation in Head and Neck ReIrradiation Cases: Comparison Between DECT and MRI","year":2020,"lang":"en","type":"article","venue":"International Journal of Radiation Oncology*Biology*Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier de l’Université de Montréal","funders":"","keywords":"Medicine; Contouring; Magnetic resonance imaging; Nuclear medicine; Radiology; Head and neck cancer; Radiation treatment planning; Radiation therapy; Head and neck; Medical imaging; Surgery","score_opus":0.029512316911869438,"score_gpt":0.3684946743287639,"score_spread":0.3389823574168945,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3093691058","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92009264,0.00079913903,0.059680186,0.01873903,0.00040056618,0.00016741086,0.000015663703,0.0000218756,0.00008350121],"genre_scores_gemma":[0.982236,0.00046122726,0.0122528095,0.0028788068,0.0020386642,0.0000033807755,0.00010551537,0.000019013096,0.0000045493475],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99848425,0.00018269868,0.00074806245,0.00021579459,0.00021003895,0.0001591584],"domain_scores_gemma":[0.9983551,0.0004516511,0.00066320336,0.00005379799,0.00026133124,0.0002149387],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005413403,0.00014439748,0.00050430506,0.00015186825,0.000049740076,0.000032016498,0.0001191207,0.00012589438,0.000016098238],"category_scores_gemma":[0.0012603244,0.00013470177,0.00007030564,0.00014893971,0.00014543466,0.00022292869,0.000043424625,0.0006474792,0.0000041755156],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022889886,0.00007910182,0.85315466,0.000014465356,0.000115361356,0.000061969564,0.0006088193,0.0008353975,0.0006308593,0.0006644521,0.00046321834,0.14314282],"study_design_scores_gemma":[0.011052085,0.0023569223,0.6233506,0.00016171427,0.00017104682,0.00056447345,0.00021262112,0.31914017,0.0005159205,0.0029225608,0.039293293,0.00025856003],"about_ca_topic_score_codex":0.000039190792,"about_ca_topic_score_gemma":0.000003354505,"teacher_disagreement_score":0.31830478,"about_ca_system_score_codex":0.00024653345,"about_ca_system_score_gemma":0.00023261098,"threshold_uncertainty_score":0.54929787},"labels":[],"label_agreement":null},{"id":"W3094028328","doi":"10.1101/2020.10.19.20215392","title":"The ANTsX ecosystem for quantitative biological and medical imaging","year":2020,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Douglas Mental Health University Institute","funders":"Office of Naval Research; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Eisai; Cohen Veterans Bioscience; Northern California Institute for Research and Education; Pfizer; Biogen; BioClinica; F. Hoffmann-La Roche; University of Southern California; Eli Lilly and Company; U.S. Department of Defense; Meso Scale Diagnostics; Alzheimer's Disease Neuroimaging Initiative; National Heart, Lung, and Blood Institute; Novartis Pharmaceuticals Corporation; Bristol-Myers Squibb; National Institute on Aging; Alzheimer's Association; Foundation for the National Institutes of Health","keywords":"Computer science; Python (programming language); Workflow; Software; Normalization (sociology); Deep learning; Interfacing; Visualization; Artificial intelligence; Machine learning; Software engineering; Data science; Programming language","score_opus":0.03984286559280696,"score_gpt":0.35148257744861944,"score_spread":0.31163971185581246,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3094028328","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7613247,0.01011705,0.049233343,0.17469324,0.001854062,0.0014842051,0.000050484738,0.00017776283,0.0010651506],"genre_scores_gemma":[0.98966813,0.002355713,0.0049241167,0.0019083163,0.0008167502,0.00012378821,0.000065554916,0.00005071208,0.00008689399],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978996,0.00019665224,0.00048359993,0.0006101686,0.00044670058,0.00036329133],"domain_scores_gemma":[0.99745685,0.0014775639,0.00019477175,0.00030992358,0.000108437845,0.00045245377],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019133983,0.00026893703,0.00062036136,0.000053778054,0.00024878897,0.00009462752,0.00032269902,0.0002144472,0.000039780625],"category_scores_gemma":[0.0076518813,0.0001536739,0.00019058015,0.00007277607,0.00033437888,0.000018559513,0.0005177085,0.0013864582,0.000014106003],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014723955,0.00027596802,0.61115116,0.0034396988,0.001510798,0.0016083344,0.0026615777,0.000030257632,0.003865443,0.027947677,0.0256546,0.3203821],"study_design_scores_gemma":[0.0028337887,0.0003600416,0.047578286,0.0021549715,0.00032268473,0.00048004324,0.00080899685,0.7122701,0.0001316014,0.010116283,0.22233005,0.0006131721],"about_ca_topic_score_codex":0.000009342987,"about_ca_topic_score_gemma":0.000005582371,"teacher_disagreement_score":0.7122398,"about_ca_system_score_codex":0.000038971826,"about_ca_system_score_gemma":0.00022121579,"threshold_uncertainty_score":0.91605693},"labels":[],"label_agreement":null},{"id":"W3094095883","doi":"10.1016/j.ijrobp.2020.07.108","title":"MRI-Radiomic Signature For Differentiating Low Grade Glioma From Glioblastoma Peritumoral Region","year":2020,"lang":"en","type":"article","venue":"International Journal of Radiation Oncology*Biology*Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; Sunnybrook Hospital; University of Toronto; Sunnybrook Health Science Centre","funders":"","keywords":"Medicine; Fluid-attenuated inversion recovery; Pattern recognition (psychology); Glioma; Support vector machine; Region of interest; Nuclear medicine; Artificial intelligence; Hyperintensity; Glioblastoma; Linear discriminant analysis; Magnetic resonance imaging; Radiology; Computer science","score_opus":0.01752613372613773,"score_gpt":0.3179540679549516,"score_spread":0.3004279342288139,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3094095883","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7518201,0.00062272226,0.21011926,0.034617886,0.002368901,0.00026895606,0.00006236284,0.00006305278,0.00005677862],"genre_scores_gemma":[0.9769426,0.00017215991,0.009139814,0.005266319,0.008181506,0.000011099795,0.00021335001,0.00005279474,0.000020387048],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980793,0.000174325,0.00079625327,0.00033593443,0.0003321113,0.0002820912],"domain_scores_gemma":[0.99744695,0.0005299542,0.001100159,0.00012718239,0.00049258047,0.00030319698],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028522685,0.00024460384,0.0006551157,0.00014638985,0.000102027785,0.000053808042,0.00042020652,0.00027293735,0.00006530775],"category_scores_gemma":[0.001040595,0.0002181231,0.00040749632,0.00017485803,0.00021005391,0.00022795315,0.000066822366,0.0009737312,0.000011395808],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005128961,0.0012906292,0.22906916,0.00012239326,0.0029476488,0.00093014736,0.0042575984,0.0040686075,0.2767985,0.008300731,0.03178439,0.43530124],"study_design_scores_gemma":[0.06314589,0.011669378,0.03413532,0.0009908756,0.0016320134,0.0021183693,0.0008452925,0.6573363,0.05979009,0.04970401,0.11704232,0.0015901576],"about_ca_topic_score_codex":0.000011754459,"about_ca_topic_score_gemma":9.0975516e-7,"teacher_disagreement_score":0.6532677,"about_ca_system_score_codex":0.00039646038,"about_ca_system_score_gemma":0.0003513969,"threshold_uncertainty_score":0.8894802},"labels":[],"label_agreement":null},{"id":"W3094176091","doi":"10.1016/j.ijrobp.2020.07.793","title":"Altering the Decision Threshold as a Simple and Effective Method for Machine Learning-Based Classification of Imbalanced Radiation Oncology Data","year":2020,"lang":"en","type":"article","venue":"International Journal of Radiation Oncology*Biology*Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre","funders":"","keywords":"Artificial intelligence; Undersampling; Medicine; Random forest; Machine learning; Pairwise comparison; Correlation; Feature (linguistics); Naive Bayes classifier; Linear discriminant analysis; Pattern recognition (psychology); Statistics; Mathematics; Support vector machine; Computer science","score_opus":0.035959563970423776,"score_gpt":0.4096029232437511,"score_spread":0.3736433592733273,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3094176091","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20714599,0.00064199883,0.76689357,0.023778986,0.0007269224,0.00059747597,0.000067826,0.000029436846,0.00011777365],"genre_scores_gemma":[0.96878713,0.00043764323,0.025813088,0.0030417603,0.0014598025,0.000020517402,0.000407693,0.000028447012,0.0000039143197],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981292,0.00038074714,0.00073712814,0.00030857997,0.00027341387,0.00017095626],"domain_scores_gemma":[0.99493915,0.0028860262,0.0013332035,0.00019078217,0.00050460873,0.00014625095],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018121313,0.0001639767,0.00054663257,0.00011489879,0.00010614235,0.000025179112,0.00046890127,0.00018021028,0.00001923402],"category_scores_gemma":[0.0044763475,0.0001235565,0.00014139614,0.00015982619,0.00020608935,0.0001846211,0.00011153275,0.00072076666,0.0000025462214],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022639614,0.00021562223,0.090219654,0.000037916612,0.0004865907,0.000012071059,0.0006801864,0.010664998,0.030964736,0.0033713835,0.000836399,0.8602465],"study_design_scores_gemma":[0.00773573,0.0026593956,0.01726794,0.00005322014,0.00024364992,0.00010317864,0.00009190714,0.90367615,0.0019466025,0.005016811,0.061090223,0.00011517554],"about_ca_topic_score_codex":0.00002220608,"about_ca_topic_score_gemma":0.000002379197,"teacher_disagreement_score":0.89301115,"about_ca_system_score_codex":0.00027738648,"about_ca_system_score_gemma":0.00044287514,"threshold_uncertainty_score":0.5358929},"labels":[],"label_agreement":null},{"id":"W3094422558","doi":"10.1016/j.ijrobp.2020.07.965","title":"Assessment of Clinical Radiosensitivity in Patients with Head-Neck Squamous Cell Carcinoma using Pre-treatment Quantitative Ultrasound Texture-Derivatives and Machine Learning Classifiers","year":2020,"lang":"en","type":"article","venue":"International Journal of Radiation Oncology*Biology*Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; University of Toronto; Sunnybrook Health Science Centre","funders":"","keywords":"Medicine; Head and neck cancer; Radiation therapy; Ultrasound; Head and neck squamous-cell carcinoma; Lymph node; Larynx; Radiology; Pathology; Surgery","score_opus":0.03692210423512948,"score_gpt":0.38163736592621084,"score_spread":0.34471526169108135,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3094422558","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97427976,0.00018901266,0.02368462,0.0011186268,0.0003186053,0.0002417916,0.000023345368,0.000011148911,0.00013305988],"genre_scores_gemma":[0.98239946,0.00013920781,0.016512724,0.0004617909,0.0003885376,0.0000018218093,0.000067484034,0.000023931414,0.0000050457934],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9978239,0.0005665031,0.0008717472,0.0002679336,0.000293985,0.00017596131],"domain_scores_gemma":[0.9968384,0.0011734817,0.0013075923,0.000075396456,0.0004158355,0.00018928385],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005751321,0.00019579116,0.0007786593,0.00012219595,0.000054105574,0.000016384447,0.00011826135,0.00014460465,0.000010142894],"category_scores_gemma":[0.0010436964,0.00015145312,0.00013958731,0.00014611018,0.00037932245,0.00016874733,0.00003675082,0.0008555264,4.4699652e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010634505,0.00078659796,0.9693038,0.000022801467,0.0002398451,0.000045467146,0.0010775046,0.0044733873,0.0027557558,0.00045744778,0.000010863296,0.019763082],"study_design_scores_gemma":[0.012563196,0.006307379,0.87869066,0.000054426167,0.000130802,0.000039572555,0.00015890962,0.101171985,0.00028933608,0.000110911285,0.00036244717,0.000120352044],"about_ca_topic_score_codex":0.000066880406,"about_ca_topic_score_gemma":0.0000035481362,"teacher_disagreement_score":0.0966986,"about_ca_system_score_codex":0.0003997416,"about_ca_system_score_gemma":0.0005453856,"threshold_uncertainty_score":0.6176079},"labels":[],"label_agreement":null},{"id":"W3094442651","doi":"10.1016/j.ijrobp.2020.07.2583","title":"Whole-Body Radiomics for Prediction of Treatment Failure in Cervical Cancer","year":2020,"lang":"en","type":"article","venue":"International Journal of Radiation Oncology*Biology*Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Medicine; Chemoradiotherapy; Confidence interval; Cervical cancer; Radiomics; Radiation treatment planning; Nuclear medicine; Radiology; Radiation therapy; Cancer; Internal medicine","score_opus":0.02189438501143476,"score_gpt":0.3442533235207351,"score_spread":0.32235893850930036,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3094442651","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83862114,0.0005551239,0.08876715,0.06913664,0.0018151174,0.00054354296,0.0003515998,0.000035174773,0.00017453243],"genre_scores_gemma":[0.98818827,0.0006394983,0.0058360067,0.0017631359,0.0033323546,0.000021362865,0.00017194702,0.000024751582,0.000022662918],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986454,0.00009719398,0.00073520263,0.000183162,0.00017548571,0.00016354308],"domain_scores_gemma":[0.9984028,0.0002770682,0.00068662013,0.00007410949,0.00040410293,0.00015535367],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029797805,0.00014077037,0.0005245485,0.00012864606,0.000026882948,0.000010362181,0.00019813268,0.00017808822,0.000036192905],"category_scores_gemma":[0.0004442875,0.00011959804,0.00022708315,0.00014196723,0.00013925556,0.0001253353,0.000023587963,0.00038068346,0.0000026810287],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014913919,0.0006475793,0.7370692,0.000052178126,0.0009579979,0.000034485423,0.0015303149,0.007860933,0.053095624,0.0056800265,0.0035598793,0.18802038],"study_design_scores_gemma":[0.044202633,0.010236967,0.11371799,0.00032896968,0.00071234605,0.00028735085,0.00034380314,0.44170755,0.007511843,0.006604644,0.37398612,0.00035975775],"about_ca_topic_score_codex":0.000028442517,"about_ca_topic_score_gemma":0.000004817119,"teacher_disagreement_score":0.6233512,"about_ca_system_score_codex":0.0008407289,"about_ca_system_score_gemma":0.00064087095,"threshold_uncertainty_score":0.48770663},"labels":[],"label_agreement":null},{"id":"W3094486545","doi":"10.1038/s41598-020-72475-9","title":"Machine learning-based prediction of microsatellite instability and high tumor mutation burden from contrast-enhanced computed tomography in endometrial cancers","year":2020,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":70,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Trillium Health Centre","funders":"National Cancer Institute; Japan Society for the Promotion of Science; Stand Up To Cancer; Cycle for Survival; Uehara Memorial Foundation; Breast Cancer Research Foundation","keywords":"Microsatellite instability; Endometrial cancer; Computed tomography; Contrast (vision); Mutation; Microsatellite; Computer science; Computational biology; Oncology; Internal medicine; Artificial intelligence; Medicine; Bioinformatics; Biology; Radiology; Cancer; Genetics; Gene","score_opus":0.009978434354818428,"score_gpt":0.24259433591604815,"score_spread":0.23261590156122972,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3094486545","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98850965,0.0005256271,0.008216713,0.0006870639,0.0013828044,0.00053271366,0.000027827295,0.0000712715,0.000046335066],"genre_scores_gemma":[0.9970207,0.0000074284885,0.0021791197,0.000114366376,0.00012766702,0.000010260378,0.0005162761,0.000013995537,0.000010142877],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978778,0.00012303458,0.00070040446,0.00064891676,0.0004501194,0.00019973108],"domain_scores_gemma":[0.99886477,0.00016124391,0.00039266105,0.0002207695,0.00015092669,0.00020961896],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010290745,0.00013755239,0.0004273553,0.00029405486,0.00009067415,0.00006373209,0.000053402473,0.000054203625,0.000062007384],"category_scores_gemma":[0.0014987923,0.00012600514,0.000081161306,0.0009691428,0.0003798927,0.00008386751,0.00002930454,0.00037463926,6.1684364e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008297349,0.00012874744,0.36005414,0.00023395618,0.00008357918,0.0005334185,0.0023134318,0.0154485125,0.59025097,0.000005927263,0.00013210502,0.029985474],"study_design_scores_gemma":[0.008839905,0.00064085785,0.22988835,0.00044491913,0.00017236902,0.00006658066,0.00023860722,0.61613137,0.13823771,0.00065842737,0.0043938328,0.0002870727],"about_ca_topic_score_codex":0.0024789213,"about_ca_topic_score_gemma":0.000034371897,"teacher_disagreement_score":0.60068285,"about_ca_system_score_codex":0.000081081074,"about_ca_system_score_gemma":0.00022938427,"threshold_uncertainty_score":0.51383406},"labels":[],"label_agreement":null},{"id":"W3095632729","doi":"10.1177/0846537120968782","title":"Validation of Prognostic Radiomic Features From Resectable Pancreatic Ductal Adenocarcinoma in Patients With Advanced Disease Undergoing Chemotherapy","year":2020,"lang":"en","type":"article","venue":"Canadian Association of Radiologists Journal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University Health Network; Sinai Health System; Lunenfeld-Tanenbaum Research Institute; Mount Sinai Hospital; Ontario Institute for Cancer Research","funders":"Ontario Institute for Cancer Research","keywords":"Medicine; Hazard ratio; Pancreatic ductal adenocarcinoma; Internal medicine; Oncology; Proportional hazards model; Chemotherapy; Confidence interval; Stage (stratigraphy); Multivariate analysis; Adenocarcinoma; Radiology; Pancreatic cancer; Cancer","score_opus":0.00591809272501946,"score_gpt":0.22487773772141045,"score_spread":0.218959644996391,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3095632729","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99377596,0.0005172764,0.0002102157,0.0050100638,0.0000831284,0.00028237258,0.000033378823,0.000009536362,0.00007806638],"genre_scores_gemma":[0.99757195,0.0001095016,0.0014878621,0.0005059405,0.00014238074,0.0000032122803,0.0001203754,0.000020859083,0.00003792572],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9986648,0.00015323564,0.00038445808,0.00018268146,0.0003432693,0.00027157608],"domain_scores_gemma":[0.99841934,0.00024402783,0.0005230239,0.000100642515,0.00018393171,0.00052900665],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031484643,0.0001253864,0.0004181745,0.00019001537,0.000069827096,0.000016878479,0.00011294592,0.000082164355,0.000056726138],"category_scores_gemma":[0.0034469164,0.00010670964,0.000070344075,0.00025180125,0.000069222435,0.00011590344,0.000006479249,0.0004453662,9.5168133e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004688172,0.0000370965,0.99651784,0.000046278255,0.00013729434,0.000065852786,0.00041604217,0.0008768781,0.00031527216,0.000014899637,0.00074998103,0.00035377074],"study_design_scores_gemma":[0.004791698,0.0003739422,0.99354994,0.00023256459,0.00010511207,0.000013041418,0.00006437742,0.0005399161,0.00010629936,0.000084610256,0.000040143328,0.00009832458],"about_ca_topic_score_codex":0.0014302599,"about_ca_topic_score_gemma":0.00040167262,"teacher_disagreement_score":0.0045041232,"about_ca_system_score_codex":0.00077391753,"about_ca_system_score_gemma":0.0010594688,"threshold_uncertainty_score":0.43514928},"labels":[],"label_agreement":null},{"id":"W3095945573","doi":"10.1158/1538-7445.tumhet2020-po-002","title":"Abstract PO-002: Revealing tumour spatial heterogeneity in breast cancer and the impact on clinical management","year":2020,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Health Science Centre; Ontario Institute for Cancer Research","funders":"","keywords":"Breast cancer; Lumpectomy; Tissue microarray; Medicine; Multiplex; Targeted therapy; Pathology; Computational biology; Oncology; Cancer; Biology; Internal medicine; Immunohistochemistry; Bioinformatics; Mastectomy","score_opus":0.09486343455098203,"score_gpt":0.4923034138679561,"score_spread":0.39743997931697406,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3095945573","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91648704,0.0008283352,0.000032026728,0.08116755,0.000097731485,0.0005028985,0.000016969105,0.000017380056,0.0008500574],"genre_scores_gemma":[0.9925296,0.0037787254,0.000034740144,0.0025436752,0.0009521411,0.00007597447,0.0000040325904,0.00002549354,0.000055658937],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99799925,0.0002560657,0.0003349515,0.00039662313,0.00057706604,0.00043602113],"domain_scores_gemma":[0.9989879,0.00031727614,0.000054494936,0.00020136233,0.00007162272,0.00036732745],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026711796,0.000128642,0.0003495936,0.00009094807,0.00011522807,0.00005758211,0.00018614535,0.000059771693,0.0002395182],"category_scores_gemma":[0.00025970023,0.00007489801,0.00010428044,0.0002630013,0.00036329788,0.000034072043,0.00014738429,0.0016043839,0.000015560474],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.009478849,0.0002564972,0.5446361,0.00058639346,0.00041603227,0.0007438925,0.00079463277,0.0017419818,0.0026602591,0.00021835341,0.015459134,0.42300788],"study_design_scores_gemma":[0.0056533134,0.00015054477,0.9807642,0.0005240881,0.000028713352,0.000017396402,0.000102319194,0.011341044,0.00018753773,0.00006612045,0.001057125,0.000107571024],"about_ca_topic_score_codex":0.0069322977,"about_ca_topic_score_gemma":0.000071457696,"teacher_disagreement_score":0.43612814,"about_ca_system_score_codex":0.00018415485,"about_ca_system_score_gemma":0.00016685002,"threshold_uncertainty_score":0.99968064},"labels":[],"label_agreement":null},{"id":"W3096120119","doi":"10.3389/fcvm.2020.591368","title":"Radiomics Signatures of Cardiovascular Risk Factors in Cardiac MRI: Results From the UK Biobank","year":2020,"lang":"en","type":"article","venue":"Frontiers in Cardiovascular Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":60,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Medical Research Council; Horizon 2020 Framework Programme; Circle Cardiovascular Imaging; Servier; European Commission; British Heart Foundation; National Cancer Institute; National Institutes of Health; Ministerio de Economía y Competitividad; Engineering and Physical Sciences Research Council; National Institute for Health and Care Research","keywords":"Medicine; Logistic regression; Receiver operating characteristic; Magnetic resonance imaging; Diabetes mellitus; Radiomics; Internal medicine; Framingham Risk Score; Area under the curve; Cardiology; Random forest; Radiology; Artificial intelligence; Disease; Computer science","score_opus":0.010806077786004219,"score_gpt":0.2309849197470213,"score_spread":0.22017884196101706,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3096120119","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4242766,0.5111344,0.04806804,0.008681803,0.0043001766,0.0019139283,0.00028375472,0.00012463078,0.0012166795],"genre_scores_gemma":[0.97761613,0.014670991,0.0049220636,0.000776675,0.0015848331,0.000021038579,0.00030979989,0.00008531162,0.000013134742],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99464303,0.0009692316,0.0011570299,0.0009903258,0.0016481939,0.0005921869],"domain_scores_gemma":[0.99710846,0.0005434664,0.0002447729,0.0015957681,0.000119254306,0.00038828832],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.004036649,0.00048730584,0.0030097303,0.00032107218,0.00008738971,0.000015484173,0.0005786444,0.0003346607,0.000019818399],"category_scores_gemma":[0.0056895376,0.0003258664,0.002037772,0.0013081434,0.00067220855,0.000073376366,0.00013695749,0.0019576591,0.0000026501932],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010525784,0.000086658336,0.7890761,0.00021049085,0.016649233,0.000657635,0.0106413085,0.07797948,0.0003556749,0.000022343223,0.05503093,0.048237592],"study_design_scores_gemma":[0.028381333,0.0006134683,0.57662284,0.001667214,0.0095534455,0.000021612981,0.008960583,0.03705634,0.0013896707,0.00034203392,0.33431455,0.0010769154],"about_ca_topic_score_codex":0.008553786,"about_ca_topic_score_gemma":0.000009954624,"teacher_disagreement_score":0.55333954,"about_ca_system_score_codex":0.00020970045,"about_ca_system_score_gemma":0.00016319781,"threshold_uncertainty_score":0.99991935},"labels":[],"label_agreement":null},{"id":"W3096788658","doi":"10.7554/elife.61523.sa2","title":"Author response: An interactive meta-analysis of MRI biomarkers of myelin","year":2020,"lang":"en","type":"peer-review","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Montreal Heart Institute; Université de Montréal; Polytechnique Montréal","funders":"","keywords":"Computational biology; Neuroscience; Myelin; Biology; Computer science","score_opus":0.0950694469753289,"score_gpt":0.43162519586190384,"score_spread":0.3365557488865749,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3096788658","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003110758,0.04810024,0.00790681,0.93349767,0.0007559969,0.0011786568,0.0007956684,0.00010037264,0.0073535074],"genre_scores_gemma":[0.016870143,0.0062110894,0.08079822,0.06626028,0.0007035536,0.0001730297,0.008955057,0.00038681756,0.8196418],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99587625,0.0008829015,0.0013758795,0.00066451874,0.0009700386,0.00023043137],"domain_scores_gemma":[0.996083,0.0010039173,0.0010477421,0.00091374584,0.00057605404,0.00037552786],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0031284352,0.00040308473,0.005059328,0.0009512485,0.000024046727,0.000011237618,0.00038951827,0.00023298888,0.009723958],"category_scores_gemma":[0.0053854366,0.0002738122,0.003255651,0.0015326972,0.0002175184,0.000055279736,0.000131996,0.0010036611,0.000013107372],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000731629,0.0001248384,0.0000237376,0.0020045137,0.2844213,0.000048272497,0.0001830797,0.000021222464,0.00050748675,0.000017631393,0.7087323,0.0031839798],"study_design_scores_gemma":[0.0002531466,0.0002934656,0.00020199158,0.00037809223,0.45330867,0.000009111235,0.000077357756,0.008287698,0.00012750141,0.000007262853,0.536888,0.00016766424],"about_ca_topic_score_codex":0.0005332237,"about_ca_topic_score_gemma":0.000024647023,"teacher_disagreement_score":0.8672374,"about_ca_system_score_codex":0.000062410385,"about_ca_system_score_gemma":0.0004078888,"threshold_uncertainty_score":0.9999714},"labels":[],"label_agreement":null},{"id":"W3096889195","doi":"10.1016/j.canlet.2020.10.033","title":"Mini review: Personalization of the radiation therapy management of prostate cancer using MRI-based radiomics","year":2020,"lang":"en","type":"review","venue":"Cancer Letters","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":21,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Trinity College","funders":"Public Health Agency","keywords":"Radiomics; Medicine; Prostate cancer; Radiation therapy; Management of prostate cancer; Guideline; Prostate; Cancer; Population; Medical physics; Intensive care medicine; Radiology; Internal medicine; Pathology","score_opus":0.03411629963051492,"score_gpt":0.36150948896739205,"score_spread":0.3273931893368771,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3096889195","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00012280319,0.9851361,0.0007171503,0.011644424,0.00049363845,0.0018024652,0.00004703096,0.000013813477,0.000022555125],"genre_scores_gemma":[0.00001529218,0.9907393,0.00063337694,0.007987066,0.0002896154,0.00015557333,0.00007128536,0.00006388665,0.0000446409],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99831694,0.0001560922,0.00063595857,0.00030829915,0.0004060692,0.00017664453],"domain_scores_gemma":[0.99856055,0.000040566767,0.00094714377,0.00031972528,0.000061326464,0.000070675145],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024719207,0.00026920444,0.0012330883,0.000087845256,0.000043528435,0.000007936687,0.00022259132,0.00007139418,0.000063828906],"category_scores_gemma":[0.00002899215,0.00017875666,0.0004659496,0.00055430643,0.0001394851,0.000029316016,0.000029729554,0.00034324641,6.3735365e-7],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018310473,0.0000145156955,0.00028643385,0.10132852,0.00046857892,0.000010045154,0.00010198033,0.00027412723,0.00006281874,0.00000671526,0.006317824,0.8911101],"study_design_scores_gemma":[0.00066015177,0.000014565255,0.000042460997,0.10324933,0.0019660206,0.0000062566614,0.000004195822,0.0027022443,0.000027117203,4.7162646e-7,0.89118195,0.00014527183],"about_ca_topic_score_codex":0.00007768123,"about_ca_topic_score_gemma":3.473912e-7,"teacher_disagreement_score":0.89096487,"about_ca_system_score_codex":0.00039340608,"about_ca_system_score_gemma":0.00047215834,"threshold_uncertainty_score":0.7289485},"labels":[],"label_agreement":null},{"id":"W3097077265","doi":"10.1016/j.radonc.2020.10.016","title":"Non-invasive imaging prediction of tumor hypoxia: A novel developed and externally validated CT and FDG-PET-based radiomic signatures","year":2020,"lang":"en","type":"article","venue":"Radiotherapy and Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto","funders":"Interreg; Eurostars; Stichting voor de Technische Wetenschappen; Horizon 2020 Framework Programme; Nederlandse Organisatie voor Wetenschappelijk Onderzoek","keywords":"Medicine; Radiomics; Hypoxia (environmental); Confidence interval; Tumor hypoxia; Nuclear medicine; Radiology; Radiation therapy; Internal medicine","score_opus":0.01419785153126344,"score_gpt":0.2840432906275348,"score_spread":0.26984543909627134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3097077265","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96826214,0.003789838,0.018601585,0.008654351,0.00012874212,0.0003703156,0.000016272877,0.000052640415,0.00012411729],"genre_scores_gemma":[0.96628314,0.0011696855,0.023354387,0.008878768,0.00022537005,0.000012294421,0.000018865996,0.000035563076,0.000021941902],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988309,0.000069345435,0.0003407766,0.0003849774,0.0001443331,0.00022967489],"domain_scores_gemma":[0.9991096,0.00028443715,0.00017373313,0.00010235902,0.00005642509,0.00027344798],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030863768,0.00020002248,0.00057556643,0.00013018803,0.00009017457,0.000024098648,0.000069971895,0.000046668487,0.00002915668],"category_scores_gemma":[0.00020705456,0.000169948,0.000047147583,0.00014021066,0.00034645625,0.00007236155,0.000026857464,0.00040638022,2.982499e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010644449,0.00014356639,0.06916185,0.00037222347,0.00023504542,0.0007397458,0.0011956259,0.00009600623,0.88807005,0.000078493904,0.000773077,0.038069874],"study_design_scores_gemma":[0.04068988,0.0040300568,0.31126443,0.0007321064,0.0005805691,0.0076734335,0.00046811253,0.57438165,0.026662024,0.000117958676,0.032711986,0.00068781205],"about_ca_topic_score_codex":0.000059473445,"about_ca_topic_score_gemma":0.0000039834385,"teacher_disagreement_score":0.86140805,"about_ca_system_score_codex":0.00008583064,"about_ca_system_score_gemma":0.00029622822,"threshold_uncertainty_score":0.69302785},"labels":[],"label_agreement":null},{"id":"W3097588083","doi":"10.1177/0846537120967349","title":"Canadian Association of Radiologists White Paper on De-Identification of Medical Imaging: Part 1, General Principles","year":2020,"lang":"en","type":"article","venue":"Canadian Association of Radiologists Journal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Carleton University; Northern Alberta Institute of Technology; Western University; University of Toronto; University of Ottawa; McGill University Health Centre; BitCan (Canada); University of Alberta; Fraser Health; Université Laval; Université de Montréal; University of British Columbia","funders":"","keywords":"Medicine; Identification (biology); Mandate; Protected health information; Identifier; Health Insurance Portability and Accountability Act; Health care; Best practice; Patient safety; Artificial intelligence; Computer security; Computer science; Confidentiality; Nursing; Health policy; Public health","score_opus":0.015789399319791852,"score_gpt":0.2775507282312287,"score_spread":0.2617613289114369,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3097588083","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.69633687,0.0005522166,0.001646623,0.29491743,0.0012946439,0.00043339844,0.00022809423,0.000040204075,0.00455053],"genre_scores_gemma":[0.99157816,0.00062887336,0.00050708634,0.0053561954,0.00085284014,0.0000047585427,0.00010235845,0.000026991038,0.00094272976],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99640495,0.00051089784,0.0012054867,0.00026586166,0.0010022116,0.0006105956],"domain_scores_gemma":[0.99560356,0.00029829057,0.0017346175,0.00019877455,0.0005705299,0.0015941994],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0048734928,0.0001900254,0.0006729624,0.0004060445,0.00014339518,0.000037500922,0.00037956412,0.00040497084,0.00041963282],"category_scores_gemma":[0.016449511,0.0001798117,0.00024477683,0.00032875026,0.00013061088,0.00010785675,0.000017723221,0.0010072271,0.00000780069],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000040567185,0.00003614634,0.91500187,0.00006153529,0.00027142654,0.00008528142,0.0006675033,0.0014179723,0.001225012,0.00091987144,0.075850785,0.0044220444],"study_design_scores_gemma":[0.0026296778,0.00027700793,0.8550123,0.0002584488,0.00024146657,0.00024385462,0.0002699331,0.037302956,0.00042094607,0.00019997082,0.102849364,0.00029404872],"about_ca_topic_score_codex":0.049031373,"about_ca_topic_score_gemma":0.058015,"teacher_disagreement_score":0.2952413,"about_ca_system_score_codex":0.004132135,"about_ca_system_score_gemma":0.0043141055,"threshold_uncertainty_score":0.99969083},"labels":[],"label_agreement":null},{"id":"W3097686141","doi":"10.1177/0846537120967345","title":"Canadian Association of Radiologists White Paper on De-identification of Medical Imaging: Part 2, Practical Considerations","year":2020,"lang":"en","type":"article","venue":"Canadian Association of Radiologists Journal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Carleton University; Northern Alberta Institute of Technology; Western University; University of Toronto; University of Ottawa; McGill University Health Centre; BitCan (Canada); University of Alberta; Fraser Health; Université Laval; Université de Montréal; University of British Columbia","funders":"","keywords":"Medicine; Identification (biology); Mandate; Best practice; White paper; Big data; Health care; Medical education; Artificial intelligence; Computer science; Data mining","score_opus":0.019140615801324673,"score_gpt":0.3071851015438825,"score_spread":0.2880444857425578,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3097686141","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16738586,0.0003380956,0.0032072763,0.8216815,0.0012368872,0.0005172454,0.00023945498,0.000042268584,0.005351401],"genre_scores_gemma":[0.9890311,0.00038257055,0.000867599,0.008722221,0.0005810799,0.000005359051,0.00007622959,0.000022933236,0.00031090926],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99632293,0.00066842575,0.0012154095,0.0002563767,0.0009865487,0.0005503234],"domain_scores_gemma":[0.99482834,0.0009113497,0.0016513143,0.00019204475,0.0007790674,0.0016378897],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005031276,0.00017625072,0.000643338,0.0003838693,0.00018674038,0.000050624512,0.00017203497,0.0004228542,0.0008452253],"category_scores_gemma":[0.048006922,0.00017050354,0.00021665446,0.00029598997,0.00016079258,0.00015199876,0.000013617778,0.0012337025,0.000011667512],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000045366614,0.00006859853,0.7010955,0.000058074707,0.0003638216,0.0002365222,0.0009092462,0.0005693052,0.0010394913,0.0029546346,0.29091924,0.0017401815],"study_design_scores_gemma":[0.0061782734,0.0006890366,0.8183909,0.00050991663,0.00076732424,0.0019109971,0.0011048941,0.04500579,0.0007209526,0.0017975175,0.12229481,0.00062956766],"about_ca_topic_score_codex":0.031888463,"about_ca_topic_score_gemma":0.05546472,"teacher_disagreement_score":0.82164526,"about_ca_system_score_codex":0.0034545988,"about_ca_system_score_gemma":0.007106634,"threshold_uncertainty_score":0.99852216},"labels":[],"label_agreement":null},{"id":"W3097966505","doi":"10.21105/joss.02705","title":"DeepReg: a deep learning toolkit for medical image registration","year":2020,"lang":"en","type":"article","venue":"The Journal of Open Source Software","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Wellcome / EPSRC Centre for Interventional and Surgical Sciences; Wellcome Trust; Royal Academy of Engineering; Engineering and Physical Sciences Research Council; National Institute for Health and Care Research; University College London","keywords":"Deep learning; Computer science; Image registration; Artificial intelligence; Open source; Image (mathematics); Computer vision; Software","score_opus":0.021512808260027275,"score_gpt":0.32708708883488874,"score_spread":0.30557428057486147,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3097966505","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07976013,0.0006229213,0.8433985,0.074933626,0.000115982264,0.0004528199,8.9048416e-7,0.00004722281,0.0006678955],"genre_scores_gemma":[0.89909464,0.00032837235,0.08029637,0.016461482,0.002214562,0.000010883202,0.000019092658,0.00010880434,0.0014658138],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983346,0.00017562234,0.0005227338,0.0001272954,0.00062757416,0.00021218948],"domain_scores_gemma":[0.9980885,0.00064520637,0.00045524546,0.00015229221,0.0002475109,0.00041129376],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0023874089,0.00012464993,0.00038870174,0.000038326318,0.00022509103,0.00013823257,0.000707184,0.00007769283,0.00030996487],"category_scores_gemma":[0.013198293,0.00007806924,0.00015831912,0.00014656225,0.00013265442,0.0002224003,0.00016950574,0.0010894748,0.000012129936],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0059491037,0.00030253796,0.027417613,0.00065654115,0.00078007614,0.00055514055,0.022804735,0.0045603667,0.0052340077,0.00027714856,0.08026721,0.8511955],"study_design_scores_gemma":[0.016721517,0.0046017845,0.007448565,0.0016054059,0.0014930384,0.0071554817,0.007529543,0.14888306,0.00085112685,0.001197149,0.80187285,0.00064046995],"about_ca_topic_score_codex":0.000018144845,"about_ca_topic_score_gemma":0.0000016543215,"teacher_disagreement_score":0.85055506,"about_ca_system_score_codex":0.000036586738,"about_ca_system_score_gemma":0.00022974171,"threshold_uncertainty_score":0.99511397},"labels":[],"label_agreement":null},{"id":"W3099167474","doi":"10.1055/a-1306-7590","title":"Establishing key research questions for the implementation of artificial intelligence in colonoscopy: a modified Delphi method","year":2020,"lang":"en","type":"article","venue":"Endoscopy","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":69,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vancouver General Hospital; University of British Columbia","funders":"Vlaamse regering; Fonds Wetenschappelijk Onderzoek; Royal Society; University College London; Wellcome Trust; Engineering and Physical Sciences Research Council; National Institute for Health and Care Research; Wellcome / EPSRC Centre for Interventional and Surgical Sciences; Boston Scientific Corporation","keywords":"Workflow; Colonoscopy; Medicine; Delphi method; Delphi; Theme (computing); Computer science; Artificial intelligence; Data science; Database; Colorectal cancer; World Wide Web","score_opus":0.11841102258718253,"score_gpt":0.49158356659903746,"score_spread":0.37317254401185496,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3099167474","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12371862,0.00022682823,0.84151965,0.03317083,0.00015109309,0.0009920067,0.0000119794695,0.00002830116,0.00018070475],"genre_scores_gemma":[0.871274,0.00005706782,0.12769192,0.0005937444,0.00021992982,0.00012134987,0.000016181195,0.000016054804,0.000009733359],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99866,0.00020295168,0.00036771197,0.00021271549,0.00029943258,0.00025713188],"domain_scores_gemma":[0.997659,0.0018801345,0.0000750288,0.00014764222,0.00013520905,0.00010293589],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022036433,0.000075245436,0.00019983054,0.00012571165,0.00012174961,0.000038964175,0.00016892389,0.000041575764,0.000059782753],"category_scores_gemma":[0.0032241505,0.000057854246,0.00005145951,0.00051605946,0.00010019746,0.000075791344,0.000051392024,0.0005088117,0.0000031400514],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0031280348,0.00038403238,0.011992638,0.00072798895,0.0002132703,0.000044760327,0.053136725,0.013094853,0.1813466,0.14988106,0.005917554,0.5801325],"study_design_scores_gemma":[0.0010110701,0.0010252835,0.002475652,0.00017885523,0.00008995469,0.000003941545,0.012130287,0.9174463,0.05315556,0.007938032,0.0044138273,0.00013123735],"about_ca_topic_score_codex":0.0012576416,"about_ca_topic_score_gemma":0.000093837705,"teacher_disagreement_score":0.9043515,"about_ca_system_score_codex":0.000055673947,"about_ca_system_score_gemma":0.00020562556,"threshold_uncertainty_score":0.3859842},"labels":[],"label_agreement":null},{"id":"W3105896181","doi":"10.1503/cmaj.200831-f","title":"Découverte fortuite d’un cas de COVID-19 par TEP-TDM","year":2020,"lang":"fr","type":"article","venue":"Canadian Medical Association Journal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Centre hospitalier universitaire de Québec; SickKids Foundation; SKiN Health; North York General Hospital","funders":"","keywords":"Coronavirus disease 2019 (COVID-19); Medicine; Human immunodeficiency virus (HIV); Humanities; Gynecology; Philosophy; Virology; Internal medicine","score_opus":0.011407886694542917,"score_gpt":0.2782205239366947,"score_spread":0.2668126372421518,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3105896181","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029292276,0.007636547,0.013958858,0.9382592,0.005580626,0.0002523077,0.00007103051,0.00006742147,0.0048817755],"genre_scores_gemma":[0.35889757,0.0044946736,0.0015013753,0.6047893,0.026111975,0.000009690419,0.000049445312,0.00010825479,0.004037688],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9935946,0.000762951,0.0010135197,0.0004155669,0.0023648783,0.001848485],"domain_scores_gemma":[0.9738608,0.00075720606,0.0004911716,0.00017389959,0.0003266119,0.024390314],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0054372107,0.0003465265,0.00069690705,0.00022601707,0.000865095,0.0002432301,0.00052698184,0.0010315509,0.02640689],"category_scores_gemma":[0.048803348,0.00035069048,0.00035312935,0.00056248653,0.00024325521,0.00020129529,0.000054230597,0.0053581377,0.00070559303],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000023947814,0.000046266105,0.17228042,0.00013596377,0.00044793473,0.0101407515,0.0031259242,0.00010676344,0.00002700439,0.00054320024,0.6601536,0.15296821],"study_design_scores_gemma":[0.0031188468,0.00018272392,0.016312663,0.00029680264,0.0003198023,0.0038581707,0.0009705242,0.052273206,0.000009949771,0.0004970874,0.92182904,0.00033119228],"about_ca_topic_score_codex":0.014751776,"about_ca_topic_score_gemma":0.008093693,"teacher_disagreement_score":0.33346984,"about_ca_system_score_codex":0.0066592162,"about_ca_system_score_gemma":0.025387274,"threshold_uncertainty_score":0.9998945},"labels":[],"label_agreement":null},{"id":"W3106980535","doi":"10.1594/ranzcr2011/r-0108","title":"Pictorial Review of Normal Pericardial Recesses and Their Potential to Simulate Pathology","year":2011,"lang":"en","type":"article","venue":"European Society of Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hamilton Health Sciences","funders":"","keywords":"Anatomy; Pathology; Medicine","score_opus":0.014802880184382895,"score_gpt":0.2604255144368423,"score_spread":0.24562263425245942,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3106980535","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95722014,0.012874369,0.010055939,0.0032305128,0.0013688131,0.0004467132,0.000020813633,0.00006356686,0.014719119],"genre_scores_gemma":[0.9700806,0.013184589,0.011868135,0.0039196904,0.00081924314,0.0000017498446,0.000019038998,0.00003079359,0.00007611866],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988355,0.00031845344,0.0003543595,0.00021920764,0.00008163504,0.00019086487],"domain_scores_gemma":[0.9993592,0.000072943774,0.00014947362,0.00020250032,0.000090967216,0.00012489823],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00086939224,0.0001221042,0.00056427997,0.000026662312,0.000035764962,0.0000017974494,0.00012042735,0.00005270983,0.000103507584],"category_scores_gemma":[0.0002811348,0.00009196033,0.00021247183,0.00006971842,0.00040550876,0.000024419556,0.00011228688,0.000247631,0.0000052385135],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022269355,0.00086110696,0.052692026,0.017334376,0.0023857232,0.0006518307,0.05584115,0.00009818072,0.28300887,0.0015135693,0.25012863,0.3332576],"study_design_scores_gemma":[0.014764621,0.011285241,0.34615898,0.0076888506,0.0015578608,0.008494409,0.0023449857,0.0025229214,0.005434075,0.00040205158,0.5977928,0.0015531646],"about_ca_topic_score_codex":0.000010423991,"about_ca_topic_score_gemma":4.0847922e-8,"teacher_disagreement_score":0.3476642,"about_ca_system_score_codex":0.00000857757,"about_ca_system_score_gemma":0.0000320145,"threshold_uncertainty_score":0.37500337},"labels":[],"label_agreement":null},{"id":"W3107459492","doi":"10.22215/etd/2020-14090","title":"Deep Learning Methods for Abnormality Detection and Segmentation in Computed Tomography and Magnetic Resonance Images","year":2020,"lang":"en","type":"dissertation","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Segmentation; Artificial intelligence; Magnetic resonance imaging; Coronal plane; Computer science; Convolutional neural network; Deep learning; Voxel; Effective diffusion coefficient; Sagittal plane; Pattern recognition (psychology); Steady-state free precession imaging; Radiology; Nuclear medicine; Medicine","score_opus":0.008813721858961654,"score_gpt":0.336678448341995,"score_spread":0.32786472648303333,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3107459492","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.471073,0.03801767,0.48409867,0.001060566,0.00057675614,0.002332786,0.0000029935795,0.00025614953,0.002581412],"genre_scores_gemma":[0.39720452,0.0024410493,0.59740627,0.0006037671,0.00019351805,0.00010838352,0.0006924823,0.0000847934,0.0012652278],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988674,0.00015718197,0.00030822208,0.00038461317,0.000114910625,0.00016766136],"domain_scores_gemma":[0.9993839,0.000253785,0.00011498222,0.00006654412,0.000066589026,0.00011414948],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00053085206,0.00018390382,0.00037590959,0.0001762472,0.00009579981,0.000051155926,0.00003303988,0.00014529274,0.000014082163],"category_scores_gemma":[0.00034657316,0.00017478756,0.00005542816,0.00022190744,0.000045782555,0.00006570328,0.000014721528,0.00058222516,3.012072e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029478423,0.000019501147,0.009811355,0.0008746004,0.000019006122,0.000007714651,0.0008784296,0.000019981166,0.015384896,0.00003120681,0.000014842606,0.9726437],"study_design_scores_gemma":[0.002914111,0.0006957143,0.44277933,0.000387192,0.00023882504,0.000053649357,0.0014597238,0.5413118,0.005859533,0.00035921752,0.003616158,0.00032473163],"about_ca_topic_score_codex":0.00011930222,"about_ca_topic_score_gemma":0.000049167433,"teacher_disagreement_score":0.97231895,"about_ca_system_score_codex":0.00002548396,"about_ca_system_score_gemma":0.00002048657,"threshold_uncertainty_score":0.712763},"labels":[],"label_agreement":null},{"id":"W3110759004","doi":"10.1002/alz.041150","title":"Reliability assessment of tissue classification algorithms for multi‐center and multi‐scanner data","year":2020,"lang":"en","type":"article","venue":"Alzheimer s & Dementia","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Kappa; Segmentation; Artificial intelligence; Scanner; Pattern recognition (psychology); Dice; Computer science; Nuclear medicine; Mathematics; Cartography; Algorithm; Medicine; Statistics; Geography; Geometry","score_opus":0.1239308809581636,"score_gpt":0.408638995087604,"score_spread":0.2847081141294404,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3110759004","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.034559086,0.017990347,0.9181088,0.02504397,0.0006681086,0.0028107,0.00031402195,0.00014981873,0.0003551514],"genre_scores_gemma":[0.6709325,0.00006228351,0.32753217,0.0008383034,0.00010383436,0.00002114836,0.00048299873,0.000019804807,0.000006988264],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99873936,0.00004768759,0.00036636306,0.00046547782,0.00019918986,0.00018190307],"domain_scores_gemma":[0.9990516,0.0000566746,0.00013899199,0.00045837357,0.00010368882,0.00019067628],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004323764,0.00012917946,0.00027031082,0.000031330357,0.000060933555,0.00001930142,0.00018920958,0.000056986068,0.000050955066],"category_scores_gemma":[0.00023676667,0.000110117595,0.000039902483,0.00007560637,0.000114237424,0.00011967972,0.00016521952,0.00018888121,0.0000031958355],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001608506,0.0015570024,0.1969687,0.0003399043,0.0076275878,0.000011863637,0.00088314817,0.000035237204,0.047838975,0.00036693425,0.020618333,0.72359145],"study_design_scores_gemma":[0.0031927067,0.00015224796,0.10581564,0.000028999355,0.0041972063,0.000004717592,0.00007640456,0.82563764,0.0011787516,0.0000070169813,0.059584443,0.00012420538],"about_ca_topic_score_codex":0.000058167436,"about_ca_topic_score_gemma":0.000002811313,"teacher_disagreement_score":0.8256024,"about_ca_system_score_codex":0.000004844784,"about_ca_system_score_gemma":0.000057098183,"threshold_uncertainty_score":0.44904652},"labels":[],"label_agreement":null},{"id":"W3111168043","doi":"10.1093/neuonc/noaa215.649","title":"NIMG-36. AUTOMATIC STRATIFICATION OF ENHANCING AND NON-ENHANCING GLIOMAS INTO GENETIC SUBTYPES USING DEEP NEURAL NETWORKS AND DIFFUSION-WEIGHTED IMAGING","year":2020,"lang":"en","type":"article","venue":"Neuro-Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network","funders":"","keywords":"Fluid-attenuated inversion recovery; Nuclear medicine; Medicine; Wild type; Magnetic resonance imaging; Mutant; Radiology; Biology; Genetics; Gene","score_opus":0.008937830575716326,"score_gpt":0.2789556554477138,"score_spread":0.27001782487199744,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3111168043","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91720057,0.0010819534,0.077513985,0.003490651,0.00024302455,0.00032050096,3.6182695e-7,0.000067237626,0.000081724866],"genre_scores_gemma":[0.98334014,0.00013350669,0.0142611535,0.0019099086,0.00030059332,0.0000057469388,0.0000071565673,0.00004055783,0.000001246965],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982888,0.00016815754,0.0005884912,0.00044838432,0.00019579299,0.0003103667],"domain_scores_gemma":[0.9986883,0.00044911954,0.00029352252,0.000179458,0.00008266947,0.00030697562],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024601063,0.00020948757,0.00054957997,0.00014447216,0.00015524769,0.00003619641,0.00009609967,0.00011429108,0.000025717649],"category_scores_gemma":[0.0005299102,0.00019311302,0.000050633127,0.0002880039,0.00023514699,0.000098920194,0.000128799,0.000526673,0.0000011654182],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008147755,0.000040891893,0.01772679,0.00025614942,0.000022579703,0.00015589267,0.0018504017,0.00062279234,0.8486714,0.000011389452,0.00001656281,0.13054371],"study_design_scores_gemma":[0.0012652903,0.00035853471,0.015360616,0.00008776761,0.00017974319,0.00040628517,0.00038693307,0.9748754,0.0067577674,0.000060845832,0.00011611231,0.00014470541],"about_ca_topic_score_codex":0.00010043285,"about_ca_topic_score_gemma":0.000025538948,"teacher_disagreement_score":0.9742526,"about_ca_system_score_codex":0.00006262868,"about_ca_system_score_gemma":0.000102277074,"threshold_uncertainty_score":0.7874921},"labels":[],"label_agreement":null},{"id":"W3111444730","doi":"10.1093/neuonc/noaa222.348","title":"IMG-13. MRI-BASED RADIOMICS PROGNOSTIC MARKERS OF POSTERIOR FOSSA EPENDYMOMA","year":2020,"lang":"en","type":"article","venue":"Neuro-Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; Hospital for Sick Children","funders":"","keywords":"Ependymoma; Medicine; Concordance; Radiomics; Magnetic resonance imaging; Radiology; Artificial intelligence; Internal medicine; Computer science","score_opus":0.016532222824277673,"score_gpt":0.29395882249949284,"score_spread":0.27742659967521516,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3111444730","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9129671,0.0001863497,0.0024133709,0.07870369,0.00069162244,0.0007477931,0.000012153218,0.00014527007,0.004132653],"genre_scores_gemma":[0.96765524,0.000034122928,0.0062850337,0.025509514,0.00036941684,0.000024852157,0.00003267199,0.000064220214,0.000024910136],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980896,0.00023465346,0.0005339859,0.0004437665,0.00029647793,0.0004014991],"domain_scores_gemma":[0.99825096,0.00063930015,0.0002550482,0.0002825524,0.00010045021,0.00047165935],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003195035,0.00021950297,0.00070457475,0.0001247567,0.000058246285,0.000013638641,0.00023603356,0.00018385882,0.00024931444],"category_scores_gemma":[0.002495455,0.00019962653,0.00018375838,0.00028039556,0.00029098507,0.000043697553,0.00009501067,0.00076300616,0.000042588355],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0043224604,0.0006149198,0.06284988,0.0007899535,0.00020006421,0.0073314775,0.0008773867,0.00048095436,0.6855777,0.00012328055,0.018849133,0.21798278],"study_design_scores_gemma":[0.027072275,0.024375776,0.058622498,0.00037702578,0.001310727,0.0062137605,0.00047525324,0.3631127,0.035148486,0.000116439,0.48217797,0.0009971022],"about_ca_topic_score_codex":0.000033867756,"about_ca_topic_score_gemma":0.0000029038622,"teacher_disagreement_score":0.65042925,"about_ca_system_score_codex":0.000092645234,"about_ca_system_score_gemma":0.00056097313,"threshold_uncertainty_score":0.81405336},"labels":[],"label_agreement":null},{"id":"W3111804892","doi":"10.1093/neuonc/noaa222.346","title":"IMG-10. MRI-BASED RADIOMIC PROGNOSTIC MARKERS OF DIFFUSE MIDLINE GLIOMA","year":2020,"lang":"en","type":"article","venue":"Neuro-Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Medicine; Radiomics; Gray level; Proportional hazards model; Concordance; Artificial intelligence; Radiology; Nuclear medicine; Internal medicine; Computer science; Image (mathematics)","score_opus":0.016125506266176086,"score_gpt":0.2940524861700402,"score_spread":0.2779269799038641,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3111804892","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9182127,0.000244194,0.002165398,0.07544785,0.00047572804,0.00063419767,0.000009432986,0.00017215202,0.0026383223],"genre_scores_gemma":[0.97946495,0.000045868903,0.004709174,0.015130796,0.0004667191,0.000027098506,0.000046000543,0.000066517074,0.000042864936],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980567,0.00024852031,0.00053933664,0.00045232478,0.0003073255,0.00039578107],"domain_scores_gemma":[0.99794996,0.00091448677,0.00024156192,0.00029503476,0.00010163839,0.00049730367],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029653092,0.00022422014,0.0007151018,0.00016885888,0.00005273964,0.000010146985,0.00023040839,0.0001712275,0.00057914597],"category_scores_gemma":[0.003461128,0.00019684432,0.00018528421,0.00039964577,0.00032494793,0.000035731566,0.00007636368,0.0006901801,0.0000744994],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0026834665,0.00072580087,0.019699119,0.000390426,0.000106963016,0.0023774123,0.0002672347,0.0002854526,0.909974,0.00006898255,0.036088046,0.027333096],"study_design_scores_gemma":[0.025106644,0.011835382,0.012170218,0.00018820904,0.00079487544,0.0009832118,0.00013743396,0.32684076,0.034676846,0.000052834184,0.5866872,0.00052638294],"about_ca_topic_score_codex":0.000018998855,"about_ca_topic_score_gemma":0.0000012445669,"teacher_disagreement_score":0.8752971,"about_ca_system_score_codex":0.00009034302,"about_ca_system_score_gemma":0.0004432423,"threshold_uncertainty_score":0.80270785},"labels":[],"label_agreement":null},{"id":"W3112138507","doi":"10.1002/cam4.3634","title":"Quantitative ultrasound radiomics in predicting recurrence for patients with node‐positive head‐neck squamous cell carcinoma treated with radical radiotherapy","year":2020,"lang":"en","type":"article","venue":"Cancer Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; University of Toronto; Institute for Clinical Evaluative Sciences; Sunnybrook Health Science Centre","funders":"National Center for Advancing Translational Sciences; Terry Fox Foundation","keywords":"Medicine; Radiation therapy; Radiomics; Lymph node; Head and neck squamous-cell carcinoma; Ultrasound; Basal cell; Head and neck; Radiology; Nuclear medicine; Head and neck cancer; Surgery; Internal medicine","score_opus":0.016061364589901702,"score_gpt":0.2987194785969758,"score_spread":0.2826581140070741,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3112138507","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9762527,0.002618239,0.010360551,0.008459489,0.00015265208,0.0016332048,0.00008101688,0.00007979066,0.00036239755],"genre_scores_gemma":[0.9856171,0.00022631619,0.008491021,0.0045296587,0.0005282265,0.00015177789,0.00031051793,0.00009933953,0.000046032972],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99756426,0.000097466655,0.00050591934,0.0007191139,0.00054816576,0.000565053],"domain_scores_gemma":[0.997923,0.0007574377,0.0002581954,0.00023360865,0.0002621228,0.0005656434],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00025292212,0.00040269166,0.0009129183,0.00016468951,0.00012346628,0.000017657194,0.0001790691,0.00011666967,0.000077922974],"category_scores_gemma":[0.00072302937,0.00026929207,0.00006376319,0.0006710093,0.0005872576,0.000116812465,0.000014224222,0.000755063,0.000001159781],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.009116835,0.00030431242,0.9747016,0.00048982905,0.00010302518,0.00012881782,0.006572246,0.0005153973,0.002342962,0.000049390612,0.001708687,0.0039669364],"study_design_scores_gemma":[0.11928382,0.037543572,0.68765295,0.0040575317,0.0010774682,0.00013802444,0.0021104624,0.13853924,0.0017639286,0.000022407474,0.006555177,0.0012554461],"about_ca_topic_score_codex":0.00059982075,"about_ca_topic_score_gemma":0.000029346962,"teacher_disagreement_score":0.28704864,"about_ca_system_score_codex":0.00037755608,"about_ca_system_score_gemma":0.00032774857,"threshold_uncertainty_score":0.9999759},"labels":[],"label_agreement":null},{"id":"W3113058170","doi":"10.1177/0840470420975062","title":"Artificial intelligence-based imaging analytics and lung cancer diagnostics: Considerations for health system leaders","year":2020,"lang":"en","type":"article","venue":"Healthcare Management Forum","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Saskatoon Medical Imaging; University of Saskatchewan; University of Regina; Saskatchewan Health Authority; Saskatoon City Hospital; Royal University Hospital","funders":"Saskatchewan Health Research Foundation","keywords":"Health care; Analytics; Business intelligence; Knowledge management; Big data; Healthcare system; Business; Data science; Medicine; Computer science; Political science; Data mining","score_opus":0.058220291691714346,"score_gpt":0.37515683112051673,"score_spread":0.3169365394288024,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3113058170","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006777835,0.0033503354,0.287588,0.706311,0.0002820114,0.0014597984,0.00003470586,0.00015047716,0.00014591994],"genre_scores_gemma":[0.9055492,0.0006400873,0.013600228,0.07966073,0.00027031833,0.00016482029,0.000048400634,0.000039544473,0.000026615937],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983109,0.000057130383,0.00050251256,0.00039412585,0.00024250247,0.0004927982],"domain_scores_gemma":[0.99890906,0.00023818806,0.00014057074,0.00016413363,0.0000909536,0.00045707996],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003364366,0.00016891336,0.00036090153,0.0001362717,0.0003718393,0.00006704014,0.000056375193,0.000035639117,0.000018606243],"category_scores_gemma":[0.0002684903,0.00016405463,0.00007634864,0.00017791273,0.000106701045,0.000043154123,0.0000457741,0.0002570529,0.0000025962631],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032903487,0.00016458063,0.09999271,0.033879198,0.00052499195,0.00030636977,0.0029987355,0.006297223,0.000015880249,0.24520753,0.1396396,0.47064415],"study_design_scores_gemma":[0.00047151596,0.00018768366,0.00064761454,0.00090541854,0.00020238756,0.0000105656,0.006702064,0.9808131,0.000029796254,0.0006673384,0.009179354,0.00018316277],"about_ca_topic_score_codex":0.00028274284,"about_ca_topic_score_gemma":0.00007757582,"teacher_disagreement_score":0.97451586,"about_ca_system_score_codex":0.00022186602,"about_ca_system_score_gemma":0.00020845835,"threshold_uncertainty_score":0.6689954},"labels":[],"label_agreement":null},{"id":"W3116382769","doi":"10.2967/jnmt.120.261890","title":"Guidelines on Setting Up Stations for Remote Viewing of Nuclear Medicine and Molecular Imaging Studies During COVID-19","year":2020,"lang":"en","type":"article","venue":"Journal of Nuclear Medicine Technology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Coronavirus disease 2019 (COVID-19); Nuclear medicine imaging; 2019-20 coronavirus outbreak; Pandemic; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Medical physicist; Medicine; Medical imaging; Process (computing); Medical physics; Nuclear medicine; Computer science; Radiology; Pathology; Infectious disease (medical specialty)","score_opus":0.07011067464718969,"score_gpt":0.4154801424905617,"score_spread":0.345369467843372,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3116382769","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2547239,0.0062399236,0.0034101629,0.734785,0.00028931865,0.00027578062,0.0000021201568,0.000108197,0.00016554956],"genre_scores_gemma":[0.8683711,0.0036868711,0.046860114,0.07988945,0.0010411052,0.0000017556163,0.0000035447235,0.00012628218,0.00001975928],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975526,0.000061311206,0.001296526,0.0003014446,0.00048250044,0.0003056186],"domain_scores_gemma":[0.99738795,0.00037731082,0.00091173354,0.00022861091,0.0006914917,0.00040293502],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0012545112,0.00024193761,0.0011144216,0.0007681623,0.00020585125,0.000006334743,0.00023920278,0.00010744046,0.000053306234],"category_scores_gemma":[0.032312743,0.00017509109,0.000116001145,0.00047575522,0.0008526195,0.00007729429,0.000118341195,0.0008333732,0.0000013528397],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0020129432,0.000116022304,0.0028384535,0.005023497,0.001631483,0.0020893319,0.027474927,0.0005934735,0.6513512,0.011688416,0.19901013,0.09617013],"study_design_scores_gemma":[0.038146425,0.0115778865,0.0009993605,0.015786078,0.0031300026,0.008650706,0.100566536,0.08925416,0.0013716252,0.017681118,0.7119699,0.00086621474],"about_ca_topic_score_codex":0.000015167256,"about_ca_topic_score_gemma":2.416995e-7,"teacher_disagreement_score":0.6548956,"about_ca_system_score_codex":0.00010921023,"about_ca_system_score_gemma":0.000092965754,"threshold_uncertainty_score":0.9758385},"labels":[],"label_agreement":null},{"id":"W3116666987","doi":"10.1016/j.neuroimage.2021.117890","title":"Translating amyloid PET of different radiotracers by a deep generative model for interchangeability","year":2021,"lang":"en","type":"article","venue":"NeuroImage","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Janssen Research and Development; National Institute on Aging; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; University of California, San Diego; Genentech; IXICO; H. Lundbeck A/S; Eisai; Johnson and Johnson; National Research Foundation of Korea; National Institutes of Health; Ministry of Science, ICT and Future Planning; Ministry of Food and Drug Safety; Ministry of Trade, Industry and Energy; Northern California Institute for Research and Education; Ministry of Health and Welfare; Biogen; BioClinica; Eli Lilly and Company; U.S. Department of Defense; GE Healthcare; Alzheimer's Disease Neuroimaging Initiative; University of Southern California; Bristol-Myers Squibb; F. Hoffmann-La Roche; Merck; Alzheimer's Drug Discovery Foundation; AbbVie; Fujirebio Europe; Alzheimer's Association","keywords":"Interchangeability; Discriminator; Neuroimaging; Artificial intelligence; Generative model; Nuclear medicine; Computer science; Generative adversarial network; Positron emission tomography; Pattern recognition (psychology); Deep learning; Medicine; Neuroscience; Generative grammar; Psychology","score_opus":0.02750209960231059,"score_gpt":0.30942162644713456,"score_spread":0.28191952684482396,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3116666987","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6883811,0.0002577913,0.30625665,0.0042865253,0.000095621595,0.00026377387,0.00003323971,0.000030056344,0.0003952674],"genre_scores_gemma":[0.9706644,0.000048950053,0.027715491,0.0010070998,0.00007580081,0.000025743147,0.0000718603,0.00003307316,0.00035756946],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988849,0.00008127099,0.0002862196,0.00033499202,0.00019044237,0.00022216924],"domain_scores_gemma":[0.9993133,0.00015552848,0.0000737283,0.00023535526,0.00008975561,0.00013230993],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018015347,0.00014241679,0.0003701708,0.000038002305,0.000054531578,0.000015962385,0.000072100636,0.000028843928,0.000049300943],"category_scores_gemma":[0.00054649555,0.00012279191,0.00017636627,0.00007874931,0.00010534071,0.000044407858,0.000026760476,0.0003135893,5.21081e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000104682746,0.00023423547,0.0016648892,0.00030457854,0.000046734447,0.000045146237,0.001739919,0.0006360285,0.97213686,0.00009861115,0.00074441184,0.022243904],"study_design_scores_gemma":[0.0015011063,0.00012525711,0.00086355465,0.000051321553,0.00008982,0.000069332804,0.00009158961,0.96262497,0.03408044,0.00016815099,0.00023131161,0.00010316244],"about_ca_topic_score_codex":0.0000073733067,"about_ca_topic_score_gemma":0.00000845811,"teacher_disagreement_score":0.9619889,"about_ca_system_score_codex":0.000041140174,"about_ca_system_score_gemma":0.000054695312,"threshold_uncertainty_score":0.5007309},"labels":[],"label_agreement":null},{"id":"W3117896427","doi":"10.1684/bdc.2008.0659","title":"Validation du Bio-plex phosphoprotein array dans l'évaluation des niveaux d'expression de phosphoprotéines de signalisation des voies PI3K et MAPK dans le cancer du sein","year":2008,"lang":"fr","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre d'expertise et de recherche en infrastructures urbaines","funders":"","keywords":"Molecular biology; Chemistry; Biology","score_opus":0.018723260973002948,"score_gpt":0.26739265667268824,"score_spread":0.2486693956996853,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3117896427","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5038539,0.0021923364,0.47924724,0.009096114,0.00026016412,0.00075831014,0.00003882837,0.00019206674,0.0043610036],"genre_scores_gemma":[0.82904035,0.018313374,0.14350486,0.00030121638,0.00026224114,0.00048547392,0.0013354429,0.00015354755,0.0066034705],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9860526,0.009920165,0.0010577693,0.0011386874,0.0009337294,0.00089709566],"domain_scores_gemma":[0.99332505,0.001477905,0.0010212592,0.0013531822,0.002291857,0.00053075684],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.012669478,0.0007011543,0.0007268969,0.00029763175,0.0016481145,0.00044153078,0.00095711526,0.000547311,0.00037590842],"category_scores_gemma":[0.0071405545,0.0007373591,0.0003613766,0.0006567929,0.0016202468,0.00046252747,0.00048977544,0.0013296824,0.00003129738],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013123729,0.0010357132,0.13481668,0.00074540626,0.00019242245,0.00003348122,0.105785996,0.012135451,0.6386461,0.009342269,0.00080867956,0.09632656],"study_design_scores_gemma":[0.0016414082,0.0000041235235,0.10733035,0.009685362,0.00024131352,0.00012081888,0.001627947,0.13412945,0.7330589,0.0063731987,0.00513222,0.0006548726],"about_ca_topic_score_codex":0.057026766,"about_ca_topic_score_gemma":0.0022513822,"teacher_disagreement_score":0.33574238,"about_ca_system_score_codex":0.0016693543,"about_ca_system_score_gemma":0.0020482396,"threshold_uncertainty_score":0.9996516},"labels":[],"label_agreement":null},{"id":"W3118485952","doi":"10.1016/j.ultrasmedbio.2020.12.012","title":"Muscle Composition Analysis of Ultrasound Images: A Narrative Review of Texture Analysis","year":2021,"lang":"en","type":"review","venue":"Ultrasound in Medicine & Biology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":69,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Canadian Institutes of Health Research","keywords":"Texture (cosmology); Computer science; Wavelet; Image texture; Artificial intelligence; Histogram; Computer vision; Pattern recognition (psychology); Image processing; Image (mathematics)","score_opus":0.02204861938239564,"score_gpt":0.3919848482175854,"score_spread":0.36993622883518973,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3118485952","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00025075217,0.9949582,0.001655867,0.0004943528,0.00019530837,0.0007878025,0.00017054008,0.000023958119,0.0014632167],"genre_scores_gemma":[0.0017916127,0.9837113,0.00096805533,0.00100988,0.00021918306,0.000055967324,0.012110957,0.000041402374,0.000091619455],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99388695,0.0014007824,0.0028146298,0.0009345676,0.0005073782,0.00045568537],"domain_scores_gemma":[0.9917666,0.004647691,0.0018392531,0.0010156329,0.00050722936,0.00022364862],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0023611388,0.0006560629,0.011328913,0.002820681,0.000054808002,0.000006464476,0.00041442644,0.0005066027,0.002052518],"category_scores_gemma":[0.0072437846,0.00044951928,0.0021863119,0.009621803,0.0011180814,0.00004382642,0.00006199925,0.0016004945,0.0000027168726],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000045965153,0.0010211362,0.0076683755,0.17117974,0.06468246,0.00019760599,0.00306297,0.00004449809,0.0023380974,0.00048760275,0.009994235,0.7392773],"study_design_scores_gemma":[0.0010850882,0.0006247131,0.0026546447,0.17996696,0.19991401,0.00024712982,0.0006749316,0.00007944935,0.000006255647,0.00004272026,0.6140949,0.0006092201],"about_ca_topic_score_codex":0.00046164318,"about_ca_topic_score_gemma":0.00003008652,"teacher_disagreement_score":0.7386681,"about_ca_system_score_codex":0.00019827085,"about_ca_system_score_gemma":0.0004160969,"threshold_uncertainty_score":0.9997957},"labels":[],"label_agreement":null},{"id":"W3119758656","doi":"10.3390/diagnostics11010072","title":"Delta Radiomics Analysis for Local Control Prediction in Pancreatic Cancer Patients Treated Using Magnetic Resonance Guided Radiotherapy","year":2021,"lang":"en","type":"article","venue":"Diagnostics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":51,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Magnetic resonance imaging; Medicine; Receiver operating characteristic; Radiation therapy; Pancreatic cancer; Wilcoxon signed-rank test; Nuclear medicine; Mann–Whitney U test; Radiomics; Radiology; Cancer; Internal medicine","score_opus":0.012764911600117574,"score_gpt":0.29562786162996624,"score_spread":0.2828629500298487,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3119758656","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8685003,0.010802262,0.11904135,0.0005649958,0.00023287274,0.00058638846,0.00020357358,0.00003924596,0.00002899944],"genre_scores_gemma":[0.985786,0.0042891633,0.0072611393,0.001657896,0.00024292147,0.00010702616,0.00045242466,0.000053470852,0.00014995506],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99841344,0.00009774098,0.00050247,0.0003738424,0.00025709765,0.00035541024],"domain_scores_gemma":[0.9985443,0.0006425674,0.000108085136,0.00025716986,0.00028605413,0.00016185347],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022420511,0.00019063108,0.0006187966,0.00023750303,0.000075323056,0.000030878127,0.0000742373,0.00012351281,0.00009076154],"category_scores_gemma":[0.0017325828,0.00018385352,0.0001706423,0.00084427104,0.00009450746,0.000046714984,0.000012847225,0.00022548396,8.453675e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014260055,0.00027649396,0.95661366,0.00005971384,0.000274135,0.00007207111,0.00012371277,0.022411553,0.00032696742,0.000023984283,0.0009554782,0.018719625],"study_design_scores_gemma":[0.0054551996,0.00013653649,0.39162442,0.00015727255,0.0012485529,0.000008858267,0.000016500415,0.5989603,0.00013364552,0.000017645816,0.0021294402,0.00011163044],"about_ca_topic_score_codex":0.0005942186,"about_ca_topic_score_gemma":0.00008882184,"teacher_disagreement_score":0.57654876,"about_ca_system_score_codex":0.00039956623,"about_ca_system_score_gemma":0.00019264991,"threshold_uncertainty_score":0.7497329},"labels":[],"label_agreement":null},{"id":"W3120864196","doi":"10.1016/j.ejrad.2021.109552","title":"Multi-classifier-based identification of COVID-19 from chest computed tomography using generalizable and interpretable radiomics features","year":2021,"lang":"en","type":"article","venue":"European Journal of Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"China Scholarship Council; Wellcome Trust; Health Service Executive; Royal College of Surgeons in Ireland; China Postdoctoral Science Foundation; Canadian Institute for Theoretical Astrophysics","keywords":"Medicine; Radiomics; Coronavirus disease 2019 (COVID-19); Receiver operating characteristic; Artificial intelligence; Random forest; Pneumonia; Kappa; Radiology; Cohen's kappa; Pattern recognition (psychology); Nuclear medicine; Machine learning; Internal medicine; Disease; Computer science; Mathematics","score_opus":0.029450816067570586,"score_gpt":0.3023062421771026,"score_spread":0.272855426109532,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3120864196","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6261398,0.004570343,0.3673015,0.0014173904,0.0004399587,0.000053140946,0.000009248957,0.000011804707,0.000056781264],"genre_scores_gemma":[0.868704,0.00020799795,0.12917203,0.0015427403,0.00025394818,2.0044044e-7,0.00004083838,0.000029435558,0.000048795708],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980022,0.0008016077,0.0006721846,0.00021121108,0.00014436674,0.00016848736],"domain_scores_gemma":[0.9985031,0.00020198167,0.00059833867,0.00020960966,0.00019331314,0.000293686],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011254706,0.00013307654,0.00050663284,0.00024866077,0.000074539945,0.000031960837,0.00014950243,0.000051937757,0.000039965118],"category_scores_gemma":[0.0009825011,0.00011564591,0.0001501696,0.00021074973,0.0002633478,0.000059294936,0.000043183605,0.00045116834,8.484626e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040290924,0.00025601164,0.05331734,0.00021515867,0.0005481928,0.0025105055,0.0009169986,0.022378214,0.91047233,0.00008413172,0.0042321803,0.0046660188],"study_design_scores_gemma":[0.012725714,0.000643678,0.22167404,0.0005498319,0.00084321946,0.017137231,0.00046412047,0.70677996,0.022289373,0.0001342618,0.016362183,0.00039640037],"about_ca_topic_score_codex":0.00003244955,"about_ca_topic_score_gemma":0.0000014665251,"teacher_disagreement_score":0.88818294,"about_ca_system_score_codex":0.000059778777,"about_ca_system_score_gemma":0.0002750876,"threshold_uncertainty_score":0.47159034},"labels":[],"label_agreement":null},{"id":"W3121451510","doi":"10.1200/op.20.00810","title":"Readiness of Healthcare Systems to Generate Real-World Evidence: Reliability of CT Radiographic End Points for Evaluation of First-Line Systemic Treatment","year":2021,"lang":"en","type":"article","venue":"JCO Oncology Practice","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Reliability (semiconductor); Health care; Healthcare system; Baseline (sea); Radiography; Resource (disambiguation); Clinical Practice","score_opus":0.08495731440286869,"score_gpt":0.45543086847026154,"score_spread":0.37047355406739285,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3121451510","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95588124,0.00417574,0.0011571868,0.034868855,0.00091794,0.002321219,0.00003631849,0.000022290178,0.00061919977],"genre_scores_gemma":[0.9902932,0.0027664795,0.0059169806,0.00027672414,0.00021289411,0.00026215866,0.00006017044,0.000023706232,0.00018770667],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960289,0.0015799291,0.0011197698,0.00043205297,0.0006054366,0.00023388189],"domain_scores_gemma":[0.9906964,0.0043783993,0.0011106909,0.00062440656,0.0030067575,0.00018336523],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0074099624,0.00016944317,0.0010391219,0.00027874962,0.00006653566,0.000006614541,0.0001078086,0.000105145475,0.00002162603],"category_scores_gemma":[0.01649395,0.00014132581,0.00017324292,0.0007159111,0.00012051981,0.00013608993,0.00003866281,0.00023252347,0.0000012991426],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0144041525,0.0086688595,0.6804613,0.034969438,0.0032806145,0.00052076415,0.006151518,0.048345353,0.06488925,0.0048939004,0.0036208758,0.12979397],"study_design_scores_gemma":[0.06026929,0.03701685,0.15008292,0.031021826,0.02931702,0.00736248,0.010208419,0.49721172,0.058250923,0.0009363563,0.11673866,0.0015835481],"about_ca_topic_score_codex":0.005768731,"about_ca_topic_score_gemma":0.00056582113,"teacher_disagreement_score":0.5303784,"about_ca_system_score_codex":0.0008222941,"about_ca_system_score_gemma":0.001533171,"threshold_uncertainty_score":0.99179053},"labels":[],"label_agreement":null},{"id":"W3121939634","doi":"10.1038/s41598-021-80998-y","title":"Improving prognostic performance in resectable pancreatic ductal adenocarcinoma using radiomics and deep learning features fusion in CT images","year":2021,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":60,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hospital for Sick Children; Lunenfeld-Tanenbaum Research Institute; Health Sciences Centre; Sinai Health System; Sunnybrook Health Science Centre; University of Alberta; University Health Network; University of Toronto","funders":"Canadian Cancer Society Research Institute; Terry Fox Research Institute; Pancreatic Cancer Canada Foundation; Hebrew University of Jerusalem; Government of Ontario; Ontario Institute for Cancer Research; Princess Margaret Cancer Foundation","keywords":"Radiomics; Feature (linguistics); Artificial intelligence; Deep learning; Transfer of learning; Medicine; Pancreatic ductal adenocarcinoma; Feature extraction; Computer science; Radiology; Machine learning; Pattern recognition (psychology); Internal medicine; Pancreatic cancer; Cancer","score_opus":0.008462360894386671,"score_gpt":0.2542151189573353,"score_spread":0.2457527580629486,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3121939634","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9915354,0.0065198527,0.00012753771,0.00017157011,0.00097511354,0.00028707317,1.7559208e-7,0.000036624348,0.000346656],"genre_scores_gemma":[0.9938062,0.00014017957,0.0048885327,0.00002994141,0.00008531667,0.00000899478,0.0000334222,0.00002828749,0.0009791472],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99769175,0.00011229651,0.00050770957,0.00078380835,0.00042532437,0.00047913476],"domain_scores_gemma":[0.99909896,0.000092599206,0.00019412625,0.0003574059,0.0000986935,0.00015821081],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018680765,0.00017095939,0.00037425684,0.00039261425,0.0002746798,0.00025071183,0.000057997342,0.00005514737,0.000027404714],"category_scores_gemma":[0.002555996,0.00015776388,0.00004896191,0.00080414873,0.00022015121,0.00024141265,0.00014669867,0.00075400306,0.0000010702221],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019358691,0.000049099635,0.87167555,0.0002683274,0.000007677584,0.009111655,0.00046725865,0.0008587981,0.10917087,0.0000029029086,0.000023087607,0.008345386],"study_design_scores_gemma":[0.0007950112,0.00005873946,0.8044123,0.00091071945,0.00006689437,0.020448366,0.0006139455,0.16377687,0.008300266,0.00012033692,0.00026318067,0.00023333273],"about_ca_topic_score_codex":0.00027653566,"about_ca_topic_score_gemma":0.000043318472,"teacher_disagreement_score":0.16291809,"about_ca_system_score_codex":0.00015153553,"about_ca_system_score_gemma":0.00030851713,"threshold_uncertainty_score":0.64334244},"labels":[],"label_agreement":null},{"id":"W3122107622","doi":"10.1158/0008-5472.can-20-1237","title":"Assessing Lung Cancer Absolute Risk Trajectory Based on a Polygenic Risk Model","year":2021,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":95,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Princess Margaret Cancer Centre; Lunenfeld-Tanenbaum Research Institute; Public Health Ontario; University of Toronto","funders":"National Center for Advancing Translational Sciences; Medical Research Council; Canadian Institutes of Health Research; Canadian Cancer Society Research Institute; National Institutes of Health; Medical Research and Materiel Command; Fundación para el Fomento en Asturias de la Investigación Científica Aplicada y la Tecnología; Princess Margaret Hospital Foundation; Universidad de Oviedo; Vanderbilt University; Moffitt Cancer Center; Herlev Hospital; Norges Forskningsråd; Vanderbilt University Medical Center; Cancer Care Ontario; National Center for Research Resources; Georgia Clinical and Translational Science Alliance; National Cancer Institute; Sundhed og Sygdom, Det Frie Forskningsråd; World Health Organization; Roy Castle Lung Cancer Foundation; U.S. Department of Defense","keywords":"Lung cancer; Absolute risk reduction; Cancer; Medicine; Oncology; Statistics; Internal medicine; Mathematics; Confidence interval","score_opus":0.06646280740802088,"score_gpt":0.46487277598174803,"score_spread":0.3984099685737271,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3122107622","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97171533,0.008208678,0.009022111,0.005883201,0.00036546,0.00033466882,0.000051882755,0.00008892872,0.004329765],"genre_scores_gemma":[0.98832875,0.0041840817,0.0025072682,0.001271511,0.00073324266,0.00019331223,0.000018746388,0.00008504272,0.0026780525],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99657536,0.0005320629,0.00027282603,0.000629285,0.0011975126,0.0007929568],"domain_scores_gemma":[0.99804485,0.0004458505,0.00009275021,0.0005743053,0.00039582024,0.00044642904],"candidate_categories":["research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0018796051,0.00018646274,0.0003557593,0.00028795327,0.00048334003,0.00015626069,0.00019608346,0.00012722719,0.0009399387],"category_scores_gemma":[0.001341203,0.00016342111,0.00017191305,0.00067829463,0.0002170532,0.000110493995,0.0000811875,0.0028233936,0.000016925163],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009297312,0.0007207401,0.16710655,0.0011232158,0.000720265,0.0010179857,0.0015519198,0.37134486,0.090572536,0.00016427324,0.056010067,0.30873784],"study_design_scores_gemma":[0.0018826849,0.000058056085,0.02895004,0.00070029043,0.00014536861,0.0000075240764,0.00010908501,0.96257377,0.0027071587,0.000098787525,0.002584863,0.00018238022],"about_ca_topic_score_codex":0.0027116742,"about_ca_topic_score_gemma":0.00014832725,"teacher_disagreement_score":0.5912289,"about_ca_system_score_codex":0.00079666707,"about_ca_system_score_gemma":0.0032494008,"threshold_uncertainty_score":0.99997336},"labels":[],"label_agreement":null},{"id":"W3122174162","doi":"10.1093/noajnl/vdaa179","title":"Artificial Intelligence, Radiomics, and Deep Learning in Neuro-Oncology","year":2020,"lang":"en","type":"editorial","venue":"Neuro-Oncology Advances","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Brain Institute; Princess Margaret Cancer Centre; Toronto Western Hospital; University Health Network","funders":"Deutsche Forschungsgemeinschaft","keywords":"Radiomics; Artificial intelligence; Deep learning; Computer science; Medicine","score_opus":0.013748439043335725,"score_gpt":0.329503696663984,"score_spread":0.31575525762064827,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3122174162","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0052220663,0.01450658,0.003286474,0.026496872,0.94258344,0.0014551292,0.00002479615,0.00052141957,0.005903203],"genre_scores_gemma":[0.019064454,0.04503287,0.0092627,0.008767779,0.91646415,0.00022256747,0.00054555293,0.00042788198,0.00021203629],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9949028,0.0008137078,0.0012721709,0.0014868783,0.00064129283,0.00088318426],"domain_scores_gemma":[0.99085164,0.007440836,0.00066830526,0.00033728743,0.00016161754,0.0005403062],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.0009411162,0.00067222654,0.0020175248,0.00057176535,0.00022275891,0.00006191419,0.00044017402,0.0014456757,0.000090862166],"category_scores_gemma":[0.021086698,0.00066157326,0.00019685626,0.000536863,0.00094588264,0.0001942627,0.00033131323,0.008609856,0.000060296323],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016379044,0.0003228791,0.002969432,0.000526213,0.000090762835,0.005671075,0.0009224088,0.0008267838,0.0051336675,0.0003164379,0.122172296,0.8594101],"study_design_scores_gemma":[0.00091383833,0.0027318804,0.000085699845,0.000104532955,0.00022492965,0.00030160538,0.00028452673,0.010188563,0.00018026255,0.0012094204,0.9833141,0.0004606626],"about_ca_topic_score_codex":0.00003678681,"about_ca_topic_score_gemma":0.000104858096,"teacher_disagreement_score":0.8611418,"about_ca_system_score_codex":0.0003848146,"about_ca_system_score_gemma":0.0010255569,"threshold_uncertainty_score":0.99985063},"labels":[],"label_agreement":null},{"id":"W3122656408","doi":"10.1186/s41747-020-00199-6","title":"MRI texture feature repeatability and image acquisition factor robustness, a phantom study and in silico study","year":2021,"lang":"en","type":"article","venue":"European Radiology Experimental","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute of Cancer Research","funders":"Engineering and Physical Sciences Research Council; Medical Research Council; National Institute for Health and Care Research; Cancer Research UK","keywords":"Repeatability; Imaging phantom; Robustness (evolution); Concordance correlation coefficient; Scanner; Artificial intelligence; Correlation coefficient; Image resolution; Computer science; Mathematics; Pattern recognition (psychology); Statistics; Nuclear medicine; Medicine","score_opus":0.009944901055693659,"score_gpt":0.3034505016345487,"score_spread":0.293505600578855,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3122656408","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9944563,0.0031784705,0.00006299836,0.0007966062,0.00015881819,0.000662519,0.000005960678,0.00006024996,0.00061811047],"genre_scores_gemma":[0.9983313,0.00004558923,0.00075013435,0.00039441403,0.00019846404,0.00001360375,0.000038888025,0.000035712645,0.00019188965],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99767303,0.0009514581,0.00026956055,0.00070144725,0.00015098517,0.000253518],"domain_scores_gemma":[0.99932104,0.00007219622,0.000062134444,0.00034455684,0.00003281039,0.00016728144],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005162873,0.00022466303,0.00044603244,0.000083396146,0.00011608517,0.000047136862,0.00007737815,0.000055692835,0.00010788262],"category_scores_gemma":[0.00016303618,0.00019024491,0.000040022544,0.00012969143,0.00022692382,0.000099248,0.000204697,0.0005824736,0.0000036063916],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003703841,0.0026708192,0.8660382,0.00003080843,0.000118203956,0.006004969,0.010436751,0.0000071857544,0.1114756,0.000004098651,0.00056647655,0.0022765147],"study_design_scores_gemma":[0.006263827,0.0010667194,0.97228724,0.000037150363,0.00005336227,0.0016938108,0.015659103,0.0013289215,0.0011668332,0.0000017866203,0.00023860983,0.00020261291],"about_ca_topic_score_codex":0.000018539069,"about_ca_topic_score_gemma":0.0000072141843,"teacher_disagreement_score":0.110308774,"about_ca_system_score_codex":0.00006743356,"about_ca_system_score_gemma":0.00003053595,"threshold_uncertainty_score":0.77579623},"labels":[],"label_agreement":null},{"id":"W3122665769","doi":"10.1109/bibm52615.2021.9669726","title":"Boosting Segmentation Performance across Datasets using Histogram Specification with Application to Pelvic Bone Segmentation","year":2021,"lang":"en","type":"preprint","venue":"2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Mitacs","keywords":"Segmentation; Computer science; Artificial intelligence; Deep learning; Boosting (machine learning); Histogram; Dice; Pattern recognition (psychology); Machine learning; Image (mathematics)","score_opus":0.05006283796301823,"score_gpt":0.3597749553319904,"score_spread":0.30971211736897214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3122665769","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.79437876,0.0001070983,0.19662957,0.005095996,0.0010738518,0.0013156356,0.0003044508,0.00006498046,0.0010296423],"genre_scores_gemma":[0.90041906,0.0010058371,0.08266353,0.00167302,0.00073003897,0.000116429655,0.013162497,0.000047377674,0.00018224043],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970727,0.00003649152,0.0009123446,0.000581436,0.0010542901,0.00034275913],"domain_scores_gemma":[0.997913,0.00005456036,0.0007026185,0.00046881314,0.0005532786,0.0003077509],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005983616,0.00041511082,0.0005312468,0.0004822148,0.00021137504,0.00035021984,0.00024142182,0.00019266254,0.00011529195],"category_scores_gemma":[0.00010083737,0.00034588334,0.00006821411,0.0003755887,0.00018379575,0.00027695615,0.00022048113,0.00075867877,0.000020969372],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009182213,0.00061431044,0.010264934,0.0027399256,0.0006677594,0.000101480284,0.00891064,0.003967674,0.1327185,0.00032389956,0.0022542777,0.83651835],"study_design_scores_gemma":[0.0024737455,0.0006155343,0.006368661,0.0037316263,0.00025278042,0.00032879732,0.0046437695,0.9739906,0.004527115,0.000034739438,0.002425242,0.00060737616],"about_ca_topic_score_codex":0.00019591766,"about_ca_topic_score_gemma":0.000018817938,"teacher_disagreement_score":0.9700229,"about_ca_system_score_codex":0.00040432255,"about_ca_system_score_gemma":0.000278674,"threshold_uncertainty_score":0.9998993},"labels":[],"label_agreement":null},{"id":"W3123565549","doi":"10.21203/rs.3.rs-185311/v1","title":"A Machine Learning Challenge for Prognostic Modelling in Head and Neck Cancer Using Multi-modal Data","year":2021,"lang":"en","type":"preprint","venue":"Research Square","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Princess Margaret Cancer Centre; University Health Network","funders":"","keywords":"Modal; Head and neck cancer; Computer science; Head (geology); Head and neck; Artificial intelligence; Machine learning; Medicine; Cancer; Geology; Surgery; Internal medicine; Materials science","score_opus":0.26594936313842155,"score_gpt":0.4935102098392712,"score_spread":0.22756084670084964,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3123565549","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8846915,0.052375894,0.055363365,0.004174868,0.00022633023,0.0028567798,0.00014798909,0.0000795771,0.00008372988],"genre_scores_gemma":[0.93108946,0.011355197,0.05505318,0.00005648292,0.00054291915,0.0002802034,0.0012996257,0.0001345317,0.00018842536],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960321,0.00042021874,0.0004960008,0.001298142,0.0008491555,0.0009043773],"domain_scores_gemma":[0.9976367,0.0006180468,0.00011850231,0.0008263537,0.000428581,0.00037186386],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.003009752,0.0003227586,0.000781322,0.0005250381,0.00027365104,0.00022296174,0.00041268292,0.00034599676,0.000037411122],"category_scores_gemma":[0.0032020372,0.0003055339,0.000099434365,0.00030580608,0.00017976586,0.00012247042,0.0021865023,0.005082141,9.3459664e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00078529224,0.0014161532,0.46806782,0.029676048,0.00051138474,0.0013747755,0.0060638213,0.39645547,0.0009012691,0.00012806071,0.0000688204,0.09455111],"study_design_scores_gemma":[0.0024327324,0.00016964783,0.0038896531,0.009842783,0.00007513919,0.00003265037,0.00044668288,0.9812286,0.0000073198003,0.000096588636,0.0015182287,0.0002600078],"about_ca_topic_score_codex":0.007992399,"about_ca_topic_score_gemma":0.00062402897,"teacher_disagreement_score":0.5847731,"about_ca_system_score_codex":0.0003189021,"about_ca_system_score_gemma":0.0010810283,"threshold_uncertainty_score":0.9999397},"labels":[],"label_agreement":null},{"id":"W3125230725","doi":"10.1101/2021.01.24.427986","title":"MRI Radiomic Signature of White Matter Hyperintensities Is Associated with Clinical Phenotypes","year":2021,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Institute of Neurological Disorders and Stroke; American Academy of Neurology; Société Française de Radiologie; Göteborgs Universitet; National Institutes of Health; Sahlgrenska Universitetssjukhuset; Helsingin ja Uudenmaan Sairaanhoitopiiri","keywords":"Medicine; Hyperintensity; Neuroimaging; Fluid-attenuated inversion recovery; White matter; Coronary artery disease; Cohort; Cardiology; Magnetic resonance imaging; Internal medicine; Radiology; Psychiatry","score_opus":0.011255947505741755,"score_gpt":0.2502147028030589,"score_spread":0.23895875529731717,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3125230725","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9916484,0.0016903899,0.0015783127,0.0031529623,0.0010854304,0.00049916527,0.000089249974,0.0002013212,0.000054816534],"genre_scores_gemma":[0.985362,0.0003532892,0.009389427,0.004019555,0.00056743313,0.000031571104,0.0000030954188,0.00019648805,0.00007716782],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.996553,0.00025682236,0.000944794,0.0010548851,0.0006451405,0.0005453605],"domain_scores_gemma":[0.9963704,0.00018638268,0.0007278705,0.0012383126,0.0010874126,0.0003896479],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.001007047,0.0005950252,0.0016653071,0.00025096638,0.00013085945,0.00010580254,0.00036264406,0.00084896054,0.00038929237],"category_scores_gemma":[0.00072095817,0.0005186064,0.00039450216,0.00040566872,0.00046961135,0.00008791991,0.00046964866,0.002764984,0.000020508112],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039981023,0.0007687618,0.8748619,0.0016551246,0.003185994,0.0011185812,0.0002474829,0.00021043958,0.1074918,0.00005593226,0.009995878,0.000008316002],"study_design_scores_gemma":[0.0026074208,0.0002348512,0.9640681,0.0049245628,0.0013156254,7.269516e-7,0.000040380215,0.003985176,0.019410485,0.0000011934363,0.0024367613,0.00097469846],"about_ca_topic_score_codex":0.00004228395,"about_ca_topic_score_gemma":0.0000010761453,"teacher_disagreement_score":0.08920624,"about_ca_system_score_codex":0.00018417135,"about_ca_system_score_gemma":0.00096064224,"threshold_uncertainty_score":0.99972653},"labels":[],"label_agreement":null},{"id":"W3125577801","doi":"10.1200/jco.2021.39.3_suppl.464","title":"Association of perioperative red blood cell transfusions with all-cause and cancer-specific death in patients undergoing surgery for gastrointestinal cancer.","year":2021,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Sunnybrook Hospital; Health Sciences Centre; Princess Margaret Cancer Centre; Ottawa Hospital; Centre hospitalier universitaire de Québec; University of Manitoba; Sunnybrook Health Science Centre; University of Toronto","funders":"","keywords":"Medicine; Hazard ratio; Perioperative; Gastrointestinal cancer; Cancer; Interquartile range; Colorectal cancer; Blood transfusion; Population; Surgery; Proportional hazards model; Anemia; Retrospective cohort study; Internal medicine; Confidence interval","score_opus":0.07445381230343684,"score_gpt":0.41177198646306873,"score_spread":0.3373181741596319,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3125577801","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9851019,0.00050856156,0.00085470686,0.012920324,0.00029329033,0.00013587183,0.0000061431965,0.0000024804967,0.00017675865],"genre_scores_gemma":[0.97659826,0.0079080565,0.014306949,0.00064482284,0.00033309247,0.000005092473,0.0000050745925,0.000015636737,0.00018301595],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99795854,0.00027826696,0.0011904341,0.00015431327,0.00023968621,0.00017878768],"domain_scores_gemma":[0.9933126,0.004826776,0.0010018655,0.00005957868,0.0006116752,0.00018752206],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015765156,0.000088910296,0.000940366,0.00007912871,0.000033650107,0.000007509997,0.00004001291,0.00010363362,0.000043320884],"category_scores_gemma":[0.004621153,0.00006546705,0.00015742527,0.00010308787,0.00006377555,0.000056425983,0.000012917935,0.0007095009,6.985407e-8],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016711019,0.00093418726,0.9804474,0.00008036945,0.00028917505,0.00018645303,0.00015684095,0.00012768648,0.00065503124,0.000014135787,0.0005387282,0.014898864],"study_design_scores_gemma":[0.018316543,0.0058569973,0.96780217,0.0011742176,0.00087659206,0.0001484394,0.00020255946,0.00069511775,0.00020038427,0.000026565658,0.0046094945,0.000090918795],"about_ca_topic_score_codex":0.000045551435,"about_ca_topic_score_gemma":0.00040751018,"teacher_disagreement_score":0.01664544,"about_ca_system_score_codex":0.00017273241,"about_ca_system_score_gemma":0.002401741,"threshold_uncertainty_score":0.55322856},"labels":[],"label_agreement":null},{"id":"W3125770257","doi":"10.1038/s41598-021-81272-x","title":"Utility of T2-weighted MRI texture analysis in assessment of peripheral zone prostate cancer aggressiveness: a single-arm, multicenter study","year":2021,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto; University Health Network; Sinai Health System; Lunenfeld-Tanenbaum Research Institute; Institute of Cancer Research","funders":"Helse Midt-Norge; Norges Teknisk-Naturvitenskapelige Universitet; Kreftforeningen","keywords":"Histogram; Medicine; Pattern recognition (psychology); Prostate cancer; Effective diffusion coefficient; Artificial intelligence; Principal component analysis; Nuclear medicine; Magnetic resonance imaging; Radiology; Cancer; Computer science; Internal medicine","score_opus":0.013314727855659642,"score_gpt":0.3338655549989416,"score_spread":0.320550827143282,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3125770257","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9959009,0.00063466013,0.0010104176,0.0004113822,0.0011558047,0.0005245518,0.000006763349,0.00001604346,0.00033947438],"genre_scores_gemma":[0.9965274,0.000018947992,0.0020094165,0.00003324849,0.000027397446,0.000024493558,0.000083151084,0.000013372034,0.0012626054],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99693847,0.00020113832,0.00096557837,0.0007544123,0.0008689185,0.00027151062],"domain_scores_gemma":[0.99776727,0.000042944444,0.0006594258,0.00080062257,0.00059471285,0.00013501957],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015973,0.00015603902,0.00072016276,0.0003414936,0.00007368527,0.000055459623,0.00008465552,0.00005530972,0.00068820274],"category_scores_gemma":[0.0002998716,0.00012384998,0.00020896125,0.0018385919,0.00029041545,0.00008157963,0.000101440986,0.00031151198,1.8959936e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000047547615,0.0033568551,0.95879096,0.00018203759,0.00044266868,0.0020245109,0.0020441124,0.0006564975,0.025965044,0.000001506254,0.00019013624,0.0062981346],"study_design_scores_gemma":[0.0015093496,0.00013241229,0.9007899,0.00048974995,0.0008601736,0.000046815123,0.0014998008,0.085685514,0.007436639,0.00004519738,0.0013520935,0.00015232206],"about_ca_topic_score_codex":0.0005397323,"about_ca_topic_score_gemma":0.0005097764,"teacher_disagreement_score":0.08502901,"about_ca_system_score_codex":0.000084512656,"about_ca_system_score_gemma":0.00053204485,"threshold_uncertainty_score":0.7535337},"labels":[],"label_agreement":null},{"id":"W3125868735","doi":"10.1016/j.media.2021.101976","title":"Synthesis of gadolinium-enhanced liver tumors on nonenhanced liver MR images using pixel-level graph reinforcement learning","year":2021,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":45,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Pixel; Reinforcement learning; Computer science; Artificial intelligence; Graph; Computer vision; Pattern recognition (psychology); Theoretical computer science","score_opus":0.01843634630885849,"score_gpt":0.30063667401865585,"score_spread":0.28220032770979736,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3125868735","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.517811,0.0006174409,0.47607952,0.0012780302,0.00012185148,0.00018932192,0.000007209137,0.000101163976,0.0037944785],"genre_scores_gemma":[0.9764043,0.0014107142,0.018731972,0.0012527952,0.00025334652,0.000018413291,0.00008440165,0.000057168705,0.001786878],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9953042,0.00032609786,0.0010507316,0.0007689738,0.0019173804,0.00063258054],"domain_scores_gemma":[0.99689317,0.00079743506,0.00044124832,0.0006604405,0.0005332679,0.0006744365],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001317536,0.00039281702,0.0014466265,0.00075617275,0.00021696373,0.00005527368,0.0002933534,0.00021444044,0.004534174],"category_scores_gemma":[0.008361416,0.00033783054,0.00094859314,0.0020428253,0.0005276604,0.0001494317,0.00019776086,0.0012154366,0.000063745974],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008942104,0.0022765817,0.012610751,0.001815472,0.0125945285,0.009165173,0.0019893001,0.018727459,0.76940686,0.00023098361,0.001893563,0.16839515],"study_design_scores_gemma":[0.0022462278,0.00029615045,0.011107308,0.0018122953,0.007828319,0.00015391095,0.00058470794,0.50866336,0.46613526,0.000028124294,0.0004478295,0.0006964967],"about_ca_topic_score_codex":0.0003794677,"about_ca_topic_score_gemma":0.00001424727,"teacher_disagreement_score":0.4899359,"about_ca_system_score_codex":0.00012528052,"about_ca_system_score_gemma":0.00037201447,"threshold_uncertainty_score":0.9999916},"labels":[],"label_agreement":null},{"id":"W3126227997","doi":"10.3390/cancers13030552","title":"Magnetic Resonance Imaging Based Radiomic Models of Prostate Cancer: A Narrative Review","year":2021,"lang":"en","type":"review","venue":"Cancers","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Nova Scotia Cancer Centre; Montreal Neurological Institute and Hospital; Dalhousie University; McGill University","funders":"","keywords":"Prostate cancer; Magnetic resonance imaging; Narrative review; Medicine; Radiology; Medical physics; Cancer; Internal medicine","score_opus":0.023964714172809043,"score_gpt":0.35122207688542223,"score_spread":0.3272573627126132,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3126227997","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000025804989,0.99579734,0.00011225931,0.0009197193,0.0004346331,0.0015986311,0.00009053659,0.000048779028,0.0009955058],"genre_scores_gemma":[0.000007777524,0.99474746,0.001140995,0.002054093,0.00020794675,0.00055202126,0.00017577465,0.00011847889,0.0009954415],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9970741,0.00026537947,0.0009986472,0.0007253263,0.00047244073,0.0004640785],"domain_scores_gemma":[0.99804986,0.00015323269,0.000627684,0.0006599914,0.00024464837,0.00026461328],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005059754,0.00052135525,0.0034538961,0.00019795608,0.000073707095,0.000019387493,0.0002788698,0.00012043303,0.00035207396],"category_scores_gemma":[0.0003012735,0.0004280727,0.00073439523,0.000776443,0.0003016046,0.00007152263,0.000060352722,0.0010041173,0.00000371908],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010800227,0.00001028048,0.000012318885,0.08354374,0.000065521504,0.00013158425,0.00017250443,0.00014473162,0.0000011185463,0.00002745605,0.015362061,0.9005179],"study_design_scores_gemma":[0.0005029414,0.00003887361,8.7436666e-7,0.3084556,0.0013852932,0.00007804889,0.000028796192,0.009086725,0.0000010712519,0.000008045791,0.6801566,0.00025716424],"about_ca_topic_score_codex":0.0003631449,"about_ca_topic_score_gemma":0.000004833574,"teacher_disagreement_score":0.90026075,"about_ca_system_score_codex":0.0019303792,"about_ca_system_score_gemma":0.00866066,"threshold_uncertainty_score":0.99981713},"labels":[],"label_agreement":null},{"id":"W3126652400","doi":"10.1038/s41598-021-82760-w","title":"Assessing robustness of carotid artery CT angiography radiomics in the identification of culprit lesions in cerebrovascular events","year":2021,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":50,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"NIHR Imperial Biomedical Research Centre; Horizon 2020; Medical Research Council; NIHR Cambridge Biomedical Research Centre; European Commission; School of Clinical Medicine, University of Cambridge; Wellcome Trust; Royal College of Surgeons of England; Dunhill Medical Trust; Department of Health and Social Care; Leverhulme Trust; National Institute for Health and Care Research; Mark Foundation For Cancer Research; Higher Education Funding Council for England; Alan Turing Institute; University of Cambridge; Cancer Research UK; British Heart Foundation; Engineering and Physical Sciences Research Council; AstraZeneca","keywords":"Radiomics; Medicine; Robustness (evolution); Radiology; Artificial intelligence; Culprit; Carotid artery disease; Segmentation; Computed tomography angiography; Feature extraction; Angiography; Feature (linguistics); Pattern recognition (psychology); Computer science; Carotid endarterectomy; Internal medicine","score_opus":0.01756022279446152,"score_gpt":0.30032661722509807,"score_spread":0.28276639443063656,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3126652400","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99454427,0.00045251282,0.0024005075,0.0005134747,0.0016068415,0.0002732999,8.359908e-7,0.000009116532,0.00019912879],"genre_scores_gemma":[0.99835485,0.000025198351,0.001361084,0.000025140034,0.00003405753,0.000011236233,0.000074138625,0.000011917862,0.00010239645],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9974079,0.00021409646,0.0010382173,0.00045328055,0.00067585154,0.00021063027],"domain_scores_gemma":[0.9983634,0.00008289675,0.00044199877,0.00086832617,0.00018610258,0.000057309633],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0046227477,0.00010287802,0.00034288678,0.0005166379,0.00007989448,0.0000750897,0.00013321608,0.000041139214,0.000021382612],"category_scores_gemma":[0.000826476,0.000081836435,0.00029511243,0.001818181,0.00022814254,0.00016843907,0.00004368151,0.00027181042,5.3475003e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005286485,0.00071464374,0.8474535,0.00036771604,0.00008706271,0.0008883691,0.0011368953,0.0058798795,0.13747507,0.000057936777,0.0008110389,0.005122646],"study_design_scores_gemma":[0.0009220004,0.000018923398,0.9456492,0.0011002839,0.00019197885,0.00262908,0.002254888,0.012100042,0.032764204,0.0012500124,0.0009215996,0.0001978041],"about_ca_topic_score_codex":0.000073386764,"about_ca_topic_score_gemma":0.000020906135,"teacher_disagreement_score":0.10471088,"about_ca_system_score_codex":0.000040763538,"about_ca_system_score_gemma":0.00026696114,"threshold_uncertainty_score":0.3337193},"labels":[],"label_agreement":null},{"id":"W3127098127","doi":"10.1101/2021.01.29.21250803","title":"Radiomics Analysis of Clinical Myocardial Perfusion Stress SPECT Images to Identify Coronary Artery Calcification","year":2021,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Society of Nuclear Medicine and Molecular Imaging","keywords":"Univariate; Coronary artery disease; Medicine; Univariate analysis; Radiology; Myocardial perfusion imaging; Feature selection; Voxel; CAD; Multivariate statistics; Nuclear medicine; Multivariate analysis; Artificial intelligence; Computer science; Cardiology; Internal medicine; Machine learning","score_opus":0.03754121682915448,"score_gpt":0.3951092581790186,"score_spread":0.3575680413498641,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3127098127","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98184204,0.00066293636,0.01185854,0.002480429,0.0020231528,0.00046498614,0.00008206208,0.000068592104,0.0005172348],"genre_scores_gemma":[0.9915952,0.0013113968,0.004274211,0.00042703177,0.00095659815,0.0000246904,0.0011419886,0.00005553229,0.00021334377],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99587846,0.00048417982,0.0014938054,0.0010187688,0.0008040612,0.0003207026],"domain_scores_gemma":[0.9969702,0.00039248736,0.00054556516,0.0013172592,0.00032407802,0.00045041568],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0018776667,0.00034128228,0.0019378079,0.00072894193,0.00006807239,0.00008099496,0.00039011284,0.00034396263,0.0002863216],"category_scores_gemma":[0.002111957,0.00031922778,0.0012598489,0.0007507661,0.00020237273,0.000048946113,0.00059114833,0.0016250918,0.00001443973],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019025346,0.00037293797,0.9462242,0.00026035678,0.002803728,0.00068468694,0.0004700925,0.003360698,0.011721797,0.000011091564,0.0008292143,0.033070914],"study_design_scores_gemma":[0.00061367336,0.00008730329,0.9604894,0.0004209658,0.0046438794,0.00005561191,0.00018702145,0.03181858,0.0010216151,0.000014916812,0.0003882314,0.00025882287],"about_ca_topic_score_codex":0.00015182424,"about_ca_topic_score_gemma":0.000012627269,"teacher_disagreement_score":0.032812092,"about_ca_system_score_codex":0.00010041757,"about_ca_system_score_gemma":0.00035807933,"threshold_uncertainty_score":0.999926},"labels":[],"label_agreement":null},{"id":"W3127346846","doi":"10.3389/fonc.2020.619274","title":"The Essential Role of Open Data and Software for the Future of Ultrasound-Based Neuronavigation","year":2021,"lang":"en","type":"article","venue":"Frontiers in Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; McGill University; Montreal Neurological Institute and Hospital","funders":"Natural Sciences and Engineering Research Council of Canada; California HIV/AIDS Research Program","keywords":"Neuronavigation; Computer science; Software; Artificial intelligence; Data collection; Graphics; Machine learning; 3D ultrasound; Data science; Medical physics; Information retrieval; Ultrasound; Medicine; Radiology; Magnetic resonance imaging; Computer graphics (images)","score_opus":0.011452106882332131,"score_gpt":0.3337846004590645,"score_spread":0.3223324935767324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3127346846","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4131716,0.054681726,0.39056024,0.12894528,0.008319896,0.003115462,0.00024096807,0.000035559322,0.0009293025],"genre_scores_gemma":[0.829801,0.0025010277,0.16393223,0.00227559,0.00066219416,0.000061616025,0.00049310375,0.000034676596,0.000238529],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993563,0.00010118228,0.00019560075,0.00015541799,0.00008841424,0.00010306332],"domain_scores_gemma":[0.99857634,0.0008563332,0.0001129386,0.00034801796,0.00007864303,0.00002774788],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00060806924,0.000050126437,0.00021446472,0.000020463314,0.00007475164,0.000014184389,0.00038619226,0.00005751208,0.0000066988237],"category_scores_gemma":[0.0013065893,0.000030645664,0.00002193238,0.000109549146,0.00023357193,0.00003714357,0.00017316637,0.00020255103,5.191166e-8],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005412491,0.00015522515,0.1360742,0.000105760766,0.000104995204,0.000012294331,0.00040848294,0.00018762844,0.004366425,0.00061835407,0.053055152,0.8043702],"study_design_scores_gemma":[0.0045049884,0.0003574827,0.0413614,0.00008693904,0.00024598278,0.0000630377,0.004262027,0.103634216,0.0020148605,0.0037774495,0.8396022,0.000089427565],"about_ca_topic_score_codex":0.00004059739,"about_ca_topic_score_gemma":0.0000327315,"teacher_disagreement_score":0.8042808,"about_ca_system_score_codex":0.000021453023,"about_ca_system_score_gemma":0.00035281645,"threshold_uncertainty_score":0.1564204},"labels":[{"model":"gemma","categories":["open_science"],"domain":null,"study_design":"theoretical_or_conceptual","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["open_science"],"domain":null,"study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W3129430687","doi":"10.1109/trpms.2021.3059780","title":"DefED-Net: Deformable Encoder-Decoder Network for Liver and Liver Tumor Segmentation","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Radiation and Plasma Medical Sciences","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":147,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"National Natural Science Foundation of China","keywords":"Computer science; Pyramid (geometry); Artificial intelligence; Segmentation; Pooling; Encoder; Feature (linguistics); Pattern recognition (psychology); Context (archaeology); Convolutional neural network; Convolution (computer science); Computer vision; Artificial neural network; Mathematics","score_opus":0.020222485530479575,"score_gpt":0.28896383307325973,"score_spread":0.2687413475427802,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3129430687","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4964698,0.0012080261,0.49278483,0.0075957584,0.0007372589,0.00038503576,0.000014548928,0.000066279186,0.00073847966],"genre_scores_gemma":[0.97393876,0.0031401198,0.017465165,0.0045038424,0.00023328965,0.000043365177,0.000017985869,0.00001200266,0.0006454731],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99873036,0.00006196171,0.00021534867,0.0002982286,0.00044189685,0.00025222538],"domain_scores_gemma":[0.9990703,0.0004331409,0.000055762353,0.00006468278,0.00003961442,0.0003365075],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00067317544,0.0001101384,0.00017651918,0.00007658157,0.00051233266,0.00007384496,0.00004967002,0.000079558966,0.0004815144],"category_scores_gemma":[0.00011815798,0.000087383254,0.000051589337,0.00023784331,0.00026544463,0.00016644309,0.0000017439286,0.00024351894,0.0000075132184],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001250277,0.00020937949,0.0026427496,0.00018217527,0.00008411226,0.00008611145,0.00094820204,0.010712145,0.0003696781,0.0008245231,0.0031910017,0.9806249],"study_design_scores_gemma":[0.0017802073,0.00031486797,0.0020655987,0.000108592896,0.00009699157,0.00045665316,0.00021887162,0.98058844,0.002079767,0.00019040925,0.011953418,0.00014618241],"about_ca_topic_score_codex":0.00006438569,"about_ca_topic_score_gemma":0.00009172214,"teacher_disagreement_score":0.9804787,"about_ca_system_score_codex":0.000029855313,"about_ca_system_score_gemma":0.0002155003,"threshold_uncertainty_score":0.5272245},"labels":[],"label_agreement":null},{"id":"W3129517280","doi":"10.1016/j.media.2021.102005","title":"Weakly-Supervised teacher-Student network for liver tumor segmentation from non-enhanced images","year":2021,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":57,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Segmentation; Artificial intelligence; Computer science; Contrast (vision); Liver tumor; Minimum bounding box; Pattern recognition (psychology); Image (mathematics); Computer vision; Medicine","score_opus":0.007663096682908042,"score_gpt":0.30743983234332845,"score_spread":0.2997767356604204,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3129517280","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4051259,0.00096318446,0.58502746,0.0067205313,0.00025986574,0.00033977735,0.000020156702,0.00010172446,0.0014414295],"genre_scores_gemma":[0.79973453,0.00067550293,0.17980519,0.010338049,0.0026810828,0.00017019799,0.0021987152,0.000084606676,0.004312138],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99694407,0.00016322109,0.0006099505,0.00068322656,0.001090215,0.0005093321],"domain_scores_gemma":[0.9980636,0.00039073057,0.00015224305,0.00048332696,0.00029928997,0.0006107634],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00082356273,0.00026446124,0.0008805845,0.00015001181,0.00018994279,0.000114066264,0.0002371068,0.00012929866,0.006819699],"category_scores_gemma":[0.0015863113,0.00022528059,0.0006638914,0.00097487797,0.00017666798,0.00013021674,0.00012875456,0.00058481283,0.00007260839],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00055338885,0.0030384609,0.16385593,0.00044716598,0.019469177,0.0061319624,0.0035654388,0.001505278,0.2910387,0.0000414324,0.13730726,0.3730458],"study_design_scores_gemma":[0.0080320975,0.00029004092,0.12603334,0.00044683056,0.016543474,0.000054833818,0.0019731296,0.80776244,0.032530706,0.00022880897,0.00529046,0.0008138547],"about_ca_topic_score_codex":0.00038596883,"about_ca_topic_score_gemma":0.0000820523,"teacher_disagreement_score":0.8062571,"about_ca_system_score_codex":0.00010427663,"about_ca_system_score_gemma":0.00022996914,"threshold_uncertainty_score":0.9940882},"labels":[],"label_agreement":null},{"id":"W3129622461","doi":"10.1158/1538-7445.sabcs20-pd13-02","title":"Abstract PD13-02: Site of recurrence after neoadjuvant therapy: A multi-center pooled analysis","year":2021,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Institute for Cancer Research","funders":"","keywords":"Medicine; Cumulative incidence; Internal medicine; Oncology; Incidence (geometry); Population; Confidence interval; Breast cancer; Disease; Cancer; Cohort","score_opus":0.061897343098025547,"score_gpt":0.43709237074682133,"score_spread":0.3751950276487958,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3129622461","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9856626,0.008990255,0.00041078427,0.0039899102,0.00012190883,0.00019686666,0.0000347542,0.000018196526,0.0005747377],"genre_scores_gemma":[0.99361175,0.0035700072,0.00078302366,0.0005004426,0.0001630893,0.000068563895,0.000046490644,0.000023120321,0.0012335163],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9979312,0.0001621524,0.0003025441,0.00040520984,0.0007557037,0.00044322194],"domain_scores_gemma":[0.99847203,0.00015034227,0.00006171642,0.00046813543,0.0006003191,0.0002474771],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009445901,0.00012066307,0.00041438016,0.0003382284,0.000065925014,0.00003869309,0.00013361062,0.000073446055,0.0022796814],"category_scores_gemma":[0.00044911224,0.00009535816,0.00022217349,0.0012190517,0.00022110887,0.000055491706,0.00009818871,0.0009111391,0.00003593551],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010122728,0.0014333253,0.52112615,0.00042792328,0.0023214037,0.0012035492,0.0022685553,0.00015274143,0.22421426,0.000022119417,0.0032551622,0.24256252],"study_design_scores_gemma":[0.0068871127,0.00018849061,0.917043,0.000983878,0.0004221525,0.000030192372,0.0002813158,0.009656159,0.028194735,0.000041446303,0.035972428,0.00029912035],"about_ca_topic_score_codex":0.00059506955,"about_ca_topic_score_gemma":0.000100655685,"teacher_disagreement_score":0.3959168,"about_ca_system_score_codex":0.00010756106,"about_ca_system_score_gemma":0.0004053324,"threshold_uncertainty_score":0.9986324},"labels":[],"label_agreement":null},{"id":"W3132686583","doi":"","title":"A multi-omics-based serial deep learning approach to predict clinical outcomes of single-agent anti-PD-1/PD-L1 immunotherapy in advanced stage non-small-cell lung cancer.","year":2021,"lang":"en","type":"article","venue":"PubMed","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":79,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Medicine; Immunotherapy; Stage (stratigraphy); Oncology; Lung cancer; Internal medicine; Cancer; Progression-free survival; Log-rank test; Survival analysis; Overall survival","score_opus":0.02895145131736814,"score_gpt":0.31666539933143023,"score_spread":0.2877139480140621,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3132686583","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9684563,0.0009108306,0.026397351,0.000882298,0.00090070534,0.0017652456,0.000014996164,0.00008492066,0.000587353],"genre_scores_gemma":[0.9616375,0.00036357436,0.03420663,0.0014870339,0.00023036677,0.000790176,0.000079786616,0.00009939384,0.0011055327],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9966876,0.0003096509,0.0010887927,0.0007235172,0.00042997603,0.00076044316],"domain_scores_gemma":[0.9982638,0.00031635983,0.00034476264,0.0004962853,0.00015085105,0.00042796228],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0014981094,0.0003294526,0.0011234962,0.00022688055,0.000080323014,0.00004741053,0.00027037543,0.00019845428,0.000035062767],"category_scores_gemma":[0.0013747754,0.000303577,0.0003297047,0.00047196826,0.00011564673,0.00007148729,0.00011716992,0.0010037943,0.0000017405445],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00071435666,0.0017710322,0.8634014,0.00039864355,0.00022277338,0.00008922453,0.0005996381,0.03993269,0.012808888,0.000003313455,0.00003786373,0.08002019],"study_design_scores_gemma":[0.013743681,0.00012648645,0.8495249,0.00012140521,0.00011381379,0.000005694724,0.00026099724,0.13063158,0.0033191585,8.419309e-7,0.0018496206,0.00030181036],"about_ca_topic_score_codex":0.00023439148,"about_ca_topic_score_gemma":0.000037594553,"teacher_disagreement_score":0.09069889,"about_ca_system_score_codex":0.0002637074,"about_ca_system_score_gemma":0.00030080057,"threshold_uncertainty_score":0.99994165},"labels":[],"label_agreement":null},{"id":"W3133560731","doi":"10.1158/1557-3265.adi21-po-025","title":"Abstract PO-025: Differentiation of benign from clinically significant prostate cancer tissues using convolution neural networks on raw micro-ultrasound data","year":2021,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Prostate cancer; Medicine; Biopsy; Ultrasound; Prostate; Radiology; Cancer; Convolutional neural network; Prostate biopsy; Artificial intelligence; Computer science; Internal medicine","score_opus":0.22390549835778356,"score_gpt":0.5266286732634722,"score_spread":0.3027231749056886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3133560731","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9895102,0.0033323693,0.0010287357,0.0041211112,0.0011099095,0.0005338946,0.00022238777,0.00003621476,0.00010521336],"genre_scores_gemma":[0.98750454,0.0077369614,0.0009804794,0.0006732256,0.0019383115,0.000025572805,0.0008480902,0.000055911732,0.00023692912],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99494535,0.0008422115,0.0014566182,0.0010550704,0.0010655774,0.00063517265],"domain_scores_gemma":[0.99318564,0.004102125,0.00038885864,0.0011211293,0.00077060645,0.00043165236],"candidate_categories":["research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0036843163,0.00021916078,0.00079902686,0.00010576637,0.00019630848,0.000099600635,0.00048812354,0.0002885929,0.0010806489],"category_scores_gemma":[0.005087511,0.00018546401,0.00018258175,0.00036415446,0.0007413577,0.00013579939,0.00034698137,0.0026141384,0.000011550708],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0031891973,0.001205534,0.77139807,0.00027257804,0.0005508883,0.00022696864,0.00021775578,0.0062501817,0.066809446,0.000034469136,0.0071365447,0.14270835],"study_design_scores_gemma":[0.0042128414,0.0005346725,0.7009279,0.001324297,0.00029047125,0.000006705387,0.00020802957,0.28681785,0.0027196337,0.0002509983,0.0023852258,0.00032134278],"about_ca_topic_score_codex":0.0042832186,"about_ca_topic_score_gemma":0.00014292511,"teacher_disagreement_score":0.28056768,"about_ca_system_score_codex":0.00019087162,"about_ca_system_score_gemma":0.0009609207,"threshold_uncertainty_score":0.9998325},"labels":[],"label_agreement":null},{"id":"W3133660616","doi":"10.1158/1557-3265.adi21-po-005","title":"Abstract PO-005: An efficient digitized annotation platform for pathology-oriented dataset generation in AI research","year":2021,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Annotation; Computer science; Digital pathology; Workflow; Prostate cancer; Artificial intelligence; Grading (engineering); Pathology; Pattern recognition (psychology); Cancer; Medicine; Biology; Database","score_opus":0.33612034587353407,"score_gpt":0.6047761300816308,"score_spread":0.2686557842080967,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3133660616","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9817883,0.00040444458,0.00082909304,0.015099956,0.00039341353,0.0008818594,0.000348922,0.000029883015,0.00022414415],"genre_scores_gemma":[0.9862378,0.0005058541,0.0015891655,0.0014929447,0.0014858932,0.00033718435,0.007944468,0.00004275857,0.00036387797],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9959711,0.000647416,0.0007933819,0.00080568244,0.0010006003,0.0007818603],"domain_scores_gemma":[0.995967,0.0018056597,0.00006798407,0.0005913032,0.0011331536,0.00043493186],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.014239195,0.0001225927,0.00040219695,0.00034239635,0.0002921454,0.000109109846,0.00020088472,0.00023442451,0.00025543952],"category_scores_gemma":[0.012198981,0.00010802206,0.00009071292,0.00080871035,0.000516918,0.00014548816,0.00015192443,0.0025933466,0.000028484033],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0069996845,0.00656143,0.06130003,0.0009394005,0.00018388778,0.0034358576,0.0017388767,0.0041877036,0.06054052,0.004043274,0.32119405,0.5288753],"study_design_scores_gemma":[0.023545349,0.0027291612,0.23481454,0.00073370687,0.000062718325,0.000116841045,0.0013560891,0.4828096,0.005908417,0.0029814257,0.24435504,0.00058711687],"about_ca_topic_score_codex":0.0003108566,"about_ca_topic_score_gemma":0.00029342424,"teacher_disagreement_score":0.5282882,"about_ca_system_score_codex":0.00028843043,"about_ca_system_score_gemma":0.0011283059,"threshold_uncertainty_score":0.9997077},"labels":[],"label_agreement":null},{"id":"W3133830369","doi":"10.1016/j.ejmp.2021.01.084","title":"Influence of inter-observer delineation variability on radiomic features of the parotid gland","year":2021,"lang":"en","type":"article","venue":"Physica Medica","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Trinity College","funders":"","keywords":"Histogram; Segmentation; Artificial intelligence; Pattern recognition (psychology); Grey level; Mathematics; Similarity (geometry); Feature (linguistics); Nuclear medicine; Computer science; Medicine; Pixel","score_opus":0.00809725748306112,"score_gpt":0.27565440989843554,"score_spread":0.2675571524153744,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3133830369","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9917648,0.00005437709,0.0006927101,0.0061598313,0.00013800977,0.00014772346,0.000005742629,0.000014678797,0.0010221594],"genre_scores_gemma":[0.9981939,0.000029989891,0.00049592735,0.0008263224,0.00018002301,0.000006368645,0.000016345983,0.0000111491145,0.00023995536],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99878347,0.00016041203,0.00030221228,0.00020973064,0.00041315763,0.00013102408],"domain_scores_gemma":[0.99876857,0.00030442455,0.00016858398,0.00048805212,0.00018023039,0.00009012766],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043237384,0.000103601575,0.00033517162,0.000027485457,0.00004355336,0.0000031974018,0.00015991963,0.000050393475,0.000045268207],"category_scores_gemma":[0.00269967,0.00006563481,0.00013349648,0.00023561745,0.00030100864,0.000033261047,0.000070687965,0.0004070639,0.00000235491],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005982456,0.002282579,0.5109453,0.0017235555,0.0006457486,0.0000615694,0.0034464442,0.003802863,0.39871612,0.005409666,0.016915066,0.05545283],"study_design_scores_gemma":[0.0015724261,0.00015391732,0.91764027,0.0008129917,0.00017752436,0.000047273264,0.000040628656,0.004087636,0.07227289,0.0006848987,0.0024041403,0.00010541173],"about_ca_topic_score_codex":0.00007532645,"about_ca_topic_score_gemma":0.000001920351,"teacher_disagreement_score":0.40669495,"about_ca_system_score_codex":0.00003202014,"about_ca_system_score_gemma":0.00022089771,"threshold_uncertainty_score":0.3231952},"labels":[],"label_agreement":null},{"id":"W3133926454","doi":"10.1101/2021.03.04.21252908","title":"The Impact of the Variation of CT Scanner on the Prediction of human papillomavirus (HPV) Association of Oropharyngeal Cancer (OPC) using Radiomic models","year":2021,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; Princess Margaret Cancer Centre; Ontario Institute for Cancer Research; University of Toronto; University Health Network","funders":"Canadian Institutes of Health Research","keywords":"Scanner; Cancer imaging; Robustness (evolution); Human papillomavirus; Radiomics; Computer science; Artificial intelligence; Medicine; Cancer; Biology","score_opus":0.03293370348539515,"score_gpt":0.3264033923880179,"score_spread":0.29346968890262276,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3133926454","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9961073,0.00064480415,0.0006601549,0.0008797498,0.00065447105,0.00057296373,0.000092258255,0.000009987128,0.0003783272],"genre_scores_gemma":[0.9989014,0.000563107,0.000072188224,0.00004144675,0.00022784683,0.000019821828,0.000026672114,0.000035965062,0.00011150247],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.997253,0.000550187,0.0008662527,0.000270259,0.00084943656,0.00021086643],"domain_scores_gemma":[0.9965276,0.00040686218,0.0018710007,0.00071687344,0.00042584067,0.000051805404],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019293604,0.00021945513,0.00071239704,0.00010130807,0.00014909302,0.000017370992,0.00035608167,0.00015521802,0.00007146733],"category_scores_gemma":[0.00086727465,0.00011069839,0.0005123189,0.0002512899,0.00019986807,0.00005146598,0.00018391812,0.0009067488,1.257929e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001978061,0.00030770374,0.26016262,0.00059576076,0.0018151619,0.0000031937593,0.0027783045,0.17089345,0.5595437,0.000529044,0.0003442722,0.0028289643],"study_design_scores_gemma":[0.0009471991,0.00015111327,0.6211311,0.0014048148,0.00074148166,0.0000056130475,0.00011475782,0.3552593,0.019359102,0.00077222486,0.000008497083,0.00010479544],"about_ca_topic_score_codex":0.0066617024,"about_ca_topic_score_gemma":0.000028033974,"teacher_disagreement_score":0.5401846,"about_ca_system_score_codex":0.0005215128,"about_ca_system_score_gemma":0.0005984185,"threshold_uncertainty_score":0.99995303},"labels":[],"label_agreement":null},{"id":"W3134000566","doi":"10.1158/1557-3265.adi21-po-053","title":"Abstract PO-053: Machine learning CADx process for classification of lung nodules below the Lung-RADS 4A threshold in LDCT scans","year":2021,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vancouver General Hospital","funders":"","keywords":"Nodule (geology); Medicine; Artificial intelligence; Radiology; Lung; Lung cancer; Parenchyma; Lung cancer screening; Computer science; Computed tomography; Pathology; Internal medicine","score_opus":0.17894207556434416,"score_gpt":0.5377358738865021,"score_spread":0.35879379832215796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3134000566","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9549625,0.0072103227,0.0004925296,0.034030244,0.00030487112,0.00091876753,0.000022044474,0.00003605411,0.0020226494],"genre_scores_gemma":[0.9952378,0.0021804506,0.00016188285,0.0004293674,0.00063530233,0.00021451498,0.000060900562,0.000051554056,0.0010281717],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99658114,0.00035630583,0.0009242755,0.00059841445,0.00094490714,0.00059493387],"domain_scores_gemma":[0.9962975,0.0020166156,0.00019338509,0.0004802157,0.0007662994,0.00024599687],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0068013784,0.00016185915,0.0005524851,0.0001697335,0.00024863004,0.00005223017,0.00038349867,0.00020398741,0.00032009874],"category_scores_gemma":[0.008157566,0.00011526075,0.0002122523,0.0007471886,0.00059189316,0.00008254025,0.00012021487,0.0030569474,0.000005739917],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00085109676,0.00056619005,0.9356883,0.0015743333,0.00015853312,0.00006664003,0.0006103726,0.0010925258,0.0046173143,0.000656197,0.0051903534,0.048928108],"study_design_scores_gemma":[0.0032612951,0.00024083702,0.6933084,0.0011684874,0.0000843148,0.000014298296,0.0005125198,0.2925483,0.0009180942,0.00045375846,0.0073069003,0.00018277887],"about_ca_topic_score_codex":0.0005086117,"about_ca_topic_score_gemma":0.0003121403,"teacher_disagreement_score":0.29145578,"about_ca_system_score_codex":0.00019136714,"about_ca_system_score_gemma":0.0012040549,"threshold_uncertainty_score":0.999243},"labels":[],"label_agreement":null},{"id":"W3134040280","doi":"10.17160/josha.8.1.739","title":"Künstliche Intelligenz in der Krebsforschung und Biomedizin - Artificial Intelligence in Cancer Research and Biomedicine","year":2021,"lang":"de","type":"article","venue":"Journal of Science Humanities and Arts - JOSHA","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Biomedicine; Biology","score_opus":0.15380563016108154,"score_gpt":0.4365289047809509,"score_spread":0.28272327461986935,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3134040280","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83793,0.14489433,0.00030936682,0.013943661,0.0021314323,0.00019869875,0.0000056031704,0.000005478646,0.0005813791],"genre_scores_gemma":[0.94405705,0.051739413,0.00078751775,0.0010884722,0.0019285677,0.0000049040073,0.0000027916903,0.000027073775,0.00036421893],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9957389,0.00017154834,0.0012778876,0.00050664326,0.00140234,0.0009026341],"domain_scores_gemma":[0.9977187,0.00057263987,0.00032791952,0.00020520733,0.0007624114,0.00041315245],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0074722203,0.00025131824,0.00069257466,0.0023639142,0.0005158855,0.00048714742,0.00037059895,0.00012466186,0.0002599766],"category_scores_gemma":[0.0018253113,0.0002018129,0.0000579443,0.00205805,0.007520109,0.0005894443,0.00033325644,0.0019860507,0.000006488373],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00064590765,0.002062368,0.051614806,0.0016458294,0.00039575528,0.009657347,0.07807949,0.00025923477,0.062205207,0.04770259,0.0023375042,0.74339396],"study_design_scores_gemma":[0.0061235996,0.008319272,0.08357462,0.046944834,0.0011621569,0.0028893063,0.3304717,0.092589565,0.038106754,0.08710929,0.30003744,0.0026714492],"about_ca_topic_score_codex":0.0006799377,"about_ca_topic_score_gemma":0.0005063126,"teacher_disagreement_score":0.74072254,"about_ca_system_score_codex":0.00034675415,"about_ca_system_score_gemma":0.001325264,"threshold_uncertainty_score":0.99518085},"labels":[],"label_agreement":null},{"id":"W3134252658","doi":"10.21203/rs.3.rs-201708/v1","title":"Optimal ATN biomarkers and their role in predicting cognitive progress of mild cognitive impairment","year":2021,"lang":"en","type":"preprint","venue":"Research Square","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Chongqing Medical University; Eisai; Northern California Institute for Research and Education; Novartis Pharmaceuticals Corporation; BioClinica; Meso Scale Diagnostics; Alzheimer's Disease Neuroimaging Initiative; F. Hoffmann-La Roche; University of Southern California; Bristol-Myers Squibb; Eli Lilly and Company; Biogen; National Institute on Aging; Alzheimer's Association; Foundation for the National Institutes of Health","keywords":"Cerebrospinal fluid; Internal medicine; Medicine; Cognitive impairment; Magnetic resonance imaging; Receiver operating characteristic; Biomarker; Area under the curve; Oncology; Neurodegeneration; Gastroenterology; Pathology; Disease; Radiology; Chemistry","score_opus":0.030115089178556594,"score_gpt":0.3920508136982582,"score_spread":0.36193572451970163,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3134252658","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9845791,0.010855404,0.00015872972,0.0010641342,0.00008332877,0.0021173013,0.000097558295,0.00004045205,0.0010040244],"genre_scores_gemma":[0.99704117,0.0010316133,0.0008931468,0.00004272461,0.00017029149,0.00029182615,0.0004202601,0.000059133923,0.00004981549],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9962363,0.0007377675,0.00052646204,0.00081476057,0.00096234435,0.00072235917],"domain_scores_gemma":[0.99712807,0.0011426652,0.00017129195,0.00027587303,0.0009060779,0.00037604547],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0029627024,0.00031469326,0.0007746837,0.0006741455,0.0001192441,0.00010135368,0.00016571504,0.00032015415,0.00007296765],"category_scores_gemma":[0.0022692825,0.0002611899,0.00017690555,0.00049353833,0.0009179287,0.000061890954,0.001244852,0.0030391852,0.0000015955347],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016004528,0.001054118,0.8940464,0.0052460935,0.0009785926,0.00068949553,0.0155316135,0.000057670924,0.0005713068,0.000010126743,0.0000792007,0.080134876],"study_design_scores_gemma":[0.007381302,0.0017409304,0.7294455,0.059078086,0.00018953955,0.00014586566,0.096744634,0.099370174,0.005210099,0.0001212252,0.00006209473,0.0005105442],"about_ca_topic_score_codex":0.00061019143,"about_ca_topic_score_gemma":0.000027225142,"teacher_disagreement_score":0.16460095,"about_ca_system_score_codex":0.00018058957,"about_ca_system_score_gemma":0.0008060687,"threshold_uncertainty_score":0.999984},"labels":[],"label_agreement":null},{"id":"W3134270751","doi":"10.2139/ssrn.3711439","title":"Stroma Amount in Human Cancer","year":2020,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; University of British Columbia Hospital","funders":"","keywords":"Stroma; Cancer; Biology; Computational biology; Genetics; Immunology","score_opus":0.010662186107178447,"score_gpt":0.3059807119440701,"score_spread":0.29531852583689167,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3134270751","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9638472,0.0024040474,0.0018856516,0.030589607,0.00008128387,0.00008719948,4.3614457e-7,0.000027405255,0.0010771545],"genre_scores_gemma":[0.99468523,0.0015560592,0.00009929957,0.002424741,0.00075799617,0.0000034585312,0.000002632944,0.000023174176,0.00044739066],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9981233,0.00004039707,0.00023462516,0.00015425566,0.00023299907,0.0012144081],"domain_scores_gemma":[0.99961716,0.000013015842,0.00007401568,0.00006987519,0.000028466744,0.00019747205],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.000583225,0.00010087208,0.00021839414,0.00007269231,0.00008027098,0.000022829201,0.00011869951,0.0000433864,0.00013686392],"category_scores_gemma":[0.00011586059,0.00008354917,0.0000755837,0.00016330628,0.000037004596,0.00005757911,0.00002120016,0.0032737502,0.000010597403],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00048425767,0.00035808247,0.60795087,0.00013171474,0.00064250914,0.0005872795,0.0028572755,0.0009411672,0.08684313,0.10700942,0.0033582759,0.18883604],"study_design_scores_gemma":[0.05450709,0.011853198,0.4416346,0.0017957017,0.001144577,0.010836477,0.015240726,0.0809949,0.002650104,0.20663467,0.16992486,0.0027831201],"about_ca_topic_score_codex":0.00023273962,"about_ca_topic_score_gemma":0.00016827774,"teacher_disagreement_score":0.18605292,"about_ca_system_score_codex":0.0006243697,"about_ca_system_score_gemma":0.0010896444,"threshold_uncertainty_score":0.99902576},"labels":[],"label_agreement":null},{"id":"W3134516012","doi":"10.1158/1557-3265.adi21-po-033","title":"Abstract PO-033: The impact of the variation of CT scanner on the prediction of HPV status in head &amp; neck cancer patients","year":2021,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University Health Network","funders":"","keywords":"Scanner; Radiomics; Medicine; Cancer imaging; Artificial intelligence; Head and neck; Head and neck squamous-cell carcinoma; Head and neck cancer; Robustness (evolution); Cancer; Radiology; Computer science; Medical physics; Nuclear medicine; Radiation therapy; Internal medicine; Surgery","score_opus":0.1461867473918891,"score_gpt":0.5199791602515118,"score_spread":0.3737924128596227,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3134516012","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9903655,0.00040049883,0.0000061659516,0.0070011094,0.00032318983,0.00046843925,0.00009954707,0.0000038970643,0.0013316383],"genre_scores_gemma":[0.99809074,0.0011861963,0.000015954629,0.00022140137,0.00021028641,0.00003918794,0.000015684795,0.000016421573,0.00020413035],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99698424,0.0007031812,0.00074370066,0.00024139065,0.0010089991,0.00031846948],"domain_scores_gemma":[0.9965767,0.0018636228,0.0002666425,0.0005418452,0.00064459245,0.000106600266],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0030649044,0.00009398412,0.00033580424,0.00007285754,0.00008484084,0.0000117739355,0.00024824688,0.00007166655,0.00091655046],"category_scores_gemma":[0.007030038,0.000042269592,0.00022941448,0.0006677609,0.00052218535,0.0000365721,0.000116280244,0.0014977017,0.0000023828811],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005702676,0.00068306713,0.94819653,0.000109447516,0.00013644659,0.000002099835,0.0005095445,0.0017538506,0.0013116607,0.000072098155,0.0053104665,0.041344497],"study_design_scores_gemma":[0.0014567212,0.0002887621,0.9940259,0.00043800942,0.000025441279,6.408316e-7,0.000059971782,0.0018725791,0.00047324807,0.00020471336,0.0011213212,0.000032693762],"about_ca_topic_score_codex":0.018061254,"about_ca_topic_score_gemma":0.0006456827,"teacher_disagreement_score":0.045829345,"about_ca_system_score_codex":0.0002485124,"about_ca_system_score_gemma":0.0013594559,"threshold_uncertainty_score":0.9999967},"labels":[],"label_agreement":null},{"id":"W3134538708","doi":"10.1016/s0016-5085(21)01702-9","title":"Sa089 ENDOSCOPIST-TARGETED INTERVENTIONS TO OPTIMIZE ADENOMA DETECTION RATE - A SYSTEMATIC REVIEW AND META-ANALYSIS","year":2021,"lang":"en","type":"review","venue":"Gastroenterology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Meta-analysis; Medicine; Adenoma; Psychological intervention; Internal medicine; Nursing","score_opus":0.05781552716296132,"score_gpt":0.37717525218126047,"score_spread":0.3193597250182991,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3134538708","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000047614103,0.9765677,0.019004775,0.001735337,0.00012161451,0.0024503646,0.00004670274,0.000053600605,0.000015134862],"genre_scores_gemma":[0.000039453425,0.9904737,0.0030795035,0.0039990596,0.00004780715,0.0011934164,0.00027656657,0.000056858164,0.000833666],"study_design_codex":"systematic_review","study_design_gemma":"meta_analysis","domain_scores_codex":[0.99515295,0.0018719828,0.0015937332,0.0007551537,0.00018871384,0.00043744946],"domain_scores_gemma":[0.99784344,0.00019931381,0.00072290306,0.0007408698,0.00012783255,0.0003656486],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012860938,0.00051500084,0.011125343,0.00066555425,0.000079210506,0.00004953212,0.00021168182,0.00016823848,0.0006764633],"category_scores_gemma":[0.0012852274,0.00036321027,0.004500361,0.00065695884,0.00007586806,0.000034492437,0.00019950738,0.00080758467,0.00003717751],"study_design_candidate":"meta_analysis","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008563348,0.000065707594,0.000005410934,0.8471985,0.15079904,0.00013268064,0.000013812775,0.0000044061935,7.929543e-7,0.0000035451387,0.0002856864,0.0014818655],"study_design_scores_gemma":[0.00024195571,0.00032094913,0.0000061958235,0.057321142,0.93116987,0.0010983328,0.0000060864368,0.00004759674,1.305557e-7,9.808819e-7,0.009656752,0.0001299838],"about_ca_topic_score_codex":0.000023673067,"about_ca_topic_score_gemma":0.000031583233,"teacher_disagreement_score":0.78987736,"about_ca_system_score_codex":0.00010873338,"about_ca_system_score_gemma":0.00005265897,"threshold_uncertainty_score":0.999882},"labels":[],"label_agreement":null},{"id":"W3134712086","doi":"10.1016/j.acra.2020.12.026","title":"Review of Artificial Intelligence Training Tools and Courses for Radiologists","year":2021,"lang":"en","type":"review","venue":"Academic Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Computer science; Alliance; Task (project management); Task force; Interpretation (philosophy); Training (meteorology); Radiology; Radiomics; Artificial intelligence; Applications of artificial intelligence; Medical physics; Medicine; Systems engineering; Engineering","score_opus":0.1858780699395856,"score_gpt":0.4610928062336111,"score_spread":0.2752147362940255,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3134712086","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000007653539,0.99259764,0.003993046,0.0014493482,0.00048750313,0.0012160459,0.000057458685,0.000034624292,0.00015667717],"genre_scores_gemma":[0.0000032715834,0.99114,0.005132253,0.0020545898,0.00087411795,0.00016650361,0.0005077845,0.000054044118,0.00006741092],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9969186,0.00038232526,0.0015000788,0.0006249148,0.00013082803,0.00044323065],"domain_scores_gemma":[0.9959251,0.002716619,0.000729139,0.00033434978,0.00010287964,0.0001918843],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0020121625,0.00038624075,0.0043471796,0.00036474422,0.000054866126,0.0000068363715,0.00028548608,0.0008292114,0.000048244],"category_scores_gemma":[0.010240165,0.0002948872,0.00054196647,0.0004606779,0.0006324353,0.000038342187,0.00008042277,0.0018487831,0.0000029407295],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000069349185,0.000009252643,0.000004434507,0.08416899,0.00021884181,0.00002349914,0.000054871867,4.1323253e-7,0.0000063736184,0.004149084,0.0062179207,0.9051394],"study_design_scores_gemma":[0.000080721235,0.00015382105,0.0000013681155,0.14251684,0.0015714593,0.0038079852,0.00003810646,0.00008811101,0.0000018280521,0.00031746813,0.85121614,0.00020617754],"about_ca_topic_score_codex":0.000003410707,"about_ca_topic_score_gemma":1.1145849e-7,"teacher_disagreement_score":0.9049332,"about_ca_system_score_codex":0.00005492895,"about_ca_system_score_gemma":0.0006184,"threshold_uncertainty_score":0.99995035},"labels":[],"label_agreement":null},{"id":"W3134750715","doi":"10.1158/1557-3265.adi21-ia-15","title":"Abstract IA-15: Platforms to improve reproducibility in artificial intelligence research","year":2021,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Princess Margaret Cancer Centre","funders":"","keywords":"Reproducibility; Computer science; Transparency (behavior); Artificial intelligence; Field (mathematics); Data science; Mathematics","score_opus":0.3980621339270541,"score_gpt":0.6218056127994603,"score_spread":0.22374347887240625,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3134750715","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9530389,0.00081520306,0.00017675218,0.04108513,0.000756889,0.00082450546,0.000008333973,0.000039587616,0.0032547128],"genre_scores_gemma":[0.99333674,0.00082004425,0.0011933374,0.0010157318,0.0019239832,0.00017138691,0.000012941788,0.000042591208,0.0014832735],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99275327,0.00056780095,0.0013346074,0.002365255,0.0017191955,0.0012598739],"domain_scores_gemma":[0.99163926,0.0034126486,0.00006161225,0.0023908163,0.0015587028,0.00093694933],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.054157764,0.0001582714,0.0006001259,0.0004082994,0.00023138545,0.0001187986,0.0004791037,0.00026557728,0.0015236005],"category_scores_gemma":[0.08735937,0.0001320048,0.00017784502,0.0022005178,0.00089319784,0.00010054695,0.0006993415,0.0066139903,0.00045195804],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001637199,0.0013148196,0.0779585,0.00031773365,0.000049439717,0.0011241295,0.00065169117,0.00009759716,0.016253648,0.0015582453,0.0072300103,0.89180696],"study_design_scores_gemma":[0.0022549275,0.0027136412,0.73833007,0.0027686271,0.000037690734,0.000067297195,0.0039472813,0.009642879,0.060149714,0.11300646,0.066210195,0.00087122276],"about_ca_topic_score_codex":0.00163206,"about_ca_topic_score_gemma":0.0008534882,"teacher_disagreement_score":0.8909358,"about_ca_system_score_codex":0.00049339054,"about_ca_system_score_gemma":0.0020051321,"threshold_uncertainty_score":0.9993892},"labels":[],"label_agreement":null},{"id":"W3134874642","doi":"10.1158/1557-3265.adi21-po-018","title":"Abstract PO-018: Computational staining of tumor hypoxia from H&amp;E images using convolutional neural networks","year":2021,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Domtar (Canada); University of Toronto","funders":"","keywords":"Hypoxia (environmental); Stain; H&E stain; Tumor hypoxia; Staining; Pathology; Biology; Convolutional neural network; Necrosis; Chemistry; Medicine; Internal medicine; Radiation therapy; Artificial intelligence; Oxygen; Computer science","score_opus":0.21495130912935417,"score_gpt":0.5289596260580025,"score_spread":0.31400831692864833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3134874642","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.981048,0.0030993037,0.010795326,0.0038102143,0.0005201357,0.00016675587,0.000058898448,0.000028785418,0.00047259952],"genre_scores_gemma":[0.9855619,0.00017061077,0.011395716,0.0009432028,0.0015388345,0.000009257095,0.00017408877,0.00003349551,0.0001728935],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967305,0.00042029403,0.00081557425,0.00049334235,0.0010451049,0.000495154],"domain_scores_gemma":[0.9948373,0.0033169491,0.00016881966,0.0002823975,0.0010155557,0.00037896947],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0024270616,0.00013368098,0.00051841425,0.00010454275,0.00018407464,0.00005222904,0.00018118603,0.00011485115,0.0015901646],"category_scores_gemma":[0.0038386118,0.000123196,0.00020702241,0.00038788115,0.0008624856,0.00007858894,0.000208252,0.0020455904,0.0000112360285],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017343115,0.0011191816,0.69248044,0.00034001443,0.00072336016,0.001237131,0.00022076193,0.16538322,0.012704858,0.0006084213,0.02087308,0.102575235],"study_design_scores_gemma":[0.002292916,0.00008403889,0.47266877,0.00039311813,0.00005714516,0.000043510707,0.00011959303,0.5202287,0.0001186326,0.0013982896,0.0024462526,0.00014903556],"about_ca_topic_score_codex":0.0009794353,"about_ca_topic_score_gemma":0.000020181633,"teacher_disagreement_score":0.35484546,"about_ca_system_score_codex":0.00014257911,"about_ca_system_score_gemma":0.0012928181,"threshold_uncertainty_score":0.99932253},"labels":[],"label_agreement":null},{"id":"W3134979252","doi":"10.1158/1557-3265.adi21-po-052","title":"Abstract PO-052: Exploring patient derived xenografts based pharmacogenomic data for precision oncology","year":2021,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network","funders":"","keywords":"Pharmacogenomics; Precision medicine; Personalized medicine; Drug response; Metadata; Computational biology; Cancer; Medicine; Visualization; Bioinformatics; Oncology; Computer science; Cancer research; Biology; Drug; Internal medicine; Pharmacology; Data mining; Pathology; World Wide Web","score_opus":0.5907452067820693,"score_gpt":0.6136193960953055,"score_spread":0.02287418931323615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3134979252","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9732725,0.002480935,0.001779429,0.018830676,0.0018111939,0.0008799656,0.000102480095,0.000056351422,0.0007864866],"genre_scores_gemma":[0.9813403,0.0036330826,0.009058732,0.002735636,0.0022405924,0.0003399802,0.0004217931,0.00007062424,0.00015927522],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99640125,0.0004738354,0.00080536224,0.00090815814,0.0007302206,0.00068115257],"domain_scores_gemma":[0.99338394,0.00425112,0.000120762765,0.001007446,0.00062392413,0.00061280344],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0051800963,0.00015034908,0.0005372911,0.00013790894,0.000232966,0.000057409467,0.0004921557,0.00015666263,0.00094948674],"category_scores_gemma":[0.008650069,0.00012955679,0.00018254534,0.00031137877,0.0003112732,0.00012273564,0.000546614,0.0017512788,0.00004631743],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016994512,0.0007493806,0.005619256,0.0002329208,0.00013853646,0.00037163403,0.00009249584,0.000098443576,0.042935297,0.000008020403,0.034627408,0.9134272],"study_design_scores_gemma":[0.008015338,0.0010982339,0.018528074,0.00058232725,0.00013087493,0.000022587377,0.00025540267,0.028450666,0.019344188,0.0001135966,0.9232082,0.00025053983],"about_ca_topic_score_codex":0.00012711377,"about_ca_topic_score_gemma":0.000025952557,"teacher_disagreement_score":0.9131766,"about_ca_system_score_codex":0.00028352346,"about_ca_system_score_gemma":0.0022950645,"threshold_uncertainty_score":0.99996376},"labels":[],"label_agreement":null},{"id":"W3135064215","doi":"10.1158/1557-3265.adi21-po-031","title":"Abstract PO-031: Evaluating clinical utility of organs-at-risk segmentation in head &amp; neck cancer by simple open-source 3D CNNs","year":2021,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; University of Toronto","funders":"","keywords":"Segmentation; Contouring; Computer science; Artificial intelligence; Deep learning; Workflow; Medical physics; Benchmark (surveying); Test set; Source code; Machine learning; Medicine","score_opus":0.3223459396933597,"score_gpt":0.6205568415552344,"score_spread":0.2982109018618747,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3135064215","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9877188,0.002627478,0.00026231445,0.006546091,0.00041132464,0.00083056156,0.00009765871,0.000029452673,0.0014762749],"genre_scores_gemma":[0.9856757,0.006671439,0.0027886925,0.0013833974,0.0006642836,0.00013348769,0.00021043843,0.000070168426,0.002402389],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99223727,0.0022743703,0.0021459886,0.0010617785,0.0015078709,0.00077272346],"domain_scores_gemma":[0.99279255,0.004480813,0.0004307067,0.000817492,0.00086524215,0.00061319495],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.019666139,0.00021192088,0.0010340716,0.00011234101,0.0002487614,0.00008044126,0.00051878183,0.00032799374,0.0073865186],"category_scores_gemma":[0.021228848,0.0001905634,0.00023578265,0.00085620244,0.00075480784,0.0001328504,0.0007976382,0.0037122662,0.000057906876],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00083450315,0.00069455773,0.6654772,0.00017201596,0.00009247172,0.000026175896,0.0001869752,0.00008479586,0.0023958748,0.0000018225544,0.027323974,0.3027096],"study_design_scores_gemma":[0.008850357,0.0004986551,0.9024761,0.00073835644,0.00010946306,0.0000073431556,0.00031200316,0.013420848,0.0011367517,0.00019824297,0.071999885,0.00025202092],"about_ca_topic_score_codex":0.016275756,"about_ca_topic_score_gemma":0.005360513,"teacher_disagreement_score":0.3024576,"about_ca_system_score_codex":0.0003949138,"about_ca_system_score_gemma":0.0022758904,"threshold_uncertainty_score":0.99858624},"labels":[],"label_agreement":null},{"id":"W3135092238","doi":"10.1016/j.compbiomed.2021.104304","title":"Machine learning-based prognostic modeling using clinical data and quantitative radiomic features from chest CT images in COVID-19 patients","year":2021,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":134,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; BC Cancer Agency","funders":"Tehran University of Medical Sciences and Health Services; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Coronavirus disease 2019 (COVID-19); 2019-20 coronavirus outbreak; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Computer science; Artificial intelligence; Radiomics; Medicine; Radiology; Pattern recognition (psychology); Machine learning; Data mining; Medical physics; Pathology","score_opus":0.07462500329854864,"score_gpt":0.42641399795461604,"score_spread":0.3517889946560674,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3135092238","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91891706,0.013017367,0.061891034,0.005461139,0.00041701907,0.00022891641,0.000019715568,0.00002932011,0.000018456261],"genre_scores_gemma":[0.9644694,0.0019946126,0.027964747,0.004073395,0.0001729004,0.0000028667073,0.0012987979,0.000017475282,0.000005847106],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997877,0.0005246933,0.00052804704,0.00069724425,0.000111858535,0.0002611837],"domain_scores_gemma":[0.9974926,0.0017791335,0.00012104688,0.00027512482,0.00004855677,0.00028350542],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011755042,0.00019952611,0.00072445796,0.00021375332,0.00010403581,0.00001076703,0.00014553784,0.00011733543,0.000014294149],"category_scores_gemma":[0.0069308775,0.00015675797,0.000026661748,0.00019911454,0.0007129646,0.000060381175,0.00022949236,0.0009944591,3.8606544e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023092245,0.00014673776,0.98631024,0.00010975317,0.000050306262,0.0005615654,0.0003395995,0.0017286325,0.00024375043,0.000041802807,0.00014941354,0.010087244],"study_design_scores_gemma":[0.008095407,0.0003505977,0.16657442,0.00073469407,0.000094023955,0.00011930167,0.00013826364,0.8228132,0.00000446878,0.0005396315,0.00039518336,0.0001408227],"about_ca_topic_score_codex":0.00079305924,"about_ca_topic_score_gemma":0.00005469506,"teacher_disagreement_score":0.82108456,"about_ca_system_score_codex":0.000053945634,"about_ca_system_score_gemma":0.00023416555,"threshold_uncertainty_score":0.8297408},"labels":[],"label_agreement":null},{"id":"W3135160265","doi":"10.1158/1557-3265.adi21-po-060","title":"Abstract PO-060: Individualized prediction of meningioma recurrence risk over prolonged time periods","year":2021,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre","funders":"","keywords":"Meningioma; Medicine; Grading (engineering); Cohort; Internal medicine; Oncology; Proportional hazards model; Surgery; Radiology","score_opus":0.1284431035524994,"score_gpt":0.5132298910673004,"score_spread":0.384786787514801,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3135160265","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98932797,0.002087101,0.00006038945,0.0029648438,0.00041130895,0.0003903122,0.00009204364,0.0000509891,0.004615018],"genre_scores_gemma":[0.9934145,0.0025506571,0.0014193106,0.00021100481,0.00081683823,0.000068848654,0.000083002655,0.00003243875,0.0014033832],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.996019,0.00079029344,0.0008563687,0.0005775352,0.0012712032,0.0004855978],"domain_scores_gemma":[0.99684656,0.0013567639,0.00021963898,0.0005119508,0.000664308,0.00040077072],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00675307,0.0001394533,0.0005758016,0.00015889427,0.00017109848,0.00004539145,0.00022217636,0.0002321117,0.0031554482],"category_scores_gemma":[0.011375825,0.00011755996,0.00023450569,0.0006435268,0.0006708619,0.0000816925,0.00019716001,0.002500287,0.00006139785],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011633878,0.0007261509,0.69565845,0.00034203997,0.00039558814,0.00025834507,0.0005567842,0.000019555242,0.008630353,0.000050878996,0.025133695,0.26706478],"study_design_scores_gemma":[0.00446796,0.00061688735,0.9376274,0.0007809584,0.00013581829,0.000031828833,0.00007476723,0.004911451,0.0018640214,0.00028694514,0.04906465,0.0001373507],"about_ca_topic_score_codex":0.00027998848,"about_ca_topic_score_gemma":0.000008936475,"teacher_disagreement_score":0.26692745,"about_ca_system_score_codex":0.00010472583,"about_ca_system_score_gemma":0.0011345657,"threshold_uncertainty_score":0.999801},"labels":[],"label_agreement":null},{"id":"W3135237341","doi":"10.1158/1557-3265.adi21-po-010","title":"Abstract PO-010: Feature pyramid network for revealing tumour infiltrating lymphocyte presence and distribution in a whole slide image","year":2021,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Health Sciences Centre; Sunnybrook Health Science Centre; University of Toronto","funders":"","keywords":"Pyramid (geometry); Breast cancer; Artificial intelligence; Computer science; Segmentation; Convolutional neural network; Feature (linguistics); Ductal carcinoma; Medicine; Cancer; Pathology; Internal medicine","score_opus":0.08339589710955707,"score_gpt":0.4877396388125088,"score_spread":0.40434374170295173,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3135237341","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94178563,0.007862152,0.0023346657,0.046140175,0.00043594945,0.00081212743,0.000077872275,0.000048782833,0.00050261745],"genre_scores_gemma":[0.98691595,0.002192789,0.006475739,0.0008654119,0.002068052,0.00013953306,0.0002298844,0.00004091427,0.0010717177],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99727106,0.00029969504,0.0005845758,0.00059949775,0.00052149314,0.0007236652],"domain_scores_gemma":[0.9962242,0.002568579,0.00010552171,0.00028892397,0.00044814294,0.0003646314],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0055669774,0.00014065129,0.00046652227,0.000052822885,0.00023652989,0.00013639804,0.00014897426,0.00019921792,0.000044206256],"category_scores_gemma":[0.014238696,0.00012566448,0.000119473385,0.00051281624,0.00038579627,0.00011624461,0.00016711942,0.0020065666,0.0000049091354],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0028278762,0.0006128554,0.34986922,0.0026180204,0.0001963484,0.001712338,0.0005092318,0.0017289538,0.0546646,0.00076500484,0.17534845,0.4091471],"study_design_scores_gemma":[0.009726151,0.00052481896,0.78362936,0.0053358064,0.000078246085,0.00014145173,0.0006349546,0.07691917,0.003098326,0.0027736048,0.11663509,0.0005030413],"about_ca_topic_score_codex":0.00039890897,"about_ca_topic_score_gemma":0.00013455172,"teacher_disagreement_score":0.4337601,"about_ca_system_score_codex":0.00022177662,"about_ca_system_score_gemma":0.0008968216,"threshold_uncertainty_score":0.9940648},"labels":[],"label_agreement":null},{"id":"W3135485367","doi":"10.1038/s41598-021-84630-x","title":"Deep learning classification of lung cancer histology using CT images","year":2021,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":251,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"National Cancer Institute; National Institutes of Health; European Commission; Howard Hughes Medical Institute","keywords":"Histology; Lung cancer; Computer science; Artificial intelligence; Lung; Cancer; Radiology; Medicine; Pathology; Internal medicine","score_opus":0.018294343437861432,"score_gpt":0.334440177149113,"score_spread":0.3161458337112516,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3135485367","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9793729,0.0035329054,0.009046453,0.0010118551,0.0043012705,0.00012027319,2.8855797e-7,0.000047634905,0.0025664056],"genre_scores_gemma":[0.99107665,0.000042892232,0.004186785,0.000057286867,0.00009650017,0.000005636424,0.000043503078,0.000017438095,0.0044733034],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998391,0.0000773585,0.00044864192,0.0004921097,0.00037075547,0.00022015582],"domain_scores_gemma":[0.9987489,0.000040344617,0.00036115164,0.00041036966,0.00032560903,0.00011364095],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00089773734,0.00009059903,0.0002724378,0.00014227051,0.00019699619,0.000046163736,0.00004663278,0.000035341473,0.0003624847],"category_scores_gemma":[0.001086579,0.000083758736,0.0000958329,0.0004042031,0.00030541042,0.000071300165,0.00004664263,0.0002988151,0.0000016468698],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006466436,0.00006761876,0.3375939,0.00017839737,0.000049271828,0.0017485443,0.00025749937,0.0015204531,0.6358998,0.00006303495,0.0025211242,0.020093858],"study_design_scores_gemma":[0.00086977216,0.00004436214,0.12310017,0.00075619953,0.00064516405,0.011672649,0.0005864266,0.6461361,0.10786217,0.0008876281,0.107002206,0.00043715007],"about_ca_topic_score_codex":0.00009776297,"about_ca_topic_score_gemma":0.000006511461,"teacher_disagreement_score":0.64461565,"about_ca_system_score_codex":0.000120279656,"about_ca_system_score_gemma":0.0004056227,"threshold_uncertainty_score":0.39689532},"labels":[],"label_agreement":null},{"id":"W3135515631","doi":"10.1158/1557-3265.adi21-ia-22","title":"Abstract IA-22: Automated treatment planning and quality assurance in radiation oncology","year":2021,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre","funders":"","keywords":"Radiation oncology; Medical physics; Quality assurance; Radiation treatment planning; Medicine; Radiation therapy; Process (computing); Radiation Therapist; Quality (philosophy); Radiation dose; Computer science; Nuclear medicine; Radiology; Pathology","score_opus":0.2702572538348785,"score_gpt":0.6378806920907509,"score_spread":0.36762343825587246,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3135515631","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97584486,0.0050255777,0.000022053755,0.014397489,0.00023454415,0.00022097223,0.0000050350277,0.000065266926,0.0041841846],"genre_scores_gemma":[0.9935982,0.0042845304,0.0005378722,0.00060197845,0.00038123853,0.000053440577,0.00002665988,0.000015570451,0.00050045986],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9975311,0.000718983,0.0005785754,0.00042271093,0.00037965935,0.00036897007],"domain_scores_gemma":[0.99641854,0.0028424584,0.0000784004,0.0002199136,0.0001623488,0.00027834004],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0041286764,0.00009159803,0.00046186327,0.000102872786,0.00008563613,0.000031945463,0.00006285251,0.00017196895,0.00022873268],"category_scores_gemma":[0.004923093,0.000075944256,0.00006522588,0.00031111087,0.00025515014,0.000046563247,0.000052286658,0.0010756202,0.000014440692],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035091565,0.00039205464,0.70343256,0.00011108757,0.000056855275,0.0005972257,0.00025231272,0.000116991316,0.0015881048,0.00006959933,0.0024204503,0.29061186],"study_design_scores_gemma":[0.0036465044,0.00031169804,0.943026,0.00022227716,0.000012475711,0.000015618883,0.0001300725,0.008786632,0.00024119498,0.000071989765,0.043462195,0.00007333233],"about_ca_topic_score_codex":0.0012704274,"about_ca_topic_score_gemma":0.00019790327,"teacher_disagreement_score":0.29053852,"about_ca_system_score_codex":0.00043317053,"about_ca_system_score_gemma":0.0011976673,"threshold_uncertainty_score":0.5893758},"labels":[],"label_agreement":null},{"id":"W3135830244","doi":"10.1158/1557-3265.adi21-po-030","title":"Abstract PO-030: Radiomics for head and neck cancer prognostication: results from the RADCURE machine learning challenge","year":2021,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto","funders":"","keywords":"Radiomics; Medicine; Head and neck cancer; Medical physics; Head and neck; Retrospective cohort study; Radiological weapon; Radiation therapy; Machine learning; Cohort; Artificial intelligence; Cancer; Radiology; Internal medicine; Computer science; Surgery","score_opus":0.20398189249554993,"score_gpt":0.515686907057502,"score_spread":0.31170501456195204,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3135830244","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.64840555,0.039038163,0.00023006882,0.30893514,0.0006742345,0.0010774097,0.00025768275,0.00007227675,0.0013094532],"genre_scores_gemma":[0.9373344,0.051177297,0.0020206333,0.002772545,0.0039662346,0.00032179753,0.00036956635,0.00007973485,0.001957765],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9967696,0.00040438122,0.0007509874,0.0008133497,0.0006765873,0.00058509334],"domain_scores_gemma":[0.9911685,0.007088884,0.00015366089,0.00051917025,0.00063419447,0.00043558225],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0040144706,0.00018394274,0.0005062555,0.000051938274,0.0004955623,0.00012719491,0.00026897423,0.00022280026,0.00028723414],"category_scores_gemma":[0.015949558,0.0001290284,0.00016929505,0.0003128624,0.00060118746,0.00006751983,0.00020247308,0.002965626,0.0000104725395],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003807968,0.0005916562,0.17303687,0.00033911964,0.00051899976,0.00019668062,0.0012799101,0.00018475327,0.0006818265,0.00055195374,0.03869182,0.78011847],"study_design_scores_gemma":[0.010244332,0.00054978865,0.26846895,0.001147493,0.00015779668,0.000021255706,0.00030508355,0.029329333,0.00019461165,0.00096064137,0.68835276,0.00026793397],"about_ca_topic_score_codex":0.0019751845,"about_ca_topic_score_gemma":0.00054644555,"teacher_disagreement_score":0.77985054,"about_ca_system_score_codex":0.00012248021,"about_ca_system_score_gemma":0.00094664114,"threshold_uncertainty_score":0.9993346},"labels":[],"label_agreement":null},{"id":"W3136531031","doi":"","title":"Simulation and synthesis in medical imaging: Second international workshop, SASHIMI 2017 held in conjunction with MICCAI 2017 Québec city, QC, Canada, September 10, 2017 proceedings","year":2017,"lang":"en","type":"article","venue":"Research Explorer (The University of Manchester)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Conjunction (astronomy); Computer science; Medical physics; Medicine; Physics","score_opus":0.05420612094904712,"score_gpt":0.3334195595498033,"score_spread":0.27921343860075615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3136531031","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9613358,0.00009169331,0.00013438702,0.034698762,0.000078657235,0.00030369707,0.0000031381574,0.000011011155,0.003342903],"genre_scores_gemma":[0.9985362,0.00009802532,0.00010715121,0.00013471783,0.000093797724,0.0000029948455,0.0000068426143,0.000013900401,0.0010063681],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99805754,0.00008071782,0.00019099373,0.00036095933,0.0009728221,0.00033697265],"domain_scores_gemma":[0.9983606,0.00063795,0.00016546693,0.00033219976,0.00027622472,0.00022757331],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015430114,0.00013864356,0.00029103836,0.00028441875,0.00036134647,0.00008118463,0.0005624981,0.000092314076,0.00058929966],"category_scores_gemma":[0.0017755285,0.00011551769,0.00003869938,0.00009159417,0.0008135318,0.00042928118,0.00033979627,0.0008582144,0.000010018621],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014629168,0.00025488395,0.90747374,0.0003077096,0.00015454892,0.0010449641,0.010915411,0.00038930913,0.00019849172,0.000038312734,0.060946316,0.016813383],"study_design_scores_gemma":[0.0035368986,0.000064872525,0.76205933,0.0015597816,0.00004365593,0.00009732434,0.009849864,0.1588402,0.00007661583,0.000052504845,0.06359471,0.00022421624],"about_ca_topic_score_codex":0.046960276,"about_ca_topic_score_gemma":0.12892257,"teacher_disagreement_score":0.15845089,"about_ca_system_score_codex":0.0004182751,"about_ca_system_score_gemma":0.0007119294,"threshold_uncertainty_score":0.9593861},"labels":[],"label_agreement":null},{"id":"W3137663578","doi":"10.3348/kjr.2020.1104","title":"Machine Learning-Based Prediction of COVID-19 Severity and Progression to Critical Illness Using CT Imaging and Clinical Data","year":2021,"lang":"en","type":"article","venue":"Korean Journal of Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"National Institute of Diabetes and Digestive and Kidney Diseases; National Cancer Institute; National Institute of Biomedical Imaging and Bioengineering; National Institute of Mental Health; National Institutes of Health","keywords":"Medicine; Concordance; Receiver operating characteristic; Severity of illness; Coronavirus disease 2019 (COVID-19); Internal medicine; Cohort; Radiology; Disease","score_opus":0.04698456969688169,"score_gpt":0.40982026300893853,"score_spread":0.36283569331205684,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3137663578","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89575225,0.004002792,0.083329044,0.01623349,0.00049988844,0.0001095533,0.000028966057,0.00001726171,0.000026730173],"genre_scores_gemma":[0.9708388,0.00046751488,0.026841572,0.0014108857,0.00037054566,3.8483395e-7,0.00004719278,0.000017987102,0.0000051272896],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979209,0.0006513885,0.00069480855,0.00030511036,0.00022294874,0.00020488504],"domain_scores_gemma":[0.9978144,0.0008457468,0.00026538115,0.00024429598,0.00019702932,0.0006331017],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0026457468,0.00012487074,0.0006093619,0.00015619621,0.00012256949,0.000019279232,0.00012698959,0.000061051,0.000033382643],"category_scores_gemma":[0.01432688,0.000098917386,0.00006738302,0.00013230066,0.0005326026,0.00010230133,0.00016401938,0.00085498695,1.7249752e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005154266,0.00017542607,0.93523973,0.00023405571,0.000103328435,0.0019861949,0.00017241227,0.00034707255,0.002798496,0.000060340066,0.0008463094,0.057521194],"study_design_scores_gemma":[0.006215422,0.0013060898,0.13268735,0.00079224317,0.00072900427,0.072522484,0.00045113428,0.76859134,0.00032470544,0.00029416307,0.015859796,0.00022628442],"about_ca_topic_score_codex":0.000026527867,"about_ca_topic_score_gemma":0.0000017540091,"teacher_disagreement_score":0.8025524,"about_ca_system_score_codex":0.00004742324,"about_ca_system_score_gemma":0.00049052143,"threshold_uncertainty_score":0.9939759},"labels":[],"label_agreement":null},{"id":"W3137777844","doi":"10.1007/s00259-021-05303-5","title":"[18F]FDG PET radiomics to predict disease-free survival in cervical cancer: a multi-scanner/center study with external validation","year":2021,"lang":"en","type":"article","venue":"European Journal of Nuclear Medicine and Molecular Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":62,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre","funders":"Horizon 2020; European Commission","keywords":"Medicine; Radiomics; Cervical cancer; Nuclear medicine; PET-CT; Radiology; Cancer; Positron emission tomography; Center (category theory); Medical physics; Internal medicine","score_opus":0.013480226580352651,"score_gpt":0.2834031396877651,"score_spread":0.26992291310741245,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3137777844","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9485809,0.0012020933,0.007808403,0.041259173,0.00033473127,0.00025115916,0.000005320928,0.000022279393,0.00053593365],"genre_scores_gemma":[0.98392266,0.00026436284,0.007038764,0.008153271,0.0004813613,0.0000013915654,0.000006518425,0.0000948393,0.00003682852],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9975468,0.00052089413,0.00059985666,0.0003417327,0.00068697834,0.00030374122],"domain_scores_gemma":[0.9984771,0.000045433397,0.00021033573,0.00032690394,0.00025143297,0.00068881945],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012714135,0.0002266608,0.0005105952,0.00030426643,0.00007130097,0.00006308004,0.00022979286,0.000008805822,0.000069749],"category_scores_gemma":[0.0007494361,0.00017079004,0.00008203618,0.00028200608,0.00012127655,0.000116915566,0.00016859811,0.00068114384,0.0000027183376],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022041327,0.0013336979,0.75071067,0.00023558887,0.0003824974,0.17058784,0.0051457738,0.0006939059,0.03411578,0.000056909386,0.0069102077,0.02762298],"study_design_scores_gemma":[0.048417937,0.0027716598,0.8562019,0.0070396457,0.0013047882,0.012547219,0.008536173,0.022167586,0.00017219693,0.000030020516,0.040105503,0.0007053801],"about_ca_topic_score_codex":0.000047759553,"about_ca_topic_score_gemma":0.0000067471096,"teacher_disagreement_score":0.15804063,"about_ca_system_score_codex":0.00007885315,"about_ca_system_score_gemma":0.00013171737,"threshold_uncertainty_score":0.69646156},"labels":[],"label_agreement":null},{"id":"W3137818185","doi":"10.1007/s00259-021-05244-z","title":"Convolutional neural networks for PET functional volume fully automatic segmentation: development and validation in a multi-center setting","year":2021,"lang":"en","type":"article","venue":"European Journal of Nuclear Medicine and Molecular Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre","funders":"H2020 Marie Skłodowska-Curie Actions","keywords":"Ground truth; Context (archaeology); Computer science; Artificial intelligence; Segmentation; Positron emission tomography; Residual; Convolutional neural network; Upsampling; Nuclear medicine; Volume (thermodynamics); Pattern recognition (psychology); Algorithm; Medicine; Image (mathematics)","score_opus":0.016973354105628627,"score_gpt":0.2708718456128037,"score_spread":0.2538984915071751,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3137818185","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7803474,0.001859679,0.18481499,0.03220482,0.0003566439,0.0001769775,9.356571e-7,0.000020428024,0.00021812516],"genre_scores_gemma":[0.92926407,0.000052969473,0.062308915,0.008015025,0.00024894325,0.0000010810874,0.00004194848,0.000037117843,0.00002991054],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99877304,0.00017212483,0.00048986444,0.00016589365,0.00023276689,0.00016629715],"domain_scores_gemma":[0.99935323,0.000054855624,0.00019798132,0.000058830126,0.00018089401,0.00015421794],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010243326,0.00011635686,0.00023165195,0.00014600501,0.000096858275,0.000037752572,0.000037093294,0.000009852898,0.000036874837],"category_scores_gemma":[0.00041050767,0.0001007158,0.00004557056,0.0000863262,0.0000910065,0.00010175226,0.000043596596,0.00030256124,7.8769233e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00066051376,0.0008906384,0.15565465,0.0011900744,0.00073504803,0.022326471,0.01063991,0.0036235787,0.10631153,0.0003411522,0.032898605,0.6647278],"study_design_scores_gemma":[0.0146089075,0.00021242764,0.0813003,0.0011672702,0.00017795457,0.011519242,0.0021344395,0.8620352,0.00010268836,0.000012717437,0.026528424,0.00020040995],"about_ca_topic_score_codex":9.619744e-7,"about_ca_topic_score_gemma":1.4126631e-7,"teacher_disagreement_score":0.8584116,"about_ca_system_score_codex":0.0000427505,"about_ca_system_score_gemma":0.00005989576,"threshold_uncertainty_score":0.4107071},"labels":[],"label_agreement":null},{"id":"W3137825840","doi":"10.1038/s41598-021-85016-9","title":"Comparative analysis of machine learning algorithms for computer-assisted reporting based on fully automated cross-lingual RadLex mappings","year":2021,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Bundesministerium für Wirtschaft und Energie; Bundesministerium für Bildung und Forschung; Universität Heidelberg","keywords":"Computer science; Artificial intelligence; Machine learning; Algorithm; Data mining","score_opus":0.03839571526579122,"score_gpt":0.3742402747972259,"score_spread":0.33584455953143466,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3137825840","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9595609,0.00012728882,0.035540793,0.00044640398,0.0026250696,0.00045710948,0.000015872045,0.00040948213,0.0008171066],"genre_scores_gemma":[0.9409997,0.000001062545,0.05525067,0.00019104604,0.00011987861,0.000017704773,0.0020052367,0.000025600722,0.0013890977],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9952173,0.00013662524,0.0021299873,0.0011408661,0.0009335502,0.00044165805],"domain_scores_gemma":[0.99471754,0.00035006995,0.002730456,0.0007780146,0.0011697386,0.00025419553],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0045008087,0.00025558076,0.001215745,0.00073198316,0.00049029314,0.0002751834,0.0001029995,0.000108611435,0.00010964776],"category_scores_gemma":[0.003993419,0.00022747675,0.0006144906,0.0023235818,0.00036546678,0.000072117866,0.000072959025,0.00046801448,0.000001376074],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036206358,0.0018079975,0.28088102,0.000873436,0.003998176,0.010562388,0.003045582,0.50093,0.1576575,0.000047285983,0.0066619613,0.03317256],"study_design_scores_gemma":[0.00080661156,0.00016458222,0.03786474,0.00023538785,0.0007822817,0.00040482497,0.00008102455,0.9366944,0.015281845,0.00002629493,0.0074573043,0.00020073872],"about_ca_topic_score_codex":0.00006169985,"about_ca_topic_score_gemma":0.000007840483,"teacher_disagreement_score":0.43576434,"about_ca_system_score_codex":0.0001080746,"about_ca_system_score_gemma":0.0005575101,"threshold_uncertainty_score":0.9276233},"labels":[],"label_agreement":null},{"id":"W3138618268","doi":"10.1029/2021jg006261","title":"Letter of Appreciation to Our 2020 Reviewers in the Time of COVID‐19","year":2021,"lang":"en","type":"article","venue":"Journal of Geophysical Research Biogeosciences","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Trent University","funders":"","keywords":"Coronavirus disease 2019 (COVID-19); Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); 2019-20 coronavirus outbreak; Psychology; Data science; Computer science; Medicine; Virology","score_opus":0.04634652508861991,"score_gpt":0.4147037169633191,"score_spread":0.3683571918746992,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3138618268","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.82205886,0.00055761606,0.00036885275,0.176188,0.0001216477,0.00017163395,0.0000039929328,0.0000015171162,0.00052786205],"genre_scores_gemma":[0.992799,0.0004593968,0.0018738415,0.0039946884,0.00053523737,0.0000025300233,0.000002184258,0.0000048059374,0.00032830416],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99689215,0.00052868226,0.00045196235,0.00013709521,0.0017581899,0.00023193925],"domain_scores_gemma":[0.9982333,0.00063862174,0.00019027584,0.00016629141,0.0005318571,0.00023964571],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006312137,0.000057797624,0.00033916355,0.00022601473,0.000054807337,0.000025871308,0.0003657584,0.000029169156,0.00003522983],"category_scores_gemma":[0.013611714,0.000032379616,0.00013626667,0.00161665,0.0002228979,0.000087582164,0.0000765354,0.00057751813,0.000010704165],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005817592,0.0019052884,0.100656986,0.0008598096,0.00010634285,0.0009030727,0.00640948,0.000077323595,0.5803222,0.0013318986,0.20963293,0.09721291],"study_design_scores_gemma":[0.003487614,0.0059498926,0.5723638,0.0029133966,0.00014429486,0.0005790172,0.008914456,0.007624612,0.017943414,0.00793524,0.37179023,0.00035405386],"about_ca_topic_score_codex":0.00039034564,"about_ca_topic_score_gemma":0.000006209556,"teacher_disagreement_score":0.56237876,"about_ca_system_score_codex":0.000048035596,"about_ca_system_score_gemma":0.0006938463,"threshold_uncertainty_score":0.99469703},"labels":[],"label_agreement":null},{"id":"W3139280509","doi":"10.1186/s13023-021-01777-6","title":"Correction to: A guide to writing systematic reviews of rare disease treatments to generate FAIRcompliant datasets: building a Treatabolome","year":2021,"lang":"en","type":"erratum","venue":"Orphanet Journal of Rare Diseases","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Ottawa Hospital; Children's Hospital of Eastern Ontario","funders":"Medical Research Council; National Institute for Health and Care Research; Ataxia UK; Wellcome Trust","keywords":"Human genetics; Data science; Computational biology; Computer science; Information retrieval; Bioinformatics; Medicine; Biology; Genetics","score_opus":0.021171445513083156,"score_gpt":0.33968825396447894,"score_spread":0.3185168084513958,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3139280509","genre_codex":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.055204313,0.7162426,0.04023716,0.016666654,0.118154086,0.024305496,0.026375992,0.00037594856,0.0024377275],"genre_scores_gemma":[0.10968338,0.1184518,0.18162803,0.08268745,0.08419492,0.0041379565,0.102638505,0.0035690055,0.31300893],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9946422,0.00061341835,0.0024030565,0.00064690557,0.0011513954,0.00054304407],"domain_scores_gemma":[0.9941576,0.00036055385,0.0015429315,0.00088522275,0.00060508325,0.0024485756],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008354118,0.00066128024,0.0031139078,0.0008510461,0.0001516941,0.00016481418,0.00051345536,0.00011561358,0.0003010106],"category_scores_gemma":[0.013301865,0.0005010791,0.0007636583,0.0007594171,0.00003901689,0.00017662061,0.00021524515,0.0007292233,0.00003482699],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044264155,0.00040624113,0.0009780221,0.021660095,0.00063602586,0.005028239,0.00013853669,0.00037420858,0.0007064212,0.0000021643293,0.9617209,0.007906531],"study_design_scores_gemma":[0.00310077,0.0015951693,0.0049805185,0.3867279,0.012028499,0.0031021833,0.0006245953,0.0019611528,0.00016540311,0.000009815864,0.58456975,0.0011342299],"about_ca_topic_score_codex":0.000080163256,"about_ca_topic_score_gemma":0.000005152364,"teacher_disagreement_score":0.59779084,"about_ca_system_score_codex":0.00052386674,"about_ca_system_score_gemma":0.0010178611,"threshold_uncertainty_score":0.99974406},"labels":[],"label_agreement":null},{"id":"W3139466633","doi":"10.1016/j.ctro.2021.03.002","title":"Ultrasound delta-radiomics during radiotherapy to predict recurrence in patients with head and neck squamous cell carcinoma","year":2021,"lang":"en","type":"article","venue":"Clinical and Translational Radiation Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; University of Toronto; Sunnybrook Health Science Centre","funders":"Terry Fox Foundation","keywords":"Medicine; Radiomics; Head and neck squamous-cell carcinoma; Radiation therapy; Radiology; Cetuximab; Ultrasound; Head and neck cancer; Larynx; Oncology; Internal medicine; Surgery; Cancer","score_opus":0.014871748479022966,"score_gpt":0.32792796016726483,"score_spread":0.3130562116882419,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3139466633","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99304706,0.0007899511,0.0009276586,0.004495228,0.00016318752,0.0002951355,0.000018969806,0.000014966038,0.00024783993],"genre_scores_gemma":[0.9910589,0.00030991566,0.0068888287,0.001351627,0.00019160911,0.000011321084,0.00012847169,0.000015648946,0.00004371205],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9986237,0.00013997093,0.00047090108,0.0003856117,0.00018460234,0.00019517363],"domain_scores_gemma":[0.99867815,0.00076515105,0.00007694386,0.00010390783,0.00008623339,0.00028962808],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030371398,0.00012541573,0.00036529935,0.000095306896,0.000077234916,0.000018031484,0.00003871811,0.00014079335,0.00004261185],"category_scores_gemma":[0.00034316085,0.00011001165,0.000042534026,0.00018981272,0.00014975313,0.0000727259,0.000008979534,0.00040388358,0.0000014515623],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00074094837,0.00039400323,0.96597105,0.00004469021,0.000015848753,0.000035433553,0.0003152155,0.00024596823,0.000053179658,0.00009856234,0.000058567828,0.032026537],"study_design_scores_gemma":[0.012725822,0.00084014086,0.9796917,0.00002998713,0.000038596136,0.00006972798,0.000014120018,0.002810957,0.000018277378,0.000094162635,0.003550197,0.00011633955],"about_ca_topic_score_codex":0.000015674366,"about_ca_topic_score_gemma":0.000025880398,"teacher_disagreement_score":0.031910196,"about_ca_system_score_codex":0.000042027972,"about_ca_system_score_gemma":0.00026548165,"threshold_uncertainty_score":0.4486145},"labels":[],"label_agreement":null},{"id":"W3139527322","doi":"10.1038/s41598-021-85221-6","title":"Assessment of clinical radiosensitivity in patients with head-neck squamous cell carcinoma from pre-treatment quantitative ultrasound radiomics","year":2021,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; Sunnybrook Hospital; University of Toronto; Sunnybrook Health Science Centre","funders":"National Center for Advancing Translational Sciences; Terry Fox Foundation","keywords":"Radiomics; Medicine; Head and neck squamous-cell carcinoma; Head and neck; Ultrasound; Radiosensitivity; Basal cell; Oncology; Radiology; Radiation therapy; Head and neck cancer; Internal medicine; Surgery","score_opus":0.019690996945579083,"score_gpt":0.3429792051487967,"score_spread":0.32328820820321763,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3139527322","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9952179,0.00017190349,0.0005275496,0.00012461194,0.0022944217,0.0005157265,0.000018031058,0.000023806386,0.0011060005],"genre_scores_gemma":[0.9788575,0.000008664309,0.01996982,0.00006005673,0.000066604705,0.000008623082,0.00051326765,0.00002792906,0.00048750284],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99640006,0.0002848081,0.0011283809,0.0010367706,0.0008057631,0.00034422867],"domain_scores_gemma":[0.9971983,0.0005847049,0.0006013615,0.0009564075,0.0003759934,0.00028323493],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014557254,0.00022821952,0.00086322095,0.00014859326,0.000108772976,0.00007607051,0.000066454966,0.00010443728,0.00006294963],"category_scores_gemma":[0.0010242264,0.00017575255,0.00019556751,0.00046487976,0.0004332538,0.00010496505,0.000047298614,0.00039166404,0.0000020343266],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013498604,0.002228557,0.98848647,0.00005379357,0.000051622173,0.0022925118,0.00047122253,0.0002749359,0.0040581776,0.000018266725,0.0003177821,0.0016116847],"study_design_scores_gemma":[0.0038726495,0.0006756554,0.98615956,0.00011457915,0.00014401348,0.00010986107,0.00013846587,0.003115796,0.004573424,0.00013463853,0.00078800117,0.0001733415],"about_ca_topic_score_codex":0.0005969471,"about_ca_topic_score_gemma":0.00012498994,"teacher_disagreement_score":0.01944227,"about_ca_system_score_codex":0.00023520036,"about_ca_system_score_gemma":0.001188608,"threshold_uncertainty_score":0.71669805},"labels":[],"label_agreement":null},{"id":"W3141830614","doi":"10.2196/23808","title":"Neural Network Pattern Recognition of Ultrasound Image Gray Scale Intensity Histograms of Breast Lesions to Differentiate Between Benign and Malignant Lesions: Analytical Study","year":2021,"lang":"en","type":"article","venue":"JMIR Biomedical Engineering","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Histogram; Grayscale; Artificial intelligence; Ultrasound; Medicine; Artificial neural network; Pattern recognition (psychology); Pathology; Radiology; Computer science; Image (mathematics)","score_opus":0.01434105579816245,"score_gpt":0.27467254545145897,"score_spread":0.2603314896532965,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3141830614","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9670888,0.000086053435,0.03127068,0.0009331646,0.00018278972,0.0003338551,0.00004017007,0.000053028863,0.00001144218],"genre_scores_gemma":[0.9960093,0.000024308561,0.0033827128,0.000096880554,0.00027684547,0.000016509823,0.00014784586,0.00003144848,0.000014171668],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9981776,0.000062247265,0.00058185443,0.00037300307,0.00045339603,0.0003518934],"domain_scores_gemma":[0.9986985,0.0002467573,0.00008824894,0.00026274467,0.00015746786,0.00054628076],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038309844,0.00020270149,0.0006872516,0.0001794855,0.000055486544,0.000019062301,0.0000980395,0.00010670307,0.00006775033],"category_scores_gemma":[0.00041919175,0.000169174,0.00013091028,0.0005083595,0.00016887972,0.000042852214,0.00015345978,0.00046878358,0.0000023138164],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002268775,0.0023235204,0.46967962,0.0012143828,0.00069760974,0.00059347844,0.0014899564,0.00024599393,0.115905985,0.000009632008,0.0012918635,0.40632108],"study_design_scores_gemma":[0.0015644908,0.00053943455,0.9639311,0.0010923661,0.00040081015,0.0003554491,0.0003642626,0.030608445,0.0006833988,0.000021986223,0.00018026945,0.00025800618],"about_ca_topic_score_codex":0.00008190825,"about_ca_topic_score_gemma":0.0000033355939,"teacher_disagreement_score":0.49425146,"about_ca_system_score_codex":0.000039600665,"about_ca_system_score_gemma":0.000037356207,"threshold_uncertainty_score":0.6898716},"labels":[],"label_agreement":null},{"id":"W3146908429","doi":"10.1007/s00261-021-03056-1","title":"Artificial intelligence in assessment of hepatocellular carcinoma treatment response","year":2021,"lang":"en","type":"review","venue":"Abdominal Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":19,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Thunder Bay Regional Health Sciences Centre","funders":"","keywords":"Medicine; Hepatocellular carcinoma; Hepatology; Radiomics; Internal medicine; Radiology; Oncology; Medical physics","score_opus":0.0629854694605953,"score_gpt":0.4092841409022283,"score_spread":0.346298671441633,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3146908429","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010416883,0.9858163,0.002158172,0.0002706201,0.00033140113,0.0007073436,0.000008724987,0.000013626421,0.00027692545],"genre_scores_gemma":[0.015884828,0.9784776,0.004893361,0.00005579309,0.00024135574,0.00011313156,0.00012727978,0.000050107403,0.00015653507],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99628437,0.0012674793,0.0012569977,0.00058494246,0.00020540571,0.0004008368],"domain_scores_gemma":[0.9975545,0.00129872,0.00038293216,0.0005343599,0.000057970832,0.00017151862],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013340068,0.00040439647,0.003395275,0.00049165374,0.000032640866,0.00000852049,0.00019082174,0.00038377673,0.00020447967],"category_scores_gemma":[0.00074257876,0.00031055204,0.000630746,0.0003941295,0.0002752306,0.000015900985,0.00006850121,0.0007966072,0.0000118389025],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020209262,0.0002825808,0.0013395734,0.0021244888,0.00019461027,0.0035623764,0.00010120902,0.000008569431,0.000055246914,0.00086092117,0.000032943277,0.9912354],"study_design_scores_gemma":[0.0007375874,0.0034354017,0.0010883014,0.013785713,0.002973025,0.009024697,0.00022250581,0.021693692,0.000078616984,0.0001968609,0.94604653,0.0007170827],"about_ca_topic_score_codex":0.0001494585,"about_ca_topic_score_gemma":0.0000039596966,"teacher_disagreement_score":0.99051833,"about_ca_system_score_codex":0.0006479657,"about_ca_system_score_gemma":0.0017646028,"threshold_uncertainty_score":0.9999347},"labels":[],"label_agreement":null},{"id":"W3152819053","doi":"10.1017/cjn.2019.98","title":"C.03 Deformation-based morphometry analysis of longitudinal low-grade glioma growth","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Neurological Sciences / Journal Canadien des Sciences Neurologiques","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mass effect; Magnetic resonance imaging; White matter; Lesion; Glioma; Medicine; Radiology; Nuclear medicine; Anatomy; Pathology; Computed tomography","score_opus":0.01861730442618205,"score_gpt":0.27714497875159727,"score_spread":0.25852767432541524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3152819053","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9923435,0.0004969872,0.00015878909,0.0048702485,0.00060708035,0.00014106923,0.000009382632,0.000013246747,0.0013596981],"genre_scores_gemma":[0.99445564,0.000074529395,0.0024293556,0.0028865954,0.00012913067,9.534004e-7,0.000001295899,0.0000100556745,0.000012454564],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99576515,0.00051343616,0.0010997946,0.00043997538,0.0011655847,0.0010160598],"domain_scores_gemma":[0.99554354,0.00074022205,0.0010531885,0.0001832001,0.0006617904,0.0018180315],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0044809836,0.00028274162,0.0009006808,0.0035869712,0.00089598255,0.0002994148,0.0013059418,0.00016680967,0.0004907962],"category_scores_gemma":[0.0031529448,0.0001840385,0.00055547187,0.004899765,0.0042151622,0.00061926094,0.000041268922,0.0013238753,0.000005198832],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000075256045,0.000047136844,0.97425437,0.000024068488,0.0000976841,0.0021353303,0.00010578048,0.021918776,0.0002480358,0.00034419147,0.00015338282,0.0005959732],"study_design_scores_gemma":[0.0006868142,0.029081307,0.871023,0.000091311755,0.00047968407,0.010073739,0.00013696053,0.08621058,0.00036635442,0.0013279767,0.0002597877,0.0002624875],"about_ca_topic_score_codex":0.0016317079,"about_ca_topic_score_gemma":0.004524865,"teacher_disagreement_score":0.103231385,"about_ca_system_score_codex":0.00020598418,"about_ca_system_score_gemma":0.0030741051,"threshold_uncertainty_score":0.9984948},"labels":[],"label_agreement":null},{"id":"W3152852152","doi":"10.1016/j.compmedimag.2021.101924","title":"Learnable image histograms-based deep radiomics for renal cell carcinoma grading and staging","year":2021,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":32,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; University of British Columbia","funders":"Nvidia","keywords":"Renal cell carcinoma; Computer science; Artificial intelligence; Grading (engineering); Histogram; Convolutional neural network; Radiology; Image histogram; Pattern recognition (psychology); Medicine; Image processing; Image texture; Image (mathematics); Pathology","score_opus":0.009041228140708143,"score_gpt":0.2655155306184199,"score_spread":0.2564743024777118,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3152852152","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31601104,0.0061088842,0.6598964,0.016559456,0.00056908256,0.00032469255,0.000008176717,0.00018574035,0.0003365351],"genre_scores_gemma":[0.787858,0.0010675223,0.19768208,0.011999013,0.0007098975,0.000035712175,0.0002475362,0.00012356976,0.00027664757],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99758476,0.00011858777,0.00047150307,0.0006943276,0.00050959556,0.00062119646],"domain_scores_gemma":[0.99789566,0.00052861054,0.00012992068,0.00031984464,0.00021062781,0.0009153576],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009352758,0.00031720052,0.0006498627,0.00025511242,0.00039703582,0.00019728807,0.00014601497,0.00013788385,0.000027718046],"category_scores_gemma":[0.0006882811,0.0003024271,0.00019172831,0.00032850658,0.0006375559,0.00011250578,0.00015186158,0.00088130427,7.7032195e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006882451,0.000945839,0.093062244,0.0050939764,0.00026143133,0.0054610455,0.0014974041,0.000055295874,0.11119182,0.004584006,0.011412296,0.7657464],"study_design_scores_gemma":[0.009102609,0.00012863913,0.002200211,0.00044630072,0.00025558335,0.0009251913,0.00014253912,0.9270763,0.0016472205,0.0008929544,0.056746487,0.0004359941],"about_ca_topic_score_codex":0.000050919603,"about_ca_topic_score_gemma":0.000001918938,"teacher_disagreement_score":0.92702097,"about_ca_system_score_codex":0.00004949124,"about_ca_system_score_gemma":0.00034340966,"threshold_uncertainty_score":0.9999428},"labels":[],"label_agreement":null},{"id":"W3153823012","doi":"10.1016/j.compbiomed.2021.104400","title":"The impact of the variation of imaging parameters on the robustness of Computed Tomography radiomic features: A review","year":2021,"lang":"en","type":"review","venue":"Computers in Biology and Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":84,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; Princess Margaret Cancer Centre; Ontario Institute for Cancer Research; University of Toronto; University Health Network","funders":"Canadian Institutes of Health Research; Princess Margaret Cancer Foundation","keywords":"Robustness (evolution); Radiomics; Computer science; Artificial intelligence; Computed tomography; Medical imaging; Data mining; Medical physics; Machine learning; Medicine; Radiology","score_opus":0.02264994673113062,"score_gpt":0.3714283807586041,"score_spread":0.3487784340274735,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3153823012","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007975378,0.9931903,0.001376697,0.0029616372,0.00070660334,0.0009026946,0.0000067046512,0.0000064039355,0.000051419862],"genre_scores_gemma":[0.0031920006,0.9956438,0.00046889763,0.00047811723,0.00012791458,0.000016344628,0.00004996155,0.000016488862,0.0000065031163],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.997419,0.0009892066,0.0009154764,0.0002909684,0.0001766529,0.0002086789],"domain_scores_gemma":[0.99515635,0.0031474193,0.00091852224,0.00060798274,0.000109714936,0.00005998731],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018911166,0.0002897211,0.002167029,0.00020403031,0.00009189033,0.0000028480335,0.00042523196,0.0001459475,0.0000063221974],"category_scores_gemma":[0.0011094917,0.00010691837,0.0005232388,0.00077740464,0.0014905174,0.000010386354,0.0001280638,0.00090657716,5.66933e-8],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000054745913,0.00011916397,0.0018236517,0.017851498,0.0012064032,0.000015088415,0.00034537457,0.00011397603,0.000021277016,0.00190569,0.0067300084,0.9698131],"study_design_scores_gemma":[0.0045008548,0.0015919115,0.029904822,0.86202013,0.0055118273,0.002065965,0.0001366243,0.013205665,0.000007156002,0.00064868445,0.07976927,0.00063709816],"about_ca_topic_score_codex":0.00010587081,"about_ca_topic_score_gemma":9.4687243e-7,"teacher_disagreement_score":0.96917605,"about_ca_system_score_codex":0.00004793381,"about_ca_system_score_gemma":0.0002423863,"threshold_uncertainty_score":0.54918736},"labels":[],"label_agreement":null},{"id":"W3154302568","doi":"","title":"Development of tensile testing machine for x-ray microtomography","year":2006,"lang":"en","type":"article","venue":"55th SPSJ Annual Meeting","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Nexen (Canada)","funders":"","keywords":"X-ray microtomography; Ultimate tensile strength; Materials testing; Materials science; Composite material; Physics; Optics","score_opus":0.01270999434364333,"score_gpt":0.2730319257712837,"score_spread":0.2603219314276404,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3154302568","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9787829,0.0005866354,0.00949754,0.00051623484,0.00021232638,0.0007145804,0.000024988,0.00015472759,0.009510049],"genre_scores_gemma":[0.5818441,0.0000013573206,0.41730192,0.00022979086,0.00027969666,0.000029281398,0.00004769712,0.000035419114,0.00023075622],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984201,0.0000236016,0.000602625,0.00029422363,0.0002662639,0.00039319607],"domain_scores_gemma":[0.99895185,0.0002559946,0.00023157979,0.0001622146,0.00028576763,0.000112594396],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008132939,0.00018379139,0.0003864159,0.00018917,0.0001907175,0.000015665553,0.0001055701,0.000067729474,0.0000118749695],"category_scores_gemma":[0.00085849455,0.0001570735,0.000116476804,0.00030488713,0.00008554594,0.000047842954,0.000051668667,0.00023566358,0.000003417044],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021765423,0.00050121365,0.28865135,0.0011879184,0.00017492025,0.00005603003,0.0017640316,0.0006173115,0.5615601,0.0003425773,0.0048085987,0.14011827],"study_design_scores_gemma":[0.014807672,0.0012758658,0.30015182,0.005818322,0.00073985534,0.0004464545,0.0026933216,0.099272095,0.15596521,0.0008978865,0.41587088,0.0020606031],"about_ca_topic_score_codex":0.0001688377,"about_ca_topic_score_gemma":0.000008617751,"teacher_disagreement_score":0.4110623,"about_ca_system_score_codex":0.000028785536,"about_ca_system_score_gemma":0.0001036041,"threshold_uncertainty_score":0.6405271},"labels":[],"label_agreement":null},{"id":"W3154535333","doi":"10.2214/ajr.21.25456","title":"Assessment of Renal Cell Carcinoma by Texture Analysis in Clinical Practice: A Six-Site, Six-Platform Analysis of Reliability","year":2021,"lang":"en","type":"article","venue":"American Journal of Roentgenology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; University of Ottawa","funders":"National Institute of Biomedical Imaging and Bioengineering","keywords":"Kurtosis; Medicine; Intraclass correlation; Software; Pearson product-moment correlation coefficient; Texture (cosmology); Reproducibility; Artificial intelligence; Pattern recognition (psychology); Skewness; Segmentation; Correlation; Image texture; Renal cell carcinoma; Nuclear medicine; Statistics; Image segmentation; Computer science; Pathology; Mathematics; Image (mathematics)","score_opus":0.00918467161824805,"score_gpt":0.3579846007332723,"score_spread":0.3487999291150243,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3154535333","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9864359,0.0007628154,0.008527362,0.0033136436,0.00010250405,0.00007202726,0.000018257084,0.0000037789619,0.0007637183],"genre_scores_gemma":[0.9785141,0.0005144484,0.020080699,0.0007161865,0.00006299437,0.0000011596698,0.000049583487,0.000013629622,0.00004719877],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9958781,0.0006799942,0.0021535705,0.00034972193,0.0006229107,0.0003157218],"domain_scores_gemma":[0.9945799,0.0011089239,0.0026522856,0.00051543873,0.00087581866,0.00026762416],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026230328,0.00017690904,0.002266234,0.0009977898,0.000026430618,0.000007764127,0.0002237267,0.00011962795,0.00022508758],"category_scores_gemma":[0.0025234406,0.00014512845,0.0009780984,0.0035971713,0.0005958166,0.00009793245,0.00008705765,0.0013026836,5.071266e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035156135,0.0013161418,0.96677613,0.000039182494,0.00474059,0.0004971465,0.00028927127,0.0046221446,0.007588374,0.000021546977,0.00039828496,0.013359643],"study_design_scores_gemma":[0.0019062888,0.0023184621,0.95717764,0.000031508025,0.015073023,0.00020668792,0.0017022181,0.019117447,0.00042645226,0.000013316017,0.0019101507,0.00011680702],"about_ca_topic_score_codex":0.00057402445,"about_ca_topic_score_gemma":0.000082982835,"teacher_disagreement_score":0.014495302,"about_ca_system_score_codex":0.00016045284,"about_ca_system_score_gemma":0.0006463646,"threshold_uncertainty_score":0.59181666},"labels":[],"label_agreement":null},{"id":"W3154545871","doi":"10.1016/j.phro.2021.04.001","title":"Automated detection of dental artifacts for large-scale radiomic analysis in radiation oncology","year":2021,"lang":"en","type":"article","venue":"Physics and Imaging in Radiation Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; Ontario Institute for Cancer Research; University of Toronto; University Health Network; Princess Margaret Cancer Centre","funders":"Canadian Institutes of Health Research; University of Toronto; Princess Margaret Cancer Foundation; University Health Network","keywords":"Radiation oncology; Precision oncology; Scale (ratio); Medical physics; Medicine; Radiation therapy; Computer science; Oncology; Radiology; Internal medicine; Cancer; Cartography","score_opus":0.008510105449662422,"score_gpt":0.3358730102121737,"score_spread":0.3273629047625113,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3154545871","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9598898,0.00077779184,0.036331125,0.0020032597,0.00031369427,0.00030402516,0.000012059279,0.000050617833,0.00031758254],"genre_scores_gemma":[0.9963521,0.00034144276,0.0023684644,0.0004899004,0.00015270297,0.000038642516,0.0002218762,0.00001743145,0.000017476641],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99862206,0.00017510632,0.00048698336,0.00032030407,0.00012193796,0.00027360316],"domain_scores_gemma":[0.9991348,0.00030381625,0.0002470306,0.00013327062,0.00009136753,0.000089758345],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00060581893,0.00012312579,0.0005613847,0.00040206304,0.000054898755,0.00001570285,0.000043021715,0.000100793906,0.000013491727],"category_scores_gemma":[0.00030494013,0.00013470619,0.00011474569,0.0008050943,0.000060474315,0.00012926372,0.000026019536,0.00025548358,0.0000014241688],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017142257,0.000651793,0.4847722,0.00009422183,0.00015516065,0.000041490424,0.0016459626,0.005370339,0.07221896,0.0002915964,0.00010981457,0.43447703],"study_design_scores_gemma":[0.003791912,0.00011967646,0.26077354,0.000019144662,0.00022160384,0.00003129961,0.00031836395,0.72610486,0.0049519045,0.0002873367,0.0032869822,0.000093377195],"about_ca_topic_score_codex":0.00014202303,"about_ca_topic_score_gemma":0.00023203017,"teacher_disagreement_score":0.72073454,"about_ca_system_score_codex":0.0004716262,"about_ca_system_score_gemma":0.00026430396,"threshold_uncertainty_score":0.54931587},"labels":[],"label_agreement":null},{"id":"W3156118784","doi":"10.82308/1615","title":"The use of Machine Learning System in Brachytherapy Treatment Planning","year":2020,"lang":"en","type":"article","venue":"eScholarship@McGill (McGill)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Brachytherapy; Radiation treatment planning; Computer science; Medical physics; Medicine; Radiation therapy; Radiology","score_opus":0.042699303196388726,"score_gpt":0.27428815555318214,"score_spread":0.2315888523567934,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3156118784","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9945586,0.00091548165,0.000010452678,0.000804351,0.00018113294,0.0005044406,0.000041721054,0.00020283436,0.0027810384],"genre_scores_gemma":[0.99680895,0.00035897145,0.0013979514,0.0008572518,0.000063157626,0.000031660304,0.00003029972,0.000085797445,0.0003659497],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974181,0.00040642347,0.00071323215,0.0004879135,0.00047705954,0.0004972417],"domain_scores_gemma":[0.9982104,0.00069147465,0.0002906709,0.0003497745,0.000087177985,0.00037051222],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006903313,0.0003300408,0.00063981925,0.00013314157,0.0005458872,0.000052281255,0.00021339653,0.00013730502,0.000024554682],"category_scores_gemma":[0.0014283843,0.00023258557,0.00021123503,0.00045973697,0.0001066155,0.00023115597,0.00008829974,0.0012179238,0.000025667103],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018476886,0.0004022194,0.06212037,0.0005688596,0.0006258693,0.0013392039,0.0001868707,0.0152771305,0.07804772,0.026808895,0.000013409681,0.8127618],"study_design_scores_gemma":[0.009003355,0.0023317516,0.010667703,0.0013262501,0.00026969003,0.00038517546,0.0005827966,0.15740512,0.01416808,0.00021721394,0.8029151,0.00072773243],"about_ca_topic_score_codex":0.00050348917,"about_ca_topic_score_gemma":0.000026390499,"teacher_disagreement_score":0.812034,"about_ca_system_score_codex":0.0004196679,"about_ca_system_score_gemma":0.000035877434,"threshold_uncertainty_score":0.94845647},"labels":[],"label_agreement":null},{"id":"W3156310576","doi":"10.1016/j.compbiomed.2021.104409","title":"Radiomics analysis on CT images for prediction of radiation-induced kidney damage by machine learning models","year":2021,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":36,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Iran University of Medical Sciences","keywords":"Random forest; Kidney disease; Radiomics; Medicine; Decision tree; Naive Bayes classifier; Artificial intelligence; Receiver operating characteristic; Radiology; Radiation therapy; Machine learning; Support vector machine; Computer science; Internal medicine","score_opus":0.017752542658745114,"score_gpt":0.3093749892375661,"score_spread":0.291622446578821,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3156310576","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.656007,0.004020447,0.32515454,0.012792676,0.0007497998,0.00041252657,0.00010530506,0.00006320574,0.0006945221],"genre_scores_gemma":[0.98834985,0.0017375698,0.005562597,0.002433085,0.00020501009,0.000011851097,0.001560385,0.000015495556,0.00012413699],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99880064,0.00013911021,0.0003947853,0.00036309578,0.000100877514,0.00020147092],"domain_scores_gemma":[0.99897105,0.0004606435,0.00013918306,0.00018147104,0.000067435554,0.00018024359],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006154966,0.00015072936,0.00064264686,0.00036348734,0.0000744463,0.0000044748786,0.00006919996,0.00008777583,0.000018468452],"category_scores_gemma":[0.00090569834,0.00012218027,0.00008483198,0.00041753292,0.00018845477,0.000037994694,0.000032769807,0.00039624987,1.9162403e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007307262,0.00055465574,0.5032611,0.0005730915,0.0020766754,0.00013834433,0.0014881382,0.006249254,0.19789574,0.0077383495,0.017738206,0.26155573],"study_design_scores_gemma":[0.008223432,0.0012317493,0.02298322,0.00041361066,0.00082181476,0.00007411801,0.00011823484,0.9536824,0.004962172,0.0018755682,0.0054463237,0.00016736239],"about_ca_topic_score_codex":0.00006790795,"about_ca_topic_score_gemma":0.0000012185144,"teacher_disagreement_score":0.9474331,"about_ca_system_score_codex":0.000042113737,"about_ca_system_score_gemma":0.000063270876,"threshold_uncertainty_score":0.4982367},"labels":[],"label_agreement":null},{"id":"W3156476574","doi":"10.1017/cjn.2019.181","title":"P.083 Radiology reporting of low-grade glioma growth underestimates tumor expansion","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Neurological Sciences / Journal Canadien des Sciences Neurologiques","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine; Radiological weapon; Glioma; Nuclear medicine; Magnetic resonance imaging; Radiology; Gold standard (test)","score_opus":0.027376343441077658,"score_gpt":0.2980629863807558,"score_spread":0.27068664293967815,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3156476574","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9892816,0.00081396295,0.00006012272,0.007078933,0.0010458209,0.00018106426,0.0000027288509,0.000018750909,0.0015170411],"genre_scores_gemma":[0.992293,0.00014427376,0.0043700393,0.0029247967,0.00023358827,0.0000010285789,4.1651919e-7,0.000015246604,0.000017584889],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.994715,0.0006433639,0.0020620206,0.0005300636,0.0008464421,0.0012031092],"domain_scores_gemma":[0.99370056,0.0007733939,0.0029891867,0.00018195748,0.0005672979,0.0017876292],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.00692606,0.0003057063,0.0009886367,0.0011668472,0.0009908772,0.00022484225,0.0012046678,0.00016707674,0.00021909241],"category_scores_gemma":[0.012647354,0.00019563353,0.00033837615,0.0012411012,0.0055337055,0.0005386706,0.00007079972,0.0016187113,0.0000037213686],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009135201,0.00003913444,0.9820312,0.00004536481,0.000019916935,0.010616896,0.00018295876,0.002163536,0.0026724213,0.00078358146,0.0004111897,0.0009424342],"study_design_scores_gemma":[0.0011970506,0.07595564,0.60795504,0.0004183689,0.00010803011,0.27772024,0.00040236668,0.015522033,0.0020817297,0.017629076,0.0005359015,0.0004745612],"about_ca_topic_score_codex":0.0014498922,"about_ca_topic_score_gemma":0.0022986913,"teacher_disagreement_score":0.3740762,"about_ca_system_score_codex":0.00016580391,"about_ca_system_score_gemma":0.0036586036,"threshold_uncertainty_score":0.99717265},"labels":[],"label_agreement":null},{"id":"W3156631419","doi":"10.1158/1557-3265.radsci21-po-071","title":"Abstract PO-071: Characterizing transcriptomic indicators of radiosensitivity in cancer and identifying sensitizing therapeutic agents","year":2021,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University Health Network","funders":"","keywords":"Radiosensitivity; Transcriptome; Computational biology; Cancer; Radiogenomics; Personalized medicine; Precision medicine; Radiation therapy; Cancer research; Gene signature; Gene; Medicine; Bioinformatics; Biology; Oncology; Gene expression; Genetics; Internal medicine; Radiomics","score_opus":0.20042949771509042,"score_gpt":0.5208171468069441,"score_spread":0.3203876490918537,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3156631419","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9870625,0.004689,0.000038398575,0.0071960716,0.00040033454,0.00026908857,0.000012186229,0.000020377915,0.00031203686],"genre_scores_gemma":[0.98836195,0.009748041,0.00014213903,0.0012078447,0.00034315532,0.00002133596,0.000010429476,0.000039410403,0.00012569553],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9969242,0.0004949427,0.00076511886,0.0005714849,0.000689715,0.0005545265],"domain_scores_gemma":[0.99811554,0.0009284978,0.00013808544,0.00029526567,0.00019287138,0.0003297277],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0042772004,0.00015395318,0.00068446394,0.0003528218,0.000117229654,0.000051025178,0.00011076735,0.00017887536,0.00018951752],"category_scores_gemma":[0.00095625105,0.00014352692,0.00015304539,0.00068329764,0.00054158695,0.00010866682,0.000103406426,0.002125847,0.0000038627395],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029669746,0.00027132712,0.54597634,0.00067305716,0.00017428053,0.0008243536,0.00087360566,0.0000065744466,0.14263059,0.000041295054,0.00014516109,0.3080867],"study_design_scores_gemma":[0.0021394177,0.00006264197,0.9823178,0.0013776611,0.000054855456,0.000039912808,0.0003504769,0.0011572941,0.010704989,0.00008456135,0.0015711257,0.0001392546],"about_ca_topic_score_codex":0.001057994,"about_ca_topic_score_gemma":0.00018088002,"teacher_disagreement_score":0.43634146,"about_ca_system_score_codex":0.00018185505,"about_ca_system_score_gemma":0.0006870809,"threshold_uncertainty_score":0.92358655},"labels":[],"label_agreement":null},{"id":"W3157197682","doi":"10.82308/30724","title":"Radiomics: enabling factors towards precision medicine","year":2018,"lang":"en","type":"article","venue":"eScholarship@McGill (McGill)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; McGill University","keywords":"Radiomics; Precision medicine; Computer science; Medicine; Artificial intelligence","score_opus":0.025273905253502205,"score_gpt":0.2922402436496616,"score_spread":0.2669663383961594,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3157197682","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92915297,0.00033968495,0.000039964583,0.0008429663,0.0017464651,0.00052754814,0.00005229831,0.00045129124,0.06684684],"genre_scores_gemma":[0.98944515,0.0003263282,0.0044928105,0.00249883,0.0007608592,0.000018352075,0.00008266505,0.0001693978,0.0022056042],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99557096,0.00026328082,0.0009685997,0.0010570025,0.001183439,0.0009567057],"domain_scores_gemma":[0.9968746,0.00039485822,0.00032296832,0.00095490704,0.00047099404,0.0009816911],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002115061,0.00060156744,0.0009782632,0.0005831346,0.001065713,0.00005410186,0.00054544513,0.0003803787,0.0013355933],"category_scores_gemma":[0.006242671,0.00047285872,0.00029111403,0.0008196957,0.00058992853,0.0004756249,0.00028330786,0.0016814629,0.0003005653],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004499543,0.00029386987,0.0023545022,0.00019686119,0.00034285503,0.00024139282,0.000074924224,0.000019158291,0.22717744,0.017362699,0.00023662661,0.75124973],"study_design_scores_gemma":[0.007812347,0.002340607,0.013157725,0.001715176,0.0006319489,0.0007171538,0.00045905984,0.002882941,0.12549824,0.015045465,0.8283637,0.0013756192],"about_ca_topic_score_codex":0.00053363905,"about_ca_topic_score_gemma":0.000023672224,"teacher_disagreement_score":0.8281271,"about_ca_system_score_codex":0.00060227036,"about_ca_system_score_gemma":0.00007604011,"threshold_uncertainty_score":0.9997723},"labels":[],"label_agreement":null},{"id":"W3157660905","doi":"10.1007/s10278-022-00767-9","title":"Deep Learning Body Region Classification of MRI and CT Examinations","year":2023,"lang":"en","type":"article","venue":"Journal of Digital Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; St. Clair College","funders":"","keywords":"Medicine; Artificial intelligence; Retrospective cohort study; Magnetic resonance imaging; Medical imaging; Radiology; Confounding; Computer science; Nuclear medicine; Pathology","score_opus":0.017136046776879348,"score_gpt":0.29846061793649614,"score_spread":0.2813245711596168,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3157660905","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96558976,0.00047585223,0.022526067,0.0063312915,0.0001588261,0.00007396264,4.4817048e-7,0.000042795687,0.0048009856],"genre_scores_gemma":[0.9986664,0.00024494517,0.0005370163,0.00005228335,0.00012844156,6.1527874e-7,0.000007889454,0.000016976726,0.0003454353],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99909014,0.00002588736,0.00038912933,0.00009560041,0.00026631192,0.00013295733],"domain_scores_gemma":[0.99911845,0.0001625187,0.00035147904,0.00007776209,0.00017466827,0.0001151307],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038309363,0.00007547559,0.0002202534,0.0003504746,0.00005961309,0.000071980896,0.00006019099,0.000013551234,0.0000039625284],"category_scores_gemma":[0.0010979781,0.00006354019,0.00007708497,0.0002801297,0.000101458376,0.00042327002,0.00003174527,0.0003618335,0.0000036537415],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003453283,0.00008819073,0.62744147,0.00013547733,0.000082354854,0.0004745857,0.0007295918,0.0002902052,0.014365617,0.00048617783,0.0012675774,0.3546042],"study_design_scores_gemma":[0.0016687986,0.0002209612,0.67686284,0.0006153924,0.00015893826,0.0043938053,0.0020456817,0.30182403,0.0004189589,0.0010757848,0.010561728,0.0001530512],"about_ca_topic_score_codex":0.000002200101,"about_ca_topic_score_gemma":7.100384e-8,"teacher_disagreement_score":0.35445115,"about_ca_system_score_codex":0.00003263051,"about_ca_system_score_gemma":0.00003863408,"threshold_uncertainty_score":0.25910938},"labels":[],"label_agreement":null},{"id":"W3158596096","doi":"10.1038/s41598-021-87564-6","title":"The ANTsX ecosystem for quantitative biological and medical imaging","year":2021,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":403,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Douglas Mental Health University Institute","funders":"National Institute of Neurological Disorders and Stroke; Office of Naval Research; National Heart, Lung, and Blood Institute; Canadian Institutes of Health Research; Cohen Veterans Bioscience; National Institute on Aging; National Institutes of Health; Alzheimer's Disease Neuroimaging Initiative","keywords":"Computer science; Python (programming language); Workflow; Software; Normalization (sociology); Deep learning; Visualization; Interfacing; Artificial intelligence; Machine learning; Data science; Software engineering; Data mining; Programming language","score_opus":0.021252614027167126,"score_gpt":0.3330902779849891,"score_spread":0.311837663957822,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3158596096","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94929713,0.006202879,0.010310574,0.023981271,0.007742172,0.00044519984,0.000002775509,0.000063038846,0.001954938],"genre_scores_gemma":[0.9935531,0.00013866738,0.003698273,0.00036566128,0.00017602033,0.000024934907,0.000046662106,0.000013884054,0.0019827664],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99829906,0.00007438801,0.0003808502,0.00051738234,0.0004503972,0.00027791213],"domain_scores_gemma":[0.9985877,0.00046011814,0.0001261944,0.0003482124,0.00023260286,0.0002451536],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036035157,0.000089970454,0.00020808459,0.00004040375,0.0005907727,0.00021941452,0.000061348044,0.000046802215,0.00007289528],"category_scores_gemma":[0.0067005465,0.000051734005,0.000084598345,0.00017816496,0.00043664355,0.0000431769,0.00008265253,0.00020034703,0.00000459085],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018582844,0.00039741927,0.2793679,0.0004070558,0.00033293656,0.020383907,0.0016304157,0.000013356892,0.06594708,0.015080089,0.15725142,0.45900258],"study_design_scores_gemma":[0.0008398608,0.000070923605,0.006851943,0.00042371007,0.00006752805,0.014003668,0.0014754627,0.06344434,0.0028095685,0.012403755,0.8973918,0.00021745698],"about_ca_topic_score_codex":0.0000024144897,"about_ca_topic_score_gemma":0.000009166133,"teacher_disagreement_score":0.7401404,"about_ca_system_score_codex":0.000022643686,"about_ca_system_score_gemma":0.00029700113,"threshold_uncertainty_score":0.8021664},"labels":[],"label_agreement":null},{"id":"W3158912897","doi":"10.1148/radiol.2021201740","title":"Oncologically Relevant Findings Reporting and Data System (ONCO-RADS): Guidelines for the Acquisition, Interpretation, and Reporting of Whole-Body MRI for Cancer Screening","year":2021,"lang":"en","type":"review","venue":"Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":63,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Medicine; Cancer; Medical physics; Geneticist; Standardization; Radiology; Internal medicine; Computer science","score_opus":0.1796389452340031,"score_gpt":0.48866872403994494,"score_spread":0.30902977880594185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3158912897","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00017862531,0.8792106,0.11391277,0.0044106254,0.0004569825,0.001661225,0.00010130977,0.00004507952,0.00002278684],"genre_scores_gemma":[0.00044457946,0.9361866,0.059823636,0.00059982535,0.0011989935,0.00041101704,0.001079502,0.00007139537,0.00018441038],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9929643,0.00020832925,0.0053758724,0.0009176624,0.00017766134,0.00035614343],"domain_scores_gemma":[0.9866127,0.0028642465,0.00888108,0.0007419021,0.00077249116,0.00012761884],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008940753,0.00034385995,0.0033336794,0.00013171244,0.0002619307,0.000046558976,0.0002943643,0.0003525683,0.000005417096],"category_scores_gemma":[0.051186506,0.00020988872,0.00030230536,0.000160491,0.0002630137,0.00006525238,0.00031180625,0.00052297127,1.2435227e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000059726663,0.000013567822,0.00079379726,0.023398366,0.0008734538,0.00010186911,0.00014390085,0.000034519202,0.0000585916,0.00041587377,0.009127794,0.9649785],"study_design_scores_gemma":[0.0007330436,0.00023519399,0.00018230619,0.03618044,0.0035678665,0.0067891376,0.00037102986,0.06646129,0.0000015766808,0.000027358274,0.88520616,0.00024459124],"about_ca_topic_score_codex":0.000066532564,"about_ca_topic_score_gemma":0.0000047357444,"teacher_disagreement_score":0.96473396,"about_ca_system_score_codex":0.00010354715,"about_ca_system_score_gemma":0.00051959645,"threshold_uncertainty_score":0.95680577},"labels":[],"label_agreement":null},{"id":"W3158938797","doi":"10.1164/ajrccm-conference.2021.203.1_meetingabstracts.a1051","title":"6MWD Worsening in COPD Predicted Using CT and MRI Texture Features and Machine Learning","year":2021,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Texture (cosmology); COPD; Computer science; Artificial intelligence; Machine learning; Medicine; Computer vision; Image (mathematics); Internal medicine","score_opus":0.010394357369105968,"score_gpt":0.2745137023711576,"score_spread":0.2641193450020516,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3158938797","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98044574,0.009595864,0.0023114325,0.0041741943,0.00010446965,0.00014398342,0.0000019759343,0.000099697434,0.0031226366],"genre_scores_gemma":[0.98254097,0.00056423945,0.012388012,0.0011831672,0.00012834358,0.000001996621,0.000040722607,0.00003124065,0.003121317],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99886966,0.00009714609,0.00021409655,0.0003507937,0.0001968122,0.0002715114],"domain_scores_gemma":[0.999454,0.00013365438,0.000051144765,0.00012276781,0.000042369422,0.00019605635],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003005276,0.00016336069,0.00033764588,0.00013472102,0.00012289501,0.000068954876,0.000033636774,0.000057607547,0.00013013015],"category_scores_gemma":[0.0006105658,0.00013441194,0.000032852888,0.00026576637,0.00009912765,0.00007533985,0.00010529316,0.0010406057,6.7725364e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008940588,0.00007953793,0.9193397,0.0002675714,0.000097555945,0.0027931267,0.0010333748,0.0006413538,0.018668821,0.00037207146,0.00095653,0.055660926],"study_design_scores_gemma":[0.005616526,0.00013925046,0.28853807,0.0011688052,0.00019908276,0.012144603,0.0012346416,0.6685848,0.0016188483,0.00016945739,0.020140223,0.00044570945],"about_ca_topic_score_codex":0.00029123292,"about_ca_topic_score_gemma":0.00006837089,"teacher_disagreement_score":0.6679434,"about_ca_system_score_codex":0.000031598578,"about_ca_system_score_gemma":0.00006696826,"threshold_uncertainty_score":0.54811597},"labels":[],"label_agreement":null},{"id":"W3158939190","doi":"10.36255/exonpublications.gliomas.2021.chapter9","title":"Survival Prediction in Gliomas: Current State and Novel Approaches","year":2021,"lang":"en","type":"book-chapter","venue":"Exon Publications eBooks","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Radiomics; Artificial intelligence; Glioma; Random forest; Convolutional neural network; Computer science; Deep learning; Machine learning; Artificial neural network; Statistical learning; Support vector machine; Medicine","score_opus":0.07084326369453826,"score_gpt":0.28825592361451635,"score_spread":0.2174126599199781,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3158939190","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014914321,0.0018876295,0.009672554,0.0032524446,0.0005302777,0.00076938036,0.000101989695,0.00013947459,0.98215485],"genre_scores_gemma":[0.018307187,0.00031805653,0.0025729267,0.00020524648,0.0005874958,0.00015909405,0.0010887913,0.00012752232,0.97663367],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983517,0.000023757333,0.00048705883,0.0005441618,0.00036320923,0.00023010431],"domain_scores_gemma":[0.99890965,0.00008092614,0.00018384474,0.00046130654,0.00013686802,0.00022741027],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00045166502,0.0002594839,0.00042163054,0.0005599939,0.000085984575,0.00010371705,0.00010909924,0.00015313798,0.00012638069],"category_scores_gemma":[0.00018471121,0.00025445427,0.000092265225,0.000058112048,0.00018815612,0.0000604952,0.000112648384,0.0010646941,0.000015290032],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000311598,0.00019637513,0.0020484144,0.00041946326,0.00018875516,0.000021756048,0.00046107883,0.00001170471,0.00028083767,0.4553938,0.0038495823,0.5370971],"study_design_scores_gemma":[0.001591783,0.00006159052,0.010664786,0.00071523205,0.00014967949,0.00017161986,0.000036392015,0.005860262,0.000020221032,0.005147471,0.9752241,0.0003568596],"about_ca_topic_score_codex":0.00001402381,"about_ca_topic_score_gemma":0.000022855982,"teacher_disagreement_score":0.9713745,"about_ca_system_score_codex":0.0001229296,"about_ca_system_score_gemma":0.0003390648,"threshold_uncertainty_score":0.99999076},"labels":[],"label_agreement":null},{"id":"W3159516509","doi":"10.1007/s00261-021-03094-9","title":"Role of the radiologist at HCC multidisciplinary conference and use of the LR-TR algorithm for improving workflow","year":2021,"lang":"en","type":"review","venue":"Abdominal Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Medicine; Hepatocellular carcinoma; Workflow; Multidisciplinary approach; Hepatology; Multidisciplinary team; Radiology; Liver disease; Medical physics; Algorithm; Internal medicine; Nursing","score_opus":0.03358602929219457,"score_gpt":0.33229695930835695,"score_spread":0.2987109300161624,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3159516509","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030237737,0.9922997,0.0022581802,0.00037099136,0.0005828891,0.001320075,0.00007574664,0.000011349111,0.000057347257],"genre_scores_gemma":[0.00177287,0.97386885,0.022770204,0.000111515816,0.00038830747,0.00012533393,0.000073875206,0.00006443332,0.000824585],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975693,0.00055850716,0.0008113661,0.000515933,0.00017607988,0.00036877644],"domain_scores_gemma":[0.9963283,0.0018646895,0.00084044517,0.0007205634,0.00013635856,0.00010964879],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006833426,0.00036312954,0.0023937752,0.00007721021,0.00018641504,0.0000124744365,0.00043124167,0.00041841355,0.000025483025],"category_scores_gemma":[0.0018663463,0.0001878468,0.00074598286,0.0001945993,0.0013658575,0.00002917967,0.0006079648,0.00085311924,6.2849523e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003855199,0.00003989558,0.0006403386,0.002987791,0.00022737174,0.000012447739,0.00012265654,0.0000051765414,0.0003577477,0.00017587522,0.00022773062,0.9951644],"study_design_scores_gemma":[0.0035646537,0.00093037257,0.004275041,0.024981307,0.0079040015,0.0107929455,0.00033949624,0.06407607,0.00019237275,0.00043246604,0.88160026,0.00091099873],"about_ca_topic_score_codex":0.00008180363,"about_ca_topic_score_gemma":0.000008326944,"teacher_disagreement_score":0.9942534,"about_ca_system_score_codex":0.00011094367,"about_ca_system_score_gemma":0.00049546215,"threshold_uncertainty_score":0.766017},"labels":[],"label_agreement":null},{"id":"W3159660070","doi":"10.1016/j.crad.2021.03.009","title":"Challenges and opportunities for artificial intelligence in oncological imaging","year":2021,"lang":"en","type":"review","venue":"Clinical Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":41,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Health Sciences Centre; Sunnybrook Health Science Centre","funders":"National Cancer Institute; National Institutes of Health","keywords":"Medicine; Medical physics; Artificial intelligence","score_opus":0.475100480926659,"score_gpt":0.5286556231799794,"score_spread":0.053555142253320365,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3159660070","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000019747435,0.9888264,0.0016362423,0.006915631,0.0008376585,0.0006179703,0.000004251223,0.000037394268,0.0011046869],"genre_scores_gemma":[0.00006476189,0.9940902,0.00289608,0.0012921302,0.0012726267,0.00013437189,0.00010355429,0.00004236272,0.0001038948],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99626356,0.0008209094,0.0015913877,0.00080224394,0.00009739931,0.00042447262],"domain_scores_gemma":[0.9924829,0.006555975,0.00029750715,0.00030817956,0.00006245858,0.00029296882],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031000772,0.0003198637,0.0035336723,0.00018987959,0.000043067917,0.00001742854,0.00017799258,0.00062658987,0.00003717266],"category_scores_gemma":[0.007944002,0.00023993468,0.00055126124,0.000068166126,0.0007900674,0.000024716997,0.00014812646,0.0015935278,0.000004915797],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022816299,0.00013118198,0.000025790214,0.0024248254,0.00008223888,0.0007718019,0.00002717778,1.9488601e-7,3.7045044e-8,0.015280978,0.0003484882,0.9808845],"study_design_scores_gemma":[0.00021251381,0.0003750903,0.00006277437,0.005461933,0.000478355,0.0015876708,0.00017977522,0.0011398676,1.9163195e-8,0.0024345992,0.98783803,0.00022935629],"about_ca_topic_score_codex":0.0000015775038,"about_ca_topic_score_gemma":0.0000035042099,"teacher_disagreement_score":0.9874896,"about_ca_system_score_codex":0.000068891444,"about_ca_system_score_gemma":0.00051868625,"threshold_uncertainty_score":0.9784252},"labels":[],"label_agreement":null},{"id":"W3160929191","doi":"10.1101/2021.05.15.444315","title":"DeepImageTranslator: a free, user-friendly graphical interface for image translation using deep-learning and its applications in 3D CT image analysis","year":2021,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier Universitaire de Sherbrooke; Université de Sherbrooke","funders":"Canadian Institutes of Health Research","keywords":"Computer science; Deep learning; Pipeline (software); Artificial intelligence; Convolutional neural network; Segmentation; Graphical user interface; Generalizability theory; Interface (matter); Sample (material); Machine learning; Noise (video); Pattern recognition (psychology); Data mining; Image (mathematics)","score_opus":0.010295752719374746,"score_gpt":0.2789165423942262,"score_spread":0.2686207896748515,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3160929191","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5958312,0.0044962442,0.39777347,0.00036658638,0.000115533316,0.001169792,0.0000648714,0.00017595505,0.000006326544],"genre_scores_gemma":[0.7953221,0.0005538702,0.2034776,0.00006930332,0.00016225847,0.00026209242,0.0000072987245,0.00014346396,0.0000019825288],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99626964,0.0002492559,0.0009252342,0.0014189302,0.00046715536,0.0006697771],"domain_scores_gemma":[0.9973925,0.0004071021,0.00039982435,0.0008371931,0.00051383075,0.00044960302],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011412128,0.00062935153,0.0012696381,0.0010813879,0.00025711843,0.00035102543,0.00035948554,0.00037868432,0.00004170024],"category_scores_gemma":[0.0010799747,0.00069166045,0.00045658916,0.0017208797,0.0002064414,0.00028445214,0.00023730048,0.002081715,0.0000017877595],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012228114,0.00041755062,0.07941759,0.002753762,0.0016302094,0.00022635466,0.00013377395,0.001222924,0.9137914,0.0001800544,0.000015043217,0.00008901626],"study_design_scores_gemma":[0.0056895963,0.00018221348,0.11857694,0.0017312958,0.008029692,0.0000012388027,0.000117606345,0.80426174,0.054279793,0.000008274818,0.0050237924,0.0020978183],"about_ca_topic_score_codex":0.00009757231,"about_ca_topic_score_gemma":0.000022251194,"teacher_disagreement_score":0.8595117,"about_ca_system_score_codex":0.00021177507,"about_ca_system_score_gemma":0.00033410024,"threshold_uncertainty_score":0.99955344},"labels":[],"label_agreement":null},{"id":"W3160989106","doi":"10.3390/cancers13102382","title":"Artificial Intelligence Applications to Improve the Treatment of Locally Advanced Non-Small Cell Lung Cancers","year":2021,"lang":"en","type":"review","venue":"Cancers","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto; University Health Network","funders":"","keywords":"Lung cancer; Medicine; Health records; Intensive care medicine; Cancer treatment; Medical physics; Artificial intelligence; Cancer; Computer science; Health care; Internal medicine","score_opus":0.027120273079849253,"score_gpt":0.3593438514879258,"score_spread":0.33222357840807654,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3160989106","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000036717174,0.95907575,0.036147833,0.00023254401,0.00055631646,0.00280735,0.000044886187,0.000024094987,0.0010744933],"genre_scores_gemma":[0.000107219006,0.9937069,0.0025711693,0.00028705486,0.00058935385,0.0017961358,0.000081601625,0.00006589458,0.0007946782],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99816704,0.00005159869,0.0006599874,0.00054944033,0.000226748,0.00034520906],"domain_scores_gemma":[0.9983758,0.00020482321,0.0003249416,0.00070223334,0.00012779252,0.0002644218],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001546186,0.0003557413,0.0013472774,0.000109520464,0.000097176744,0.000022848088,0.0002882284,0.00013578574,0.00006787803],"category_scores_gemma":[0.000057520185,0.00023484361,0.00047183895,0.00055132987,0.00014530479,0.000014699545,0.000040755993,0.00040653063,0.000018001063],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001148485,0.000033160948,0.000002247603,0.0035083762,0.00016548537,0.000013052533,0.00031618332,0.0016925785,0.000030530526,0.00007506002,0.0002771693,0.99387467],"study_design_scores_gemma":[0.00011112311,0.00028960055,5.481554e-7,0.004721804,0.0012416297,0.000009565998,0.00024353826,0.0019929234,0.00022519736,0.000010591486,0.9909355,0.00021797187],"about_ca_topic_score_codex":0.0005485,"about_ca_topic_score_gemma":0.000056731355,"teacher_disagreement_score":0.9936567,"about_ca_system_score_codex":0.0036930523,"about_ca_system_score_gemma":0.00489379,"threshold_uncertainty_score":0.9657203},"labels":[],"label_agreement":null},{"id":"W3161520686","doi":"10.1007/s00330-021-08021-6","title":"ESUR/ESUI position paper: developing artificial intelligence for precision diagnosis of prostate cancer using magnetic resonance imaging","year":2021,"lang":"en","type":"article","venue":"European Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":68,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sinai Health System; University of Toronto; University Health Network","funders":"Berlin Institute of Health","keywords":"Medicine; Neuroradiology; Magnetic resonance imaging; Prostate cancer; Interventional radiology; Radiology; Position (finance); Ultrasound; Medical physics; Prostate; Position statement; Cancer; Nuclear medicine; Neurology; Internal medicine","score_opus":0.027112000941605315,"score_gpt":0.3238093566749438,"score_spread":0.2966973557333385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3161520686","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8877367,0.03047761,0.07077385,0.008680712,0.0009456163,0.0005796873,0.000026319363,0.000071551935,0.0007079783],"genre_scores_gemma":[0.93240577,0.0032078524,0.061263435,0.0022565322,0.0005710309,0.000034555174,0.000050789768,0.0000716317,0.00013838586],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99829316,0.00030927802,0.00054309407,0.0004034028,0.00013649139,0.000314556],"domain_scores_gemma":[0.9990256,0.0002983208,0.00015343772,0.000217782,0.00021880116,0.000086104075],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007192958,0.00014824605,0.0003550548,0.00009742845,0.000115777846,0.000020602387,0.00010773212,0.00003567747,0.000088934175],"category_scores_gemma":[0.0010315722,0.00013943676,0.0000960359,0.00021554348,0.00016276819,0.00006806493,0.00007488921,0.0002356216,0.000005368608],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021287215,0.00006400343,0.04456602,0.0001520287,0.000022079406,0.0002972418,0.0006280638,0.0006490833,0.05119042,0.0010847953,0.00042471616,0.9007087],"study_design_scores_gemma":[0.0041683842,0.0014849089,0.36290893,0.008706969,0.00091258774,0.0048267487,0.00105676,0.32489845,0.14122711,0.010079193,0.13791409,0.0018158656],"about_ca_topic_score_codex":0.000030719395,"about_ca_topic_score_gemma":0.00000386644,"teacher_disagreement_score":0.8988928,"about_ca_system_score_codex":0.00009362296,"about_ca_system_score_gemma":0.00017644686,"threshold_uncertainty_score":0.5686066},"labels":[],"label_agreement":null},{"id":"W3161818078","doi":"10.3390/cancers13092269","title":"Prediction of Human Papillomavirus (HPV) Association of Oropharyngeal Cancer (OPC) Using Radiomics: The Impact of the Variation of CT Scanner","year":2021,"lang":"en","type":"article","venue":"Cancers","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; Princess Margaret Cancer Centre; Ontario Institute for Cancer Research; University of Toronto; University Health Network","funders":"Canadian Institutes of Health Research","keywords":"Scanner; Radiomics; Robustness (evolution); Cancer imaging; Computer science; Artificial intelligence; Human papillomavirus; Pattern recognition (psychology); Medicine; Machine learning; Cancer; Biology","score_opus":0.022300310416081465,"score_gpt":0.322361247152477,"score_spread":0.30006093673639556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3161818078","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99762684,0.0007886984,0.00021240082,0.00028297945,0.00037923997,0.00017905326,0.0000797105,0.000005113252,0.00044595829],"genre_scores_gemma":[0.9992396,0.00025903748,0.00010540317,0.00005841954,0.00017299625,0.0000045785678,0.0000129592345,0.000015021875,0.00013195536],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9988377,0.00012890426,0.00042244475,0.0001260396,0.00035340697,0.00013151918],"domain_scores_gemma":[0.99860394,0.00008458862,0.0007291154,0.00024266874,0.00030020202,0.00003946108],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047236847,0.00008882875,0.00036271787,0.000050490053,0.000061268984,0.0000038680114,0.00010006869,0.00004937547,0.00015162188],"category_scores_gemma":[0.0003498143,0.000055371147,0.000210608,0.00030616065,0.00013074232,0.000053404907,0.000029121997,0.00021265858,8.264709e-8],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000067911606,0.000037285372,0.20512016,0.00018197426,0.00049546396,0.0000014755765,0.0012599659,0.031816084,0.7567597,0.00008935492,0.000663696,0.0035069294],"study_design_scores_gemma":[0.0020670379,0.00016576669,0.837108,0.00053191767,0.0006274556,0.0000119921215,0.00027522398,0.07035922,0.088566944,0.0001185069,0.00009014009,0.000077783974],"about_ca_topic_score_codex":0.0120241,"about_ca_topic_score_gemma":0.000046150653,"teacher_disagreement_score":0.66819274,"about_ca_system_score_codex":0.0013927618,"about_ca_system_score_gemma":0.0011570073,"threshold_uncertainty_score":0.99455494},"labels":[],"label_agreement":null},{"id":"W3164225675","doi":"10.1038/s41591-021-01359-w","title":"Clinical integration of machine learning for curative-intent radiation treatment of patients with prostate cancer","year":2021,"lang":"en","type":"article","venue":"Nature Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":172,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; Princess Margaret Cancer Centre; University of Toronto; University Health Network","funders":"Canadian Institutes of Health Research; Natural Sciences and Engineering Research Council of Canada; Government of Canada; Princess Margaret Cancer Foundation","keywords":"Prostate cancer; Medicine; Radiation therapy; Cancer; Medical physics; Cancer treatment; Oncology; Artificial intelligence; Internal medicine; Computer science","score_opus":0.014264484788570678,"score_gpt":0.3686040817544943,"score_spread":0.3543395969659236,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3164225675","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9744122,0.008158742,0.0059860293,0.009690116,0.0005730862,0.0008747685,0.000027345252,0.000025026724,0.0002527067],"genre_scores_gemma":[0.9930067,0.0018440495,0.0027744954,0.0004166336,0.00028530345,0.000035727327,0.00083848275,0.000022846261,0.00077576406],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99866164,0.000088244684,0.00051359256,0.0002465819,0.00035214922,0.00013778338],"domain_scores_gemma":[0.998326,0.00027865628,0.00036246784,0.0001501876,0.0007780578,0.00010463632],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002925716,0.00014691555,0.0006086156,0.000094756426,0.000038316855,0.0000025100549,0.000036844067,0.00012976445,0.00008408495],"category_scores_gemma":[0.00163043,0.00008341796,0.00009593877,0.00022087684,0.00015655672,0.00003908356,0.000008454021,0.0004607048,2.4716007e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017399886,0.00054275605,0.5588498,0.00018009749,0.0002577013,0.000008856841,0.0011197338,0.00007315302,0.003225618,0.00015718046,0.00040164503,0.4334435],"study_design_scores_gemma":[0.031792555,0.01218923,0.82337517,0.002132441,0.0011319035,0.000012506525,0.0004903562,0.031622697,0.02067003,0.00009278082,0.07626003,0.00023027821],"about_ca_topic_score_codex":0.000080437465,"about_ca_topic_score_gemma":0.000021973015,"teacher_disagreement_score":0.4332132,"about_ca_system_score_codex":0.00008693458,"about_ca_system_score_gemma":0.00015658964,"threshold_uncertainty_score":0.34016857},"labels":[],"label_agreement":null},{"id":"W3164329335","doi":"10.1007/s00261-021-03098-5","title":"Correction to: Artificial intelligence in assessment of hepatocellular carcinoma treatment response","year":2021,"lang":"en","type":"article","venue":"Abdominal Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Thunder Bay Regional Health Sciences Centre","funders":"","keywords":"Hepatology; Hepatocellular carcinoma; Medicine; Internal medicine; Carcinoma; Medical physics; Gastroenterology","score_opus":0.023697011522828052,"score_gpt":0.34385857164785955,"score_spread":0.3201615601250315,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3164329335","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9686279,0.00017179006,0.026592335,0.0028993152,0.00081582443,0.0001909792,0.0000011605099,0.00001161861,0.0006890712],"genre_scores_gemma":[0.9909817,0.000044440927,0.008082731,0.00032035063,0.00012078522,0.000024116518,0.000012903311,0.0000120353625,0.00040093446],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9986377,0.0003408765,0.0003878428,0.00028687296,0.00012315233,0.00022358604],"domain_scores_gemma":[0.99898076,0.00052501383,0.00006737085,0.00022626693,0.00007134965,0.00012926746],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00060986896,0.00011489444,0.00042228005,0.00018318342,0.000029567529,0.000005087737,0.00005539828,0.00006665254,0.00014323599],"category_scores_gemma":[0.0010416463,0.00010233784,0.00008966312,0.0002745688,0.0000887959,0.000015994749,0.000027619759,0.00023977691,0.000010010832],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0035106787,0.00065514824,0.41088745,0.00003807169,0.00007372818,0.0031797462,0.0011272251,0.0014376923,0.3581107,0.0013955681,0.0004568382,0.21912716],"study_design_scores_gemma":[0.0009270883,0.0032123076,0.48574856,0.00014885874,0.000108039654,0.0025701101,0.0009517295,0.43560678,0.06791734,0.000403247,0.0022106706,0.00019528117],"about_ca_topic_score_codex":0.00029757217,"about_ca_topic_score_gemma":0.000031247786,"teacher_disagreement_score":0.43416908,"about_ca_system_score_codex":0.00029056892,"about_ca_system_score_gemma":0.00042164643,"threshold_uncertainty_score":0.4173216},"labels":[],"label_agreement":null},{"id":"W3164816110","doi":"","title":"Unsupervised background removal by dual-modality PET/CT guidance: application to PSMA imaging of metastases","year":2021,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Artificial intelligence; Convolutional neural network; Computer science; PET-CT; Segmentation; Deep learning; Nuclear medicine; Leverage (statistics); Medicine; Pattern recognition (psychology); Computer vision; Positron emission tomography; Radiology","score_opus":0.013261938935531651,"score_gpt":0.31557432642814703,"score_spread":0.3023123874926154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3164816110","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88183075,0.0014235853,0.0788116,0.024684427,0.00015788061,0.00036369034,0.000040474584,0.00011864785,0.012568911],"genre_scores_gemma":[0.9413485,0.000058805785,0.051829785,0.00429748,0.00012130444,0.000019992072,0.00020444796,0.00003243796,0.002087235],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983525,0.00009958816,0.000443659,0.00042263372,0.00041648533,0.00026513496],"domain_scores_gemma":[0.998807,0.00011542867,0.00008645971,0.0005084897,0.00022664887,0.00025595125],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006511073,0.00015937188,0.0004006074,0.00006846298,0.00006837331,0.00003211171,0.000099670484,0.000008394032,0.00045994925],"category_scores_gemma":[0.00043905576,0.00014028474,0.00011971014,0.00037963127,0.000084501036,0.00008244909,0.00009066136,0.00022203077,0.000034054945],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014998257,0.0007285936,0.034004673,0.0006216809,0.00025254823,0.0021111066,0.00015240573,0.00015173618,0.78903806,0.0063741556,0.07230577,0.094109274],"study_design_scores_gemma":[0.00872103,0.0002642229,0.03484091,0.0005884621,0.00095631,0.014918875,0.0030112243,0.122486815,0.24872212,0.0020000115,0.5622411,0.0012489433],"about_ca_topic_score_codex":0.00038043558,"about_ca_topic_score_gemma":0.000008540226,"teacher_disagreement_score":0.5403159,"about_ca_system_score_codex":0.0000653449,"about_ca_system_score_gemma":0.00013699224,"threshold_uncertainty_score":0.5720646},"labels":[],"label_agreement":null},{"id":"W3164980040","doi":"","title":"Can PET/CT Radiomics Harmonization Improve Gene Mutation Status Prediction in Non-small Cell Lung Cancer?","year":2021,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Univariate; Feature selection; KRAS; Radiomics; Receiver operating characteristic; Random forest; Medicine; Artificial intelligence; Radiogenomics; Computer science; Multivariate statistics; Cancer; Machine learning; Internal medicine; Colorectal cancer","score_opus":0.005992038991778449,"score_gpt":0.2563992135990696,"score_spread":0.2504071746072911,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3164980040","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96693146,0.0005964831,0.026458055,0.002450554,0.00069727673,0.000407055,0.000025489802,0.00007949182,0.0023541297],"genre_scores_gemma":[0.98377424,0.00073887006,0.010618089,0.0010476492,0.00027091888,0.000044133143,0.0005098176,0.00004333868,0.0029529314],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99866325,0.000051536208,0.00035206025,0.0003667969,0.00022481396,0.00034152434],"domain_scores_gemma":[0.999302,0.00004378198,0.00010054699,0.00019629995,0.00015193847,0.00020539392],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021506587,0.00015145294,0.00024774906,0.00014872503,0.00006762298,0.000045292367,0.00004951329,0.000023147873,0.00018503754],"category_scores_gemma":[0.00016479113,0.00014835522,0.00005692402,0.0003717636,0.000028644554,0.000079760735,0.000024245179,0.00040288782,0.0000041130975],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001208885,0.000453983,0.5682815,0.00083625165,0.00014608179,0.0044991504,0.0018636785,0.01992017,0.34467155,0.00013717495,0.0031061568,0.055963438],"study_design_scores_gemma":[0.0035038674,0.00007020846,0.050883107,0.00011957299,0.00014885624,0.00043608426,0.00044571125,0.87677824,0.06685578,0.000036893565,0.00054228836,0.00017939064],"about_ca_topic_score_codex":0.0021464066,"about_ca_topic_score_gemma":0.00026127018,"teacher_disagreement_score":0.8568581,"about_ca_system_score_codex":0.00046114207,"about_ca_system_score_gemma":0.0005333836,"threshold_uncertainty_score":0.60497504},"labels":[],"label_agreement":null},{"id":"W3165659910","doi":"10.1136/annrheumdis-2021-eular.3427","title":"POS0032 SCORING MRI STRUCTURAL LESIONS IN SACROILIAC JOINTS OF PATIENTS WITH AXIAL SPONDYLOARTHRITIS: HOW MANY SLICES ARE OPTIMAL?","year":2021,"lang":"en","type":"article","venue":"Annals of the Rheumatic Diseases","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Medicine; Lesion; Sacroiliac joint; Axial spondyloarthritis; Ankylosis; Magnetic resonance imaging; Nuclear medicine; Radiology; Orthodontics; Pathology; Sacroiliitis","score_opus":0.016049179851298247,"score_gpt":0.27982444023363556,"score_spread":0.26377526038233734,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3165659910","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99438566,0.0014153093,0.000034742123,0.0036419437,0.00015201214,0.00021905209,0.00007850999,0.000013776959,0.000058998918],"genre_scores_gemma":[0.99836504,0.00029867663,0.00092590885,0.00024094502,0.000026746466,0.0000069911175,0.000030748564,0.000020015925,0.000084922656],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9986265,0.000107547865,0.00034106712,0.00020522847,0.00048132174,0.0002383644],"domain_scores_gemma":[0.9988213,0.00013026483,0.00031026342,0.00037886103,0.00021360253,0.0001456712],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012962292,0.00015023173,0.00048013448,0.00008681339,0.000070410446,0.000026544962,0.00017414155,0.000033275897,0.00008040909],"category_scores_gemma":[0.0011872523,0.0000974309,0.0001568524,0.00025522994,0.00019375172,0.0001263571,0.00011290601,0.00018278013,0.0000011137938],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030564296,0.00044989746,0.9479585,0.0012000119,0.00021575308,0.000055739427,0.0005161301,0.0007286347,0.00011347937,0.00018719875,0.0007136121,0.04755535],"study_design_scores_gemma":[0.0015541846,0.00009797423,0.9893676,0.0052432423,0.00009578113,0.00000888839,0.00075151847,0.0017812296,0.0007182762,0.00022866177,0.00004008759,0.00011256927],"about_ca_topic_score_codex":0.000053559535,"about_ca_topic_score_gemma":0.000011302315,"teacher_disagreement_score":0.047442783,"about_ca_system_score_codex":0.000012302026,"about_ca_system_score_gemma":0.0001224866,"threshold_uncertainty_score":0.3973117},"labels":[],"label_agreement":null},{"id":"W3165678011","doi":"","title":"Enhancement of conventional segmentation techniques to achieve deep framework performance for lymphoma lesion segmentation in PET images","year":2021,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Segmentation; Artificial intelligence; Computer science; Thresholding; Pattern recognition (psychology); Ground truth; Image segmentation; Deep learning; Computer vision; Image (mathematics)","score_opus":0.013340223437611766,"score_gpt":0.3316390321567714,"score_spread":0.3182988087191596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3165678011","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5256953,0.000043059114,0.4710132,0.0021976866,0.000081699945,0.00041284985,0.000002335828,0.000020686224,0.000533188],"genre_scores_gemma":[0.5820033,0.00017291067,0.4159334,0.001120049,0.00005565446,0.00011088184,0.00013729002,0.000010924562,0.00045559317],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990706,0.00003183882,0.0003166253,0.00019916812,0.00024070768,0.00014109768],"domain_scores_gemma":[0.99952227,0.00009426224,0.00008008927,0.00010709843,0.00013377404,0.00006251638],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032529223,0.00009140405,0.00018965812,0.00011297537,0.00004081781,0.000012941166,0.000041832704,0.00003542047,0.00019197543],"category_scores_gemma":[0.00016939148,0.00008298957,0.00005563061,0.00017212618,0.000027173834,0.00008313535,0.000029542554,0.000081406455,0.0000042449683],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003623984,0.00038396998,0.012083833,0.00042461642,0.00003492875,0.000012992744,0.0003916813,0.00007515793,0.5970887,0.00078700384,0.00067255326,0.38768217],"study_design_scores_gemma":[0.0014655353,0.000534561,0.014058668,0.0005514523,0.00003514102,0.00003229301,0.0005320751,0.009533907,0.97200924,0.0005110418,0.00062450755,0.00011156769],"about_ca_topic_score_codex":0.00001499201,"about_ca_topic_score_gemma":0.0000029826872,"teacher_disagreement_score":0.38757062,"about_ca_system_score_codex":0.00011681107,"about_ca_system_score_gemma":0.00007610048,"threshold_uncertainty_score":0.33842167},"labels":[],"label_agreement":null},{"id":"W3166988676","doi":"10.1093/ecco-jcc/jjab076.264","title":"P137 Preliminary validation of a multi-stage machine learning algorithm to assess histological inflammation in inflammatory bowel disease","year":2021,"lang":"en","type":"article","venue":"Journal of Crohn s and Colitis","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Inflammatory bowel disease; Algorithm; Medicine; Stage (stratigraphy); Ulcerative colitis; Artificial intelligence; Grading (engineering); Biopsy; Ground truth; Crohn's disease; H&E stain; Convolutional neural network; Machine learning; Pathology; Radiology; Disease; Pattern recognition (psychology); Computer science; Staining","score_opus":0.024402211127538924,"score_gpt":0.31063867573502507,"score_spread":0.28623646460748614,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3166988676","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98406005,0.0013293994,0.012434736,0.0018373955,0.00011341958,0.00012137377,0.0000057652146,0.00000754549,0.00009031873],"genre_scores_gemma":[0.98700356,0.00039453094,0.0117925415,0.00017874633,0.00014593215,0.0000046036885,0.000017387263,0.000012519705,0.00045018503],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99871737,0.00015899392,0.00055617135,0.00012674104,0.00029555152,0.00014516704],"domain_scores_gemma":[0.99898076,0.00011034226,0.00030328776,0.00008436013,0.00024524177,0.0002759798],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005861914,0.000096391705,0.00030523818,0.00018290263,0.00004614566,0.000031731866,0.00005273913,0.00005811431,0.00006718642],"category_scores_gemma":[0.0012483601,0.00008360051,0.00008118323,0.00011776957,0.00005328442,0.00012859443,0.000049805407,0.00045888283,8.015375e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00515195,0.00073181075,0.5565351,0.0012893883,0.00017497926,0.014289398,0.002466864,0.0063479547,0.008645872,0.0007678687,0.0002877245,0.40331107],"study_design_scores_gemma":[0.0017781506,0.00031169606,0.9336344,0.00049907085,0.00007329992,0.00034384098,0.00020763125,0.05531912,0.0012510775,0.00006725069,0.0064237304,0.00009074734],"about_ca_topic_score_codex":0.00002291164,"about_ca_topic_score_gemma":0.0000027647868,"teacher_disagreement_score":0.40322033,"about_ca_system_score_codex":0.00007261978,"about_ca_system_score_gemma":0.00021065751,"threshold_uncertainty_score":0.340913},"labels":[],"label_agreement":null},{"id":"W3167119435","doi":"10.1200/jco.2021.39.15_suppl.e16169","title":"Computational extraction and analysis of de-identified medical records to characterize hyperammonemia in patients with fibrolamellar carcinoma (FLC).","year":2021,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University Health Network; University of Toronto","funders":"","keywords":"Hyperammonemia; Medicine; Internal medicine; Context (archaeology); Everolimus; Incidence (geometry); Oncology; Cancer; Gastroenterology","score_opus":0.03433985110914035,"score_gpt":0.4078413049839669,"score_spread":0.3735014538748266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3167119435","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9900007,0.00006369179,0.0029847862,0.006493986,0.00027710394,0.000060848983,0.0000025219624,0.0000023314528,0.000114015085],"genre_scores_gemma":[0.9819347,0.000083392704,0.01588665,0.0018502728,0.00018033528,7.544391e-7,0.00002375355,0.000008090936,0.000032032793],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99732053,0.00037135478,0.0014694374,0.00016295892,0.0005367219,0.00013901868],"domain_scores_gemma":[0.9967156,0.0015727328,0.0007151076,0.00009215639,0.0004642048,0.0004401793],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026685533,0.00007839458,0.0011351157,0.00028487493,0.000018103048,0.000008457162,0.00006999719,0.00021521159,0.00017619049],"category_scores_gemma":[0.006592498,0.00005901824,0.00017734052,0.0004087306,0.00010771409,0.00005999218,0.000035853882,0.00091087044,8.4125423e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016669596,0.00069316546,0.90761936,0.000022317348,0.00045717988,0.0005262238,0.00009085368,0.00035005712,0.00010489239,0.000011229335,0.00014256283,0.088315226],"study_design_scores_gemma":[0.004907298,0.0017094003,0.97962683,0.000104667575,0.0007015397,0.00014599517,0.000034723264,0.011152412,0.000015610613,0.000034805103,0.0015149235,0.000051790365],"about_ca_topic_score_codex":0.000040274812,"about_ca_topic_score_gemma":0.000032667118,"teacher_disagreement_score":0.08826343,"about_ca_system_score_codex":0.00008675475,"about_ca_system_score_gemma":0.0012253035,"threshold_uncertainty_score":0.78923124},"labels":[],"label_agreement":null},{"id":"W3167348704","doi":"10.1200/jco.2021.39.15_suppl.8548","title":"NRG-RTOG 1106/ACRIN 6697: A phase IIR trial of standard versus adaptive (mid-treatment PET-based) chemoradiotherapy for stage III NSCLC—Results and comparison to NRG-RTOG 0617 (non-personalized RT dose escalation).","year":2021,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Saskatchewan Cancer Agency; University of Saskatchewan; McGill University Health Centre","funders":"","keywords":"Medicine; Clinical endpoint; Carboplatin; Chemoradiotherapy; Radiation therapy; Oncology; Internal medicine; Lung cancer; Nuclear medicine; Clinical trial; Chemotherapy; Cisplatin","score_opus":0.13194428327960817,"score_gpt":0.5175746026962688,"score_spread":0.3856303194166606,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3167348704","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94381565,0.00052937254,0.030831125,0.02037274,0.0023985647,0.0011649242,0.000108434986,0.000018039138,0.00076112803],"genre_scores_gemma":[0.942949,0.00054792763,0.05219444,0.0016108502,0.001963548,0.00002978984,0.00004878751,0.000047671994,0.0006080003],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.9947511,0.0005659957,0.003116267,0.00046560753,0.0007010007,0.0004000082],"domain_scores_gemma":[0.99009115,0.005881163,0.0020227823,0.00031143453,0.0008350438,0.00085844117],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0040583243,0.00031021461,0.0031328222,0.00019900932,0.000106827356,0.00003022558,0.00017256963,0.00026996713,0.0001591424],"category_scores_gemma":[0.0073547685,0.0002354899,0.0008143223,0.00022275643,0.00037358477,0.00009109098,0.00004322446,0.00091736886,0.0000021072553],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.79080635,0.0054403525,0.0007618938,0.000059057733,0.001186409,0.0007504618,0.0006386589,0.0005223149,0.0010962351,0.00010804206,0.00400702,0.1946232],"study_design_scores_gemma":[0.7654048,0.08274998,0.0010047888,0.00025665373,0.0009846996,0.00010087865,0.00058650156,0.019031117,0.0012791503,0.00004888107,0.12832719,0.00022531654],"about_ca_topic_score_codex":0.000051414067,"about_ca_topic_score_gemma":0.000039784598,"teacher_disagreement_score":0.19439788,"about_ca_system_score_codex":0.00047880734,"about_ca_system_score_gemma":0.003771428,"threshold_uncertainty_score":0.96029997},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"randomized_trial","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":[],"domain":null,"study_design":"randomized_trial","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W3168115304","doi":"10.1158/0008-5472.can-21-0950","title":"NCI Imaging Data Commons","year":2021,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":78,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"National Institute of Biomedical Imaging and Bioengineering; National Cancer Institute","keywords":"Documentation; Cloud computing; Data science; Commons; Computer science; Cyberinfrastructure; Political science","score_opus":0.1610928151742399,"score_gpt":0.5090268107221984,"score_spread":0.34793399554795845,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3168115304","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6455831,0.02590715,0.0024120722,0.25923193,0.00096661947,0.00048311244,0.00008521774,0.00020011832,0.06513072],"genre_scores_gemma":[0.986322,0.0011875676,0.0016760082,0.0022374787,0.0009405856,0.000028487068,0.00022997124,0.00004497631,0.0073329583],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99824876,0.00015271315,0.00013953925,0.0003907144,0.0006296517,0.000438629],"domain_scores_gemma":[0.9981949,0.00019912074,0.000016455595,0.0010258392,0.00030040898,0.0002633228],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012660355,0.00006977051,0.00017269237,0.00009853734,0.00018873948,0.00007266958,0.00035318098,0.000029080535,0.0011717957],"category_scores_gemma":[0.0013909863,0.00006169522,0.00003134816,0.00045138478,0.00022678997,0.000087052154,0.0006132647,0.0010910775,0.00008192176],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006315513,0.00015738746,0.11263826,0.0002275526,0.000097412405,0.0021163484,0.00028106148,0.000014526024,0.086109094,0.0011571796,0.50817615,0.28896186],"study_design_scores_gemma":[0.0014063822,0.000026257963,0.021626715,0.00042518033,0.000041951593,0.0003257175,0.00041988486,0.015784157,0.005413319,0.00046100456,0.9539195,0.00014994951],"about_ca_topic_score_codex":0.00047616157,"about_ca_topic_score_gemma":0.000048824742,"teacher_disagreement_score":0.44574332,"about_ca_system_score_codex":0.00011822393,"about_ca_system_score_gemma":0.0007905946,"threshold_uncertainty_score":0.99974126},"labels":[],"label_agreement":null},{"id":"W3169091023","doi":"10.1093/ecco-jcc/jjab076.324","title":"P198 Practical deep learning tool for the scoring of ulcerative colitis disease activity in central reading","year":2021,"lang":"en","type":"article","venue":"Journal of Crohn s and Colitis","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary; University of British Columbia; Vancouver General Hospital","funders":"","keywords":"Computer science; Metadata; Reading (process); Software; Artificial intelligence; Ulcerative colitis; Interface (matter); F1 score; Machine learning; Information retrieval; World Wide Web; Medicine; Disease; Internal medicine; Operating system","score_opus":0.01522868656182426,"score_gpt":0.3209111985999108,"score_spread":0.30568251203808655,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3169091023","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9785274,0.00057466334,0.012684478,0.0076042535,0.00020113325,0.00016949802,0.000003710561,0.00000366386,0.00023120131],"genre_scores_gemma":[0.9961751,0.0009314405,0.002099428,0.00024254061,0.00034627042,0.000005680324,0.0000013568919,0.000012169965,0.00018600633],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9989129,0.00013021445,0.0003432366,0.000118355565,0.00024808533,0.0002472276],"domain_scores_gemma":[0.99845433,0.0007909041,0.0002486384,0.00007929188,0.00022334048,0.0002035062],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00067378936,0.0000876972,0.0003406778,0.000059217808,0.00011436612,0.000057068526,0.000041633113,0.000038222104,0.000037906735],"category_scores_gemma":[0.002988311,0.00006424513,0.0001248893,0.00010997787,0.00010218975,0.00016091029,0.000032864882,0.0005963413,1.3185415e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.037425615,0.0010994988,0.23676908,0.0017952254,0.00093220966,0.009549337,0.0063500307,0.001877096,0.0035948076,0.022363452,0.0012364953,0.67700714],"study_design_scores_gemma":[0.0017578955,0.00021620297,0.971451,0.00054131995,0.00016912604,0.0006384217,0.0006567537,0.018340062,0.0005124921,0.00043232378,0.0052108206,0.000073600655],"about_ca_topic_score_codex":0.000032905136,"about_ca_topic_score_gemma":0.000014583684,"teacher_disagreement_score":0.7346819,"about_ca_system_score_codex":0.00007555072,"about_ca_system_score_gemma":0.00034161028,"threshold_uncertainty_score":0.35775033},"labels":[],"label_agreement":null},{"id":"W3169138340","doi":"10.1200/jco.2021.39.15_suppl.2653","title":"Impact of pharmacodynamic biomarkers in immuno-oncology (IO) phase 1 clinical trials.","year":2021,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; Princess Margaret Cancer Centre; University of Toronto","funders":"","keywords":"Medicine; Pharmacodynamics; Clinical trial; Biomarker; Internal medicine; Oncology; Phases of clinical research; Pharmacokinetics","score_opus":0.23179269958224755,"score_gpt":0.6457526772047778,"score_spread":0.41395997762253023,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3169138340","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97851413,0.0021935701,0.00083277834,0.011131561,0.004126937,0.00022523975,0.0000074679174,0.000009498355,0.0029588363],"genre_scores_gemma":[0.9815403,0.0066348417,0.007603164,0.002120602,0.0019542153,0.0000025168501,0.0000133808635,0.000031701053,0.00009923703],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98072237,0.0078065856,0.010233791,0.0003421494,0.0004760697,0.00041904568],"domain_scores_gemma":[0.9697004,0.02204707,0.0061451383,0.00035903105,0.0008187041,0.0009296883],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05243638,0.00022398528,0.005430336,0.00036158127,0.000028534823,0.000009602259,0.00030992535,0.0008147598,0.00094574393],"category_scores_gemma":[0.10180269,0.00015420697,0.0029752506,0.0004529413,0.0006759351,0.000114542745,0.00011493212,0.003604377,0.0000102197655],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.014717959,0.010223302,0.1675907,0.000041470557,0.0030066506,0.0061838212,0.000079367426,0.00006223383,0.009331107,0.000026966101,0.0081310235,0.7806054],"study_design_scores_gemma":[0.20389059,0.06598301,0.5445098,0.00073102704,0.0034598305,0.0069003506,0.000402872,0.030170826,0.00025528815,0.00081774476,0.14244026,0.0004383385],"about_ca_topic_score_codex":0.00006209481,"about_ca_topic_score_gemma":0.000014537907,"teacher_disagreement_score":0.78016704,"about_ca_system_score_codex":0.00042164724,"about_ca_system_score_gemma":0.009775217,"threshold_uncertainty_score":0.9999675},"labels":[],"label_agreement":null},{"id":"W3170601740","doi":"10.1016/j.ejca.2021.04.041","title":"Integration of quantitative imaging biomarkers in clinical trials for MR-guided radiotherapy: Conceptual guidance for multicentre studies from the MR-Linac Consortium Imaging Biomarker Working Group","year":2021,"lang":"en","type":"article","venue":"European Journal of Cancer","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":52,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Princess Margaret Cancer Centre; University Health Network","funders":"National Institute of Dental and Craniofacial Research; National Institute of Biomedical Imaging and Bioengineering; National Cancer Institute; Cancer Research UK","keywords":"Medical physics; Clinical trial; Quality assurance; Medicine; Imaging biomarker; Magnetic resonance imaging; Computer science; Radiology; Pathology","score_opus":0.2061265245229712,"score_gpt":0.48300888817508164,"score_spread":0.27688236365211044,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3170601740","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49758732,0.21878485,0.24568991,0.032282006,0.0041968925,0.0012099206,0.00005941598,0.000021682547,0.00016797708],"genre_scores_gemma":[0.91486716,0.005931352,0.07472271,0.002924237,0.0013824707,0.000017135368,0.000018930508,0.00007393548,0.00006207828],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99448335,0.0023274736,0.0023369829,0.0002906661,0.0003028451,0.0002587013],"domain_scores_gemma":[0.99024254,0.006748842,0.0018254241,0.0001929344,0.00088112836,0.00010912987],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.013423582,0.0001996153,0.0010368988,0.00010980383,0.00009480619,0.00004689817,0.00019917467,0.000024811035,0.000031195366],"category_scores_gemma":[0.021727286,0.00013011592,0.0005214776,0.00021026522,0.0004989287,0.00012500458,0.00003904135,0.00041240657,3.3906332e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005159617,0.00022281402,0.18030246,0.00013948018,0.0033014852,0.00029303227,0.008669386,0.00021570064,0.14634153,0.00035478733,0.026799224,0.6282005],"study_design_scores_gemma":[0.09138334,0.00093461754,0.25623634,0.025007715,0.0039129895,0.0002393481,0.0829813,0.31539142,0.009748674,0.000601146,0.21246572,0.0010973831],"about_ca_topic_score_codex":0.00003607115,"about_ca_topic_score_gemma":0.000026650312,"teacher_disagreement_score":0.6271031,"about_ca_system_score_codex":0.00014346204,"about_ca_system_score_gemma":0.00025026067,"threshold_uncertainty_score":0.98651314},"labels":[],"label_agreement":null},{"id":"W3170936139","doi":"10.1200/jco.2021.39.15_suppl.1086","title":"The impact of radiological assessment schedules on progression-free survival in metastatic breast cancer: A systemic review and meta-analysis.","year":2021,"lang":"en","type":"review","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto","funders":"","keywords":"Medicine; Confidence interval; Metastatic breast cancer; Internal medicine; Hazard ratio; Breast cancer; Oncology; Meta-analysis; Subgroup analysis; Cancer; Randomized controlled trial; Progression-free survival; Overall survival","score_opus":0.26687377171932375,"score_gpt":0.6124790798086444,"score_spread":0.3456053080893206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3170936139","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00018677012,0.99011946,0.000055600918,0.008515318,0.00026526683,0.00071283896,0.000042248164,0.0000035292976,0.00009899958],"genre_scores_gemma":[0.000636197,0.99643767,0.0020510643,0.00047436636,0.0002799121,0.000052794403,0.000011611834,0.00002436982,0.000032035718],"study_design_codex":"design_other","study_design_gemma":"meta_analysis","domain_scores_codex":[0.9849571,0.007463948,0.0061215307,0.00039022046,0.00075124804,0.00031596664],"domain_scores_gemma":[0.9771555,0.01438306,0.0069644367,0.000581741,0.00046804867,0.00044722322],"candidate_categories":["metaresearch","metaepi_broad","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.023578439,0.00040768975,0.022062885,0.0002829878,0.0000490622,0.00002185992,0.000546416,0.00039845656,0.00020864942],"category_scores_gemma":[0.013138662,0.00015513776,0.007815196,0.000685448,0.0004531796,0.00003762404,0.0001753966,0.004021909,7.130266e-7],"study_design_candidate":"meta_analysis","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014566505,0.00096868415,0.0019999244,0.00956026,0.20168471,0.0009497718,0.0000047173216,0.000042870124,7.178049e-8,0.00025066859,0.00093945954,0.78345317],"study_design_scores_gemma":[0.0022062242,0.0037040159,0.0057217963,0.01694108,0.88083637,0.0039523584,0.000023581333,0.00019286653,6.2054326e-9,0.00007853139,0.08613321,0.00020995665],"about_ca_topic_score_codex":0.000047427242,"about_ca_topic_score_gemma":0.0000105759755,"teacher_disagreement_score":0.78324324,"about_ca_system_score_codex":0.00036881477,"about_ca_system_score_gemma":0.0054453476,"threshold_uncertainty_score":0.9982759},"labels":[],"label_agreement":null},{"id":"W3171268121","doi":"10.1093/neuonc/noab090.039","title":"EMBR-21. CLINICALLY TRACTABLE OUTCOME PREDICTION OF GROUP 3/4 MEDULLOBLASTOMA BASED ON TPD52 IMMUNOHISTOCHEMISTRY: A MULTICOHORT STUDY","year":2021,"lang":"en","type":"article","venue":"Neuro-Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Children's Hospital","funders":"","keywords":"Medulloblastoma; Oncology; Internal medicine; Biomarker; Immunohistochemistry; Risk stratification; Receiver operating characteristic; Multivariate analysis; Medicine; Bioinformatics; Biology; Pathology; Genetics","score_opus":0.02222417297214018,"score_gpt":0.3545420029800312,"score_spread":0.332317830007891,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3171268121","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98563176,0.000059198093,0.0008712528,0.0031855437,0.0011734427,0.0006394009,0.000013059723,0.00012530271,0.008301037],"genre_scores_gemma":[0.9928887,0.000023863684,0.002594737,0.0037733552,0.00027079514,0.00006771812,0.00006545661,0.000052328105,0.00026307054],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9969647,0.00038700015,0.0011134727,0.00062607095,0.00053781935,0.00037093676],"domain_scores_gemma":[0.997313,0.0011935404,0.0003370665,0.00067420834,0.00020731021,0.0002748812],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010622882,0.00024180682,0.0009039628,0.000121499506,0.00009687172,0.0000140020975,0.00019033352,0.00025275422,0.00028942284],"category_scores_gemma":[0.004680029,0.0002229722,0.0002352999,0.0002686641,0.00019187224,0.000040578772,0.00008340419,0.0012932888,0.000018687368],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012625789,0.0058643357,0.2226166,0.00013167334,0.00012609472,0.001384769,0.00031951535,0.00028065374,0.7493796,0.000012800399,0.0013394958,0.017281892],"study_design_scores_gemma":[0.05919516,0.044168286,0.46677193,0.00059817755,0.0025975124,0.0018566449,0.0029093083,0.243283,0.03272727,0.000059045753,0.14480084,0.0010328302],"about_ca_topic_score_codex":0.000042976353,"about_ca_topic_score_gemma":0.0000031920677,"teacher_disagreement_score":0.71665233,"about_ca_system_score_codex":0.00023912969,"about_ca_system_score_gemma":0.00052311335,"threshold_uncertainty_score":0.90925425},"labels":[],"label_agreement":null},{"id":"W3171972617","doi":"10.1200/jco.2021.39.15_suppl.1552","title":"Automated imaging-based stratification of early-stage lung cancer patients prior to receiving surgical resection using deep learning applied to CTs.","year":2021,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto","funders":"","keywords":"Medicine; Lung cancer; Stage (stratigraphy); Proportional hazards model; Cancer; Hazard ratio; Internal medicine; Radiology; Oncology; Confidence interval","score_opus":0.04646463709203122,"score_gpt":0.4621154341330034,"score_spread":0.4156507970409722,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3171972617","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9860218,0.00011452932,0.008262832,0.0036281128,0.0009881664,0.00027073643,0.0000010615967,0.00003665678,0.000676077],"genre_scores_gemma":[0.98010117,0.00003857571,0.018127142,0.0010249441,0.0005709021,0.000005255579,0.0000073592323,0.00002962478,0.000095046846],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9961674,0.00056860223,0.0021116398,0.0002954064,0.00057560246,0.0002813295],"domain_scores_gemma":[0.99554443,0.0012521925,0.0014203793,0.00016810957,0.0010697925,0.00054509396],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032301003,0.00014247348,0.0010662681,0.00024377002,0.00009293181,0.000026238718,0.00013355695,0.00020541059,0.0001741867],"category_scores_gemma":[0.0081327595,0.00012233274,0.00024610618,0.00047322974,0.000084867286,0.00008104029,0.00005910571,0.0013554967,0.000003709333],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0033553585,0.0010281127,0.7430477,0.00013983564,0.00018251527,0.00033090293,0.00036980963,0.043484442,0.009939239,0.000033067194,0.00036266004,0.19772632],"study_design_scores_gemma":[0.006936194,0.002353497,0.7304524,0.0005903534,0.00032433678,0.000061663006,0.00013627387,0.24938147,0.0012350634,0.000009343974,0.008347572,0.00017182057],"about_ca_topic_score_codex":0.00009072682,"about_ca_topic_score_gemma":0.000033279808,"teacher_disagreement_score":0.20589702,"about_ca_system_score_codex":0.0003326432,"about_ca_system_score_gemma":0.001427662,"threshold_uncertainty_score":0.973626},"labels":[],"label_agreement":null},{"id":"W3172569740","doi":"","title":"Assessing the evidence on Artificial Intelligence: Health technology assessments and real-world needs for decision-making in health care","year":2021,"lang":"en","type":"article","venue":"CMBES Proceedings","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Canadian Agency for Drugs and Technologies in Health","funders":"","keywords":"Presentation (obstetrics); Health care; Context (archaeology); Health technology; Applications of artificial intelligence; Mental health; Medicine; Agency (philosophy); Clinical decision support system; Decision support system; Artificial intelligence; Knowledge management; Computer science; Political science; Psychiatry","score_opus":0.06268552149051926,"score_gpt":0.475429877848829,"score_spread":0.41274435635830975,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3172569740","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8813961,0.00482337,0.01795811,0.09308143,0.00043248563,0.0010456272,0.0000019817007,0.00013255455,0.0011283492],"genre_scores_gemma":[0.9704285,0.000778115,0.02433918,0.0041333395,0.00019391201,0.00005068027,0.0000035430983,0.000029572864,0.00004310415],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.99823296,0.000026540534,0.0005585891,0.000418981,0.0003186088,0.00044432955],"domain_scores_gemma":[0.99853516,0.0007096458,0.00023304274,0.00015419914,0.0002380501,0.00012989309],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013447772,0.00016656618,0.00041892388,0.00047021033,0.0003861127,0.00021004502,0.00014894364,0.0000791802,0.000008560902],"category_scores_gemma":[0.0031568704,0.00012601816,0.00005116397,0.001147947,0.00014657153,0.00017855802,0.0001077546,0.0006792499,0.0000013431096],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000076136224,0.00007184689,0.053929947,0.0007692023,0.000017360944,0.00001436781,0.0027754358,0.00001576173,0.0004873178,0.021110015,0.00062377076,0.92010885],"study_design_scores_gemma":[0.0025188054,0.005995668,0.2622367,0.1289407,0.00024587364,0.0010349742,0.33853647,0.12656343,0.00569219,0.09319743,0.033131402,0.001906355],"about_ca_topic_score_codex":0.00007675951,"about_ca_topic_score_gemma":0.000051936284,"teacher_disagreement_score":0.91820246,"about_ca_system_score_codex":0.00037815134,"about_ca_system_score_gemma":0.0006223314,"threshold_uncertainty_score":0.51388717},"labels":[],"label_agreement":null},{"id":"W3172681723","doi":"10.1038/s41467-022-30695-9","title":"The Medical Segmentation Decathlon","year":2022,"lang":"en","type":"article","venue":"Nature Communications","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1202,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; Polytechnique Montréal","funders":"National Institute of Neurological Disorders and Stroke; NIH Clinical Center; National Cancer Institute; National Institutes of Health; Engineering and Physical Sciences Research Council; KWF Kankerbestrijding; National Institute for Health and Care Research; Siemens Healthineers; UK Research and Innovation; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Wellcome Trust","keywords":"Generalizability theory; Segmentation; Computer science; Task (project management); Set (abstract data type); Artificial intelligence; Machine learning; Image segmentation; Modalities; Image (mathematics); Range (aeronautics); Pattern recognition (psychology); Mathematics","score_opus":0.012895257459997176,"score_gpt":0.35563583564786605,"score_spread":0.34274057818786885,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3172681723","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07596477,0.037388276,0.0011496424,0.84072274,0.001310721,0.0007846337,0.000010950106,0.00028236,0.042385887],"genre_scores_gemma":[0.98687583,0.0012209557,0.0034445343,0.0073685725,0.00007644531,0.00011632233,0.00013356436,0.000013157034,0.0007506417],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99888295,0.00020073538,0.00015660991,0.00009450985,0.00054396596,0.00012121255],"domain_scores_gemma":[0.99833906,0.0005156055,0.000056384986,0.0009355106,0.000050572307,0.000102884565],"candidate_categories":["sts","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0009175428,0.00005342168,0.00007709409,0.00004132052,0.001431847,0.00002205547,0.0007294866,0.00006010083,0.0001861372],"category_scores_gemma":[0.0009309822,0.00003791621,0.000053889074,0.00024045965,0.00015256267,0.000022154889,0.00048119854,0.0024161655,0.000010344548],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013299979,0.0008315836,0.040027395,0.000023362754,0.0002560079,0.000057211615,0.0014363335,0.000080470396,0.0024855232,0.15574044,0.25025892,0.54866976],"study_design_scores_gemma":[0.00047004508,0.000044408152,0.0078068697,0.000009158167,0.000033639888,0.00023557033,0.0004071413,0.017369958,0.000030117526,0.00034964137,0.97319,0.00005342435],"about_ca_topic_score_codex":0.000016112048,"about_ca_topic_score_gemma":0.000028477736,"teacher_disagreement_score":0.910911,"about_ca_system_score_codex":0.00009320196,"about_ca_system_score_gemma":0.00015915904,"threshold_uncertainty_score":0.9998853},"labels":[],"label_agreement":null},{"id":"W3173521037","doi":"10.1016/j.brachy.2021.05.091","title":"PRSOR12 Presentation Time: 12:55 PM","year":2021,"lang":"en","type":"article","venue":"Brachytherapy","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Health Science Centre","funders":"","keywords":"Medicine; Presentation (obstetrics); Surgery","score_opus":0.01124921783448751,"score_gpt":0.30495438005990955,"score_spread":0.29370516222542203,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3173521037","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91565377,0.0022334317,0.007268438,0.02776604,0.0005845463,0.0005054863,0.0000028724464,0.00025073238,0.045734707],"genre_scores_gemma":[0.759854,0.0019164336,0.04476873,0.026086263,0.0033528006,0.000099983044,0.00044708463,0.00018357289,0.16329111],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990576,0.00007302379,0.00019388113,0.00022289282,0.00026105728,0.0001915677],"domain_scores_gemma":[0.99942046,0.000087091634,0.00005732052,0.00023449214,0.00007285555,0.00012775432],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001998674,0.00010419257,0.00025038334,0.00004937017,0.000066844455,0.000037749716,0.000050650084,0.000058787613,0.0017727847],"category_scores_gemma":[0.00022855435,0.00008779765,0.00010752211,0.00013335477,0.000045070796,0.000072268,0.000015923008,0.0002588842,0.0002665581],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007709402,0.0008021613,0.04706706,0.00016062654,0.00045796236,0.0009963957,0.0014127399,0.000147888,0.3220316,0.0017201129,0.10740443,0.5170281],"study_design_scores_gemma":[0.02340596,0.00043414958,0.13960163,0.00032881377,0.0002542336,0.0020036916,0.00021531427,0.08366049,0.025617134,0.0023459902,0.72146946,0.0006631171],"about_ca_topic_score_codex":0.0000142837525,"about_ca_topic_score_gemma":0.000001399715,"teacher_disagreement_score":0.61406505,"about_ca_system_score_codex":0.000026913976,"about_ca_system_score_gemma":0.000110167544,"threshold_uncertainty_score":0.9991397},"labels":[],"label_agreement":null},{"id":"W3174427513","doi":"","title":"Hybrid Machine Learning Methods and Ensemble Voting for Identification of Parkinson’s Disease Subtypes","year":2021,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Artificial intelligence; Computer science; Cluster analysis; Classifier (UML); Pattern recognition (psychology); Weighted voting; Voting; Majority rule; Machine learning; Ensemble learning; Thresholding; Centroid","score_opus":0.016613049469340953,"score_gpt":0.3427401413282805,"score_spread":0.32612709185893957,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3174427513","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39364767,0.0024996628,0.60020596,0.0028679625,0.00012492482,0.00017938025,0.0000058834366,0.000053484237,0.0004150484],"genre_scores_gemma":[0.90047145,0.00017090136,0.095873356,0.00024831214,0.0000737864,0.000009817754,0.00007165979,0.000018989267,0.0030617372],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99910295,0.00010334372,0.00028634258,0.00024507887,0.00012134883,0.00014095874],"domain_scores_gemma":[0.99915826,0.00032019796,0.00011230042,0.0001274188,0.00012919596,0.00015259453],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009388823,0.00008292144,0.00022518061,0.000057482073,0.000087570894,0.000024804702,0.00003399916,0.0000205708,0.000045508576],"category_scores_gemma":[0.0031951156,0.00007236346,0.00007215023,0.00006822225,0.00004748449,0.00004478359,0.00003730886,0.00017050422,0.0000012460179],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023168996,0.00016977852,0.2234458,0.0011475154,0.00015178914,0.000060774375,0.0002672567,0.00029879122,0.41002235,0.0055419854,0.00059690775,0.35806537],"study_design_scores_gemma":[0.0012922543,0.00006804314,0.06311319,0.00012397948,0.00027870294,0.000084372456,0.00010742853,0.7970994,0.102309756,0.001039153,0.034333672,0.00015000819],"about_ca_topic_score_codex":0.000023210627,"about_ca_topic_score_gemma":0.0000014169685,"teacher_disagreement_score":0.7968007,"about_ca_system_score_codex":0.0000136978215,"about_ca_system_score_gemma":0.00006321831,"threshold_uncertainty_score":0.38250828},"labels":[],"label_agreement":null},{"id":"W3174703119","doi":"10.30574/gscarr.2021.7.3.0035","title":"High resolution computed tomography signs lead an early diagnosis of COVID-19","year":2021,"lang":"en","type":"article","venue":"GSC Advanced Research and Reviews","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"ASTER","funders":"","keywords":"Radiological weapon; Medicine; Coronavirus disease 2019 (COVID-19); Computed tomography; Signs and symptoms; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Radiology; Clinical significance; Disease; Internal medicine; Infectious disease (medical specialty)","score_opus":0.08696665160998847,"score_gpt":0.4291629318789984,"score_spread":0.34219628026900994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3174703119","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7463864,0.20708227,0.026139654,0.017358743,0.0003068598,0.0018244059,0.000027517164,0.00010751236,0.0007666312],"genre_scores_gemma":[0.61757785,0.27079728,0.1051095,0.0030535036,0.0006341671,0.00031231504,0.00037113266,0.000078536395,0.002065686],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99767923,0.00062555925,0.00041772757,0.0004143262,0.00046509842,0.00039803883],"domain_scores_gemma":[0.99818194,0.0003762874,0.00009746331,0.0004138944,0.00029220208,0.0006382291],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017198334,0.00013017615,0.0005600686,0.000229939,0.00022029846,0.000028643899,0.00011955291,0.000075711876,0.00009593224],"category_scores_gemma":[0.0029487363,0.00009753351,0.000110588626,0.0008613722,0.00043709064,0.000109636094,0.000100273835,0.0006887132,0.000008644791],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046492537,0.0011534401,0.065904506,0.0043589594,0.00013763054,0.0005646899,0.0008478437,0.000213946,0.07133842,0.0037342426,0.01574308,0.8355383],"study_design_scores_gemma":[0.0054773567,0.00414366,0.030249625,0.002813076,0.00011604342,0.00018700935,0.00043859053,0.0028158226,0.008104137,0.0049370937,0.94023114,0.0004864439],"about_ca_topic_score_codex":0.00015327896,"about_ca_topic_score_gemma":0.000020866266,"teacher_disagreement_score":0.92448807,"about_ca_system_score_codex":0.000049536393,"about_ca_system_score_gemma":0.00018534383,"threshold_uncertainty_score":0.3977301},"labels":[],"label_agreement":null},{"id":"W3175402130","doi":"","title":"A review of recent FDG-PET studies on Alzheimer' s disease; for application to health insurance-covered medicine","year":2007,"lang":"en","type":"review","venue":"Rinshō hōshasen","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hatch (Canada)","funders":"","keywords":"Medicine; Disease; Family medicine; Pathology","score_opus":0.16711341619865652,"score_gpt":0.5075313176571072,"score_spread":0.34041790145845074,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3175402130","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000016383419,0.98157257,0.0010608182,0.00989335,0.00044114667,0.006355204,0.00022131045,0.00006786543,0.00038611842],"genre_scores_gemma":[0.0000050295553,0.97893536,0.0018175663,0.016192598,0.000868272,0.0007111134,0.0012650324,0.000106248575,0.00009880778],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99620247,0.00017795678,0.0017892028,0.0007431412,0.0006225863,0.0004646476],"domain_scores_gemma":[0.9961925,0.0007099457,0.0011327654,0.00090419967,0.00033798753,0.0007226056],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002253936,0.0005399263,0.0038551437,0.0003768883,0.00010117338,0.000005402016,0.00028427364,0.00008800625,0.000044477507],"category_scores_gemma":[0.0029352708,0.00037296506,0.00048341195,0.00070494565,0.00014629717,0.000024705161,0.000075090764,0.0005600288,0.0000320904],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007768399,0.00012690018,0.00001028763,0.18177968,0.00045930684,0.000011941228,0.00004008235,0.0000012082023,3.1341557e-7,0.00017813535,0.029519822,0.78779465],"study_design_scores_gemma":[0.0006408494,0.00046128072,0.00002404802,0.2660372,0.0012041081,0.000030579977,0.000008317507,0.000031426527,3.576642e-7,0.000029565277,0.73133075,0.00020152649],"about_ca_topic_score_codex":0.000034763423,"about_ca_topic_score_gemma":0.0000025994661,"teacher_disagreement_score":0.7875931,"about_ca_system_score_codex":0.0003371621,"about_ca_system_score_gemma":0.00066051993,"threshold_uncertainty_score":0.9998722},"labels":[],"label_agreement":null},{"id":"W3176744136","doi":"10.3390/curroncol28040217","title":"Recent Radiomics Advancements in Breast Cancer: Lessons and Pitfalls for the Next Future","year":2021,"lang":"en","type":"review","venue":"Current Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":82,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine; Radiomics; Breast cancer; Cancer; Data science; Internal medicine; Computer science; Radiology","score_opus":0.15460896146012817,"score_gpt":0.49613582612576235,"score_spread":0.3415268646656342,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3176744136","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000134541815,0.9700956,0.00018269676,0.023220466,0.0049911444,0.001330683,0.00009208888,0.000015765616,0.00005813848],"genre_scores_gemma":[0.0000015575982,0.99588245,0.00031784203,0.00050551683,0.0022907944,0.0005800863,0.00028091524,0.000051980343,0.00008885699],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.998174,0.00017355823,0.00056753686,0.0005108358,0.00015988901,0.00041413886],"domain_scores_gemma":[0.99852794,0.0005752542,0.0003122122,0.00030938795,0.00010114059,0.00017406813],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00055632385,0.0003330155,0.0017953219,0.00013894156,0.00010431438,0.00003191856,0.00021040726,0.00027078477,0.000093733885],"category_scores_gemma":[0.00019223128,0.00021362469,0.00024247525,0.0002815753,0.00014723623,0.00003663202,0.00013333288,0.001383166,0.0000024302115],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023009317,0.0001834243,0.00010191554,0.0051884055,0.00015438936,0.0000248901,0.00009596054,0.000001708428,3.2114428e-7,0.0002132992,0.008776281,0.9852364],"study_design_scores_gemma":[0.0014483866,0.000062605,0.000070565,0.008864035,0.0011518985,0.00046297786,0.000120075085,0.00045938088,2.647648e-8,0.0000142220215,0.98715436,0.0001914373],"about_ca_topic_score_codex":0.000012646271,"about_ca_topic_score_gemma":0.000020134248,"teacher_disagreement_score":0.98504496,"about_ca_system_score_codex":0.00065081805,"about_ca_system_score_gemma":0.0010934492,"threshold_uncertainty_score":0.8711362},"labels":[],"label_agreement":null},{"id":"W3176861478","doi":"10.1016/j.media.2021.102154","title":"United adversarial learning for liver tumor segmentation and detection of multi-modality non-contrast MRI","year":2021,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":69,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Primary Research and Development Plan of Zhejiang Province; Taishan Scholar Project of Shandong Province; China Scholarship Council; National Natural Science Foundation of China","keywords":"Computer science; Modality (human–computer interaction); Artificial intelligence; Feature (linguistics); Feature selection; Segmentation; Feature extraction; Pattern recognition (psychology); Discriminator; Magnetic resonance imaging; Computer vision; Radiology; Medicine","score_opus":0.009171958537115481,"score_gpt":0.2997309343071358,"score_spread":0.2905589757700203,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3176861478","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3653848,0.00012745829,0.6327238,0.0014935278,0.00006306882,0.00013724425,0.000003858592,0.000023894137,0.000042353808],"genre_scores_gemma":[0.9842158,0.00014986166,0.014341712,0.0005710762,0.0001753619,0.000016092199,0.00025281883,0.000016105012,0.0002611946],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99846035,0.00015263546,0.00039746208,0.00032127887,0.0004652127,0.00020305747],"domain_scores_gemma":[0.99881834,0.000292976,0.00015623002,0.00014882385,0.0003059477,0.000277677],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008739857,0.0001252384,0.00049576606,0.00029988794,0.00011498359,0.00002630304,0.000054820728,0.00009086894,0.00028845484],"category_scores_gemma":[0.0035796973,0.00011106338,0.00024656559,0.00084837,0.00018858949,0.000083778636,0.000047098794,0.0004028037,0.0000021580386],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008690803,0.0011892555,0.10575804,0.0012272311,0.006974583,0.0010414151,0.002383485,0.0019119536,0.6168955,0.00003885638,0.00035196214,0.26135865],"study_design_scores_gemma":[0.0036518865,0.00010157488,0.03039565,0.00006129211,0.002969436,0.000042470412,0.00050128426,0.9423726,0.01924764,0.000009792424,0.00053620397,0.00011016249],"about_ca_topic_score_codex":0.0005286698,"about_ca_topic_score_gemma":0.000087351335,"teacher_disagreement_score":0.9404607,"about_ca_system_score_codex":0.000043652388,"about_ca_system_score_gemma":0.000105527666,"threshold_uncertainty_score":0.45290333},"labels":[],"label_agreement":null},{"id":"W3177078060","doi":"10.1371/journal.pone.0253653","title":"A transfer learning approach to facilitate ComBat-based harmonization of multicentre radiomic features in new datasets","year":2021,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre","funders":"H2020 Marie Skłodowska-Curie Actions; Horizon 2020 Framework Programme","keywords":"Harmonization; Transfer of learning; Computer science; Medicine; Data science; Artificial intelligence; Physics","score_opus":0.0455377235558162,"score_gpt":0.2602857313860382,"score_spread":0.21474800783022202,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3177078060","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97583824,0.00056150835,0.01936105,0.0032922646,0.000023467986,0.00040059755,0.00003572819,0.000047132075,0.00043999508],"genre_scores_gemma":[0.9560287,0.000050008366,0.040414635,0.0009498844,0.000050712966,0.000008249035,0.0012377702,0.00002767075,0.0012323948],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99875665,0.00011604824,0.00026679653,0.00028965963,0.00035538885,0.00021544103],"domain_scores_gemma":[0.9993817,0.00009152737,0.000028867651,0.00021892962,0.00006576169,0.00021316712],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021247951,0.00012263747,0.00039771004,0.00014770932,0.000037597736,0.000012442791,0.00008238021,0.000061952545,0.00007128756],"category_scores_gemma":[0.0008258718,0.000119668824,0.000049242895,0.00037021577,0.00003810234,0.00005715872,0.000021880875,0.00047437317,0.000009014178],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008934037,0.0068044234,0.100194655,0.0024069562,0.00050343585,0.00028060825,0.0072876387,0.035315633,0.8305583,0.00021556839,0.0033754008,0.012164002],"study_design_scores_gemma":[0.024683507,0.00057334494,0.12098385,0.0035368758,0.0010954405,0.00007302512,0.0011269788,0.5532872,0.2896817,0.000035435995,0.004115977,0.000806651],"about_ca_topic_score_codex":0.00019546642,"about_ca_topic_score_gemma":0.000011699335,"teacher_disagreement_score":0.54087657,"about_ca_system_score_codex":0.000049597467,"about_ca_system_score_gemma":0.00022953456,"threshold_uncertainty_score":0.4879953},"labels":[],"label_agreement":null},{"id":"W3178035954","doi":"10.1158/1538-7445.am2021-2619","title":"Abstract 2619: Defining real-world recurrence in the AACR Project GENIE Biopharma Collaborative Data","year":2021,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network","funders":"","keywords":"Medicine; Cancer; Disease; Internal medicine; Colorectal cancer; Lung cancer; Stage (stratigraphy); Oncology; Medical physics","score_opus":0.1850372014363198,"score_gpt":0.5244202844852826,"score_spread":0.33938308304896275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3178035954","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8975485,0.01200461,0.000027392667,0.031767387,0.0004625124,0.0011028765,0.00019094991,0.000051521092,0.05684428],"genre_scores_gemma":[0.9860496,0.009703179,0.0011534655,0.0010461655,0.0005087101,0.00017701068,0.00027583807,0.000033280157,0.0010527844],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972473,0.00045180562,0.00027806408,0.0005555152,0.0009141072,0.0005532128],"domain_scores_gemma":[0.99781674,0.0007551038,0.000055586195,0.0008550623,0.00039248713,0.00012499839],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037391747,0.00012151441,0.00024849095,0.00025381235,0.00020489494,0.00013162143,0.00062723004,0.000049731,0.00032526543],"category_scores_gemma":[0.0022539592,0.00008574384,0.000030099407,0.0025864386,0.00027800465,0.00013922586,0.00032153967,0.0018257488,0.000038506238],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000988677,0.00089139823,0.1442809,0.0013807487,0.00032340913,0.008129049,0.016334333,0.00012163302,0.06947379,0.0048589697,0.38878176,0.36443534],"study_design_scores_gemma":[0.005630263,0.00026910688,0.18984076,0.0032653725,0.00010657781,0.00018986824,0.012707591,0.008095814,0.008097645,0.00079827145,0.7703454,0.0006533215],"about_ca_topic_score_codex":0.0032018453,"about_ca_topic_score_gemma":0.001142465,"teacher_disagreement_score":0.38156366,"about_ca_system_score_codex":0.00021594492,"about_ca_system_score_gemma":0.002901217,"threshold_uncertainty_score":0.79320717},"labels":[],"label_agreement":null},{"id":"W3178193369","doi":"10.3389/fnins.2021.691244","title":"MRI Radiomic Signature of White Matter Hyperintensities Is Associated With Clinical Phenotypes","year":2021,"lang":"en","type":"article","venue":"Frontiers in Neuroscience","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Institute of Neurological Disorders and Stroke; National Heart, Lung, and Blood Institute; Agence Nationale de la Recherche","keywords":"Medicine; Neuroimaging; Hyperintensity; Fluid-attenuated inversion recovery; Coronary artery disease; White matter; Diabetes mellitus; Cardiology; Magnetic resonance imaging; Internal medicine; Radiology","score_opus":0.01166537861810454,"score_gpt":0.2762815659163152,"score_spread":0.2646161872982107,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3178193369","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97772264,0.00042003687,0.010639632,0.007780981,0.0016969661,0.00012697536,0.0000071347727,0.000029069619,0.0015765392],"genre_scores_gemma":[0.97511333,0.00013450143,0.009439963,0.012514887,0.000057218207,0.000002385975,0.0000048772017,0.000019823237,0.002713039],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99858916,0.0001067178,0.00031266583,0.00040415113,0.0003277814,0.00025950407],"domain_scores_gemma":[0.99934137,0.00006437544,0.00011511235,0.00025831247,0.00010869791,0.00011215416],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038408907,0.000118538796,0.00043250588,0.000109953035,0.000066511624,0.000018542927,0.00015457139,0.000081241495,0.000045530323],"category_scores_gemma":[0.0007615029,0.00009392519,0.00007617194,0.00048195873,0.00056394597,0.000079306956,0.00007605272,0.0005957856,0.0000017074454],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007256008,0.000116923846,0.9670905,0.000028846163,0.000013518282,0.00033963568,0.00045584608,0.00012720935,0.0034165627,0.000012557788,0.027551576,0.0007742808],"study_design_scores_gemma":[0.0014479036,0.00019313674,0.9565351,0.0003156379,0.000055712993,0.0001711164,0.0003280847,0.03399386,0.00109194,0.00009273434,0.005603527,0.0001712246],"about_ca_topic_score_codex":0.0000053664185,"about_ca_topic_score_gemma":9.818875e-7,"teacher_disagreement_score":0.033866648,"about_ca_system_score_codex":0.000034419776,"about_ca_system_score_gemma":0.00016720216,"threshold_uncertainty_score":0.3830158},"labels":[],"label_agreement":null},{"id":"W3178947120","doi":"10.3389/fonc.2021.639326","title":"Diagnostic Utility of Radiomics in Thyroid and Head and Neck Cancers","year":2021,"lang":"en","type":"review","venue":"Frontiers in Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Discovery Centre","funders":"National Institutes of Health","keywords":"Radiomics; Medicine; Otorhinolaryngology; Head and neck; Medical imaging; Medical physics; Radiogenomics; Disease; Radiology; Pathology; Surgery","score_opus":0.023425822364703468,"score_gpt":0.3656006319548759,"score_spread":0.34217480959017244,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3178947120","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003945676,0.9932213,0.00023103967,0.00036227718,0.00090445,0.00055490504,0.000011167027,0.000007848075,0.000761373],"genre_scores_gemma":[0.0003154867,0.99092925,0.008275443,0.00019302963,0.00010338885,0.000044404485,0.0000506622,0.000029333469,0.00005899554],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981262,0.00033766092,0.000679433,0.00044676775,0.0001133196,0.00029658317],"domain_scores_gemma":[0.99855125,0.0008116587,0.0002293942,0.00023012982,0.00002429537,0.00015328178],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00067259185,0.00024238304,0.002830758,0.0003644938,0.00001906015,0.000006733026,0.00010167953,0.0004243171,0.000016417162],"category_scores_gemma":[0.0022660708,0.00021641696,0.00011065084,0.0003149133,0.0004217246,0.000025074083,0.00010452046,0.0011249841,2.7280785e-7],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023285218,0.00006997325,0.0408087,0.005727133,0.000079355326,0.0004326752,0.00018958503,0.0000016537327,1.6911848e-7,0.000024042192,0.00522254,0.9474209],"study_design_scores_gemma":[0.0018010498,0.0002525134,0.004177639,0.010386091,0.0003720241,0.00033214968,0.00012552194,0.0013829758,1.3863998e-7,0.00009144978,0.9809055,0.00017298068],"about_ca_topic_score_codex":0.0004035276,"about_ca_topic_score_gemma":0.000113460126,"teacher_disagreement_score":0.9756829,"about_ca_system_score_codex":0.0005061235,"about_ca_system_score_gemma":0.0011482057,"threshold_uncertainty_score":0.88252276},"labels":[],"label_agreement":null},{"id":"W3179446910","doi":"10.1158/1538-7445.am2021-3131","title":"Abstract 3131: Tumour spatial heterogeneity in breast cancer and the impact on clinical management","year":2021,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Health Science Centre; Ontario Institute for Cancer Research","funders":"","keywords":"Breast cancer; Lumpectomy; Computational biology; Targeted therapy; Tissue microarray; Medicine; Pathology; Oncology; Biology; Cancer; Immunohistochemistry; Internal medicine; Mastectomy","score_opus":0.07406126000756398,"score_gpt":0.5000764452879315,"score_spread":0.4260151852803675,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3179446910","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9641176,0.0011754857,0.000010560679,0.03234183,0.00016797111,0.00031428668,0.000017974395,0.000010692831,0.0018435973],"genre_scores_gemma":[0.9916315,0.0065106526,0.0000277494,0.00079621765,0.00054136594,0.0000887301,0.0000065374134,0.000019877389,0.0003773669],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9981113,0.00028912496,0.00027171406,0.0003641678,0.0005515061,0.000412189],"domain_scores_gemma":[0.998993,0.00034354778,0.00003704252,0.00028033604,0.00011654438,0.00022953191],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025976351,0.00010957508,0.00030206481,0.00009939044,0.0001068005,0.000062418774,0.00012811867,0.000058209658,0.0004880252],"category_scores_gemma":[0.00019305346,0.00006363746,0.000103884726,0.00025309305,0.00039405236,0.00002805841,0.00014769392,0.0013591169,0.000017450035],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0036974617,0.00043446492,0.57298,0.00027119755,0.00036962272,0.0015307879,0.00020074994,0.00042209824,0.0028271785,0.00031812798,0.010982847,0.40596548],"study_design_scores_gemma":[0.004627171,0.000056883797,0.9906047,0.0003981087,0.000020858311,0.000049331335,0.00007750543,0.002244764,0.0003166902,0.00010849214,0.0014210348,0.000074479794],"about_ca_topic_score_codex":0.0060594627,"about_ca_topic_score_gemma":0.00028824544,"teacher_disagreement_score":0.41762468,"about_ca_system_score_codex":0.00023305033,"about_ca_system_score_gemma":0.00031476642,"threshold_uncertainty_score":0.91601354},"labels":[],"label_agreement":null},{"id":"W3179608547","doi":"10.48550/arxiv.2107.04540","title":"Objective task-based evaluation of artificial intelligence-based medical imaging methods: Framework, strategies and role of the physician","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Task (project management); Modalities; Context (archaeology); Artificial intelligence; Medical imaging; Focus (optics); Engineering; Systems engineering","score_opus":0.05626120817646408,"score_gpt":0.30783032690206324,"score_spread":0.2515691187255992,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3179608547","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48643658,0.00044014514,0.51141727,0.00049413345,0.00021833765,0.00032365983,0.0000050581143,0.000021379063,0.00064345635],"genre_scores_gemma":[0.99144894,0.000040151728,0.008103972,0.00026435705,0.000093241804,0.0000018328437,0.000022242695,0.000021131802,0.0000041401418],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99756694,0.0008815586,0.00034687095,0.0005511436,0.00045676922,0.00019673714],"domain_scores_gemma":[0.9976836,0.000600044,0.00043889793,0.00056320545,0.00057890394,0.00013536951],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018321462,0.00022515915,0.0005351438,0.00019006147,0.000078506615,0.000038554925,0.0003172317,0.00024683133,0.00008794489],"category_scores_gemma":[0.0017259442,0.00019538899,0.00026693233,0.00045928475,0.0006904797,0.00007838418,0.00027228007,0.0012823363,5.05211e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037343396,0.0007817737,0.016220247,0.0010379123,0.00058629224,0.00009618556,0.0019628196,0.60736275,0.007457729,0.056052458,0.0000104125465,0.308058],"study_design_scores_gemma":[0.000302333,0.00003226306,0.0029174648,0.0013559872,0.00079664664,0.0000020912444,0.00538175,0.9165397,0.0066349944,0.06588144,0.0000073324713,0.00014795159],"about_ca_topic_score_codex":0.00034134314,"about_ca_topic_score_gemma":0.000023860106,"teacher_disagreement_score":0.5050124,"about_ca_system_score_codex":0.00013890088,"about_ca_system_score_gemma":0.002750377,"threshold_uncertainty_score":0.7967732},"labels":[],"label_agreement":null},{"id":"W3181477033","doi":"10.1158/1538-7445.am2021-lb018","title":"Abstract LB018: Cloud-based biological domain knowledge derived gene expression classifier to predict the cancer clinical outcome","year":2021,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brantford Energy (Canada)","funders":"","keywords":"Radiation therapy; Gene; Gene expression; Bioinformatics; Medicine; Cancer; Signal transduction; Computational biology; Oncology; Cancer research; Biology; Internal medicine; Genetics","score_opus":0.23126440430392511,"score_gpt":0.5231201485028837,"score_spread":0.29185574419895854,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3181477033","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94736874,0.0035118852,0.0014950975,0.044024274,0.0012305016,0.0006240884,0.000028748573,0.00007275245,0.0016438911],"genre_scores_gemma":[0.9877504,0.0010686892,0.0022343837,0.0039507607,0.0030432132,0.000445674,0.000033914825,0.00005352418,0.0014194312],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9960552,0.0008319603,0.00064748985,0.00080514594,0.0008157381,0.00084450917],"domain_scores_gemma":[0.9965574,0.0012822954,0.00007871212,0.0007814725,0.00054213766,0.000757978],"candidate_categories":["research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004204567,0.00021157865,0.0005201798,0.00012572153,0.0003938094,0.00008693886,0.0005036673,0.0002584902,0.0022853233],"category_scores_gemma":[0.0030298112,0.0001249827,0.00023798188,0.0006227267,0.0006367177,0.000035753375,0.00037081254,0.0024104035,0.00012239987],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000806069,0.00047895472,0.28724793,0.00016445178,0.00012109914,0.0004320619,0.0003648249,0.00016231922,0.5880924,0.00009398616,0.07706734,0.04496857],"study_design_scores_gemma":[0.0045070155,0.00040307405,0.50705457,0.0010021023,0.00005811165,0.000029310431,0.00042206066,0.0014826966,0.07726927,0.00022944379,0.4071578,0.00038451434],"about_ca_topic_score_codex":0.00021509868,"about_ca_topic_score_gemma":0.00006277798,"teacher_disagreement_score":0.51082313,"about_ca_system_score_codex":0.0003527371,"about_ca_system_score_gemma":0.0015619345,"threshold_uncertainty_score":0.9998911},"labels":[],"label_agreement":null},{"id":"W3181844394","doi":"10.1158/1538-7445.am2021-3147","title":"Abstract 3147: Stereotactic image-guided epigenome profiling reveals a neural stem cell evolutionary origin of diffuse gliomas","year":2021,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Lineage (genetic); Glioma; White matter; Biology; Epigenome; Pathology; Brain tumor; Biopsy; Evolutionary biology; DNA methylation; Magnetic resonance imaging; Medicine; Cancer research; Gene; Radiology; Genetics","score_opus":0.08187370815978155,"score_gpt":0.4166930715948029,"score_spread":0.33481936343502133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3181844394","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98621905,0.0068493243,0.00006374817,0.003252829,0.00026049765,0.00046657192,0.000022625642,0.00004362051,0.0028217412],"genre_scores_gemma":[0.99296504,0.0005747115,0.0014214145,0.00016433546,0.00042901462,0.0000746119,0.000030628,0.000055061675,0.0042851954],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99701107,0.00027492328,0.0005108233,0.0004895031,0.0010402541,0.00067341275],"domain_scores_gemma":[0.9977331,0.00039678073,0.00012654332,0.00054385356,0.00082894356,0.00037076618],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012219764,0.00016868369,0.0004447173,0.00029719234,0.00016874932,0.000052166768,0.00023069709,0.00009367982,0.000552506],"category_scores_gemma":[0.00044535252,0.0001495276,0.0001393983,0.00079045846,0.00024364905,0.00013947644,0.0001694014,0.0012733368,0.000039978415],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018921377,0.00034361955,0.035653245,0.0017027745,0.00008749922,0.0012905961,0.0004021343,0.000039723247,0.9512728,0.00014174457,0.0039361017,0.004940555],"study_design_scores_gemma":[0.019104764,0.0010661121,0.37419727,0.0040630647,0.00042227522,0.0011495188,0.0030070317,0.022767844,0.54416275,0.0020799548,0.02649187,0.0014875218],"about_ca_topic_score_codex":0.00028480025,"about_ca_topic_score_gemma":0.0000036237914,"teacher_disagreement_score":0.40711004,"about_ca_system_score_codex":0.0003996971,"about_ca_system_score_gemma":0.0011042177,"threshold_uncertainty_score":0.6097558},"labels":[],"label_agreement":null},{"id":"W3182997057","doi":"10.3389/fonc.2021.661123","title":"Efficacy of Location-Based Features for Survival Prediction of Patients With Glioblastoma Depending on Resection Status","year":2021,"lang":"en","type":"article","venue":"Frontiers in Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":35,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Glioblastoma; Medicine; Magnetic resonance imaging; Glioma; Resection; Regression; Overall survival; Artificial intelligence; Brain cancer; Machine learning; Cancer; Computer science; Oncology; Radiology; Internal medicine; Surgery; Statistics","score_opus":0.00819348889708413,"score_gpt":0.2879373924347972,"score_spread":0.27974390353771306,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3182997057","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.943839,0.000108826884,0.053602733,0.0003962035,0.0012083014,0.00040024356,0.000021918995,0.000014776535,0.00040800162],"genre_scores_gemma":[0.98192656,0.000014526594,0.01764408,0.00009171402,0.00007488163,0.000019742336,0.0001642585,0.00001588591,0.0000483428],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99908507,0.0000998277,0.00025071195,0.00018940079,0.0002062191,0.00016879269],"domain_scores_gemma":[0.999097,0.00030732126,0.0001580213,0.00013526654,0.00024261192,0.000059766015],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024633566,0.000077759825,0.00031961672,0.00023097105,0.000030557156,0.000002580462,0.000039241786,0.00010359704,0.000008608515],"category_scores_gemma":[0.0012692073,0.00006733156,0.00004185283,0.00028319962,0.00009047072,0.000023964634,0.000008893464,0.00022995305,1.3077496e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.014430042,0.0010221245,0.9220085,0.00027162337,0.000104257284,0.000011909145,0.00024996663,0.007844554,0.0005336259,0.00010664275,0.0032182657,0.050198484],"study_design_scores_gemma":[0.013593138,0.004893422,0.9572787,0.00029140405,0.00009385338,0.0000027954409,0.00029530993,0.014960613,0.0041909153,0.0000535956,0.004277931,0.000068291374],"about_ca_topic_score_codex":0.000025429357,"about_ca_topic_score_gemma":0.00003893913,"teacher_disagreement_score":0.050130196,"about_ca_system_score_codex":0.00024254365,"about_ca_system_score_gemma":0.00035118376,"threshold_uncertainty_score":0.27457014},"labels":[],"label_agreement":null},{"id":"W3183402540","doi":"10.1007/s10278-021-00484-9","title":"CT-Based Hand-crafted Radiomic Signatures Can Predict PD-L1 Expression Levels in Non-small Cell Lung Cancer: a Two-Center Study","year":2021,"lang":"en","type":"article","venue":"Journal of Digital Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":32,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"Taishan Scholar Project of Shandong Province; National Natural Science Foundation of China","keywords":"Nomogram; Logistic regression; Medicine; Radiomics; Lung cancer; Cohort; Oncology; Retrospective cohort study; Internal medicine; Artificial intelligence; Radiology; Computer science","score_opus":0.008676278426573241,"score_gpt":0.2882745818422732,"score_spread":0.27959830341569997,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3183402540","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.991156,0.0022912754,0.0026142253,0.0023713417,0.0005616106,0.00033259793,0.000024156461,0.000023434064,0.00062539004],"genre_scores_gemma":[0.9973902,0.000028969995,0.0009330569,0.000921776,0.00042495312,0.00000853116,0.0000175683,0.000060557664,0.00021435073],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9976314,0.000106360785,0.00083078555,0.00034720328,0.00061876443,0.00046552107],"domain_scores_gemma":[0.99850136,0.00016327723,0.00042580746,0.00025714864,0.00027863943,0.00037374988],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047747736,0.00029066266,0.0006788007,0.00043123978,0.00009655173,0.00035711602,0.00023683699,0.00003616911,0.000053478685],"category_scores_gemma":[0.00035250827,0.00023629791,0.00024680104,0.0003596526,0.00008741552,0.00038116143,0.00010101245,0.0012421113,0.0000011825877],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023313805,0.0013408384,0.8723593,0.00019332372,0.000116043324,0.008063826,0.0012148474,0.0030346892,0.10190323,3.4603363e-7,0.002096034,0.009444382],"study_design_scores_gemma":[0.0862317,0.00096042623,0.46981323,0.013425717,0.0010975599,0.003841715,0.0043115774,0.30420303,0.11135784,0.000087513625,0.0031628865,0.0015068128],"about_ca_topic_score_codex":0.00007317802,"about_ca_topic_score_gemma":0.000015840691,"teacher_disagreement_score":0.40254608,"about_ca_system_score_codex":0.00032168592,"about_ca_system_score_gemma":0.0007067646,"threshold_uncertainty_score":0.9635949},"labels":[],"label_agreement":null},{"id":"W3183573067","doi":"10.1016/j.tranon.2021.101183","title":"Prediction of chemotherapy response in breast cancer patients at pre-treatment using second derivative texture of CT images and machine learning","year":2021,"lang":"en","type":"article","venue":"Translational Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University; University of Waterloo; University of Toronto; Sunnybrook Health Science Centre","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Terry Fox Foundation; York University","keywords":"Breast cancer; Receiver operating characteristic; AdaBoost; Feature (linguistics); Feature selection; Artificial intelligence; Medicine; Parametric statistics; Computer science; Pattern recognition (psychology); Cancer; Machine learning; Internal medicine; Mathematics; Statistics; Support vector machine","score_opus":0.01697151064624298,"score_gpt":0.31618849659858733,"score_spread":0.29921698595234436,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3183573067","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99572676,0.00070234673,0.0003321692,0.0027790775,0.000042060412,0.00015748413,0.00013758797,0.000006357589,0.0001161567],"genre_scores_gemma":[0.9977723,0.00012612175,0.0016458752,0.00013834886,0.000029397146,0.000006120949,0.000094649295,0.000011857899,0.00017534851],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99917215,0.00017376084,0.00026830842,0.00015895572,0.00013016012,0.00009667164],"domain_scores_gemma":[0.99943835,0.00024266806,0.00012250632,0.00004909742,0.00010186158,0.00004550241],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017202408,0.00008807425,0.0002965374,0.00008696733,0.00003320878,0.0000017010843,0.000017960208,0.00005169921,0.00038891408],"category_scores_gemma":[0.00004481644,0.00007548251,0.000041386706,0.00011604661,0.000110340756,0.000040588282,0.0000085841775,0.00016077148,1.2539039e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0029413463,0.00033258164,0.8645016,0.00006730127,0.000099730576,0.000020354732,0.0014722445,0.0017010375,0.108974,0.0000074996833,0.000010989096,0.019871313],"study_design_scores_gemma":[0.005246064,0.00043995006,0.964364,0.000102129685,0.000053995616,0.000103356106,0.000029091598,0.022643112,0.0056039253,0.00002802492,0.0013404074,0.000045950783],"about_ca_topic_score_codex":0.00010920835,"about_ca_topic_score_gemma":0.000042167667,"teacher_disagreement_score":0.10337008,"about_ca_system_score_codex":0.0001683849,"about_ca_system_score_gemma":0.00025137354,"threshold_uncertainty_score":0.42583364},"labels":[],"label_agreement":null},{"id":"W3184650787","doi":"10.1007/s11307-021-01634-9","title":"Reply to Letter to Editor RE: “Integration of PET/CT Radiomics and Semantic Features for Differentiation Between Active Pulmonary Tuberculosis and Lung Cancer”","year":2021,"lang":"en","type":"letter","venue":"Molecular Imaging and Biology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Occupational Cancer Research Centre; University of British Columbia","funders":"Basic and Applied Basic Research Foundation of Guangdong Province; Guangdong Province Higher Vocational Colleges and Schools Pearl River Scholar Funded Scheme; Postdoctoral Research Foundation of China; National Natural Science Foundation of China","keywords":"Radiomics; Lung cancer; Pulmonary tuberculosis; Tuberculosis; Medicine; Lung cancer screening; Radiology; Pathology","score_opus":0.008675348422270612,"score_gpt":0.29432188319619906,"score_spread":0.28564653477392843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3184650787","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23669133,0.0028286397,0.0099532455,0.7488902,0.00083717663,0.0006506151,0.00010869534,0.00002311453,0.000016969732],"genre_scores_gemma":[0.33762658,0.0006081566,0.005640099,0.6424044,0.011370013,0.00014766914,0.0019181134,0.00009670719,0.0001883037],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99856675,0.00012994798,0.0002770049,0.00062680367,0.00011375919,0.00028573503],"domain_scores_gemma":[0.99923325,0.00019762924,0.00013095578,0.00020450157,0.00011500661,0.00011868635],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000186146,0.0002716888,0.0006345156,0.00024767508,0.00008282263,0.000047473124,0.000065977496,0.00008412506,0.0000035691096],"category_scores_gemma":[0.00034242662,0.00022731049,0.00008628648,0.00010202221,0.00011163298,0.000030869778,0.00009567908,0.00075549434,1.03218916e-7],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000105132,0.000020374076,0.021304116,0.0010312381,0.0005216626,0.00043227363,0.00026009895,0.0000028490413,0.16826352,0.0000075972052,0.7531413,0.054909833],"study_design_scores_gemma":[0.0036232905,0.0008157726,0.065118626,0.0047546523,0.0055207266,0.0024080481,0.000259839,0.018467816,0.040732257,0.00048482898,0.85588497,0.0019291611],"about_ca_topic_score_codex":0.00047381205,"about_ca_topic_score_gemma":0.0000037080042,"teacher_disagreement_score":0.12753126,"about_ca_system_score_codex":0.00005726995,"about_ca_system_score_gemma":0.00004125005,"threshold_uncertainty_score":0.92694527},"labels":[],"label_agreement":null},{"id":"W3185060682","doi":"","title":"Clinical Evaluation of Deep Learning for Improving PET Image Quality","year":2020,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network","funders":"","keywords":"Convolutional neural network; Artificial intelligence; Image quality; Computer science; Context (archaeology); Deep learning; Gaussian blur; Positron emission tomography; Pattern recognition (psychology); Gaussian filter; Nuclear medicine; Computer vision; Medicine; Image processing; Image (mathematics); Image restoration","score_opus":0.07372974722406589,"score_gpt":0.4511167457780888,"score_spread":0.3773869985540229,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3185060682","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6931358,0.000087923494,0.29385465,0.006888733,0.00012644542,0.0005073355,7.93982e-7,0.000078443896,0.0053198966],"genre_scores_gemma":[0.9379922,0.000008041893,0.06015545,0.0013742355,0.00032745206,0.000011539898,0.000024716614,0.000016639711,0.00008972119],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998413,0.00023940009,0.0005437812,0.00023946803,0.0004183127,0.00014599165],"domain_scores_gemma":[0.99877405,0.00039655008,0.00018967643,0.00011700258,0.0003421939,0.00018053774],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0046983617,0.000078093675,0.00032723526,0.000026242931,0.000047276957,0.000011463096,0.00006471639,0.000038868082,0.00028179886],"category_scores_gemma":[0.016115755,0.00006378767,0.00016545868,0.000081825245,0.00007663553,0.00005355554,0.00003566909,0.00036790656,0.000008271024],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024012743,0.000098564306,0.053139735,0.00047982344,0.00006791876,0.00000396251,0.0003801758,0.00023335658,0.03224152,0.00041711453,0.00038820397,0.9123095],"study_design_scores_gemma":[0.0030124888,0.0003509923,0.02867847,0.00001725835,0.0002296637,0.000005919483,0.0003177981,0.96567976,0.00046016462,0.00012202484,0.001049568,0.00007591077],"about_ca_topic_score_codex":0.000034329856,"about_ca_topic_score_gemma":0.0000013734399,"teacher_disagreement_score":0.9654464,"about_ca_system_score_codex":0.00002212558,"about_ca_system_score_gemma":0.00009851474,"threshold_uncertainty_score":0.99217194},"labels":[],"label_agreement":null},{"id":"W3185690765","doi":"10.18280/ts.380310","title":"Predictions for Central Lymph Node Metastasis of Papillary Thyroid Carcinoma via CNN-Based Fusion Modeling of Ultrasound Images","year":2021,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Natural Science Foundation of Guangdong Province; National Natural Science Foundation of China","keywords":"Convolutional neural network; Thyroid carcinoma; Artificial intelligence; Ultrasound; Medicine; Context (archaeology); Feature extraction; Computer science; Pattern recognition (psychology); Radiology; Classifier (UML); Internal medicine; Thyroid","score_opus":0.014701604769402512,"score_gpt":0.2593779246439803,"score_spread":0.24467631987457777,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3185690765","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4947997,0.0006591382,0.50306773,0.00077994727,0.000105723106,0.0002600728,0.00010343135,0.000027749016,0.00019651341],"genre_scores_gemma":[0.97802246,0.00007370584,0.02097694,0.000348514,0.0001801234,0.00002479633,0.00030506877,0.000029570623,0.000038826132],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99835426,0.00007181135,0.00055440696,0.00027871758,0.00042825894,0.00031256425],"domain_scores_gemma":[0.99898285,0.00022649368,0.00015189042,0.00020799956,0.00026209193,0.00016869586],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037061362,0.00016798545,0.0004209419,0.00011587463,0.00010082324,0.000012088739,0.0000912299,0.000059544134,0.00032018858],"category_scores_gemma":[0.00017979136,0.00015058846,0.00027777144,0.00017139937,0.000095856645,0.000056295943,0.000023479746,0.00014653432,6.162451e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037358058,0.0007665316,0.03188138,0.0008880989,0.0003310234,0.00003628973,0.00044110385,0.16614269,0.7939158,0.00008728352,0.0007365688,0.004399645],"study_design_scores_gemma":[0.004257654,0.0002703362,0.017999824,0.00024563566,0.00067072496,0.00004850183,0.00025786235,0.8941638,0.08167658,0.00010173738,0.00015521687,0.00015212368],"about_ca_topic_score_codex":0.00010554388,"about_ca_topic_score_gemma":0.0000012471395,"teacher_disagreement_score":0.7280211,"about_ca_system_score_codex":0.000064624655,"about_ca_system_score_gemma":0.00025830907,"threshold_uncertainty_score":0.6140819},"labels":[],"label_agreement":null},{"id":"W3185777129","doi":"10.3390/cancers13153723","title":"Site-Specific Variation in Radiomic Features of Head and Neck Squamous Cell Carcinoma and Its Impact on Machine Learning Models","year":2021,"lang":"en","type":"article","venue":"Cancers","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; McGill University Health Centre; Princess Margaret Cancer Centre; Jewish General Hospital; University of Toronto; University Health Network","funders":"National Center for Advancing Translational Sciences","keywords":"Head and neck squamous-cell carcinoma; Medicine; Larynx; Head and neck; Basal cell; Head and neck cancer; Radiology; Pathology; Radiation therapy; Surgery","score_opus":0.014504884042247729,"score_gpt":0.27538936088179583,"score_spread":0.2608844768395481,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3185777129","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98423576,0.013934052,0.00010855476,0.0003289752,0.000079588164,0.00012258446,0.000007672846,0.000013925932,0.001168894],"genre_scores_gemma":[0.99819326,0.0008311877,0.00031393135,0.00017737398,0.000074439726,0.0000035537237,0.000027863141,0.000021929014,0.00035642905],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9991699,0.00006356765,0.00017285481,0.00026156442,0.00015138552,0.00018075455],"domain_scores_gemma":[0.9995402,0.00010308865,0.000073834206,0.00011026452,0.000040440686,0.00013213667],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016536158,0.00012917689,0.00030382254,0.000121255616,0.00005083071,0.000013436029,0.000030098749,0.00006569935,0.000038191436],"category_scores_gemma":[0.00009697277,0.00011144429,0.000042828964,0.0001502606,0.000042171047,0.000048497568,0.000022973565,0.00046801916,7.163482e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018836455,0.00015675239,0.36564782,0.0010543652,0.00006570085,0.00088982383,0.012868294,0.3114921,0.28899732,0.00083006156,0.0011894621,0.014924685],"study_design_scores_gemma":[0.005089714,0.0004683218,0.5115201,0.00017644202,0.000047758167,0.00017216205,0.00010285615,0.47836104,0.0034692287,0.00009617092,0.00031589487,0.00018029299],"about_ca_topic_score_codex":0.00092061225,"about_ca_topic_score_gemma":0.000026841988,"teacher_disagreement_score":0.2855281,"about_ca_system_score_codex":0.00033979135,"about_ca_system_score_gemma":0.00021425822,"threshold_uncertainty_score":0.45445663},"labels":[],"label_agreement":null},{"id":"W3186077304","doi":"10.1016/j.compmedimag.2021.101957","title":"MSDS-UNet: A multi-scale deeply supervised 3D U-Net for automatic segmentation of lung tumor in CT","year":2021,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":68,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Fundamental Research Funds for the Central Universities; Beijing Science and Technology Planning Project; National University's Basic Research Foundation of China; National Natural Science Foundation of China","keywords":"Computer science; Scale (ratio); Artificial intelligence; Segmentation; Computer vision; Nuclear medicine; Pattern recognition (psychology); Medicine; Cartography; Geography","score_opus":0.011006501930095686,"score_gpt":0.3016983485890285,"score_spread":0.29069184665893283,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3186077304","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6907326,0.0016303419,0.30095774,0.005687019,0.00040188732,0.0004448789,0.000008827002,0.00009068026,0.000045990728],"genre_scores_gemma":[0.65740466,0.0006282979,0.3331157,0.008151289,0.00024339817,0.00007226193,0.000246945,0.00006760266,0.0000698503],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981353,0.00012604173,0.00058623415,0.00038328816,0.00043517697,0.00033395045],"domain_scores_gemma":[0.99880475,0.00038832723,0.0001157491,0.00021888889,0.00012554624,0.00034673852],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00077409873,0.00019018279,0.00058795454,0.00022131414,0.000076782264,0.000037847538,0.00011399179,0.000048981987,0.000043002223],"category_scores_gemma":[0.0007053333,0.00017255043,0.0001273669,0.00036516876,0.000278351,0.00007507542,0.00009151875,0.00043725714,5.5174456e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019196859,0.0013502286,0.29720622,0.0047979103,0.00026308128,0.0016809189,0.0025432466,0.000039010833,0.02619139,0.00037509328,0.0020734167,0.6632875],"study_design_scores_gemma":[0.008718239,0.00004948711,0.020330302,0.0010785809,0.00010512456,0.000515281,0.00014667588,0.9670242,0.00045907655,0.00014022128,0.0012684322,0.0001643774],"about_ca_topic_score_codex":0.00007276982,"about_ca_topic_score_gemma":0.00001156836,"teacher_disagreement_score":0.96698517,"about_ca_system_score_codex":0.00002745324,"about_ca_system_score_gemma":0.00023105714,"threshold_uncertainty_score":0.7036402},"labels":[],"label_agreement":null},{"id":"W3188453164","doi":"","title":"Re-evaluating the value of CT-based attenuation correction in Myocardial Perfusion Imaging","year":2018,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Michener Institute","funders":"","keywords":"Medical physics; Medicine; Diagnostic odds ratio; Correction for attenuation; Radiology; MEDLINE; Diagnostic accuracy; Nuclear medicine; Computer science; Positron emission tomography","score_opus":0.017406551099535473,"score_gpt":0.33965556149307524,"score_spread":0.32224901039353976,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3188453164","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96430105,0.000039116894,0.016123082,0.007785842,0.00084165763,0.00023668834,2.0893701e-7,0.00003690437,0.01063545],"genre_scores_gemma":[0.9950375,0.0000044832527,0.0024214895,0.0018888148,0.00039092827,0.000006429796,0.0000088290335,0.000013229384,0.00022832489],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989356,0.00014745127,0.0002613611,0.00016694436,0.0003420575,0.00014658355],"domain_scores_gemma":[0.999333,0.00022290241,0.00009790434,0.00018831505,0.00011775284,0.000040112518],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016486952,0.00007772824,0.0001570767,0.000112790185,0.00009824709,0.000012668765,0.000059832775,0.000018647384,0.00015494258],"category_scores_gemma":[0.0013268241,0.000051372306,0.000060396374,0.00023997063,0.00013967967,0.000044701563,0.000024614721,0.00025502028,0.000012569501],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027553018,0.0001123828,0.43984595,0.000040877476,0.000016554866,0.0000107524675,0.0011786894,0.0026361605,0.07690333,0.00019794882,0.004762019,0.47401983],"study_design_scores_gemma":[0.001066983,0.00018961978,0.09441925,0.00016412284,0.00003869941,0.000014947899,0.00040489237,0.89883167,0.004344894,0.000054424254,0.00041643155,0.00005409483],"about_ca_topic_score_codex":0.00071039033,"about_ca_topic_score_gemma":0.00001986107,"teacher_disagreement_score":0.8961955,"about_ca_system_score_codex":0.000066022716,"about_ca_system_score_gemma":0.00010406377,"threshold_uncertainty_score":0.20949018},"labels":[],"label_agreement":null},{"id":"W3189107271","doi":"10.11591/eei.v10i5.3132","title":"Classifying lymphoma and tuberculosis case reports using machine learning algorithms","year":2021,"lang":"en","type":"article","venue":"Bulletin of Electrical Engineering and Informatics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Durham College","funders":"","keywords":"Machine learning; Artificial intelligence; Tuberculosis; Cluster analysis; Computer science; Perceptron; Natural language processing; Recall; Lymphoma; Algorithm; Artificial neural network; Medicine; Pathology; Psychology","score_opus":0.007735461172515772,"score_gpt":0.23193154898518753,"score_spread":0.22419608781267175,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3189107271","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9803887,0.003066077,0.015305449,0.0005219567,0.000076720185,0.000091861664,0.0000011105994,0.000078255536,0.00046987628],"genre_scores_gemma":[0.8932801,0.000887888,0.105246,0.00030770732,0.0000794176,0.0000028205654,0.000013649037,0.000031759133,0.00015067452],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989006,0.000018054949,0.0005182526,0.00012394959,0.00019226821,0.00024688416],"domain_scores_gemma":[0.9993086,0.0001595815,0.00012206102,0.00012064758,0.00008441941,0.00020467506],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032572425,0.00014993994,0.00035898914,0.00012255453,0.00009372739,0.00003870321,0.000017363534,0.00009431367,0.000024603838],"category_scores_gemma":[0.001231133,0.00013768119,0.000056165292,0.00020002206,0.000042375534,0.00003309256,0.000064914195,0.0003716955,6.1685535e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015382537,0.00066075876,0.056323662,0.007973385,0.0013314708,0.048863683,0.0042981575,0.036873497,0.022101138,0.0015109114,0.0016111296,0.8182984],"study_design_scores_gemma":[0.000588806,0.00009871928,0.00053521676,0.00017897357,0.000106737396,0.07755875,0.0000788164,0.89554614,0.00084145257,0.000005334668,0.02431926,0.00014179006],"about_ca_topic_score_codex":0.00009188583,"about_ca_topic_score_gemma":1.7485822e-7,"teacher_disagreement_score":0.8586726,"about_ca_system_score_codex":0.000038393766,"about_ca_system_score_gemma":0.00004874755,"threshold_uncertainty_score":0.56144756},"labels":[],"label_agreement":null},{"id":"W3189544101","doi":"10.1097/ju.0000000000002064.17","title":"MP43-17 DIFFERENCES IN GLEASON SCORE (GS) DISTRIBUTION AND TUMOR AGGRESSIVENESS IN LARGE COHORTS OF ASIAN AND CAUCASIAN MEN","year":2021,"lang":"en","type":"article","venue":"The Journal of Urology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Medicine","score_opus":0.008484821881420634,"score_gpt":0.26765862033719734,"score_spread":0.2591737984557767,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3189544101","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98579615,0.0040731574,0.00031569295,0.009566921,0.00006165165,0.000056219844,0.0000032276007,0.0000013180068,0.00012565001],"genre_scores_gemma":[0.9987435,0.0009191195,0.000048100985,0.00022042799,0.000045563305,5.861427e-7,0.0000040485543,0.000004479289,0.000014170121],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9991404,0.00024218528,0.00027962422,0.00007504499,0.00012028295,0.00014248477],"domain_scores_gemma":[0.99944913,0.00014063362,0.00021838334,0.00007176888,0.00005047586,0.00006958921],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00077326276,0.00006555774,0.00035242282,0.0000675094,0.000026904543,0.0000055703654,0.000054187447,0.00004332864,0.000019637679],"category_scores_gemma":[0.00050981366,0.000041635027,0.000021318663,0.000100785015,0.00014300951,0.000032868527,0.00004175306,0.00044401392,8.817994e-8],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002748595,0.00008485207,0.99041915,0.00004542193,0.000029571846,0.000871178,0.0007351314,0.000008512524,0.0018554986,0.00012791314,0.00008576097,0.0054621794],"study_design_scores_gemma":[0.0015657718,0.00025056704,0.9918836,0.00023572819,0.0000812239,0.0032185395,0.0004846949,0.0013617309,0.00015377143,0.00041081986,0.00031705553,0.000036513924],"about_ca_topic_score_codex":0.000047425376,"about_ca_topic_score_gemma":0.00006476498,"teacher_disagreement_score":0.012947342,"about_ca_system_score_codex":0.00001632449,"about_ca_system_score_gemma":0.00007725805,"threshold_uncertainty_score":0.19290443},"labels":[],"label_agreement":null},{"id":"W3192156946","doi":"10.1007/s10278-021-00500-y","title":"Overall Survival Prediction in Renal Cell Carcinoma Patients Using Computed Tomography Radiomic and Clinical Information","year":2021,"lang":"en","type":"article","venue":"Journal of Digital Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":71,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Université de Genève; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung","keywords":"Computed tomography; Renal cell carcinoma; Medicine; Radiology; Radiomics; Carcinoma; Tomography; Kidney cancer; Medical physics; Oncology; Pathology","score_opus":0.01119431458532491,"score_gpt":0.27321169718508886,"score_spread":0.2620173825997639,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3192156946","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9929955,0.00024549398,0.0050012623,0.00034082058,0.0005634854,0.00006882943,0.0000069720504,0.00000945942,0.0007681689],"genre_scores_gemma":[0.99681586,0.000022274875,0.0026213143,0.00025991639,0.00022385083,1.4116262e-7,0.000036070964,0.000011061007,0.000009537785],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9984733,0.000060000777,0.00084237027,0.0001118327,0.00033677267,0.00017576254],"domain_scores_gemma":[0.9989922,0.00009748405,0.00035646974,0.00008565098,0.00027885585,0.00018932464],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004274811,0.000110155,0.00033324337,0.00031328853,0.000038979113,0.00017751416,0.00005357651,0.000042714528,0.000005650667],"category_scores_gemma":[0.00034485137,0.00009926585,0.0001477057,0.00020512243,0.0000698244,0.0012558976,0.00005418737,0.00054744846,8.995219e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008667162,0.00016590272,0.9739448,0.0000449297,0.000026692658,0.00013505609,0.0001312905,0.00014573893,0.00038492135,0.0000044276157,0.00021672847,0.024712866],"study_design_scores_gemma":[0.005500996,0.00014829195,0.9056929,0.00024142067,0.0000777385,0.0005701236,0.00009658244,0.086732894,0.000118869124,0.00007259165,0.00065352843,0.00009410132],"about_ca_topic_score_codex":0.000009017885,"about_ca_topic_score_gemma":2.5326082e-7,"teacher_disagreement_score":0.08658715,"about_ca_system_score_codex":0.00008214781,"about_ca_system_score_gemma":0.00015123171,"threshold_uncertainty_score":0.4047944},"labels":[],"label_agreement":null},{"id":"W3192284081","doi":"10.1016/j.ebiom.2021.103531","title":"Radiomics: The endocrinologists’ new best friend?","year":2021,"lang":"en","type":"letter","venue":"EBioMedicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Medicine; Adipose tissue; Weight loss; Body mass index; Obesity; Radiomics; Internal medicine; Bioinformatics; Radiology; Biology","score_opus":0.02713013240347573,"score_gpt":0.29856428895771936,"score_spread":0.27143415655424363,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3192284081","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00037379607,0.012354246,0.0013267961,0.96383804,0.0034830954,0.0005379012,0.000015924319,0.00017993446,0.01789025],"genre_scores_gemma":[0.0008366118,0.0019417309,0.0013684878,0.872361,0.04201272,0.000029414134,0.0014959895,0.0001648386,0.079789214],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99610204,0.00016304309,0.0007440002,0.00087930163,0.001121699,0.0009898919],"domain_scores_gemma":[0.99723464,0.00047018274,0.000312241,0.0014523304,0.00015038121,0.00038024716],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004007573,0.0006275505,0.0012710877,0.00036176827,0.00021060192,0.00007633176,0.00064142793,0.0007096336,0.001822293],"category_scores_gemma":[0.0011729413,0.00038256383,0.00040132154,0.0006045467,0.00089647254,0.000044162258,0.0002252258,0.0067916196,0.00030705638],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021338394,0.00004204253,0.00022995507,0.00023577177,0.00035156874,0.00956567,0.00023397326,0.0000010855622,0.00033284287,0.000036328478,0.9507544,0.038195018],"study_design_scores_gemma":[0.002205927,0.0003119772,0.00021671448,0.0008807823,0.0007715514,0.0048632943,0.0001798626,0.00024699685,0.000100271754,0.00017337548,0.9896928,0.0003564414],"about_ca_topic_score_codex":0.0006332831,"about_ca_topic_score_gemma":0.0000033497263,"teacher_disagreement_score":0.09147707,"about_ca_system_score_codex":0.00022479404,"about_ca_system_score_gemma":0.0008540851,"threshold_uncertainty_score":0.9998626},"labels":[],"label_agreement":null},{"id":"W3194191313","doi":"10.2139/ssrn.3901760","title":"Novel CT Radiomics Nomograms for Prediction of EGFR Mutations and Ki-67 Proliferation Index in Non-Small Cell Lung Cancer: A Multicentre Study","year":2021,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Radiomics; Nomogram; Lung cancer; Oncology; Medicine; Cancer; Index (typography); Internal medicine; Proliferation index; Radiology; Computer science; Immunohistochemistry","score_opus":0.008025807292064037,"score_gpt":0.28027264790126116,"score_spread":0.2722468406091971,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3194191313","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9117617,0.0021220432,0.08429335,0.0008070047,0.00015915949,0.0008094552,0.000010413832,0.000010579859,0.00002629412],"genre_scores_gemma":[0.9961672,0.0017772114,0.0014365496,0.00007330437,0.00023163384,0.000051944688,0.000037338887,0.00002572881,0.0001991126],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984409,0.000050280534,0.0004150118,0.00021700168,0.00019076384,0.0006860309],"domain_scores_gemma":[0.9993591,0.000073769865,0.00018641082,0.00010045845,0.00017864055,0.00010164035],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009249549,0.00012519439,0.00027268313,0.0001580248,0.000112796544,0.000034720913,0.000058921305,0.000045281507,0.0000042954666],"category_scores_gemma":[0.00017511008,0.00011689948,0.0000702654,0.00021306369,0.000031430718,0.00008925989,0.000018204566,0.0011813497,1.0968216e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021972062,0.001169105,0.9446519,0.00018675717,0.0002816191,0.000021643964,0.0023662995,0.0033135458,0.014156087,0.00023525617,0.000019592384,0.03337845],"study_design_scores_gemma":[0.022643834,0.0009267022,0.19948965,0.0003317434,0.00068857154,0.0011932215,0.009935232,0.762741,0.0009830848,0.00072402175,0.00013479308,0.00020809473],"about_ca_topic_score_codex":0.00023272347,"about_ca_topic_score_gemma":0.0013274851,"teacher_disagreement_score":0.7594275,"about_ca_system_score_codex":0.0005769932,"about_ca_system_score_gemma":0.0018257227,"threshold_uncertainty_score":0.5132443},"labels":[],"label_agreement":null},{"id":"W3194381195","doi":"10.1186/s13550-021-00809-3","title":"Preselection of robust radiomic features does not improve outcome modelling in non-small cell lung cancer based on clinical routine FDG-PET imaging","year":2021,"lang":"en","type":"article","venue":"EJNMMI Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kingston Health Sciences Centre; Queen's University","funders":"Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Medicine; Radiomics; Intraclass correlation; Generalizability theory; Lung cancer; Positron emission tomography; Receiver operating characteristic; Correction for attenuation; Nuclear medicine; Logistic regression; Radiology; Internal medicine; Statistics","score_opus":0.05661806362235724,"score_gpt":0.42129536344072793,"score_spread":0.3646772998183707,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3194381195","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9745436,0.0006745146,0.012215671,0.008980789,0.00066159863,0.0007071429,0.00001677747,0.000044811262,0.0021551207],"genre_scores_gemma":[0.9865293,0.00029447844,0.006769026,0.00059589895,0.0006268851,0.00005687491,0.000031815274,0.00006798035,0.0050277617],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960607,0.00060135464,0.0007908125,0.0007579306,0.0010152981,0.0007738881],"domain_scores_gemma":[0.9973402,0.0011306956,0.00015520465,0.00058121904,0.0004934821,0.0002992147],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.004887172,0.00022787928,0.00067308574,0.0005515246,0.00016511959,0.000059953833,0.00026733178,0.00013298751,0.00014363528],"category_scores_gemma":[0.0016276697,0.00017689221,0.00021976033,0.0006950032,0.00023688996,0.00007971767,0.00014097622,0.0031430814,0.0000054361353],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009508917,0.0007111638,0.8344936,0.0009861438,0.000063846484,0.000885319,0.0003115777,0.10462184,0.050460607,0.000034474077,0.0017944453,0.0046861283],"study_design_scores_gemma":[0.0037125736,0.00016313186,0.040997665,0.00048098725,0.000050599523,0.00002176936,0.00012540308,0.9307786,0.023299858,0.000019829882,0.00017297147,0.00017656072],"about_ca_topic_score_codex":0.001997117,"about_ca_topic_score_gemma":0.00009827474,"teacher_disagreement_score":0.8261568,"about_ca_system_score_codex":0.00031897888,"about_ca_system_score_gemma":0.00078901893,"threshold_uncertainty_score":0.9991567},"labels":[],"label_agreement":null},{"id":"W3194419317","doi":"","title":"RAIVEN: A novel framework for translation of AI tools to the radiology environment","year":2021,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Terry Fox Research Institute","funders":"","keywords":"DICOM; Computer science; Python (programming language); Workflow; Artificial intelligence; Software engineering; Programming language; Database","score_opus":0.030266078847702042,"score_gpt":0.3222373166494264,"score_spread":0.29197123780172435,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3194419317","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009395352,0.000198804,0.85542184,0.13397124,0.000104986764,0.00027724748,0.00000502919,0.000009024402,0.0006164921],"genre_scores_gemma":[0.48813272,0.000060039256,0.4823082,0.028308839,0.00033231286,0.000051718816,0.00004128348,0.000017979391,0.0007469133],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99945813,0.0000213083,0.00016335903,0.00013701005,0.0001036461,0.00011656479],"domain_scores_gemma":[0.99933445,0.00037652184,0.0000264153,0.00017773488,0.000022936794,0.00006195935],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024365375,0.000055621196,0.0001691166,0.000020782561,0.000033652956,0.0000065963736,0.00005001341,0.000053530264,0.0002467434],"category_scores_gemma":[0.0005144634,0.000035790832,0.000078516,0.00005836286,0.000038059567,0.000015547006,0.000013301706,0.00019109002,0.0000061999026],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045322915,0.0005212081,0.0035814752,0.00022717989,0.00036342186,0.000019800613,0.003291623,0.0069231223,0.18550105,0.16012245,0.01748767,0.62150776],"study_design_scores_gemma":[0.0026358601,0.00046520025,0.01036042,0.000148932,0.00018494291,0.00016235781,0.00034758143,0.042046595,0.012625444,0.005071769,0.92579025,0.00016066476],"about_ca_topic_score_codex":0.0000070212805,"about_ca_topic_score_gemma":8.337442e-7,"teacher_disagreement_score":0.90830255,"about_ca_system_score_codex":0.000014873363,"about_ca_system_score_gemma":0.000043398868,"threshold_uncertainty_score":0.27016672},"labels":[],"label_agreement":null},{"id":"W3194507152","doi":"10.1016/j.compbiomed.2021.104752","title":"Non-small cell lung carcinoma histopathological subtype phenotyping using high-dimensional multinomial multiclass CT radiomics signature","year":2021,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":101,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Radiomics; Signature (topology); Pathology; Lung; Medicine; Carcinoma; Radiology; Internal medicine; Mathematics","score_opus":0.014404754018156983,"score_gpt":0.28578331501196425,"score_spread":0.27137856099380725,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3194507152","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97359914,0.0044834786,0.017252425,0.002418647,0.0018166493,0.0002271531,0.0000023430173,0.000037776917,0.00016238421],"genre_scores_gemma":[0.9518651,0.00013080685,0.04336104,0.003665733,0.00077752856,0.0000034318666,0.00010701482,0.000022266742,0.000067073284],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982687,0.00016133692,0.0004283108,0.00060584024,0.000111170215,0.00042461563],"domain_scores_gemma":[0.99895227,0.00035295426,0.00012345711,0.00023724014,0.00008720167,0.00024684763],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005236666,0.00026105368,0.0007191727,0.00018655739,0.0001369831,0.0000073744563,0.00011531814,0.00021836451,0.00003917128],"category_scores_gemma":[0.00032068836,0.00020462093,0.00006563365,0.00020259937,0.0004946589,0.000027348926,0.00016754458,0.0010144202,0.0000015745433],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045921758,0.00035563507,0.6714715,0.00039951724,0.000079976366,0.00661922,0.0011649177,0.001117062,0.2904317,0.0009867104,0.0014369047,0.025477637],"study_design_scores_gemma":[0.012494433,0.0003822235,0.21274787,0.0006778973,0.000230285,0.0027517765,0.00014214561,0.76688343,0.00174653,0.00035880363,0.0011607285,0.00042388483],"about_ca_topic_score_codex":0.0001390786,"about_ca_topic_score_gemma":0.000004874312,"teacher_disagreement_score":0.7657664,"about_ca_system_score_codex":0.00014910054,"about_ca_system_score_gemma":0.00016768614,"threshold_uncertainty_score":0.8344199},"labels":[],"label_agreement":null},{"id":"W3195552573","doi":"10.3390/app11167488","title":"Interactive Machine Learning-Based Multi-Label Segmentation of Solid Tumors and Organs","year":2021,"lang":"en","type":"article","venue":"Applied Sciences","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"National Institute of Neurological Disorders and Stroke; National Cancer Institute; National Institutes of Health","keywords":"Computer science; Artificial intelligence","score_opus":0.0192261891643533,"score_gpt":0.32648074892789314,"score_spread":0.3072545597635398,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3195552573","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9776196,0.00019939808,0.018887145,0.001654495,0.00006161696,0.00013623993,0.0000031177851,0.0000346514,0.0014037276],"genre_scores_gemma":[0.9728761,0.000020397436,0.02627811,0.00061798916,0.000021677952,0.0000052983078,0.000017817008,0.000007068408,0.00015554813],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99919754,0.00003200885,0.00016956651,0.00023370737,0.00023224561,0.00013493915],"domain_scores_gemma":[0.9995755,0.00012653212,0.00009992573,0.00006611883,0.000052825624,0.00007910646],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035040567,0.00007817564,0.00018981902,0.00007750613,0.00012957705,0.000019873616,0.000057025118,0.000022928667,0.00007766276],"category_scores_gemma":[0.0002757077,0.000062246545,0.00001923536,0.0002836177,0.00034682962,0.00004533765,0.000035688172,0.00022096609,0.000003763038],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000061017516,0.00030317466,0.052266594,0.0001154256,0.000040195944,0.000039153398,0.0018420507,0.0011744848,0.89406794,0.00047652694,0.00008457699,0.04952888],"study_design_scores_gemma":[0.0028042097,0.00026677578,0.012743642,0.00011772961,0.00006175256,0.0000551013,0.0025042323,0.73171604,0.24919447,0.00012733723,0.00025656447,0.00015216378],"about_ca_topic_score_codex":0.00003559246,"about_ca_topic_score_gemma":0.000007614151,"teacher_disagreement_score":0.7305415,"about_ca_system_score_codex":0.000016472015,"about_ca_system_score_gemma":0.00013637399,"threshold_uncertainty_score":0.25383404},"labels":[],"label_agreement":null},{"id":"W3197251808","doi":"10.21203/rs.3.rs-875843/v1","title":"Comparison of radiomic pre-processing steps in the reproducible prediction of disease free survival across multi-scanners/centers","year":2021,"lang":"en","type":"preprint","venue":"Research Square","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre","funders":"European Commission","keywords":"Computer science; Artificial intelligence","score_opus":0.11157565153572958,"score_gpt":0.47727100530051964,"score_spread":0.36569535376479007,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3197251808","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9866073,0.0059905215,0.0020375666,0.0030809734,0.00040257254,0.0013981889,0.0002017095,0.00003707466,0.00024409412],"genre_scores_gemma":[0.997289,0.00047461942,0.0011724797,0.000028119,0.00029100841,0.00009319207,0.00046867336,0.000052267944,0.00013063115],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99401236,0.0012444087,0.0009563239,0.00095838483,0.0021715304,0.0006569834],"domain_scores_gemma":[0.99621135,0.00043496952,0.00035415022,0.002012086,0.0007120822,0.00027534354],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.007294456,0.00025474717,0.00092246337,0.00038598495,0.0001644222,0.000110774214,0.0008485464,0.00021973634,0.000035231104],"category_scores_gemma":[0.0061894804,0.00020030694,0.0002778985,0.0007518783,0.0006476645,0.00009170631,0.0010250568,0.0033361586,7.916838e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001051318,0.001850728,0.94064146,0.012845965,0.00014491151,0.00011917509,0.018831864,0.0063863704,0.004066447,0.000015047757,0.0014432927,0.012603408],"study_design_scores_gemma":[0.0027190817,0.00024939806,0.7582632,0.007822243,0.00009003644,0.0000076188308,0.014110501,0.21551104,0.00076476805,0.000057204936,0.0002462813,0.00015868653],"about_ca_topic_score_codex":0.0018599196,"about_ca_topic_score_gemma":0.0001099624,"teacher_disagreement_score":0.20912467,"about_ca_system_score_codex":0.00026173383,"about_ca_system_score_gemma":0.0009768256,"threshold_uncertainty_score":0.9989632},"labels":[],"label_agreement":null},{"id":"W3197838407","doi":"10.1038/s41379-021-00898-4","title":"Correction to: Quantitative comparison of PD-L1 IHC assays against NIST standard reference material 1934","year":2021,"lang":"en","type":"erratum","venue":"Modern Pathology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan; Saskatchewan Health Authority","funders":"","keywords":"NIST; Pathology; Medicine; Medical physics; Computer science; Information retrieval; Natural language processing","score_opus":0.03211153992684969,"score_gpt":0.35871918882398746,"score_spread":0.3266076488971378,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3197838407","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22894314,0.004673425,0.24862298,0.0055440534,0.23734424,0.0018528672,0.0013309604,0.00047686257,0.27121148],"genre_scores_gemma":[0.79609424,0.0013158317,0.026954975,0.0033735058,0.0039489344,0.00013727907,0.014017121,0.00038895677,0.15376915],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99701405,0.0003964637,0.0007944119,0.00077937654,0.00056078064,0.00045494732],"domain_scores_gemma":[0.99811614,0.00017354154,0.00049198314,0.00056824216,0.00042830303,0.00022178979],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006077589,0.00039627813,0.0016654987,0.0002792751,0.00012470671,0.000044186363,0.00022869307,0.0006165655,0.00019399534],"category_scores_gemma":[0.0017842016,0.00037525746,0.00017247042,0.00019277359,0.00027869767,0.000036012672,0.00019273706,0.0022335288,0.000029874009],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010437678,0.00024959978,0.0014885628,0.0005382494,0.00016050383,0.00083476823,0.0020017854,0.0004407133,0.026192546,0.0002182086,0.94126844,0.025562858],"study_design_scores_gemma":[0.003966274,0.005817186,0.010395446,0.005836213,0.00104554,0.0008964706,0.0014024299,0.1533511,0.005047645,0.0008126333,0.8097812,0.0016478861],"about_ca_topic_score_codex":0.00012913914,"about_ca_topic_score_gemma":0.000099649515,"teacher_disagreement_score":0.56715107,"about_ca_system_score_codex":0.00021926282,"about_ca_system_score_gemma":0.00059507595,"threshold_uncertainty_score":0.99986994},"labels":[],"label_agreement":null},{"id":"W3198829827","doi":"10.1038/s41598-021-96600-4","title":"Radiomics feature stability of open-source software evaluated on apparent diffusion coefficient maps in head and neck cancer","year":2021,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier de l’Université de Montréal","funders":"National Institute of Biomedical Imaging and Bioengineering; Peter MacCallum Foundation; Royal Australian and New Zealand College of Radiologists; Radiological Society of North America","keywords":"Radiomics; Feature (linguistics); Software; Effective diffusion coefficient; Open source software; Open source; Head and neck cancer; Computer science; Diffusion; Head and neck; Stability (learning theory); Cancer; Medicine; Artificial intelligence; Radiology; Machine learning; Surgery; Internal medicine; Physics; Magnetic resonance imaging","score_opus":0.022702651219568163,"score_gpt":0.3277586097178452,"score_spread":0.30505595849827705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3198829827","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9935555,0.0011678013,0.00035637186,0.0019394989,0.0020740516,0.0005673328,0.0000071562577,0.000031261654,0.00030101204],"genre_scores_gemma":[0.9961027,0.000066829554,0.0016333305,0.0002587874,0.000042191503,0.00002161819,0.00017858509,0.000023842813,0.0016721317],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9974853,0.00012298327,0.0005166354,0.0008775377,0.00070825435,0.0002892839],"domain_scores_gemma":[0.9984035,0.000076736666,0.00025240867,0.00077412574,0.00027067793,0.00022257722],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020051957,0.00015982613,0.00046013572,0.00014880595,0.00015313452,0.00015219848,0.00011769792,0.00008754198,0.00013210812],"category_scores_gemma":[0.0015298098,0.00012978217,0.00006818115,0.00066874723,0.00028807065,0.00006068864,0.00027216165,0.00041606431,0.0000010082097],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028333487,0.001541057,0.8180101,0.00055395963,0.000052352505,0.0014700128,0.0022457216,0.0034712753,0.0820455,0.000030758318,0.018840946,0.07145496],"study_design_scores_gemma":[0.010496355,0.00062453316,0.50962126,0.0069310633,0.0003528823,0.0024970172,0.0013743128,0.10768567,0.09625201,0.0016810519,0.2613564,0.0011274073],"about_ca_topic_score_codex":0.00026630424,"about_ca_topic_score_gemma":0.00010048064,"teacher_disagreement_score":0.30838883,"about_ca_system_score_codex":0.00018114605,"about_ca_system_score_gemma":0.0005375849,"threshold_uncertainty_score":0.5292363},"labels":[],"label_agreement":null},{"id":"W3199061724","doi":"10.1109/ius52206.2021.9593470","title":"An Ultra-Fast Method for Simulation of Realistic Ultrasound Images","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada; Nvidia","keywords":"Computer science; Convolutional neural network; Artificial intelligence; Field (mathematics); Segmentation; Dice; Sørensen–Dice coefficient; Deep learning; Pattern recognition (psychology); Image (mathematics); Fidelity; Computer vision; Image segmentation; Mathematics","score_opus":0.022698366004853532,"score_gpt":0.39296922521937033,"score_spread":0.3702708592145168,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3199061724","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015980111,0.00016795653,0.97758955,0.0006918498,0.00034284825,0.00058402354,0.00005579176,0.000083213265,0.004504654],"genre_scores_gemma":[0.6823968,0.00006287905,0.31505832,0.00038833835,0.00033925683,0.000024162444,0.0011469683,0.000043603253,0.0005396739],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983836,0.00013539327,0.0004881826,0.0004948583,0.00029078158,0.00020718988],"domain_scores_gemma":[0.99736655,0.0012576625,0.0002427087,0.00058017386,0.00037311515,0.0001797685],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008919725,0.00021860236,0.00067615847,0.00012401977,0.000045562705,0.00006107243,0.00014561905,0.0002265004,0.00020861227],"category_scores_gemma":[0.0027948902,0.00018799753,0.00023691935,0.00008331971,0.00007651731,0.00004656443,0.000028916997,0.0006011813,6.6315073e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022939811,0.0005471773,0.0034386977,0.004164726,0.0005006355,0.000039074064,0.0011975146,0.59198964,0.3300766,0.0007431308,0.001389819,0.065683566],"study_design_scores_gemma":[0.0014338889,0.00026031802,0.005193373,0.00076630217,0.0008721006,0.00007230008,0.00055037317,0.9629505,0.024958547,0.0018774199,0.0007042462,0.00036060697],"about_ca_topic_score_codex":0.0004884521,"about_ca_topic_score_gemma":0.0000068581285,"teacher_disagreement_score":0.6664167,"about_ca_system_score_codex":0.00005138126,"about_ca_system_score_gemma":0.00021475927,"threshold_uncertainty_score":0.76663166},"labels":[],"label_agreement":null},{"id":"W3199152014","doi":"10.1016/j.cpet.2021.06.001","title":"Toward High-Throughput Artificial Intelligence-Based Segmentation in Oncological PET Imaging","year":2021,"lang":"en","type":"review","venue":"PET Clinics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":44,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Simon Fraser University","keywords":"Segmentation; Artificial intelligence; Convolutional neural network; Workflow; Medical imaging; Computer science; Deep learning; Image segmentation; Pattern recognition (psychology); Machine learning; Medicine","score_opus":0.13053603802637523,"score_gpt":0.456635040400157,"score_spread":0.32609900237378175,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3199152014","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00018708812,0.9773055,0.016166942,0.002953857,0.0018759028,0.0009132341,0.000024953133,0.00011877891,0.00045379542],"genre_scores_gemma":[0.0003697891,0.9690311,0.026595527,0.0015531593,0.000980546,0.00009203994,0.0011983751,0.00008144876,0.00009802179],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9959293,0.00051308534,0.001758082,0.0008134107,0.0005077537,0.00047837835],"domain_scores_gemma":[0.9972779,0.0014017085,0.0005389656,0.00044320017,0.00011089394,0.00022730563],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0017054519,0.00045382886,0.002420967,0.0002916003,0.00006900043,0.00009462171,0.00026192606,0.00018322485,0.0005358894],"category_scores_gemma":[0.002825095,0.00037328523,0.0006425488,0.00057212857,0.00019175424,0.00005675778,0.00013070485,0.0022242763,0.00012449281],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017970882,0.00033258178,0.00012431595,0.0037724408,0.000057147096,0.0036728408,0.00005072101,0.00006326428,3.9431043e-7,0.0005090659,0.0003859683,0.9910133],"study_design_scores_gemma":[0.000589265,0.00022953223,0.000027764745,0.01812723,0.0013315275,0.0008856954,0.00022592298,0.023098066,0.0000025055215,0.0009973098,0.953861,0.0006241784],"about_ca_topic_score_codex":0.000058058526,"about_ca_topic_score_gemma":0.000008760831,"teacher_disagreement_score":0.9903891,"about_ca_system_score_codex":0.0004606553,"about_ca_system_score_gemma":0.001340432,"threshold_uncertainty_score":0.9998719},"labels":[],"label_agreement":null},{"id":"W3199368218","doi":"10.1016/j.cpet.2021.06.007","title":"Radiomics in PET Imaging","year":2021,"lang":"en","type":"review","venue":"PET Clinics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":88,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Radiomics; Medicine; Medical physics; Pipeline (software); Harmonization; Checklist; Pet imaging; Artificial intelligence; Nuclear medicine; Positron emission tomography; Computer science; Radiology; Psychology","score_opus":0.04016412162525951,"score_gpt":0.4178017834804213,"score_spread":0.3776376618551618,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3199368218","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00003746918,0.99464613,0.00017162849,0.0006936281,0.0012390963,0.00043715184,0.000015425188,0.00007969088,0.0026798062],"genre_scores_gemma":[0.0000066906136,0.99027133,0.0057553453,0.0010923822,0.0008681055,0.000033464406,0.0005086691,0.00014975839,0.001314279],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9967097,0.0002828546,0.0014022784,0.0007203345,0.00036518113,0.0005196716],"domain_scores_gemma":[0.9975521,0.00089731923,0.00042804133,0.0007587397,0.00007555259,0.0002882291],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0015743071,0.00046654322,0.0031633463,0.00037708072,0.000051845527,0.00007223906,0.00030921193,0.00013064283,0.00020915829],"category_scores_gemma":[0.0029434438,0.00040600795,0.00088949635,0.00055338826,0.00012487358,0.000050333132,0.00019032728,0.0027784852,0.00011326715],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003615382,0.00011425177,0.00045900798,0.0072628874,0.00009814287,0.006580946,0.00003036554,0.000002270811,5.811111e-8,0.00017182236,0.0030315698,0.9822451],"study_design_scores_gemma":[0.0007170672,0.000020869598,0.000016654272,0.023340037,0.00086284534,0.0053913556,0.000025793981,0.003748841,2.1103231e-8,0.00004899098,0.96548474,0.0003427978],"about_ca_topic_score_codex":0.000022861324,"about_ca_topic_score_gemma":0.0000035018281,"teacher_disagreement_score":0.98190224,"about_ca_system_score_codex":0.00025062828,"about_ca_system_score_gemma":0.0011291346,"threshold_uncertainty_score":0.9998392},"labels":[],"label_agreement":null},{"id":"W3199730712","doi":"10.1136/gutjnl-2020-bsgcampus.201","title":"P126 Phenotypic characterisation of suspected small bowel Crohn’s disease with natural language processing of MRE reports","year":2021,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Crohn's disease; Computer science; Crohn disease; Disease; Medicine; Natural language processing; Gastroenterology; Pathology","score_opus":0.0059366000086024055,"score_gpt":0.25417129566350394,"score_spread":0.24823469565490153,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3199730712","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99473023,0.0012035874,0.0014641297,0.0011134498,0.00007688703,0.00013633785,0.0000014065436,0.000048187336,0.0012258001],"genre_scores_gemma":[0.99337566,0.00001108004,0.004553611,0.00028401605,0.0000891217,0.0000035916908,0.000121028505,0.000018883764,0.0015430155],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99908185,0.000027612174,0.0003064436,0.00020755414,0.00024149027,0.00013504984],"domain_scores_gemma":[0.99916,0.000025023273,0.00022659289,0.00022838311,0.00024067149,0.00011932127],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013251956,0.000098082965,0.00025390225,0.00006248233,0.000029284933,0.000012879735,0.00003436127,0.000029796023,0.00015376623],"category_scores_gemma":[0.00045678052,0.00007022705,0.00005178845,0.00018502562,0.000077107135,0.00005946271,0.00002395737,0.00020867374,5.1729245e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011624552,0.0007848928,0.5433766,0.003319875,0.0002294048,0.010170427,0.0044366284,0.000052177635,0.2774782,0.00026340995,0.00027176965,0.15845415],"study_design_scores_gemma":[0.0008724314,0.00004612318,0.97556674,0.00062963733,0.00016298822,0.00025968996,0.00059478055,0.01153737,0.010074467,0.00003101257,0.00011086805,0.00011390512],"about_ca_topic_score_codex":0.000066970286,"about_ca_topic_score_gemma":0.000014657284,"teacher_disagreement_score":0.4321901,"about_ca_system_score_codex":0.00002444849,"about_ca_system_score_gemma":0.00027486455,"threshold_uncertainty_score":0.2863776},"labels":[],"label_agreement":null},{"id":"W3200071490","doi":"10.1038/s41598-021-98445-3","title":"Author Correction: Radiomics feature stability of open-source software evaluated on apparent diffusion coefficient maps in head and neck cancer","year":2021,"lang":"en","type":"erratum","venue":"Scientific Reports","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier de l’Université de Montréal","funders":"","keywords":"Radiomics; Feature (linguistics); Diffusion; Software; Head and neck; Head and neck cancer; Open source software; Stability (learning theory); Head (geology); Effective diffusion coefficient; Open source; Computer science; Cancer; Medicine; Radiology; Artificial intelligence; Physics; Geology; Internal medicine; Surgery; Machine learning; Geomorphology; Philosophy","score_opus":0.02500301590032127,"score_gpt":0.33472695808927566,"score_spread":0.3097239421889544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3200071490","genre_codex":"empirical","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6916547,0.010525565,0.00072181196,0.005328776,0.28485417,0.0034294194,0.00006652841,0.00016412543,0.0032549514],"genre_scores_gemma":[0.13788457,0.0010270231,0.0027396537,0.00090144615,0.0019607586,0.00032982414,0.009777053,0.00035052272,0.8450292],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99477553,0.0002685472,0.0010700761,0.0018695717,0.0015191432,0.0004971394],"domain_scores_gemma":[0.9965655,0.00011832447,0.00090928137,0.0014539555,0.0005645922,0.0003882996],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0034634566,0.0004422197,0.0012549849,0.0004590832,0.00031271696,0.00037525146,0.0002704242,0.0005051434,0.0002822537],"category_scores_gemma":[0.0030849322,0.00037154858,0.00018629318,0.0011483107,0.0005296355,0.00007546332,0.0005059817,0.002200663,0.0000014375568],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016148244,0.000664156,0.02836651,0.0007709804,0.00005943288,0.0007173594,0.00088227785,0.00082166254,0.00088900654,0.0000016996203,0.9405597,0.026105773],"study_design_scores_gemma":[0.0014759477,0.00024214985,0.01646282,0.008138186,0.00024717682,0.0008440446,0.00030351517,0.034200557,0.0007043924,0.00007422807,0.9368077,0.0004993115],"about_ca_topic_score_codex":0.00083229,"about_ca_topic_score_gemma":0.0003114734,"teacher_disagreement_score":0.8417742,"about_ca_system_score_codex":0.00063075824,"about_ca_system_score_gemma":0.002000031,"threshold_uncertainty_score":0.99987364},"labels":[],"label_agreement":null},{"id":"W3200719698","doi":"10.1016/j.cpet.2021.07.003","title":"PET and AI Trajectories Finally Coming into Alignment","year":2021,"lang":"en","type":"editorial","venue":"PET Clinics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Variety (cybernetics); Artificial intelligence; Deep learning; Convolutional neural network; General partnership; Data science; Computer science; Medicine","score_opus":0.010192912866891318,"score_gpt":0.3443031422175338,"score_spread":0.33411022935064244,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3200719698","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0115254205,0.0033330563,0.0007664469,0.0072273565,0.9756209,0.00031453976,0.000056207882,0.00012783048,0.001028238],"genre_scores_gemma":[0.0026696352,0.0073313937,0.0117145,0.0022531843,0.9684207,0.000028216135,0.0013307258,0.0001467971,0.0061048805],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99722075,0.00012547313,0.00071781845,0.0006522044,0.0009212353,0.0003624989],"domain_scores_gemma":[0.9968196,0.0018395231,0.00027121435,0.00047462972,0.00027551275,0.00031948785],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0011776681,0.00036934472,0.0010350398,0.00010146621,0.00015388663,0.0001366241,0.00018389196,0.00030544685,0.000119377684],"category_scores_gemma":[0.008322923,0.00034013216,0.0002110771,0.000115092946,0.0002160961,0.00005046119,0.00020711262,0.002706567,0.000012776572],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000084345906,0.00010289803,0.001081791,0.0007680767,0.00020955135,0.0015289896,0.0004468194,0.000004383373,0.000027178887,0.00006736322,0.986622,0.009056618],"study_design_scores_gemma":[0.0016396921,0.0002788191,0.00014968535,0.0009388319,0.00047870833,0.00013194776,0.00015094005,0.0018567808,0.000006369206,0.00037671698,0.9936692,0.00032228415],"about_ca_topic_score_codex":0.00013140096,"about_ca_topic_score_gemma":0.000031053376,"teacher_disagreement_score":0.010948054,"about_ca_system_score_codex":0.00013256512,"about_ca_system_score_gemma":0.0009438644,"threshold_uncertainty_score":0.99990505},"labels":[],"label_agreement":null},{"id":"W3201496287","doi":"10.1007/s00234-021-02813-9","title":"Radiomics, machine learning, and artificial intelligence—what the neuroradiologist needs to know","year":2021,"lang":"en","type":"review","venue":"Neuroradiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":161,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"SickKids Foundation; Hospital for Sick Children; University of Toronto","funders":"","keywords":"Neuroradiologist; Artificial intelligence; Neuroradiology; Machine learning; Overfitting; Computer science; Convolutional neural network; Deep learning; Artificial neural network; Medicine; Neurology; Magnetic resonance imaging; Radiology","score_opus":0.04842318495692746,"score_gpt":0.36467878984079,"score_spread":0.3162556048838625,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3201496287","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001677568,0.9854315,0.0008569966,0.009653998,0.0023420358,0.0011146844,0.000012453036,0.000156953,0.00026364863],"genre_scores_gemma":[0.00011747587,0.99263966,0.0005082331,0.0038522223,0.0014211017,0.00010584935,0.0002627282,0.00017597164,0.0009167639],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99495155,0.001617884,0.0011715287,0.001127967,0.00028975846,0.00084131205],"domain_scores_gemma":[0.99656266,0.0016228564,0.00041495767,0.0008202694,0.00010305029,0.00047620284],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0010463396,0.00082742714,0.003424508,0.00063261663,0.00035730738,0.00027761428,0.0005812936,0.00058156735,0.000175205],"category_scores_gemma":[0.0034321828,0.00054433505,0.00063566543,0.0010679552,0.0008410088,0.00008036228,0.00046739058,0.0040627094,0.00012083453],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023809895,0.000052745265,0.00007563337,0.0011844723,0.00017436217,0.00053536426,0.00014192624,0.00002267827,0.000009423991,0.0024769534,0.002245322,0.9930573],"study_design_scores_gemma":[0.00011077307,0.00063596637,0.000008545939,0.0022993523,0.00096589583,0.009366854,0.000105022584,0.0010734893,0.000001914921,0.00009663435,0.98490834,0.00042718006],"about_ca_topic_score_codex":0.000032996628,"about_ca_topic_score_gemma":0.000005015701,"teacher_disagreement_score":0.9926301,"about_ca_system_score_codex":0.00011083523,"about_ca_system_score_gemma":0.00037460975,"threshold_uncertainty_score":0.99970084},"labels":[],"label_agreement":null},{"id":"W3201539940","doi":"10.1088/1361-6560/ac287d","title":"Multi-level multi-modality (PET and CT) fusion radiomics: prognostic modeling for non-small cell lung carcinoma","year":2021,"lang":"en","type":"article","venue":"Physics in Medicine and Biology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":73,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"BC Cancer Foundation; Shahid Beheshti University of Medical Sciences; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Radiomics; Modality (human–computer interaction); Medicine; Small Cell Lung Carcinoma; Lung; Nuclear medicine; Radiology; Lung cancer; Oncology; Computer science; Small-cell carcinoma; Artificial intelligence; Internal medicine","score_opus":0.15061062848207787,"score_gpt":0.37795876525691685,"score_spread":0.22734813677483898,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3201539940","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.80057037,0.0020990248,0.1934963,0.0030643507,0.00021215649,0.00046721345,0.000012332575,0.000019094146,0.00005917197],"genre_scores_gemma":[0.95212036,0.00097290025,0.04476899,0.0013190482,0.00048716503,0.00004162971,0.00018802992,0.000027874003,0.000073990224],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985195,0.00008451367,0.00039523415,0.0005471344,0.000077771634,0.0003758486],"domain_scores_gemma":[0.99902844,0.00034848627,0.00009160504,0.00021171525,0.00012964562,0.00019007787],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00058142096,0.00022936033,0.0006476727,0.00008901305,0.000106783766,0.000010416109,0.000076689365,0.0000743799,0.0000052762252],"category_scores_gemma":[0.0006197607,0.00017746216,0.000058076526,0.0001489848,0.00022888902,0.00003475985,0.00011331679,0.00048457517,5.3417335e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023876864,0.00087364216,0.6769483,0.0026094227,0.00013571957,0.00043377306,0.002834862,0.0005664112,0.23571159,0.000875795,0.00032553176,0.078446165],"study_design_scores_gemma":[0.0082796775,0.00022646929,0.01640819,0.00034097434,0.00017387346,0.00018680301,0.0005181034,0.9719771,0.00059050915,0.0009159087,0.00018345941,0.00019889015],"about_ca_topic_score_codex":0.0002752255,"about_ca_topic_score_gemma":0.00002752206,"teacher_disagreement_score":0.97141075,"about_ca_system_score_codex":0.000039768503,"about_ca_system_score_gemma":0.00012266227,"threshold_uncertainty_score":0.7236697},"labels":[],"label_agreement":null},{"id":"W3201582508","doi":"10.21203/rs.3.rs-923769/v1","title":"Radiomics Derived Brain Age Predicts Functional Outcome After Acute Ischemic Stroke","year":2021,"lang":"en","type":"preprint","venue":"Research Square","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Radiomics; Medicine; Stroke (engine); Ischemic stroke; Outcome (game theory); Acute stroke; Cardiology; Internal medicine; Neuroscience; Psychology; Ischemia; Radiology; Economics; Physics","score_opus":0.04597003529257114,"score_gpt":0.386593345116113,"score_spread":0.34062330982354183,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3201582508","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97057253,0.0023683428,0.005150453,0.015332965,0.0010130662,0.0012172719,0.00018377199,0.00020226714,0.003959325],"genre_scores_gemma":[0.9747402,0.00059265766,0.0049806656,0.0013940784,0.0015799768,0.00039724153,0.0021908064,0.00016284845,0.013961496],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99399424,0.0005182254,0.00071116164,0.0011980487,0.00244318,0.0011351487],"domain_scores_gemma":[0.99643576,0.0006346581,0.00014022928,0.0012458793,0.0006807546,0.0008627115],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0022940845,0.00047733638,0.00097380654,0.00065500673,0.00022274077,0.00035407383,0.00044147234,0.0006980642,0.0013658612],"category_scores_gemma":[0.0032329804,0.00043814527,0.0005849453,0.000384946,0.0005125127,0.000103237326,0.0016903528,0.007590066,0.0000907963],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0037145724,0.0016929412,0.5010033,0.015092804,0.0050224727,0.04179098,0.0037029884,0.0009262559,0.19572833,0.00014669578,0.19957148,0.03160715],"study_design_scores_gemma":[0.012302111,0.0010026674,0.7864519,0.007670392,0.0012151551,0.0017556504,0.0018098427,0.0430818,0.0063116574,0.00038291892,0.13580517,0.002210767],"about_ca_topic_score_codex":0.00014487778,"about_ca_topic_score_gemma":0.000015595433,"teacher_disagreement_score":0.28544855,"about_ca_system_score_codex":0.00065392244,"about_ca_system_score_gemma":0.0013258768,"threshold_uncertainty_score":0.99980706},"labels":[],"label_agreement":null},{"id":"W3202543463","doi":"10.2139/ssrn.3900665","title":"A Deep Learning System for Classifying T Stage and Predicting Prognosis of Colorectal Cancer via Preoperative Computed Tomography Images","year":2021,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computed tomography; Colorectal cancer; Stage (stratigraphy); Medicine; Cancer; Radiology; Artificial intelligence; Deep learning; Internal medicine; Computer science","score_opus":0.006757523644686049,"score_gpt":0.27017351265639916,"score_spread":0.2634159890117131,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3202543463","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8432756,0.0109341685,0.1443906,0.00067795254,0.00016188255,0.00036506972,0.0000037584648,0.00005870309,0.00013224698],"genre_scores_gemma":[0.9940582,0.0012110583,0.0042025973,0.000038770715,0.00023459109,0.000038209466,0.000012131916,0.00003682652,0.00016764375],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979014,0.00015494334,0.00039283186,0.00026637473,0.00025905826,0.0010254069],"domain_scores_gemma":[0.99896944,0.00018592198,0.00028373298,0.0000619251,0.0003568429,0.00014214512],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011588421,0.00016611398,0.00043166563,0.00014266156,0.0003229716,0.00005797664,0.00007305516,0.00007630174,0.000007857232],"category_scores_gemma":[0.0002955058,0.00014158305,0.00015319313,0.00026299758,0.000098438635,0.00010656414,0.000044392214,0.0018745213,1.5458347e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035151283,0.00015359644,0.83998156,0.0010542732,0.0016737527,0.00005553083,0.0015485071,0.0019280004,0.06505342,0.0024642246,0.000016210226,0.08571939],"study_design_scores_gemma":[0.00969223,0.002762185,0.074630976,0.0027595689,0.0012835416,0.005328535,0.022252996,0.8471309,0.032373346,0.00077458436,0.00042447975,0.0005866767],"about_ca_topic_score_codex":0.000059555015,"about_ca_topic_score_gemma":0.00006735241,"teacher_disagreement_score":0.84520286,"about_ca_system_score_codex":0.0003619464,"about_ca_system_score_gemma":0.0010048624,"threshold_uncertainty_score":0.8143966},"labels":[],"label_agreement":null},{"id":"W3204145332","doi":"10.18280/ts.380405","title":"Improving Parotid Gland Tumor Segmentation and Classification Using Geometric Active Contour Model and Deep Neural Network Framework","year":2021,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Parotid gland; Segmentation; Artificial intelligence; Image segmentation; Artificial neural network; Pattern recognition (psychology); Process (computing); Medical diagnosis; Image (mathematics); Variety (cybernetics); Magnetic resonance imaging; Ground truth; Machine learning; Pathology; Radiology; Medicine","score_opus":0.023653131025738062,"score_gpt":0.28855520848624044,"score_spread":0.26490207746050237,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3204145332","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7485183,0.00053485227,0.25004017,0.0005370174,0.000068264606,0.00022386832,0.0000027378087,0.00002477738,0.00005003255],"genre_scores_gemma":[0.9587167,0.000058786267,0.0397667,0.0010249431,0.00034159914,0.000013608243,0.00003912287,0.00001969314,0.00001883504],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988698,0.00006800588,0.00025288234,0.0003118787,0.00024861936,0.00024884756],"domain_scores_gemma":[0.99937075,0.00015222997,0.00013515289,0.00009059716,0.00007981539,0.00017142849],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028528107,0.00014228407,0.00023283073,0.00009138292,0.00017536836,0.000085300366,0.00003185655,0.00005405765,0.000053099026],"category_scores_gemma":[0.00015459572,0.00013177133,0.000036279223,0.00024397075,0.0000661209,0.0001352622,0.000037956048,0.00032065235,5.7250617e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005881881,0.00031963157,0.23168334,0.00049471925,0.00033498803,0.00022951495,0.0022538207,0.06834166,0.19396561,0.0011200792,0.00016302335,0.50050545],"study_design_scores_gemma":[0.0013714182,0.00008380895,0.07663423,0.00008389153,0.0001646664,0.00013195604,0.00035669323,0.9202957,0.00045504924,0.00027956848,0.000020283187,0.00012270255],"about_ca_topic_score_codex":0.000026863878,"about_ca_topic_score_gemma":0.000003414727,"teacher_disagreement_score":0.8519541,"about_ca_system_score_codex":0.000072077535,"about_ca_system_score_gemma":0.000056200082,"threshold_uncertainty_score":0.5373479},"labels":[],"label_agreement":null},{"id":"W3204239919","doi":"10.1016/j.annonc.2021.08.1957","title":"1357P A deep radiomics approach to assess PD-L1 expression and clinical outcomes in patients with advanced non-small cell lung cancer treated with immune checkpoint inhibitors: A multicentric study","year":2021,"lang":"en","type":"article","venue":"Annals of Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Jewish General Hospital; McGill University; Centre Hospitalier de l’Université de Montréal","funders":"","keywords":"Medicine; Radiomics; Lung cancer; Oncology; PD-L1; Internal medicine; Cancer; Immune checkpoint; Immune system; Immunotherapy; Immunology; Radiology","score_opus":0.031731320779081355,"score_gpt":0.3765750969259539,"score_spread":0.34484377614687256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3204239919","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99658674,0.00036249516,0.0006632056,0.00063473225,0.000095135816,0.0013064209,0.0000034572683,0.000016905915,0.00033089845],"genre_scores_gemma":[0.986324,0.00022002934,0.0126017565,0.0005860103,0.000048705588,0.00009414917,0.000025863757,0.000036927875,0.00006252043],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99784106,0.00026724942,0.00074375677,0.00052022515,0.0002630777,0.00036462652],"domain_scores_gemma":[0.9984473,0.0003039483,0.0003326205,0.00030383313,0.00034318,0.0002691008],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005892624,0.00023188368,0.0010680637,0.00018980354,0.000045510023,0.000013485163,0.00010797608,0.00013944646,0.0000077864925],"category_scores_gemma":[0.000428293,0.000157398,0.00008132831,0.0003883866,0.000098201184,0.00006787003,0.00012355579,0.0005519509,4.6683678e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021298388,0.0070144343,0.9717836,0.00013590121,0.00020086957,0.00013861059,0.0012932935,0.00054887275,0.0009428363,5.2885173e-7,0.000034818997,0.015776426],"study_design_scores_gemma":[0.021490352,0.004666735,0.96488136,0.00031419512,0.00021849097,0.0000093285835,0.0011512686,0.0052361293,0.0017073012,6.674451e-7,0.00012919768,0.00019494531],"about_ca_topic_score_codex":0.0002469696,"about_ca_topic_score_gemma":0.000059510887,"teacher_disagreement_score":0.019360514,"about_ca_system_score_codex":0.00008419527,"about_ca_system_score_gemma":0.00029315532,"threshold_uncertainty_score":0.64185035},"labels":[],"label_agreement":null},{"id":"W3204589419","doi":"10.5489/cuaj.7467","title":"Predictive radiomics signature for treatment response to nivolumab in patients with advanced renal cell carcinoma","year":2021,"lang":"en","type":"article","venue":"Canadian Urological Association Journal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Toronto; Princess Margaret Cancer Centre","funders":"Astellas Pharma","keywords":"Medicine; Nivolumab; Renal cell carcinoma; Radiomics; Response Evaluation Criteria in Solid Tumors; Internal medicine; Radiology; Oncology; Nephrectomy; Progressive disease; Disease; Immunotherapy; Cancer; Kidney","score_opus":0.003997884513563394,"score_gpt":0.21508076544041432,"score_spread":0.21108288092685093,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3204589419","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9782064,0.00013086111,0.00069170044,0.020118877,0.00016215934,0.00038928687,0.00007859503,0.00000966917,0.00021244658],"genre_scores_gemma":[0.99220854,0.000008492621,0.0028019715,0.003787862,0.00017572184,0.000022481632,0.00009972785,0.000018281711,0.00087694364],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99856555,0.00020150344,0.00025110552,0.0002550027,0.00027152515,0.00045530128],"domain_scores_gemma":[0.998353,0.00026374776,0.0001359804,0.00009985234,0.00035948685,0.00078790763],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004762155,0.00013861567,0.00030814984,0.00018680585,0.0001545961,0.00004636344,0.00006320154,0.00017240767,0.000081037026],"category_scores_gemma":[0.0015861213,0.00010605579,0.0000914939,0.00024824837,0.000017713985,0.000054014534,0.000008226369,0.00044424523,0.000003692562],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0046703923,0.00021502847,0.9773377,0.0000049975547,0.0000672798,0.00032856935,0.00036358525,0.0026269518,0.0005814796,0.0000068565664,0.0039504203,0.009846727],"study_design_scores_gemma":[0.0093994215,0.003692233,0.9490338,0.000022929416,0.0000695704,0.000039065846,0.00007252371,0.0008204468,0.0001489288,0.000048611797,0.03652263,0.0001298313],"about_ca_topic_score_codex":0.00013370832,"about_ca_topic_score_gemma":0.000305083,"teacher_disagreement_score":0.03257221,"about_ca_system_score_codex":0.002962525,"about_ca_system_score_gemma":0.0012374923,"threshold_uncertainty_score":0.77469003},"labels":[],"label_agreement":null},{"id":"W3206015921","doi":"10.48550/arxiv.2110.10332","title":"AI-Based Detection, Classification and Prediction/Prognosis in Medical Imaging: Towards Radiophenomics","year":2021,"lang":"en","type":"preprint","venue":"PubMed","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency","funders":"","keywords":"Computer science; Artificial intelligence; Radiomics; Workflow; Medical imaging; Identification (biology); Field (mathematics); Contextual image classification; Machine learning; Deep learning; Feature extraction; Applications of artificial intelligence; Pattern recognition (psychology); Image (mathematics); Database","score_opus":0.019021042745852167,"score_gpt":0.2699751022935993,"score_spread":0.25095405954774713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3206015921","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8564784,0.004069183,0.033880945,0.097928405,0.0029254628,0.0025914293,0.000026274825,0.00040268243,0.001697211],"genre_scores_gemma":[0.9915778,0.0006563339,0.0009325776,0.0036397083,0.000692264,0.0021393024,0.00023705067,0.00006588996,0.000059069953],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9970567,0.00017489119,0.0006985123,0.0008564672,0.0007413011,0.00047213005],"domain_scores_gemma":[0.9984958,0.000105634266,0.00019715488,0.0004272841,0.00017702475,0.00059708196],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.001521475,0.00031736688,0.00062205864,0.0004268007,0.00008254375,0.0001730415,0.00019440125,0.0004379558,0.000049427872],"category_scores_gemma":[0.0021600674,0.0003173477,0.0001557822,0.00029155487,0.00024762904,0.000079086996,0.00024076387,0.0023710844,0.0000011840095],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000082755425,0.00022656436,0.23909056,0.0004873243,0.00008618474,0.0002019026,0.00013239366,0.00014448224,0.00006368381,0.000021367874,0.00046468747,0.7589981],"study_design_scores_gemma":[0.0015607269,0.000011131046,0.7056686,0.00024122917,0.0001443467,0.00017519116,0.00007474538,0.2889739,0.00017901638,0.00010945849,0.0026637593,0.00019788671],"about_ca_topic_score_codex":0.00023364549,"about_ca_topic_score_gemma":0.000027657068,"teacher_disagreement_score":0.7588002,"about_ca_system_score_codex":0.0004413428,"about_ca_system_score_gemma":0.00064410013,"threshold_uncertainty_score":0.9999305},"labels":[],"label_agreement":null},{"id":"W3208793479","doi":"10.1093/neuonc/noab249","title":"The data behind the image—Deep learning and its potential impact in neuro-oncological imaging","year":2021,"lang":"en","type":"letter","venue":"Neuro-Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mental Health Research Canada; Hospital for Sick Children; University of Toronto","funders":"","keywords":"Deep learning; Artificial intelligence; Computer science; Data science","score_opus":0.02253871348312259,"score_gpt":0.34445580765706363,"score_spread":0.32191709417394104,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3208793479","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017442571,0.0060721436,0.00018439855,0.97078097,0.0022166662,0.0008945987,0.000024117937,0.00011342121,0.0022710892],"genre_scores_gemma":[0.074516386,0.009648745,0.0006091896,0.89935803,0.013458518,0.00011015532,0.0012754296,0.00033343642,0.0006901094],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9932318,0.0024822918,0.0008749947,0.0014168749,0.0007394019,0.0012546751],"domain_scores_gemma":[0.99198353,0.0059474,0.00051179185,0.0011327782,0.00016927505,0.00025524007],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0021537188,0.00062990387,0.0011961183,0.00021620521,0.0006864559,0.0003554401,0.0012680267,0.0007478135,0.00025689186],"category_scores_gemma":[0.009365461,0.00036412344,0.00025995463,0.0002946285,0.00082630315,0.00017949588,0.0019131933,0.015324366,0.000036421727],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027888457,0.00014906119,0.0047675543,0.0001380755,0.00019801641,0.05711928,0.00041656915,0.0000903451,0.027587667,0.000012943706,0.7461228,0.16311882],"study_design_scores_gemma":[0.0018140187,0.00048120823,0.0024570513,0.00007217691,0.00035482773,0.009300169,0.0001913734,0.07071426,0.000021499323,0.00005085688,0.9142346,0.0003079569],"about_ca_topic_score_codex":0.00009772302,"about_ca_topic_score_gemma":0.000026285705,"teacher_disagreement_score":0.16811183,"about_ca_system_score_codex":0.00030146205,"about_ca_system_score_gemma":0.00078174094,"threshold_uncertainty_score":0.9998811},"labels":[],"label_agreement":null},{"id":"W3208806084","doi":"10.1038/s41598-021-01024-9","title":"A priori prediction of local failure in brain metastasis after hypo-fractionated stereotactic radiotherapy using quantitative MRI and machine learning","year":2021,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; University of Toronto; York University; Sunnybrook Health Science Centre","funders":"Natural Sciences and Engineering Research Council of Canada; Terry Fox Foundation; Lotte and John Hecht Memorial Foundation","keywords":"Medicine; Radiomics; Fluid-attenuated inversion recovery; Radiation therapy; Magnetic resonance imaging; Feature selection; Biomarker; Feature (linguistics); Artificial intelligence; Machine learning; Radiology; Computer science","score_opus":0.019572903431696796,"score_gpt":0.298569265034564,"score_spread":0.27899636160286717,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3208806084","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9674285,0.0020008541,0.027788445,0.0015073217,0.00095895666,0.00022443205,0.0000040463033,0.000033721153,0.00005371601],"genre_scores_gemma":[0.98230624,0.000050096078,0.016837057,0.000100321806,0.000035133526,0.000007487643,0.00006725347,0.000024772282,0.00057161937],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99790275,0.00021170602,0.0005752647,0.0005938779,0.00048647381,0.00022994884],"domain_scores_gemma":[0.9989322,0.00012216679,0.0003007392,0.00029619245,0.00021569066,0.00013305015],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016652246,0.00014557788,0.0003823652,0.00034151826,0.00011983978,0.00008727562,0.000030364783,0.00007398009,0.00016482161],"category_scores_gemma":[0.00085447787,0.00013077875,0.000083061495,0.00072210084,0.00031179722,0.00021656326,0.000040754054,0.000499919,6.854625e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042285357,0.0005101355,0.5126551,0.0005398727,0.00048008503,0.007956099,0.0040490455,0.0055709756,0.4270574,0.00006902306,0.00082231784,0.0398671],"study_design_scores_gemma":[0.0039880467,0.00044298804,0.17636423,0.0013801809,0.0004463434,0.015038276,0.0030568289,0.71822584,0.01899759,0.0008504072,0.06069171,0.0005175447],"about_ca_topic_score_codex":0.0002277968,"about_ca_topic_score_gemma":0.00006300942,"teacher_disagreement_score":0.7126549,"about_ca_system_score_codex":0.00012225038,"about_ca_system_score_gemma":0.00026587897,"threshold_uncertainty_score":0.5333003},"labels":[],"label_agreement":null},{"id":"W3208845509","doi":"10.5281/zenodo.4573155","title":"HEad and neCK TumOR segmentation and outcome prediction in PET/CT images","year":2021,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Segmentation; Head and neck; Artificial intelligence; Image segmentation; Computer vision; Medicine; Computer science; Radiology; Surgery","score_opus":0.02290328021342394,"score_gpt":0.2962883061180544,"score_spread":0.2733850259046305,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3208845509","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98347497,0.00022830021,0.0006545268,0.0028003452,0.000056645145,0.00021868123,0.000029237053,0.00018896199,0.012348306],"genre_scores_gemma":[0.99586177,0.00019204528,0.0015249201,0.0004772384,0.00007306693,4.4758735e-8,0.0005143444,0.00033410077,0.001022495],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99904126,0.0001349849,0.00019575942,0.00026846872,0.00019052843,0.0001689865],"domain_scores_gemma":[0.9995344,0.000019000943,0.000040869687,0.00013736113,0.00012935174,0.0001389686],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00039966035,0.00007925131,0.0001339721,0.00013071157,0.00040993086,0.00023279178,0.00007115242,0.000007408853,0.0014110956],"category_scores_gemma":[0.0008223267,0.00007986599,0.000017365854,0.00022371172,0.000097106225,0.00013761989,0.00024670808,0.00027639596,0.00014478361],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045585926,0.0009495084,0.1053509,0.0016680001,0.00019423183,0.006405867,0.0035192491,0.00015939173,0.13357915,0.0027482926,0.08944777,0.6555218],"study_design_scores_gemma":[0.006024538,0.00056079583,0.42880815,0.00034630383,0.000078529316,0.016632691,0.0016538915,0.013347197,0.0020735853,0.00024647434,0.5299193,0.00030850118],"about_ca_topic_score_codex":0.00002362491,"about_ca_topic_score_gemma":3.755687e-7,"teacher_disagreement_score":0.6552133,"about_ca_system_score_codex":0.000065811764,"about_ca_system_score_gemma":0.000004072738,"threshold_uncertainty_score":0.99950176},"labels":[],"label_agreement":null},{"id":"W3209261377","doi":"10.2967/jnumed.121.262567","title":"Nuclear Medicine and Artificial Intelligence: Best Practices for Algorithm Development","year":2021,"lang":"en","type":"article","venue":"Journal of Nuclear Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":92,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Institute on Aging","keywords":"Best practice; Task (project management); Computer science; Artificial intelligence; Field (mathematics); Algorithm; Data science; Engineering; Political science; Mathematics; Systems engineering","score_opus":0.08673199332690784,"score_gpt":0.3928749737902669,"score_spread":0.3061429804633591,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3209261377","genre_codex":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20912312,0.014921479,0.038555767,0.72218496,0.0046544624,0.00084603985,0.0000043707328,0.000107396336,0.009602413],"genre_scores_gemma":[0.29533765,0.011757218,0.62046486,0.049378805,0.019979937,0.000008377875,0.000049805556,0.00039430283,0.002629053],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99760824,0.0000760875,0.0010422515,0.00026064945,0.00072078174,0.0002919756],"domain_scores_gemma":[0.9971645,0.00047430262,0.0009843349,0.00018765923,0.00070114026,0.00048804606],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017913193,0.0002074073,0.0007800311,0.0002648115,0.00019685739,0.0000303383,0.00014788705,0.00011637195,0.0008749152],"category_scores_gemma":[0.0067142984,0.0001432789,0.000091535985,0.0002571315,0.00041704468,0.00015135708,0.00006369634,0.0007715586,0.0000143332445],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039635197,0.00031455935,0.00012636698,0.00029888883,0.00035923798,0.00096707087,0.0053522144,0.0000052256505,0.016838815,0.002128079,0.031245671,0.94196755],"study_design_scores_gemma":[0.0020611521,0.0024715594,0.00047112635,0.0021688142,0.00068366376,0.005944699,0.012647412,0.009216166,0.00032588758,0.0013400739,0.96247345,0.00019597795],"about_ca_topic_score_codex":0.000026311947,"about_ca_topic_score_gemma":0.0000021443548,"teacher_disagreement_score":0.94177157,"about_ca_system_score_codex":0.000084758205,"about_ca_system_score_gemma":0.00023908842,"threshold_uncertainty_score":0.9579708},"labels":[],"label_agreement":null},{"id":"W3209674794","doi":"10.5281/zenodo.4590294","title":"Virtual cohort of adult healthy four-chamber heart meshes from CT images","year":2021,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Thomas Hospital","funders":"European Commission; Research Councils UK; Wellcome","keywords":"Polygon mesh; Cohort; Medicine; Computer science; Computer graphics (images); Nuclear medicine; Computer vision; Artificial intelligence; Internal medicine","score_opus":0.020878134899622588,"score_gpt":0.28210911182394016,"score_spread":0.26123097692431757,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3209674794","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007519268,0.00046884833,0.0004478188,0.005229822,0.00045751914,0.00076299574,0.9799618,0.0003697575,0.0047821715],"genre_scores_gemma":[0.0034761527,0.0014617977,0.0004906223,0.0017121112,0.0005950299,9.429401e-8,0.99055487,0.0011777938,0.0005315551],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9968333,0.0005243713,0.0005838127,0.000704469,0.00090628065,0.00044776875],"domain_scores_gemma":[0.99734986,0.000108818436,0.00027438937,0.0009606475,0.0008859799,0.00042027837],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0007349837,0.0002960985,0.0007016751,0.00029434453,0.0007415975,0.0002880316,0.0005562218,0.00013823873,0.020038633],"category_scores_gemma":[0.0035940874,0.0002909981,0.00017319297,0.00041631795,0.00034752546,0.00010221439,0.001071435,0.0013103433,0.0023822084],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012712057,0.00020593124,0.0000262664,0.0002623403,0.00022594379,0.0002712367,0.00006438839,0.000009588897,0.00060199347,0.000030350255,0.9887675,0.009407307],"study_design_scores_gemma":[0.0009494442,0.00041269528,0.0011129229,0.00039089762,0.0001759864,0.0006865406,0.00011911117,0.00016767488,0.00014991472,0.000014840255,0.9955858,0.00023414812],"about_ca_topic_score_codex":0.0006238264,"about_ca_topic_score_gemma":0.0000011623434,"teacher_disagreement_score":0.017656425,"about_ca_system_score_codex":0.00015649319,"about_ca_system_score_gemma":0.000036119523,"threshold_uncertainty_score":0.9999542},"labels":[],"label_agreement":null},{"id":"W3209683665","doi":"10.5281/zenodo.5105319","title":"Alpha Thunder Testo Canada Reviews [2021] | Is it legit or scam?","year":2021,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Thunder; Physics; Meteorology","score_opus":0.051161524650219226,"score_gpt":0.3012807713972935,"score_spread":0.25011924674707425,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3209683665","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023600655,0.005011469,0.008899402,0.18107906,0.0009908277,0.0017727445,0.00021561747,0.0008220829,0.77760816],"genre_scores_gemma":[0.67707545,0.00992345,0.007855083,0.0821744,0.0030175385,4.7295092e-7,0.0051203053,0.006719418,0.20811386],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980386,0.0002611067,0.00034451048,0.00045040148,0.00051151816,0.00039384436],"domain_scores_gemma":[0.9984393,0.000038712104,0.00009919124,0.00055267813,0.0004913929,0.00037868472],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00064452813,0.0001592294,0.0003005737,0.000092593946,0.0010317249,0.00033169758,0.00040922576,0.00005293148,0.060700398],"category_scores_gemma":[0.003475532,0.00013656574,0.000070927956,0.00061888667,0.000110379646,0.00010923163,0.0005357353,0.00052418606,0.0029464166],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000046398156,0.000071782866,0.00001953243,0.00013343981,0.00004497494,0.00027199605,0.00030546798,0.0000042321917,0.0016881815,0.00023737385,0.84157103,0.15560561],"study_design_scores_gemma":[0.0006726466,0.00013115472,0.00045468358,0.00021202637,0.00004406853,0.0008238136,0.00030975387,0.0006563532,0.00034297057,0.000022198872,0.996176,0.00015430058],"about_ca_topic_score_codex":0.0030622452,"about_ca_topic_score_gemma":0.00021671708,"teacher_disagreement_score":0.6534748,"about_ca_system_score_codex":0.00027411265,"about_ca_system_score_gemma":0.000087219734,"threshold_uncertainty_score":0.9978299},"labels":[],"label_agreement":null},{"id":"W3209702343","doi":"10.1117/12.2611292","title":"3D PET image generation with tumour masks using TGAN","year":2022,"lang":"en","type":"preprint","venue":"Medical Imaging 2022: Image Processing","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Artificial intelligence; Computer science; Synthetic data; Segmentation; Pattern recognition (psychology); Data set; Feature (linguistics); Generator (circuit theory); Computer vision; Generative model; Image (mathematics); Image segmentation; Set (abstract data type); Dice; Mathematics; Generative grammar; Statistics","score_opus":0.015975241761395965,"score_gpt":0.3240131242369655,"score_spread":0.3080378824755695,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3209702343","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2599644,0.010069499,0.6776509,0.032907292,0.003020512,0.0021574784,0.00007925873,0.0016376885,0.012512929],"genre_scores_gemma":[0.49954602,0.00044987435,0.47969705,0.009787526,0.005878857,0.00032530315,0.0019263874,0.0008438421,0.0015451284],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9913335,0.0004200524,0.0012947534,0.0019831469,0.003648879,0.0013196581],"domain_scores_gemma":[0.99636513,0.00013016333,0.0008548381,0.0009692417,0.00053821603,0.0011424283],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0027172933,0.00104174,0.0014786591,0.00069890846,0.0010342563,0.0009262413,0.0009087958,0.0002369445,0.0041596373],"category_scores_gemma":[0.0021498287,0.0009189284,0.00033622127,0.00074785366,0.0010407498,0.00054727145,0.0019001372,0.007512137,0.000025243315],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00072012446,0.0021064533,0.02187349,0.013338861,0.0010444968,0.07379139,0.004431989,0.0024867742,0.2886005,0.000053898206,0.019899854,0.5716522],"study_design_scores_gemma":[0.0024199216,0.00007692612,0.0004139094,0.0027282683,0.0009475595,0.008429125,0.0005591619,0.9781927,0.00085151393,0.00012450996,0.0041641095,0.0010923209],"about_ca_topic_score_codex":0.00038706156,"about_ca_topic_score_gemma":0.0000065337126,"teacher_disagreement_score":0.9757059,"about_ca_system_score_codex":0.0008116704,"about_ca_system_score_gemma":0.0036708491,"threshold_uncertainty_score":0.9993261},"labels":[],"label_agreement":null},{"id":"W3209710982","doi":"10.5281/zenodo.4593739","title":"Virtual cohort of extreme and average four-chamber heart meshes from statistical shape model","year":2021,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Thomas Hospital","funders":"European Commission; Research Councils UK; Wellcome","keywords":"Polygon mesh; Cohort; Mathematics; Computer science; Statistics; Computer graphics (images)","score_opus":0.03884697281809946,"score_gpt":0.2766191471307145,"score_spread":0.23777217431261505,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3209710982","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0078337,0.00028209097,0.0090942085,0.0010211586,0.00013165323,0.0004905358,0.9785967,0.00018408438,0.0023658786],"genre_scores_gemma":[0.010301708,0.0007385623,0.001720603,0.0005571174,0.00023780021,6.1446556e-8,0.9852716,0.00082404976,0.00034852608],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976886,0.00029754516,0.0004150018,0.0005958508,0.0006861725,0.00031684307],"domain_scores_gemma":[0.99845165,0.000112745256,0.0001390794,0.0005677107,0.00037204815,0.00035674783],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006444283,0.00023459956,0.0005386263,0.00018515353,0.0004989978,0.00025775775,0.00030026704,0.0001713864,0.01915208],"category_scores_gemma":[0.0021988826,0.0002315245,0.000071015646,0.00018732852,0.0003496411,0.00007867488,0.001038843,0.00094542623,0.000561879],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000085827945,0.00012608916,0.000013534308,0.0001656639,0.0001598306,0.00017543497,0.00008778922,0.00010406464,0.00073862495,0.00013085036,0.9870278,0.011184464],"study_design_scores_gemma":[0.0007201036,0.00019478107,0.0010032667,0.00021634206,0.00016795786,0.00033199656,0.000042013093,0.041314043,0.000017916671,0.00006653627,0.95572627,0.00019879146],"about_ca_topic_score_codex":0.00013862738,"about_ca_topic_score_gemma":4.9584435e-7,"teacher_disagreement_score":0.041209977,"about_ca_system_score_codex":0.000080356156,"about_ca_system_score_gemma":0.000022768449,"threshold_uncertainty_score":0.9817445},"labels":[],"label_agreement":null},{"id":"W3209728716","doi":"10.21203/rs.3.rs-971708/v1","title":"Renal Cell Carcinoma Whole-Slide Image Classification and Search Using Deep Learning","year":2021,"lang":"en","type":"preprint","venue":"Research Square","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Artificial intelligence; Computer science; Renal cell carcinoma; Deep learning; Image (mathematics); Pattern recognition (psychology); Contextual image classification; Machine learning; Pathology; Medicine","score_opus":0.06877876743371962,"score_gpt":0.4051075553292775,"score_spread":0.33632878789555787,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3209728716","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9801768,0.0043317,0.008119258,0.002929134,0.00013935755,0.00084096,0.000008362396,0.000088756795,0.0033656848],"genre_scores_gemma":[0.9827713,0.00074579887,0.013623219,0.00006913554,0.00070859864,0.000047095964,0.0004993427,0.00011945049,0.0014160856],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99425757,0.0013054615,0.00049340416,0.0011430347,0.0018175844,0.0009829323],"domain_scores_gemma":[0.99681735,0.0004884301,0.00013186528,0.00078294904,0.0010916613,0.0006877731],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.003651095,0.0003428532,0.00064573775,0.00072642945,0.00057525927,0.00058659585,0.0002977068,0.000454085,0.00020098109],"category_scores_gemma":[0.0018045321,0.00033285096,0.00020158199,0.00052496657,0.0005276642,0.00012462682,0.0014341483,0.008182111,0.000030159568],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035277882,0.000562604,0.23191914,0.013761273,0.00019734398,0.0034937512,0.006920389,0.0034099175,0.65883434,0.00012645882,0.0009758496,0.07944617],"study_design_scores_gemma":[0.0018304408,0.00038031745,0.1917881,0.0027542058,0.00014769887,0.00029590804,0.007459632,0.78581756,0.0047895038,0.00011076563,0.0040743966,0.000551425],"about_ca_topic_score_codex":0.0008455658,"about_ca_topic_score_gemma":0.0000099876925,"teacher_disagreement_score":0.7824077,"about_ca_system_score_codex":0.00052032433,"about_ca_system_score_gemma":0.0010453421,"threshold_uncertainty_score":0.9999124},"labels":[],"label_agreement":null},{"id":"W3210087576","doi":"10.1212/wnl.96.15_supplement.4121","title":"Machine Learning-Based Classification of Acute versus Chronic Multiple Sclerosis Lesions using Radiomic Features from Unenhanced Cross-Sectional Brain MRI (4121)","year":2021,"lang":"en","type":"article","venue":"Neurology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; NeuroRx Research (Canada)","funders":"","keywords":"Medicine; Multiple sclerosis; Magnetic resonance imaging; Radiology; Psychiatry","score_opus":0.0412707683216141,"score_gpt":0.3238106171403856,"score_spread":0.28253984881877153,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3210087576","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98167485,0.0006164907,0.011440208,0.0050038868,0.0008998879,0.00014943993,0.000047856334,0.00008372942,0.000083671664],"genre_scores_gemma":[0.99572515,0.00010774888,0.0020179367,0.0010791463,0.00033996653,0.00001008896,0.00053982413,0.00004537874,0.00013476459],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9981998,0.00029121284,0.00037847212,0.00054100464,0.0002835265,0.00030593676],"domain_scores_gemma":[0.998297,0.0008557954,0.00022849084,0.00033386974,0.00014491212,0.0001399789],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021141078,0.0001881079,0.00040390756,0.0001489089,0.00023668027,0.000020662843,0.00013029702,0.00023820897,0.00030425188],"category_scores_gemma":[0.0008884952,0.00018699173,0.0001830963,0.00027305138,0.00034228925,0.00005164762,0.00006106063,0.0010671436,0.000010139884],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017910975,0.00012277934,0.25174093,0.000025192943,0.00017449382,0.00009423746,0.00004377494,0.014315687,0.730595,0.00003633687,0.00012502138,0.000935434],"study_design_scores_gemma":[0.0052636242,0.00048518326,0.6410227,0.000023012688,0.000117370495,0.00008015454,0.0000019239737,0.3421662,0.009677925,0.00001712034,0.0010442064,0.0001005918],"about_ca_topic_score_codex":0.0004879297,"about_ca_topic_score_gemma":0.000077284334,"teacher_disagreement_score":0.7209171,"about_ca_system_score_codex":0.0001016783,"about_ca_system_score_gemma":0.00042967204,"threshold_uncertainty_score":0.76253015},"labels":[],"label_agreement":null},{"id":"W3210390499","doi":"10.1016/j.ijrobp.2021.07.487","title":"Deep Learning and Harmonization of Multi-Institutional Data for Automated Gross Tumor and Nodal Segmentation for Oropharyngeal Cancer","year":2021,"lang":"en","type":"article","venue":"International Journal of Radiation Oncology*Biology*Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Medicine; Contouring; Segmentation; Ground truth; Artificial intelligence; Medical physics; Nuclear medicine; Cancer; Contrast (vision); Deep learning; Radiology; Computer science; Internal medicine","score_opus":0.02951057957855611,"score_gpt":0.3888168802289662,"score_spread":0.3593063006504101,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3210390499","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35018757,0.002000972,0.64287335,0.0031522785,0.0012571174,0.00030289084,0.00017956778,0.000030374289,0.00001589241],"genre_scores_gemma":[0.89702207,0.0014881381,0.09826994,0.00066960166,0.0012111769,0.000019254374,0.0012680319,0.000022886587,0.000028895485],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99893934,0.00008620837,0.0004880196,0.00021194015,0.00015176093,0.00012273267],"domain_scores_gemma":[0.9978963,0.00040109412,0.000646526,0.000066545545,0.00090483937,0.00008468219],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004888414,0.00011091184,0.0003573279,0.00008338886,0.00010593888,0.000025144045,0.00012243095,0.00008664812,0.000013205062],"category_scores_gemma":[0.0013166121,0.000099786754,0.00006397085,0.00007687842,0.000199935,0.00024688497,0.000066040884,0.00023131858,2.7222734e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00088302273,0.0004980925,0.39395985,0.00019477373,0.001079245,0.000041176816,0.00066068745,0.008045953,0.11458929,0.005504768,0.0006191998,0.47392392],"study_design_scores_gemma":[0.009963843,0.00044458717,0.025621586,0.00009902267,0.0002574103,0.0003407723,0.00014125767,0.95214057,0.0037515403,0.0006144211,0.0065146224,0.00011037807],"about_ca_topic_score_codex":0.000012725862,"about_ca_topic_score_gemma":0.0000036534982,"teacher_disagreement_score":0.9440946,"about_ca_system_score_codex":0.00017801452,"about_ca_system_score_gemma":0.0004667404,"threshold_uncertainty_score":0.40691856},"labels":[],"label_agreement":null},{"id":"W3210821830","doi":"10.1016/j.ijrobp.2021.07.532","title":"Machine Learning Classifier to Reproduce Lung Metastases Tumor Board Decisions","year":2021,"lang":"en","type":"article","venue":"International Journal of Radiation Oncology*Biology*Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University Health Network; Princess Margaret Cancer Centre","funders":"","keywords":"Medicine; Lung cancer; Logistic regression; Radiation therapy; Decision tree; Institutional review board; Artificial intelligence; Machine learning; Radiation oncologist; Radiology; Medical physics; Surgery; Internal medicine","score_opus":0.024385753837614772,"score_gpt":0.3611587433393179,"score_spread":0.33677298950170315,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3210821830","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6980432,0.0037035076,0.22281925,0.064493,0.0071148267,0.0003520407,0.0000662902,0.00012442777,0.00328343],"genre_scores_gemma":[0.9326419,0.0010414151,0.05227891,0.008830595,0.004098634,0.000010487885,0.00018782985,0.000059459373,0.0008507725],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976202,0.00040112453,0.0008603152,0.0003797518,0.00045744437,0.00028111628],"domain_scores_gemma":[0.9966547,0.00085752684,0.0007290058,0.00023794657,0.0011914201,0.00032943932],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0011331376,0.00020194672,0.0006108314,0.00023250545,0.00012672979,0.000055376222,0.00033237285,0.00012034628,0.00024870774],"category_scores_gemma":[0.008364076,0.00017737248,0.0003124685,0.00031996478,0.00014329808,0.0001821078,0.00014394276,0.0011878965,0.00005040089],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006277559,0.00079791434,0.46147802,0.000015768326,0.0014191758,0.0013474363,0.0005432895,0.007998408,0.034076475,0.013801951,0.013732192,0.4641616],"study_design_scores_gemma":[0.0092998035,0.0015729384,0.035577644,0.00037931403,0.0006795252,0.0034511406,0.0002779274,0.05193474,0.010377344,0.0075001055,0.8784305,0.0005190266],"about_ca_topic_score_codex":0.00001825459,"about_ca_topic_score_gemma":0.000002784461,"teacher_disagreement_score":0.8646983,"about_ca_system_score_codex":0.00050854904,"about_ca_system_score_gemma":0.0009482995,"threshold_uncertainty_score":0.9999889},"labels":[],"label_agreement":null},{"id":"W3212494582","doi":"10.1136/jitc-2021-sitc2021.036","title":"36 Digital Whole Slide Image (WSI) scoring is equivalent to microscope glass slide scoring for evaluation of programmed death-ligand 1 (PD-L1) expression across multiple tumor indications","year":2021,"lang":"en","type":"article","venue":"Regular and Young Investigator Award Abstracts","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Concordance; Medicine; Digital pathology; Digital image analysis; Nuclear medicine; Cutoff; Pathology; Internal medicine; Computer science; Computer vision; Physics","score_opus":0.03299134903457568,"score_gpt":0.3410151725997529,"score_spread":0.3080238235651772,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3212494582","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99256843,0.00070339517,0.0025165812,0.0023742456,0.0003459677,0.0011911945,0.00010717046,0.00007413629,0.000118866395],"genre_scores_gemma":[0.97592753,0.000024947205,0.022608135,0.00047907792,0.00024261909,0.00017164729,0.00021857471,0.00006761003,0.00025983117],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99712586,0.000063083295,0.0007141026,0.00067805726,0.0008284437,0.000590456],"domain_scores_gemma":[0.9975559,0.00015924542,0.0003206849,0.00048680027,0.0005786111,0.00089871744],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012911756,0.00029939107,0.0005146266,0.0001248384,0.0003146648,0.00030874021,0.00015928263,0.000118639844,0.00000637419],"category_scores_gemma":[0.0061947373,0.0002837925,0.0001703227,0.00026871377,0.00022501108,0.000377041,0.0001738133,0.00034357145,0.000008152474],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011334155,0.00019815713,0.057610814,0.00061125896,0.0000925415,0.00004358108,0.001721474,0.00018207729,0.9300602,0.000021362108,0.00084738404,0.0084978],"study_design_scores_gemma":[0.0038324688,0.00016179626,0.12150577,0.0020644176,0.00027158821,0.00020011126,0.0007989265,0.005511531,0.8585632,0.00034074878,0.00639993,0.00034953657],"about_ca_topic_score_codex":0.00006544569,"about_ca_topic_score_gemma":0.0000092232,"teacher_disagreement_score":0.07149703,"about_ca_system_score_codex":0.0001573977,"about_ca_system_score_gemma":0.0006409855,"threshold_uncertainty_score":0.99996144},"labels":[],"label_agreement":null},{"id":"W3213811889","doi":"10.21203/rs.3.rs-1078827/v1","title":"Predicting Survival in Patients with Glioblastoma Using MRI Radiomic Features Extracted from Radiation Planning Volumes","year":2021,"lang":"en","type":"preprint","venue":"Research Square","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; Sunnybrook Health Science Centre","funders":"Terry Fox Foundation","keywords":"Glioblastoma; Radiation therapy; Medicine; Radiation treatment planning; Radiology; Nuclear medicine; Computer science; Medical physics; Artificial intelligence; Cancer research","score_opus":0.023130762294841723,"score_gpt":0.3602724441656402,"score_spread":0.33714168187079846,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3213811889","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99465793,0.0020803562,0.00091284845,0.00036261865,0.00050274376,0.0011418486,0.00006333437,0.00011424461,0.00016405071],"genre_scores_gemma":[0.99367833,0.00009741554,0.0035920502,0.00003811064,0.00084207277,0.000042333668,0.0014947001,0.00012404281,0.00009095505],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9944659,0.00086759333,0.00056332943,0.0010344731,0.0021979173,0.0008708022],"domain_scores_gemma":[0.99735415,0.00069861603,0.00025158035,0.0006930732,0.00061179866,0.0003907869],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.001577958,0.00039719307,0.0008719673,0.0009505372,0.00030069117,0.00026952106,0.00031080656,0.0005067917,0.00011156344],"category_scores_gemma":[0.002130299,0.0003584122,0.00014533174,0.00072679657,0.0002219126,0.0001810419,0.0005311722,0.00559597,0.0000032095784],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00093398575,0.00027011032,0.9786328,0.0005732299,0.0002106101,0.0007071595,0.0026808477,0.010798416,0.0003822773,0.0000018468834,0.00018813144,0.004620563],"study_design_scores_gemma":[0.0032025827,0.00027664547,0.8800591,0.0061901896,0.00007301041,0.000016347813,0.0008799137,0.108805604,0.000114734954,0.000021162183,0.00007178491,0.00028890255],"about_ca_topic_score_codex":0.0048568556,"about_ca_topic_score_gemma":0.000130414,"teacher_disagreement_score":0.09857371,"about_ca_system_score_codex":0.00086336944,"about_ca_system_score_gemma":0.0011323292,"threshold_uncertainty_score":0.9998868},"labels":[],"label_agreement":null},{"id":"W3213990473","doi":"10.1016/j.media.2023.103058","title":"Acquisition-invariant brain MRI segmentation with informative uncertainties","year":2023,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Eisai; National Institute on Aging; National Institute for Health and Care Research; Northern California Institute for Research and Education; BioClinica; Biogen; Pfizer; Novartis Pharmaceuticals Corporation; Wellcome Trust; University of Southern California; Engineering and Physical Sciences Research Council; U.S. Department of Defense; Eli Lilly and Company; Bristol-Myers Squibb; University College London Hospitals NHS Foundation Trust; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; Alzheimer's Association","keywords":"Segmentation; Computer science; Task (project management); Artificial intelligence; Context (archaeology); Machine learning; Invariant (physics); Quality (philosophy); Data mining; Mathematics","score_opus":0.00644885826553453,"score_gpt":0.29685513854852047,"score_spread":0.29040628028298593,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3213990473","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24368085,0.0000798546,0.63144666,0.11615886,0.00011785897,0.00039164882,0.000015853,0.00056905113,0.007539369],"genre_scores_gemma":[0.9552686,0.00030788372,0.016171675,0.020664828,0.0004638136,0.00008958968,0.0019417071,0.00005261145,0.0050392835],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977127,0.00009855854,0.0003836516,0.00026825457,0.0011943133,0.00034252513],"domain_scores_gemma":[0.99873763,0.00031664345,0.00011735673,0.00026526794,0.00015399262,0.0004091143],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0010871955,0.0001671585,0.00046009303,0.00066855486,0.00015736409,0.000072967436,0.00013688783,0.000086988664,0.0022631658],"category_scores_gemma":[0.0009044532,0.00011436141,0.00019769778,0.0027244175,0.00030683205,0.00021727,0.00006322149,0.00041596554,0.0002529173],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001379034,0.0011069207,0.2696352,0.0013981843,0.03331619,0.012395584,0.030621773,0.011277475,0.009199643,0.005034866,0.44941133,0.1752238],"study_design_scores_gemma":[0.0035312376,0.00035168967,0.06587263,0.00026243096,0.003490137,0.00013711042,0.004921779,0.91404307,0.00075741956,0.00039711717,0.005816384,0.0004189872],"about_ca_topic_score_codex":0.00021349697,"about_ca_topic_score_gemma":0.000024317787,"teacher_disagreement_score":0.9027656,"about_ca_system_score_codex":0.00006917728,"about_ca_system_score_gemma":0.0001686827,"threshold_uncertainty_score":0.9986489},"labels":[],"label_agreement":null},{"id":"W3214926239","doi":"10.1016/j.cpet.2021.09.002","title":"Clinical Application of Artificial Intelligence in Positron Emission Tomography: Imaging of Prostate Cancer","year":2021,"lang":"en","type":"review","venue":"PET Clinics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Medicine; Positron emission tomography; Prostate cancer; Cancer imaging; Medical physics; Pet imaging; Translational research; Molecular imaging; Applications of artificial intelligence; Cancer; Artificial intelligence; Radiology; Pathology; Internal medicine; Computer science","score_opus":0.042726569023566974,"score_gpt":0.4611554051695018,"score_spread":0.41842883614593485,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3214926239","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011225884,0.9947933,0.0026126413,0.00022532066,0.00041987546,0.0006959115,0.000025067124,0.000018822382,0.00008647068],"genre_scores_gemma":[0.0011757718,0.9938709,0.0042782463,0.000079898186,0.0002699638,0.00005180618,0.0001877633,0.00004673465,0.00003890331],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9960923,0.00028274054,0.0025598833,0.00051005563,0.0003257987,0.00022921515],"domain_scores_gemma":[0.99728185,0.00070633326,0.0012055361,0.00047609146,0.00019040599,0.00013980792],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020095417,0.00024518324,0.0022564507,0.00027372307,0.000020736363,0.000009176837,0.00021092074,0.00016768186,0.000027906784],"category_scores_gemma":[0.0012122333,0.00020324413,0.0007000117,0.00064310903,0.00022037668,0.000030092298,0.00010915474,0.0012884147,0.000002318871],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027406688,0.00027267943,0.018619295,0.008159458,0.00007220287,0.000033304175,0.000049250757,0.000008682205,0.0000041176822,0.000102730184,0.000041862128,0.972609],"study_design_scores_gemma":[0.0006885436,0.0003306341,0.0013930794,0.11475914,0.0034372373,0.00015185087,0.0001650756,0.05630359,0.00003525328,0.0009080139,0.82105935,0.0007682233],"about_ca_topic_score_codex":0.00012423871,"about_ca_topic_score_gemma":0.0000072406647,"teacher_disagreement_score":0.9718408,"about_ca_system_score_codex":0.0000552376,"about_ca_system_score_gemma":0.00067699695,"threshold_uncertainty_score":0.82880545},"labels":[],"label_agreement":null},{"id":"W3215218792","doi":"10.1016/j.cpet.2021.06.011","title":"Artificial Intelligence and Cardiac PET/Computed Tomography Imaging","year":2021,"lang":"en","type":"review","venue":"PET Clinics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"National Institutes of Health","keywords":"Artificial intelligence; Medicine; Segmentation; Correction for attenuation; Computed tomography; Computed tomographic; Medical physics; Positron emission tomography; Computer science; Radiology","score_opus":0.051416746458673904,"score_gpt":0.39861334721134656,"score_spread":0.34719660075267267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3215218792","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000034639597,0.99427253,0.0025877198,0.00046892464,0.0016627603,0.0004049933,0.000022686916,0.00011155279,0.00043418288],"genre_scores_gemma":[0.00004078042,0.9891555,0.008652363,0.00033561504,0.0012351053,0.000021299396,0.00030556336,0.00009091548,0.00016289529],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99710715,0.0002658461,0.0011233547,0.0007470035,0.00035231558,0.0004043466],"domain_scores_gemma":[0.99768734,0.0009289766,0.00035548588,0.00055555766,0.00012815167,0.00034449864],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001168119,0.00043498975,0.0024753981,0.00029577018,0.00011569107,0.00012697448,0.00020182294,0.00009249853,0.00006978386],"category_scores_gemma":[0.001193641,0.00037110317,0.0009718957,0.000558997,0.00024152447,0.000042385156,0.00023229842,0.0017659232,0.00003630601],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002817058,0.000059811602,0.00026830056,0.0046550245,0.00023497955,0.000972817,0.000029553777,0.0000012159478,1.0466103e-7,0.00059184304,0.00061433035,0.9925692],"study_design_scores_gemma":[0.000051694788,0.000039448823,0.000020930802,0.012210087,0.0018721581,0.0010240895,0.000044483797,0.0043812455,2.127906e-7,0.00027583944,0.9797204,0.00035940594],"about_ca_topic_score_codex":0.000013235394,"about_ca_topic_score_gemma":4.853734e-7,"teacher_disagreement_score":0.9922098,"about_ca_system_score_codex":0.000044649893,"about_ca_system_score_gemma":0.0004023954,"threshold_uncertainty_score":0.9998741},"labels":[],"label_agreement":null},{"id":"W3215495292","doi":"10.1016/j.jclinepi.2021.11.024","title":"GRADE concept paper 2: Concepts for judging certainty on the calibration of prognostic models in a body of validation studies","year":2021,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":21,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Impact; Ted Rogers Centre for Heart Research","funders":"British Heart Foundation","keywords":"Certainty; Inference; Calibration; Econometrics; Computer science; Medicine; Statistics; Artificial intelligence; Mathematics","score_opus":0.2834012222335031,"score_gpt":0.5316164983690372,"score_spread":0.24821527613553412,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3215495292","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8884524,0.0013434122,0.042179134,0.067157365,0.00052822643,0.0002799217,0.0000032105336,0.0000036075448,0.000052687803],"genre_scores_gemma":[0.98881423,0.00078099174,0.005565737,0.004453282,0.00034480702,0.000006250775,0.00000574487,0.000009179625,0.000019796502],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99400514,0.00253247,0.0029605706,0.00015661126,0.00017654659,0.00016865821],"domain_scores_gemma":[0.94255483,0.05472899,0.0020091669,0.00015766089,0.00045762683,0.00009172917],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.013026645,0.00009381092,0.0016700006,0.00006438509,0.000025859408,0.000001976272,0.0000947061,0.00013504854,0.00001928746],"category_scores_gemma":[0.19893986,0.000054215583,0.00038655425,0.00010842173,0.00038567407,0.000070581824,0.000028168193,0.00070047064,1.2285092e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002617079,0.0019316915,0.67939574,0.0008887597,0.0017888857,0.00013497814,0.0027965354,0.1270429,0.0062649366,0.13408026,0.009480731,0.033577494],"study_design_scores_gemma":[0.0102391355,0.0044339434,0.13409412,0.003345955,0.00069262594,0.00016218843,0.0021067152,0.67872316,0.003112139,0.16181698,0.0010607949,0.00021227056],"about_ca_topic_score_codex":0.000007989419,"about_ca_topic_score_gemma":0.0000014655091,"teacher_disagreement_score":0.5516802,"about_ca_system_score_codex":0.00002417045,"about_ca_system_score_gemma":0.00025026465,"threshold_uncertainty_score":0.8078078},"labels":[],"label_agreement":null},{"id":"W3215573305","doi":"10.1007/s40336-021-00474-5","title":"Thoracic imaging radiomics for staging lung cancer: a systematic review and radiomic quality assessment","year":2021,"lang":"en","type":"review","venue":"Clinical and Translational Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Population Health Research Institute; McMaster University; St. Joseph’s Healthcare Hamilton; Impact","funders":"","keywords":"Medicine; Lung cancer; Observational study; Radiomics; Data extraction; MEDLINE; Meta-analysis; Medical physics; Radiology; Lung cancer screening; Systematic review; Malignancy; Algorithm; Internal medicine","score_opus":0.08892289590041863,"score_gpt":0.5296096177267255,"score_spread":0.4406867218263069,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3215573305","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00001242931,0.96894425,0.020446012,0.006475223,0.00037211934,0.0034366078,0.00014190294,0.00007714821,0.000094312716],"genre_scores_gemma":[0.0000846876,0.9859183,0.00965452,0.0026348038,0.0004681823,0.00048219247,0.000520098,0.0001144009,0.00012281645],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.99425685,0.00083755166,0.0028796575,0.0011069898,0.00043423695,0.0004847037],"domain_scores_gemma":[0.99482024,0.0031714959,0.0008699981,0.00044645817,0.00023258763,0.0004592341],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.004834831,0.00063312915,0.00582354,0.00020283168,0.00029094753,0.0001929212,0.0001858781,0.00015544973,0.00003431034],"category_scores_gemma":[0.0010865529,0.0005029406,0.0011009559,0.00028172325,0.00039811528,0.00019019622,0.000080981394,0.0013717023,8.508614e-7],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000058406076,0.00005176788,0.004683543,0.61374396,0.0006156938,0.00002999602,0.00002096032,6.0268184e-7,2.6705354e-7,0.00049926597,0.00021073484,0.38013732],"study_design_scores_gemma":[0.0018498264,0.000019412428,0.00055098557,0.82871383,0.03783141,0.0008361948,0.000031638745,0.031490833,7.127223e-8,0.00024486755,0.097533174,0.0008977475],"about_ca_topic_score_codex":0.000020155852,"about_ca_topic_score_gemma":8.146373e-7,"teacher_disagreement_score":0.3792396,"about_ca_system_score_codex":0.00008658422,"about_ca_system_score_gemma":0.0009533876,"threshold_uncertainty_score":0.9997422},"labels":[],"label_agreement":null},{"id":"W3215696868","doi":"10.1093/neuonc/noab196.498","title":"PATH-46. DIAGNOSTIC IMPACT OF THE CNS TUMOR METHYLATION PROFILING IN A NEUROPATHOLOGY CONSULT PRACTICE","year":2021,"lang":"en","type":"article","venue":"Neuro-Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Neuropathology; Classifier (UML); Brain tumor; Medulloblastoma; Methylation; Medicine; DNA methylation; Profiling (computer programming); Oncology; Pathology; Internal medicine; Artificial intelligence; Computer science; Biology; Disease","score_opus":0.015847717853677324,"score_gpt":0.35420435867283906,"score_spread":0.3383566408191617,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3215696868","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9796624,0.00039862143,0.00030276747,0.013826767,0.00070718356,0.00042543572,0.00000511089,0.000029212479,0.00464249],"genre_scores_gemma":[0.9918909,0.00015265867,0.002295562,0.0054314667,0.00013973807,0.000025822204,0.000009027943,0.00003196758,0.000022873064],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99730664,0.0013726706,0.0004734176,0.0003431678,0.00020734934,0.0002967638],"domain_scores_gemma":[0.9938975,0.0050659487,0.0003293466,0.00035918562,0.00023640618,0.00011160764],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00080007745,0.00014156707,0.0004690201,0.00010030824,0.00004522793,0.0000091456,0.0001206799,0.00010657642,0.000063475454],"category_scores_gemma":[0.070774876,0.00010132762,0.0001430219,0.00045650086,0.00020429125,0.000066404114,0.00012543192,0.0011076225,0.000013665785],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023609838,0.00055647723,0.11291507,0.00008480055,0.000036441856,0.005809446,0.00070750393,0.0005523976,0.8654527,0.00033189153,0.00050088577,0.012816262],"study_design_scores_gemma":[0.019980002,0.0069917655,0.69912827,0.00061031844,0.0013496715,0.04594821,0.0017142304,0.04933231,0.104126565,0.0013164387,0.06874484,0.00075740064],"about_ca_topic_score_codex":0.00008273402,"about_ca_topic_score_gemma":0.0000065813906,"teacher_disagreement_score":0.7613262,"about_ca_system_score_codex":0.0001525099,"about_ca_system_score_gemma":0.0009521292,"threshold_uncertainty_score":0.93705237},"labels":[],"label_agreement":null},{"id":"W3216187193","doi":"10.1016/j.cpet.2021.11.002","title":"Taming the Complexity: Using Artificial Intelligence in a Cross-Disciplinary Innovative Platform to Redefine Molecular Imaging and Radiopharmaceutical Therapy","year":2021,"lang":"en","type":"editorial","venue":"PET Clinics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Artificial intelligence; Deep learning; Big data; Medical imaging; Medicine; Applications of artificial intelligence; Health care; Data science; Medical physics; Computer science; Law; Political science","score_opus":0.0995162434095314,"score_gpt":0.4627139241597098,"score_spread":0.3631976807501784,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3216187193","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43159407,0.010035377,0.031344753,0.019477958,0.50449437,0.002063447,0.0001259848,0.00016429457,0.00069971284],"genre_scores_gemma":[0.20304221,0.005367822,0.055644635,0.00939687,0.7247809,0.000111140194,0.0010164013,0.00048566048,0.00015434157],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963146,0.00016479846,0.0011878127,0.0008397313,0.0008969225,0.0005961243],"domain_scores_gemma":[0.99679565,0.001655005,0.00030727033,0.00051512016,0.00047447553,0.00025245058],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0026259755,0.00044544254,0.0009649352,0.00029422872,0.0002622665,0.0002715849,0.00033846917,0.00026561358,0.000045630255],"category_scores_gemma":[0.0054811044,0.00035386631,0.00014594728,0.0009801695,0.00088482734,0.00008668255,0.0005387373,0.003905987,0.000004740874],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0071803215,0.0021443577,0.01249745,0.0025194234,0.0014066903,0.02087502,0.01509413,0.0037404632,0.0070832786,0.015455879,0.113208525,0.79879445],"study_design_scores_gemma":[0.0035578315,0.00060442433,0.0010646788,0.004913038,0.000346879,0.0006076295,0.0025207463,0.65902185,0.0004971955,0.019128243,0.30603963,0.001697882],"about_ca_topic_score_codex":0.000082138824,"about_ca_topic_score_gemma":0.000007111527,"teacher_disagreement_score":0.79709655,"about_ca_system_score_codex":0.00023614266,"about_ca_system_score_gemma":0.00078985095,"threshold_uncertainty_score":0.99989134},"labels":[],"label_agreement":null},{"id":"W3216265150","doi":"10.1038/s41523-021-00354-1","title":"Mammographic texture features associated with contralateral breast cancer in the WECARE Study","year":2021,"lang":"en","type":"article","venue":"npj Breast Cancer","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario; Lunenfeld-Tanenbaum Research Institute","funders":"National Institute of Allergy and Infectious Diseases; U.S. Department of Health and Human Services; Cancer Australia; National Cancer Institute; Cure Cancer Australia Foundation; Cancer Council Victoria","keywords":"Medicine; Breast cancer; Confounding; MAMMOGRAPHIC DENSITY; Mammography; Texture (cosmology); Odds ratio; Cancer; Internal medicine; Artificial intelligence; Computer science; Image (mathematics)","score_opus":0.005498334503839506,"score_gpt":0.2790828574298052,"score_spread":0.2735845229259657,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3216265150","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95305103,0.0019263907,0.0000061780747,0.043264765,0.00026896817,0.00048411175,0.00022243094,0.000059253285,0.0007168511],"genre_scores_gemma":[0.993269,0.000146892,0.00001277849,0.0050731674,0.00045246852,0.00015116883,0.000046042536,0.00004121269,0.00080721686],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9981421,0.00021259373,0.00021869366,0.00040889607,0.0005691623,0.00044853406],"domain_scores_gemma":[0.9991424,0.00007208497,0.0000938783,0.0003129904,0.00023769958,0.00014094617],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00030208286,0.00024407737,0.00042368865,0.000092209746,0.00012761174,0.00008786909,0.00017464657,0.00010980582,0.0009273839],"category_scores_gemma":[0.000040967232,0.00014165309,0.00009861149,0.0006673534,0.0001207641,0.00007754291,0.00003378336,0.0010739755,0.000002176369],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026358428,0.00041640562,0.9652628,0.000032541007,0.00033905197,0.0008917378,0.0015119504,0.00014095062,0.00021447583,0.00001818233,0.0024713536,0.028436987],"study_design_scores_gemma":[0.003924441,0.00006566607,0.9915071,0.00060236914,0.0002775823,0.0011831553,0.0012384251,0.00035405369,0.00000685254,0.000013275757,0.00064195425,0.00018513651],"about_ca_topic_score_codex":0.0032304365,"about_ca_topic_score_gemma":0.0048410962,"teacher_disagreement_score":0.040218,"about_ca_system_score_codex":0.00016842142,"about_ca_system_score_gemma":0.00033283318,"threshold_uncertainty_score":0.99998593},"labels":[],"label_agreement":null},{"id":"W3216421291","doi":"10.1016/j.cpet.2021.09.001","title":"Clinical Applications of Artificial Intelligence in Positron Emission Tomography of Lung Cancer","year":2021,"lang":"en","type":"review","venue":"PET Clinics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; University of Waterloo; University of Toronto; McMaster University","funders":"","keywords":"Positron emission tomography; Medicine; Artificial intelligence; Medical imaging; Medical physics; Precision medicine; Radiomics; Lung cancer; Disease; Molecular imaging; Pathology; Machine learning; Computer science; Radiology","score_opus":0.05397528226570601,"score_gpt":0.49187014350657216,"score_spread":0.43789486124086613,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3216421291","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00019965884,0.9931836,0.0052174325,0.00013367647,0.00035905704,0.00066446007,0.000031497497,0.000014184532,0.00019642599],"genre_scores_gemma":[0.00014886598,0.9941662,0.0048935157,0.00006901173,0.0003768431,0.00008206202,0.00014384453,0.00003704656,0.000082590355],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99637777,0.00025728298,0.0024450067,0.00043001154,0.00029629125,0.0001936537],"domain_scores_gemma":[0.9971275,0.0011053099,0.0009427897,0.00050656847,0.00016381184,0.00015404788],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015597921,0.00021341046,0.0023244608,0.00028652034,0.000021463129,0.0000066703046,0.00024484142,0.0002672851,0.00009832872],"category_scores_gemma":[0.0010940576,0.00017622649,0.00087860774,0.0008199087,0.00020707044,0.000017240849,0.00010686102,0.0013706277,0.0000018153169],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011482461,0.0003609689,0.003928195,0.010659492,0.00013606042,0.00001822908,0.0000260492,0.000004259761,8.887079e-7,0.00025813575,0.00014715116,0.9844491],"study_design_scores_gemma":[0.00025027175,0.00016533687,0.00024351427,0.061446737,0.002918678,0.000049765946,0.00004382867,0.008605914,0.0000054028924,0.00027624372,0.9256572,0.00033708854],"about_ca_topic_score_codex":0.00005216941,"about_ca_topic_score_gemma":0.0000063820817,"teacher_disagreement_score":0.984112,"about_ca_system_score_codex":0.000045150307,"about_ca_system_score_gemma":0.00080312515,"threshold_uncertainty_score":0.7186308},"labels":[],"label_agreement":null},{"id":"W3217285723","doi":"10.1016/j.cpet.2021.09.010","title":"AI-Based Detection, Classification and Prediction/Prognosis in Medical Imaging","year":2021,"lang":"en","type":"review","venue":"PET Clinics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":66,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Artificial intelligence; Radiomics; Workflow; Computer science; Identification (biology); Medical imaging; Machine learning; Deep learning; Field (mathematics); Applications of artificial intelligence; Contextual image classification; Pattern recognition (psychology); Medicine; Image (mathematics)","score_opus":0.039531335769018336,"score_gpt":0.4074976124008745,"score_spread":0.36796627663185616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3217285723","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007470023,0.9912653,0.0030762544,0.0040545985,0.0007391986,0.00046839655,0.000013735161,0.00010592879,0.00020189043],"genre_scores_gemma":[0.0006807385,0.99562097,0.0007663664,0.0017100924,0.00060268445,0.00012570941,0.00034695334,0.00007383886,0.000072675546],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9969805,0.0003093358,0.0011882544,0.00065953366,0.0005740024,0.0002883958],"domain_scores_gemma":[0.9980575,0.0008098873,0.0003141009,0.00034455225,0.00013128693,0.0003427076],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0017510315,0.00030701928,0.0014584598,0.00035740214,0.00008420622,0.00006329027,0.00014026399,0.00029965345,0.00014432892],"category_scores_gemma":[0.004445097,0.0002663523,0.0003204052,0.00051914115,0.0001769831,0.000053510816,0.000071297836,0.0022215992,0.0000143311545],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000050330414,0.0001237423,0.006794099,0.0044421772,0.00005266591,0.00035504927,0.000012476024,8.547889e-7,1.9215528e-7,0.00002746079,0.0005555296,0.9876307],"study_design_scores_gemma":[0.00080911245,0.000037953938,0.0008982228,0.01658527,0.000715565,0.000989318,0.000020777417,0.09161854,1.9669717e-7,0.000020183767,0.8881119,0.0001929641],"about_ca_topic_score_codex":0.000017235088,"about_ca_topic_score_gemma":0.000010005379,"teacher_disagreement_score":0.9874378,"about_ca_system_score_codex":0.00015550035,"about_ca_system_score_gemma":0.0010660833,"threshold_uncertainty_score":0.99997884},"labels":[],"label_agreement":null},{"id":"W3217467881","doi":"10.5281/zenodo.898165","title":"loli/medpy: MedPy 0.3.0 Python 3","year":2017,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Python (programming language); Computer science; Programming language","score_opus":0.03599378314495356,"score_gpt":0.30495573706866497,"score_spread":0.2689619539237114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3217467881","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13766536,0.00023096174,0.010369316,0.02784318,0.00060628576,0.0008259166,0.000060582468,0.0017149298,0.8206835],"genre_scores_gemma":[0.99059767,0.00017152123,0.0010165508,0.0008147068,0.00058495713,3.3098114e-8,0.00050222053,0.0013992956,0.0049130265],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984333,0.00013220253,0.00022145352,0.00038010904,0.00044197578,0.00039093939],"domain_scores_gemma":[0.99824625,0.000020049609,0.00014904675,0.00089446927,0.0003285386,0.00036163442],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0008709273,0.00013913566,0.0002156083,0.0001546935,0.0034803234,0.000889523,0.00090426457,0.00007159653,0.008488937],"category_scores_gemma":[0.0031467276,0.00013049314,0.00007685369,0.00012119261,0.00035096367,0.0002106282,0.0008914085,0.00054506504,0.0054408056],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017835962,0.00024308015,0.00025603053,0.00017633731,0.00012015485,0.00023172966,0.0009592831,0.000021825763,0.012681641,0.0051480606,0.3895687,0.5904148],"study_design_scores_gemma":[0.001109772,0.00019340987,0.00933494,0.00008779205,0.00003442979,0.00039584682,0.00008036832,0.0019961868,0.00042489887,0.00022034062,0.9859793,0.0001426723],"about_ca_topic_score_codex":0.00003892492,"about_ca_topic_score_gemma":1.4247487e-7,"teacher_disagreement_score":0.85293233,"about_ca_system_score_codex":0.000104167324,"about_ca_system_score_gemma":0.000006662824,"threshold_uncertainty_score":0.99781704},"labels":[],"label_agreement":null},{"id":"W3217585033","doi":"10.1007/s00261-021-03359-3","title":"A primer on texture analysis in abdominal radiology","year":2021,"lang":"es","type":"review","venue":"Abdominal Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":21,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"National Cancer Institute","keywords":"Radiogenomics; Medicine; Medical physics; Radiomics; Standardization; Workflow; Radiology; Radiological weapon; Field (mathematics); Data science; Computer science","score_opus":0.017565003669398848,"score_gpt":0.35223537758971996,"score_spread":0.3346703739203211,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3217585033","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00916548,0.9757193,0.0022205326,0.0035273824,0.002304587,0.0014326492,0.00005494902,0.00007671044,0.005498458],"genre_scores_gemma":[0.022894073,0.96302426,0.0024454538,0.0038488356,0.0036921243,0.0002527283,0.0013717787,0.00023491059,0.0022358475],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9872564,0.0042028804,0.0028987082,0.0027750079,0.0007195045,0.00214751],"domain_scores_gemma":[0.99142206,0.004335935,0.0013265142,0.0018550665,0.00021392679,0.00084652606],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow","research_integrity"],"category_scores_codex":[0.003523113,0.0017565887,0.011246727,0.0032103425,0.0002379346,0.00008138137,0.0011578348,0.002468692,0.0031625887],"category_scores_gemma":[0.004685701,0.0014363034,0.0030282298,0.0034075126,0.0013306608,0.00007778148,0.00032181598,0.00687745,0.0006239904],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008828605,0.00079850195,0.011584667,0.0037476884,0.01121814,0.013301408,0.0004798125,0.00052276184,0.00010840773,0.002296052,0.009613056,0.94544667],"study_design_scores_gemma":[0.0051343353,0.0018727671,0.010105678,0.010300996,0.028282875,0.01334922,0.0002875229,0.009983384,0.000008801018,0.00010062733,0.9187342,0.0018395985],"about_ca_topic_score_codex":0.00040959145,"about_ca_topic_score_gemma":0.00004839238,"teacher_disagreement_score":0.94360703,"about_ca_system_score_codex":0.0009691423,"about_ca_system_score_gemma":0.0015077818,"threshold_uncertainty_score":0.999518},"labels":[],"label_agreement":null},{"id":"W3217612255","doi":"10.1088/1361-6560/ac3eac","title":"Impact of image pre-processing methods on computed tomography radiomics features in chronic obstructive pulmonary disease","year":2021,"lang":"en","type":"article","venue":"Physics in Medicine and Biology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"St. Michael's Hospital; McGill University Health Centre; McGill University; University of British Columbia; Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Radiomics; Pulmonary disease; Computed tomography; Medicine; Radiology; Tomography; Image processing; Nuclear medicine; Artificial intelligence; Image (mathematics); Computer science; Internal medicine","score_opus":0.04609452963168671,"score_gpt":0.42818458186281355,"score_spread":0.38209005223112685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3217612255","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9798172,0.009889159,0.0069529554,0.0020609996,0.00015334156,0.00020103985,0.000007704005,0.000020650301,0.0008969582],"genre_scores_gemma":[0.9907299,0.00049841276,0.007820006,0.00039103322,0.00042146142,0.000007337932,0.0001028042,0.00001749337,0.0000115193],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99870336,0.00024237177,0.00032100544,0.00037058035,0.00009482939,0.00026782937],"domain_scores_gemma":[0.9991424,0.00029986637,0.0001194033,0.00020497988,0.000080797145,0.00015255272],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037486778,0.000189336,0.0006467509,0.00022885173,0.000031637373,0.0000051109905,0.00008161284,0.0000860082,0.000012565613],"category_scores_gemma":[0.00039683713,0.00013314153,0.00010044138,0.0006073297,0.00044514003,0.000044692693,0.000058562484,0.0006417707,1.6194087e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005598464,0.0003507319,0.25298208,0.00049255724,0.000111316454,0.0002996665,0.000793295,0.0004251728,0.20576677,0.0014285903,0.000107593514,0.53668237],"study_design_scores_gemma":[0.0023924112,0.00053852604,0.9439785,0.0008921579,0.00009672123,0.000086087675,0.00014726656,0.037514053,0.0011783089,0.012885218,0.00012014281,0.00017064248],"about_ca_topic_score_codex":0.00015645011,"about_ca_topic_score_gemma":0.000003579727,"teacher_disagreement_score":0.6909964,"about_ca_system_score_codex":0.00011224948,"about_ca_system_score_gemma":0.00024190442,"threshold_uncertainty_score":0.5429354},"labels":[],"label_agreement":null},{"id":"W327862399","doi":"10.1007/978-3-319-03590-1","title":"Bio-Imaging and Visualization for Patient-Customized Simulations","year":2013,"lang":"en","type":"book","venue":"Lecture notes in computational vision and biomechanics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Visualization; Computer science; Data science; Computer graphics (images); Medical physics; Artificial intelligence; Medicine","score_opus":0.008786600565870092,"score_gpt":0.3045838399610278,"score_spread":0.2957972393951577,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W327862399","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035199765,0.0017647297,0.98831916,0.0042547276,0.00036215349,0.001312897,0.00006759205,0.0000778722,0.00032086455],"genre_scores_gemma":[0.8883708,0.00045836912,0.091946825,0.009498286,0.0006566254,0.000057469286,0.0062190997,0.00021015416,0.0025823566],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987041,0.000039548097,0.00040594145,0.000377155,0.0002863951,0.00018686161],"domain_scores_gemma":[0.99844664,0.000929062,0.00018938027,0.00010240549,0.00020582609,0.00012671149],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001765683,0.00026659862,0.00042911392,0.00049938913,0.00013636363,0.00008958278,0.000045546793,0.00024301479,0.000045125926],"category_scores_gemma":[0.0004903695,0.00021990004,0.000071734605,0.00015131659,0.000074319774,0.000062700405,0.00007020816,0.0003245185,0.0000026913406],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021052343,0.00013359444,0.00015744889,0.0006646348,0.000095926385,0.000012932049,0.00050320756,0.008644861,0.0015605554,0.0076470557,0.0031480042,0.97722125],"study_design_scores_gemma":[0.0019761946,0.00016260892,0.000048374208,0.00046309622,0.000075188735,0.00004187921,0.0000058621795,0.88705933,0.000037951373,0.09245526,0.017460717,0.0002135639],"about_ca_topic_score_codex":0.000007225478,"about_ca_topic_score_gemma":0.0000018509293,"teacher_disagreement_score":0.9770077,"about_ca_system_score_codex":0.00009750465,"about_ca_system_score_gemma":0.00014900521,"threshold_uncertainty_score":0.89672637},"labels":[],"label_agreement":null},{"id":"W363173866","doi":"10.1371/journal.pone.0126817","title":"A Method for 3D Histopathology Reconstruction Supporting Mouse Microvasculature Analysis","year":2015,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Canadian Institutes of Health Research; Cancer Care Ontario; Natural Sciences and Engineering Research Council of Canada; Heart and Stroke Foundation of Canada","keywords":"Histopathology; Pathology; Biology; Medicine","score_opus":0.04906408346483134,"score_gpt":0.3172262163472931,"score_spread":0.26816213288246177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W363173866","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.75221235,0.00029046068,0.24222293,0.0038841213,0.0000840957,0.0003676482,0.0000064281635,0.000118359065,0.0008135841],"genre_scores_gemma":[0.055583976,0.00001580419,0.94081455,0.000879967,0.00031190633,0.000032736094,0.00009466109,0.000027064172,0.0022393405],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99891925,0.00007756014,0.00027921217,0.00028062877,0.00020874762,0.00023458191],"domain_scores_gemma":[0.9991318,0.00008261535,0.0001447141,0.0002372692,0.00020097292,0.000202636],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011061986,0.000103528444,0.0005063451,0.00024022194,0.00005340689,0.000013431673,0.000058668462,0.00010849112,0.00005195048],"category_scores_gemma":[0.0013368808,0.00009279808,0.0001819726,0.00027934206,0.00004748419,0.000042635,0.000022046612,0.000317922,0.0000069342796],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005968978,0.0019463162,0.20307496,0.00076909136,0.0071849353,0.00012255734,0.0025114603,0.00033344433,0.55691856,0.000307991,0.003714075,0.22251974],"study_design_scores_gemma":[0.00807182,0.00084601063,0.008315911,0.00027378026,0.027163474,0.00072281365,0.0005869907,0.9052404,0.034429017,0.0010478894,0.0126188025,0.0006830463],"about_ca_topic_score_codex":0.000047180765,"about_ca_topic_score_gemma":0.000005498831,"teacher_disagreement_score":0.904907,"about_ca_system_score_codex":0.00009586893,"about_ca_system_score_gemma":0.00007507602,"threshold_uncertainty_score":0.3784196},"labels":[],"label_agreement":null},{"id":"W37225499","doi":"10.1253/circj.cj-66-0214","title":"Evaluation of serious and unsuspected conditions detected in cancer patients undergoing FDG PET/CT","year":2010,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier de l’Université de Montréal","funders":"","keywords":"Medicine; Radiology; Medical record; Nuclear medicine","score_opus":0.011866520418323137,"score_gpt":0.3289633344658178,"score_spread":0.3170968140474947,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W37225499","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9971626,0.000040495794,0.000024802237,0.0005065783,0.00015183784,0.00027780462,0.0000034648463,0.000027176182,0.0018052337],"genre_scores_gemma":[0.9991281,0.000027746197,0.00059889467,0.00010939672,0.000025738798,0.000017675973,0.00002665654,0.000010468713,0.000055291046],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9991845,0.000053089225,0.00018423553,0.00013353028,0.00033310155,0.00011157025],"domain_scores_gemma":[0.99942565,0.00008807685,0.00006200194,0.00009344596,0.00025864952,0.00007218245],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035151176,0.00006608137,0.00013808798,0.00012413187,0.00003417313,0.0000074892628,0.000027728973,0.000010405531,0.0004739945],"category_scores_gemma":[0.0012561271,0.00005583258,0.000015743817,0.00017682224,0.00006895001,0.00004314485,0.000015567815,0.00028164397,0.0000013378037],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023486236,0.00023380839,0.926447,0.000068686546,0.000059523987,0.000024014587,0.00013000485,0.0001271736,0.044718,0.00028818203,0.00018944923,0.027690666],"study_design_scores_gemma":[0.0039304695,0.000091463226,0.9093007,0.00009580681,0.00014155309,0.000056139168,0.00007442535,0.08429251,0.0014698142,0.00041923035,0.00005586501,0.00007202208],"about_ca_topic_score_codex":0.00069865026,"about_ca_topic_score_gemma":0.0024614728,"teacher_disagreement_score":0.084165335,"about_ca_system_score_codex":0.00005097245,"about_ca_system_score_gemma":0.00020539192,"threshold_uncertainty_score":0.51899076},"labels":[],"label_agreement":null},{"id":"W372924851","doi":"10.5281/zenodo.10046","title":"feelpp v0.98.0","year":2014,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Canadian Military Institute","funders":"","keywords":"Computer science","score_opus":0.020323485841612168,"score_gpt":0.26525932361519033,"score_spread":0.24493583777357816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W372924851","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10767545,0.000086072505,0.037112575,0.0131637985,0.00025013945,0.00045552535,0.000016631415,0.0015860256,0.8396538],"genre_scores_gemma":[0.99084806,0.00004405653,0.0014049498,0.0014605258,0.00046200448,1.810767e-8,0.0005805694,0.0011556384,0.0040442017],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99867254,0.00019166095,0.000187206,0.00029772957,0.00034528188,0.00030559234],"domain_scores_gemma":[0.9989961,0.000028199504,0.000059519654,0.00037344467,0.00026353274,0.00027919962],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0008534965,0.00010613532,0.00016977022,0.00015718653,0.0010199957,0.00027196563,0.0003797137,0.000050496794,0.009796986],"category_scores_gemma":[0.0019558345,0.00009951545,0.00005680291,0.00027927544,0.00014668074,0.000086348366,0.00037884375,0.0004128131,0.007174809],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008431678,0.00017167369,0.00007777002,0.000114309725,0.000061628474,0.000029774585,0.00057323434,0.000046736986,0.013321694,0.0113108475,0.4337516,0.5404564],"study_design_scores_gemma":[0.00077732175,0.00023355734,0.00259299,0.00004344325,0.000022990798,0.0002570906,0.000056785557,0.0059745815,0.00025169042,0.00024537335,0.989438,0.00010618815],"about_ca_topic_score_codex":0.00001264529,"about_ca_topic_score_gemma":3.4426563e-8,"teacher_disagreement_score":0.8831726,"about_ca_system_score_codex":0.0000723381,"about_ca_system_score_gemma":0.00000290239,"threshold_uncertainty_score":0.9935982},"labels":[],"label_agreement":null},{"id":"W4200066891","doi":"10.1016/j.media.2021.102336","title":"Head and neck tumor segmentation in PET/CT: The HECKTOR challenge","year":2021,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":203,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency; Université de Sherbrooke","funders":"Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Segmentation; Thresholding; Artificial intelligence; Computer science; Sørensen–Dice coefficient; Modality (human–computer interaction); Leverage (statistics); Positron emission tomography; Medicine; Nuclear medicine; Medical physics; Pattern recognition (psychology); Image segmentation; Computer vision; Image (mathematics)","score_opus":0.009524723942521691,"score_gpt":0.3205935885383795,"score_spread":0.3110688645958578,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200066891","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93156624,0.0016856819,0.0022206304,0.062325645,0.00007063656,0.000111464615,0.000001940773,0.000031980544,0.0019857916],"genre_scores_gemma":[0.9880181,0.0009808907,0.003254615,0.0066135055,0.00019489079,0.000020766583,0.00007440078,0.000017983568,0.0008248326],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99817896,0.00016513202,0.0003570565,0.00034755023,0.0006884378,0.00026287153],"domain_scores_gemma":[0.99906766,0.0001981572,0.00006453217,0.00028942738,0.00007002192,0.00031019884],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008039452,0.000132149,0.00044039945,0.00017715397,0.000089789995,0.00005205758,0.00010434509,0.000014694182,0.0016453441],"category_scores_gemma":[0.001772995,0.000088381545,0.0001673589,0.00091722835,0.00020924608,0.000073295196,0.00008859398,0.0006014485,0.000021909696],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015382298,0.0019147868,0.614062,0.0005927432,0.0037786853,0.104182556,0.0028010178,0.000068242356,0.005461352,0.00069703226,0.00682184,0.2594659],"study_design_scores_gemma":[0.008366926,0.00024662854,0.45618173,0.0005669863,0.0048511545,0.0049886582,0.004218274,0.49612457,0.001195922,0.0005351261,0.022098256,0.0006257548],"about_ca_topic_score_codex":0.00031580345,"about_ca_topic_score_gemma":0.00028229112,"teacher_disagreement_score":0.49605635,"about_ca_system_score_codex":0.000047460366,"about_ca_system_score_gemma":0.00013180054,"threshold_uncertainty_score":0.9992673},"labels":[],"label_agreement":null},{"id":"W4200084039","doi":"10.1371/journal.pone.0259692","title":"Prediction of post transarterial chemoembolization MR images of hepatocellular carcinoma using spatio-temporal graph convolutional networks","year":2021,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier de l’Université de Montréal; Polytechnique Montréal","funders":"Canadian Institutes of Health Research; Nvidia","keywords":"Magnetic resonance imaging; Artificial intelligence; Computer science; Convolutional neural network; Pattern recognition (psychology); Hepatocellular carcinoma; Discriminant; Linear discriminant analysis; Graph; Dynamic contrast; Dynamic contrast-enhanced MRI; Radiology; Medicine; Internal medicine","score_opus":0.029772172624526534,"score_gpt":0.23185128813637587,"score_spread":0.20207911551184934,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200084039","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9608618,0.00038713496,0.037977826,0.00032060486,0.00012109069,0.00018568373,0.000047269823,0.000023930686,0.000074650095],"genre_scores_gemma":[0.9912229,0.00005451026,0.007445083,0.00007352337,0.00033272002,0.000003592544,0.000814047,0.000021028443,0.000032598884],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988296,0.00006199322,0.00039412524,0.00018306452,0.00038702568,0.00014416907],"domain_scores_gemma":[0.9991361,0.000031720327,0.00015838427,0.00015637827,0.00043339285,0.0000840166],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017767782,0.0001012804,0.00036932816,0.00009118977,0.00004607267,0.0000076189044,0.00004347681,0.000086990854,0.00017852975],"category_scores_gemma":[0.00014627032,0.00010587308,0.00009292574,0.00021882872,0.00013190457,0.00007141241,0.000015698748,0.00018061636,4.6053253e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012784373,0.0006345682,0.48418674,0.00034062224,0.00016186235,0.000017678794,0.0001140678,0.00039171177,0.51381123,0.000063544074,0.00002854237,0.00012155599],"study_design_scores_gemma":[0.0020266182,0.00018187823,0.117575705,0.0005272316,0.000574922,0.000035823785,0.000052014148,0.66290194,0.2159532,0.00006607161,0.000011550254,0.0000930385],"about_ca_topic_score_codex":0.00012479907,"about_ca_topic_score_gemma":0.0000016585894,"teacher_disagreement_score":0.6625102,"about_ca_system_score_codex":0.000032394168,"about_ca_system_score_gemma":0.00016132994,"threshold_uncertainty_score":0.43173787},"labels":[],"label_agreement":null},{"id":"W4200133544","doi":"10.3390/curroncol28060444","title":"Feasibility on the Use of Radiomics Features of 11[C]-MET PET/CT in Central Nervous System Tumours: Preliminary Results on Potential Grading Discrimination Using a Machine Learning Model","year":2021,"lang":"en","type":"article","venue":"Current Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine; Grading (engineering); Magnetic resonance imaging; Radiomics; Radiology; Segmentation; Machine learning; Artificial intelligence; Nuclear medicine; Computer science","score_opus":0.11476448603196414,"score_gpt":0.3761987733237885,"score_spread":0.26143428729182433,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200133544","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99477327,0.00040414638,0.001863746,0.0016227033,0.0007230817,0.00044910147,0.000039233786,0.000029833269,0.00009488947],"genre_scores_gemma":[0.997005,0.000106689615,0.0024608893,0.00006725342,0.00012693589,0.000007583213,0.00015386997,0.000028414783,0.00004339253],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99732524,0.00077080325,0.0006983683,0.00043942037,0.00039789575,0.00036829468],"domain_scores_gemma":[0.99829966,0.0006161174,0.00046322463,0.0003551022,0.00014425413,0.000121667006],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009314485,0.00021732328,0.0006396088,0.00023120113,0.000108217064,0.00001956384,0.00014650768,0.000042479678,0.000004021531],"category_scores_gemma":[0.0025751365,0.00016222494,0.00019011059,0.000277393,0.00018310346,0.00007361765,0.00010058926,0.0011183183,3.694053e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00809636,0.004206155,0.116798624,0.0020424617,0.00013362276,0.0026422169,0.003702908,0.79019856,0.017438155,0.006943233,0.00071951596,0.047078207],"study_design_scores_gemma":[0.0028940893,0.00083679036,0.043112583,0.0015079313,0.00021636064,0.0010572999,0.00063225493,0.9482217,0.0011640216,0.000052505842,0.0001683056,0.00013617237],"about_ca_topic_score_codex":0.0001934101,"about_ca_topic_score_gemma":0.000031856,"teacher_disagreement_score":0.15802313,"about_ca_system_score_codex":0.00062865217,"about_ca_system_score_gemma":0.00031727352,"threshold_uncertainty_score":0.6615341},"labels":[],"label_agreement":null},{"id":"W4200138024","doi":"10.3389/fsurg.2021.803750.s002","title":"Image_2_Oral Mucosa vs. Penile Skin Flap in Substitution Urethroplasty for Anterior Urethral Strictures: A Systematic Review and Meta-Analysis.TIF","year":2021,"lang":"en","type":"paratext","venue":"Figshare","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer vision; Computer science; Artificial intelligence","score_opus":0.03822968649892373,"score_gpt":0.34164442955816743,"score_spread":0.3034147430592437,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200138024","genre_codex":"review","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000034873487,0.8327883,0.0003169999,0.0022281404,0.00026622205,0.006539468,0.15653284,0.00006113306,0.0012320597],"genre_scores_gemma":[0.015076901,0.008699699,0.0031107585,0.0121994605,0.00089689717,0.007826417,0.89623046,0.00029222626,0.05566721],"study_design_codex":"systematic_review","study_design_gemma":"meta_analysis","domain_scores_codex":[0.99659646,0.0003555678,0.0011720504,0.00088492007,0.00050869153,0.00048231895],"domain_scores_gemma":[0.99761134,0.00040696465,0.00069945934,0.00067473185,0.00034548668,0.0002620054],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004999955,0.0006179526,0.00550084,0.00044771645,0.00011428925,0.00017285017,0.00024994882,0.00041837792,0.14350307],"category_scores_gemma":[0.005643432,0.00044821398,0.0017311102,0.0007894459,0.000038667902,0.000112238435,0.00014638547,0.0011782229,0.00045764516],"study_design_candidate":"meta_analysis","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022510674,0.00005460874,0.0000030952751,0.49625045,0.017009558,0.00017209297,0.00007706872,0.000032451167,0.000005831139,0.0000028143183,0.48634344,0.000026089281],"study_design_scores_gemma":[0.0020144559,0.00022502412,0.00016136053,0.14235134,0.72927785,0.00046327716,0.00006418622,0.006318304,0.000041397256,0.0000057141006,0.117928594,0.0011484695],"about_ca_topic_score_codex":0.000042774478,"about_ca_topic_score_gemma":0.00004201185,"teacher_disagreement_score":0.8240886,"about_ca_system_score_codex":0.00014564981,"about_ca_system_score_gemma":0.0003783355,"threshold_uncertainty_score":0.999797},"labels":[],"label_agreement":null},{"id":"W4200156550","doi":"10.3389/fsurg.2021.803750.s001","title":"Image_1_Oral Mucosa vs. Penile Skin Flap in Substitution Urethroplasty for Anterior Urethral Strictures: A Systematic Review and Meta-Analysis.TIF","year":2021,"lang":"en","type":"paratext","venue":"Figshare","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science","score_opus":0.03831653147531158,"score_gpt":0.3417103468688367,"score_spread":0.30339381539352517,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200156550","genre_codex":"review","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00003450799,0.8334233,0.00031607033,0.002240845,0.00026622007,0.006515999,0.15591893,0.00006089577,0.0012232432],"genre_scores_gemma":[0.015353546,0.008658958,0.0030731293,0.012168675,0.0008972327,0.0078044357,0.896577,0.00029140717,0.05517559],"study_design_codex":"systematic_review","study_design_gemma":"meta_analysis","domain_scores_codex":[0.9965954,0.00035575364,0.001172587,0.0008850514,0.0005087861,0.00048246115],"domain_scores_gemma":[0.9976081,0.00040689379,0.00070221117,0.00067503995,0.0003456927,0.00026202196],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005006774,0.0006180289,0.005509731,0.00044780457,0.00011319554,0.00017288892,0.00025000752,0.00041843555,0.14766446],"category_scores_gemma":[0.0056023514,0.00044825953,0.0017312259,0.0007897418,0.000038688915,0.000112242575,0.00014640758,0.0011785983,0.00045673773],"study_design_candidate":"meta_analysis","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022378495,0.00005436339,0.0000030682443,0.49373358,0.01688483,0.00017102194,0.000077283745,0.000032380536,0.0000056670547,0.000002821554,0.48898685,0.000025741],"study_design_scores_gemma":[0.0020032916,0.00022481837,0.00016161482,0.14156881,0.72816956,0.00046103192,0.00006416204,0.0060393866,0.00004108944,0.000005779899,0.12011689,0.0011435815],"about_ca_topic_score_codex":0.000043612843,"about_ca_topic_score_gemma":0.000042010914,"teacher_disagreement_score":0.8247643,"about_ca_system_score_codex":0.00014577231,"about_ca_system_score_gemma":0.0003774358,"threshold_uncertainty_score":0.9997969},"labels":[],"label_agreement":null},{"id":"W4200214032","doi":"10.18632/oncotarget.28139","title":"Radiomics in predicting recurrence for patients with locally advanced breast cancer using quantitative ultrasound","year":2021,"lang":"en","type":"article","venue":"Oncotarget","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Sunnybrook Health Science Centre; York University; University of Toronto; Toronto Metropolitan University; Health Sciences Centre","funders":"Canadian Institutes of Health Research; Terry Fox Foundation","keywords":"Medicine; Radiomics; Breast cancer; Ultrasound; Support vector machine; Radiology; Internal medicine; Artificial intelligence; Cancer; Computer science","score_opus":0.011845640291005464,"score_gpt":0.3153721325523649,"score_spread":0.3035264922613594,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200214032","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98286235,0.000464587,0.014901224,0.0007706559,0.00031551885,0.00041008444,0.000088532535,0.000027576489,0.00015945798],"genre_scores_gemma":[0.87607086,0.00016659804,0.12266741,0.00063347595,0.00013915492,0.0000392059,0.00015431184,0.00004739607,0.000081611375],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9987426,0.000046035064,0.00027360162,0.0003573724,0.00024786656,0.0003325465],"domain_scores_gemma":[0.9989824,0.00027979046,0.00012763907,0.00015874005,0.00031159777,0.00013979572],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021762795,0.0001565283,0.0003390698,0.000072960225,0.00008722505,0.000025297659,0.00006825915,0.00005708409,0.000041967694],"category_scores_gemma":[0.0007263018,0.00013333971,0.00005278446,0.00031382506,0.000084269865,0.00013817498,0.00002130078,0.0003404537,9.823783e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005845261,0.00023897867,0.9867446,0.00012952679,0.00005682992,0.00003308342,0.00045447226,0.0032545484,0.002373891,0.000107030064,0.00012558952,0.005896942],"study_design_scores_gemma":[0.011781051,0.00052778237,0.82712376,0.0026261522,0.00016523333,0.00016055065,0.0006025692,0.15296105,0.00037824528,0.00020031279,0.0030221487,0.00045116252],"about_ca_topic_score_codex":0.00010750543,"about_ca_topic_score_gemma":0.000050278726,"teacher_disagreement_score":0.15962084,"about_ca_system_score_codex":0.00023397167,"about_ca_system_score_gemma":0.00045553592,"threshold_uncertainty_score":0.54374355},"labels":[],"label_agreement":null},{"id":"W4200240386","doi":"10.1093/neuonc/noab196.525","title":"NIMG-25. IMPROVING THE NONINVASIVE CLASSIFICATION OF GLIOMA GENETIC SUBTYPE WITH DEEP LEARNING AND DIFFUSION-WEIGHTED IMAGING","year":2021,"lang":"en","type":"article","venue":"Neuro-Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Medicine; Glioma; Fluid-attenuated inversion recovery; Nuclear medicine; Artificial intelligence; Radiology; Computer science; Magnetic resonance imaging; Cancer research","score_opus":0.008333367874437536,"score_gpt":0.2677057116391958,"score_spread":0.25937234376475826,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200240386","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98439705,0.0011881563,0.004634507,0.0074436297,0.00018917891,0.00022369513,5.112154e-7,0.000046114685,0.0018771493],"genre_scores_gemma":[0.9941371,0.0003045538,0.0042267856,0.0010428774,0.0001689179,0.000012926356,0.000012217882,0.000037141766,0.000057489877],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985442,0.00028528302,0.00030059236,0.0003739682,0.00023117015,0.0002647825],"domain_scores_gemma":[0.99840665,0.00075123936,0.00025828785,0.00023706858,0.00021343512,0.00013332079],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024388403,0.00014850486,0.00033973862,0.00010091802,0.00017881309,0.000025767245,0.00009438023,0.00008104667,0.00006119392],"category_scores_gemma":[0.0009356184,0.00010075276,0.00004952346,0.0002971932,0.00031805818,0.000040368217,0.00011148067,0.00073162693,0.000004639168],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010231023,0.00007696174,0.085591905,0.00005702311,0.000028088929,0.0008112301,0.00057591306,0.000013601239,0.7398256,0.0001215874,0.00004637154,0.17274943],"study_design_scores_gemma":[0.010135545,0.0024743094,0.4177682,0.00031982124,0.0009954319,0.020009395,0.005192716,0.42536336,0.05045391,0.00025399635,0.06645593,0.0005773711],"about_ca_topic_score_codex":0.000041772564,"about_ca_topic_score_gemma":0.000016181502,"teacher_disagreement_score":0.68937165,"about_ca_system_score_codex":0.0000620281,"about_ca_system_score_gemma":0.00029921017,"threshold_uncertainty_score":0.41085783},"labels":[],"label_agreement":null},{"id":"W4200250907","doi":"10.1101/2021.12.07.21267367","title":"Diagnosis of COVID-19 Using CT image Radiomics Features: A Comprehensive Machine Learning Study Involving 26,307 Patients","year":2021,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Artificial intelligence; Coronavirus disease 2019 (COVID-19); Logistic regression; Normalization (sociology); Voxel; Pattern recognition (psychology); Univariate; Support vector machine; Computer science; Dimensionality reduction; Pneumonia; Medicine; Machine learning; Multivariate statistics; Internal medicine","score_opus":0.03275712200630746,"score_gpt":0.33260704622974385,"score_spread":0.29984992422343637,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200250907","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9889376,0.0057199514,0.0014622035,0.00080768834,0.00109603,0.0016321362,0.000036041445,0.00023616145,0.00007219845],"genre_scores_gemma":[0.9871355,0.0016795959,0.008900088,0.0011399207,0.0003232646,0.000086790635,0.00040781905,0.00023894821,0.0000880241],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99470294,0.0009975759,0.0012049271,0.001266508,0.0011826209,0.0006454293],"domain_scores_gemma":[0.9956461,0.00089436705,0.001021801,0.0010532145,0.0006100919,0.00077442854],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0011246118,0.0007571031,0.001990879,0.0006268343,0.0003334605,0.00016925043,0.00055266154,0.00025312245,0.00017777162],"category_scores_gemma":[0.00781533,0.00071713707,0.00056129624,0.0005345391,0.00033250335,0.00011286196,0.0014995214,0.0039839414,0.000004699121],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013134415,0.0013370053,0.9780128,0.0024844743,0.0008095201,0.0013673857,0.004989941,0.0059768767,0.002478453,0.000004617201,0.00029108027,0.002116491],"study_design_scores_gemma":[0.02060873,0.001439315,0.76551926,0.006723748,0.0048684035,0.00064862,0.01129138,0.17583916,0.0024419832,0.00015994057,0.0076637617,0.002795685],"about_ca_topic_score_codex":0.0032680328,"about_ca_topic_score_gemma":0.00006772671,"teacher_disagreement_score":0.21249354,"about_ca_system_score_codex":0.00056828937,"about_ca_system_score_gemma":0.0008663698,"threshold_uncertainty_score":0.999528},"labels":[],"label_agreement":null},{"id":"W4200313985","doi":"10.1101/2021.12.07.21267364","title":"COVID-19 Prognostic Modeling Using CT Radiomic Features and Machine Learning Algorithms: Analysis of a Multi-Institutional Dataset of 14,339 Patients","year":2021,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Random forest; Artificial intelligence; Feature selection; Receiver operating characteristic; Linear discriminant analysis; Pattern recognition (psychology); Computer science; Naive Bayes classifier; Machine learning; AdaBoost; Lasso (programming language); Algorithm; Support vector machine; Mathematics","score_opus":0.04512579382478547,"score_gpt":0.33875913348112036,"score_spread":0.29363333965633487,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200313985","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86887676,0.0032314314,0.12610511,0.00013607975,0.00021152514,0.0003996162,0.0009995512,0.000034064724,0.000005868793],"genre_scores_gemma":[0.94481695,0.0004794033,0.039480004,0.00022023226,0.00006828155,0.000012915436,0.014865265,0.00004015485,0.000016807373],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969719,0.00028339375,0.00092783314,0.00078059104,0.0007316598,0.00030461117],"domain_scores_gemma":[0.99785066,0.00026690905,0.000622214,0.00051099993,0.0002733846,0.0004758551],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010701761,0.00040130474,0.0014802659,0.0009200372,0.00019012352,0.00003506604,0.00024188383,0.00017085405,0.00007083764],"category_scores_gemma":[0.0069636717,0.00034276056,0.00034429028,0.0006054032,0.00037025346,0.00007118607,0.0005854895,0.0014727259,2.629885e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000056237765,0.00027538682,0.5690517,0.0013265697,0.0019877546,0.00020281733,0.00049471384,0.4245949,0.0008254833,0.0000056088575,0.000020429075,0.0011584014],"study_design_scores_gemma":[0.00182225,0.000050322007,0.03491163,0.0005639894,0.004608375,0.00012664183,0.000064318265,0.95737964,0.0000977873,0.0000074686677,0.00011394883,0.0002536072],"about_ca_topic_score_codex":0.002555739,"about_ca_topic_score_gemma":0.000043267308,"teacher_disagreement_score":0.53414005,"about_ca_system_score_codex":0.00018193632,"about_ca_system_score_gemma":0.0009395829,"threshold_uncertainty_score":0.9999024},"labels":[],"label_agreement":null},{"id":"W4200423604","doi":"10.1016/j.ijrobp.2021.11.027","title":"A Systematic Review Into the Radiologic Features Predicting Local Recurrence After Stereotactic Ablative Body Radiotherapy (SABR) in Patients With Non-Small Cell Lung Cancer (NSCLC)","year":2021,"lang":"en","type":"review","venue":"International Journal of Radiation Oncology*Biology*Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":30,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"SABR volatility model; Medicine; Ablative case; Lung cancer; Radiology; Radiation therapy; Positron emission tomography; Nuclear medicine; Radiosurgery; Medical physics; Oncology","score_opus":0.010031060772091458,"score_gpt":0.3439139418668085,"score_spread":0.33388288109471703,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200423604","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018496067,0.98586076,0.0076329964,0.00086882577,0.0016035474,0.0020732007,0.000029654731,0.000018308063,0.00006312415],"genre_scores_gemma":[0.0065270783,0.98858494,0.0011667836,0.001943916,0.0012027,0.000287957,0.00016746692,0.00007570676,0.00004345886],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.9950779,0.0015883184,0.0019210147,0.0004974603,0.00054050284,0.00037480483],"domain_scores_gemma":[0.9933644,0.0015745665,0.0036513305,0.000350484,0.0008865385,0.00017266249],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0016449864,0.00056046934,0.0032213444,0.000269867,0.00008793057,0.000061124105,0.0007583966,0.00041161955,0.0000474727],"category_scores_gemma":[0.0010037057,0.0003270056,0.00063901005,0.00046376462,0.00034749522,0.00018573864,0.00009976097,0.0026516109,0.0000034439274],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046959784,0.001024807,0.13141584,0.131171,0.007795993,0.00047508394,0.002586735,0.00031973192,0.0000020920672,0.00015465975,0.0010014864,0.723583],"study_design_scores_gemma":[0.010703018,0.002436173,0.006676252,0.9081908,0.011876986,0.0010124329,0.00016603745,0.00550567,0.0000031598,0.00012063716,0.052205697,0.0011031313],"about_ca_topic_score_codex":0.0000440526,"about_ca_topic_score_gemma":0.000005165266,"teacher_disagreement_score":0.7770198,"about_ca_system_score_codex":0.0022015693,"about_ca_system_score_gemma":0.0019250741,"threshold_uncertainty_score":0.9999182},"labels":[],"label_agreement":null},{"id":"W4200438520","doi":"10.1016/j.cmpb.2021.106609","title":"Interpretation of radiomics features–A pictorial review","year":2021,"lang":"en","type":"review","venue":"Computer Methods and Programs in Biomedicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":141,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier de l’Université de Montréal","funders":"","keywords":"Radiomics; Computer science; Digital pathology; Medical imaging; Feature (linguistics); Artificial intelligence; Pixel; Field (mathematics); Interpretation (philosophy); Feature extraction; Medical physics; Pattern recognition (psychology); Medicine; Mathematics","score_opus":0.058400778073939605,"score_gpt":0.45005488262880244,"score_spread":0.3916541045548628,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200438520","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000001257083,0.90887743,0.08758777,0.0004083196,0.0018425849,0.0011340501,0.0000028362833,0.00003230404,0.00011342008],"genre_scores_gemma":[5.419494e-7,0.67206454,0.32622185,0.00036514428,0.000900583,0.00003880068,0.00033747955,0.00003594547,0.000035118093],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.996617,0.00090920186,0.0012889134,0.00059233647,0.0003001702,0.00029237705],"domain_scores_gemma":[0.99807036,0.0006025802,0.000511681,0.00046871323,0.0001214562,0.00022520134],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0030623847,0.0004273328,0.004013694,0.00042168147,0.000025683265,0.000025169473,0.0002016333,0.00032993642,0.000019565443],"category_scores_gemma":[0.0005218811,0.0002959234,0.00042659263,0.0009992998,0.0002992819,0.00003294049,0.00018330435,0.0010922514,6.358528e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010977856,0.000092318194,0.000013730659,0.0837936,0.00019225692,0.000090892565,0.00010448458,3.847146e-8,0.000001611128,0.00011957984,0.0009636631,0.9146168],"study_design_scores_gemma":[0.0006706106,0.00035054126,0.0000114391905,0.22895192,0.0012468037,0.00083956827,0.0000054298694,0.0005873276,4.190509e-7,0.000049066894,0.7671022,0.00018470694],"about_ca_topic_score_codex":0.000019601388,"about_ca_topic_score_gemma":3.821073e-7,"teacher_disagreement_score":0.9144321,"about_ca_system_score_codex":0.00007561212,"about_ca_system_score_gemma":0.00022942256,"threshold_uncertainty_score":0.9999493},"labels":[],"label_agreement":null},{"id":"W4200446741","doi":"10.1016/j.annonc.2021.10.100","title":"82P Exploring treatment patterns and outcomes of patients with advanced lung cancer (aLC) using artificial intelligence (AI)-extracted data","year":2021,"lang":"en","type":"article","venue":"Annals of Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Health Services; University of Calgary","funders":"","keywords":"Medicine; Proportional hazards model; Retrospective cohort study; Cohort; Medical record; Lung cancer; Chart; Artificial intelligence; Emergency medicine; Internal medicine; Statistics","score_opus":0.18561029526929018,"score_gpt":0.46054737946719637,"score_spread":0.2749370841979062,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200446741","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9931811,0.00038795001,0.0029867964,0.0029912533,0.00017002538,0.00015962348,0.000060006325,0.000009223206,0.000054039672],"genre_scores_gemma":[0.99461883,0.0011798107,0.003501377,0.000516848,0.00005027192,0.000009763701,0.00009648551,0.000015375555,0.000011253878],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9989683,0.00005695851,0.00035048567,0.0002676185,0.0001650163,0.00019161869],"domain_scores_gemma":[0.9990143,0.00015255502,0.00019501941,0.0003064931,0.00023497708,0.00009663846],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001437079,0.000117298594,0.00049776916,0.0000708955,0.00003464104,0.0000054920424,0.000083252904,0.000049025755,0.000063503874],"category_scores_gemma":[0.0002401485,0.00008753269,0.00003519616,0.000108729124,0.00010108695,0.00013749363,0.00009187621,0.00014720882,1.8334879e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018291142,0.0004562673,0.5875245,0.00007933971,0.00021574677,0.0000488076,0.00031306414,0.0002100923,0.0008827034,0.00007872856,0.000010423797,0.40999746],"study_design_scores_gemma":[0.0017427539,0.002035865,0.95278996,0.0005101077,0.00047120664,0.000021870466,0.0006099201,0.022311583,0.016485037,0.00010052787,0.0027019538,0.00021919214],"about_ca_topic_score_codex":0.00050925725,"about_ca_topic_score_gemma":0.00013931349,"teacher_disagreement_score":0.40977827,"about_ca_system_score_codex":0.000040871528,"about_ca_system_score_gemma":0.00023205226,"threshold_uncertainty_score":0.35694793},"labels":[],"label_agreement":null},{"id":"W4200579708","doi":"10.1080/24699322.2021.1994014","title":"Radiomics in surgical oncology: applications and challenges","year":2021,"lang":"en","type":"review","venue":"Computer Assisted Surgery","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"National Cancer Institute","keywords":"Radiomics; Medicine; Neoadjuvant therapy; Clinical trial; Oncology; Precision medicine; Personalized medicine; Adjuvant; Medical physics; Internal medicine; Cancer; Radiology; Bioinformatics; Pathology; Breast cancer","score_opus":0.09936091144498894,"score_gpt":0.37434767200648217,"score_spread":0.27498676056149324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200579708","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000055477135,0.99560714,0.0009232841,0.0011050759,0.00037380544,0.0004598626,0.0000044623553,0.00007384493,0.0014469763],"genre_scores_gemma":[0.000003918492,0.9944999,0.0037795394,0.0001712728,0.00095915305,0.0001633976,0.00029385273,0.00006154824,0.00006738247],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975192,0.00045926453,0.0008246093,0.0006617221,0.00019562419,0.0003395839],"domain_scores_gemma":[0.99648345,0.0024986065,0.00024362913,0.00043853483,0.000052227268,0.000283572],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009888068,0.0003526167,0.00316681,0.0005055971,0.00005545735,0.000044234886,0.000118218086,0.00048172605,0.00001954116],"category_scores_gemma":[0.000076846234,0.0003006857,0.00052901695,0.00041583204,0.00014589497,0.000030882627,0.00017041499,0.0011803621,0.000011296485],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000029667067,0.00017223619,0.000050955827,0.0093101645,0.00015819482,0.0016807237,0.000020168356,4.4108714e-7,1.9753607e-8,0.00013986205,0.0010261666,0.9874381],"study_design_scores_gemma":[0.00025354055,0.000018510666,0.0001224641,0.011500144,0.0003388886,0.005122495,0.000007017449,0.00040946272,1.3912853e-8,0.0000059199474,0.9819722,0.00024930175],"about_ca_topic_score_codex":0.000004643055,"about_ca_topic_score_gemma":0.0000011903594,"teacher_disagreement_score":0.9871888,"about_ca_system_score_codex":0.00022105698,"about_ca_system_score_gemma":0.00076385133,"threshold_uncertainty_score":0.9999445},"labels":[],"label_agreement":null},{"id":"W4205108661","doi":"10.1007/978-3-030-79956-4_8","title":"Examples of Published Research Studies in Medical Imaging: A Selected Review","year":2021,"lang":"en","type":"review","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Burnaby Hospital","funders":"","keywords":"Medical research; Focus (optics); Research design; Management science; Computer science; Data science; Engineering ethics; Medical physics; Medicine; Engineering; Pathology; Sociology; Social science","score_opus":0.19436299149494682,"score_gpt":0.5325949804967741,"score_spread":0.33823198900182727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205108661","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000016932552,0.98854285,0.000022871538,0.0059379907,0.0002115642,0.001050803,0.000002361278,0.000052390358,0.00417746],"genre_scores_gemma":[0.0000025229842,0.9963586,0.0008924515,0.0008237192,0.00021734713,0.00016030062,0.00021699478,0.00007184726,0.0012562239],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99292856,0.0017332854,0.001823386,0.00079151185,0.0020792375,0.00064400735],"domain_scores_gemma":[0.9940906,0.002858157,0.00031867565,0.000839236,0.0014837476,0.00040957096],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01030266,0.00038931746,0.00533215,0.0009002375,0.000049694485,0.000031563657,0.0005038331,0.0002602146,0.0019735377],"category_scores_gemma":[0.0753488,0.00025297387,0.0004659075,0.003928513,0.00066479854,0.00007124487,0.0004834105,0.0036116878,0.000018375722],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000016170277,0.00012751103,0.00006890801,0.2029027,0.00025213897,0.00075958425,0.000038674087,7.381542e-9,2.0265797e-7,0.00021092509,0.1024428,0.6931949],"study_design_scores_gemma":[0.0002734374,0.000023627712,0.0000065845907,0.34593642,0.00039444756,0.0006899324,0.000058821388,0.00003729653,1.7552867e-7,0.000018384539,0.6524329,0.00012792976],"about_ca_topic_score_codex":0.00019268505,"about_ca_topic_score_gemma":0.00001599684,"teacher_disagreement_score":0.693067,"about_ca_system_score_codex":0.0002611147,"about_ca_system_score_gemma":0.0036637974,"threshold_uncertainty_score":0.99999225},"labels":[],"label_agreement":null},{"id":"W4205170083","doi":"10.1017/cjn.2021.342","title":"P.062 Does the intensity of brain parenchymal contrast staining on post-recanalization dual energy head CT (DECT) of stroke patients predict the fate of brain tissue?","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Neurological Sciences / Journal Canadien des Sciences Neurologiques","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Parenchyma; Staining; Medicine; Iodine; Brain infarction; Superior sagittal sinus; Nuclear medicine; Stroke (engine); Radiology; Contrast (vision); Infarction; Pathology; Ischemia; Myocardial infarction; Cardiology; Internal medicine; Chemistry","score_opus":0.016863164699746924,"score_gpt":0.2788432907763376,"score_spread":0.2619801260765907,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205170083","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.971223,0.0003970004,0.000104505,0.027026583,0.0006207283,0.000118747266,0.000039330986,0.000004998584,0.00046512714],"genre_scores_gemma":[0.99196255,0.00013481446,0.00022265452,0.0074851285,0.00014999199,0.0000010089392,0.0000017661499,0.000008625615,0.000033440636],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99540657,0.0013414499,0.0010821152,0.00034680602,0.0011080103,0.00071507593],"domain_scores_gemma":[0.9947153,0.0018227346,0.0012579246,0.0001914449,0.0012167149,0.00079588365],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.004372563,0.00023208043,0.0006472601,0.00044159224,0.0009450634,0.00013550057,0.0009597091,0.000084652806,0.00009678133],"category_scores_gemma":[0.012094978,0.00011003714,0.00022693325,0.0008624887,0.0060989615,0.0002578733,0.00007594288,0.0010345203,1.4492866e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030476466,0.00010455901,0.9691602,0.000023521177,0.00006689384,0.0020509176,0.0008882068,0.005152484,0.0016560926,0.0013269171,0.0009659699,0.018299483],"study_design_scores_gemma":[0.0013891355,0.079591386,0.8818606,0.00032008535,0.00017208794,0.012099575,0.0017097688,0.009017352,0.0052715163,0.0034831997,0.004778887,0.00030642346],"about_ca_topic_score_codex":0.005650696,"about_ca_topic_score_gemma":0.04327529,"teacher_disagreement_score":0.08729961,"about_ca_system_score_codex":0.000098140095,"about_ca_system_score_gemma":0.0030375733,"threshold_uncertainty_score":0.9966059},"labels":[],"label_agreement":null},{"id":"W4205261476","doi":"10.1017/cjn.2021.264","title":"A.2 Clinical application of T1-w/T2-w ratio images for in vivo comparisons of myelin content in patients with trigeminal neuralgia","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Neurological Sciences / Journal Canadien des Sciences Neurologiques","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Systems, Applications & Products in Data Processing (Canada); Toronto Public Health","funders":"","keywords":"Trigeminal neuralgia; Multiple sclerosis; Myelin; Magnetic resonance imaging; White matter; In vivo; Medicine; Nuclear medicine; Pathology; Radiology; Internal medicine; Surgery; Biology; Central nervous system","score_opus":0.04224569277869435,"score_gpt":0.32694710807279076,"score_spread":0.2847014152940964,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205261476","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9947331,0.00037618945,0.0005663955,0.003588194,0.00024267905,0.00025661362,0.000012573168,0.0000031798527,0.00022105493],"genre_scores_gemma":[0.9922245,0.000113516646,0.006464291,0.0011003095,0.00007658078,0.000003180626,8.908706e-7,0.0000070718315,0.000009666744],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99648833,0.0006082353,0.001367476,0.00037343206,0.00055259507,0.0006098999],"domain_scores_gemma":[0.9965437,0.0008675627,0.0009448935,0.00011922962,0.0007602693,0.00076433865],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0040376526,0.00017784593,0.0007577904,0.0006367093,0.00028682945,0.00007879518,0.00061435654,0.00011670273,0.000035182118],"category_scores_gemma":[0.004271386,0.00011569351,0.0001812252,0.0009773661,0.0035359883,0.00024857157,0.00002972057,0.0010025193,1.3032215e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003378026,0.00013017931,0.9923478,0.000019941268,0.00000940804,0.00051030837,0.000086761545,0.0017295609,0.00017280535,0.00018826491,0.00021890932,0.0042482647],"study_design_scores_gemma":[0.0016299689,0.029925492,0.95981544,0.00011100857,0.000040470204,0.0011845462,0.00016915637,0.0056241746,0.0003200319,0.000589757,0.0004721094,0.00011784539],"about_ca_topic_score_codex":0.001264488,"about_ca_topic_score_gemma":0.01685032,"teacher_disagreement_score":0.032532353,"about_ca_system_score_codex":0.00010211208,"about_ca_system_score_gemma":0.0025484567,"threshold_uncertainty_score":0.9991758},"labels":[],"label_agreement":null},{"id":"W4205327116","doi":"10.32920/16814995","title":"No-Reference Image Quality Assessment Of Large FLAIR MRI Datasets","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph; Toronto Metropolitan University","funders":"","keywords":"Fluid-attenuated inversion recovery; Artifact (error); Outlier; Image quality; Computer science; Artificial intelligence; Pattern recognition (psychology); Noise (video); Contrast (vision); Scanner; Computer vision; Medicine; Magnetic resonance imaging; Image (mathematics); Radiology","score_opus":0.03642563654566433,"score_gpt":0.4226185302078891,"score_spread":0.38619289366222476,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205327116","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27043626,0.0009948486,0.3543668,0.01431915,0.0031381191,0.0019393407,0.0033107228,0.00047544503,0.35101932],"genre_scores_gemma":[0.69798416,0.0008286306,0.26996887,0.003174308,0.0004646104,0.000048378697,0.02293353,0.00007564536,0.0045218654],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9971633,0.00024707103,0.00078531104,0.00070432393,0.00074356154,0.00035641468],"domain_scores_gemma":[0.997505,0.0001693151,0.0003625481,0.0013602793,0.00033330478,0.000269548],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0016546042,0.00030275565,0.0010108504,0.000101684695,0.000051676925,0.00006502784,0.00034721516,0.0002576442,0.0031154763],"category_scores_gemma":[0.00086407166,0.00024911785,0.0002229212,0.00009948178,0.000127551,0.000065189066,0.0013137572,0.0020597724,0.000030900006],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003811942,0.009548396,0.2209239,0.03967157,0.0042739073,0.0024463714,0.0011220066,0.00048652568,0.13391012,0.030313808,0.5250536,0.031868573],"study_design_scores_gemma":[0.008552988,0.00043866213,0.48123983,0.0057890937,0.0013265613,0.0001448252,0.00088194205,0.183847,0.0041621984,0.0007792031,0.3107702,0.0020674889],"about_ca_topic_score_codex":0.00089777977,"about_ca_topic_score_gemma":0.000033849046,"teacher_disagreement_score":0.42754793,"about_ca_system_score_codex":0.00010196784,"about_ca_system_score_gemma":0.00078385905,"threshold_uncertainty_score":0.9999961},"labels":[],"label_agreement":null},{"id":"W4205334579","doi":"10.1016/j.compbiomed.2022.105230","title":"Impact of feature harmonization on radiogenomics analysis: Prediction of EGFR and KRAS mutations from non-small cell lung cancer PET/CT images","year":2022,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":88,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; BC Cancer Agency","funders":"BC Cancer Foundation; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Radiogenomics; KRAS; Feature (linguistics); Lung cancer; Cancer; Harmonization; Computer science; Computational biology; Medicine; Artificial intelligence; Radiomics; Oncology; Biology; Internal medicine; Colorectal cancer","score_opus":0.007789998847016184,"score_gpt":0.3044521610248692,"score_spread":0.296662162177853,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205334579","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98426366,0.0035848687,0.010278791,0.001251831,0.00024410995,0.00019675119,0.000097767974,0.000009804555,0.000072410774],"genre_scores_gemma":[0.9953913,0.0013304396,0.0023735263,0.0002601083,0.00010444352,0.000010818976,0.00049824704,0.000008241612,0.000022847868],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9992289,0.00009469049,0.00025129106,0.00023369648,0.00007750058,0.00011389957],"domain_scores_gemma":[0.99939203,0.00020394046,0.0001681835,0.00012130097,0.000039222974,0.000075300544],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025959653,0.00011018717,0.00044449457,0.0003854337,0.00006800204,0.0000019543827,0.000060999188,0.00002023253,0.00003983577],"category_scores_gemma":[0.000056012654,0.0000849457,0.000055600784,0.00034958211,0.00022105721,0.000016198903,0.00004833399,0.00032502288,3.1549522e-8],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014071573,0.000090941954,0.9712985,0.00006710229,0.0005165854,0.000043329364,0.00089990906,0.0077302936,0.01419032,0.000031497013,0.0009573765,0.0040333844],"study_design_scores_gemma":[0.0028716428,0.0007819758,0.76575094,0.00013628621,0.0008588169,0.00006158056,0.00020347768,0.22886795,0.00021607558,0.00010129786,0.00008210022,0.00006783996],"about_ca_topic_score_codex":0.00087341614,"about_ca_topic_score_gemma":0.0000060190096,"teacher_disagreement_score":0.22113766,"about_ca_system_score_codex":0.00007841958,"about_ca_system_score_gemma":0.000061783816,"threshold_uncertainty_score":0.3463985},"labels":[],"label_agreement":null},{"id":"W4205515013","doi":"10.7759/cureus.21347","title":"Deep Learning Model With Convolutional Neural Network for Detecting and Segmenting Hepatocellular Carcinoma in CT: A Preliminary Study","year":2022,"lang":"en","type":"article","venue":"Cureus","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Medicine; Hepatocellular carcinoma; Convolutional neural network; Artificial intelligence; Radiology; Segmentation; Deep learning; Pattern recognition (psychology); Internal medicine; Computer science","score_opus":0.016343005782572466,"score_gpt":0.26002548833912537,"score_spread":0.2436824825565529,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205515013","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98638135,0.0015560765,0.010920395,0.0002321474,0.000075825774,0.0007315081,8.422249e-7,0.000044774697,0.000057078734],"genre_scores_gemma":[0.9938483,0.0000034088953,0.0054727774,0.00016872458,0.00013332898,0.00020107916,0.000024036908,0.000035684458,0.00011264449],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987946,0.00009609115,0.00021602136,0.0003139349,0.0002414742,0.00033783435],"domain_scores_gemma":[0.99953014,0.00014488255,0.00009200171,0.00011083681,0.000029479857,0.000092685834],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007128526,0.00012936747,0.0002367117,0.000059578328,0.00047418883,0.000020310996,0.000070916925,0.00001525299,0.000012956058],"category_scores_gemma":[0.00015764184,0.00012155376,0.00003658004,0.00014781396,0.000040334442,0.00005282615,0.0001499008,0.00066979195,1.8213558e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022198004,0.00009916485,0.6679176,0.000035936187,0.00002669279,0.00016425758,0.0010494764,0.32796633,0.00010048717,0.000021862505,0.000019313406,0.0023768537],"study_design_scores_gemma":[0.002512631,0.0012596198,0.060638975,0.000028918881,0.00008578734,0.00033667314,0.0023502677,0.93250334,0.0000039827996,0.00006813878,0.00008997166,0.00012170061],"about_ca_topic_score_codex":0.00011123503,"about_ca_topic_score_gemma":0.000013298696,"teacher_disagreement_score":0.60727865,"about_ca_system_score_codex":0.00010760801,"about_ca_system_score_gemma":0.000054662738,"threshold_uncertainty_score":0.49568185},"labels":[],"label_agreement":null},{"id":"W4205601010","doi":"10.1002/path.5864","title":"Computer‐extracted features of nuclear morphology in hematoxylin and eosin images distinguish <scp>s</scp>tage <scp>II</scp> and <scp>IV</scp> colon tumors","year":2022,"lang":"en","type":"article","venue":"The Journal of Pathology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Center for Advancing Translational Sciences; National Center for Research Resources; National Institute of Biomedical Imaging and Bioengineering; National Cancer Institute; National Heart, Lung, and Blood Institute; U.S. Department of Veterans Affairs","keywords":"Colorectal cancer; H&E stain; Artificial intelligence; Stage (stratigraphy); Digital pathology; Medicine; Random forest; Convolutional neural network; Cancer; Pathology; Oncology; Internal medicine; Computer science; Immunohistochemistry; Biology","score_opus":0.007140593702023906,"score_gpt":0.2551362489681132,"score_spread":0.2479956552660893,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205601010","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99317914,0.0036388815,0.00025367376,0.0015125829,0.00047464398,0.00027656052,0.000023840166,0.000032639327,0.0006080208],"genre_scores_gemma":[0.99385214,0.0005583507,0.0031990958,0.001609276,0.00033095677,0.000004783391,0.000013490719,0.0000638481,0.00036806863],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99674004,0.0009919029,0.0009333708,0.00033210046,0.00044318437,0.00055941305],"domain_scores_gemma":[0.9951561,0.0030504134,0.0010684727,0.00030556894,0.00016061874,0.00025884397],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0029816986,0.00030844624,0.0011059081,0.00047020672,0.00035688604,0.00003094784,0.0004160582,0.00017461152,0.000010900551],"category_scores_gemma":[0.00562584,0.00023759382,0.00013221757,0.00034375023,0.0008598681,0.000086152046,0.0005531447,0.0024576944,0.0000016070541],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029132178,0.0022089789,0.16260251,0.000891648,0.00057292456,0.0360606,0.055925526,0.0018256813,0.5995544,0.0017865641,0.12642547,0.01185433],"study_design_scores_gemma":[0.0068199174,0.004503528,0.8484898,0.0004162976,0.0004884029,0.106364146,0.009172613,0.0052092955,0.0023792356,0.001471592,0.014593917,0.000091244976],"about_ca_topic_score_codex":0.00006947344,"about_ca_topic_score_gemma":0.000005101628,"teacher_disagreement_score":0.6858873,"about_ca_system_score_codex":0.00007160954,"about_ca_system_score_gemma":0.00011416182,"threshold_uncertainty_score":0.99984366},"labels":[],"label_agreement":null},{"id":"W4205733409","doi":"10.1017/cjn.2021.433","title":"P.157 Frame-based stereotactic brain biopsy: A retrospective review of diagnostic yield and complications at a Canadian Center","year":2021,"lang":"en","type":"review","venue":"Canadian Journal of Neurological Sciences / Journal Canadien des Sciences Neurologiques","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Systems, Applications & Products in Data Processing (Canada); Toronto Public Health","funders":"","keywords":"Medicine; Biopsy; Neuroimaging; Radiology; Retrospective cohort study; Stereotactic biopsy; Brain biopsy; Single Center; Surgery","score_opus":0.04993242118221124,"score_gpt":0.3392843318708942,"score_spread":0.28935191068868293,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205733409","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0393386,0.9408999,0.000013031647,0.0174553,0.00055559864,0.0004912386,0.00007955787,0.00000966861,0.0011570983],"genre_scores_gemma":[0.021405835,0.9620489,0.0010798511,0.015186958,0.00020855307,0.000009779725,0.000006053622,0.000027775824,0.000026309635],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99444133,0.0011797927,0.0015565779,0.00074696244,0.0008356915,0.0012396273],"domain_scores_gemma":[0.9896976,0.0038350783,0.0016741888,0.00029755934,0.00069555826,0.0038000247],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity"],"consensus_categories":["sts"],"category_scores_codex":[0.0042577246,0.0005214592,0.0022399551,0.0014802105,0.0016031633,0.000334149,0.0012981838,0.00033580902,0.00034505007],"category_scores_gemma":[0.032332946,0.00034472533,0.00067122333,0.0017786771,0.005984235,0.00026278052,0.00009258949,0.0026712343,0.0000026464845],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043708365,0.00022587285,0.6858517,0.014961146,0.00036912743,0.055640057,0.00029231785,0.00007411485,0.0000029245973,0.0008542696,0.014047883,0.22763687],"study_design_scores_gemma":[0.00048267518,0.025124779,0.023243768,0.05972982,0.001079417,0.22639383,0.00003979581,0.0002917515,9.359098e-7,0.0006186044,0.6622547,0.0007399416],"about_ca_topic_score_codex":0.013105504,"about_ca_topic_score_gemma":0.12399547,"teacher_disagreement_score":0.66260797,"about_ca_system_score_codex":0.00090175,"about_ca_system_score_gemma":0.014804589,"threshold_uncertainty_score":0.99990046},"labels":[],"label_agreement":null},{"id":"W4205748458","doi":"10.1017/cjn.2021.329","title":"P.048 International MAGNIMS-CMSC-NAIMS consensus recommendations on the use of standardized MRI in MS","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Neurological Sciences / Journal Canadien des Sciences Neurologiques","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Systems, Applications & Products in Data Processing (Canada); Toronto Public Health; Vancouver Biotech (Canada)","funders":"","keywords":"Medicine; Protocol (science); Multiple sclerosis; Magnetic resonance imaging; Clinical Practice; Medical physics; Radiology; Physical therapy; Alternative medicine; Psychiatry; Pathology","score_opus":0.06439382662675376,"score_gpt":0.3223580542524027,"score_spread":0.25796422762564897,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205748458","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8750023,0.0001976888,0.0000544611,0.121234156,0.00095019554,0.00009755952,0.000015018077,0.000005719065,0.0024428726],"genre_scores_gemma":[0.98206145,0.0006934074,0.00599557,0.0110124145,0.00017069561,0.000001388069,7.5389903e-7,0.000007959294,0.000056384426],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9963571,0.0009983731,0.00085979357,0.00033996312,0.0007830015,0.00066176883],"domain_scores_gemma":[0.9960819,0.0017097882,0.0005760847,0.0001481491,0.00060188916,0.0008821739],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.003995287,0.00018822766,0.00043590378,0.00069335493,0.00086476764,0.00039117812,0.0008541537,0.00010308691,0.0005226097],"category_scores_gemma":[0.010449051,0.00011038656,0.00020590644,0.0010776757,0.0042282827,0.0002864733,0.000055071716,0.0015806712,0.000001314162],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023203186,0.00010383739,0.95504975,0.000008478704,0.000044414515,0.0107933525,0.0004665663,0.007490974,0.00026830754,0.004388785,0.011297243,0.009856229],"study_design_scores_gemma":[0.003087444,0.057833426,0.5464075,0.00071995554,0.0001661483,0.085319646,0.001343603,0.038031373,0.0007627249,0.021099271,0.24448924,0.00073962886],"about_ca_topic_score_codex":0.00092719623,"about_ca_topic_score_gemma":0.017284842,"teacher_disagreement_score":0.40864223,"about_ca_system_score_codex":0.00019683295,"about_ca_system_score_gemma":0.0034873267,"threshold_uncertainty_score":0.99848163},"labels":[],"label_agreement":null},{"id":"W4205914284","doi":"10.1016/j.cbpa.2021.102111","title":"Extendable and explainable deep learning for pan-cancer radiogenomics research","year":2022,"lang":"en","type":"review","venue":"Current Opinion in Chemical Biology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":26,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"CancerCare Manitoba Foundation; Manitoba Medical Service Foundation","keywords":"Radiogenomics; Deep learning; Radiomics; Genomics; Artificial intelligence; Precision medicine; Computer science; Field (mathematics); Data science; Computational biology; Medicine; Genome; Biology; Pathology; Genetics; Mathematics; Gene","score_opus":0.21979121707928465,"score_gpt":0.5104612478471682,"score_spread":0.29067003076788356,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205914284","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00006205063,0.9960304,0.0003342196,0.0002117153,0.002064935,0.0011355741,0.000018868894,0.000035093766,0.00010718132],"genre_scores_gemma":[0.00002154351,0.99527895,0.0007452489,0.000020235273,0.0012767547,0.0015132285,0.0009940952,0.00006843725,0.00008149169],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99719024,0.0004012156,0.0006557207,0.00082473084,0.00018610877,0.0007420149],"domain_scores_gemma":[0.9975507,0.0017434206,0.00019368781,0.00024816644,0.000058936334,0.0002050387],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0016542829,0.0003181111,0.0014914112,0.00041989493,0.00018652959,0.000025666788,0.00027012816,0.00034134858,0.00023761127],"category_scores_gemma":[0.0019108289,0.00026768722,0.00025275516,0.0004187082,0.00032619506,0.0000271079,0.00039450795,0.0031313794,0.0000062570202],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038038004,0.0000890816,0.00017817253,0.016691009,0.000041824944,0.000001500807,0.00005247273,0.0000016393349,0.000044493678,0.00057280494,0.00092745334,0.9813615],"study_design_scores_gemma":[0.00080278976,0.00014558139,0.0000022301735,0.0048827385,0.000084704305,0.000070931426,0.000036912697,0.001072867,0.0000037785856,0.0005096543,0.99214035,0.00024748518],"about_ca_topic_score_codex":0.000019985102,"about_ca_topic_score_gemma":1.2976422e-7,"teacher_disagreement_score":0.99121284,"about_ca_system_score_codex":0.00049971265,"about_ca_system_score_gemma":0.0003203034,"threshold_uncertainty_score":0.9999775},"labels":[],"label_agreement":null},{"id":"W4205917292","doi":"10.3389/fimmu.2021.773581","title":"Radiomics Assessment of the Tumor Immune Microenvironment to Predict Outcomes in Breast Cancer","year":2022,"lang":"en","type":"article","venue":"Frontiers in Immunology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":53,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"High-level Hospital Construction Project of Guangdong Provincial People's Hospital; China Postdoctoral Science Foundation; National Natural Science Foundation of China; University of Alberta; National Science Foundation","keywords":"Radiomics; Tumor microenvironment; Breast cancer; Medicine; Immune system; Oncology; Cancer; Internal medicine; Cancer research; Immunology","score_opus":0.004071311478104318,"score_gpt":0.2553336789073992,"score_spread":0.2512623674292949,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205917292","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97495687,0.001455485,0.00071952573,0.01987105,0.0022789135,0.0005213621,0.000038625032,0.000011135097,0.0001470114],"genre_scores_gemma":[0.9926166,0.00023232172,0.004879498,0.001627087,0.000024347955,0.00019198966,0.000008761326,0.000025092942,0.00039429386],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9985546,0.00020346786,0.00044783115,0.00024346376,0.00023352826,0.00031710748],"domain_scores_gemma":[0.9993875,0.00003415471,0.00013576384,0.00039169224,0.000009496424,0.00004137147],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004588843,0.00013237448,0.00051930203,0.00027549444,0.0000731997,0.0000037028817,0.0003584512,0.000037169455,0.00016356846],"category_scores_gemma":[0.000050766987,0.000104326136,0.00010030215,0.0003118963,0.00018220283,0.000021622365,0.0003873122,0.0008433648,5.784924e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014439395,0.0002755614,0.9763746,0.000018552855,0.000118850905,0.00003199365,0.00035300895,0.0032683387,0.0119284,0.000050212315,0.0018413089,0.005594749],"study_design_scores_gemma":[0.0021345338,0.00010643908,0.9846878,0.000056514215,0.000030743384,0.00010740906,0.00064732874,0.004759426,0.00015445157,0.000052925818,0.0071714954,0.000090907226],"about_ca_topic_score_codex":0.0006259848,"about_ca_topic_score_gemma":0.000007712547,"teacher_disagreement_score":0.018243963,"about_ca_system_score_codex":0.0009060039,"about_ca_system_score_gemma":0.00018044135,"threshold_uncertainty_score":0.42542964},"labels":[],"label_agreement":null},{"id":"W4206115253","doi":"10.1007/s00261-021-03385-1","title":"Correction to: A new proposal for secondary surveillance following potentially curative therapy of HCC: alternating MRI and CEUS","year":2022,"lang":"en","type":"erratum","venue":"Abdominal Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Foothills Medical Centre; University of Calgary","funders":"","keywords":"Hepatology; Medicine; Internal medicine; General surgery; Radiology; Medical physics","score_opus":0.009202725475252874,"score_gpt":0.3043491431084006,"score_spread":0.29514641763314775,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206115253","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12882811,0.042378575,0.3685545,0.045146473,0.37043115,0.010248735,0.00023319527,0.00040229651,0.03377697],"genre_scores_gemma":[0.15364332,0.014804437,0.30310428,0.015250046,0.027057925,0.0011266625,0.0049551665,0.0010935136,0.47896463],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978812,0.00024494104,0.0005606759,0.00061994814,0.00028363688,0.0004096125],"domain_scores_gemma":[0.99835116,0.00064607634,0.00043308805,0.00024594303,0.000099850055,0.00022390072],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008940516,0.00032854622,0.0011819281,0.0002600611,0.00017591633,0.000021768494,0.0002094189,0.00022277379,0.0001778063],"category_scores_gemma":[0.0014875503,0.00029503228,0.00029793874,0.00015755622,0.00012345228,0.00004827737,0.000104037405,0.0015596527,0.0000012585049],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014136808,0.00004960618,0.0010340034,0.00014706411,0.00056725426,0.00014455612,0.0011018086,0.00010442845,0.003957946,0.00006286361,0.72518724,0.2662295],"study_design_scores_gemma":[0.0076171504,0.006261919,0.005466533,0.0006757184,0.00025058392,0.00249041,0.00054929155,0.017325392,0.00018679223,0.0008349193,0.95764625,0.00069502165],"about_ca_topic_score_codex":0.0007103856,"about_ca_topic_score_gemma":0.000056945715,"teacher_disagreement_score":0.44518766,"about_ca_system_score_codex":0.00013366493,"about_ca_system_score_gemma":0.0014410384,"threshold_uncertainty_score":0.9999502},"labels":[],"label_agreement":null},{"id":"W4206137264","doi":"10.32920/16814995.v1","title":"No-Reference Image Quality Assessment Of Large FLAIR MRI Datasets","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph; Toronto Metropolitan University","funders":"","keywords":"Fluid-attenuated inversion recovery; Artifact (error); Outlier; Image quality; Computer science; Artificial intelligence; Pattern recognition (psychology); Contrast (vision); Noise (video); Computer vision; Medicine; Magnetic resonance imaging; Image (mathematics); Radiology","score_opus":0.03642563654566433,"score_gpt":0.4226185302078891,"score_spread":0.38619289366222476,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206137264","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27043626,0.0009948486,0.3543668,0.01431915,0.0031381191,0.0019393407,0.0033107228,0.00047544503,0.35101932],"genre_scores_gemma":[0.69798416,0.0008286306,0.26996887,0.003174308,0.0004646104,0.000048378697,0.02293353,0.00007564536,0.0045218654],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9971633,0.00024707103,0.00078531104,0.00070432393,0.00074356154,0.00035641468],"domain_scores_gemma":[0.997505,0.0001693151,0.0003625481,0.0013602793,0.00033330478,0.000269548],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0016546042,0.00030275565,0.0010108504,0.000101684695,0.000051676925,0.00006502784,0.00034721516,0.0002576442,0.0031154763],"category_scores_gemma":[0.00086407166,0.00024911785,0.0002229212,0.00009948178,0.000127551,0.000065189066,0.0013137572,0.0020597724,0.000030900006],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003811942,0.009548396,0.2209239,0.03967157,0.0042739073,0.0024463714,0.0011220066,0.00048652568,0.13391012,0.030313808,0.5250536,0.031868573],"study_design_scores_gemma":[0.008552988,0.00043866213,0.48123983,0.0057890937,0.0013265613,0.0001448252,0.00088194205,0.183847,0.0041621984,0.0007792031,0.3107702,0.0020674889],"about_ca_topic_score_codex":0.00089777977,"about_ca_topic_score_gemma":0.000033849046,"teacher_disagreement_score":0.42754793,"about_ca_system_score_codex":0.00010196784,"about_ca_system_score_gemma":0.00078385905,"threshold_uncertainty_score":0.9999961},"labels":[],"label_agreement":null},{"id":"W4206159629","doi":"10.7287/peerj-cs.464v0.1/reviews/1","title":"Peer Review #1 of \"Optimal 1-NN prototypes for pathological geometries (v0.1)\"","year":2021,"lang":"en","type":"peer-review","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Pathological; Computer science; Medicine; Internal medicine","score_opus":0.04970064856412533,"score_gpt":0.39273608527332776,"score_spread":0.34303543670920245,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206159629","genre_codex":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000010122471,0.5025566,0.003347601,0.47009313,0.00079608057,0.0036825468,0.00016672278,0.000070387025,0.019276796],"genre_scores_gemma":[0.0000072611774,0.27327824,0.022601923,0.038214926,0.00076134637,0.00065825996,0.004174204,0.00006920849,0.66023463],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99611205,0.00011034959,0.001109564,0.0006562064,0.0015851891,0.00042666236],"domain_scores_gemma":[0.9945554,0.000448527,0.00046509903,0.00067130977,0.0036201396,0.00023953986],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0036828385,0.00043459365,0.002568048,0.00017271067,0.000057814857,0.000022596438,0.0002998133,0.0003404372,0.0051727435],"category_scores_gemma":[0.04296893,0.0002872556,0.0009005157,0.00047612062,0.00022862028,0.000033384247,0.0001693645,0.0011985824,0.000023350278],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002078851,0.00010677561,0.000022346072,0.17298453,0.0001279552,0.00006888196,0.0000075514063,2.449981e-7,0.000023446615,0.000103706676,0.7949737,0.03156012],"study_design_scores_gemma":[0.00051556405,0.00038688423,0.000028715507,0.12014838,0.0010673598,0.00023216559,0.00000878722,0.00005573411,0.00006772283,0.000025820793,0.87721056,0.00025228268],"about_ca_topic_score_codex":0.000023675815,"about_ca_topic_score_gemma":9.3738595e-7,"teacher_disagreement_score":0.64095783,"about_ca_system_score_codex":0.000056490215,"about_ca_system_score_gemma":0.0005616154,"threshold_uncertainty_score":0.999958},"labels":[],"label_agreement":null},{"id":"W4206194534","doi":"10.1002/sta4.450","title":"Sparse Bayesian predictive modelling of tumour response using radiomic features","year":2022,"lang":"en","type":"article","venue":"Stat","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Frequentist inference; Computer science; Bayesian probability; Feature selection; Bayesian inference; Artificial intelligence; Feature (linguistics); Inference; Machine learning; Model selection; Radiomics; Pattern recognition (psychology); Data mining","score_opus":0.02290875228337112,"score_gpt":0.2906381868352594,"score_spread":0.26772943455188825,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206194534","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8568835,0.00045399973,0.1410001,0.00078715733,0.00021534492,0.00020431561,0.000031639913,0.000044610188,0.00037927492],"genre_scores_gemma":[0.9832841,0.00001804265,0.015630398,0.00029586902,0.0000978199,0.000008429297,0.000018345214,0.000036201673,0.0006107893],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99861723,0.0002338272,0.000244567,0.0002356322,0.0004233526,0.00024541345],"domain_scores_gemma":[0.99933577,0.00015016514,0.00012048994,0.00021007816,0.000043720498,0.00013980575],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000830073,0.00012015073,0.00029930047,0.00020499656,0.0002217774,0.0000068249483,0.0001116801,0.000029447741,0.00017839733],"category_scores_gemma":[0.0001809617,0.000114486604,0.00009987251,0.00022014746,0.0001190883,0.00004423777,0.00009337981,0.0005980624,0.0000010324923],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.009291629,0.00026819357,0.007977532,0.00014413074,0.00022093758,0.00089579396,0.0067526572,0.77631056,0.19283015,0.0002743606,0.0034401482,0.0015938948],"study_design_scores_gemma":[0.001510948,0.00036056098,0.0031601952,0.000073528114,0.00012472998,0.0006532318,0.0009616741,0.9900313,0.001363751,0.00035239686,0.0012752668,0.00013243855],"about_ca_topic_score_codex":0.00017188222,"about_ca_topic_score_gemma":4.467822e-7,"teacher_disagreement_score":0.21372071,"about_ca_system_score_codex":0.00017232969,"about_ca_system_score_gemma":0.00025828753,"threshold_uncertainty_score":0.46686283},"labels":[],"label_agreement":null},{"id":"W4206378559","doi":"10.1177/0846537120931222","title":"Corrigendum to Canadian Association of Thoracic Radiology/Canadian Association of Radiologists Consensus Statement Regarding Chest Imaging in Suspected and Confirmed COVID-19","year":2020,"lang":"en","type":"erratum","venue":"Canadian Association of Radiologists Journal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Medicine; Coronavirus disease 2019 (COVID-19); Statement (logic); 2019-20 coronavirus outbreak; Association (psychology); Radiology; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Coronavirus Infections; Betacoronavirus; Medical physics; Pathology; Disease","score_opus":0.02157812042575905,"score_gpt":0.3128641047034446,"score_spread":0.29128598427768554,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206378559","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19698799,0.009576769,0.0008543836,0.6740557,0.06599631,0.007950505,0.008558095,0.00025204843,0.035768222],"genre_scores_gemma":[0.9540153,0.0039122244,0.0016266918,0.01098818,0.002158121,0.000042607357,0.002522962,0.00018558114,0.024548342],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99177873,0.001904725,0.002606036,0.0008072108,0.0010605045,0.0018427982],"domain_scores_gemma":[0.9870071,0.001235229,0.0051598195,0.00039395184,0.0015758226,0.0046281223],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.009735271,0.0006611767,0.0026069744,0.0032824706,0.0004003986,0.000108153065,0.00053810666,0.0016869031,0.00022168191],"category_scores_gemma":[0.06897067,0.0007186604,0.00038305364,0.001100368,0.00025409405,0.000113392976,0.000047768855,0.0037647574,0.0000075081975],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00007361722,0.000017154178,0.4359462,0.00022845106,0.00054416514,0.00046133573,0.0009478436,0.000149081,0.0001373017,0.00006382546,0.5603402,0.0010908113],"study_design_scores_gemma":[0.004053876,0.0004507628,0.36672252,0.0009510053,0.00076744653,0.0005887639,0.001254004,0.0028239065,0.000026557022,0.00026142914,0.6212103,0.0008894486],"about_ca_topic_score_codex":0.7327503,"about_ca_topic_score_gemma":0.95023966,"teacher_disagreement_score":0.7570273,"about_ca_system_score_codex":0.055125263,"about_ca_system_score_gemma":0.029295953,"threshold_uncertainty_score":0.9996091},"labels":[],"label_agreement":null},{"id":"W4206581770","doi":"10.1200/jco.2022.40.4_suppl.357","title":"Survival prediction using radiomic signatures in metastatic gastric and esophageal adenocarcinoma (GEA).","year":2022,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Mount Sinai Hospital; Toronto General Hospital; Princess Margaret Cancer Centre; University Health Network","funders":"","keywords":"Medicine; Internal medicine; Cohort; Proportional hazards model; Concordance; Oncology; Retrospective cohort study; Radiology","score_opus":0.08355915223648386,"score_gpt":0.435015212716623,"score_spread":0.35145606048013917,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206581770","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.990455,0.0031038898,0.0013123497,0.0030799527,0.0016513434,0.0001443718,0.00000385595,0.0000078081375,0.00024146141],"genre_scores_gemma":[0.98943526,0.0002571259,0.008163843,0.0012516903,0.0007964224,0.000002150302,0.0000026989517,0.000017837014,0.00007294994],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9962754,0.0011363261,0.0016876885,0.00019418272,0.00047543313,0.0002309427],"domain_scores_gemma":[0.9968715,0.0016975285,0.00093790033,0.00010249219,0.00008070385,0.00030989046],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.00668043,0.0001138458,0.00112599,0.00036625864,0.00008605502,0.000009859106,0.00013166954,0.000105717474,0.00017598685],"category_scores_gemma":[0.0032336835,0.00009250772,0.00022007388,0.00026464753,0.00017065102,0.000084463514,0.00010006534,0.0027007817,5.6320073e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0027035812,0.0010774431,0.9072959,0.000053359545,0.00032528836,0.00568316,0.00024508234,0.008024598,0.0010946885,0.00014295068,0.001599735,0.071754254],"study_design_scores_gemma":[0.011248683,0.0069419527,0.86489093,0.000049456285,0.0005044707,0.004694235,0.000356338,0.105360344,0.0000045291918,0.0003916894,0.00546461,0.000092760085],"about_ca_topic_score_codex":0.00004222972,"about_ca_topic_score_gemma":0.0000028513477,"teacher_disagreement_score":0.09733574,"about_ca_system_score_codex":0.00024783096,"about_ca_system_score_gemma":0.001009637,"threshold_uncertainty_score":0.99960005},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"agree"},{"id":"W4206707518","doi":"10.5489/cuaj.866","title":"MRI and prostate cancer: the next frontier","year":2013,"lang":"en","type":"article","venue":"Canadian Urological Association Journal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Prostate cancer; Frontier; Medicine; Magnetic resonance imaging; Cancer; Oncology; Radiology; Internal medicine; Geography; Archaeology","score_opus":0.007810286932602959,"score_gpt":0.232946386845175,"score_spread":0.22513609991257202,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206707518","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5826775,0.0012612508,0.000073876305,0.4138113,0.0003127562,0.0001843204,0.0000028335637,0.0000131208635,0.0016630687],"genre_scores_gemma":[0.96866554,0.00090034393,0.00036504018,0.026979946,0.00057205756,0.00001663806,0.0000031048196,0.0000090307185,0.002488302],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9990966,0.0000928731,0.0001710894,0.00010596564,0.00019820059,0.00033531035],"domain_scores_gemma":[0.9990057,0.00008825931,0.00011543724,0.000058765545,0.00013455958,0.00059730135],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000503955,0.00007597316,0.00014607995,0.000055849883,0.0003110359,0.00020253319,0.00007272979,0.00009064102,0.0009769171],"category_scores_gemma":[0.0006210679,0.00004333564,0.000047636953,0.00008290014,0.000054315526,0.000098562035,0.000011411454,0.00079942436,0.000039856885],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005325974,0.000006648316,0.804894,0.0000022004308,0.000056099463,0.000020250405,0.00018836158,0.000023555443,0.00006322943,0.0000931714,0.14104503,0.053602155],"study_design_scores_gemma":[0.00041464096,0.00005489952,0.6834887,0.000009114045,0.000036323458,0.00014915844,0.00008822726,0.004106511,0.0000013168584,0.0011238318,0.3104717,0.000055559598],"about_ca_topic_score_codex":0.005060361,"about_ca_topic_score_gemma":0.00019198147,"teacher_disagreement_score":0.38683134,"about_ca_system_score_codex":0.00029647522,"about_ca_system_score_gemma":0.00022612911,"threshold_uncertainty_score":0.99993634},"labels":[],"label_agreement":null},{"id":"W4206757132","doi":"10.1007/s12149-021-01708-2","title":"The application of artificial intelligence in nuclear cardiology","year":2022,"lang":"en","type":"review","venue":"Annals of Nuclear Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Medicine; Nuclear medicine; Cardiology; Artificial intelligence; Internal medicine; Medical physics; Interpretation (philosophy); Radiology; Computer science","score_opus":0.11604659907970367,"score_gpt":0.4279545826597412,"score_spread":0.3119079835800375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206757132","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000046122874,0.98956156,0.00011726447,0.005646196,0.00027232995,0.00062859984,0.000005734434,0.000017967272,0.0037042007],"genre_scores_gemma":[0.0007764831,0.99803954,0.0001261417,0.0005404634,0.0003671413,0.000019323383,0.000039779097,0.000065878914,0.000025243653],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99740595,0.000292556,0.0012508446,0.0003194811,0.00045339137,0.00027776088],"domain_scores_gemma":[0.9978005,0.00073433836,0.00067430275,0.0006006295,0.00008101632,0.000109177854],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019887204,0.00022934945,0.0019740371,0.0003087469,0.00008950021,0.0000035390333,0.00044883467,0.00016572773,0.000354661],"category_scores_gemma":[0.0016130146,0.00014458732,0.0003341892,0.00058110995,0.0007209042,0.000018788882,0.00015134303,0.001073028,0.00002163377],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004899463,0.000045169887,0.000004082316,0.0022425584,0.00012156836,0.000025954423,0.00018142504,0.000006583885,0.000008557879,0.008517464,0.0021738193,0.9866238],"study_design_scores_gemma":[0.00007955938,0.00041908308,0.000024460476,0.0027615011,0.00027056027,0.00009671757,0.00033394096,0.0012024571,2.650646e-7,0.00054690265,0.9941668,0.00009778844],"about_ca_topic_score_codex":0.0001512579,"about_ca_topic_score_gemma":0.0000019371025,"teacher_disagreement_score":0.99199295,"about_ca_system_score_codex":0.00003702381,"about_ca_system_score_gemma":0.000108784225,"threshold_uncertainty_score":0.58961},"labels":[],"label_agreement":null},{"id":"W4206865815","doi":"","title":"Performance comparison of modified ComBat for harmonization of radiomic features in multicentric studies","year":2020,"lang":"en","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Harmonization; Computer science; Artificial intelligence; Art","score_opus":0.0343028849792563,"score_gpt":0.31802484469293246,"score_spread":0.28372195971367614,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206865815","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9069995,0.005401078,0.07639994,0.008506713,0.0002131654,0.0010402882,0.000027722961,0.00006161729,0.0013499713],"genre_scores_gemma":[0.95579326,0.0015398876,0.041801978,0.00005580718,0.000019545301,0.00004251878,0.0003351808,0.00003206013,0.0003797687],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99735147,0.0009433332,0.0007614527,0.00041283708,0.0003321887,0.00019870102],"domain_scores_gemma":[0.99579006,0.0012711023,0.00073913584,0.00066188636,0.0014347469,0.00010306207],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022417384,0.00021536832,0.0008657879,0.00026251152,0.000089302186,0.00002039042,0.00040603787,0.00016851403,0.000008259694],"category_scores_gemma":[0.0045072446,0.00021004729,0.00016366917,0.00034182367,0.00028639383,0.000044320434,0.00038228062,0.0006538806,7.9418464e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012199449,0.0049147597,0.4549495,0.025989806,0.0014988178,0.000016474498,0.13284396,0.020189647,0.07262881,0.020996688,0.0066820323,0.25806957],"study_design_scores_gemma":[0.00264733,0.0000032288626,0.04609388,0.0044396967,0.00019117603,0.0000052928185,0.000307954,0.88051295,0.06496751,0.00037570042,0.0002453939,0.0002098887],"about_ca_topic_score_codex":0.00023989957,"about_ca_topic_score_gemma":0.000041217394,"teacher_disagreement_score":0.8603233,"about_ca_system_score_codex":0.00010453456,"about_ca_system_score_gemma":0.00021682988,"threshold_uncertainty_score":0.856548},"labels":[],"label_agreement":null},{"id":"W4206955435","doi":"10.17160/josha.9.1.801","title":"Philosophy Research Program on Artificial Intelligence and Machine Learning in Oncology","year":2022,"lang":"en","type":"article","venue":"Journal of Science Humanities and Arts - JOSHA","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Artificial intelligence; Computer science","score_opus":0.2026430015915143,"score_gpt":0.4179458348165192,"score_spread":0.2153028332250049,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206955435","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9800658,0.0007688786,0.000027346025,0.011480285,0.00024182815,0.00016328126,7.12569e-7,0.000010920493,0.0072409506],"genre_scores_gemma":[0.99794316,0.00029426604,0.00060112344,0.0007313317,0.00024721576,0.0000063710595,6.1439226e-7,0.000007337281,0.00016856764],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983318,0.00012422614,0.000332702,0.00017548735,0.0007498432,0.00028593934],"domain_scores_gemma":[0.99934113,0.00020923335,0.00013701238,0.00006380184,0.00012721213,0.000121627716],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004419803,0.00007449703,0.00022172491,0.00077339244,0.00095250504,0.00010979573,0.00015708504,0.000019086001,0.00010629747],"category_scores_gemma":[0.0005666031,0.000058561884,0.000028813585,0.00035682938,0.0017468176,0.00015093709,0.00018157548,0.0016853955,8.517547e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00050699327,0.0010704813,0.005989595,0.0000837106,0.000018054714,0.0011138433,0.011836658,0.001024996,0.0027399953,0.07479409,0.00029886997,0.9005227],"study_design_scores_gemma":[0.0026343474,0.053855147,0.028483598,0.0012119152,0.00008034629,0.0087034255,0.06494547,0.14659907,0.0008899571,0.09791302,0.5939732,0.00071050477],"about_ca_topic_score_codex":0.000037392525,"about_ca_topic_score_gemma":0.0000067740266,"teacher_disagreement_score":0.8998122,"about_ca_system_score_codex":0.00013812502,"about_ca_system_score_gemma":0.00022347156,"threshold_uncertainty_score":0.7325995},"labels":[],"label_agreement":null},{"id":"W4207000458","doi":"10.1002/xrs.3190","title":"News article","year":2020,"lang":"en","type":"article","venue":"X-Ray Spectrometry","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Obituary; Web site; Group (periodic table); Art; Art history; Library science; Media studies; History; World Wide Web; Sociology; The Internet; Computer science; Archaeology; Physics","score_opus":0.01320787691267289,"score_gpt":0.27465068679174043,"score_spread":0.26144280987906754,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4207000458","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87152916,0.00043824973,0.012106041,0.08350603,0.00021097143,0.00017526471,0.0000017988203,0.00028204144,0.031750448],"genre_scores_gemma":[0.9705346,0.000045978846,0.0131487,0.014514484,0.0011759495,0.000002479301,0.0000050260187,0.00002614333,0.0005466176],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99905556,0.000016059428,0.00017381585,0.00023997022,0.000250431,0.00026416278],"domain_scores_gemma":[0.9992925,0.00007424908,0.000037196987,0.00017920119,0.000020871381,0.00039596047],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000103267805,0.00010261104,0.00022843192,0.00006902702,0.000045537276,0.000027376658,0.00009248074,0.00004234979,0.0011815866],"category_scores_gemma":[0.001023469,0.000086631364,0.00008992302,0.00047449942,0.000050706076,0.000047904923,0.00003784692,0.0004438153,0.0005217945],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014421812,0.00038467962,0.30475765,0.00016106335,0.00015030436,0.00044696478,0.00091590895,0.000053810498,0.5693017,0.0020889658,0.07613594,0.04545875],"study_design_scores_gemma":[0.008728566,0.0029635404,0.3966807,0.00015174192,0.0004065853,0.00037495457,0.0010903223,0.08714963,0.028399607,0.0012729194,0.47185883,0.0009225859],"about_ca_topic_score_codex":0.000014344844,"about_ca_topic_score_gemma":2.7957492e-7,"teacher_disagreement_score":0.54090214,"about_ca_system_score_codex":0.000032261978,"about_ca_system_score_gemma":0.000037840022,"threshold_uncertainty_score":0.9997315},"labels":[],"label_agreement":null},{"id":"W4207014659","doi":"10.1093/ecco-jcc/jjab232.014","title":"OP15 A new simplified histology artificial intelligence system for accurate assessment of remission in Ulcerative Colitis","year":2022,"lang":"en","type":"article","venue":"Journal of Crohn s and Colitis","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Ulcerative colitis; Biopsy; Rectum; Medicine; Artificial intelligence; Colonoscopy; Machine learning; Internal medicine; Disease; Gastroenterology; Radiology; Surgery; Computer science; Colorectal cancer; Cancer","score_opus":0.03244251417956577,"score_gpt":0.3586296442855274,"score_spread":0.3261871301059616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4207014659","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9351393,0.0004232053,0.055220764,0.0066894544,0.0007151974,0.0005056251,0.000022820994,0.0000084336825,0.001275218],"genre_scores_gemma":[0.9957564,0.00007412405,0.0034892042,0.00023286579,0.00018521887,0.000012077863,0.0000039860493,0.000010349905,0.00023579603],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99861556,0.00013579318,0.0006968591,0.00012353189,0.0002536491,0.0001746046],"domain_scores_gemma":[0.9989265,0.00021730876,0.00045803032,0.00007689016,0.00014456113,0.00017670494],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008815206,0.0000858441,0.00049283035,0.00016807386,0.00010059553,0.000017290318,0.00008655886,0.000040134524,0.00009604514],"category_scores_gemma":[0.00024512285,0.000074204465,0.00008953389,0.00013070954,0.00006132616,0.000049376395,0.000046661415,0.00041583582,1.07096e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.02862344,0.0009630508,0.0075754183,0.0020052688,0.00044933875,0.003375867,0.0068947133,0.0040946156,0.00486371,0.1429988,0.015458056,0.78269774],"study_design_scores_gemma":[0.0077264416,0.008776755,0.6989721,0.002348329,0.0005244669,0.010098991,0.018440163,0.13718316,0.0024647082,0.021878293,0.09099018,0.00059640635],"about_ca_topic_score_codex":0.000115479445,"about_ca_topic_score_gemma":0.00001609878,"teacher_disagreement_score":0.78210133,"about_ca_system_score_codex":0.0002610222,"about_ca_system_score_gemma":0.000568038,"threshold_uncertainty_score":0.30259702},"labels":[],"label_agreement":null},{"id":"W4210343112","doi":"10.1016/j.ctro.2022.01.003","title":"Cleaning radiotherapy contours for radiomics studies, is it worth it? A head and neck cancer study","year":2022,"lang":"en","type":"article","venue":"Clinical and Translational Radiation Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"Canadian Institute for Advanced Research; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Radiation therapy; Radiomics; Medicine; Head and neck cancer; Concordance; Radiation treatment planning; Nuclear medicine; Positron emission tomography; Radiology; Head and neck; Medical physics; Surgery; Internal medicine","score_opus":0.0972995325131289,"score_gpt":0.4875713216892286,"score_spread":0.3902717891760997,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210343112","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.84803873,0.008661208,0.0017185187,0.13945599,0.0007389097,0.0011177376,0.000050562303,0.000027700682,0.00019064429],"genre_scores_gemma":[0.96168476,0.0059545506,0.004155387,0.02652893,0.0008632421,0.00026957382,0.00006223367,0.000029179797,0.00045212367],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99828804,0.00022988657,0.00064486684,0.00041108966,0.0002236495,0.00020247385],"domain_scores_gemma":[0.9978974,0.001561945,0.00017379073,0.00009524481,0.000082709645,0.00018894387],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013590005,0.00014010187,0.0005801483,0.00009285167,0.00038025907,0.00001550012,0.000060455084,0.00008274468,0.00018713222],"category_scores_gemma":[0.00027977815,0.00012882755,0.0001069113,0.00012670255,0.00022772825,0.0000579297,0.00002144752,0.0004957192,4.881659e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015061119,0.00068690313,0.5137756,0.000047068334,0.000714224,0.000021129528,0.006827201,0.000734066,0.000015226015,0.0007348217,0.01129738,0.46364024],"study_design_scores_gemma":[0.02328721,0.0037567893,0.30315045,0.000031968822,0.00037225286,0.00006264053,0.002542812,0.08826994,7.683046e-7,0.0006328693,0.57768005,0.0002122272],"about_ca_topic_score_codex":0.000036678535,"about_ca_topic_score_gemma":0.000050912182,"teacher_disagreement_score":0.5663827,"about_ca_system_score_codex":0.00007791664,"about_ca_system_score_gemma":0.00032431143,"threshold_uncertainty_score":0.52534354},"labels":[],"label_agreement":null},{"id":"W4210497372","doi":"10.5272/jimab.2022281.4211","title":"INSTITUTIONALIZATION PATTERNS IN BREAST CANCER IMMUNOHISTOCHEMISTRY","year":2022,"lang":"en","type":"article","venue":"Journal of IMAB - Annual Proceeding (Scientific Papers)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Scopus; MEDLINE; Web of science; Library science; Citation; Breast cancer; Science Citation Index; Impact factor; Citation analysis; Bibliometrics; Medicine; Family medicine; Cancer; Political science; Internal medicine; Computer science","score_opus":0.008268342641236713,"score_gpt":0.29050846792456725,"score_spread":0.28224012528333053,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210497372","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99122334,0.00065473834,0.00014486974,0.0047635944,0.0014084207,0.00010259938,0.000061025323,0.000014933375,0.0016264576],"genre_scores_gemma":[0.99794,0.000050510436,0.00016661319,0.00037186441,0.00025552252,0.000010049916,0.000022393877,0.000014594134,0.0011684732],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99825376,0.000023068975,0.00049211003,0.0002063583,0.0007941584,0.00023056896],"domain_scores_gemma":[0.999088,0.00002053161,0.00034668684,0.000084194675,0.00032542177,0.00013517374],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011236652,0.00011370424,0.0002478462,0.00032507782,0.0003372692,0.000067159126,0.00021193128,0.00003177359,0.0007440381],"category_scores_gemma":[0.00016068517,0.00010040969,0.00011280119,0.00050354504,0.00013223538,0.00024206656,0.00009017229,0.0007948809,0.0000014249671],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006341831,0.0009506519,0.32195258,0.00040828975,0.00016734225,0.00038934633,0.0066624326,0.0043505947,0.61723906,0.000495309,0.02268508,0.024065157],"study_design_scores_gemma":[0.02335691,0.00092775613,0.5879455,0.0043490073,0.0007946656,0.030465383,0.047496095,0.028135134,0.006348946,0.00088212645,0.2674469,0.0018515306],"about_ca_topic_score_codex":0.00003377169,"about_ca_topic_score_gemma":3.4994426e-7,"teacher_disagreement_score":0.6108901,"about_ca_system_score_codex":0.00049835915,"about_ca_system_score_gemma":0.00054275704,"threshold_uncertainty_score":0.81466955},"labels":[],"label_agreement":null},{"id":"W4210572355","doi":"10.1002/advs.202104538","title":"Regional Radiomics Similarity Networks Reveal Distinct Subtypes and Abnormality Patterns in Mild Cognitive Impairment","year":2022,"lang":"en","type":"article","venue":"Advanced Science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":60,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Fundamental Research Funds for the Central Universities; Canadian Institutes of Health Research; National Institutes of Health; H. Lundbeck A/S; Eisai; Servier; Beijing Normal University; Genentech; IXICO; National Natural Science Foundation of China; Pfizer; Novartis Pharmaceuticals Corporation; F. Hoffmann-La Roche; Biogen; Eli Lilly and Company; Bristol-Myers Squibb; BioClinica; U.S. Department of Defense; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; National Institute on Aging; Alzheimer's Association","keywords":"Abnormality; Dementia; Neuroimaging; Cognitive impairment; Cognition; Medicine; Disease; Internal medicine; Bioinformatics; Psychology; Neuroscience; Biology; Psychiatry","score_opus":0.013580183040887681,"score_gpt":0.3013514475775353,"score_spread":0.2877712645366476,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210572355","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9927756,0.00030148882,0.0042950627,0.0019394045,0.00017488787,0.00026879282,0.000010399191,0.000026950709,0.00020740862],"genre_scores_gemma":[0.9969023,0.0000889308,0.00086310203,0.0019732413,0.00005255481,0.000029388511,0.00002109554,0.000008626924,0.00006079007],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99846166,0.00007191274,0.00021289922,0.00042984617,0.00045209515,0.0003715685],"domain_scores_gemma":[0.999353,0.00016033831,0.00008285916,0.00015549567,0.000048921323,0.00019939456],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013216856,0.0001104948,0.00020091752,0.00010699598,0.0004070072,0.000023441758,0.00015716648,0.000019736379,0.0000353009],"category_scores_gemma":[0.00025121158,0.000103278,0.000032561176,0.00043001282,0.0005124007,0.0001583305,0.00022608785,0.0006288815,4.9511203e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037197417,0.0002080717,0.9652475,0.00004207315,0.000009188581,0.00021502322,0.00065513665,0.0043141637,0.00045694123,0.0002806192,0.00011091345,0.028088361],"study_design_scores_gemma":[0.0016278219,0.00016688334,0.86869055,0.00008818031,0.000015122353,0.0002461723,0.00038279901,0.1280258,0.00003623972,0.00023852827,0.00033794524,0.00014393471],"about_ca_topic_score_codex":0.00010659185,"about_ca_topic_score_gemma":0.000015475334,"teacher_disagreement_score":0.123711646,"about_ca_system_score_codex":0.00020370107,"about_ca_system_score_gemma":0.00014256049,"threshold_uncertainty_score":0.42115545},"labels":[],"label_agreement":null},{"id":"W4210656052","doi":"10.1101/2022.01.15.22269276","title":"SCARF: Auto-Segmentation Clinical Acceptability &amp; Reproducibility Framework for Benchmarking Essential Radiation Therapy Targets in Head and Neck Cancer","year":2022,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; Princess Margaret Cancer Centre; Ontario Institute for Cancer Research; University of Toronto; University Health Network","funders":"","keywords":"Benchmarking; Segmentation; Computer science; Artificial intelligence; Reproducibility; Generalizability theory; Benchmark (surveying); Medical physics; Machine learning; Medicine; Mathematics; Statistics","score_opus":0.05033500927863903,"score_gpt":0.43017009327147765,"score_spread":0.3798350839928386,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210656052","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96585786,0.0036777225,0.018777642,0.005940902,0.0034075018,0.0021712163,0.000034519617,0.00008497724,0.000047649894],"genre_scores_gemma":[0.944914,0.004157912,0.046646,0.00094238186,0.001997514,0.00070391945,0.00052598875,0.000061137835,0.000051185776],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99541765,0.0006055268,0.0011068763,0.0020291116,0.00046727588,0.0003735321],"domain_scores_gemma":[0.9971796,0.00070837385,0.0004884176,0.0013240423,0.000103145976,0.0001964008],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00766581,0.00031282223,0.0008465827,0.00016315684,0.00017804732,0.00007019786,0.0002137346,0.0003655938,0.0010135802],"category_scores_gemma":[0.005557064,0.00029814255,0.00028084786,0.00020573598,0.00019493331,0.00007667837,0.00033970282,0.0023345558,9.5189597e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042611326,0.00027463597,0.7811517,0.00034159952,0.000083986175,0.0000039852507,0.0007984893,0.00047542067,0.00019963687,0.00003556978,0.0001630208,0.21604584],"study_design_scores_gemma":[0.0020743692,0.00014243883,0.96938485,0.00019521636,0.0000883515,0.0000031811203,0.00003630115,0.014771335,0.00011001236,0.0044001234,0.008536872,0.0002569494],"about_ca_topic_score_codex":0.0008278711,"about_ca_topic_score_gemma":0.00008961346,"teacher_disagreement_score":0.21578889,"about_ca_system_score_codex":0.0003424109,"about_ca_system_score_gemma":0.0004064484,"threshold_uncertainty_score":0.9999671},"labels":[],"label_agreement":null},{"id":"W4210761061","doi":"10.1039/d0lc90127j","title":"Correction: Deep-LUMEN assay – human lung epithelial spheroid classification from brightfield images using deep learning","year":2020,"lang":"en","type":"erratum","venue":"Lab on a Chip","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Spheroid; Deep learning; Human lung; Artificial intelligence; Lumen (anatomy); Biology; Lung; Pathology; Computer science; Medicine; Cell biology; Cell culture; Internal medicine","score_opus":0.01780057304056891,"score_gpt":0.2963106339900375,"score_spread":0.27851006094946856,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210761061","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.043310165,0.009055929,0.11940499,0.023504853,0.17787205,0.0032652256,0.00009733369,0.002910733,0.6205787],"genre_scores_gemma":[0.31298795,0.0017229231,0.012610749,0.012272736,0.06795476,0.00011851536,0.010165485,0.0011166014,0.5810503],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9965027,0.0004384707,0.0006684652,0.0010329435,0.0008248472,0.000532595],"domain_scores_gemma":[0.9979857,0.00032477078,0.000588028,0.00055838044,0.00013102316,0.00041209473],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000497702,0.0005882597,0.0009828857,0.00019485223,0.0005160011,0.00021779825,0.00033586845,0.000787488,0.0013955198],"category_scores_gemma":[0.0014258226,0.00054956257,0.00031943526,0.0003115791,0.00015262867,0.000104238214,0.00011012222,0.006350707,0.00014843371],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002917165,0.00025639933,0.005421954,0.0004556747,0.000667991,0.0004901978,0.0014541677,0.00030292434,0.028376108,0.00018637834,0.8860931,0.076003425],"study_design_scores_gemma":[0.0019339045,0.00039382366,0.012185512,0.0019431768,0.00088672806,0.0000901982,0.0002805774,0.45409408,0.0006708766,0.00020147293,0.52645594,0.00086370826],"about_ca_topic_score_codex":0.00074448064,"about_ca_topic_score_gemma":0.0000504315,"teacher_disagreement_score":0.45379114,"about_ca_system_score_codex":0.0003702966,"about_ca_system_score_gemma":0.0002277501,"threshold_uncertainty_score":0.9996956},"labels":[],"label_agreement":null},{"id":"W4210918265","doi":"10.1111/vru.13069","title":"Comparison of error rates between four pretrained DenseNet convolutional neural network models and 13 board‐certified veterinary radiologists when evaluating 15 labels of canine thoracic radiographs","year":2022,"lang":"en","type":"article","venue":"Veterinary Radiology & Ultrasound","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Rogue Research (Canada); Canadian Veterinary Medical Association; Montreal Police Service","funders":"","keywords":"Medicine; Radiography; Gold standard (test); Convolutional neural network; Institutional review board; Radiology; Veterinary medicine; Artificial intelligence; Surgery; Computer science","score_opus":0.1545214343275972,"score_gpt":0.4121974365414585,"score_spread":0.25767600221386133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210918265","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9908114,0.0059915013,0.0010817825,0.0006123827,0.00047088807,0.00069147494,0.0001247182,0.00008709244,0.00012873937],"genre_scores_gemma":[0.9870354,0.00011481183,0.011602955,0.00025900023,0.00032938036,0.000088259745,0.0004171688,0.00006238839,0.00009065718],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99533695,0.0016078008,0.0011636333,0.00070246065,0.0004911359,0.00069801655],"domain_scores_gemma":[0.9963875,0.0020626914,0.0006766558,0.0004719339,0.00013781991,0.00026339706],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0019901164,0.0004237704,0.0015654222,0.00029900746,0.00040387912,0.000015790813,0.00036768493,0.00020398025,0.00024701137],"category_scores_gemma":[0.0004958561,0.0004090518,0.0002463635,0.00039273905,0.0011882368,0.000118773365,0.00025869493,0.0010303524,7.434185e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0029600493,0.00020911077,0.71251297,0.00044392177,0.00092495175,0.00021236984,0.001841775,0.07362244,0.20135498,0.00009189999,0.002707913,0.0031175935],"study_design_scores_gemma":[0.0053089405,0.023233721,0.58298147,0.00027225175,0.0010184,0.014154447,0.00086261885,0.3674403,0.00023284514,0.00296306,0.0006835649,0.0008483466],"about_ca_topic_score_codex":0.00022338651,"about_ca_topic_score_gemma":0.0000028303073,"teacher_disagreement_score":0.29381788,"about_ca_system_score_codex":0.000118244745,"about_ca_system_score_gemma":0.00017659475,"threshold_uncertainty_score":0.99983615},"labels":[],"label_agreement":null},{"id":"W4210939367","doi":"10.1088/1361-6560/ac530e","title":"U-net architecture with embedded Inception-ResNet-v2 image encoding modules for automatic segmentation of organs-at-risk in head and neck cancer radiation therapy based on computed tomography scans","year":2022,"lang":"en","type":"article","venue":"Physics in Medicine and Biology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba; CancerCare Manitoba","funders":"University of Manitoba; CancerCare Manitoba Foundation","keywords":"Jaccard index; Hausdorff distance; Segmentation; Computer science; Sørensen–Dice coefficient; Artificial intelligence; Dice; Interpretability; Deep learning; Histogram; Pattern recognition (psychology); Image segmentation; Mathematics; Image (mathematics); Statistics","score_opus":0.03616315635573278,"score_gpt":0.35403994659602794,"score_spread":0.31787679024029514,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210939367","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98569876,0.000550856,0.010853241,0.0022388017,0.000062323095,0.00052434334,0.000025594152,0.00001539727,0.00003071121],"genre_scores_gemma":[0.993412,0.0003480017,0.004682708,0.0010928133,0.00011730848,0.00010109461,0.00023031245,0.0000132864825,0.0000024467697],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991329,0.0001450435,0.00022803716,0.00023039184,0.00011480163,0.000148839],"domain_scores_gemma":[0.99938715,0.00029672694,0.0001514524,0.00009208738,0.000027392653,0.000045188757],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033622936,0.00012131104,0.00034451246,0.00023469838,0.000086309556,0.0000030046838,0.000044258446,0.000033304786,0.000025044257],"category_scores_gemma":[0.000051354527,0.00008582401,0.00002116756,0.00032201246,0.00020500594,0.000020334857,0.0000183713,0.00027857866,3.1311515e-8],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012717975,0.00025819635,0.5587726,0.00025820785,0.00008109855,0.0000055114338,0.005312329,0.021718325,0.05750388,0.0002014446,0.00017008878,0.35444653],"study_design_scores_gemma":[0.015099229,0.0038505879,0.24485736,0.00043839906,0.00007137877,0.000009623544,0.00063255976,0.731551,0.0011447159,0.0019688185,0.00019995363,0.0001763708],"about_ca_topic_score_codex":0.0004596905,"about_ca_topic_score_gemma":0.000076773715,"teacher_disagreement_score":0.70983267,"about_ca_system_score_codex":0.000056869543,"about_ca_system_score_gemma":0.000038624512,"threshold_uncertainty_score":0.34998015},"labels":[],"label_agreement":null},{"id":"W4210987106","doi":"10.2144/fsoa-2021-0074","title":"An Overview of Artificial Intelligence in Oncology","year":2022,"lang":"en","type":"review","venue":"Future Science OA","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":122,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Health care; Personalized medicine; Precision medicine; Medicine; Survivorship curve; Clinical Oncology; Cancer; Oncology; Medical physics; Internal medicine; Data science; Bioinformatics; Computer science; Pathology; Biology","score_opus":0.1117844067401208,"score_gpt":0.47354199826257487,"score_spread":0.36175759152245407,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210987106","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00001983757,0.9955896,0.00015169528,0.0003764936,0.0015066516,0.00038644904,0.0000046812006,0.000019731786,0.0019448374],"genre_scores_gemma":[0.000025753116,0.9958607,0.0030628287,0.00026117393,0.0006878227,0.000028421444,0.000026303323,0.000019637524,0.000027336779],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976359,0.00019538493,0.00066511583,0.00053142355,0.0006296136,0.00034255552],"domain_scores_gemma":[0.9988368,0.00013447822,0.00028882906,0.00049154874,0.000041822757,0.00020652833],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002633493,0.00019813087,0.0012864976,0.0006207448,0.000102623126,0.000021050115,0.000754684,0.00014215986,0.0010239987],"category_scores_gemma":[0.0005543036,0.00014742182,0.00018928634,0.0021341036,0.0005860514,0.000092755254,0.00015681528,0.0013040458,0.000015881798],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000041900757,0.00012583559,0.000005542271,0.0024405192,0.0000054398583,0.00007378992,0.00019811225,0.000005227925,0.000008380675,0.0044620456,0.00004375457,0.99262714],"study_design_scores_gemma":[0.0000338584,0.00029399456,0.0000136630115,0.0019290327,0.00010095352,0.00017508447,0.00023455615,0.0012422515,0.0000014026338,0.0002420148,0.9956033,0.00012988833],"about_ca_topic_score_codex":0.00003901309,"about_ca_topic_score_gemma":0.000008776861,"teacher_disagreement_score":0.9955596,"about_ca_system_score_codex":0.00035432098,"about_ca_system_score_gemma":0.0020274604,"threshold_uncertainty_score":0.9998892},"labels":[],"label_agreement":null},{"id":"W4211193760","doi":"10.17504/protocols.io.z4af8se","title":"BDA Histology v1","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Histology; Medicine; Pathology","score_opus":0.01531804475338842,"score_gpt":0.31271326151798984,"score_spread":0.2973952167646014,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4211193760","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21738064,0.0024425893,0.035807658,0.05101213,0.0073949737,0.0009828331,0.0000057437246,0.00049871666,0.6844747],"genre_scores_gemma":[0.886311,0.00025664674,0.016675131,0.010187238,0.0008050165,0.000019970264,0.00017250355,0.00006705256,0.08550544],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988533,0.00003631356,0.00025065057,0.00041132414,0.00020888547,0.0002395153],"domain_scores_gemma":[0.9990429,0.00006660227,0.00009788717,0.000580775,0.0000554551,0.00015636966],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00022200755,0.00018603767,0.00054666586,0.0001267348,0.000022977465,0.000016490238,0.00016451228,0.0003149005,0.0014637294],"category_scores_gemma":[0.00027824737,0.00014697721,0.00017071856,0.000036760433,0.000086495,0.000010010794,0.0003674088,0.0016509963,0.0005560233],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020897218,0.0004314541,0.12428255,0.003243965,0.00081736926,0.0008705771,0.0006314109,0.0017428537,0.0024500105,0.012609541,0.7130403,0.13967103],"study_design_scores_gemma":[0.0019997924,0.00018751234,0.018347984,0.0005718026,0.0003969617,0.000517558,0.000046365454,0.08484003,0.00015086903,0.00316879,0.88922054,0.00055181846],"about_ca_topic_score_codex":0.00021293618,"about_ca_topic_score_gemma":0.0000018760915,"teacher_disagreement_score":0.66893035,"about_ca_system_score_codex":0.00010645621,"about_ca_system_score_gemma":0.00026355154,"threshold_uncertainty_score":0.9994491},"labels":[],"label_agreement":null},{"id":"W4212809016","doi":"10.21037/qims-21-980","title":"Development and validation of novel radiomics-based nomograms for the prediction of EGFR mutations and Ki-67 proliferation index in non-small cell lung cancer","year":2022,"lang":"en","type":"article","venue":"Quantitative Imaging in Medicine and Surgery","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Nomogram; Radiomics; Medicine; Proliferation index; Receiver operating characteristic; Lung cancer; Cohort; Oncology; Stage (stratigraphy); Area under the curve; Internal medicine; Radiology; Immunohistochemistry; Biology","score_opus":0.03808206448449742,"score_gpt":0.32577286106874837,"score_spread":0.28769079658425095,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4212809016","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93408525,0.0018617834,0.05870733,0.0045358543,0.00012806666,0.0006460661,0.000012861671,0.000006797786,0.000015977133],"genre_scores_gemma":[0.9925325,0.0001749324,0.006564699,0.00036147737,0.000030810068,0.00022120858,0.00008896645,0.0000148044355,0.00001059871],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99885535,0.00006867136,0.00051901664,0.00021029756,0.0002047665,0.00014189388],"domain_scores_gemma":[0.9982277,0.0013291807,0.00022215309,0.00007396575,0.00009932215,0.000047682974],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016693451,0.00011112889,0.00034490394,0.00045033032,0.0001196683,0.000008483333,0.00003263481,0.000022732727,0.000005566344],"category_scores_gemma":[0.0004534174,0.00008765356,0.000025408732,0.00029569204,0.00022769839,0.000067762194,0.000022953156,0.00022416977,8.054669e-9],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001950237,0.00013486597,0.9674844,0.00062329485,0.00002946526,0.0000051323746,0.008201875,0.003017556,0.008454669,0.000111102985,0.00017866842,0.0115639195],"study_design_scores_gemma":[0.0030359793,0.000079987905,0.2643523,0.0005425042,0.000084905216,0.000012982304,0.0043517654,0.72597814,0.001093458,0.000030830975,0.00035624177,0.00008090733],"about_ca_topic_score_codex":0.0004721072,"about_ca_topic_score_gemma":0.00002740071,"teacher_disagreement_score":0.7229606,"about_ca_system_score_codex":0.00006599362,"about_ca_system_score_gemma":0.00021206624,"threshold_uncertainty_score":0.35744086},"labels":[],"label_agreement":null},{"id":"W4212846230","doi":"10.1093/jcag/gwab049.120","title":"A121 QUANTIFYING INTER-OBSERVER VARIABILITY IN THE SEGMENTATION OF RECTAL TUMORS IN ENDOSCOPY IMAGES AND ITS EFFECTS ON DEEP LEARNING","year":2022,"lang":"en","type":"article","venue":"Journal of the Canadian Association of Gastroenterology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; Jewish General Hospital; McGill University","funders":"","keywords":"Artificial intelligence; Deep learning; Segmentation; Ground truth; Computer science; Medical diagnosis; Endoscopy; Image segmentation; Observer (physics); Pattern recognition (psychology); Medicine; Radiology","score_opus":0.009244807373542874,"score_gpt":0.2671262182556357,"score_spread":0.2578814108820928,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4212846230","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98909795,0.000020832227,0.000039744686,0.010427174,0.00021845337,0.00014784174,0.0000025785096,9.464145e-7,0.00004445176],"genre_scores_gemma":[0.998778,0.000010056083,0.00014387786,0.0010068995,0.00003278178,0.0000038084952,0.0000021637577,0.000005929902,0.000016513064],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.997238,0.0018290983,0.00040950833,0.000078624,0.00027540178,0.00016939052],"domain_scores_gemma":[0.99862075,0.00051473733,0.0006781483,0.00006249901,0.00006780701,0.00005606464],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00445277,0.00006249649,0.0002725196,0.00024915955,0.00007298111,0.0000071880645,0.00013512328,0.000030933825,0.000017581291],"category_scores_gemma":[0.0027479418,0.00004535547,0.000070801,0.00014181585,0.000027404685,0.000043246488,0.00002981057,0.0008900283,9.5577064e-8],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024096218,0.000046487814,0.99300885,0.00004162843,0.00003701228,0.000023886912,0.0010744581,0.0012002849,0.0034683468,0.000025575284,0.00006581242,0.0007667022],"study_design_scores_gemma":[0.0020333102,0.0010453212,0.9927921,0.00012037921,0.000039854014,0.000091056834,0.00047785137,0.002952128,0.00032098455,0.000058665235,0.000045393084,0.000022955504],"about_ca_topic_score_codex":0.0020205174,"about_ca_topic_score_gemma":0.012315175,"teacher_disagreement_score":0.010294657,"about_ca_system_score_codex":0.000741955,"about_ca_system_score_gemma":0.000105950945,"threshold_uncertainty_score":0.6872156},"labels":[],"label_agreement":null},{"id":"W4213047154","doi":"10.1200/jco.2022.40.6_suppl.223","title":"An AI-derived digital pathology-based biomarker to predict the benefit of androgen deprivation therapy in localized prostate cancer with validation in NRG/RTOG 9408.","year":2022,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; University of Saskatchewan; Dalhousie University","funders":"","keywords":"Medicine; Prostate cancer; Biomarker; Oncology; Androgen deprivation therapy; Randomized controlled trial; Radiation therapy; Internal medicine; Cohort; Cancer","score_opus":0.04698736294900667,"score_gpt":0.4218052130759005,"score_spread":0.37481785012689384,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4213047154","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9738622,0.00014383161,0.0009926634,0.024260735,0.00026044017,0.00042200292,0.00000708201,0.0000059281324,0.000045153512],"genre_scores_gemma":[0.99361634,0.00016884466,0.0011146386,0.004914273,0.00010644343,0.000036106456,0.000015041243,0.000016831262,0.0000114696595],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9973083,0.00055429584,0.0013818161,0.0001857315,0.00039199303,0.00017785106],"domain_scores_gemma":[0.9979118,0.0007115536,0.0008643953,0.00016839046,0.00019156096,0.00015230358],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038892175,0.00010226448,0.0007255817,0.00023161575,0.00004130916,0.0000108364875,0.00018938023,0.00010018933,0.00006030072],"category_scores_gemma":[0.00135242,0.00006154868,0.0001128792,0.00037493824,0.00017696495,0.00011055597,0.000037044403,0.0009565782,3.477267e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.010162771,0.0009897875,0.7341302,0.0000092410755,0.00006452513,0.00025911053,0.00038851518,0.018377371,0.0019879518,0.000008303246,0.00012887124,0.23349337],"study_design_scores_gemma":[0.020015165,0.014397333,0.93265444,0.00017443365,0.00007605973,0.00019096605,0.0002984649,0.023182955,0.00047965205,0.0003730874,0.008042236,0.00011519299],"about_ca_topic_score_codex":0.00007371148,"about_ca_topic_score_gemma":0.00004956152,"teacher_disagreement_score":0.23337817,"about_ca_system_score_codex":0.00015268134,"about_ca_system_score_gemma":0.0010995935,"threshold_uncertainty_score":0.41559094},"labels":[],"label_agreement":null},{"id":"W4213208144","doi":"10.3390/curroncol29020091","title":"CT and 3 Tesla MRI in the TN Staging of Colon Cancer: A Prospective, Blind Study","year":2022,"lang":"en","type":"article","venue":"Current Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine; Colorectal cancer; Cancer; Radiology; Prospective cohort study; Nuclear medicine; Medical physics; Pathology; Internal medicine","score_opus":0.05712746829958972,"score_gpt":0.43658779648371315,"score_spread":0.37946032818412345,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4213208144","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99100935,0.0019438781,0.000026643169,0.004133669,0.00045563898,0.0009102237,0.000004696011,0.000011155052,0.0015047173],"genre_scores_gemma":[0.99902916,0.00022869196,0.000063138104,0.00024946957,0.00008471166,0.00026502067,0.0000034950406,0.000008476019,0.00006785017],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9989076,0.0002819632,0.0002163054,0.0002035552,0.00022466341,0.00016585918],"domain_scores_gemma":[0.99949396,0.00020264491,0.000103039674,0.0001291169,0.000029106295,0.00004214954],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000972389,0.000078025325,0.00028309543,0.00012078508,0.00010288113,0.0000057552797,0.00011648471,0.000009323728,0.00010568762],"category_scores_gemma":[0.0001196561,0.00005657667,0.000026394535,0.00026124532,0.000112571994,0.000017217595,0.00012640296,0.0007557206,3.5109872e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017428593,0.0014353637,0.91921127,0.000054395197,0.000029865312,0.00009767827,0.0062149446,0.00005921202,0.00007552886,0.00012718231,0.0026945046,0.06982579],"study_design_scores_gemma":[0.015617811,0.004334714,0.6299546,0.0000941769,0.00025169057,0.00025065558,0.018228102,0.018860051,0.00001750587,0.00033939045,0.31186783,0.00018349041],"about_ca_topic_score_codex":0.0001817439,"about_ca_topic_score_gemma":0.000034920784,"teacher_disagreement_score":0.30917332,"about_ca_system_score_codex":0.00018356662,"about_ca_system_score_gemma":0.00018379062,"threshold_uncertainty_score":0.3283272},"labels":[],"label_agreement":null},{"id":"W4213241801","doi":"10.1200/jco.2022.40.6_suppl.222","title":"Development and validation of a prognostic AI biomarker using multi-modal deep learning with digital histopathology in localized prostate cancer on NRG Oncology phase III clinical trials.","year":2022,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; University of Saskatchewan; Horizon Health Network; Saint John Regional Hospital","funders":"","keywords":"Histopathology; Medicine; Prostate cancer; Cancer; Oncology; Biopsy; Clinical trial; Stage (stratigraphy); Prostate; Internal medicine; Radiology; Pathology","score_opus":0.18158956860530254,"score_gpt":0.5355532580715139,"score_spread":0.3539636894662114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4213241801","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9872859,0.00046369876,0.007176895,0.003478498,0.0009329942,0.0005602176,0.0000026003217,0.000010707144,0.000088474546],"genre_scores_gemma":[0.98007846,0.00023051065,0.01793246,0.0013720271,0.0002597483,0.000028257891,0.0000141218125,0.000031178723,0.000053208314],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99001974,0.0037600233,0.0050161043,0.00038194205,0.0004901728,0.00033200975],"domain_scores_gemma":[0.9895848,0.005567732,0.0040335516,0.00011984843,0.00030118236,0.00039289295],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.022087118,0.00020363274,0.0028330137,0.00038297227,0.00011209837,0.000013837271,0.00014274754,0.0003008076,0.00008468556],"category_scores_gemma":[0.020183219,0.00014562729,0.00027997236,0.00025690545,0.0005661656,0.000109798464,0.00013695672,0.0031592974,7.452232e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.030903434,0.0046364646,0.30369744,0.000046314217,0.00026010623,0.0020156156,0.00091557833,0.002505952,0.00039725652,0.000012911806,0.000034504897,0.65457445],"study_design_scores_gemma":[0.2468372,0.07365245,0.22729425,0.00078341924,0.0017458288,0.004695677,0.0021822606,0.2613487,0.00010113137,0.000104203486,0.18064433,0.0006105379],"about_ca_topic_score_codex":0.000029029066,"about_ca_topic_score_gemma":0.000018200584,"teacher_disagreement_score":0.6539639,"about_ca_system_score_codex":0.0005386005,"about_ca_system_score_gemma":0.0032385476,"threshold_uncertainty_score":0.99914044},"labels":[],"label_agreement":null},{"id":"W4214699115","doi":"10.5220/0010916000003123","title":"Survival Status Prediction for Non-small Cell Lung Cancer Patients using Machine Learning","year":2022,"lang":"en","type":"article","venue":"Proceedings of the 15th International Joint Conference on Biomedical Engineering Systems and Technologies","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Computer science; Lung cancer; Machine learning; Artificial intelligence; Oncology; Medicine","score_opus":0.016244705614510375,"score_gpt":0.24979858695150567,"score_spread":0.23355388133699528,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4214699115","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9927183,0.00027280475,0.0023053,0.0018837396,0.001620873,0.00065070164,0.00012369719,0.0002168538,0.00020777858],"genre_scores_gemma":[0.9983398,0.00012230805,0.0011266645,0.000020432664,0.00007791248,0.00014551464,0.000022817578,0.000023089948,0.000121459634],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99865544,0.0000049162873,0.00035006154,0.00025509222,0.0004970612,0.00023741138],"domain_scores_gemma":[0.9993666,0.000036512032,0.00024441912,0.00006367181,0.00022485157,0.00006393945],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032232364,0.00015634499,0.00028257782,0.0002669343,0.00015404877,0.000042070038,0.0002278029,0.00008178471,0.0000096383865],"category_scores_gemma":[0.00053876644,0.0001147248,0.00007485239,0.00017660545,0.00009563859,0.000046920617,0.00023867152,0.0005956644,8.436898e-8],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004086791,0.0009334064,0.6314045,0.0047309548,0.00078876683,0.000005524364,0.00089936703,0.0111427205,0.30374992,0.032009885,0.0008890615,0.0130371945],"study_design_scores_gemma":[0.0013766969,0.00034086022,0.0055911215,0.0006105185,0.000061502025,0.000014284906,0.00073530583,0.9855953,0.001657081,0.000039024817,0.0038496065,0.0001287411],"about_ca_topic_score_codex":0.00012811157,"about_ca_topic_score_gemma":1.6050025e-7,"teacher_disagreement_score":0.97445256,"about_ca_system_score_codex":0.0001785196,"about_ca_system_score_gemma":0.000056180776,"threshold_uncertainty_score":0.46783414},"labels":[],"label_agreement":null},{"id":"W4214916274","doi":"10.3390/info13030124","title":"An Attentive Multi-Modal CNN for Brain Tumor Radiogenomic Classification","year":2022,"lang":"en","type":"article","venue":"Information","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Artificial intelligence; Brain tumor; Modal; Feature (linguistics); Modality (human–computer interaction); Pattern recognition (psychology); Feature extraction; Process (computing); Magnetic resonance imaging; Embedding; Deep learning; Medical imaging; Image (mathematics); Modalities; Radiology; Medicine; Pathology","score_opus":0.019907245384279078,"score_gpt":0.31334287239915837,"score_spread":0.2934356270148793,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4214916274","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83434445,0.000022369593,0.15652582,0.006577274,0.0004259879,0.0009444902,0.000043275388,0.00012645373,0.0009898756],"genre_scores_gemma":[0.98776627,0.0000015968071,0.0064230515,0.0043773195,0.00011419615,0.000110891415,0.0010328704,0.000011769498,0.0001620246],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992555,0.000040820458,0.00026645223,0.00009609908,0.00019328643,0.00014785674],"domain_scores_gemma":[0.9994957,0.000047150243,0.00014972202,0.00015653463,0.000064739696,0.0000861607],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000563684,0.00007393692,0.00011624026,0.00014780193,0.00025640908,0.00003657504,0.00009169684,0.000020245348,0.0000713753],"category_scores_gemma":[0.00019531048,0.00007326707,0.000059218415,0.00010273988,0.000028644365,0.00043283927,0.000021395856,0.00020573036,0.00002695821],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0020101406,0.0010600776,0.043288667,0.000655399,0.00028826777,0.00002026066,0.028237246,0.024470123,0.13903163,0.014991223,0.060434893,0.68551207],"study_design_scores_gemma":[0.0022245531,0.00026056642,0.03633165,0.000007859878,0.000027631984,0.00006627765,0.0013081086,0.85800946,0.00016874284,0.000059819973,0.10143812,0.000097193515],"about_ca_topic_score_codex":0.000019996909,"about_ca_topic_score_gemma":4.0159946e-7,"teacher_disagreement_score":0.83353937,"about_ca_system_score_codex":0.00018755063,"about_ca_system_score_gemma":0.00008311695,"threshold_uncertainty_score":0.29877445},"labels":[],"label_agreement":null},{"id":"W4214933629","doi":"10.3389/frai.2022.826402","title":"Developing a Cancer Digital Twin: Supervised Metastases Detection From Consecutive Structured Radiology Reports","year":2022,"lang":"en","type":"article","venue":"Frontiers in Artificial Intelligence","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":62,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"National Cancer Institute; National Institutes of Health; Social Sciences and Humanities Research Council of Canada; Canada Research Chairs","keywords":"Convolutional neural network; Artificial intelligence; Ground truth; Cancer; Medicine; Deep learning; Computer science; Radiology; Natural language processing; Machine learning; Medical physics; Internal medicine","score_opus":0.027149950896165592,"score_gpt":0.3043130408535752,"score_spread":0.27716308995740957,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4214933629","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6485082,0.0013140427,0.3449305,0.0011960543,0.0034526673,0.00035807752,0.00005652161,0.00006917948,0.00011473963],"genre_scores_gemma":[0.9859471,0.00007274159,0.012704297,0.0007909118,0.00020826353,0.00009807975,0.00010870153,0.00002703634,0.00004286985],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99805444,0.00015698728,0.00059941545,0.0005198037,0.0003174536,0.00035190955],"domain_scores_gemma":[0.9992983,0.000117096424,0.00016868823,0.00023741252,0.000060780174,0.000117737814],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036877973,0.00018640452,0.00044922336,0.0002753149,0.00022488621,0.00005044645,0.00014185799,0.00006567742,0.0002693179],"category_scores_gemma":[0.0007027335,0.00018669116,0.00009879437,0.0004838098,0.00022600223,0.00010861302,0.00011826028,0.0007099998,0.0000026745658],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010303213,0.00014527618,0.13107209,0.000035313908,0.0003277854,0.0019387152,0.004152766,0.008464783,0.007813266,0.0005043988,0.0019116807,0.8426036],"study_design_scores_gemma":[0.0011366719,0.0010135564,0.021683674,0.00039429625,0.0005430875,0.0024795379,0.043728888,0.540766,0.12544832,0.21133205,0.049350347,0.0021235673],"about_ca_topic_score_codex":0.0011691231,"about_ca_topic_score_gemma":0.00009119482,"teacher_disagreement_score":0.84048,"about_ca_system_score_codex":0.0004884028,"about_ca_system_score_gemma":0.00028815024,"threshold_uncertainty_score":0.7613045},"labels":[],"label_agreement":null},{"id":"W4220671431","doi":"10.3390/cancers14071674","title":"Context-Aware Saliency Guided Radiomics: Application to Prediction of Outcome and HPV-Status from Multi-Center PET/CT Images of Head and Neck Cancer","year":2022,"lang":"en","type":"article","venue":"Cancers","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Basic and Applied Basic Research Foundation of Guangdong Province; China Postdoctoral Science Foundation; National Natural Science Foundation of China","keywords":"Radiomics; Head and neck cancer; Context (archaeology); Medicine; Head and neck; Center (category theory); Cancer imaging; Radiology; Medical physics; Cancer; Artificial intelligence; Computer science; Radiation therapy; Internal medicine; Surgery; Biology","score_opus":0.021065617805942318,"score_gpt":0.32702189568526785,"score_spread":0.30595627787932556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220671431","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9932204,0.0018261184,0.0026290482,0.0010138395,0.00025894688,0.00042555958,0.00052064785,0.000024152154,0.00008131743],"genre_scores_gemma":[0.9967748,0.0005512634,0.0014048053,0.00088073814,0.000061823055,0.000101932535,0.00008629043,0.000020383965,0.00011798819],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9990019,0.000035331643,0.00033602887,0.00027342298,0.00019032585,0.0001629535],"domain_scores_gemma":[0.99941254,0.00003973726,0.00015623255,0.00017434444,0.00005804525,0.00015911533],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014361093,0.000107060434,0.00032230484,0.00009195775,0.00007021618,0.000006198246,0.00006434922,0.000008879759,0.0000817281],"category_scores_gemma":[0.00008457319,0.00010287578,0.00003985163,0.00011600853,0.00011892236,0.000044038177,0.00006921734,0.00019520697,3.2140034e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017916784,0.000053044954,0.9436397,0.00016004233,0.000088418834,0.0000152032435,0.00084582175,0.001214836,0.010114874,0.000020995758,0.0024217982,0.041246124],"study_design_scores_gemma":[0.01528204,0.00054510334,0.79253864,0.000311509,0.00030582384,0.00016870101,0.0024546757,0.15348606,0.0023028178,0.000048629947,0.032239977,0.00031600357],"about_ca_topic_score_codex":0.009567638,"about_ca_topic_score_gemma":0.00008680404,"teacher_disagreement_score":0.15227123,"about_ca_system_score_codex":0.0004389593,"about_ca_system_score_gemma":0.00014442891,"threshold_uncertainty_score":0.99702775},"labels":[],"label_agreement":null},{"id":"W4220672073","doi":"10.1016/j.cmpb.2022.106750","title":"Testing the Ability of Convolutional Neural Networks to Learn Radiomic Features","year":2022,"lang":"en","type":"article","venue":"Computer Methods and Programs in Biomedicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":20,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; University of British Columbia; BC Cancer Agency","funders":"Canadian Institutes of Health Research","keywords":"Artificial intelligence; Convolutional neural network; Computer science; Pattern recognition (psychology); Radiomics; Deep learning; Feature (linguistics); Artificial neural network; Machine learning","score_opus":0.046378536738786426,"score_gpt":0.366186759643011,"score_spread":0.31980822290422456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220672073","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7092084,0.003439673,0.27361873,0.011645064,0.0010281871,0.000904054,0.0000022095087,0.000063886546,0.000089766036],"genre_scores_gemma":[0.649482,0.000009069555,0.3482437,0.0017678937,0.0003990967,0.000043442047,0.000019692805,0.000013465378,0.000021635535],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99817437,0.0005619075,0.0003864108,0.0003191909,0.00027945792,0.0002786853],"domain_scores_gemma":[0.99862015,0.0008106626,0.00010234881,0.0002479609,0.000060306164,0.0001585844],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036934,0.00014038911,0.00041640087,0.0001598583,0.00020036523,0.0000122345045,0.00018478655,0.000039729624,0.000023540846],"category_scores_gemma":[0.00032122884,0.00009211019,0.000058821406,0.00083234155,0.0004653724,0.000018277238,0.00031530607,0.0007720969,1.0712577e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010872401,0.00011256049,0.08653797,0.00006622688,0.00003175884,0.000034568868,0.00062011776,0.0018728756,0.0030955328,0.00012674318,0.00044229388,0.90695065],"study_design_scores_gemma":[0.0012369712,0.0011818036,0.44545808,0.0000791968,0.000042439242,0.000822026,0.00012812793,0.5419899,0.000009114583,0.0002946359,0.008653138,0.000104543135],"about_ca_topic_score_codex":0.00017309573,"about_ca_topic_score_gemma":6.006577e-7,"teacher_disagreement_score":0.9068461,"about_ca_system_score_codex":0.00005048404,"about_ca_system_score_gemma":0.000044678356,"threshold_uncertainty_score":0.37561446},"labels":[],"label_agreement":null},{"id":"W4220680585","doi":"10.3390/cancers14051349","title":"Advancements in Oncology with Artificial Intelligence—A Review Article","year":2022,"lang":"en","type":"review","venue":"Cancers","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":80,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Medicine; Medical physics; Standardization; Breast cancer; Grading (engineering); Generalizability theory; Precision medicine; Personalized medicine; Colorectal cancer; Neuroimaging; Cancer; Oncology; Artificial intelligence; Internal medicine; Pathology; Bioinformatics; Computer science; Psychology","score_opus":0.0806369913517267,"score_gpt":0.4364614543406138,"score_spread":0.3558244629888871,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220680585","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000003451243,0.9942978,0.00021759451,0.00053529727,0.00031862085,0.0008968194,0.0000036824415,0.000024029472,0.0037026964],"genre_scores_gemma":[0.0000036669621,0.9965084,0.00061056344,0.0020337745,0.00015101809,0.00038451495,0.00006637942,0.00004230013,0.00019936143],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983667,0.0001420152,0.0005594229,0.00036218687,0.00026850298,0.00030117575],"domain_scores_gemma":[0.99920315,0.00013019699,0.00023409488,0.0002723283,0.000016886737,0.00014332695],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00050800154,0.00021383597,0.001415231,0.00013634628,0.000045087934,0.000006649865,0.00015632431,0.00007077673,0.001965425],"category_scores_gemma":[0.00026079168,0.00015709474,0.00014694128,0.00060111424,0.00010309642,0.000028114251,0.00005443304,0.0011161313,0.000038309376],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017759401,0.000022679276,0.0000063177754,0.01671388,0.000055029377,0.00027170312,0.000030504143,0.00004113675,8.906406e-8,0.00009837864,0.0007561056,0.9819864],"study_design_scores_gemma":[0.00010311613,0.00024467916,4.491511e-7,0.03710636,0.0005063058,0.00013213215,0.000049402945,0.00018067347,1.882457e-7,0.000035742272,0.96148986,0.00015108296],"about_ca_topic_score_codex":0.000074775744,"about_ca_topic_score_gemma":0.000016301796,"teacher_disagreement_score":0.9818353,"about_ca_system_score_codex":0.0033888996,"about_ca_system_score_gemma":0.0024067482,"threshold_uncertainty_score":0.9989469},"labels":[],"label_agreement":null},{"id":"W4220687928","doi":"10.1117/12.2612684","title":"A cascaded deep network for automated tumor detection and segmentation in clinical PET imaging of diffuse large B-cell lymphoma","year":2022,"lang":"en","type":"article","venue":"Medical Imaging 2022: Image Processing","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Children's Hospital; University of British Columbia","funders":"Canadian Institutes of Health Research; Society of Nuclear Medicine and Molecular Imaging","keywords":"Segmentation; Computer science; Artificial intelligence; Deep learning; Image segmentation; Diffuse large B-cell lymphoma; Computer vision; Pattern recognition (psychology); Lymphoma; Medicine; Pathology","score_opus":0.007140134130324495,"score_gpt":0.31650639408651143,"score_spread":0.30936625995618694,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220687928","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81163865,0.0047899997,0.17735316,0.0038666204,0.0006842786,0.0009766233,0.000016945683,0.00045943633,0.00021430205],"genre_scores_gemma":[0.97535855,0.00007016158,0.020892981,0.002955344,0.00032990615,0.00017621407,0.00008441965,0.00008639197,0.000046031106],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962054,0.00035206287,0.0011601323,0.00066773844,0.00090539607,0.00070928317],"domain_scores_gemma":[0.9983658,0.00043526382,0.00047579195,0.00021343412,0.00013802366,0.00037164873],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.004008833,0.0002773397,0.0006697404,0.00030487278,0.00047803388,0.00008605451,0.0002139335,0.000043856646,0.0000955817],"category_scores_gemma":[0.0020331105,0.00027524075,0.00015556699,0.00065498124,0.00033329232,0.00027393582,0.00031029363,0.000896436,0.0000012307281],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007492685,0.0033606691,0.14940071,0.0016130066,0.00005760375,0.0017640417,0.0015082243,0.000085262625,0.018435938,0.000010604071,0.0017220052,0.8212927],"study_design_scores_gemma":[0.016996931,0.00009313831,0.012041545,0.00034245593,0.00014284861,0.0012660824,0.001463538,0.96578807,0.0005502203,0.000108398955,0.0009483096,0.00025845214],"about_ca_topic_score_codex":0.00008738793,"about_ca_topic_score_gemma":0.000011224069,"teacher_disagreement_score":0.96570283,"about_ca_system_score_codex":0.00021150791,"about_ca_system_score_gemma":0.0003906184,"threshold_uncertainty_score":0.99996996},"labels":[],"label_agreement":null},{"id":"W4220742071","doi":"10.1038/s41374-022-00759-x","title":"USCAP 2022 Abstracts: Informatics (977-1017)","year":2022,"lang":"en","type":"article","venue":"Laboratory Investigation","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Health Services; University of Alberta; University of Calgary; Alberta Hospital Edmonton; University of Alberta Hospital","funders":"Foundation Medicine","keywords":"Informatics; Medicine; Computer science; Library science; Engineering; Electrical engineering","score_opus":0.009212656423472547,"score_gpt":0.2527011562683321,"score_spread":0.24348849984485957,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220742071","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99016565,0.0001890331,0.00020452273,0.004392913,0.00051049306,0.00023276827,0.000027129361,0.00015213706,0.004125339],"genre_scores_gemma":[0.9760362,0.000025069607,0.005867669,0.016477471,0.00030235847,0.00007692932,0.0003435602,0.000037030077,0.00083372777],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99866503,0.000085173815,0.0004099461,0.00012942743,0.00051453913,0.00019587635],"domain_scores_gemma":[0.9991682,0.000049339433,0.0002093915,0.00025051786,0.00009974891,0.0002228052],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007438222,0.00011383756,0.00016845156,0.00013702834,0.00030009408,0.00003456126,0.000111174464,0.000043353848,0.0005407268],"category_scores_gemma":[0.00040536415,0.00011512641,0.000038480473,0.00050747563,0.00011187775,0.00018295836,0.000069347094,0.0007211714,0.000056952707],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027893344,0.0006443185,0.26111713,0.001387487,0.0004228497,0.00040333526,0.027643623,0.028672442,0.23677653,0.02278391,0.37951198,0.040357463],"study_design_scores_gemma":[0.0023299702,0.00039393743,0.0531153,0.000088905224,0.00014102002,0.00013141923,0.0037702473,0.04604613,0.005425101,0.0018504818,0.8862562,0.00045126016],"about_ca_topic_score_codex":0.000022719725,"about_ca_topic_score_gemma":0.0000010280432,"teacher_disagreement_score":0.50674427,"about_ca_system_score_codex":0.00015636798,"about_ca_system_score_gemma":0.00033472438,"threshold_uncertainty_score":0.59205794},"labels":[],"label_agreement":null},{"id":"W4220759745","doi":"10.21203/rs.3.rs-1446196/v1","title":"A radiomics-based machine learning pipeline to distinguish between metastatic and healthy bone using lesion-center-based geometric regions of interest","year":2022,"lang":"en","type":"preprint","venue":"Research Square","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre; McGill University","funders":"McGill University Health Centre; McGill University","keywords":"Radiomics; Artificial intelligence; Segmentation; Computer science; Region of interest; Pipeline (software); Feature selection; Medicine; Pattern recognition (psychology); Machine learning","score_opus":0.22219214741209486,"score_gpt":0.4651025672261061,"score_spread":0.24291041981401124,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220759745","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8907115,0.0038455387,0.08570366,0.01616006,0.0002719898,0.0025233438,0.00050476496,0.00014819189,0.0001309829],"genre_scores_gemma":[0.9775173,0.00022925889,0.019441206,0.0004702912,0.00035407572,0.00010568559,0.0015429417,0.0001623098,0.00017693722],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9935407,0.0016150811,0.0011516458,0.0011127879,0.0015691421,0.0010106537],"domain_scores_gemma":[0.99433994,0.0025068175,0.000489846,0.0009226805,0.00065728603,0.0010834538],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0062214304,0.00046920215,0.0015245095,0.0040008035,0.00058958674,0.00012199322,0.00048118387,0.0001835871,0.00022208516],"category_scores_gemma":[0.014297256,0.00044975022,0.00033410636,0.0022688955,0.00040967122,0.000035428664,0.0014925532,0.00594357,0.000004169521],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0041668843,0.003416709,0.8054456,0.03695493,0.00079266663,0.0021891184,0.0014048481,0.058588415,0.0025216567,0.00029489177,0.005673147,0.0785511],"study_design_scores_gemma":[0.0122375395,0.005380809,0.020327682,0.011316699,0.0007394297,0.00016516323,0.0009686011,0.8968579,0.00032553682,0.00040030852,0.05001962,0.0012607158],"about_ca_topic_score_codex":0.0031957736,"about_ca_topic_score_gemma":0.000043807002,"teacher_disagreement_score":0.8382695,"about_ca_system_score_codex":0.0008326459,"about_ca_system_score_gemma":0.0013791717,"threshold_uncertainty_score":0.99979544},"labels":[],"label_agreement":null},{"id":"W4220761695","doi":"10.1002/jha2.421","title":"A prognostic model integrating PET‐derived metrics and image texture analyses with clinical risk factors from GOYA","year":2022,"lang":"en","type":"article","venue":"eJHaem","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Spinal Cord Injury BC; University of British Columbia; BC Cancer Agency","funders":"F. Hoffmann-La Roche","keywords":"Texture (cosmology); Computer science; Image (mathematics); Artificial intelligence","score_opus":0.04346131077421968,"score_gpt":0.3716677394525217,"score_spread":0.328206428678302,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220761695","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9675487,0.000508988,0.030310694,0.0006877196,0.00011307438,0.00023013877,0.000044445682,0.00008929615,0.00046691604],"genre_scores_gemma":[0.96070147,0.00009550491,0.03837621,0.0003884257,0.00013399441,0.000017512715,0.00009961363,0.000037503505,0.0001497587],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99834883,0.00020958747,0.0003459944,0.0004220608,0.00043562404,0.00023790597],"domain_scores_gemma":[0.9984556,0.00079285813,0.00020325276,0.00024550682,0.00006163633,0.00024114082],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005424009,0.00019289905,0.000483585,0.00014750533,0.00029221462,0.000054044227,0.00012705819,0.000038724,0.0001353328],"category_scores_gemma":[0.0028752892,0.00012949883,0.000109326334,0.00038746538,0.00017284717,0.00006454208,0.0001597713,0.0015600554,0.0000022036725],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019035762,0.00028121687,0.9570269,0.000034281522,0.00046119446,0.00048242934,0.0020544734,0.0019246045,0.002444403,0.000044415257,0.0010085047,0.03404722],"study_design_scores_gemma":[0.0017008972,0.0005003979,0.1128095,0.00006367604,0.00079898775,0.000067663335,0.003266213,0.8795471,0.000065378605,0.000318924,0.00062983343,0.00023138268],"about_ca_topic_score_codex":0.00050094124,"about_ca_topic_score_gemma":0.000014114829,"teacher_disagreement_score":0.87762254,"about_ca_system_score_codex":0.00005130942,"about_ca_system_score_gemma":0.00012122502,"threshold_uncertainty_score":0.67777514},"labels":[],"label_agreement":null},{"id":"W4220777195","doi":"10.1038/s41379-022-01042-6","title":"USCAP 2022 Abstracts: Informatics (977-1017)","year":2022,"lang":"en","type":"article","venue":"Modern Pathology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Health Services; University of Alberta; University of Calgary; University of Alberta Hospital; Alberta Hospital Edmonton","funders":"Foundation Medicine","keywords":"Informatics; Medicine; Medical physics; Pathology; Computer science; Engineering","score_opus":0.010515315182583376,"score_gpt":0.2724443975795147,"score_spread":0.26192908239693136,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220777195","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9596806,0.0004426586,0.011500713,0.004541207,0.00063355,0.00022061482,0.000015858392,0.00013442576,0.022830324],"genre_scores_gemma":[0.98505235,0.00004216034,0.0043262215,0.0073835705,0.00014812604,0.00005165569,0.000099544646,0.000031192638,0.002865177],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987153,0.000077974124,0.00038892022,0.0001745699,0.00031761976,0.0003256084],"domain_scores_gemma":[0.99930185,0.000058583682,0.000135596,0.00033776494,0.000030374782,0.00013585477],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006605538,0.00012248686,0.00027404202,0.00014102693,0.00022652194,0.0000129108885,0.00016486295,0.00005950064,0.0008329268],"category_scores_gemma":[0.00019608355,0.0001160048,0.00008252924,0.0001170551,0.00009571057,0.000050376133,0.0002123387,0.0009700314,0.00006707569],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007146481,0.0017373352,0.05479606,0.00062814815,0.0003439754,0.009841992,0.032209996,0.073289335,0.06406046,0.004609641,0.078742154,0.67902625],"study_design_scores_gemma":[0.004348712,0.00094858656,0.028284084,0.000031154086,0.00017445085,0.010408842,0.0017204302,0.47968316,0.00027178164,0.0053977943,0.46821448,0.0005165275],"about_ca_topic_score_codex":0.000015306457,"about_ca_topic_score_gemma":0.0000010439027,"teacher_disagreement_score":0.6785097,"about_ca_system_score_codex":0.00008533134,"about_ca_system_score_gemma":0.00008729109,"threshold_uncertainty_score":0.9119964},"labels":[],"label_agreement":null},{"id":"W4220807877","doi":"10.21203/rs.3.rs-1409681/v1","title":"Prognostic value of PET/CT and MR-based baseline radiomics among patients with Nasopharyngeal Carcinoma","year":2022,"lang":"en","type":"preprint","venue":"Research Square","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University Health Network","funders":"","keywords":"Medicine; Nasopharyngeal carcinoma; Radiomics; Radiology; Univariate analysis; Nuclear medicine; PET-CT; Multivariate analysis; Overall survival; Radiation therapy; Oncology; Computed tomography; Internal medicine","score_opus":0.0205505498543136,"score_gpt":0.33578985820386265,"score_spread":0.31523930834954905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220807877","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9947583,0.000903038,0.00021603303,0.0009962786,0.00015450413,0.0022950901,0.00018134699,0.000058437647,0.00043694436],"genre_scores_gemma":[0.9949769,0.000102718135,0.002717957,0.00010403155,0.00016686735,0.00021653844,0.0014397532,0.0001125616,0.0001626797],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99495333,0.00084294804,0.00051011797,0.0008351923,0.0021859962,0.000672394],"domain_scores_gemma":[0.9967083,0.0010859233,0.00022457875,0.00079319894,0.0006478078,0.000540239],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0027279195,0.00035067383,0.00080581434,0.00072240096,0.0002489934,0.000064371816,0.00035772228,0.000042292264,0.00031254647],"category_scores_gemma":[0.0026260386,0.00028741488,0.00015661417,0.0004719994,0.00071237626,0.00004902731,0.00081508106,0.0037355754,0.0000021926712],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00059640186,0.00055330043,0.9877248,0.0043297373,0.00012913151,0.0019534563,0.00011351821,0.0017888026,0.000032383843,0.00007080269,0.0006611227,0.0020465788],"study_design_scores_gemma":[0.0044120722,0.0015785136,0.8204608,0.0018164725,0.00019896003,0.000082188046,0.00015715505,0.1700798,0.000086791406,0.00007318525,0.00074547675,0.00030861542],"about_ca_topic_score_codex":0.00088848156,"about_ca_topic_score_gemma":0.000008135659,"teacher_disagreement_score":0.16829099,"about_ca_system_score_codex":0.0003160635,"about_ca_system_score_gemma":0.00121985,"threshold_uncertainty_score":0.9999578},"labels":[],"label_agreement":null},{"id":"W4220943451","doi":"10.1002/ima.22724","title":"Machine learning based on automated breast volume scanner (<scp>ABVS</scp>) radiomics for differential diagnosis of benign and malignant <scp>BI‐RADS</scp> 4 lesions","year":2022,"lang":"en","type":"article","venue":"International Journal of Imaging Systems and Technology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Sun Yat-sen University","keywords":"Medicine; BI-RADS; Radiology; McNemar's test; Biopsy; Breast MRI; Differential diagnosis; Predictive value; Breast cancer; Breast biopsy; Prospective cohort study; Cancer; Pathology; Internal medicine; Mammography","score_opus":0.006079978347424159,"score_gpt":0.25417710919572345,"score_spread":0.2480971308482993,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220943451","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9734539,0.003121583,0.01329667,0.007992532,0.0014302639,0.0003404028,0.00013608208,0.00014567544,0.000082918756],"genre_scores_gemma":[0.998026,0.00020714462,0.0009602505,0.00018140984,0.00023451065,0.000040732204,0.000039534505,0.000046285764,0.00026410076],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99799806,0.000115994946,0.00074129837,0.0002900821,0.00056653755,0.00028800435],"domain_scores_gemma":[0.9979623,0.00051426864,0.0007868412,0.00015038367,0.00043686014,0.00014937508],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007305036,0.00021712568,0.00059814414,0.0012044306,0.00022580252,0.00008215866,0.00031193005,0.00009128296,0.000008897564],"category_scores_gemma":[0.0012679228,0.00018461801,0.00014260811,0.00022185106,0.00019500793,0.00008215355,0.00016183674,0.00082990946,4.5189321e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016284776,0.00083505444,0.9095149,0.00037557943,0.0011122447,0.00082902785,0.0005022418,0.009646601,0.02168416,0.0046679447,0.012273865,0.038395554],"study_design_scores_gemma":[0.004766267,0.00072571775,0.011498667,0.0008429885,0.00023009564,0.008149312,0.0009803644,0.9393014,0.0006242966,0.00021936008,0.032585453,0.00007609566],"about_ca_topic_score_codex":0.00013987957,"about_ca_topic_score_gemma":8.489677e-7,"teacher_disagreement_score":0.9296548,"about_ca_system_score_codex":0.00014928618,"about_ca_system_score_gemma":0.00012485472,"threshold_uncertainty_score":0.7528504},"labels":[],"label_agreement":null},{"id":"W4220992462","doi":"10.3390/curroncol29030159","title":"Radiomic and Artificial Intelligence Analysis with Textural Metrics Extracted by Contrast-Enhanced Mammography and Dynamic Contrast Magnetic Resonance Imaging to Detect Breast Malignant Lesions","year":2022,"lang":"en","type":"article","venue":"Current Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Cancer Institute","keywords":"Receiver operating characteristic; Kurtosis; Feature selection; Artificial intelligence; Linear discriminant analysis; Medicine; Pattern recognition (psychology); Breast MRI; Magnetic resonance imaging; Univariate; Mammography; Computer science; Radiology; Breast cancer; Machine learning; Multivariate statistics; Mathematics; Statistics; Cancer","score_opus":0.017558070483443575,"score_gpt":0.3272314085717398,"score_spread":0.3096733380882962,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220992462","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8735729,0.0259747,0.09582152,0.003405084,0.00032510835,0.00065283995,0.00012726786,0.00007148658,0.000049114915],"genre_scores_gemma":[0.9965239,0.00070964196,0.0020958355,0.00037042546,0.000051709827,0.00010666216,0.00008125754,0.000027399692,0.000033167307],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.997791,0.00023728608,0.00046494143,0.00065268995,0.00034177,0.00051232026],"domain_scores_gemma":[0.9987204,0.00037626468,0.0001637783,0.00022715077,0.00010434892,0.0004080214],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005507701,0.00026130458,0.00068650075,0.0008146018,0.00034041645,0.000053318585,0.00015613876,0.000048805883,0.00010851988],"category_scores_gemma":[0.00019683414,0.00022169371,0.00009772951,0.0017783869,0.00037840198,0.000058465375,0.00013495472,0.0008048892,0.0000016416266],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005791902,0.00020377136,0.024342177,0.000028581522,0.00010200628,0.00009835036,0.00035518032,0.00007693939,0.021308683,0.000057522495,0.00024418844,0.9526034],"study_design_scores_gemma":[0.0047356645,0.0039062775,0.5189451,0.00025796724,0.00433858,0.004023949,0.0027034755,0.42911085,0.00077656034,0.0004666287,0.029426955,0.0013079877],"about_ca_topic_score_codex":0.0000806845,"about_ca_topic_score_gemma":0.000067494955,"teacher_disagreement_score":0.95129544,"about_ca_system_score_codex":0.00021013209,"about_ca_system_score_gemma":0.00011597523,"threshold_uncertainty_score":0.90404075},"labels":[],"label_agreement":null},{"id":"W4220993128","doi":"10.18280/isi.270117","title":"Federated Learning for Medical Imaging: An Updated State of the Art","year":2022,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Convolutional neural network; Artificial intelligence; Deep learning; Medical imaging; Machine learning; Training set; Federated learning; State (computer science); Artificial neural network; Algorithm","score_opus":0.007982630205686642,"score_gpt":0.26216131283236743,"score_spread":0.2541786826266808,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220993128","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9130612,0.00007273069,0.07684076,0.0027708712,0.0006464679,0.0008722154,0.000021998441,0.00020693257,0.0055068475],"genre_scores_gemma":[0.99688977,0.0000056160134,0.000521124,0.0014603862,0.000047480877,0.000065827255,0.0005972456,0.000018287343,0.0003942726],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998333,0.00014610932,0.0005604583,0.0001067328,0.0006145874,0.00023912633],"domain_scores_gemma":[0.9991248,0.00006010423,0.0003196253,0.00014498939,0.00021836185,0.00013209452],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012398144,0.000115333074,0.00022538663,0.00013893073,0.00062947854,0.000066875626,0.00017028763,0.000030861134,0.0003034348],"category_scores_gemma":[0.0009597001,0.0000887888,0.00009089645,0.00033197392,0.00016525037,0.0004931568,0.00011514306,0.0005266845,0.0000059830336],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00069801183,0.00021227222,0.04244886,0.0005740202,0.00018447555,0.000015088222,0.009095551,0.01518305,0.0028404996,0.00090615783,0.02344787,0.90439415],"study_design_scores_gemma":[0.0018378237,0.00023975056,0.011336643,0.0000980194,0.00004893994,0.0002957735,0.001379798,0.8503887,0.00067568343,0.0006200236,0.13292721,0.00015163873],"about_ca_topic_score_codex":0.0000475166,"about_ca_topic_score_gemma":0.0000023908192,"teacher_disagreement_score":0.9042425,"about_ca_system_score_codex":0.00016779003,"about_ca_system_score_gemma":0.00029685913,"threshold_uncertainty_score":0.48415035},"labels":[],"label_agreement":null},{"id":"W4221054875","doi":"10.1016/j.acra.2022.03.003","title":"The Importance of Data Quality in the Nascent Algorithmic Age of Radiology","year":2022,"lang":"en","type":"editorial","venue":"Academic Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University Health Network","funders":"","keywords":"Convolutional neural network; Computer science; Artificial intelligence; Deep learning; Generalizability theory; Machine learning; Medical physics; Data science; Medicine; Psychology","score_opus":0.037008250386528115,"score_gpt":0.39530660749331675,"score_spread":0.35829835710678865,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4221054875","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.063348345,0.06990948,0.000396963,0.03075688,0.8302234,0.002573034,0.00091370323,0.0000744082,0.001803801],"genre_scores_gemma":[0.02114005,0.14023253,0.0015723549,0.0034109731,0.8197496,0.0002883156,0.012347998,0.00019621199,0.0010619482],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9934856,0.0023257409,0.0018875529,0.0008028854,0.0008863673,0.0006118475],"domain_scores_gemma":[0.98630893,0.010106505,0.0013078742,0.0021107895,0.0000793288,0.00008659984],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.012651467,0.00033164275,0.001552569,0.0003274072,0.00013210828,0.0000048181982,0.0034277884,0.0011654171,0.00006677483],"category_scores_gemma":[0.013435317,0.00019713701,0.00018375307,0.0006137888,0.0014607193,0.00004926555,0.0006938835,0.008662721,0.0000017600748],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024720977,0.000047353366,0.008988164,0.00019226554,0.00019826737,0.00013783747,0.00058985344,0.000013927697,0.00044833677,0.0009456788,0.9839462,0.0042449166],"study_design_scores_gemma":[0.0014572052,0.00025146257,0.0049207686,0.00008444627,0.00017068192,0.0003725724,0.00036367663,0.00044685442,0.000003881217,0.00085197185,0.9909058,0.00017067906],"about_ca_topic_score_codex":0.0005714208,"about_ca_topic_score_gemma":0.00003766428,"teacher_disagreement_score":0.07032306,"about_ca_system_score_codex":0.0001493668,"about_ca_system_score_gemma":0.00070452644,"threshold_uncertainty_score":0.99487495},"labels":[],"label_agreement":null},{"id":"W4221076966","doi":"10.1109/tmi.2022.3157048","title":"Author’s Reply to “MoNuSAC2020: A Multi-Organ Nuclei Segmentation and Classification Challenge”","year":2022,"lang":"en","type":"letter","venue":"IEEE Transactions on Medical Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Segmentation; Metric (unit); Header; Swap (finance); Artificial intelligence; Computation; Data science; Programming language","score_opus":0.030341224745854777,"score_gpt":0.32470714125378103,"score_spread":0.29436591650792626,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4221076966","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00043088614,0.00016566912,0.31165645,0.6850098,0.001407193,0.000657048,0.000027285982,0.00027626907,0.0003694237],"genre_scores_gemma":[0.02420625,0.0004713286,0.009363023,0.9578449,0.001779255,0.00039844416,0.00024688768,0.0002762279,0.005413668],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99521595,0.0003222634,0.0007741649,0.0011565605,0.0018857445,0.0006453344],"domain_scores_gemma":[0.99791837,0.0003571924,0.00021258015,0.000648307,0.00010892431,0.00075465493],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00096552714,0.00051277835,0.00069762656,0.0007417462,0.0005289666,0.00011181247,0.00031200305,0.00038869397,0.0028472021],"category_scores_gemma":[0.00029725698,0.0005045941,0.00022711616,0.0004595312,0.00026591675,0.00013233616,0.000013408831,0.0067121135,0.00012887892],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011840631,0.0003664811,0.000058853017,0.00042727822,0.000210652,0.0017765606,0.0014891672,0.000075704585,0.0012054289,0.000005902407,0.60386115,0.39040443],"study_design_scores_gemma":[0.0023035863,0.00030328953,0.00019775296,0.00069517887,0.0005004984,0.000858052,0.0005943105,0.094005264,0.00018287088,0.000024366956,0.8997139,0.0006209825],"about_ca_topic_score_codex":0.00016700328,"about_ca_topic_score_gemma":0.000005748914,"teacher_disagreement_score":0.38978344,"about_ca_system_score_codex":0.00046528032,"about_ca_system_score_gemma":0.00031653768,"threshold_uncertainty_score":0.99974054},"labels":[],"label_agreement":null},{"id":"W4221108361","doi":"10.3390/curroncol29030146","title":"Applications of Artificial Intelligence in Screening, Diagnosis, Treatment, and Prognosis of Colorectal Cancer","year":2022,"lang":"en","type":"review","venue":"Current Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":74,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Key Research and Development Program of Sichuan Province; National Natural Science Foundation of China","keywords":"Medicine; Colorectal cancer; Clinical Practice; Artificial intelligence; Cancer; Intensive care medicine; Internal medicine; Computer science; Family medicine","score_opus":0.17733424046789512,"score_gpt":0.4962540904952588,"score_spread":0.31891985002736367,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4221108361","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00050973566,0.99683183,0.0006397637,0.00011385954,0.00022726452,0.0014855512,0.00006555069,0.000010838466,0.00011562316],"genre_scores_gemma":[0.00029963037,0.99459386,0.0007405205,0.0000067501173,0.00011597247,0.0040740157,0.00014002084,0.000021697475,0.0000075229977],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984955,0.0001754055,0.0007195281,0.00031488948,0.00011962609,0.00017502473],"domain_scores_gemma":[0.9986606,0.0005934024,0.0004974151,0.00012681476,0.000033821212,0.00008790065],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002727431,0.00019177068,0.0014939515,0.00032841662,0.00003321465,0.0000029756427,0.00011931082,0.00012471143,0.00027333206],"category_scores_gemma":[0.00018776268,0.00015497222,0.00018793864,0.0004270395,0.00026591105,0.000012750235,0.00009200045,0.000515654,8.38308e-7],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001731676,0.0009124236,0.008842159,0.0048132916,0.000096490345,0.0000047536305,0.0001475679,0.0000018251743,5.595284e-7,0.00020993073,0.00005904046,0.98489463],"study_design_scores_gemma":[0.00017646319,0.0005829332,0.00013012183,0.0026151857,0.00086730183,0.000026350655,0.000051068746,0.00037051327,0.000005878566,0.00003833664,0.9950362,0.000099651596],"about_ca_topic_score_codex":0.0001702613,"about_ca_topic_score_gemma":0.000050004095,"teacher_disagreement_score":0.9949772,"about_ca_system_score_codex":0.00027049973,"about_ca_system_score_gemma":0.0005246587,"threshold_uncertainty_score":0.63195837},"labels":[],"label_agreement":null},{"id":"W4221164117","doi":"10.1109/nss/mic44845.2022.10399050","title":"Tensor Radiomics: Paradigm for Systematic Incorporation of Multi-Flavoured Radiomics Features","year":2022,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency; University of British Columbia","funders":"Canadian Institutes of Health Research; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; Eisai; Sanofi; AstraZeneca; Natural Sciences and Engineering Research Council of Canada; Amgen; Pfizer; BC Cancer Foundation; National Science Foundation","keywords":"Radiomics; Artificial intelligence; Pattern recognition (psychology); Computer science; Voxel; Reproducibility; Convolutional neural network; Mathematics; Nuclear medicine; Medicine; Statistics","score_opus":0.017684086909222612,"score_gpt":0.2952200234248548,"score_spread":0.2775359365156322,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4221164117","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5346589,0.00393262,0.42011684,0.021637395,0.002431872,0.014396571,0.00017504297,0.0006343486,0.0020163755],"genre_scores_gemma":[0.9385052,0.000027907867,0.05618634,0.0013838876,0.00018364158,0.00038424582,0.00017747437,0.00006414024,0.0030871674],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99831957,0.00014114319,0.0006175251,0.00029134634,0.00037753492,0.00025287783],"domain_scores_gemma":[0.9987257,0.00029521657,0.00037688744,0.00037225054,0.000083868916,0.00014607834],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010392421,0.00018119134,0.00071547314,0.0002499064,0.00021298195,0.00002195959,0.00019425714,0.00006428975,0.00006664913],"category_scores_gemma":[0.0007350303,0.00014816086,0.00023010837,0.00024312417,0.00008302743,0.00005871246,0.0000622647,0.00037256564,0.000002404959],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0075296815,0.0068965564,0.048397735,0.16821939,0.0055329874,0.00038265737,0.016531806,0.058612704,0.31499067,0.19051753,0.16234781,0.020040482],"study_design_scores_gemma":[0.015544216,0.0014877558,0.0044312403,0.0017778175,0.0010659321,0.0011919073,0.0026101987,0.9597614,0.0046018194,0.002252395,0.0045756986,0.00069962564],"about_ca_topic_score_codex":0.000059518883,"about_ca_topic_score_gemma":0.0000034758643,"teacher_disagreement_score":0.9011487,"about_ca_system_score_codex":0.00017128441,"about_ca_system_score_gemma":0.00015273174,"threshold_uncertainty_score":0.6041824},"labels":[],"label_agreement":null},{"id":"W4223430324","doi":"10.1038/s41746-022-00592-y","title":"Machine learning for medical imaging: methodological failures and recommendations for the future","year":2022,"lang":"en","type":"review","venue":"npj Digital Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":593,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute; Institut National de la Recherche Scientifique","funders":"Novo Nordisk Fonden; Agence Nationale de la Recherche","keywords":"Medical imaging; Psychology; Computer science; Data science; Engineering ethics; Artificial intelligence; Medical physics; Medicine; Engineering","score_opus":0.10375791139864335,"score_gpt":0.4339280365929593,"score_spread":0.330170125194316,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4223430324","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.1881414e-7,0.8506236,0.021318167,0.12364536,0.0012359296,0.0020048006,0.0000898205,0.00013113522,0.00095094304],"genre_scores_gemma":[0.000015423031,0.9840838,0.003109542,0.0027420423,0.0042821686,0.001007613,0.0027571577,0.00013873995,0.0018635647],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99665284,0.000291466,0.0010149821,0.0007546689,0.0007451072,0.00054093736],"domain_scores_gemma":[0.9844901,0.014075771,0.00044738542,0.00039959635,0.00009075358,0.0004963703],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003334709,0.00057515164,0.0022766902,0.00026231495,0.0006411668,0.00009913933,0.00046379937,0.00027329836,0.0011499228],"category_scores_gemma":[0.019935507,0.00030198824,0.000584203,0.00033501154,0.00056154135,0.00009845938,0.00028092752,0.0024048113,0.0000030746066],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000065599386,0.000049118506,0.000020691035,0.0039612353,0.0002909222,0.000028922788,0.00008144583,4.5833124e-7,9.1891806e-8,0.0018413573,0.034040574,0.9596196],"study_design_scores_gemma":[0.0017674961,0.0004877794,0.0000036815047,0.0033340878,0.0018343508,0.001380518,0.0004025262,0.004588564,2.7683228e-8,0.0005076544,0.9854048,0.00028852167],"about_ca_topic_score_codex":0.000021186732,"about_ca_topic_score_gemma":0.0000019823967,"teacher_disagreement_score":0.95933104,"about_ca_system_score_codex":0.00011152957,"about_ca_system_score_gemma":0.0003046417,"threshold_uncertainty_score":0.9999432},"labels":[],"label_agreement":null},{"id":"W4223439916","doi":"10.1101/2022.04.07.22273504","title":"Histopathological growth patterns of liver metastasis: updated consensus guidelines for pattern scoring, perspectives, and recent mechanistic insights","year":2022,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre; McGill University","funders":"National Cancer Institute; European Regional Development Fund; Engineering and Physical Sciences Research Council; Agència de Gestió d'Ajuts Universitaris i de Recerca; Canadian Institutes of Health Research; Knut och Alice Wallenbergs Stiftelse; Koning Boudewijnstichting; Cancer Research Foundation in Northern Sweden; Generalitat de Catalunya; Umeå Universitet; Vetenskapsrådet; Fondation contre le Cancer; Cancerfonden; McGill University","keywords":"Histopathology; Metastasis; Categorization; Liver cancer; Medicine; Colorectal cancer; Biology; Cancer; Pathology; Computer science; Internal medicine; Artificial intelligence","score_opus":0.07174157681604577,"score_gpt":0.3436748683754575,"score_spread":0.27193329155941176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4223439916","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9493033,0.008929494,0.03241597,0.0067357332,0.0008848827,0.0012371858,0.00018094562,0.00013090344,0.00018156682],"genre_scores_gemma":[0.98189324,0.0053876294,0.010544121,0.0010899995,0.00031952982,0.00017424494,0.00028015889,0.00007920855,0.00023185661],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99715716,0.00026111497,0.0007747264,0.0008953132,0.00059717864,0.00031452632],"domain_scores_gemma":[0.9975346,0.00020017756,0.00046432385,0.0004931667,0.0010790518,0.0002287367],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001222689,0.00038934263,0.0009918634,0.00026901963,0.00012833175,0.000025539162,0.00025303365,0.00018217538,0.0004636086],"category_scores_gemma":[0.0039119325,0.00031583762,0.00021908943,0.00010378133,0.0001696798,0.000014937344,0.00064983533,0.0010895637,0.0000013936673],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0038778833,0.0056940536,0.5743534,0.02567487,0.0064129075,0.013396227,0.023053132,0.0009422954,0.043893993,0.029625358,0.047293387,0.2257825],"study_design_scores_gemma":[0.02486271,0.007245584,0.3835978,0.0074140336,0.014390651,0.003820259,0.012333872,0.18765773,0.0075448984,0.021597799,0.3234219,0.0061127692],"about_ca_topic_score_codex":0.00034276713,"about_ca_topic_score_gemma":0.000012984324,"teacher_disagreement_score":0.2761285,"about_ca_system_score_codex":0.00021437908,"about_ca_system_score_gemma":0.00020595618,"threshold_uncertainty_score":0.99992937},"labels":[],"label_agreement":null},{"id":"W4223652179","doi":"10.52987/icsp.2022","title":"ICSPConference Proceedings 2022","year":2022,"lang":"en","type":"paratext","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Universiti Malaysia Sabah; Eurostars; Canadian Patient Safety Institute","keywords":"Computer science","score_opus":0.01415563163550097,"score_gpt":0.30384858110433277,"score_spread":0.2896929494688318,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4223652179","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012428875,0.0012901116,0.0003302327,0.005210145,0.0022843801,0.0003913617,0.000018358598,0.00009615674,0.98913634],"genre_scores_gemma":[0.0036913785,0.0016091773,0.0013304502,0.0048869466,0.0010169054,0.000091099144,0.0005392549,0.00008957586,0.98674524],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981249,0.000015996055,0.00032280016,0.00053179316,0.0006312198,0.0003733072],"domain_scores_gemma":[0.9992046,0.000043682183,0.0001546077,0.0002279028,0.000107638654,0.00026157248],"candidate_categories":["research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0003205394,0.00028857554,0.0005991943,0.00023481136,0.00015941051,0.00006273265,0.00027001026,0.00018351056,0.29332173],"category_scores_gemma":[0.00020922103,0.00024368233,0.00017457314,0.0002600711,0.00009208063,0.00004053349,0.00024736742,0.0024100845,0.005129312],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026247197,0.0000594486,0.00017367002,0.00031387177,0.00007881783,0.000034098677,0.000069598915,0.0000030337014,0.0003360761,0.0009385653,0.9879566,0.010010015],"study_design_scores_gemma":[0.0005281236,0.0001759775,0.00010527152,0.00012867898,0.00010197586,0.00022236035,0.00010728891,0.0016171787,0.000055115186,0.00004491192,0.9966554,0.00025771488],"about_ca_topic_score_codex":0.00008702196,"about_ca_topic_score_gemma":3.1702925e-7,"teacher_disagreement_score":0.28819242,"about_ca_system_score_codex":0.000158721,"about_ca_system_score_gemma":0.00041486855,"threshold_uncertainty_score":0.9998914},"labels":[],"label_agreement":null},{"id":"W4224088275","doi":"10.3390/tomography8020091","title":"Noise-Based Image Harmonization Significantly Increases Repeatability and Reproducibility of Radiomics Features in PET Images: A Phantom Study","year":2022,"lang":"en","type":"article","venue":"Tomography","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; Lawson Health Research Institute; BC Cancer Agency; University Health Network; University of Toronto; University of British Columbia","funders":"Canadian Institutes of Health Research; National Cancer Institute; National Institutes of Health; Ontario Institute for Cancer Research; University of Iowa; Geoffrey Beene Cancer Research Center; Memorial Sloan-Kettering Cancer Center","keywords":"Repeatability; Imaging phantom; Reproducibility; Artificial intelligence; Scanner; Robustness (evolution); Feature (linguistics); Pattern recognition (psychology); Noise (video); Image noise; Intraclass correlation; Computer science; Computer vision; Image texture; Image processing; Mathematics; Image (mathematics); Nuclear medicine; Statistics; Medicine","score_opus":0.00931209864084437,"score_gpt":0.2763780063939373,"score_spread":0.2670659077530929,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4224088275","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99704957,0.0005716889,0.00024424546,0.0006991831,0.000084823674,0.001079156,0.000054328466,0.00007709459,0.00013991196],"genre_scores_gemma":[0.99637985,0.000023598841,0.0031192484,0.00022214756,0.000039293216,0.00007897511,0.00008658924,0.000025705376,0.000024594707],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99724734,0.0005396951,0.0005079641,0.0010322412,0.00044487344,0.00022791713],"domain_scores_gemma":[0.99811834,0.00023075545,0.00018810079,0.0012250505,0.0001051063,0.00013267114],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0039462666,0.00018292047,0.00050363695,0.0004892967,0.00013740535,0.000024123516,0.00015074309,0.000022933527,0.00008195812],"category_scores_gemma":[0.0020349538,0.0001702141,0.00012806297,0.0010677204,0.00029426816,0.00008288572,0.00012296201,0.00052989,1.9890474e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00074848894,0.0024394777,0.96975815,0.00020247645,0.000053674667,0.00016884999,0.0007196246,0.00010014444,0.023231758,0.000007653535,0.00029116435,0.002278524],"study_design_scores_gemma":[0.00351904,0.0007317361,0.9872396,0.000038678416,0.00015102164,0.00007822177,0.0014707237,0.0025820322,0.0037965113,0.00012461269,0.00009431804,0.00017348632],"about_ca_topic_score_codex":0.0017297976,"about_ca_topic_score_gemma":0.000021168391,"teacher_disagreement_score":0.019435246,"about_ca_system_score_codex":0.00006291679,"about_ca_system_score_gemma":0.00011993789,"threshold_uncertainty_score":0.69411296},"labels":[],"label_agreement":null},{"id":"W4224222733","doi":"10.1148/radiol.212137","title":"MRI Radiogenomics of Pediatric Medulloblastoma: A Multicenter Study","year":2022,"lang":"en","type":"article","venue":"Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":74,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Centre Hospitalier Universitaire Sainte-Justine; SickKids Foundation; Hospital for Sick Children","funders":"National Cancer Institute; Cancer Research UK; National Institutes of Health; Brain Tumour Charity; Canadian Institutes of Health Research; National Institute for Health and Care Research; American Brain Tumor Association","keywords":"Radiogenomics; Medicine; Medulloblastoma; Mann–Whitney U test; Classifier (UML); Artificial intelligence; Receiver operating characteristic; Binary classification; Machine learning; Oncology; Internal medicine; Pathology; Radiology; Radiomics; Computer science","score_opus":0.009778225191930154,"score_gpt":0.27943010155888137,"score_spread":0.2696518763669512,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4224222733","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9961646,0.0006463067,0.0004988819,0.0010008638,0.00060008594,0.00046852074,0.000007102418,0.00004324034,0.00057039334],"genre_scores_gemma":[0.99733627,0.00007140434,0.0012871883,0.00057874655,0.00037802104,0.000047666505,0.000016141656,0.000027068623,0.00025752434],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99861395,0.0002578562,0.0003633677,0.0002803906,0.0002186038,0.00026580668],"domain_scores_gemma":[0.9992559,0.00014952266,0.00014464413,0.0002947342,0.000033290136,0.00012191791],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00062714424,0.00012063087,0.00044112487,0.00023028582,0.00011524666,0.0000028752486,0.00018565159,0.000037182002,0.00043721093],"category_scores_gemma":[0.00018662214,0.00011079392,0.000110554836,0.00023480908,0.00008308374,0.000016438218,0.00015846605,0.00051663956,0.00000961201],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044035882,0.0012149044,0.98295486,0.000047853777,0.00024058022,0.00035040083,0.0020205248,0.001376271,0.0022168537,0.00018357314,0.006948458,0.002005347],"study_design_scores_gemma":[0.028401628,0.010956419,0.8174483,0.000014090235,0.0018178263,0.0035149967,0.00587336,0.06479135,0.00019767437,0.00022307581,0.0659797,0.0007815678],"about_ca_topic_score_codex":0.00004457036,"about_ca_topic_score_gemma":0.0000011895752,"teacher_disagreement_score":0.16550656,"about_ca_system_score_codex":0.0001036219,"about_ca_system_score_gemma":0.00009961347,"threshold_uncertainty_score":0.4787153},"labels":[],"label_agreement":null},{"id":"W4224223045","doi":"10.3389/fmed.2022.894726","title":"Using Deep Learning Radiomics to Distinguish Cognitively Normal Adults at Risk of Alzheimer’s Disease From Normal Control: An Exploratory Study Based on Structural MRI","year":2022,"lang":"en","type":"article","venue":"Frontiers in Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Pfizer; Novartis Pharmaceuticals Corporation; Biogen; Eli Lilly and Company; Bristol-Myers Squibb; BioClinica; U.S. Department of Defense; Meso Scale Diagnostics; Alzheimer's Disease Neuroimaging Initiative; Eisai; National Institute on Aging; Alzheimer's Association","keywords":"Artificial intelligence; Alzheimer's Disease Neuroimaging Initiative; Support vector machine; Positron emission tomography; Neuroimaging; Pattern recognition (psychology); Medicine; Machine learning; Computer science; Alzheimer's disease; Disease; Nuclear medicine; Psychology; Pathology; Neuroscience","score_opus":0.015614956279333344,"score_gpt":0.287864877587212,"score_spread":0.2722499213078787,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4224223045","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9686215,0.00092339044,0.026799668,0.0005837254,0.001574854,0.0012083487,0.00010738642,0.000074661926,0.00010645263],"genre_scores_gemma":[0.9881657,0.000016568707,0.008978844,0.0015492251,0.0007495304,0.00007114588,0.00036435347,0.000086637345,0.000017990536],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9956196,0.0010670291,0.00082228327,0.0007374058,0.0012008994,0.0005527897],"domain_scores_gemma":[0.9978651,0.00028721124,0.00046406465,0.00045528737,0.00015357003,0.00077478145],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0016187584,0.0003877471,0.0011207121,0.00060930144,0.00048559104,0.000012590018,0.00030688927,0.000060379443,0.00024794266],"category_scores_gemma":[0.001986899,0.00035401675,0.00012108871,0.0005170526,0.00029470044,0.00010659568,0.00016844072,0.0014277757,0.0000012326411],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.009068847,0.00036764148,0.8462204,0.000034758374,0.00024849488,0.0006000454,0.007852952,0.124601744,0.00013765447,0.0000018271261,0.0005583327,0.010307315],"study_design_scores_gemma":[0.014096324,0.0022983856,0.30267558,0.00024492553,0.00097040465,0.000007901583,0.010975474,0.66808665,0.000016138078,0.000018789326,0.00033664232,0.0002727857],"about_ca_topic_score_codex":0.0007503426,"about_ca_topic_score_gemma":0.000046139845,"teacher_disagreement_score":0.5435448,"about_ca_system_score_codex":0.00039372596,"about_ca_system_score_gemma":0.0001643121,"threshold_uncertainty_score":0.99989116},"labels":[],"label_agreement":null},{"id":"W4225080248","doi":"10.1101/2022.04.27.22274369","title":"High-Dimensional Multinomial Multiclass Severity Scoring of COVID-19 Pneumonia Using CT Radiomics Features and Machine Learning Algorithms","year":2022,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Artificial intelligence; Random forest; Computer science; Feature selection; Machine learning; Pattern recognition (psychology); Receiver operating characteristic; Algorithm","score_opus":0.02950441022698212,"score_gpt":0.3141564050143378,"score_spread":0.28465199478735564,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225080248","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99077517,0.0020662956,0.0029534511,0.0017312216,0.0015589896,0.00062589016,0.00008876418,0.0001651816,0.000035047076],"genre_scores_gemma":[0.9487832,0.0003746249,0.048970815,0.0006424183,0.0005287612,0.000025030264,0.00027252643,0.0001272777,0.00027533108],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962398,0.00050400296,0.00080860703,0.0010393367,0.00087175483,0.0005365052],"domain_scores_gemma":[0.9974985,0.00053129473,0.00061954575,0.00056230405,0.000101578145,0.00068677176],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0019282367,0.0005641671,0.0013506385,0.00043851422,0.00046671194,0.00006333813,0.0003361235,0.00021359367,0.00018595108],"category_scores_gemma":[0.0027795068,0.0005455178,0.00029818297,0.00022704153,0.00040382904,0.00006321884,0.0015728452,0.0042303335,0.0000012630402],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00068430445,0.00040071618,0.6716011,0.0030215394,0.0007996343,0.0020906152,0.0015829856,0.24102992,0.059200346,0.00008865519,0.00015576878,0.019344386],"study_design_scores_gemma":[0.004233634,0.00016029489,0.07968471,0.000435109,0.0005638187,0.0019232694,0.00012978564,0.90750074,0.0014657448,0.0001474853,0.0030682092,0.00068721565],"about_ca_topic_score_codex":0.005523499,"about_ca_topic_score_gemma":0.000019200494,"teacher_disagreement_score":0.6664708,"about_ca_system_score_codex":0.00051158876,"about_ca_system_score_gemma":0.00069649745,"threshold_uncertainty_score":0.99969965},"labels":[],"label_agreement":null},{"id":"W4225316186","doi":"10.1164/ajrccm-conference.2022.205.1_meetingabstracts.a1079","title":"Comparison of Feature Selection Methods and Machine Learning Classifiers with CT Radiomics-Based Features for Predicting Chronic Obstructive Pulmonary Disease","year":2022,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Paul's Hospital; Western University; Toronto Metropolitan University","funders":"","keywords":"Radiomics; Feature selection; Pulmonary disease; Artificial intelligence; Computer science; Machine learning; Selection (genetic algorithm); Feature (linguistics); Disease; Pattern recognition (psychology); Medicine; Pathology; Internal medicine","score_opus":0.01654892174967451,"score_gpt":0.3413419133510513,"score_spread":0.32479299160137676,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225316186","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.74857306,0.0076926993,0.23348708,0.0065894383,0.00037760867,0.0018380075,0.000050106133,0.00032721815,0.0010647991],"genre_scores_gemma":[0.9162947,0.000014521144,0.08211294,0.00019348561,0.00012622592,0.00009409008,0.00018116721,0.00004980119,0.00093307876],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984969,0.00025835686,0.00024177258,0.00040872075,0.00030977212,0.00028449512],"domain_scores_gemma":[0.9988899,0.000430554,0.00023604813,0.00013960243,0.00007199287,0.00023189338],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006415707,0.0002044632,0.00047161436,0.00020228927,0.0005077639,0.000021516933,0.00008576197,0.000036616035,0.000054329103],"category_scores_gemma":[0.00039965936,0.00016380368,0.00010405692,0.00030469729,0.00016085726,0.000058981885,0.000056486835,0.0011942848,5.3257665e-8],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0028842974,0.00022079489,0.8027285,0.0007305238,0.0002513286,0.00003622027,0.00035367676,0.05444746,0.017927706,0.0003369467,0.00053049286,0.11955207],"study_design_scores_gemma":[0.0020857519,0.0009403939,0.07973727,0.000074664924,0.00038828238,0.00022495126,0.00068747526,0.9037959,0.0024029738,0.000059453774,0.009421047,0.0001818447],"about_ca_topic_score_codex":0.00008380046,"about_ca_topic_score_gemma":0.000007427003,"teacher_disagreement_score":0.8493484,"about_ca_system_score_codex":0.000254416,"about_ca_system_score_gemma":0.0002689829,"threshold_uncertainty_score":0.667972},"labels":[],"label_agreement":null},{"id":"W4225796813","doi":"","title":"Segmentation of Polyps in Gastrointestinal Tract Images","year":2021,"lang":"en","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Gastrointestinal tract; Segmentation; Computer science; Artificial intelligence; Medicine; Internal medicine","score_opus":0.011365822164276916,"score_gpt":0.26805331074146593,"score_spread":0.25668748857718904,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225796813","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8421691,0.00084908755,0.12454311,0.016889738,0.000100232784,0.00037403574,0.000016785258,0.000077622986,0.014980269],"genre_scores_gemma":[0.83800715,0.00024614157,0.1597039,0.00010170163,0.00002054062,0.000019965084,0.00048177704,0.00003087981,0.0013879632],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.996468,0.0018651722,0.0005656284,0.00047316102,0.00038962162,0.00023840126],"domain_scores_gemma":[0.996912,0.0007207665,0.0004145228,0.00086509454,0.00093924766,0.00014833685],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003241952,0.00020988191,0.000448364,0.00023335297,0.00005976888,0.00010268859,0.00032213374,0.00011044833,0.00017749405],"category_scores_gemma":[0.003095805,0.00022016087,0.00017865849,0.00025750828,0.00019288747,0.00007096788,0.0003929813,0.0010295295,0.0000036836368],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009802103,0.004282966,0.5212016,0.0025429407,0.00013522696,0.0003629203,0.016661115,0.00067258324,0.2482318,0.0046240487,0.0009437285,0.20024306],"study_design_scores_gemma":[0.004348427,0.0000042693405,0.6199732,0.039725102,0.0002530246,0.0008116922,0.0016477042,0.09257931,0.23781252,0.0014004944,0.00063347735,0.0008108053],"about_ca_topic_score_codex":0.0017723371,"about_ca_topic_score_gemma":0.0001581553,"teacher_disagreement_score":0.19943225,"about_ca_system_score_codex":0.0001112262,"about_ca_system_score_gemma":0.0004011792,"threshold_uncertainty_score":0.89779},"labels":[],"label_agreement":null},{"id":"W4225856902","doi":"10.2196/38655","title":"Levels of Autonomous Radiology","year":2022,"lang":"en","type":"preprint","venue":"Interactive Journal of Medical Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Workflow; Modalities; Data science; Computer science; Radiology; Automation; Medicine; Medical physics; Engineering","score_opus":0.0926620856865341,"score_gpt":0.5032429644822688,"score_spread":0.4105808787957347,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225856902","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8987974,0.005356912,0.0060024904,0.07245129,0.0045232642,0.00059116306,0.0000422676,0.000020374804,0.0122148525],"genre_scores_gemma":[0.99375135,0.0016445112,0.0016661288,0.0005796321,0.0015010698,0.000014105587,0.000010363756,0.000049809663,0.0007830169],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98990786,0.0019351405,0.001469948,0.00035863082,0.005798254,0.0005301441],"domain_scores_gemma":[0.99147606,0.004633402,0.0009738944,0.00046331852,0.0015658755,0.00088748016],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.017190691,0.00022370002,0.0013954939,0.0013618863,0.00009112962,0.000031953317,0.0013976354,0.00047644376,0.014843286],"category_scores_gemma":[0.03746965,0.00016997664,0.00055502757,0.00032596194,0.0009007914,0.00006473517,0.0020231197,0.019428834,0.000010961019],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0063068205,0.0034463867,0.012041969,0.002685776,0.005099984,0.02798991,0.00751078,0.0007968878,0.0088814115,0.002085257,0.109007925,0.8141469],"study_design_scores_gemma":[0.019880004,0.017554156,0.09681638,0.023275612,0.0010925732,0.04785564,0.009585211,0.064679004,0.0053968695,0.025273168,0.6872856,0.0013057482],"about_ca_topic_score_codex":0.00020761549,"about_ca_topic_score_gemma":0.000001922268,"teacher_disagreement_score":0.8128411,"about_ca_system_score_codex":0.00077463174,"about_ca_system_score_gemma":0.005607082,"threshold_uncertainty_score":0.9946723},"labels":[],"label_agreement":null},{"id":"W4225985732","doi":"10.1245/s10434-022-11674-2","title":"ASO Visual Abstract: Recurrence After Resection of Pancreatic Cancer – Can Radiomics Predict Patients at Greatest Risk of Liver Metastasis?","year":2022,"lang":"en","type":"article","venue":"Annals of Surgical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Medicine; Surgical oncology; Radiomics; Metastasis; Resection; General surgery; Pancreatic cancer; Radiology; Internal medicine; Oncology; Cancer; Surgery","score_opus":0.031665248788151835,"score_gpt":0.3558008206089354,"score_spread":0.32413557182078356,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225985732","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99520016,0.0016161321,0.000006036508,0.0013930738,0.00027482715,0.00027129325,0.0003039377,0.000010410074,0.00092410855],"genre_scores_gemma":[0.9892905,0.010015193,0.00013205915,0.00017074386,0.00008204693,0.00006026207,0.00008468794,0.00001851494,0.0001459897],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99792933,0.00032161127,0.000690069,0.00027343398,0.0005099438,0.00027561557],"domain_scores_gemma":[0.9980884,0.0005773696,0.000676888,0.00019103823,0.00028733493,0.00017895355],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009815295,0.00014666044,0.00077210896,0.00018524124,0.00007581857,0.0000021390254,0.00012618426,0.00009734028,0.0011886331],"category_scores_gemma":[0.00026846293,0.00012469395,0.00021450745,0.0002836244,0.00034495594,0.000043312895,0.0001592807,0.0005447329,0.0000014595691],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.007220294,0.0019652285,0.8313959,0.00043014757,0.00069977524,0.0002871376,0.0007760284,0.0006272978,0.0006452437,0.000035945683,0.004201674,0.15171528],"study_design_scores_gemma":[0.0058067823,0.009596152,0.8470719,0.00029897754,0.000890439,0.0001485244,0.00011876706,0.0041386145,0.0039864117,0.000093026676,0.12758806,0.00026233136],"about_ca_topic_score_codex":0.0023701452,"about_ca_topic_score_gemma":0.00007697434,"teacher_disagreement_score":0.15145294,"about_ca_system_score_codex":0.0001480196,"about_ca_system_score_gemma":0.00021156315,"threshold_uncertainty_score":0.9997244},"labels":[],"label_agreement":null},{"id":"W4226059105","doi":"10.1016/j.compbiomed.2022.105467","title":"COVID-19 prognostic modeling using CT radiomic features and machine learning algorithms: Analysis of a multi-institutional dataset of 14,339 patients","year":2022,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":73,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency","funders":"Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Coronavirus disease 2019 (COVID-19); Computer science; 2019-20 coronavirus outbreak; Artificial intelligence; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Machine learning; Algorithm; Data mining; Medicine; Virology; Pathology","score_opus":0.035746018200811726,"score_gpt":0.354767890532422,"score_spread":0.3190218723316103,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226059105","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.894195,0.003720146,0.10093405,0.0005229464,0.00020521528,0.00022838991,0.00017609153,0.000013217399,0.000004936664],"genre_scores_gemma":[0.982368,0.00029904023,0.013365343,0.0009318884,0.000039148406,0.000005810751,0.0029791673,0.000007634706,0.0000039912484],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986784,0.00021236954,0.0004461609,0.00032340016,0.00016518414,0.0001744761],"domain_scores_gemma":[0.9991241,0.00033030723,0.00018885612,0.00012693915,0.000039588485,0.00019021644],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00084288773,0.00014617847,0.0006941239,0.0007327015,0.00020299481,0.0000016856839,0.00009788192,0.000041348816,0.000029825402],"category_scores_gemma":[0.0011912734,0.000111638285,0.000045364268,0.0004679177,0.00062029733,0.000026265454,0.00019361883,0.000508505,2.6521947e-8],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019822555,0.00020335388,0.8946664,0.00021848896,0.0005892797,0.00009683858,0.0010125963,0.094196394,0.0007189881,0.00019266004,0.00012371181,0.007783074],"study_design_scores_gemma":[0.0042506177,0.0003955361,0.030355683,0.00009115971,0.0006385447,0.00025814614,0.00011152554,0.9632969,0.000003837554,0.000053242005,0.00045381708,0.00009098977],"about_ca_topic_score_codex":0.0009899517,"about_ca_topic_score_gemma":0.000010688594,"teacher_disagreement_score":0.8691005,"about_ca_system_score_codex":0.00007960026,"about_ca_system_score_gemma":0.00012954845,"threshold_uncertainty_score":0.4552477},"labels":[],"label_agreement":null},{"id":"W4226084777","doi":"10.1007/978-3-030-98253-9_1","title":"Overview of the HECKTOR Challenge at MICCAI 2021: Automatic Head and Neck Tumor Segmentation and Outcome Prediction in PET/CT Images","year":2022,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":91,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Contouring; Computer science; Artificial intelligence; Task (project management); Segmentation; Sørensen–Dice coefficient; Head and neck; Ground truth; Pattern recognition (psychology); Image segmentation; Computer vision; Medicine; Computer graphics (images)","score_opus":0.02126084119170922,"score_gpt":0.29995053990377396,"score_spread":0.2786896987120647,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226084777","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94793856,0.013038961,0.021201888,0.012057578,0.0021165127,0.0019931493,0.000040610532,0.00007224032,0.0015405115],"genre_scores_gemma":[0.9638271,0.001496314,0.03111708,0.0025165358,0.00026977144,0.000025905865,0.000020442943,0.000053687738,0.00067321747],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983499,0.000047821854,0.00040858777,0.00048466198,0.0005097907,0.00019920792],"domain_scores_gemma":[0.99918896,0.00020715044,0.00020054124,0.00029789645,0.000030589643,0.000074833675],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00063492585,0.00020763764,0.0004247861,0.0002564172,0.00012822307,0.000034672685,0.00020770381,0.000020529755,0.00011989132],"category_scores_gemma":[0.00016052728,0.00015075949,0.000055425207,0.00016834235,0.0004517393,0.00010028822,0.00044981146,0.0006596113,9.653759e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006310883,0.000175326,0.20966686,0.0035414216,0.000067575886,0.0009650625,0.0030318897,0.0036478376,0.002138218,0.000669996,0.00012808725,0.7759046],"study_design_scores_gemma":[0.0031378225,0.00072881195,0.20826179,0.004666607,0.00013888668,0.0031723685,0.000006491645,0.770788,0.00037139346,0.0056990325,0.0024726233,0.0005561763],"about_ca_topic_score_codex":0.00007533605,"about_ca_topic_score_gemma":0.000052962252,"teacher_disagreement_score":0.7753484,"about_ca_system_score_codex":0.00024113744,"about_ca_system_score_gemma":0.00010447084,"threshold_uncertainty_score":0.61477935},"labels":[],"label_agreement":null},{"id":"W4226199676","doi":"10.5167/uzh-214495","title":"Multi-Centre, Multi-Vendor and Multi-Disease Cardiac Segmentation: The M&Ms Challenge","year":2021,"lang":"en","type":"article","venue":"Zurich Open Repository and Archive (University of Zurich)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":85,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"European Commission","keywords":"Generalizability theory; Benchmarking; Segmentation; Computer science; Deep learning; Vendor; Artificial intelligence; Scanner; Field (mathematics); Cardiac imaging; Image segmentation; Data science; Machine learning; Medical physics; Data mining; Medicine; Radiology; Business","score_opus":0.01784446899483396,"score_gpt":0.2571554625033866,"score_spread":0.23931099350855264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226199676","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93446064,0.009112096,0.03882632,0.010523157,0.00056702446,0.0016475072,0.00010177788,0.00008527963,0.004676207],"genre_scores_gemma":[0.80793405,0.0037381707,0.16910806,0.0005519154,0.0002080105,0.0000034018792,0.00013527114,0.00004344922,0.018277653],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9985773,0.0004723009,0.00014770542,0.0004137168,0.0001896727,0.00019928177],"domain_scores_gemma":[0.9988708,0.00027785648,0.00012600889,0.0002944379,0.00009063982,0.0003402806],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036848334,0.00015384273,0.0003278411,0.00005830635,0.00059857557,0.00006046024,0.00020628628,0.00004170066,0.00003831503],"category_scores_gemma":[0.000105209554,0.00013673506,0.000103249535,0.00011554343,0.0003384385,0.00017710304,0.00050275656,0.0003069798,0.000004288582],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002118335,0.0058299727,0.63412225,0.0021446482,0.0029005418,0.010209729,0.05677919,0.00018305183,0.17149541,0.0018155896,0.021505099,0.0908962],"study_design_scores_gemma":[0.014554852,0.00027086193,0.84547174,0.00060073065,0.0012048079,0.0002640592,0.01951288,0.07044919,0.0010688949,0.00008819455,0.045896072,0.0006177192],"about_ca_topic_score_codex":0.00037047907,"about_ca_topic_score_gemma":0.00003664244,"teacher_disagreement_score":0.2113495,"about_ca_system_score_codex":0.000022922337,"about_ca_system_score_gemma":0.00011883656,"threshold_uncertainty_score":0.5575894},"labels":[],"label_agreement":null},{"id":"W4226337630","doi":"10.1007/978-3-030-98253-9_22","title":"Segmentation and Risk Score Prediction of Head and Neck Cancers in PET/CT Volumes with 3D U-Net and Cox Proportional Hazard Neural Networks","year":2022,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; University of British Columbia","funders":"","keywords":"Segmentation; Convolutional neural network; Computer science; Artificial intelligence; Proportional hazards model; Artificial neural network; Pattern recognition (psychology); Deep learning; Statistics; Mathematics","score_opus":0.008779037312565059,"score_gpt":0.24823082437210467,"score_spread":0.23945178705953962,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226337630","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.78108114,0.0014410208,0.21607699,0.00048648386,0.00029820803,0.0005017673,0.000014456642,0.000020573238,0.0000793652],"genre_scores_gemma":[0.97358745,0.0007856782,0.02504142,0.0003424695,0.00014573795,0.000009444601,0.000038956292,0.000018591982,0.00003025703],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99863523,0.000026338752,0.00025485916,0.0004915057,0.0004093438,0.00018272935],"domain_scores_gemma":[0.9994356,0.00010643319,0.0001913109,0.00012598623,0.000046596906,0.000094073854],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040152235,0.00017924342,0.00031086046,0.00025008418,0.00011852352,0.000044645243,0.00007640294,0.000025079398,0.0000147029705],"category_scores_gemma":[0.00005096576,0.00014467977,0.000016192544,0.00014560898,0.000774925,0.000117568976,0.00011462001,0.00076630746,2.7873094e-8],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011540931,0.000014415976,0.49314457,0.0001387351,0.000023357776,0.00021670808,0.0004001653,0.1548583,0.000024078601,0.00005623529,0.000010758769,0.35099727],"study_design_scores_gemma":[0.00090604357,0.0005072166,0.09575895,0.00044653518,0.000038637314,0.00090771116,0.0000016939423,0.90081584,0.000005482579,0.0004053627,0.00009232537,0.00011418565],"about_ca_topic_score_codex":0.000421589,"about_ca_topic_score_gemma":0.00032818172,"teacher_disagreement_score":0.74595755,"about_ca_system_score_codex":0.00013571716,"about_ca_system_score_gemma":0.0001990045,"threshold_uncertainty_score":0.589987},"labels":[],"label_agreement":null},{"id":"W4226514417","doi":"10.5281/zenodo.6463431","title":"An interactive meta-analysis of MRI biomarkers of myelin","year":2022,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Montreal Heart Institute; Polytechnique Montréal","funders":"","keywords":"Computer science; Myelin; Meta-analysis; Computational biology; Neuroscience; Medicine; Psychology; Pathology; Biology","score_opus":0.045987842684725944,"score_gpt":0.31760824426586587,"score_spread":0.2716204015811399,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226514417","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7214551,0.0015696194,0.064346746,0.0186806,0.00040436516,0.002491458,0.0023321074,0.0013516458,0.18736833],"genre_scores_gemma":[0.9969675,0.00002008305,0.00091882254,0.00023555408,0.000020345351,5.2578674e-8,0.0012658971,0.0003542544,0.00021751969],"study_design_codex":"meta_analysis","study_design_gemma":"not_applicable","domain_scores_codex":[0.99829537,0.0005067925,0.00031372125,0.00026071226,0.00047032424,0.0001530936],"domain_scores_gemma":[0.9988673,0.00004493937,0.00020302914,0.00040907564,0.00034668445,0.00012898221],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012192306,0.00008406766,0.00043677536,0.0006192156,0.0004943877,0.000044743716,0.00045156424,0.000019364972,0.03840507],"category_scores_gemma":[0.0005047192,0.00007765726,0.00029325005,0.001203302,0.00014854169,0.000082662315,0.00047658765,0.0003047589,0.00005510662],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0028297172,0.0041844086,0.0004411254,0.0005147412,0.30429086,0.00018589411,0.019943155,0.026221836,0.23915523,0.0066064773,0.1920429,0.20358367],"study_design_scores_gemma":[0.001425124,0.0017264524,0.0038102574,0.000010932472,0.04755579,0.00014529708,0.0035940334,0.083973184,0.0022140576,0.00010470192,0.8551838,0.00025639095],"about_ca_topic_score_codex":0.000054223252,"about_ca_topic_score_gemma":1.2399066e-7,"teacher_disagreement_score":0.6631409,"about_ca_system_score_codex":0.00007218536,"about_ca_system_score_gemma":0.0000053456233,"threshold_uncertainty_score":0.962474},"labels":[],"label_agreement":null},{"id":"W4229798136","doi":"10.1109/iembs.2006.4398542","title":"Segmentation of Lung Lobes in Volumetric CT images for Surgical Planning of Treating Lung Cancer","year":2006,"lang":"en","type":"article","venue":"Conference proceedings","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Foothills Medical Centre; University of Calgary","funders":"","keywords":"Lung; Surgical planning; Lung cancer; Radiation treatment planning; Radiology; Medicine; Image segmentation; Segmentation; Computer science; Biomedical engineering; Computer vision; Pathology; Radiation therapy; Internal medicine","score_opus":0.014047231760161271,"score_gpt":0.336396283511647,"score_spread":0.32234905175148576,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4229798136","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99366283,0.001119663,0.002522123,0.0002883201,0.0000472101,0.00035110643,0.0000058739447,0.000021971942,0.0019809038],"genre_scores_gemma":[0.9957715,0.00006494116,0.0037259073,0.000017857174,0.00010239891,0.00005225493,0.000016851309,0.00001497519,0.00023326148],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99898374,0.0000057760644,0.00040309742,0.00019917719,0.00020349993,0.00020468043],"domain_scores_gemma":[0.9993212,0.00011400996,0.00023671327,0.000039938626,0.00024145762,0.00004666659],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031580322,0.00011120378,0.00035609448,0.0002126674,0.000032782416,0.000019585454,0.00007347715,0.000036886195,0.000036646303],"category_scores_gemma":[0.00029315025,0.00009883784,0.000060444036,0.00035348622,0.000082369515,0.000115096846,0.000021516369,0.00016380333,1.1383176e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008214597,0.00006299994,0.95895845,0.0010441933,0.00002087731,0.0000066763478,0.0005011538,0.000059535345,0.02275071,0.00036238864,0.00059331465,0.015557561],"study_design_scores_gemma":[0.006767248,0.00021581438,0.41545445,0.003242719,0.00026554315,0.000048624148,0.0012360803,0.5033021,0.06857954,0.0002880567,0.0003120334,0.00028781703],"about_ca_topic_score_codex":0.00065850804,"about_ca_topic_score_gemma":0.0000014248433,"teacher_disagreement_score":0.543504,"about_ca_system_score_codex":0.0000676344,"about_ca_system_score_gemma":0.00007468839,"threshold_uncertainty_score":0.40304902},"labels":[],"label_agreement":null},{"id":"W4230033833","doi":"10.1158/1538-7445.am2021-207","title":"Abstract 207: The cBioPortal for Cancer Genomics","year":2021,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre","funders":"","keywords":"Visualization; Genomics; Computer science; World Wide Web; Data visualization; Data science; Data mining; Genome; Biology; Genetics","score_opus":0.09070789689338121,"score_gpt":0.47488212390527046,"score_spread":0.38417422701188925,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4230033833","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9084045,0.013775496,0.00032987958,0.071934536,0.00066047185,0.00057574565,0.000039572,0.00003080911,0.0042489558],"genre_scores_gemma":[0.9782936,0.0061773374,0.00058232597,0.0023692288,0.002048646,0.0004801379,0.00003141912,0.000055442426,0.00996188],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986002,0.000041158037,0.00017669455,0.0002782102,0.0004391089,0.00046463308],"domain_scores_gemma":[0.9987872,0.0002657583,0.000033966393,0.00030954025,0.000422194,0.00018130637],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0010420963,0.00008359081,0.00018158813,0.00005433142,0.00027548897,0.00006273895,0.0001659468,0.000059989125,0.0011440263],"category_scores_gemma":[0.00056294136,0.000056588753,0.00010091751,0.00023819631,0.00023028658,0.00003073565,0.000073000636,0.0008217102,0.000018795663],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035497904,0.00018111442,0.014974714,0.00068874244,0.00038758316,0.0003532328,0.0011186827,0.00036406607,0.374772,0.0018843327,0.15715007,0.44777045],"study_design_scores_gemma":[0.0013668457,0.000058301903,0.020083508,0.0002777706,0.00005401341,0.000046710025,0.00053626666,0.002923488,0.025116686,0.00065742433,0.9487395,0.0001394338],"about_ca_topic_score_codex":0.0007353653,"about_ca_topic_score_gemma":0.00012810578,"teacher_disagreement_score":0.7915895,"about_ca_system_score_codex":0.00023974288,"about_ca_system_score_gemma":0.0013687169,"threshold_uncertainty_score":0.9997691},"labels":[],"label_agreement":null},{"id":"W4230436748","doi":"10.1109/tmi.2014.2307772","title":"IEEE Transactions on Medical Imaging publication information","year":2014,"lang":"en","type":"article","venue":"IEEE Transactions on Medical Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Medical imaging; Computer science; Medical physics; Information retrieval; Artificial intelligence; Medicine","score_opus":0.007603488287088895,"score_gpt":0.2789357131475343,"score_spread":0.2713322248604454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4230436748","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030623188,0.000039381863,0.9216451,0.06554261,0.002338462,0.00040438274,0.000011823025,0.00060852605,0.00634742],"genre_scores_gemma":[0.961837,0.0001942322,0.0017977428,0.034875847,0.00051024515,0.00012292634,0.00004509689,0.00008400907,0.000532913],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99419785,0.0002761869,0.001094875,0.00062146975,0.0029888148,0.00082083605],"domain_scores_gemma":[0.9964709,0.00068310945,0.00022059231,0.0006962884,0.00032570987,0.0016033507],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0022264628,0.00047004854,0.00059514045,0.0008832428,0.0006212921,0.0002034259,0.00046965532,0.0002846208,0.0039182743],"category_scores_gemma":[0.0007853626,0.0004206625,0.0003704518,0.0007249753,0.00050712016,0.0009137416,0.0000019652343,0.0030183366,0.0007521787],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012476303,0.00051022304,0.00012239265,0.000114628005,0.000083024075,0.000049735572,0.0003748455,0.001001108,0.0002928842,0.00014441054,0.005510148,0.99167186],"study_design_scores_gemma":[0.0042307912,0.00013929763,0.0003087721,0.00087439845,0.00023030562,0.0008911199,0.00023190147,0.9356787,0.003427897,0.00013657745,0.053328555,0.0005216902],"about_ca_topic_score_codex":0.00016662628,"about_ca_topic_score_gemma":0.0000114317045,"teacher_disagreement_score":0.99115014,"about_ca_system_score_codex":0.0002828073,"about_ca_system_score_gemma":0.00048713613,"threshold_uncertainty_score":0.9998245},"labels":[],"label_agreement":null},{"id":"W4230549700","doi":"10.1007/s12630-020-01782-6","title":"2020 CAS Virtual Annual Meeting Abstracts","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Anesthesia/Journal canadien d anesthésie","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland; Saskatchewan Polytechnic; McGill University; University of British Columbia; Earl Haig Secondary School; Western University; Dalhousie University; Université de Montréal; University of Saskatchewan","funders":"","keywords":"Library science; Computer science","score_opus":0.009833343786135146,"score_gpt":0.2355849908034935,"score_spread":0.22575164701735834,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4230549700","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8921753,0.0011647767,0.000035117693,0.104376994,0.0003845135,0.00012787759,0.000005900928,0.000017931641,0.001711584],"genre_scores_gemma":[0.9919265,0.000092890485,0.0010955587,0.0030305323,0.0034814142,8.241073e-7,0.0000067603683,0.00008883537,0.0002766638],"study_design_codex":"case_report","study_design_gemma":"case_report","domain_scores_codex":[0.9964709,0.00014734839,0.0012641404,0.00029206625,0.00077971735,0.0010458049],"domain_scores_gemma":[0.99005234,0.0001201371,0.00085209496,0.0001893073,0.00077989505,0.008006227],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0014170539,0.000381489,0.00087333267,0.00046491885,0.00048454708,0.0002492013,0.00056977087,0.00022202876,0.0003647675],"category_scores_gemma":[0.0019358253,0.00033645454,0.0004175308,0.00052872236,0.00028621647,0.00041530616,0.000012542669,0.0024618828,0.000043375472],"study_design_candidate":"case_report","study_design_consensus":"case_report","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018312299,0.00002466049,0.010182591,0.00005023375,0.00016306601,0.92153007,0.004340552,0.0020866005,0.0001657151,0.000068075125,0.052634526,0.008570788],"study_design_scores_gemma":[0.0013965559,0.00162731,0.010391387,0.00033798642,0.00021354381,0.8946053,0.0018168627,0.0005026838,0.000078442325,0.000052443564,0.08866259,0.00031491587],"about_ca_topic_score_codex":0.004685714,"about_ca_topic_score_gemma":0.0015287476,"teacher_disagreement_score":0.10134646,"about_ca_system_score_codex":0.0006015275,"about_ca_system_score_gemma":0.0061471006,"threshold_uncertainty_score":0.99990875},"labels":[],"label_agreement":null},{"id":"W4233411193","doi":"10.1109/tmi.2015.2398575","title":"IEEE Transactions on Medical Imaging publication information","year":2015,"lang":"en","type":"article","venue":"IEEE Transactions on Medical Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Laboratory of Pattern Recognition; Westfälische Wilhelms-Universität Münster; Erasmus Medisch Centrum; Connaught Fund; Lawrence Berkeley National Laboratory; Chinese Academy of Sciences","keywords":"Medical imaging; Computer science; Medical physics; Computer vision; Computer graphics (images); Information retrieval; Artificial intelligence; Medicine","score_opus":0.014240141193794187,"score_gpt":0.29869561554119944,"score_spread":0.28445547434740526,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4233411193","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0033369989,0.00008668587,0.9158442,0.07065637,0.002871328,0.0004531316,0.000016746824,0.00061673747,0.006117828],"genre_scores_gemma":[0.96734,0.00019357489,0.0019570491,0.029046,0.00048863393,0.00013538808,0.000054857093,0.00008684451,0.000697663],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9937028,0.00022966013,0.0010852498,0.00058850145,0.0035873132,0.0008064435],"domain_scores_gemma":[0.9957932,0.00040682565,0.00021177632,0.0006474633,0.00050127023,0.0024394237],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002252851,0.0004623292,0.00057555543,0.00089982344,0.0004374846,0.00020664999,0.00046332448,0.00028377643,0.002413784],"category_scores_gemma":[0.00081792404,0.00041315556,0.00032352342,0.00083295826,0.0005047894,0.0011218232,0.0000022261147,0.0029749167,0.0008398503],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024088443,0.0007274707,0.00017092761,0.00009349667,0.00011190267,0.00018470133,0.0009081896,0.0015705567,0.00015486093,0.000081056605,0.016669735,0.9790862],"study_design_scores_gemma":[0.007116015,0.00019714839,0.00018497581,0.00095322053,0.00029751743,0.0018204908,0.00093449553,0.9259567,0.0033230113,0.00017149474,0.058380313,0.000664606],"about_ca_topic_score_codex":0.00024206523,"about_ca_topic_score_gemma":0.000012475481,"teacher_disagreement_score":0.9784216,"about_ca_system_score_codex":0.00046446233,"about_ca_system_score_gemma":0.0011376564,"threshold_uncertainty_score":0.99993813},"labels":[],"label_agreement":null},{"id":"W4233866456","doi":"10.1111/2041-210x.13712/v3/decision1","title":"Decision letter for \"Sashimi : A toolkit for facilitating high‐throughput organismal image segmentation using deep learning\"","year":2021,"lang":"en","type":"peer-review","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Institute for Advanced Research; Vector Institute; University of Guelph","funders":"","keywords":"Throughput; Segmentation; Computer science; Artificial intelligence; Image (mathematics); Computer architecture; Operating system","score_opus":0.03018337108238494,"score_gpt":0.3686002196223991,"score_spread":0.33841684854001414,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4233866456","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020937966,0.006769672,0.9365722,0.047223922,0.0036431272,0.0030182486,0.00012269171,0.0001625471,0.0003937821],"genre_scores_gemma":[0.00014206374,0.0014564669,0.8792494,0.026649708,0.002654785,0.00031379279,0.007690969,0.0002531705,0.08158963],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9962018,0.00014340687,0.0010971249,0.0010677445,0.0007913869,0.00069854053],"domain_scores_gemma":[0.9962251,0.0017652183,0.00050218165,0.00045493658,0.000807599,0.0002449426],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0014730144,0.000596603,0.0014710454,0.0001984082,0.00039919856,0.0001845237,0.00022433975,0.00037986776,0.0016086887],"category_scores_gemma":[0.0072700446,0.0005192342,0.0006362151,0.00023782489,0.00010002794,0.00017529797,0.0001577187,0.0011987397,0.000028079989],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012259815,0.0001036744,0.000049269784,0.013426354,0.00032530754,0.000057793146,0.00034736373,0.00024490381,0.010928726,0.000044231052,0.7391645,0.2351853],"study_design_scores_gemma":[0.0034937013,0.00039117175,0.00001895139,0.006790268,0.0015597383,0.00015254275,0.00032226244,0.061175823,0.0005345852,0.0001856822,0.92472255,0.0006527454],"about_ca_topic_score_codex":0.00012518185,"about_ca_topic_score_gemma":0.000017252009,"teacher_disagreement_score":0.23453255,"about_ca_system_score_codex":0.00038494696,"about_ca_system_score_gemma":0.00037561773,"threshold_uncertainty_score":0.99972594},"labels":[],"label_agreement":null},{"id":"W4234267758","doi":"10.32920/ryerson.14656104","title":"Investigating the effect of micro-CT radiation dose on tumour growth in mice","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University; University of Waterloo","funders":"","keywords":"Radiation dose; Nuclear medicine; Radiation therapy; In vivo; Medicine; Analysis of variance; Significant difference; High resolution; Radiology; Biology; Internal medicine","score_opus":0.008692589328722277,"score_gpt":0.28505562218478075,"score_spread":0.27636303285605845,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4234267758","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9891329,0.0005330014,0.00013271383,0.005800116,0.000360236,0.000558195,0.0000016110268,0.000035316898,0.0034459305],"genre_scores_gemma":[0.9962424,0.00011758711,0.0017514038,0.0013429766,0.00022864109,0.000030515044,0.000089573296,0.000032972817,0.00016392682],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.998219,0.00041486727,0.00045088385,0.0003768135,0.0003322887,0.00020611446],"domain_scores_gemma":[0.9985642,0.000777894,0.00024764417,0.000261392,0.000047519145,0.00010137468],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014421442,0.00023248835,0.0005763675,0.00016661717,0.000039157854,0.000041266554,0.00019269128,0.00010044539,0.000040699946],"category_scores_gemma":[0.0033793433,0.00014566327,0.00016922073,0.00020326802,0.00010966354,0.000023388317,0.00020701194,0.0018411035,0.000004945897],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021811368,0.00028056008,0.5311805,0.0072320704,0.0004809386,0.0005027905,0.0039720265,0.006246381,0.36764175,0.0005763466,0.0041982485,0.07747027],"study_design_scores_gemma":[0.0069334474,0.0008259698,0.2690129,0.009303137,0.0005559897,0.00025118602,0.0004044361,0.0972,0.6138619,0.0007513788,0.0002288518,0.0006708042],"about_ca_topic_score_codex":0.0017052962,"about_ca_topic_score_gemma":0.000009190049,"teacher_disagreement_score":0.2621676,"about_ca_system_score_codex":0.0001078891,"about_ca_system_score_gemma":0.00017486583,"threshold_uncertainty_score":0.7998781},"labels":[],"label_agreement":null},{"id":"W4234542180","doi":"10.1016/j.jalz.2013.05.790","title":"P2–146: Evaluation of common changes in the aging brain: Comparing high‐ and low‐field MRI","year":2013,"lang":"en","type":"article","venue":"Alzheimer s & Dementia","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Atrophy; Neuroimaging; White matter; Hyperintensity; Medicine; Psychology; Fluid-attenuated inversion recovery; Alzheimer's Disease Neuroimaging Initiative; Magnetic resonance imaging; Alzheimer's disease; Nuclear medicine; Neuroscience; Internal medicine; Disease; Radiology","score_opus":0.031459348903087186,"score_gpt":0.3209440073395431,"score_spread":0.2894846584364559,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4234542180","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9475624,0.016462967,0.0001638412,0.033581626,0.00014064499,0.0005312541,2.8076835e-7,0.000016621543,0.0015403557],"genre_scores_gemma":[0.99565464,0.00007089858,0.0005411012,0.0035697496,0.00009556527,0.00003875866,0.000014776189,0.000011561647,0.0000029626324],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99887675,0.00015885867,0.00022160028,0.00016380817,0.00039575438,0.00018325544],"domain_scores_gemma":[0.9993792,0.00019559273,0.0000946319,0.00021213737,0.000066618195,0.00005180103],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012994927,0.00009959309,0.00021660526,0.000093324976,0.000059288628,0.00003326286,0.00011071799,0.000038925293,0.00019051581],"category_scores_gemma":[0.000102264894,0.00007280896,0.000026565109,0.00011899026,0.000063054205,0.00007541502,0.00005804109,0.00025127208,0.000007883037],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024358053,0.00024800148,0.3768477,0.00007359508,0.0024680437,0.000011218762,0.0038688313,0.00019864226,0.008235507,0.0008289119,0.01372027,0.5934749],"study_design_scores_gemma":[0.0036439854,0.00024965068,0.7785735,0.0004012081,0.008145406,0.000043888827,0.0009918218,0.19455315,0.009260114,0.001281745,0.0025923573,0.00026318379],"about_ca_topic_score_codex":0.0014691825,"about_ca_topic_score_gemma":0.00014423551,"teacher_disagreement_score":0.5932117,"about_ca_system_score_codex":0.000004320216,"about_ca_system_score_gemma":0.000020418462,"threshold_uncertainty_score":0.29690632},"labels":[],"label_agreement":null},{"id":"W4236139177","doi":"10.5194/essd-2021-91-rc1","title":"Comment on essd-2021-91","year":2021,"lang":"en","type":"peer-review","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Geology; Radar; Stratigraphy; Geodesy; Remote sensing; Meteorology; Seismology; Geography; Engineering; Aerospace engineering","score_opus":0.026290395690011743,"score_gpt":0.35902856462569926,"score_spread":0.33273816893568753,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4236139177","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000035681571,0.02952929,0.0003690737,0.728289,0.002571281,0.00038198027,0.000017842896,0.00005607485,0.23878188],"genre_scores_gemma":[0.000016735969,0.02718737,0.0017883251,0.43371648,0.0014096369,0.000035198314,0.002217028,0.00006196878,0.53356725],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99766535,0.000114410934,0.00047532213,0.00054884964,0.0008451524,0.00035094155],"domain_scores_gemma":[0.99835217,0.0002011052,0.00014849815,0.0007909,0.00017653538,0.00033077833],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006486373,0.00036250587,0.0011619505,0.000114367824,0.000067041685,0.000037722286,0.00019681214,0.00021960693,0.019065116],"category_scores_gemma":[0.0010561002,0.0002654867,0.0003781959,0.00018548554,0.000063844476,0.000013175343,0.00013698661,0.0019186162,0.00049124734],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006175184,0.00014701381,0.000018699411,0.0030377686,0.00014774875,0.00034415905,0.000008854475,0.0000010192963,0.0000039443757,0.0005073238,0.92832524,0.06745207],"study_design_scores_gemma":[0.00061443454,0.00013630516,0.000020647853,0.0180081,0.00043639127,0.00009453778,0.000010088221,0.0003157267,0.00001718411,0.000029157427,0.98006964,0.00024781187],"about_ca_topic_score_codex":0.00015367196,"about_ca_topic_score_gemma":0.0000040709256,"teacher_disagreement_score":0.29478538,"about_ca_system_score_codex":0.00015356165,"about_ca_system_score_gemma":0.00030344204,"threshold_uncertainty_score":0.99997973},"labels":[],"label_agreement":null},{"id":"W4236149930","doi":"10.1503/cmaj.070554","title":"Imaging possibilities","year":2007,"lang":"en","type":"article","venue":"Canadian Medical Association Journal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Suite; Computer science; Foundation (evidence); Library science; Data science; World Wide Web; Computer graphics (images); Political science; Law","score_opus":0.004799708294048373,"score_gpt":0.2665786422480327,"score_spread":0.2617789339539843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4236149930","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7401681,0.00086201663,0.0050540944,0.16985479,0.0026898107,0.0001573938,0.0000050040467,0.00008705697,0.08112175],"genre_scores_gemma":[0.9432778,0.00006709318,0.0011209741,0.04876279,0.0037977232,8.7717626e-7,0.000006954037,0.000025170591,0.00294063],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974154,0.000056015815,0.00042744516,0.00013281757,0.0013361274,0.00063219824],"domain_scores_gemma":[0.996507,0.00021070607,0.00012742913,0.00009333743,0.00031648274,0.0027450782],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004965532,0.000098944605,0.00020212862,0.00027346992,0.00025054853,0.00008145356,0.00012411596,0.0001734655,0.0033862267],"category_scores_gemma":[0.0053415955,0.00008562736,0.00011509581,0.00018893278,0.00006227304,0.000092395894,0.000011038966,0.0015668368,0.00012335843],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000140515385,0.000026309297,0.6048591,0.000012057313,0.00007380345,0.0032775567,0.00040280566,0.0000011759207,0.000061326886,0.0005673662,0.10831587,0.28238857],"study_design_scores_gemma":[0.0016602871,0.000045640027,0.24102484,0.00016269373,0.0000463255,0.006516505,0.0011310934,0.0019276968,0.000033698616,0.00066557655,0.74660337,0.00018228978],"about_ca_topic_score_codex":0.0027012427,"about_ca_topic_score_gemma":0.0033910573,"teacher_disagreement_score":0.6382875,"about_ca_system_score_codex":0.0010700598,"about_ca_system_score_gemma":0.0021547042,"threshold_uncertainty_score":0.9975248},"labels":[],"label_agreement":null},{"id":"W4236180932","doi":"10.1109/tmi.2013.2296433","title":"IEEE Transactions on Medical Imaging publication information","year":2014,"lang":"en","type":"article","venue":"IEEE Transactions on Medical Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Medical imaging; Computer science; Medical physics; Information retrieval; Artificial intelligence; Medicine","score_opus":0.007603488287088895,"score_gpt":0.2789357131475343,"score_spread":0.2713322248604454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4236180932","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030623188,0.000039381863,0.9216451,0.06554261,0.002338462,0.00040438274,0.000011823025,0.00060852605,0.00634742],"genre_scores_gemma":[0.961837,0.0001942322,0.0017977428,0.034875847,0.00051024515,0.00012292634,0.00004509689,0.00008400907,0.000532913],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99419785,0.0002761869,0.001094875,0.00062146975,0.0029888148,0.00082083605],"domain_scores_gemma":[0.9964709,0.00068310945,0.00022059231,0.0006962884,0.00032570987,0.0016033507],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0022264628,0.00047004854,0.00059514045,0.0008832428,0.0006212921,0.0002034259,0.00046965532,0.0002846208,0.0039182743],"category_scores_gemma":[0.0007853626,0.0004206625,0.0003704518,0.0007249753,0.00050712016,0.0009137416,0.0000019652343,0.0030183366,0.0007521787],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012476303,0.00051022304,0.00012239265,0.000114628005,0.000083024075,0.000049735572,0.0003748455,0.001001108,0.0002928842,0.00014441054,0.005510148,0.99167186],"study_design_scores_gemma":[0.0042307912,0.00013929763,0.0003087721,0.00087439845,0.00023030562,0.0008911199,0.00023190147,0.9356787,0.003427897,0.00013657745,0.053328555,0.0005216902],"about_ca_topic_score_codex":0.00016662628,"about_ca_topic_score_gemma":0.0000114317045,"teacher_disagreement_score":0.99115014,"about_ca_system_score_codex":0.0002828073,"about_ca_system_score_gemma":0.00048713613,"threshold_uncertainty_score":0.9998245},"labels":[],"label_agreement":null},{"id":"W4236205242","doi":"10.21203/rs.3.rs-263971/v1","title":"Quantitative Mapping of Individual Voxels in the Peritumoral Region of Glioblastoma to Distinguish Between Tumor Infiltration and Edema","year":2021,"lang":"en","type":"preprint","venue":"Research Square","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; Sunnybrook Health Science Centre","funders":"Terry Fox Foundation","keywords":"Infiltration (HVAC); Glioblastoma; Voxel; Pathology; Medicine; Geography; Radiology; Cancer research","score_opus":0.09657507539366611,"score_gpt":0.42458917197998264,"score_spread":0.32801409658631653,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4236205242","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9935133,0.00049590535,0.0010146354,0.0035140086,0.000052553885,0.00097341865,0.000030013862,0.000011096603,0.0003950886],"genre_scores_gemma":[0.9965878,0.000046607965,0.0028847528,0.00007738639,0.00020509641,0.00005750057,0.00010020685,0.000022354363,0.000018277931],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99647784,0.00085203355,0.00056298217,0.00041547674,0.0013504659,0.00034119308],"domain_scores_gemma":[0.99759084,0.001078848,0.00020348284,0.0004068773,0.0005723223,0.00014763609],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003974004,0.00016611449,0.00064109446,0.00063400925,0.00008544678,0.00009480707,0.00031377026,0.000120456905,0.000010041474],"category_scores_gemma":[0.0084178,0.00013011158,0.00009513801,0.0007219347,0.000357018,0.000047512876,0.0006090471,0.001779841,6.3606257e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005024617,0.00041417108,0.8778311,0.011740126,0.00025893966,0.0010977876,0.07778983,0.00028599118,0.003319884,0.0019079134,0.0012719881,0.023579806],"study_design_scores_gemma":[0.00086424773,0.0013925064,0.9561844,0.010458317,0.00005790984,0.00009128794,0.026419632,0.0028490336,0.00069427345,0.0005445724,0.00025236234,0.00019144318],"about_ca_topic_score_codex":0.0005962941,"about_ca_topic_score_gemma":0.00005097401,"teacher_disagreement_score":0.07835331,"about_ca_system_score_codex":0.00007036886,"about_ca_system_score_gemma":0.0004090987,"threshold_uncertainty_score":0.99993473},"labels":[],"label_agreement":null},{"id":"W4237080054","doi":"10.1109/tmi.2014.2318232","title":"IEEE Transactions on Medical Imaging publication information","year":2014,"lang":"en","type":"article","venue":"IEEE Transactions on Medical Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Medical imaging; Computer science; Medical physics; Information retrieval; Artificial intelligence; Medicine","score_opus":0.007603488287088895,"score_gpt":0.2789357131475343,"score_spread":0.2713322248604454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4237080054","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030623188,0.000039381863,0.9216451,0.06554261,0.002338462,0.00040438274,0.000011823025,0.00060852605,0.00634742],"genre_scores_gemma":[0.961837,0.0001942322,0.0017977428,0.034875847,0.00051024515,0.00012292634,0.00004509689,0.00008400907,0.000532913],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99419785,0.0002761869,0.001094875,0.00062146975,0.0029888148,0.00082083605],"domain_scores_gemma":[0.9964709,0.00068310945,0.00022059231,0.0006962884,0.00032570987,0.0016033507],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0022264628,0.00047004854,0.00059514045,0.0008832428,0.0006212921,0.0002034259,0.00046965532,0.0002846208,0.0039182743],"category_scores_gemma":[0.0007853626,0.0004206625,0.0003704518,0.0007249753,0.00050712016,0.0009137416,0.0000019652343,0.0030183366,0.0007521787],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012476303,0.00051022304,0.00012239265,0.000114628005,0.000083024075,0.000049735572,0.0003748455,0.001001108,0.0002928842,0.00014441054,0.005510148,0.99167186],"study_design_scores_gemma":[0.0042307912,0.00013929763,0.0003087721,0.00087439845,0.00023030562,0.0008911199,0.00023190147,0.9356787,0.003427897,0.00013657745,0.053328555,0.0005216902],"about_ca_topic_score_codex":0.00016662628,"about_ca_topic_score_gemma":0.0000114317045,"teacher_disagreement_score":0.99115014,"about_ca_system_score_codex":0.0002828073,"about_ca_system_score_gemma":0.00048713613,"threshold_uncertainty_score":0.9998245},"labels":[],"label_agreement":null},{"id":"W4237186189","doi":"10.21037/atm-21-4349","title":"Combining PET with MRI to improve predictions of progression from mild cognitive impairment to Alzheimer’s disease: an exploratory radiomic analysis study","year":2022,"lang":"en","type":"article","venue":"Annals of Translational Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute on Aging; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; National Institutes of Health; H. Lundbeck A/S; Higher Education Discipline Innovation Project; Servier; National Natural Science Foundation of China; Eisai; Genentech; IXICO; Northern California Institute for Research and Education; University of California, San Diego; Pfizer; Biogen; BioClinica; University of Southern California; Massachusetts Department of Agricultural Resources; Eli Lilly and Company; U.S. Department of Defense; Meso Scale Diagnostics; Alzheimer's Disease Neuroimaging Initiative; Novartis Pharmaceuticals Corporation; Bristol-Myers Squibb; Alzheimer's Association; Foundation for the National Institutes of Health","keywords":"Cognitive impairment; Medicine; Disease; Cognition; Exploratory analysis; Pathology; Computer science; Psychiatry; Data science","score_opus":0.04745436993137711,"score_gpt":0.3793627286040559,"score_spread":0.33190835867267876,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4237186189","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9677273,0.0009884492,0.007137793,0.021789074,0.00013564799,0.0017063641,0.00040700068,0.000042979114,0.00006541017],"genre_scores_gemma":[0.9956094,0.000022226177,0.0017631386,0.0013190894,0.00016501978,0.00029469922,0.0007808416,0.000030622865,0.000014973237],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9971176,0.00023345476,0.0006254078,0.000473135,0.001318278,0.00023214241],"domain_scores_gemma":[0.9982038,0.0002994852,0.00021945804,0.00031023065,0.00033448692,0.0006325021],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00088035647,0.00020569922,0.0006722938,0.00070108875,0.00019892951,0.000005270243,0.0001633339,0.000018280738,0.00037276003],"category_scores_gemma":[0.0001184015,0.00016217277,0.00012494496,0.0011043391,0.00014562711,0.00009659581,0.000047073863,0.00030782304,0.0000010104831],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.020066192,0.008855445,0.83042866,0.00016384617,0.011846369,0.00032376946,0.047314294,0.058753736,0.0042310595,0.00014679556,0.0026197373,0.015250089],"study_design_scores_gemma":[0.008925013,0.015546049,0.9218455,0.00085215224,0.008098147,0.000010710816,0.011441629,0.03193704,0.0004915385,0.00012254062,0.0004008841,0.0003287819],"about_ca_topic_score_codex":0.00022310496,"about_ca_topic_score_gemma":0.00003888556,"teacher_disagreement_score":0.09141684,"about_ca_system_score_codex":0.000019940402,"about_ca_system_score_gemma":0.00021118805,"threshold_uncertainty_score":0.6613214},"labels":[],"label_agreement":null},{"id":"W4237520672","doi":"10.5858/133.9.1362.a","title":"Coronal Serial Sequential Sampling of Breast Specimen in the Assessment of the Extent of Ductal Carcinoma In Situ","year":2009,"lang":"en","type":"article","venue":"Archives of Pathology & Laboratory Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; University of Ottawa","funders":"","keywords":"Coronal plane; Mastectomy; Ductal carcinoma; Frozen section procedure; Medicine; Radiology; In situ; Pathology; Breast cancer; Cancer; Physics; Internal medicine","score_opus":0.01539291181043608,"score_gpt":0.3200560386010473,"score_spread":0.30466312679061125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4237520672","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99418104,0.00034370198,0.00026831252,0.003570198,0.00022238045,0.0003024436,0.000027065045,0.0000035908463,0.001081287],"genre_scores_gemma":[0.99783474,0.00006379232,0.0015287545,0.00034318335,0.00019581358,0.0000036273,0.000017781644,0.000009063111,0.0000032390778],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99795336,0.0004496272,0.0007802672,0.00020893254,0.0003988238,0.00020898253],"domain_scores_gemma":[0.99874705,0.0003414822,0.00041170913,0.00037345887,0.00007304736,0.00005323301],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001108967,0.00014177893,0.0006495593,0.00021675842,0.000022061466,9.404108e-7,0.00029019266,0.00005872548,0.000026925343],"category_scores_gemma":[0.0003127233,0.0000835773,0.00008224864,0.00032433955,0.0012309366,0.000028318573,0.00006281288,0.00050765986,8.554432e-8],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022263877,0.00029729033,0.21332896,0.00009639843,0.00002150507,0.00016463707,0.0030042082,0.00011583823,0.7791303,0.0017155928,0.00002389843,0.0018787667],"study_design_scores_gemma":[0.0031266408,0.00071623904,0.9844288,0.00048681584,0.000084820174,0.0002904641,0.0010245218,0.0004193085,0.008795974,0.0005534208,0.000016995184,0.000055996945],"about_ca_topic_score_codex":0.00006980353,"about_ca_topic_score_gemma":0.000024814957,"teacher_disagreement_score":0.77109987,"about_ca_system_score_codex":0.000024778194,"about_ca_system_score_gemma":0.00032789595,"threshold_uncertainty_score":0.45354372},"labels":[],"label_agreement":null},{"id":"W4237681400","doi":"10.1200/jco.2004.22.14_suppl.3772","title":"Linear regression is a reproducible model of tumor response to pre-operative endorectal brachytherapy","year":2004,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre","funders":"","keywords":"Medicine; Brachytherapy; Linear regression; Radiology; Oncology; Nuclear medicine; Internal medicine; Radiation therapy; Statistics","score_opus":0.08667919022008272,"score_gpt":0.5030077746902517,"score_spread":0.41632858447016896,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4237681400","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93280435,0.00022144719,0.007442445,0.058323264,0.0005457396,0.00021732542,0.0000026452674,0.000010165716,0.0004326205],"genre_scores_gemma":[0.88912475,0.0002224039,0.0977383,0.01134518,0.00092319585,0.0000029503417,6.836721e-7,0.000024229275,0.00061829423],"study_design_codex":"design_other","study_design_gemma":"nonrandomized_trial","domain_scores_codex":[0.99636,0.0005066622,0.0021234113,0.0003111027,0.00047546646,0.00022335688],"domain_scores_gemma":[0.99607056,0.0012395193,0.001284278,0.0003413192,0.00054585555,0.0005184849],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.007975504,0.0001440041,0.0014193717,0.00019685629,0.000045315777,0.000005822326,0.00019494745,0.00019613732,0.00006972297],"category_scores_gemma":[0.02169492,0.00009184433,0.0004314843,0.00019444386,0.00021737517,0.000094907264,0.000061625884,0.0015048698,0.000009203383],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.24583137,0.008866279,0.0299094,0.00015006939,0.0011147048,0.003372355,0.013456384,0.04915484,0.31443942,0.00037304996,0.017160738,0.3161714],"study_design_scores_gemma":[0.123592764,0.2348833,0.17277204,0.0058490834,0.0015133313,0.01010036,0.0011127143,0.17077227,0.11211651,0.012835747,0.15318441,0.0012674899],"about_ca_topic_score_codex":0.000022408962,"about_ca_topic_score_gemma":0.0000020314142,"teacher_disagreement_score":0.31490391,"about_ca_system_score_codex":0.00013549668,"about_ca_system_score_gemma":0.0026355141,"threshold_uncertainty_score":0.98654574},"labels":[],"label_agreement":null},{"id":"W4239200550","doi":"10.1016/j.jalz.2016.06.2255","title":"P4‐163: Effects of Scanner Manufacturer and Strength On Cortical Surfaces, Thicknesses and Volumes in the Aging Brain","year":2016,"lang":"en","type":"article","venue":"Alzheimer s & Dementia","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; Institut Universitaire en Santé Mentale de Québec","funders":"","keywords":"Original equipment manufacturer; Siemens; Volume (thermodynamics); Statistics; Scanner; Mathematics; Medicine; Engineering; Computer science; Physics; Electrical engineering","score_opus":0.008496714323874274,"score_gpt":0.2686144297667417,"score_spread":0.26011771544286744,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4239200550","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97193426,0.015612426,0.00012169404,0.011665751,0.000110828434,0.00022936355,0.0000014581683,0.000015646005,0.00030858692],"genre_scores_gemma":[0.99728966,0.00034426522,0.00041963987,0.0018539279,0.000053511652,0.0000074244276,0.0000029724652,0.000015340185,0.000013248549],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99897015,0.00014445173,0.00019915929,0.00023109726,0.00023799571,0.00021712153],"domain_scores_gemma":[0.9987316,0.00092246203,0.000060389408,0.00018279618,0.000018837067,0.00008390577],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004811768,0.00013474948,0.00022836136,0.00007697768,0.000060576513,0.000022771303,0.00007917274,0.000045485736,0.000039627303],"category_scores_gemma":[0.0003384398,0.00006985966,0.000030379582,0.000071820745,0.0002289036,0.00005885601,0.000048612586,0.00024115131,0.0000030014928],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013544691,0.00029803521,0.37529194,0.00016175103,0.0031616953,0.00018067929,0.0019486152,0.000005782965,0.020492459,0.001509323,0.0060034203,0.59081084],"study_design_scores_gemma":[0.003537909,0.00041042545,0.9565907,0.0007279732,0.003919839,0.000081080194,0.00017182206,0.001035188,0.02342367,0.00037692772,0.009476328,0.00024811993],"about_ca_topic_score_codex":0.00014364226,"about_ca_topic_score_gemma":0.000025382418,"teacher_disagreement_score":0.5905627,"about_ca_system_score_codex":0.0000026065707,"about_ca_system_score_gemma":0.000021279098,"threshold_uncertainty_score":0.28487942},"labels":[],"label_agreement":null},{"id":"W4239286032","doi":"10.32920/ryerson.14656104.v1","title":"Investigating the effect of micro-CT radiation dose on tumour growth in mice","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University; University of Waterloo","funders":"","keywords":"Radiation dose; Nuclear medicine; Medicine; Radiation therapy; In vivo; Significant difference; High resolution; Radiology; Biology; Internal medicine","score_opus":0.008692589328722277,"score_gpt":0.28505562218478075,"score_spread":0.27636303285605845,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4239286032","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9891329,0.0005330014,0.00013271383,0.005800116,0.000360236,0.000558195,0.0000016110268,0.000035316898,0.0034459305],"genre_scores_gemma":[0.9962424,0.00011758711,0.0017514038,0.0013429766,0.00022864109,0.000030515044,0.000089573296,0.000032972817,0.00016392682],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.998219,0.00041486727,0.00045088385,0.0003768135,0.0003322887,0.00020611446],"domain_scores_gemma":[0.9985642,0.000777894,0.00024764417,0.000261392,0.000047519145,0.00010137468],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014421442,0.00023248835,0.0005763675,0.00016661717,0.000039157854,0.000041266554,0.00019269128,0.00010044539,0.000040699946],"category_scores_gemma":[0.0033793433,0.00014566327,0.00016922073,0.00020326802,0.00010966354,0.000023388317,0.00020701194,0.0018411035,0.000004945897],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021811368,0.00028056008,0.5311805,0.0072320704,0.0004809386,0.0005027905,0.0039720265,0.006246381,0.36764175,0.0005763466,0.0041982485,0.07747027],"study_design_scores_gemma":[0.0069334474,0.0008259698,0.2690129,0.009303137,0.0005559897,0.00025118602,0.0004044361,0.0972,0.6138619,0.0007513788,0.0002288518,0.0006708042],"about_ca_topic_score_codex":0.0017052962,"about_ca_topic_score_gemma":0.000009190049,"teacher_disagreement_score":0.2621676,"about_ca_system_score_codex":0.0001078891,"about_ca_system_score_gemma":0.00017486583,"threshold_uncertainty_score":0.7998781},"labels":[],"label_agreement":null},{"id":"W4239316177","doi":"10.12688/f1000research.10401.2","title":"Texture analysis of the developing human brain using customization of a knowledge-based system","year":2017,"lang":"en","type":"preprint","venue":"F1000Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Uniwersytet Medyczny w Lodzi; Uniwersytet Łódzki; U.S. Department of Education","keywords":"Artificial intelligence; Pattern recognition (psychology); Linear discriminant analysis; Computer science","score_opus":0.06392572114699797,"score_gpt":0.4246370980886597,"score_spread":0.3607113769416617,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4239316177","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9381716,0.00093325373,0.05041224,0.0035921508,0.00041864504,0.0013786915,0.00005429149,0.00006611581,0.004972991],"genre_scores_gemma":[0.996532,0.0000098919545,0.0024011834,0.00004947008,0.00016894832,0.000016519114,0.000100038,0.000044613662,0.0006773257],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99732995,0.00048731538,0.00060102943,0.00040036254,0.00088861387,0.00029275025],"domain_scores_gemma":[0.9969072,0.00029945013,0.0006273786,0.001276437,0.0007745435,0.0001150215],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024737106,0.00020184206,0.0009487011,0.0010147225,0.0002982621,0.000052307263,0.00081336574,0.00029636515,0.00004173024],"category_scores_gemma":[0.0020303195,0.00014248444,0.00046759972,0.0008018031,0.00043676753,0.000023750306,0.0008053405,0.0013170226,0.0000014915776],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004218783,0.00069478207,0.5998002,0.04218474,0.011354736,0.00010294892,0.0046156934,0.1802304,0.12262262,0.005112759,0.008498394,0.024360843],"study_design_scores_gemma":[0.00076885475,0.000026390922,0.107111774,0.0049611903,0.0015455107,0.000004642332,0.000096987984,0.88278604,0.001599712,0.000037434154,0.00090848247,0.00015297576],"about_ca_topic_score_codex":0.0009940526,"about_ca_topic_score_gemma":0.00004572123,"teacher_disagreement_score":0.70255566,"about_ca_system_score_codex":0.00039550808,"about_ca_system_score_gemma":0.001678498,"threshold_uncertainty_score":0.58103466},"labels":[],"label_agreement":null},{"id":"W4239949434","doi":"10.1007/s00259-021-05397-x","title":"Correction to: [18F]FDG PET radiomics to predict disease-free survival in cervical cancer: a multi-scanner/center study with external validation","year":2021,"lang":"en","type":"article","venue":"European Journal of Nuclear Medicine and Molecular Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre","funders":"","keywords":"Medicine; Radiomics; Cervical cancer; Nuclear medicine; Center (category theory); Medical physics; PET-CT; Positron emission tomography; Radiology; Cancer; Internal medicine","score_opus":0.012025706521191242,"score_gpt":0.2824821496767044,"score_spread":0.27045644315551315,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4239949434","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94276696,0.0005587923,0.017449427,0.037246685,0.001078694,0.0003097835,0.0000040195846,0.000025395779,0.0005602159],"genre_scores_gemma":[0.9843139,0.00013622794,0.00562896,0.00920535,0.00054885604,0.0000018601646,0.0000058198175,0.00008692792,0.000072112074],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99772966,0.00047218145,0.0005469949,0.00034012162,0.00063189183,0.00027914296],"domain_scores_gemma":[0.99847835,0.000052829582,0.00017635571,0.0002855121,0.00026820452,0.0007387575],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011721664,0.00020964646,0.0004507867,0.00034508103,0.00007445847,0.000063707776,0.0001906537,0.0000074444256,0.00005400889],"category_scores_gemma":[0.0011526454,0.00016324571,0.00007149699,0.00034361452,0.00007368683,0.00010628999,0.00014894867,0.0006431839,0.0000036028064],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0034199597,0.001437208,0.7422033,0.00018516646,0.00035743715,0.10188283,0.0076354262,0.0024062449,0.05302309,0.000024359404,0.03196233,0.055462632],"study_design_scores_gemma":[0.029235434,0.0032466738,0.86887956,0.007512637,0.0009181811,0.009671186,0.00785613,0.034150228,0.00022327808,0.000010807441,0.03770429,0.000591625],"about_ca_topic_score_codex":0.00008272469,"about_ca_topic_score_gemma":0.00001521006,"teacher_disagreement_score":0.12667622,"about_ca_system_score_codex":0.000103492486,"about_ca_system_score_gemma":0.00011944996,"threshold_uncertainty_score":0.6656967},"labels":[],"label_agreement":null},{"id":"W4240387376","doi":"10.21203/rs.3.rs-758924/v1","title":"MRI Radiomics to Differentiate Between Low Grade Glioma and Glioblastoma Peritumoral Region","year":2021,"lang":"en","type":"preprint","venue":"Research Square","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; Sunnybrook Health Science Centre","funders":"Terry Fox Foundation","keywords":"Radiomics; Glioblastoma; Feature selection; Glioma; Fluid-attenuated inversion recovery; Tumor grade; Artificial intelligence; Hyperintensity; Pattern recognition (psychology); Computer science; Magnetic resonance imaging; Medicine; Radiology; Pathology; Immunohistochemistry","score_opus":0.04407158610384245,"score_gpt":0.3865181957994698,"score_spread":0.34244660969562735,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4240387376","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97669506,0.0015597566,0.0033580402,0.016392672,0.00034241946,0.0012839342,0.000028916478,0.00014016785,0.00019901534],"genre_scores_gemma":[0.9943494,0.0009011013,0.001994344,0.00019461017,0.0014363356,0.00011621552,0.00028725175,0.00013425494,0.0005864375],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99488914,0.00062877056,0.0005361371,0.0012532878,0.0015995527,0.0010931109],"domain_scores_gemma":[0.9966439,0.00035409033,0.00011260752,0.0010649993,0.00049478206,0.0013295921],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0013266056,0.00045517687,0.0010874736,0.001065655,0.000327414,0.00051850826,0.0004403546,0.00045823446,0.00006887868],"category_scores_gemma":[0.0013275645,0.00042011356,0.00028299014,0.0007286448,0.00039768752,0.000075906595,0.0020418253,0.004347154,0.000023330173],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002575536,0.0021969117,0.634569,0.03717229,0.0024652693,0.035786107,0.015659485,0.0007275643,0.03075071,0.0011150399,0.046144996,0.1908371],"study_design_scores_gemma":[0.010476116,0.004475754,0.8495927,0.03515928,0.0007981976,0.003359635,0.0042613456,0.051984657,0.011941136,0.0027449597,0.022110742,0.0030954808],"about_ca_topic_score_codex":0.00032826426,"about_ca_topic_score_gemma":0.000019581028,"teacher_disagreement_score":0.21502371,"about_ca_system_score_codex":0.00038198006,"about_ca_system_score_gemma":0.00050869747,"threshold_uncertainty_score":0.99982506},"labels":[],"label_agreement":null},{"id":"W4240473936","doi":"10.1139/y04-902","title":"6th International Symposium of Fundamental and Applied Radiobiology / 6<sup>e</sup> Colloque international de radiobiologie fondamentale et appliqué","year":2004,"lang":"en","type":"article","venue":"Canadian Journal of Physiology and Pharmacology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Radiobiology; Physics; Philosophy; Nuclear medicine; Medical physics; Medicine; Nuclear physics; Irradiation","score_opus":0.008512645820105975,"score_gpt":0.2931317725453929,"score_spread":0.28461912672528694,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4240473936","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98654526,0.000467517,0.00032594163,0.01087587,0.0007688956,0.00014857121,0.00003321601,0.0000058175,0.00082888786],"genre_scores_gemma":[0.99174494,0.0006186095,0.001405671,0.0057393997,0.0003942752,0.0000070268256,0.000042942975,0.000012421879,0.0000347376],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999027,0.000095336465,0.00035548938,0.00018713974,0.000062326115,0.00027271977],"domain_scores_gemma":[0.99913913,0.00011789733,0.00022055021,0.000056465517,0.000075416974,0.00039052055],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037884602,0.00014274249,0.0004074327,0.00020761135,0.00007538438,0.000008515075,0.00018317536,0.00015381623,0.00044946943],"category_scores_gemma":[0.00004551103,0.00012478202,0.00007168017,0.00005615459,0.00075743225,0.000056861416,0.00004033414,0.0005535944,0.0000015791622],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004894613,0.00008763352,0.013969391,0.000052639625,0.00057037856,0.000122444,0.0010645839,0.002819886,0.9770188,0.0013151406,0.0014773356,0.0010123258],"study_design_scores_gemma":[0.080589056,0.008071682,0.14671408,0.00055659265,0.0019322524,0.036922783,0.0038471816,0.009027887,0.46832183,0.021152934,0.22110884,0.001754891],"about_ca_topic_score_codex":0.00029348547,"about_ca_topic_score_gemma":0.000033376713,"teacher_disagreement_score":0.508697,"about_ca_system_score_codex":0.00021340983,"about_ca_system_score_gemma":0.0006651612,"threshold_uncertainty_score":0.5088463},"labels":[],"label_agreement":null},{"id":"W4240573104","doi":"10.1164/ajrccm-conference.2021.203.1_meetingabstracts.a4568","title":"Radiomics Analysis to Predict Presence of Chronic Obstructive Pulmonary Disease and Symptoms Using Machine Learning","year":2021,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Paul's Hospital; Toronto Metropolitan University","funders":"","keywords":"Radiomics; Pulmonary disease; Medicine; Computer science; Disease; Artificial intelligence; Machine learning; Internal medicine","score_opus":0.008262739076586189,"score_gpt":0.2722305324846669,"score_spread":0.2639677934080807,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4240573104","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9681962,0.0027395429,0.027546842,0.00068082125,0.000083994644,0.0001790033,0.0000119332,0.00004908431,0.00051256036],"genre_scores_gemma":[0.9904323,0.00017211684,0.008036662,0.00018786207,0.00013585942,0.0000045781553,0.000059697708,0.000024301518,0.0009465751],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99859244,0.00009407335,0.0003082466,0.00042104063,0.00032461734,0.00025957517],"domain_scores_gemma":[0.99884444,0.00014383039,0.00009314869,0.0002935307,0.0001294357,0.0004955903],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002216099,0.00015965862,0.0004651719,0.00026355562,0.00009531715,0.000024603693,0.00008185716,0.00004796884,0.0001766031],"category_scores_gemma":[0.00083678885,0.00014074874,0.00014894005,0.00087629136,0.00013076275,0.00008155293,0.00016346946,0.00035649474,0.0000012020795],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001656786,0.00014803084,0.8952625,0.00026199283,0.0012933407,0.0004887326,0.00029269233,0.032742858,0.040239185,0.0002737943,0.000014765789,0.028816435],"study_design_scores_gemma":[0.00040838498,0.00007982124,0.15578124,0.00010063102,0.0016445192,0.00012415092,0.00009517766,0.84025174,0.0009246257,0.00005257199,0.00040794897,0.00012918685],"about_ca_topic_score_codex":0.00019048004,"about_ca_topic_score_gemma":0.000010208066,"teacher_disagreement_score":0.8075089,"about_ca_system_score_codex":0.00010288444,"about_ca_system_score_gemma":0.00021783599,"threshold_uncertainty_score":0.5739567},"labels":[],"label_agreement":null},{"id":"W4240957902","doi":"10.17504/protocols.io.sfvebn6","title":"Cloning guides to lentiCRISPR v2 v2","year":2018,"lang":"fr","type":"preprint","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Cloning (programming); Computational biology; Biology; Computer science; Programming language","score_opus":0.020728574875812176,"score_gpt":0.34699781745250485,"score_spread":0.32626924257669265,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4240957902","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.221885,0.0064643715,0.31222978,0.11933227,0.032381997,0.0020869628,0.0000234536,0.00074425957,0.30485192],"genre_scores_gemma":[0.4058864,0.0015698764,0.27294883,0.029190466,0.022810427,0.00011447619,0.0001828632,0.0003818444,0.2669148],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99495554,0.00023529,0.0011737515,0.0013577014,0.0008815799,0.0013961189],"domain_scores_gemma":[0.9962492,0.0003572972,0.00027830343,0.0013127647,0.00040103373,0.001401429],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0023488905,0.0007390821,0.0012134265,0.0003595853,0.0003011698,0.00024674195,0.00080104044,0.0005615588,0.008806623],"category_scores_gemma":[0.004101475,0.0006610401,0.00044142542,0.00032374111,0.0004855094,0.000086715496,0.0015913902,0.0023590026,0.006540688],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001546571,0.00048475276,0.04436923,0.0017533571,0.0010927836,0.0009880554,0.003147306,0.0021538166,0.008627923,0.027439844,0.73464227,0.17514598],"study_design_scores_gemma":[0.0012297163,0.00045820497,0.012181611,0.0055192295,0.0006900121,0.0003211792,0.00041094908,0.045477904,0.002357913,0.0015068096,0.9289076,0.000938873],"about_ca_topic_score_codex":0.002371234,"about_ca_topic_score_gemma":0.000030443549,"teacher_disagreement_score":0.1942653,"about_ca_system_score_codex":0.00045329545,"about_ca_system_score_gemma":0.00047913013,"threshold_uncertainty_score":0.9999426},"labels":[],"label_agreement":null},{"id":"W4242038247","doi":"10.4018/978-1-4666-9840-6.ch069","title":"The Role of Big Data in Radiation Oncology","year":2016,"lang":"en","type":"book-chapter","venue":"Big Data","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Big data; Radiation therapy; Radiation oncology; Medical physics; Data science; Demographics; Confidentiality; Data sharing; Computer science; Medicine; Bioinformatics; Internal medicine; Biology; Alternative medicine; Pathology; Data mining","score_opus":0.07895370055716519,"score_gpt":0.34235811649437964,"score_spread":0.2634044159372144,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4242038247","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000100346995,0.018443875,0.0008338103,0.01494474,0.0027168118,0.00063807116,0.002129679,0.000043945813,0.9601487],"genre_scores_gemma":[0.06342244,0.1071427,0.0031630222,0.00461544,0.028770564,0.000030464036,0.059286933,0.0005375763,0.73303086],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986177,0.000039963452,0.00041282797,0.0004503753,0.00029357473,0.0001855559],"domain_scores_gemma":[0.9961156,0.00041364614,0.00028349206,0.0030673763,0.00003349425,0.000086351545],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001176702,0.00015102979,0.0003920087,0.00012487457,0.0000428249,0.0000120728855,0.0012944165,0.0002156776,0.000052191714],"category_scores_gemma":[0.0011635979,0.00009121384,0.00002858656,0.000028180428,0.00020983578,0.00005579783,0.0011321723,0.0005555056,0.000058719354],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004926683,0.000017790566,0.00035931738,0.00002857987,0.00006299916,0.000029298277,0.00001909003,9.643369e-8,0.00012899646,0.0064756474,0.01693322,0.9758957],"study_design_scores_gemma":[0.0007518489,0.00005753663,0.00037327028,0.00032422694,0.00010029952,0.00003131093,0.00000840711,0.001367966,0.0000067133465,0.0031424682,0.99374187,0.00009409866],"about_ca_topic_score_codex":0.00012099593,"about_ca_topic_score_gemma":0.0001225663,"teacher_disagreement_score":0.9768086,"about_ca_system_score_codex":0.00006888552,"about_ca_system_score_gemma":0.00043687058,"threshold_uncertainty_score":0.37195927},"labels":[],"label_agreement":null},{"id":"W4243590773","doi":"10.21203/rs.3.rs-127490/v1","title":"Radiomics in Predicting Recurrence for Patients with Locally Advanced Breast Cancer using Quantitative Ultrasound","year":2020,"lang":"en","type":"preprint","venue":"Research Square","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University; York University; Sunnybrook Health Science Centre","funders":"Canadian Institutes of Health Research; Terry Fox Foundation","keywords":"Radiomics; Medicine; Support vector machine; Breast cancer; Ultrasound; Artificial intelligence; Radiology; Internal medicine; Cancer; Computer science","score_opus":0.05378092247755752,"score_gpt":0.42837839425389923,"score_spread":0.37459747177634173,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4243590773","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97643834,0.0009228155,0.014665145,0.002713099,0.00033209394,0.0040660175,0.0006657069,0.00007183094,0.000124941],"genre_scores_gemma":[0.9646444,0.0006830897,0.033192307,0.00013504554,0.00034528592,0.00039162044,0.0004615736,0.00012114124,0.000025581114],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961827,0.00029304402,0.00050409115,0.00096281513,0.0012272699,0.00083011866],"domain_scores_gemma":[0.9964809,0.0012250867,0.00022729547,0.000406939,0.0012377903,0.00042201777],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0012567943,0.00033875645,0.00073024153,0.00042437986,0.00020410729,0.00011103995,0.0003362921,0.00023407531,0.000029028972],"category_scores_gemma":[0.004014327,0.00028625972,0.00012492882,0.00066083565,0.00034506235,0.000121036464,0.0003156373,0.0033604456,0.000002209889],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004540658,0.00046894813,0.9400061,0.005669627,0.00024116499,0.00008490175,0.0023328594,0.017010026,0.00070335524,0.00020580959,0.00030801137,0.028428564],"study_design_scores_gemma":[0.009996376,0.0017871541,0.43529823,0.029033272,0.00016292388,0.000042656127,0.0015646799,0.51956254,0.00007659679,0.0009989999,0.00069957343,0.0007769681],"about_ca_topic_score_codex":0.0007565818,"about_ca_topic_score_gemma":0.00006673283,"teacher_disagreement_score":0.5047078,"about_ca_system_score_codex":0.00090121344,"about_ca_system_score_gemma":0.0016925668,"threshold_uncertainty_score":0.99995893},"labels":[],"label_agreement":null},{"id":"W4245042304","doi":"10.1016/s0735-1097(01)98323-8","title":"Time to treatment influences the impact of ST segment resolution on one year prognosis: Insights from ASSENT-2 Yuling Fu, Shaun Goodman, Wei-Ching Chang, Padma Kaul, Frans Van de Werf, Christopher B. Granger, Paul W. Armstrong, for the ASSENT 2 Investigators. University of Alberta, Edmonton, AB, Canada","year":2001,"lang":"en","type":"article","venue":"Journal of the American College of Cardiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Medicine","score_opus":0.010682610473595072,"score_gpt":0.25446870678043637,"score_spread":0.2437860963068413,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4245042304","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9874496,0.001074107,0.000795984,0.0098907035,0.00012380586,0.00048273162,0.00007281218,0.0000031771585,0.00010710809],"genre_scores_gemma":[0.99785686,0.0006248586,0.00078380207,0.00030159703,0.00031098168,0.0000040375157,0.0000035396765,0.000015969068,0.00009834997],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99840903,0.0003874375,0.00042386193,0.00015750293,0.0003761776,0.000245967],"domain_scores_gemma":[0.99770635,0.00073162344,0.00089680863,0.00029282685,0.00020025138,0.00017216236],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047381062,0.00017072423,0.0007866254,0.00008814124,0.00015593012,0.0000039158067,0.00033785336,0.00004755373,0.00001706139],"category_scores_gemma":[0.00034776953,0.00008983566,0.00039813074,0.00024079886,0.00041372582,0.000034001925,0.000042533404,0.0002990696,4.28899e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0094744265,0.0010528917,0.5895657,0.00013765668,0.015061698,0.00044187962,0.0060316552,0.20453487,0.06698559,0.00012578529,0.08816972,0.018418146],"study_design_scores_gemma":[0.0051333285,0.008539434,0.90062654,0.0011764751,0.0027303437,0.0002914053,0.0065933117,0.015095945,0.0019756556,0.00022835429,0.05723134,0.00037785288],"about_ca_topic_score_codex":0.14038445,"about_ca_topic_score_gemma":0.01343385,"teacher_disagreement_score":0.31106088,"about_ca_system_score_codex":0.0005454184,"about_ca_system_score_gemma":0.0008369372,"threshold_uncertainty_score":0.8653398},"labels":[],"label_agreement":null},{"id":"W4245231620","doi":"10.32920/ryerson.14655537","title":"A computer-aided diagnosis system for lung nodule detection in pulmonary CT images based on LS-SVM and wavelet transformation","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer-aided diagnosis; CAD; Computer science; Segmentation; Artificial intelligence; Wavelet; Support vector machine; Transformation (genetics); Filter (signal processing); Computer vision; Pattern recognition (psychology); Region of interest; Task (project management); Image processing; Image (mathematics); Engineering; Engineering drawing","score_opus":0.009220084394289337,"score_gpt":0.2662858504630631,"score_spread":0.25706576606877374,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4245231620","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45160514,0.00040440497,0.53995323,0.0033412757,0.00087908044,0.0020132067,0.000022729862,0.00019049029,0.0015904256],"genre_scores_gemma":[0.98012066,0.00014684138,0.017698325,0.00080673624,0.0002593979,0.000520682,0.00036280102,0.000042438533,0.000042114396],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99839514,0.0001166354,0.00048051338,0.0005115826,0.00026082192,0.00023529497],"domain_scores_gemma":[0.9990994,0.0002728113,0.00012611249,0.0002721528,0.00009122246,0.00013832925],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00058719097,0.00027073902,0.0005847405,0.00035223097,0.000076967866,0.00010661806,0.00007754539,0.0001543959,0.000015760896],"category_scores_gemma":[0.0001270073,0.00024030144,0.00016991323,0.000120581215,0.00003522217,0.00007640079,0.00005681076,0.0007687254,7.0100975e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038208973,0.0006782901,0.009631952,0.021027757,0.00014179312,0.00036679718,0.00040639157,0.0073867356,0.0021033152,0.000083343206,0.000505388,0.9572861],"study_design_scores_gemma":[0.0015589851,0.0001365559,0.008788886,0.0040188837,0.00013488991,0.00013248484,0.00019179207,0.9792924,0.0051911445,0.000011198969,0.0003176477,0.00022516485],"about_ca_topic_score_codex":0.00048498777,"about_ca_topic_score_gemma":0.000019283183,"teacher_disagreement_score":0.97190565,"about_ca_system_score_codex":0.00026486831,"about_ca_system_score_gemma":0.00014721703,"threshold_uncertainty_score":0.9799208},"labels":[],"label_agreement":null},{"id":"W4245306903","doi":"10.1139/y02-905","title":"Fifth international symposium of fundamental and applied radiobiology \"from radiobiology to clinic\" / Cinquième colloque international de radio-biologie fondamentale et appliquée « de la radiobiologie à la clinique »","year":2002,"lang":"fr","type":"article","venue":"Canadian Journal of Physiology and Pharmacology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Radiobiology; Medicine; Medical physics; Nuclear medicine; Physics; Internal medicine; Radiation therapy","score_opus":0.017701956744610614,"score_gpt":0.3414749317764889,"score_spread":0.3237729750318783,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4245306903","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95149595,0.010966618,0.0010658796,0.026274463,0.007104424,0.00041700905,0.0004229652,0.000015919064,0.0022367826],"genre_scores_gemma":[0.96944577,0.01505377,0.003325636,0.009533625,0.0020991324,0.000027471864,0.000102147555,0.000039894945,0.0003725867],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9955032,0.0019662532,0.0010474417,0.00054205547,0.00009043186,0.0008506597],"domain_scores_gemma":[0.9947506,0.0031998428,0.00063923595,0.00016183927,0.00012249788,0.0011259796],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002336687,0.0004087334,0.0011720585,0.0004066025,0.00014460261,0.000030989777,0.0006155224,0.000931094,0.004338075],"category_scores_gemma":[0.000408675,0.0003917526,0.00020887202,0.0001381891,0.0033678042,0.000097792596,0.00015224543,0.0018521821,0.000014222183],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011847579,0.00033713534,0.047011234,0.00012613805,0.0019351363,0.00061863865,0.0035667892,0.0005238625,0.9034915,0.0022792183,0.02695499,0.011970589],"study_design_scores_gemma":[0.021359783,0.005401617,0.07960537,0.0005747157,0.0015488584,0.013324523,0.0016894955,0.0051724,0.047719713,0.0067354655,0.8155973,0.0012707732],"about_ca_topic_score_codex":0.00092765474,"about_ca_topic_score_gemma":0.000096245334,"teacher_disagreement_score":0.8557718,"about_ca_system_score_codex":0.0005597896,"about_ca_system_score_gemma":0.0010005222,"threshold_uncertainty_score":0.99985343},"labels":[],"label_agreement":null},{"id":"W4246668736","doi":"10.1109/ultsym.2018.8580180","title":"Predicting Radiotherapy Response in Head and Neck Patients Using Quantitative Ultrasound","year":2018,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Health Science Centre","funders":"","keywords":"Medicine; Radiation therapy; Head and neck cancer; Magnetic resonance imaging; Ultrasound; Radiology; Lymph; Head and neck; Surgery; Pathology","score_opus":0.02099950571520235,"score_gpt":0.35087298612492507,"score_spread":0.3298734804097227,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4246668736","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99524355,0.00014519595,0.002881227,0.00057257083,0.00012760086,0.00019604836,0.0000011127282,0.000037887337,0.00079480914],"genre_scores_gemma":[0.9563853,0.00003307075,0.04220735,0.0011080037,0.00010530795,0.0000017738225,0.000002983358,0.000020673491,0.00013551788],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9990723,0.000115586045,0.00021267499,0.0002185423,0.00016659992,0.00021428848],"domain_scores_gemma":[0.9992872,0.00035993493,0.000051774914,0.00011770125,0.00006500872,0.00011837546],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005645358,0.00010209376,0.00020209231,0.00014409637,0.000084307074,0.000025084493,0.000038214675,0.00004929543,0.00007428155],"category_scores_gemma":[0.0014631024,0.00008287634,0.00002338076,0.00017745106,0.00019541135,0.000085734944,0.000016426282,0.0002193088,0.0000030060714],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016327035,0.0000861235,0.97828484,0.00001611139,0.000023188031,0.000011669481,0.002017849,0.000012408951,0.01547587,0.000087654706,0.00008516293,0.0022663937],"study_design_scores_gemma":[0.0039048798,0.0013295752,0.8908999,0.0002475855,0.000015652291,0.00005609121,0.00027992422,0.101806514,0.00028199912,0.000059199992,0.0010038947,0.00011480189],"about_ca_topic_score_codex":0.00032910434,"about_ca_topic_score_gemma":0.000017681328,"teacher_disagreement_score":0.1017941,"about_ca_system_score_codex":0.00007754211,"about_ca_system_score_gemma":0.000052289033,"threshold_uncertainty_score":0.3379599},"labels":[],"label_agreement":null},{"id":"W4246937588","doi":"10.5489/cuaj.734","title":"HIFU: Definitely ready for prime time","year":2013,"lang":"en","type":"article","venue":"Canadian Urological Association Journal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Prime time; Prime (order theory); Computer science; Medicine; Mathematics; Telecommunications; Combinatorics","score_opus":0.014529171884097703,"score_gpt":0.2525608013312605,"score_spread":0.23803162944716283,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4246937588","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.71271294,0.00029487428,0.002019811,0.25909647,0.00074668915,0.0008710214,0.00003179993,0.00010867529,0.024117704],"genre_scores_gemma":[0.9583229,0.00002812368,0.0052954922,0.027666371,0.0012322114,0.00002878892,0.00007150548,0.000027849012,0.0073267627],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.998742,0.000079260506,0.00028875005,0.00014858229,0.00024134252,0.0005000578],"domain_scores_gemma":[0.99817795,0.00028254383,0.00018280998,0.00008280526,0.0003180759,0.00095581776],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00076706754,0.000105448904,0.00024581954,0.00013586627,0.00023645401,0.00012389866,0.00010301304,0.00019228224,0.0019643537],"category_scores_gemma":[0.0033013227,0.000081618964,0.000121452635,0.00010158073,0.000028445384,0.00008687561,0.000008152688,0.0006513555,0.0006833224],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043688124,0.00008276382,0.43629223,0.000010108189,0.00022842675,0.000069532354,0.0001223675,0.00003623452,0.0017805749,0.0011931994,0.5092417,0.05089916],"study_design_scores_gemma":[0.0015960002,0.00043078183,0.47733736,0.000017289245,0.00009893516,0.00040381186,0.000018886547,0.009805812,0.000017368708,0.003968047,0.50611943,0.00018627913],"about_ca_topic_score_codex":0.0008123329,"about_ca_topic_score_gemma":0.000019904226,"teacher_disagreement_score":0.24560995,"about_ca_system_score_codex":0.0005845099,"about_ca_system_score_gemma":0.00037269044,"threshold_uncertainty_score":0.998948},"labels":[],"label_agreement":null},{"id":"W4247596941","doi":"10.1109/tmi.2014.2313493","title":"IEEE Transactions on Medical Imaging publication information","year":2014,"lang":"en","type":"article","venue":"IEEE Transactions on Medical Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Medical imaging; Computer science; Computer vision; Medical physics; Computer graphics (images); Information retrieval; Artificial intelligence; Medicine","score_opus":0.007603488287088895,"score_gpt":0.2789357131475343,"score_spread":0.2713322248604454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4247596941","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030623188,0.000039381863,0.9216451,0.06554261,0.002338462,0.00040438274,0.000011823025,0.00060852605,0.00634742],"genre_scores_gemma":[0.961837,0.0001942322,0.0017977428,0.034875847,0.00051024515,0.00012292634,0.00004509689,0.00008400907,0.000532913],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99419785,0.0002761869,0.001094875,0.00062146975,0.0029888148,0.00082083605],"domain_scores_gemma":[0.9964709,0.00068310945,0.00022059231,0.0006962884,0.00032570987,0.0016033507],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0022264628,0.00047004854,0.00059514045,0.0008832428,0.0006212921,0.0002034259,0.00046965532,0.0002846208,0.0039182743],"category_scores_gemma":[0.0007853626,0.0004206625,0.0003704518,0.0007249753,0.00050712016,0.0009137416,0.0000019652343,0.0030183366,0.0007521787],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012476303,0.00051022304,0.00012239265,0.000114628005,0.000083024075,0.000049735572,0.0003748455,0.001001108,0.0002928842,0.00014441054,0.005510148,0.99167186],"study_design_scores_gemma":[0.0042307912,0.00013929763,0.0003087721,0.00087439845,0.00023030562,0.0008911199,0.00023190147,0.9356787,0.003427897,0.00013657745,0.053328555,0.0005216902],"about_ca_topic_score_codex":0.00016662628,"about_ca_topic_score_gemma":0.0000114317045,"teacher_disagreement_score":0.99115014,"about_ca_system_score_codex":0.0002828073,"about_ca_system_score_gemma":0.00048713613,"threshold_uncertainty_score":0.9998245},"labels":[],"label_agreement":null},{"id":"W4248178644","doi":"10.21203/rs.3.rs-47377/v1","title":"MRI background parenchymal enhancement, breast density and breast cancer risk factors: A cross-sectional study in pre- and post-menopausal women.","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Breast cancer; Medicine; Cross-sectional study; Oncology; Obstetrics; Gynecology; Cancer; Radiology; Internal medicine; Pathology","score_opus":0.018412109715669478,"score_gpt":0.3286091812365281,"score_spread":0.3101970715208586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4248178644","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99603784,0.00021803571,0.00063853094,0.0010665283,0.00044786802,0.0011056403,0.0002744804,0.00008082857,0.00013024829],"genre_scores_gemma":[0.9976765,0.00039831642,0.00031393731,0.00039075947,0.0004891558,0.00013416453,0.0001247479,0.0000475369,0.00042486918],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99687785,0.00017258764,0.0006488671,0.0012130969,0.0005748271,0.00051280076],"domain_scores_gemma":[0.99852264,0.00012953379,0.0002745844,0.00032694612,0.00017672929,0.00056955963],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007146924,0.0005013244,0.0008399727,0.00018523757,0.00017902505,0.0003049513,0.00015501944,0.00025063023,0.00063207967],"category_scores_gemma":[0.00010987372,0.00041295294,0.000046535595,0.0001389751,0.0002703884,0.00012368229,0.0008745875,0.0021594083,0.000004053849],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006737451,0.0004982917,0.9923968,0.000310252,0.00044649775,0.00007437365,0.0026743016,0.000070356065,0.0014840456,0.000010788297,0.00005983493,0.0013007612],"study_design_scores_gemma":[0.0026135226,0.00057420187,0.9914012,0.00015490392,0.0001493532,0.00028388193,0.00069592235,0.0035937768,0.00001448688,0.00010852989,0.00003546048,0.00037478175],"about_ca_topic_score_codex":0.024542663,"about_ca_topic_score_gemma":0.00052711804,"teacher_disagreement_score":0.024015544,"about_ca_system_score_codex":0.00043249087,"about_ca_system_score_gemma":0.0003557779,"threshold_uncertainty_score":0.9998322},"labels":[],"label_agreement":null},{"id":"W4248260710","doi":"10.1055/s-0035-1552206","title":"Hochkarätige Auszeichnung für RWTH-Radiologin – Univ.-Prof. Dr. med. Christiane Kuhl erhält Gold-Medaille der International Society of Magnetic Resonance in Medicine (ISMRM)","year":2015,"lang":"de","type":"article","venue":"RöFo - Fortschritte auf dem Gebiet der Röntgenstrahlen und der bildgebenden Verfahren","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Gold medal; Nuclear medicine; Magnetic resonance imaging; Medicine; Art; Radiology; Art history","score_opus":0.03159644182635454,"score_gpt":0.3297082073065797,"score_spread":0.2981117654802251,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4248260710","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19125286,0.70640486,0.005296943,0.06795761,0.011772649,0.0042791115,0.00049508986,0.00064258365,0.011898319],"genre_scores_gemma":[0.9131136,0.03833265,0.010384922,0.006946522,0.0077753556,0.0002459346,0.002061794,0.0007471195,0.020392122],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9869384,0.0006823503,0.0036553915,0.0026474772,0.00330466,0.00277169],"domain_scores_gemma":[0.9928229,0.0008441975,0.001354127,0.0020516359,0.0009909349,0.0019361917],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow","research_integrity"],"category_scores_codex":[0.004484528,0.0018511846,0.0032033685,0.0010165063,0.00031285745,0.00018683965,0.0021513293,0.0015775744,0.0009906556],"category_scores_gemma":[0.0017420542,0.0017111666,0.00087797194,0.0018008308,0.0023660741,0.00067982875,0.0009388479,0.0037969376,0.00031876034],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013108768,0.0015242109,0.21254621,0.0014022666,0.005005587,0.0021760769,0.008273753,0.0014240541,0.0027740586,0.0015320736,0.6928674,0.069163434],"study_design_scores_gemma":[0.02533561,0.0023982404,0.0817285,0.0047343457,0.0053139236,0.0007650283,0.002851088,0.06550517,0.0010411502,0.0023924746,0.80494255,0.002991909],"about_ca_topic_score_codex":0.003942306,"about_ca_topic_score_gemma":0.00026379217,"teacher_disagreement_score":0.7218607,"about_ca_system_score_codex":0.0010941161,"about_ca_system_score_gemma":0.0021618742,"threshold_uncertainty_score":0.9999226},"labels":[],"label_agreement":null},{"id":"W4248833175","doi":"10.1109/tmi.2014.2302951","title":"IEEE Transactions on Medical Imaging publication information","year":2014,"lang":"en","type":"article","venue":"IEEE Transactions on Medical Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Medical imaging; Computer science; Medical physics; Computer vision; Artificial intelligence; Medicine","score_opus":0.007603488287088895,"score_gpt":0.2789357131475343,"score_spread":0.2713322248604454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4248833175","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030623188,0.000039381863,0.9216451,0.06554261,0.002338462,0.00040438274,0.000011823025,0.00060852605,0.00634742],"genre_scores_gemma":[0.961837,0.0001942322,0.0017977428,0.034875847,0.00051024515,0.00012292634,0.00004509689,0.00008400907,0.000532913],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99419785,0.0002761869,0.001094875,0.00062146975,0.0029888148,0.00082083605],"domain_scores_gemma":[0.9964709,0.00068310945,0.00022059231,0.0006962884,0.00032570987,0.0016033507],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0022264628,0.00047004854,0.00059514045,0.0008832428,0.0006212921,0.0002034259,0.00046965532,0.0002846208,0.0039182743],"category_scores_gemma":[0.0007853626,0.0004206625,0.0003704518,0.0007249753,0.00050712016,0.0009137416,0.0000019652343,0.0030183366,0.0007521787],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012476303,0.00051022304,0.00012239265,0.000114628005,0.000083024075,0.000049735572,0.0003748455,0.001001108,0.0002928842,0.00014441054,0.005510148,0.99167186],"study_design_scores_gemma":[0.0042307912,0.00013929763,0.0003087721,0.00087439845,0.00023030562,0.0008911199,0.00023190147,0.9356787,0.003427897,0.00013657745,0.053328555,0.0005216902],"about_ca_topic_score_codex":0.00016662628,"about_ca_topic_score_gemma":0.0000114317045,"teacher_disagreement_score":0.99115014,"about_ca_system_score_codex":0.0002828073,"about_ca_system_score_gemma":0.00048713613,"threshold_uncertainty_score":0.9998245},"labels":[],"label_agreement":null},{"id":"W4249119398","doi":"10.1016/s1701-2163(16)30349-8","title":"JOGC Self-Assessment Test","year":2003,"lang":"en","type":"article","venue":"Journal of Obstetrics and Gynaecology Canada","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine; Test (biology); Medical physics","score_opus":0.006191849410539667,"score_gpt":0.2521038020279154,"score_spread":0.24591195261737572,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4249119398","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9651657,0.004708671,0.00037965117,0.0030673249,0.010458846,0.00011903793,0.0000023303555,0.000008799406,0.016089646],"genre_scores_gemma":[0.99046016,0.00024483146,0.00763168,0.0014449393,0.000030750372,6.360961e-7,6.1868263e-7,0.00001018674,0.00017620422],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.999034,0.00004568976,0.00034445093,0.000092050366,0.00028612083,0.00019771101],"domain_scores_gemma":[0.9972893,0.0018892806,0.00022889604,0.00008537417,0.0001964366,0.00031072923],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041831422,0.000089653484,0.00030745528,0.00014391098,0.000077674915,0.000015621301,0.00006162547,0.00006209544,0.00019469894],"category_scores_gemma":[0.0063470053,0.0000690902,0.000044366323,0.00020224892,0.000033420016,0.000032865744,0.000013296165,0.0005509096,3.18277e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[9.567958e-7,0.00016883649,0.93991387,0.00004580149,0.00012883056,0.004303684,0.000040698134,0.000023618572,0.00006132733,0.0009376796,0.0073769423,0.046997763],"study_design_scores_gemma":[0.0029264241,0.0005506582,0.77361107,0.000009014111,0.00016490734,0.0009120403,0.00014601617,0.0007612995,0.00003416334,0.00019096225,0.22058356,0.000109871624],"about_ca_topic_score_codex":0.0013615589,"about_ca_topic_score_gemma":0.0005916278,"teacher_disagreement_score":0.21320662,"about_ca_system_score_codex":0.00076031935,"about_ca_system_score_gemma":0.0028896877,"threshold_uncertainty_score":0.7598417},"labels":[],"label_agreement":null},{"id":"W4250965155","doi":"10.1158/1538-7755.carisk16-b17","title":"Abstract B17: Comprehensive colorectal cancer risk prediction to inform personalized screening and intervention","year":2017,"lang":"en","type":"article","venue":"Cancer Epidemiology Biomarkers & Prevention","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Cancer; Colorectal cancer; Citation; Intervention (counseling); Medicine; Gerontology; White (mutation); Library science; Oncology; Internal medicine; Computer science; Biology; Psychiatry; Genetics","score_opus":0.05363729525855996,"score_gpt":0.4097620313023526,"score_spread":0.35612473604379263,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4250965155","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9631658,0.005251902,0.015951935,0.0133024035,0.0011500752,0.00077737804,0.00004810724,0.00008906674,0.00026328626],"genre_scores_gemma":[0.98770124,0.0032224748,0.0068821106,0.000833891,0.000449185,0.00026189812,0.00012490913,0.000031412656,0.0004928784],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9980849,0.00023619607,0.0006241175,0.0005036626,0.00015754082,0.00039357747],"domain_scores_gemma":[0.9982071,0.00028612727,0.0007621017,0.0002806036,0.00014936274,0.00031472865],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017794393,0.00022987703,0.0005696231,0.00016262787,0.000665796,0.000040091476,0.00015040433,0.000216806,0.00027744746],"category_scores_gemma":[0.0019106956,0.00020721175,0.00024784476,0.00007633389,0.00044189318,0.00025744224,0.00012655697,0.00048701424,0.0000090025],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008854474,0.000036269394,0.64171916,0.00013102581,0.00059281144,0.0000056063436,0.00013601486,0.00004959468,0.002424208,0.00007675124,0.0038232356,0.35011983],"study_design_scores_gemma":[0.0029045513,0.0002970716,0.9681359,0.0011710712,0.00035252052,0.0000276845,0.00012372066,0.011456296,0.00012266352,0.00058400107,0.014651837,0.00017268103],"about_ca_topic_score_codex":0.0023778817,"about_ca_topic_score_gemma":0.00022902929,"teacher_disagreement_score":0.34994715,"about_ca_system_score_codex":0.00019295778,"about_ca_system_score_gemma":0.000070123926,"threshold_uncertainty_score":0.84498495},"labels":[],"label_agreement":null},{"id":"W4251107680","doi":"10.1149/ma2008-02/27/2020","title":"New GI Imaging Technologies: Seeing the Bowel from a New Angle","year":2008,"lang":"en","type":"article","venue":"ECS Meeting Abstracts","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University Medical Centre","funders":"","keywords":"Medicine; Computer science","score_opus":0.01308273763394881,"score_gpt":0.25876282688522323,"score_spread":0.2456800892512744,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4251107680","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8734711,0.0044578305,0.00092229946,0.041586403,0.0006387082,0.00028920887,0.0000018051303,0.0010361423,0.0775965],"genre_scores_gemma":[0.9665448,0.00015601717,0.028560393,0.0015212756,0.0009641567,0.0000035939659,0.000012907574,0.00005451159,0.00218234],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982122,0.00003268169,0.00041411823,0.00040333768,0.0004376095,0.0005000587],"domain_scores_gemma":[0.99856293,0.00041071052,0.00021110523,0.0005104739,0.00004461154,0.00026014182],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004525606,0.00023244854,0.00030340077,0.00010469797,0.00035952963,0.00006712446,0.00032734795,0.00010588734,0.00006627219],"category_scores_gemma":[0.0027428064,0.00016768275,0.0001224121,0.00023736997,0.0001481,0.00010758361,0.00012321558,0.0010628194,0.00011967229],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001775725,0.00023676819,0.23259655,0.00010808353,0.00035280528,0.004215569,0.011195955,0.010714779,0.13942043,0.00005294592,0.3545398,0.24638873],"study_design_scores_gemma":[0.008297594,0.00022375672,0.37225154,0.003621896,0.00056310877,0.0034510347,0.005164627,0.04376527,0.08237109,0.008480079,0.47015,0.0016600107],"about_ca_topic_score_codex":0.0056534456,"about_ca_topic_score_gemma":0.000010955817,"teacher_disagreement_score":0.24472871,"about_ca_system_score_codex":0.00007462422,"about_ca_system_score_gemma":0.00032562445,"threshold_uncertainty_score":0.8546356},"labels":[],"label_agreement":null},{"id":"W4251819856","doi":"10.5152/ced.2013.35","title":"X-Ray-Evaluation 2","year":2013,"lang":"en","type":"article","venue":"Çocuk Enfeksiyon Dergisi/Journal of Pediatric Infection","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Nortel (Canada)","funders":"","keywords":"X-ray; Physics; Optics","score_opus":0.01493453050172464,"score_gpt":0.30431884456267827,"score_spread":0.2893843140609536,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4251819856","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97592777,0.0010020836,0.013928264,0.0020019975,0.0017155289,0.00039178,3.0704615e-7,0.000049375136,0.0049829073],"genre_scores_gemma":[0.99103904,0.0013968406,0.002813362,0.00045283817,0.0039698505,0.000014032485,0.0000071338186,0.000031563184,0.00027535568],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99777067,0.00016593032,0.0007203357,0.00017966336,0.000890403,0.00027302842],"domain_scores_gemma":[0.99776894,0.00013931346,0.00062814663,0.0001906002,0.0009973787,0.00027564596],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0016718638,0.000175578,0.0003536528,0.0006106075,0.000113961374,0.00007664845,0.000088850065,0.0001456234,0.0014933948],"category_scores_gemma":[0.0015500489,0.00014240881,0.00023896938,0.0004747816,0.000040150488,0.00046765807,0.000029138186,0.0007974175,0.00020636978],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014070208,0.00065253425,0.6190927,0.00027376073,0.0003115074,0.00010608718,0.00046954013,0.0060457084,0.0044734646,0.00023793527,0.076184265,0.2920118],"study_design_scores_gemma":[0.008791044,0.001795776,0.8946457,0.00014588733,0.0024320746,0.0023848156,0.000112258036,0.054378536,0.0005408408,0.0032372114,0.03097609,0.0005597763],"about_ca_topic_score_codex":0.00014812396,"about_ca_topic_score_gemma":0.0000014612372,"teacher_disagreement_score":0.29145202,"about_ca_system_score_codex":0.00021325397,"about_ca_system_score_gemma":0.00029859718,"threshold_uncertainty_score":0.9994194},"labels":[],"label_agreement":null},{"id":"W4252535443","doi":"10.21203/rs.3.rs-35238/v1","title":"Predicting Pathological Complete Response (Pcr) After Stereotactic Ablative Radiation Therapy (Sabr) of Lung Cancer Using Quantitative Dynamic [18f]fdg Pet and Ct Perfusion: A Prospective Exploratory Clinical Study","year":2020,"lang":"en","type":"preprint","venue":"Research Square","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; London Health Sciences Centre; Sunnybrook Health Science Centre; Western University","funders":"Ontario Institute for Cancer Research","keywords":"SABR volatility model; Medicine; Nuclear medicine; Lung cancer; Radiation therapy; Ablative case; Radiosurgery; Radiology; Internal medicine","score_opus":0.1385060250834018,"score_gpt":0.5014855697976511,"score_spread":0.3629795447142493,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4252535443","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98799986,0.0046164882,0.00047205266,0.0016031506,0.00026474375,0.004746137,0.00018670927,0.000079387886,0.00003145329],"genre_scores_gemma":[0.99542534,0.0021965054,0.0013023395,0.00012396238,0.0002465938,0.00053757854,0.000048424154,0.0000916861,0.000027553508],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98889214,0.00650132,0.0010670761,0.0013573129,0.001588296,0.0005938282],"domain_scores_gemma":[0.9940985,0.0033073663,0.00053637,0.0005785664,0.0010251156,0.0004540737],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.007656343,0.00044944714,0.0013303678,0.000484382,0.00032238112,0.0001212552,0.00026354048,0.00015800298,0.0001141514],"category_scores_gemma":[0.007214944,0.00036077917,0.00023738586,0.00059073366,0.0008702245,0.00015706051,0.00097561185,0.0049597006,0.0000026419677],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.015353781,0.0008309977,0.9559746,0.0008057351,0.0006248588,0.0024222448,0.019065158,0.00015368979,0.0015443874,0.000012840082,0.00003351837,0.0031782163],"study_design_scores_gemma":[0.003376154,0.0034208887,0.7192396,0.0018009793,0.00016963783,0.00006413369,0.0071686604,0.2643364,0.000014121782,0.0001186225,0.000036101144,0.00025467156],"about_ca_topic_score_codex":0.0003602166,"about_ca_topic_score_gemma":0.000028928853,"teacher_disagreement_score":0.26418272,"about_ca_system_score_codex":0.00065278774,"about_ca_system_score_gemma":0.0012867779,"threshold_uncertainty_score":0.9998844},"labels":[],"label_agreement":null},{"id":"W4253312121","doi":"10.1093/neuonc/now073.105","title":"HG-109CONTEMPORARY SURVIVAL ENDPOINTS: AN INTERNATIONAL DIFFUSE INTRINSIC PONTINE GLIOMA REGISTRY STUDY","year":2016,"lang":"en","type":"article","venue":"Neuro-Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier Universitaire Sainte-Justine; Hospital for Sick Children","funders":"","keywords":"Medicine; Glioma; Oncology; Cancer research","score_opus":0.023863114997970326,"score_gpt":0.3341269492117,"score_spread":0.31026383421372966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4253312121","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95920694,0.00003312258,0.0004451041,0.024986988,0.0028102563,0.00040757595,0.000009096905,0.00019336081,0.0119075645],"genre_scores_gemma":[0.99455327,0.00005750186,0.00048415572,0.0027391294,0.0014494545,0.000025442896,0.00002539288,0.00005603725,0.000609607],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976193,0.00043345988,0.0005326766,0.0006096807,0.0004382588,0.00036663123],"domain_scores_gemma":[0.99809134,0.00053228077,0.00024048288,0.00061899325,0.00013153857,0.00038535078],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00076116534,0.00023359548,0.0005400151,0.0002476636,0.000080497084,0.00003155945,0.00041574345,0.00014568455,0.00038622212],"category_scores_gemma":[0.002330467,0.0001619214,0.00010319006,0.00016294503,0.0002241673,0.00023093242,0.00021304413,0.0006080875,0.00008307106],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015311339,0.003868346,0.34142512,0.000018928664,0.0002056334,0.008488176,0.0005891333,7.531456e-7,0.4100429,0.0005579206,0.0067228097,0.22654912],"study_design_scores_gemma":[0.034277894,0.0092761405,0.2302747,0.00012459242,0.00022089852,0.0035515495,0.00096848153,0.00053087214,0.003251464,0.00031773528,0.7166344,0.00057128916],"about_ca_topic_score_codex":0.00007945995,"about_ca_topic_score_gemma":0.000024857462,"teacher_disagreement_score":0.7099116,"about_ca_system_score_codex":0.00018922304,"about_ca_system_score_gemma":0.0002454337,"threshold_uncertainty_score":0.6602963},"labels":[],"label_agreement":null},{"id":"W4253412803","doi":"10.1155/2004/614149","title":"Helical Computed Tomography Has a Role in the Screening of Lung Cancer ‐‐ The Con Argument","year":2004,"lang":"en","type":"letter","venue":"Canadian Respiratory Journal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Medicine; Asymptomatic; Lung cancer screening; Computed tomography; Lung cancer; Disease; Subclinical infection; Radiology; Cancer screening; Cancer; Screening test; Population; Test (biology); Diagnostic test; Surgery; Pediatrics; Pathology; Internal medicine","score_opus":0.020415264704287638,"score_gpt":0.28240075883314775,"score_spread":0.26198549412886013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4253412803","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025729511,0.019315252,0.0003847974,0.9524079,0.0004983902,0.0006820273,0.00003871771,0.00001383535,0.00092956517],"genre_scores_gemma":[0.07945187,0.00007665457,0.00020767399,0.91610885,0.003979396,0.000030466395,0.000022445503,0.00006015831,0.00006251428],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972513,0.00042976975,0.0006276883,0.0002627708,0.00075513066,0.0006733979],"domain_scores_gemma":[0.9985227,0.00018377989,0.0003377674,0.00038993024,0.0001539756,0.00041186405],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0014071425,0.00028516765,0.00052439,0.0006952963,0.00040546185,0.00018704805,0.0006025205,0.000369725,0.00022591319],"category_scores_gemma":[0.0001515114,0.00016954097,0.00031011706,0.0004483752,0.00042923738,0.000045177174,0.000026323387,0.006822136,0.000001933017],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028140385,0.000021075793,0.027994912,0.00015638348,0.00032790483,0.0047945324,0.0010498158,0.0006627988,0.00004466069,0.00006292495,0.9562633,0.008593534],"study_design_scores_gemma":[0.0013438688,0.00009716472,0.016241523,0.0019003138,0.00021393847,0.0008125192,0.00014439458,0.00107042,0.00001028038,0.00012979057,0.9778339,0.00020188073],"about_ca_topic_score_codex":0.022089321,"about_ca_topic_score_gemma":0.0080659585,"teacher_disagreement_score":0.05372236,"about_ca_system_score_codex":0.0005106809,"about_ca_system_score_gemma":0.0032248665,"threshold_uncertainty_score":0.99546915},"labels":[],"label_agreement":null},{"id":"W4254024135","doi":"10.1016/j.jalz.2016.06.1005","title":"P1‐256: Estimating and Accounting for The Effect of MRI Scanner Hardware Changes on Longitudinal Whole‐Brain Atrophy Measurements","year":2016,"lang":"en","type":"article","venue":"Alzheimer s & Dementia","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Montreal Neurological Institute and Hospital; McGill University","funders":"","keywords":"Scanner; Atrophy; Neuroimaging; Nuclear medicine; Computer science; Psychology; Medicine; Artificial intelligence; Neuroscience; Pathology","score_opus":0.02859066959290551,"score_gpt":0.30673262737162765,"score_spread":0.27814195777872214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4254024135","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.69889337,0.06750614,0.113657475,0.111861676,0.002756541,0.004321509,0.000050101888,0.00023510473,0.0007180677],"genre_scores_gemma":[0.9941554,0.000015627116,0.0046167867,0.00061090884,0.0004508351,0.0000762811,0.0000079670945,0.000039600673,0.000026600606],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9986533,0.00006903291,0.0002445734,0.00031543782,0.00039458368,0.00032307944],"domain_scores_gemma":[0.99872833,0.00065573596,0.00018354377,0.00026308213,0.00007674519,0.00009255752],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001182851,0.0002005955,0.00031593998,0.00008325542,0.0002133172,0.000036515357,0.00013793854,0.000051140556,0.000035645106],"category_scores_gemma":[0.00059426355,0.00010481766,0.000098055556,0.000083048966,0.00014069377,0.00006110297,0.00007479079,0.00014781304,0.0000060040907],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030453215,0.00003304468,0.1788382,0.000107867505,0.0062466306,0.000006189247,0.0001193056,0.00007501995,0.017470414,0.000039919727,0.0070105284,0.7897484],"study_design_scores_gemma":[0.04097842,0.010788556,0.37599006,0.007898174,0.09357122,0.00020751172,0.00020384332,0.13059491,0.18012764,0.00036358606,0.15717208,0.0021040088],"about_ca_topic_score_codex":0.000051962208,"about_ca_topic_score_gemma":0.000008221412,"teacher_disagreement_score":0.7876443,"about_ca_system_score_codex":0.000008481353,"about_ca_system_score_gemma":0.000019734034,"threshold_uncertainty_score":0.427434},"labels":[],"label_agreement":null},{"id":"W4280507273","doi":"10.1097/rlu.0000000000004253","title":"Combined 18F-FDG PET/CT Radiomics and Sarcopenia Score in Predicting Relapse-Free Survival and Overall Survival in Patients With Esophagogastric Cancer","year":2022,"lang":"en","type":"article","venue":"Clinical Nuclear Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; Toronto General Hospital; University Health Network; Health Sciences Centre; Sunnybrook Health Science Centre","funders":"","keywords":"Medicine; Sarcopenia; Radiomics; Cancer; Stage (stratigraphy); Internal medicine; Esophageal cancer; Adenocarcinoma; Positron emission tomography; Radiology; Oncology","score_opus":0.02079249347028335,"score_gpt":0.3057204929899885,"score_spread":0.28492799951970516,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4280507273","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9869988,0.0005733164,0.0000045742536,0.010344496,0.00084501406,0.00063308154,0.000016475,0.00005961775,0.0005246559],"genre_scores_gemma":[0.99611294,0.0006092572,0.00044041523,0.0022581106,0.00028747134,0.000017026152,0.000051689163,0.00008976157,0.00013331795],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.996516,0.00045344204,0.0010116483,0.0007138028,0.00081185135,0.00049324933],"domain_scores_gemma":[0.9978553,0.0009018269,0.00026553468,0.00045138795,0.000060120936,0.00046583888],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027357193,0.00029548124,0.0011201815,0.00030194558,0.00017722421,0.00002086252,0.00027692798,0.000032446882,0.000319435],"category_scores_gemma":[0.0028576723,0.00023673772,0.000056018776,0.00049689604,0.0006421807,0.000104860424,0.00050250796,0.0021834902,0.0000016664081],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002299779,0.00039228302,0.98791003,0.00009504882,0.00006391511,0.0010552704,0.00024864546,0.000063172454,0.000009661802,0.00020417896,0.0013121904,0.0063458183],"study_design_scores_gemma":[0.036478166,0.0027134118,0.94591045,0.00051883457,0.00012443437,0.00012719422,0.00046843733,0.011293808,1.5227867e-7,0.00012997868,0.0020217316,0.0002133767],"about_ca_topic_score_codex":0.0009110585,"about_ca_topic_score_gemma":0.00007974954,"teacher_disagreement_score":0.04199956,"about_ca_system_score_codex":0.00018156285,"about_ca_system_score_gemma":0.0001300154,"threshold_uncertainty_score":0.9653884},"labels":[],"label_agreement":null},{"id":"W4280565666","doi":"10.1177/14604582221102314","title":"Can artificial intelligence improve cancer treatments?","year":2022,"lang":"en","type":"review","venue":"Health Informatics Journal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Artificial intelligence; Computer science; Cancer; Population; Machine learning; Transformation (genetics); Scale (ratio); Medical physics; Medicine; Internal medicine; Biology","score_opus":0.11293171525724917,"score_gpt":0.45287275905793073,"score_spread":0.3399410438006816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4280565666","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000029846194,0.9916364,0.0014284842,0.0033810101,0.002021445,0.0007788035,0.000062819985,0.00003823884,0.0006497967],"genre_scores_gemma":[0.0000012792516,0.9906589,0.0048963125,0.0028500617,0.0009773601,0.000091023976,0.00011515808,0.000057641755,0.0003522828],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9957208,0.00015898432,0.0026165303,0.00013911666,0.0007136356,0.0006509303],"domain_scores_gemma":[0.9965803,0.00015003276,0.0020870809,0.00030153533,0.000059196023,0.0008218705],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0016279874,0.00037828137,0.0017694171,0.00042919454,0.0006098673,0.00012368384,0.00027392784,0.00013655343,0.0013255738],"category_scores_gemma":[0.00031353626,0.00027048966,0.00047655715,0.00034649667,0.00006989573,0.00008984022,0.0001009493,0.0034870761,0.000037210626],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000070545957,0.000056832727,0.000002185519,0.012672289,0.00022076585,0.000047361194,0.0009040543,0.000021007296,8.419586e-9,0.00018979989,0.0016473482,0.9842313],"study_design_scores_gemma":[0.00013984699,0.00037420593,5.435713e-7,0.006462491,0.0005476321,0.0029276265,0.0002920126,0.0027198875,8.5712244e-8,0.00028533436,0.9860534,0.00019692538],"about_ca_topic_score_codex":0.000114545925,"about_ca_topic_score_gemma":0.0000044033463,"teacher_disagreement_score":0.98440605,"about_ca_system_score_codex":0.001855616,"about_ca_system_score_gemma":0.0053018103,"threshold_uncertainty_score":0.9999747},"labels":[],"label_agreement":null},{"id":"W4280603043","doi":"10.1088/1361-6560/ac6fab","title":"Radiomics-guided radiation therapy: opportunities and challenges","year":2022,"lang":"en","type":"review","venue":"Physics in Medicine and Biology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Spinal Cord Injury BC; BC Cancer Agency; University of British Columbia; Surrey Memorial Hospital; Okanagan University College; BC Cancer Foundation; University of British Columbia, Okanagan Campus","funders":"BC Cancer Agency","keywords":"Radiomics; Radiation therapy; Medical physics; Medicine; Image-guided radiation therapy; Personalized medicine; Medical imaging; Radiogenomics; Radiology; Bioinformatics","score_opus":0.5535911643878426,"score_gpt":0.46505138673738083,"score_spread":0.08853977765046178,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4280603043","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00009440356,0.9913801,0.000026179481,0.0056280675,0.00032167064,0.00043669518,0.0000064013193,0.000025431707,0.0020810468],"genre_scores_gemma":[0.000055738587,0.99709886,0.000077607954,0.0011107646,0.0011092529,0.00008068155,0.00034940586,0.000042382035,0.00007529525],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983609,0.00031522545,0.0004994376,0.00045070425,0.0001134281,0.00026033467],"domain_scores_gemma":[0.9987526,0.00062440534,0.00023813281,0.0002292628,0.000016986243,0.00013861225],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008623343,0.00032958304,0.0018466115,0.00027930236,0.00007964307,0.000006640612,0.000107209824,0.00018902695,0.00008489968],"category_scores_gemma":[0.00024384294,0.0002240978,0.00009211107,0.00014914479,0.00046094717,0.000030541334,0.00009565754,0.00085247605,7.920115e-7],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009140031,0.00003374704,0.000041125324,0.003282051,0.0001161508,0.000033213226,0.00034499646,1.0428446e-7,0.000002458144,0.006807815,0.0004637912,0.98886544],"study_design_scores_gemma":[0.0011847733,0.00040024484,0.00002489567,0.0017341968,0.00026550575,0.00030570937,0.00021408834,0.00011847774,1.4811108e-7,0.0017351711,0.99382323,0.00019356165],"about_ca_topic_score_codex":0.0000663066,"about_ca_topic_score_gemma":8.06277e-7,"teacher_disagreement_score":0.99335945,"about_ca_system_score_codex":0.00006224413,"about_ca_system_score_gemma":0.00014818249,"threshold_uncertainty_score":0.9138443},"labels":[],"label_agreement":null},{"id":"W4280617333","doi":"10.1016/j.csbj.2022.05.031","title":"A novel integrative computational framework for breast cancer radiogenomic biomarker discovery","year":2022,"lang":"en","type":"article","venue":"Computational and Structural Biotechnology Journal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada; CancerCare Manitoba Foundation; Manitoba Medical Service Foundation","keywords":"Radiogenomics; Interpretability; Medicine; Personalized medicine; Biomarker; Biomarker discovery; Precision medicine; Computer science; Radiomics; Computational biology; Bioinformatics; Artificial intelligence; Pathology; Proteomics; Biology","score_opus":0.011846033591099373,"score_gpt":0.3016078635133302,"score_spread":0.2897618299222308,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4280617333","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45879078,0.000635079,0.4967051,0.042936444,0.00042692316,0.00017033427,0.00029572737,0.000033818673,0.00000577381],"genre_scores_gemma":[0.86718524,0.00003825236,0.13089168,0.0015353274,0.0001869473,0.000020468515,0.00008142161,0.000015793024,0.000044897766],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989642,0.000033785152,0.00028751002,0.00025124403,0.00024107787,0.00022219948],"domain_scores_gemma":[0.9993057,0.00023612693,0.00018147044,0.000058928912,0.00011099209,0.000106749954],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018655829,0.00015835362,0.00027041763,0.0002486018,0.0007804086,0.00006611624,0.0001328136,0.00009649442,0.00014855115],"category_scores_gemma":[0.00009400085,0.0001203134,0.000115816845,0.00019145588,0.00031412812,0.000094055744,0.00010794066,0.0009917929,4.1397337e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002122457,0.00018189997,0.021519667,0.00010599724,0.0015657813,0.00013693144,0.0009306888,0.2033837,0.012787841,0.27084795,0.0035312155,0.48288587],"study_design_scores_gemma":[0.002685143,0.00025423596,0.16174306,0.00007633607,0.000100571095,0.02825706,0.00042797247,0.55786365,0.000030088077,0.24720342,0.0011236649,0.0002348125],"about_ca_topic_score_codex":0.000010379401,"about_ca_topic_score_gemma":3.8736215e-7,"teacher_disagreement_score":0.48265105,"about_ca_system_score_codex":0.00018212378,"about_ca_system_score_gemma":0.0002316974,"threshold_uncertainty_score":0.6002351},"labels":[],"label_agreement":null},{"id":"W4281381325","doi":"10.5281/zenodo.4833117","title":"ML Reproducibility Challenge 2020","year":2021,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Instituto de Ciencias del Mar y Limnología, Universidad Nacional Autónoma de México; Universiteit van Amsterdam; Institute for Catastrophic Loss Reduction","keywords":"Reproducibility; Computer science; Chromatography; Chemistry","score_opus":0.03422465548572512,"score_gpt":0.28929268899937954,"score_spread":0.2550680335136544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281381325","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19680826,0.00157677,0.0067656944,0.07360593,0.00050706946,0.00078257563,0.00007219586,0.0021639282,0.7177176],"genre_scores_gemma":[0.989001,0.0005388992,0.0016230536,0.0011962366,0.00065425376,3.0398066e-8,0.0013993761,0.0012211883,0.004365962],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99807626,0.00026572074,0.00023105257,0.00078717637,0.00035310592,0.00028668737],"domain_scores_gemma":[0.99803656,0.000022730723,0.000057522204,0.0010774335,0.00054644764,0.00025927887],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0013971713,0.00010432847,0.00018726375,0.00006884655,0.0008909665,0.00022513414,0.00029388024,0.000052958294,0.016118567],"category_scores_gemma":[0.005853714,0.00010423133,0.00007090982,0.00039704266,0.00013862301,0.00008904754,0.00064929755,0.0005005102,0.0028670675],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012873944,0.0006766295,0.000102172766,0.00031798007,0.00012732834,0.00058821496,0.0015141552,0.000030120858,0.021767465,0.0040598144,0.36369944,0.60698795],"study_design_scores_gemma":[0.00067401543,0.00015401341,0.0027257418,0.00005065468,0.000026380007,0.00072775583,0.00018150425,0.0009320988,0.00077994494,0.0002616793,0.9933777,0.000108535925],"about_ca_topic_score_codex":0.0000071355344,"about_ca_topic_score_gemma":8.6631225e-8,"teacher_disagreement_score":0.79219276,"about_ca_system_score_codex":0.00010016673,"about_ca_system_score_gemma":0.000009979045,"threshold_uncertainty_score":0.9979093},"labels":[],"label_agreement":null},{"id":"W4281568834","doi":"10.32902/2663-0338-2022-1-16-22","title":"Determination of dynamics and stage of development of COVID-19 pneumonia based on digital software processing of images of computed tomography of the chest","year":2022,"lang":"en","type":"article","venue":"Infusion & Chemotherapy","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"DICOM; Computer science; Software; Image processing; Image registration; Hounsfield scale; Medicine; Artificial intelligence; Radiology; Computed tomography; Image (mathematics)","score_opus":0.008669250503462636,"score_gpt":0.2721845373962696,"score_spread":0.26351528689280695,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281568834","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9735094,0.000066464396,0.025626268,0.00042348503,0.000023896298,0.0002366767,0.000056813416,0.0000087465405,0.000048263733],"genre_scores_gemma":[0.984887,0.000011766433,0.014870515,0.00016177387,0.0000037757063,0.000003575745,0.000025708836,0.0000145079,0.000021378472],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987501,0.00003992149,0.0005382755,0.00012576388,0.00046812408,0.00007780302],"domain_scores_gemma":[0.9986808,0.00016527019,0.0007808122,0.00017417723,0.00015447395,0.000044523687],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035484898,0.00009805595,0.00036406098,0.00020782207,0.00004723189,0.0000027771587,0.00013480564,0.00003505326,0.000027311207],"category_scores_gemma":[0.00019744317,0.000075289216,0.000082654864,0.00035466926,0.00027239494,0.00003069907,0.00006508902,0.00013559416,7.124543e-9],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004930926,0.00078011915,0.24128994,0.003655873,0.000046413494,0.0000017041738,0.0036339492,0.001179241,0.3810867,0.00001900809,0.000013406442,0.36780053],"study_design_scores_gemma":[0.005997894,0.0010567008,0.37409022,0.0012924331,0.00005820805,0.000009218263,0.0010470233,0.23212956,0.3834624,0.000100050405,0.00055531313,0.00020096175],"about_ca_topic_score_codex":0.00003119738,"about_ca_topic_score_gemma":0.0000016310594,"teacher_disagreement_score":0.36759958,"about_ca_system_score_codex":0.00004226595,"about_ca_system_score_gemma":0.0003238699,"threshold_uncertainty_score":0.30702052},"labels":[],"label_agreement":null},{"id":"W4281683906","doi":"10.1200/jco.2022.40.16_suppl.e14009","title":"Treatment patterns and outcomes of patients with high-grade glioma during the COVID-19 pandemic.","year":2022,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; University of Ottawa; BC Cancer Agency","funders":"","keywords":"Medicine; Cohort; Internal medicine; Survival analysis; Coronavirus disease 2019 (COVID-19); Proportional hazards model; Pandemic; Glioma; Oncology; Radiation therapy; Radiosurgery; Retrospective cohort study; Disease","score_opus":0.06418059529165542,"score_gpt":0.43881177957461664,"score_spread":0.3746311842829612,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281683906","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97885495,0.00008474245,0.000101427206,0.02036057,0.00039285756,0.00015541846,0.0000095739915,0.0000058543264,0.00003457888],"genre_scores_gemma":[0.9958635,0.00017045581,0.00052081794,0.0031448868,0.00018698665,0.0000050440544,0.0000031953064,0.000011526112,0.00009358193],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9978036,0.0004642554,0.001067873,0.00012572942,0.00039493846,0.0001435651],"domain_scores_gemma":[0.9961256,0.0021966419,0.0011413827,0.00013886463,0.00007300487,0.00032451734],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014554871,0.000097942095,0.0009274982,0.0000877255,0.000114777526,0.000004442393,0.00012726437,0.000063836254,0.00012219339],"category_scores_gemma":[0.0019003245,0.000046841746,0.00018112524,0.00007600697,0.0002068179,0.00002896131,0.00008288429,0.000787358,2.8552503e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014740092,0.0010558766,0.9807825,0.000022383634,0.00039165284,0.00039440437,0.00019921579,0.00010905164,0.000018966512,0.000028566146,0.0001326953,0.01539065],"study_design_scores_gemma":[0.015469508,0.008721624,0.9511762,0.000008824142,0.0003007054,0.00068775826,0.00015731878,0.00006304019,0.0000032778903,0.00006705849,0.023298165,0.000046492358],"about_ca_topic_score_codex":0.00015056467,"about_ca_topic_score_gemma":0.000016815005,"teacher_disagreement_score":0.0296063,"about_ca_system_score_codex":0.00023017082,"about_ca_system_score_gemma":0.0004992788,"threshold_uncertainty_score":0.34207225},"labels":[],"label_agreement":null},{"id":"W4281703599","doi":"10.1038/s41416-022-01859-7","title":"Histopathological growth patterns of liver metastasis: updated consensus guidelines for pattern scoring, perspectives and recent mechanistic insights","year":2022,"lang":"en","type":"review","venue":"British Journal of Cancer","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":89,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre; McGill University","funders":"National Cancer Institute; European Regional Development Fund; Engineering and Physical Sciences Research Council; Agència de Gestió d'Ajuts Universitaris i de Recerca; Canadian Institutes of Health Research; Fondation contre le Cancer; Stichting Tegen Kanker; Generalitat de Catalunya; Umeå Universitet; Koning Boudewijnstichting; Knut och Alice Wallenbergs Stiftelse; Cancerfonden; Vetenskapsrådet; Government of Canada; Cancer Research Foundation in Northern Sweden; Research Councils UK; McGill University","keywords":"Histopathology; Metastasis; Liver cancer; Biology; Cancer; Colorectal cancer; Pathology; Medicine; Bioinformatics; Internal medicine","score_opus":0.10417403090189503,"score_gpt":0.39629367409761557,"score_spread":0.29211964319572054,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281703599","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00074728683,0.995565,0.0020447206,0.00042539398,0.0005338106,0.00046332975,0.00018398916,0.000011064583,0.000025383963],"genre_scores_gemma":[0.00048435695,0.9965496,0.0018418165,0.00032151403,0.00057293935,0.00004497828,0.000037864836,0.000055744706,0.0000911727],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975583,0.00024794065,0.0011953312,0.00032342318,0.00045819054,0.00021680284],"domain_scores_gemma":[0.9972566,0.00021721197,0.0012663465,0.00011812901,0.0009453553,0.00019638405],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00078022596,0.0002614808,0.0019352465,0.00022560368,0.00009946601,0.000035584588,0.00018280848,0.000116077965,0.00061604247],"category_scores_gemma":[0.0019641668,0.00021909285,0.00045722033,0.00012793284,0.00011404003,0.0000328519,0.000087739936,0.0009182836,2.2464968e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044103806,0.00009428162,0.000045195262,0.005298313,0.00046255958,0.0019503922,0.00009493206,0.0000014356689,0.000004333735,0.000046629826,0.002736104,0.9892217],"study_design_scores_gemma":[0.0011493146,0.00039884556,0.00013530445,0.017361354,0.0034285968,0.013344104,0.00018811265,0.000074973526,0.0000026239954,0.00006854329,0.963631,0.00021723098],"about_ca_topic_score_codex":0.00032930326,"about_ca_topic_score_gemma":0.00003278151,"teacher_disagreement_score":0.9890045,"about_ca_system_score_codex":0.0002682353,"about_ca_system_score_gemma":0.0004698083,"threshold_uncertainty_score":0.8934347},"labels":[],"label_agreement":null},{"id":"W4281711757","doi":"10.1093/neuonc/noac079.587","title":"PATH-03. Clinically Tractable Outcome Prediction of Group 3/4 Medulloblastoma Based on TPD52 Immunohistochemistry: a Multicohort Study","year":2022,"lang":"en","type":"article","venue":"Neuro-Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"SickKids Foundation; Hospital for Sick Children; Canada's Michael Smith Genome Sciences Centre; University of British Columbia","funders":"","keywords":"Medulloblastoma; Oncology; Internal medicine; Immunohistochemistry; Biomarker; Multivariate analysis; Receiver operating characteristic; Biology; Medicine; Bioinformatics; Pathology; Genetics","score_opus":0.020240693518660563,"score_gpt":0.34173489698509263,"score_spread":0.3214942034664321,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281711757","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9898011,0.000035680587,0.00035527573,0.0022671693,0.0012658406,0.0010409344,0.000032984306,0.00014110979,0.0050598877],"genre_scores_gemma":[0.99440956,0.000008711634,0.0011167201,0.0037850337,0.00019235225,0.00024636555,0.000067688416,0.000054895136,0.00011867237],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967205,0.00053982844,0.0010738405,0.000572551,0.0007250683,0.00036821084],"domain_scores_gemma":[0.9976421,0.0010374723,0.00041690154,0.0005902617,0.00008620868,0.00022702664],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017249939,0.00022771583,0.0007871,0.0001714664,0.00021441361,0.000008423413,0.00028533672,0.00013085995,0.0005309752],"category_scores_gemma":[0.0021799628,0.00021623152,0.00022328495,0.00028061832,0.00016803069,0.000033225748,0.00015472606,0.0017758883,0.0000113004935],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003712958,0.010397788,0.39365977,0.00013969713,0.0001401496,0.001087071,0.0006996665,0.0015325297,0.56565624,0.00001916405,0.003195273,0.019759687],"study_design_scores_gemma":[0.049085226,0.09470899,0.26885825,0.00015594972,0.0015540054,0.0011329973,0.0033335618,0.3802975,0.0020079287,0.00004426601,0.19801418,0.00080713583],"about_ca_topic_score_codex":0.00007675265,"about_ca_topic_score_gemma":0.0000010810919,"teacher_disagreement_score":0.5636483,"about_ca_system_score_codex":0.0004284666,"about_ca_system_score_gemma":0.00034292488,"threshold_uncertainty_score":0.88176656},"labels":[],"label_agreement":null},{"id":"W4281742561","doi":"10.1200/jco.2022.40.16_suppl.108","title":"Prostate cancer risk in African American men evaluated via digital histopathology multi-modal deep learning models developed on NRG Oncology phase III clinical trials.","year":2022,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; University of Saskatchewan; Horizon Health Network; Saint John Regional Hospital","funders":"National Institutes of Health","keywords":"Medicine; Prostate cancer; Internal medicine; Proportional hazards model; Oncology; Clinical endpoint; Cumulative incidence; Clinical trial; Hazard ratio; Cancer; Confidence interval; Cohort","score_opus":0.21280575996906073,"score_gpt":0.5514069190639074,"score_spread":0.33860115909484667,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281742561","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9683992,0.0006026374,0.008843991,0.015953079,0.0028273624,0.0008757415,0.000020632948,0.000049884857,0.002427439],"genre_scores_gemma":[0.98598015,0.0023087081,0.0061176107,0.0036897396,0.0011997247,0.00008691912,0.000029474428,0.000075837044,0.00051183027],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9740212,0.015225789,0.008290223,0.00074783847,0.00094561826,0.00076933135],"domain_scores_gemma":[0.9759765,0.013115116,0.009005027,0.0003247417,0.00053260144,0.0010460005],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.055081975,0.00038546836,0.005615438,0.00061235786,0.00025344326,0.000024337658,0.0005254305,0.000445443,0.00031016304],"category_scores_gemma":[0.050629776,0.0003002695,0.0010577586,0.0006378544,0.0010946862,0.00018031619,0.00032848175,0.010859128,0.000011910181],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.036726955,0.0069267326,0.071084455,0.000010449924,0.00042227138,0.0034893134,0.0012955425,0.02337324,0.000086555054,0.000019661516,0.0009970356,0.8555678],"study_design_scores_gemma":[0.1027557,0.06325522,0.068284854,0.0000783211,0.0010972383,0.0012005076,0.0020222806,0.5974007,0.0000031819488,0.0005885336,0.16285126,0.00046219846],"about_ca_topic_score_codex":0.00037961555,"about_ca_topic_score_gemma":0.00008940297,"teacher_disagreement_score":0.8551056,"about_ca_system_score_codex":0.0016474021,"about_ca_system_score_gemma":0.00503604,"threshold_uncertainty_score":0.9999449},"labels":[],"label_agreement":null},{"id":"W4281821394","doi":"10.1016/j.jvir.2022.03.206","title":"Abstract No. 125 Outpatient approach for the treatment of lung lesions using cryoablation: 18 months follow-up","year":2022,"lang":"en","type":"article","venue":"Journal of Vascular and Interventional Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Association of Thoracic Surgeons","funders":"","keywords":"Medicine; Cryoablation; Radiology; General surgery; Internal medicine","score_opus":0.03556125760982425,"score_gpt":0.32976902322452073,"score_spread":0.29420776561469647,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281821394","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87419033,0.020678801,0.10235218,0.00081319356,0.0011943736,0.0005103048,0.000020988991,0.000004817144,0.00023499959],"genre_scores_gemma":[0.99327815,0.0005732916,0.005459886,0.000088239554,0.00036457705,0.000019861118,0.000030439769,0.00001203502,0.00017354828],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989603,0.0000970379,0.0004932311,0.000105794425,0.00022981557,0.00011378278],"domain_scores_gemma":[0.9991392,0.00020439047,0.0003387726,0.00009736472,0.0001524884,0.0000677807],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00073259295,0.00008719853,0.000338244,0.00011271298,0.00019220717,0.0000074884565,0.0000799696,0.000035719077,0.00023814729],"category_scores_gemma":[0.0001938747,0.000055196204,0.00069187203,0.00005231963,0.00008314399,0.00003812467,0.000023156737,0.00021408626,1.3431217e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.015007402,0.022122724,0.26226234,0.002929883,0.035812497,0.00031652287,0.008924181,0.29163468,0.02338247,0.00966182,0.062066313,0.26587918],"study_design_scores_gemma":[0.020156883,0.013978704,0.17981918,0.00030569968,0.0025936973,0.003247813,0.001277358,0.6578642,0.00010891016,0.0006241886,0.11973512,0.00028823633],"about_ca_topic_score_codex":0.00003315285,"about_ca_topic_score_gemma":3.910301e-7,"teacher_disagreement_score":0.36622953,"about_ca_system_score_codex":0.00012581694,"about_ca_system_score_gemma":0.00007630179,"threshold_uncertainty_score":0.2607546},"labels":[],"label_agreement":null},{"id":"W4281825562","doi":"10.1200/jco.2022.40.16_suppl.9128","title":"Molecular testing and patterns of treatment in patients with NSCLC: An IASLC analysis of ASCO CancerLinQ Discovery Data.","year":2022,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"International Association for the Study of Lung Cancer","keywords":"Medicine; Internal medicine; Lung cancer; Oncology; Adenocarcinoma; Stage (stratigraphy); Univariate analysis; Logistic regression; Cancer; Multivariate analysis","score_opus":0.07360579011254115,"score_gpt":0.4469978150138076,"score_spread":0.37339202490126644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281825562","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9984915,0.00011882683,0.0005336652,0.00053996197,0.0001192335,0.000102156664,0.000029050025,0.0000014455702,0.000064135995],"genre_scores_gemma":[0.9957185,0.000064580025,0.0037218893,0.00038390877,0.00006558944,0.0000016833832,0.000025213158,0.000009213668,0.000009417572],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99756014,0.00039736123,0.001344741,0.00018232751,0.0003966925,0.00011871177],"domain_scores_gemma":[0.99684906,0.0011630598,0.0014052809,0.0002554478,0.0001734395,0.00015373327],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002220013,0.00008333062,0.0012735691,0.00021268295,0.000020730611,0.000003801416,0.00016278356,0.000052309857,0.000023677794],"category_scores_gemma":[0.00229738,0.000055372628,0.00012240124,0.0003084651,0.00010691467,0.00009964937,0.00010896966,0.0005513829,2.3485352e-8],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001212809,0.0015222678,0.8891505,0.000015599206,0.0009149951,0.00016530544,0.00013099813,0.00430178,0.000047330723,0.0000074491186,0.0000067730853,0.102524176],"study_design_scores_gemma":[0.006945337,0.017592851,0.95664346,0.00006197731,0.0019323791,0.000019486728,0.00015429963,0.016230894,0.0000049285663,0.000014757223,0.00035032793,0.000049322774],"about_ca_topic_score_codex":0.0009636554,"about_ca_topic_score_gemma":0.00016788111,"teacher_disagreement_score":0.10247485,"about_ca_system_score_codex":0.00020989058,"about_ca_system_score_gemma":0.0012342283,"threshold_uncertainty_score":0.27503446},"labels":[],"label_agreement":null},{"id":"W4281861761","doi":"10.1200/jco.2022.40.16_suppl.e20575","title":"Automated imaging-based prognostication (IPRO) for stage I non-small cell lung cancer using deep learning applied to computed tomography.","year":2022,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto","funders":"","keywords":"Medicine; Stage (stratigraphy); Lung cancer; Radiation therapy; Radiology; Cancer staging; Computed tomography; Cancer; Adjuvant therapy; T-stage; Internal medicine; Oncology","score_opus":0.04091642380794118,"score_gpt":0.4299737815159568,"score_spread":0.3890573577080156,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281861761","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.76309264,0.00046919566,0.22714977,0.006084993,0.0015347527,0.0011719147,0.000005984677,0.0001073094,0.00038346043],"genre_scores_gemma":[0.8964147,0.000011186237,0.09700226,0.0056431144,0.0007342424,0.00006879437,0.000018835053,0.00004783941,0.000059048107],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99674994,0.00037025518,0.0017550961,0.0003125851,0.00042785163,0.00038427938],"domain_scores_gemma":[0.99523664,0.001975039,0.0016828164,0.00015573479,0.0004570411,0.000492761],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0043961415,0.00017598222,0.0011004717,0.00036644124,0.00025060604,0.000024620358,0.0002622085,0.00012111476,0.00011879124],"category_scores_gemma":[0.0018415212,0.00015476998,0.0004040975,0.0004243235,0.00010284631,0.000040709823,0.00010457315,0.0018154146,0.0000011164581],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0037749847,0.0020351035,0.4483399,0.00038233865,0.0003555452,0.0003096277,0.0004566177,0.3864461,0.008736168,0.000045153716,0.0037435263,0.14537494],"study_design_scores_gemma":[0.0076616644,0.002447071,0.05164242,0.00009332318,0.0005237401,0.000053372278,0.000184406,0.9066194,0.00013398136,0.000012516698,0.030472802,0.0001552866],"about_ca_topic_score_codex":0.000038185473,"about_ca_topic_score_gemma":0.000004086872,"teacher_disagreement_score":0.5201733,"about_ca_system_score_codex":0.0003211111,"about_ca_system_score_gemma":0.0016545296,"threshold_uncertainty_score":0.78871745},"labels":[],"label_agreement":null},{"id":"W4281925782","doi":"10.1002/cyto.a.24404","title":"Volume 101A, Number 6, June 2022 Cover Image","year":2022,"lang":"en","type":"article","venue":"Cytometry Part A","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Cover (algebra); Cytometry; Computer science; Flow cytometry; Cartography; Biology; Geography; Molecular biology; Engineering","score_opus":0.009515233084763047,"score_gpt":0.29281959065448726,"score_spread":0.2833043575697242,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281925782","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87254846,0.00066242804,0.0033798655,0.014043328,0.003305031,0.0004646934,0.000054817832,0.0003284418,0.10521292],"genre_scores_gemma":[0.8047686,0.00004532661,0.0019300124,0.0047697998,0.0007636233,0.00008143361,0.00015277526,0.00007051201,0.18741788],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982447,0.00009625525,0.0002692237,0.00034915496,0.0006461118,0.0003945737],"domain_scores_gemma":[0.99913555,0.00007180294,0.00008449544,0.00040115326,0.00004765551,0.00025933387],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0006763587,0.00015536913,0.00033348307,0.00018196518,0.0002919362,0.000035726043,0.00018232294,0.00004202577,0.048097156],"category_scores_gemma":[0.00033261743,0.00015255145,0.00015388854,0.0008527424,0.00011702688,0.0000791152,0.00026543628,0.000948016,0.0021543729],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000087164866,0.0002343813,0.0931475,0.000051695406,0.000086416774,0.00050468015,0.00013014802,0.000036573834,0.005321304,0.00012963482,0.8962027,0.0040678056],"study_design_scores_gemma":[0.0013197439,0.000100301775,0.012918457,0.000017317678,0.0000758966,0.0005803403,0.000105154046,0.0056911437,0.00016320619,0.00009218562,0.97875124,0.00018502583],"about_ca_topic_score_codex":0.000020185644,"about_ca_topic_score_gemma":1.974963e-7,"teacher_disagreement_score":0.08254854,"about_ca_system_score_codex":0.00015833485,"about_ca_system_score_gemma":0.00009943806,"threshold_uncertainty_score":0.99862254},"labels":[],"label_agreement":null},{"id":"W4282913119","doi":"10.1038/s41598-022-13379-8","title":"Radiomics-based machine learning models to distinguish between metastatic and healthy bone using lesion-center-based geometric regions of interest","year":2022,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre; McGill University","funders":"McGill University Health Centre; Faculty of Medicine and Health, University of Sydney; McGill University","keywords":"Radiomics; Segmentation; Artificial intelligence; Computer science; Region of interest; Medicine; Feature selection; Pattern recognition (psychology); Machine learning; Radiology","score_opus":0.13249413706351953,"score_gpt":0.34488742192136035,"score_spread":0.21239328485784081,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4282913119","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91953844,0.00050804944,0.07639068,0.0017116605,0.0011624637,0.0005271021,0.000020656209,0.000069419584,0.00007152513],"genre_scores_gemma":[0.98327935,0.0000029873438,0.015754435,0.00034524946,0.000057567635,0.000018976569,0.00027998062,0.000045625296,0.00021584748],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99690366,0.0002304856,0.0009191866,0.000796186,0.0007161142,0.00043437118],"domain_scores_gemma":[0.99786013,0.00025676063,0.0006263309,0.000603736,0.00016495869,0.0004880783],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036817167,0.00020520698,0.0006270891,0.0013978851,0.0007836603,0.00009523423,0.00013309502,0.000030506637,0.000062483196],"category_scores_gemma":[0.0015420415,0.00019634658,0.00015028629,0.0017986157,0.00027432005,0.000066416585,0.00021551255,0.0006561433,6.939321e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006392727,0.0018539062,0.5788057,0.0017458578,0.00028840738,0.0045740507,0.001645698,0.336542,0.02884725,0.00025504883,0.0062101325,0.03859267],"study_design_scores_gemma":[0.002705275,0.0009033148,0.0023001053,0.0005144411,0.00037082838,0.0014155527,0.0003384198,0.9680742,0.0010151925,0.0013321289,0.020562325,0.0004682148],"about_ca_topic_score_codex":0.00040174008,"about_ca_topic_score_gemma":0.000008037575,"teacher_disagreement_score":0.6315322,"about_ca_system_score_codex":0.00022321881,"about_ca_system_score_gemma":0.00044402157,"threshold_uncertainty_score":0.80067813},"labels":[],"label_agreement":null},{"id":"W4282916804","doi":"10.1158/1538-7445.am2022-463","title":"Abstract 463: Highly accurate machine learning assessment of immune-related pathologic response criteria (irPRC) scoring in patients with non-small cell lung carcinoma (NSCLC) treated with neoadjuvant anti-PD-1-based therapies","year":2022,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Medicine; Neoadjuvant therapy; Oncology; Digital pathology; Internal medicine; Radiology; Pathology; Cancer","score_opus":0.02415591630071456,"score_gpt":0.3482531996067472,"score_spread":0.32409728330603266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4282916804","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9963426,0.001092102,0.000080931386,0.0008322744,0.00008244903,0.0011965482,0.000035664663,0.000059060236,0.00027839217],"genre_scores_gemma":[0.9985929,0.00007539206,0.00049911457,0.000073547344,0.000024333138,0.00027969305,0.00014193919,0.000097744756,0.00021534887],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9956564,0.0011039586,0.00063605024,0.0006597454,0.0011517826,0.00079207623],"domain_scores_gemma":[0.9981627,0.00045540702,0.0003163439,0.0005112878,0.00035659125,0.0001977038],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0036380722,0.00031560936,0.000683824,0.0007895097,0.00043966144,0.00006396818,0.00036442734,0.00008374397,0.00040457485],"category_scores_gemma":[0.00016958668,0.00023100387,0.0000928779,0.0011328211,0.00029320226,0.00010158173,0.00019086267,0.0027078066,0.0000015207639],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00678719,0.00052254286,0.8678591,0.00030751503,0.00008222001,0.0009174556,0.0009839113,0.01343039,0.107292056,0.0000023490577,0.000024904684,0.0017903463],"study_design_scores_gemma":[0.011306632,0.002764532,0.94596064,0.0007107806,0.000054209766,0.000011321474,0.00058319775,0.034564238,0.0036963604,0.0000021015444,0.00008696722,0.00025902322],"about_ca_topic_score_codex":0.0025744827,"about_ca_topic_score_gemma":0.000020491432,"teacher_disagreement_score":0.1035957,"about_ca_system_score_codex":0.00069351366,"about_ca_system_score_gemma":0.0010097366,"threshold_uncertainty_score":0.99959296},"labels":[],"label_agreement":null},{"id":"W4282922560","doi":"10.2967/jnumed.121.263239","title":"Nuclear Medicine and Artificial Intelligence: Best Practices for Evaluation (the RELAINCE Guidelines)","year":2022,"lang":"en","type":"article","venue":"Journal of Nuclear Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":108,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Center for Advancing Translational Sciences","keywords":"Task (project management); Artificial intelligence; Best practice; Computer science; Class (philosophy); Machine learning; Data science; Engineering; Systems engineering; Political science","score_opus":0.18378330941124446,"score_gpt":0.46283040922463414,"score_spread":0.2790470998133897,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4282922560","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13277364,0.0056112246,0.0013553107,0.85506487,0.0019830714,0.0008294295,0.0000023920259,0.000029192679,0.00235088],"genre_scores_gemma":[0.9352184,0.0025474539,0.008849038,0.043958277,0.008779978,0.000020180698,0.000016928068,0.00013796036,0.0004717672],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9966168,0.00027586194,0.0011467257,0.00022817007,0.0014981031,0.00023438688],"domain_scores_gemma":[0.9961838,0.0007929336,0.0016202575,0.00025784617,0.00090094947,0.0002441887],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.009818162,0.00017124617,0.00054799695,0.00027968464,0.00055421743,0.000021705077,0.00029098522,0.000056096447,0.0018032944],"category_scores_gemma":[0.01975386,0.0001023489,0.00010377784,0.00033174467,0.00048640225,0.00013721603,0.00010381682,0.0011283521,0.0000059131385],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0024033585,0.0003200708,0.00020779495,0.00019028375,0.00037414432,0.00017890763,0.008990475,0.0008901634,0.01301095,0.010203509,0.3444118,0.6188186],"study_design_scores_gemma":[0.0022375355,0.0046857605,0.00020355842,0.0004915529,0.0012581204,0.0030087435,0.020829555,0.1359478,0.000007355616,0.004285611,0.8269231,0.0001213555],"about_ca_topic_score_codex":0.00010358477,"about_ca_topic_score_gemma":0.0000020172913,"teacher_disagreement_score":0.81110656,"about_ca_system_score_codex":0.00015868343,"about_ca_system_score_gemma":0.0001598403,"threshold_uncertainty_score":0.9991092},"labels":[],"label_agreement":null},{"id":"W4282942659","doi":"10.1038/s41746-022-00613-w","title":"Prostate cancer therapy personalization via multi-modal deep learning on randomized phase III clinical trials","year":2022,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":197,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre; Nova Scotia Cancer Centre; Centre Hospitalier de l’Université de Montréal; Horizon Health Network; Occupational Cancer Research Centre; Saint John Regional Hospital","funders":"National Cancer Institute; NRG Oncology","keywords":"Randomized controlled trial; Modal; Prostate cancer; Personalization; Clinical trial; Medicine; Cancer; Medical physics; Computer science; Artificial intelligence; Oncology; Internal medicine; World Wide Web","score_opus":0.07307830830311975,"score_gpt":0.45086439510705606,"score_spread":0.3777860868039363,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4282942659","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87714016,0.009041826,0.058115672,0.037079718,0.0039775595,0.005920546,0.00004172785,0.00058460067,0.008098181],"genre_scores_gemma":[0.986001,0.0016161911,0.00018121226,0.0054274383,0.001407445,0.00036261752,0.00045564625,0.00007827608,0.0044701523],"study_design_codex":"design_other","study_design_gemma":"randomized_trial","domain_scores_codex":[0.9951386,0.0013555256,0.001521282,0.0005624607,0.0010201674,0.00040197367],"domain_scores_gemma":[0.99621147,0.002337102,0.00065946823,0.00024650324,0.00013649336,0.00040895335],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008494128,0.0003178568,0.001978607,0.00024160292,0.00033349564,0.000046819267,0.00016270594,0.00008591483,0.0018308826],"category_scores_gemma":[0.011366142,0.00021214424,0.00043192328,0.00034717994,0.0004892675,0.00012755068,0.000069399954,0.0014598325,0.000013981703],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.12756567,0.0013572031,0.0044531673,0.00005779624,0.0006106232,0.00019017591,0.003243143,0.00072962436,0.0014798698,0.0001783422,0.0022468888,0.8578875],"study_design_scores_gemma":[0.65937835,0.0034880848,0.0004979505,0.00027964954,0.0003427302,0.00010438996,0.0008818447,0.26376012,0.00003540176,0.00015497812,0.07076724,0.0003092963],"about_ca_topic_score_codex":0.00009935773,"about_ca_topic_score_gemma":8.6440366e-7,"teacher_disagreement_score":0.8575782,"about_ca_system_score_codex":0.000144651,"about_ca_system_score_gemma":0.00014436354,"threshold_uncertainty_score":0.99908155},"labels":[],"label_agreement":null},{"id":"W4282967195","doi":"10.1158/1538-7445.am2022-5048","title":"Abstract 5048: Imaging based EGFR mutation subtype classification using EfficientNet","year":2022,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Mutation; Epidermal growth factor receptor; Lymph node; Medicine; Cancer research; Computer science; Biology; Cancer; Pathology; Internal medicine; Genetics; Gene","score_opus":0.10442309308096148,"score_gpt":0.456435762780487,"score_spread":0.3520126696995255,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4282967195","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98680425,0.00082135515,0.001667439,0.007939031,0.0003301856,0.00038538565,0.000009982519,0.00006234072,0.0019800516],"genre_scores_gemma":[0.99805665,0.000015637248,0.000593053,0.00059840165,0.00023827002,0.000097973985,0.000079317746,0.00003639361,0.0002842785],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99779904,0.0001925916,0.00020809112,0.00033392126,0.0010534454,0.00041289374],"domain_scores_gemma":[0.9991094,0.00017387352,0.00007087453,0.00026359176,0.00021846904,0.00016377447],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0020375485,0.00008790243,0.00014201732,0.00037346967,0.0005923537,0.000057145557,0.00016375295,0.00002453264,0.001590453],"category_scores_gemma":[0.00035267603,0.00008762113,0.000053703512,0.0006836513,0.00015688194,0.00005946109,0.00007865782,0.0011228442,0.000019561929],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00057327887,0.0004126662,0.06460076,0.00036299828,0.000052207455,0.0004395835,0.00081384054,0.06011777,0.7372416,0.0005277195,0.011687006,0.12317056],"study_design_scores_gemma":[0.0016585452,0.000090263675,0.07950262,0.00012163641,0.000031607437,0.00006112651,0.0008740419,0.885529,0.0028553964,0.000097215314,0.029016156,0.00016243638],"about_ca_topic_score_codex":0.0008011324,"about_ca_topic_score_gemma":0.0000033651709,"teacher_disagreement_score":0.8254112,"about_ca_system_score_codex":0.00090933364,"about_ca_system_score_gemma":0.00075187243,"threshold_uncertainty_score":0.99932224},"labels":[],"label_agreement":null},{"id":"W4282969792","doi":"10.1158/1538-7445.am2022-1685","title":"Abstract 1685: Deep learning approaches to deciphering intra-tumoural heterogeneity in glioblastoma","year":2022,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; University of Toronto","funders":"","keywords":"Workflow; Precision medicine; Tumor heterogeneity; Computational biology; Cluster analysis; Glioblastoma; Pharmacogenomics; Tumour heterogeneity; Computer science; Laser capture microdissection; Artificial intelligence; Bioinformatics; Biology; Machine learning; Cancer; Cancer research; Database","score_opus":0.12395924035455103,"score_gpt":0.39536261296594233,"score_spread":0.2714033726113913,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4282969792","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9919351,0.00089739804,0.00022337501,0.0050808997,0.00016255822,0.0004221465,0.000001929433,0.00005654122,0.0012200939],"genre_scores_gemma":[0.9981366,0.00005893151,0.00040725485,0.00032185935,0.0002811757,0.00041496658,0.0000053917975,0.000049997758,0.00032382846],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9972466,0.00027729265,0.00027440433,0.00046723438,0.0009694859,0.0007649556],"domain_scores_gemma":[0.99911106,0.00017929214,0.00003868644,0.00024554427,0.000052663036,0.0003727649],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0024300867,0.00013632668,0.0002804107,0.000427194,0.0004047653,0.000058143833,0.00029863746,0.0000436472,0.00084499817],"category_scores_gemma":[0.0005570632,0.00013540863,0.00007089002,0.00091975526,0.00010977582,0.000064608605,0.00043139298,0.0027709168,0.000028865403],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018593494,0.000418,0.2354283,0.00040222256,0.00011321491,0.0013123865,0.005561157,0.19204319,0.076908104,0.0002631563,0.0015555427,0.4841354],"study_design_scores_gemma":[0.00857546,0.0033569778,0.59006244,0.0009274888,0.000056308134,0.00064641854,0.011861021,0.198717,0.028718876,0.0004788061,0.1551607,0.0014385328],"about_ca_topic_score_codex":0.00073842093,"about_ca_topic_score_gemma":0.00024037182,"teacher_disagreement_score":0.48269683,"about_ca_system_score_codex":0.00082491245,"about_ca_system_score_gemma":0.00020650862,"threshold_uncertainty_score":0.9995297},"labels":[],"label_agreement":null},{"id":"W4282973317","doi":"10.1158/1538-7445.am2022-6299","title":"Abstract 6299: Population kinetics (PopKin) of non-small cell lung cancer (NSCLC) adjuvant therapy","year":2022,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Medicine; Adjuvant; Population; Oncology; Internal medicine; Chemotherapy; Surgery","score_opus":0.04543331961204916,"score_gpt":0.41282728985439077,"score_spread":0.3673939702423416,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4282973317","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9855057,0.007927995,0.00010994315,0.0029557524,0.0003867165,0.0006470694,0.000030188621,0.000025605792,0.0024110414],"genre_scores_gemma":[0.99421173,0.0031029456,0.00024756533,0.00037313116,0.0004156031,0.00028323018,0.000046983634,0.000054653523,0.0012641574],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9976901,0.0001308703,0.00032866152,0.00033200742,0.0010412743,0.00047713335],"domain_scores_gemma":[0.9989816,0.00013826134,0.00011613508,0.00034407133,0.00022582589,0.00019409502],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0010800406,0.000130578,0.00031185924,0.00028465196,0.00021862927,0.000021443428,0.00027001312,0.00005474053,0.0023585067],"category_scores_gemma":[0.000082429346,0.0001157753,0.00009517906,0.00052014756,0.000110598805,0.000037078236,0.00014709831,0.0013144729,0.000003527008],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007327367,0.0005323731,0.2239227,0.0007763995,0.00012735283,0.0000975801,0.0017843646,0.0067393095,0.5526829,0.000055646484,0.015782708,0.19676597],"study_design_scores_gemma":[0.0072001643,0.0010079166,0.84117246,0.00070364744,0.00009208166,0.000021025806,0.000725037,0.035901457,0.045035098,0.00013587392,0.067528486,0.00047673032],"about_ca_topic_score_codex":0.008177436,"about_ca_topic_score_gemma":0.00005115291,"teacher_disagreement_score":0.6172498,"about_ca_system_score_codex":0.00045523787,"about_ca_system_score_gemma":0.00044540246,"threshold_uncertainty_score":0.99855345},"labels":[],"label_agreement":null},{"id":"W4282983424","doi":"10.1158/1538-7445.am2022-455","title":"Abstract 455: Automating integration of histomorphologic and immunohistochemistry data using computer vision tools","year":2022,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Convolutional neural network; Artificial intelligence; Pathology; Glioma; Computer science; Immunohistochemistry; Deep learning; Schwannoma; Scale-invariant feature transform; ATRX; Medicine; Feature extraction; Biology; Cancer research","score_opus":0.1586580104194773,"score_gpt":0.4852931253728527,"score_spread":0.3266351149533754,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4282983424","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9959784,0.0015159724,0.0009723739,0.00079715904,0.00012041582,0.0001785495,0.000028698605,0.000022031772,0.00038639604],"genre_scores_gemma":[0.9939122,0.00007419382,0.0055360016,0.00010342668,0.00012292786,0.000015009882,0.00012577054,0.00001415023,0.00009630043],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987093,0.0000921769,0.00021979063,0.00027378032,0.0005143803,0.00019052783],"domain_scores_gemma":[0.9991751,0.00017964313,0.000083924,0.00038680973,0.000103659215,0.00007091407],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017650679,0.000065890345,0.00017830383,0.00010771706,0.00026590377,0.000029559684,0.0002419464,0.000031650055,0.00042275817],"category_scores_gemma":[0.00033320626,0.000058943675,0.000020888436,0.00019591533,0.00021251934,0.00009145407,0.00060288503,0.0008917623,7.90103e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007439892,0.00004547577,0.00055118394,0.00013295977,0.000015243518,0.0000463074,0.00019651122,0.00028649042,0.8623292,0.000014406105,0.0031675308,0.13314033],"study_design_scores_gemma":[0.002793142,0.00072937086,0.037577674,0.0012124132,0.0000733753,0.00064991176,0.0012057971,0.92393285,0.018104723,0.00017875593,0.013201133,0.00034084372],"about_ca_topic_score_codex":0.00062274473,"about_ca_topic_score_gemma":6.9505387e-7,"teacher_disagreement_score":0.9236464,"about_ca_system_score_codex":0.00035044548,"about_ca_system_score_gemma":0.00025294506,"threshold_uncertainty_score":0.46289054},"labels":[],"label_agreement":null},{"id":"W4283030324","doi":"10.1101/2022.06.15.22276090","title":"Two-Step Machine Learning to Diagnose and Predict Involvement of Lungs in COVID-19 and Pneumonia using CT Radiomics","year":2022,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Random forest; Artificial intelligence; Feature selection; Computer science; Machine learning; Support vector machine; Correlation; Majority rule; Radiomics; Oversampling; Pattern recognition (psychology); Histogram; Pneumonia; Decision tree; Feature (linguistics); Medicine; Mathematics; Image (mathematics)","score_opus":0.023742288672227805,"score_gpt":0.32600683632506033,"score_spread":0.3022645476528325,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283030324","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9886387,0.004868103,0.0014527793,0.0034719706,0.0003562005,0.001012306,0.000032633507,0.00006887384,0.000098442084],"genre_scores_gemma":[0.9876523,0.0028693136,0.0070705917,0.0018911186,0.00014171713,0.00008067148,0.00011191914,0.00008744462,0.00009493177],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99706423,0.0003583945,0.0007597213,0.00083460467,0.0005665989,0.00041644266],"domain_scores_gemma":[0.9980232,0.00042124142,0.00034274056,0.00045340566,0.00004088247,0.000718507],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0023023938,0.00039673998,0.0010064525,0.0006759159,0.00014887628,0.000055299053,0.0002404219,0.000097826465,0.0001060768],"category_scores_gemma":[0.002499207,0.000390872,0.00010582,0.0003185516,0.00020267833,0.000051276347,0.0014874215,0.0021789344,4.6116125e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014051805,0.00012573064,0.96766865,0.0016623455,0.00012067266,0.0006105814,0.002109099,0.017001115,0.0050277393,0.000055124445,0.000067500456,0.0054109013],"study_design_scores_gemma":[0.008109076,0.00067157997,0.14772092,0.0024000371,0.0006166223,0.00063255226,0.0012374669,0.81178683,0.00026723574,0.00035001637,0.025278032,0.0009296134],"about_ca_topic_score_codex":0.005056806,"about_ca_topic_score_gemma":0.0001310051,"teacher_disagreement_score":0.8199478,"about_ca_system_score_codex":0.00041371363,"about_ca_system_score_gemma":0.0003796594,"threshold_uncertainty_score":0.9998543},"labels":[],"label_agreement":null},{"id":"W4283211600","doi":"10.1155/2022/1293548","title":"[Retracted] Dense Convolutional Neural Network for Detection of Cancer from CT Images","year":2022,"lang":"en","type":"article","venue":"BioMed Research International","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":18,"is_retracted":true,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"Saint Joseph University; King Saud University; Saveetha Dental College","keywords":"Convolutional neural network; Cancer; Computer science; Artificial intelligence; Pattern recognition (psychology); Medicine; Radiology; Internal medicine","score_opus":0.045053806115720525,"score_gpt":0.4131156881702692,"score_spread":0.3680618820545487,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283211600","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9788081,0.0010223935,0.0028196992,0.012430257,0.0035015005,0.00043842295,0.00057660544,0.00003599518,0.00036703367],"genre_scores_gemma":[0.994174,0.000058899634,0.0016046062,0.00023620002,0.00199505,0.00023445423,0.0004335821,0.000018562172,0.0012446548],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.997995,0.00013954488,0.0002399512,0.00023304565,0.0011122964,0.0002801134],"domain_scores_gemma":[0.99877524,0.0005062767,0.00008622871,0.00011302796,0.00040417985,0.00011504104],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0011292043,0.00007193224,0.00014476507,0.00027600417,0.00025409018,0.000021613678,0.00020918254,0.000026764648,0.0012335919],"category_scores_gemma":[0.00072311366,0.00006740563,0.000099713114,0.00029369764,0.00021070214,0.000049804876,0.0001470673,0.00071017176,0.0000031919876],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002484678,0.0004907079,0.0864985,0.0000748136,0.0007752615,0.000119755816,0.0001552859,0.0032619548,0.65686256,0.00090111856,0.11563542,0.13273993],"study_design_scores_gemma":[0.0038956744,0.00049804273,0.2393694,0.000080868114,0.00005519198,0.00010922168,0.00018982732,0.35609022,0.012502777,0.0022345567,0.38479778,0.00017642847],"about_ca_topic_score_codex":0.0013615214,"about_ca_topic_score_gemma":0.00001651401,"teacher_disagreement_score":0.6443598,"about_ca_system_score_codex":0.0003126887,"about_ca_system_score_gemma":0.00019274418,"threshold_uncertainty_score":0.9996794},"labels":[],"label_agreement":null},{"id":"W4283265236","doi":"10.21203/rs.3.rs-1747001/v1","title":"Can we improve prediction of Alzheimer's disease and Mild Cognitive Impairment by combining MMSE score and MRI-based imaging data?","year":2022,"lang":"en","type":"preprint","venue":"Research Square","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Silesian University of Technology; Eisai; Novartis Pharmaceuticals Corporation; BioClinica; Northern California Institute for Research and Education; F. Hoffmann-La Roche; Biogen; Eli Lilly and Company; Bristol-Myers Squibb; U.S. Department of Defense; Meso Scale Diagnostics; National Institute on Aging; Alzheimer's Association; Foundation for the National Institutes of Health","keywords":"Cognitive impairment; Logistic regression; Multinomial logistic regression; Medicine; Internal medicine; Disease; Psychology; Computer science; Machine learning","score_opus":0.05468188646478312,"score_gpt":0.38925454632803275,"score_spread":0.33457265986324963,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283265236","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87589127,0.062671565,0.0011278581,0.03800407,0.00060426194,0.0066328715,0.014491279,0.00021363587,0.00036319075],"genre_scores_gemma":[0.98929286,0.0029599895,0.00036685038,0.00023478891,0.00018265475,0.0002488096,0.0065702447,0.00008119133,0.000062635954],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9958689,0.0005403801,0.00047186782,0.0011075223,0.0014272098,0.00058410125],"domain_scores_gemma":[0.9972855,0.0005384931,0.00020681364,0.0008350185,0.00032131412,0.00081287615],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0025585047,0.00031322608,0.0005753399,0.00047937254,0.00036098476,0.000113775895,0.00029527576,0.00010358985,0.000121748344],"category_scores_gemma":[0.00097318715,0.00029727543,0.000085609514,0.00023388826,0.0007331842,0.00008709092,0.0023539606,0.0028575913,6.5962786e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0032631492,0.0017700858,0.842915,0.015798971,0.001682643,0.0010365429,0.0031958988,0.00031969172,0.002346578,0.00008303748,0.031444382,0.096144006],"study_design_scores_gemma":[0.011688208,0.001650005,0.15856455,0.014586946,0.0018946163,0.000040408617,0.005338197,0.8011082,0.0005201036,0.0010341563,0.0028431052,0.0007315054],"about_ca_topic_score_codex":0.0012339095,"about_ca_topic_score_gemma":0.000005745671,"teacher_disagreement_score":0.8007885,"about_ca_system_score_codex":0.00016403028,"about_ca_system_score_gemma":0.0009939111,"threshold_uncertainty_score":0.99994797},"labels":[],"label_agreement":null},{"id":"W4283371744","doi":"10.1017/cjn.2022.86","title":"GP.2 Deep learning prediction of response to disease modifying therapy in primary progressive multiple sclerosis","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Neurological Sciences / Journal Canadien des Sciences Neurologiques","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine; Ocrelizumab; Multiple sclerosis; Placebo; Randomized controlled trial; Clinical trial; Internal medicine; Rituximab; Oncology; Physical therapy; Pathology; Psychiatry","score_opus":0.04024238356655961,"score_gpt":0.27680001894493395,"score_spread":0.23655763537837432,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283371744","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9897007,0.0017871782,0.000050968454,0.0075404155,0.00043708476,0.0002695294,0.0000093681565,0.000014218904,0.00019055733],"genre_scores_gemma":[0.99411637,0.00024493088,0.0016838845,0.0038010133,0.00011657888,0.000011009515,6.710275e-7,0.000012777942,0.000012741899],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9949419,0.0018561186,0.0008224672,0.00043706768,0.0010494436,0.0008929986],"domain_scores_gemma":[0.99631655,0.0007684115,0.0006180578,0.00011795932,0.00025558847,0.001923448],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.007525296,0.00021368862,0.00048325647,0.0015046907,0.001983311,0.00017715932,0.0009935464,0.00006546356,0.0001301438],"category_scores_gemma":[0.006495666,0.00015610164,0.00019165731,0.0016874142,0.00233923,0.00038713694,0.000105641135,0.0019623796,4.4789348e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015573864,0.00006355223,0.8983634,0.000008017041,0.000008879326,0.004060644,0.0007789395,0.07991614,0.00080073264,0.000019580933,0.000066838445,0.0143558625],"study_design_scores_gemma":[0.0009406058,0.057164103,0.9141964,0.0000844179,0.000021010337,0.005711409,0.0004183075,0.01936941,0.000039650295,0.0005986206,0.00130666,0.00014944257],"about_ca_topic_score_codex":0.0006277814,"about_ca_topic_score_gemma":0.0010768606,"teacher_disagreement_score":0.06054673,"about_ca_system_score_codex":0.00044790294,"about_ca_system_score_gemma":0.0030450546,"threshold_uncertainty_score":0.999316},"labels":[],"label_agreement":null},{"id":"W4283380731","doi":"10.30978/tb-2022-2-36","title":"Possibilities of radiomics in processing data of CT scan of the chest organs in diagnosis of pulmonary tuberculosis","year":2022,"lang":"en","type":"article","venue":"Tuberculosis Lung Diseases HIV Infection","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"DICOM; Grayscale; Software; Histogram; Image processing; Computer science; Artificial intelligence; Medical imaging; Sørensen–Dice coefficient; Radiology; Pixel; Segmentation; Medicine; Computer vision; Image segmentation; Image (mathematics)","score_opus":0.012255042744120032,"score_gpt":0.28218815526238605,"score_spread":0.269933112518266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283380731","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9958268,0.0022999234,0.000026602907,0.00066727237,0.00014477139,0.00050194544,0.00026592312,0.000016707563,0.00025005246],"genre_scores_gemma":[0.9989074,0.0006250369,0.00007585206,0.000052823903,0.00004454916,0.0000671667,0.00018120305,0.00003187877,0.000014101163],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9977117,0.00033323336,0.00087503187,0.00035031,0.0005201287,0.00020958782],"domain_scores_gemma":[0.99834204,0.0003403873,0.00044420865,0.0007055272,0.00009366452,0.000074160824],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00075856707,0.00017349784,0.0006182963,0.0004332171,0.00007195358,0.0000059920217,0.00031342104,0.000041612966,0.0001150476],"category_scores_gemma":[0.0009676298,0.00014831568,0.0001777684,0.0012562509,0.000311032,0.00019603602,0.00036566507,0.00040898513,1.5202671e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014552717,0.0014363684,0.9784012,0.0024299491,0.00008508108,0.000008788457,0.00067671156,0.0024696812,0.0032489942,0.00001909778,0.0001486584,0.010929979],"study_design_scores_gemma":[0.000876746,0.00009474658,0.9325104,0.00095303886,0.00046633836,0.000050041213,0.0005211119,0.06144174,0.002812277,0.00009234604,0.000055020177,0.00012624449],"about_ca_topic_score_codex":0.0035534962,"about_ca_topic_score_gemma":0.00006139182,"teacher_disagreement_score":0.058972057,"about_ca_system_score_codex":0.0002998213,"about_ca_system_score_gemma":0.0003138683,"threshold_uncertainty_score":0.6048138},"labels":[],"label_agreement":null},{"id":"W4283390496","doi":"10.1017/cjn.2022.201","title":"P.107 Personalized prediction of future lesion activity and treatment effect in multiple sclerosis from baseline MRI","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Neurological Sciences / Journal Canadien des Sciences Neurologiques","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine; Lesion; Multiple sclerosis; Placebo; Clinical trial; Limiting; Treatment effect; Randomized controlled trial; Baseline (sea); Internal medicine; Surgery; Pathology; Alternative medicine; Psychiatry","score_opus":0.0395460189932205,"score_gpt":0.2711937267131004,"score_spread":0.2316477077198799,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283390496","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9896968,0.0016100693,0.00003679912,0.0077713304,0.00056369917,0.00017947494,0.000038235463,0.000007988564,0.000095629264],"genre_scores_gemma":[0.99672395,0.00091043994,0.0010430515,0.0010476207,0.0002535848,0.0000042745933,0.0000011360958,0.000007625192,0.000008330551],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9963541,0.0014860887,0.0005299007,0.00039562592,0.0006570034,0.0005772698],"domain_scores_gemma":[0.9974585,0.00087789865,0.00047828694,0.00009231972,0.000103999606,0.0009889766],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.004265373,0.00021516942,0.0005627673,0.0007347689,0.0014235053,0.00011105647,0.0004684564,0.000088332476,0.00016433801],"category_scores_gemma":[0.0015025833,0.0001355522,0.0001728175,0.0007843065,0.0026683295,0.000305209,0.00005575429,0.0011671697,1.7220005e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044742078,0.00006241875,0.9664825,0.000006019489,0.00001472085,0.0020690758,0.00043392586,0.0031106856,0.001318639,0.0000255104,0.0001279942,0.025901075],"study_design_scores_gemma":[0.0019743326,0.08687818,0.85811657,0.00006568651,0.00008254892,0.00719352,0.00037706227,0.04232918,0.00027042886,0.0006080297,0.0019482891,0.0001561817],"about_ca_topic_score_codex":0.0070690955,"about_ca_topic_score_gemma":0.018311473,"teacher_disagreement_score":0.10836596,"about_ca_system_score_codex":0.00034326848,"about_ca_system_score_gemma":0.0013500375,"threshold_uncertainty_score":0.9998765},"labels":[],"label_agreement":null},{"id":"W4283460785","doi":"10.3390/cancers14133105","title":"Nasopharyngeal Carcinoma Radiomic Evaluation with Serial PET/CT: Exploring Features Predictive of Survival in Patients with Long-Term Follow-Up","year":2022,"lang":"en","type":"article","venue":"Cancers","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University Health Network; Toronto General Hospital; University of Toronto; Health Sciences Centre; Sunnybrook Health Science Centre","funders":"","keywords":"Nasopharyngeal carcinoma; Medicine; Radiomics; Term (time); Radiology; Medical physics; Oncology; Nuclear medicine; Radiation therapy","score_opus":0.01804794657440946,"score_gpt":0.2670552855713296,"score_spread":0.24900733899692018,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283460785","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99761415,0.0002130302,0.0000350689,0.0000964599,0.0009504523,0.00071037933,0.000027768281,0.000023220808,0.00032946796],"genre_scores_gemma":[0.99914294,0.000011730615,0.00011202757,0.00006833782,0.00015572763,0.00021626065,0.0001876073,0.000037719485,0.00006762603],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99823177,0.00013191515,0.00020766325,0.00031640613,0.0008609063,0.0002513194],"domain_scores_gemma":[0.99938923,0.000044026594,0.00014416015,0.00020087461,0.00010911594,0.00011257586],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041131963,0.00015648249,0.0003539152,0.0001692596,0.0000989757,0.000009657982,0.00011500334,0.0000079022275,0.00013646501],"category_scores_gemma":[0.00007117269,0.00012810758,0.000046259385,0.00029190088,0.000103917075,0.00011239161,0.000047932717,0.00045689745,3.8209464e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0052952194,0.000046529745,0.9735933,0.00008254142,0.00011741798,0.00018705576,0.0010223467,0.015523245,0.00012210003,0.000007936939,0.00012004681,0.0038822605],"study_design_scores_gemma":[0.016628426,0.0013743594,0.9755461,0.00015708563,0.00021879475,0.00006600254,0.0004892056,0.0051327925,0.0002047206,0.00000391925,0.000028862298,0.00014970188],"about_ca_topic_score_codex":0.0005555438,"about_ca_topic_score_gemma":0.00007451368,"teacher_disagreement_score":0.011333207,"about_ca_system_score_codex":0.0017003784,"about_ca_system_score_gemma":0.0008836252,"threshold_uncertainty_score":0.5224076},"labels":[],"label_agreement":null},{"id":"W4283590852","doi":"10.1186/s13550-022-00910-1","title":"Dopamine transporter single-photon emission computed tomography-derived radiomics signature for detecting Parkinson’s disease","year":2022,"lang":"en","type":"article","venue":"EJNMMI Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Japan Society for the Promotion of Science; Avid Radiopharmaceuticals; Sanofi Genzyme; Allergan; Genentech; H. Lundbeck A/S; Servier; Japan Society for the Promotion of Science London; Voyager Therapeutics; Neurocrine Biosciences; Biogen; Celgene; Verily Life Sciences; Teva Pharmaceutical Industries; Sanofi; GlaxoSmithKline; Pfizer; Eli Lilly and Company; Bristol-Myers Squibb; Michael J. Fox Foundation for Parkinson's Research","keywords":"Receiver operating characteristic; Radiomics; Putamen; Medicine; Dopamine transporter; Artificial intelligence; Pattern recognition (psychology); Nuclear medicine; Radiology; Internal medicine; Computer science; Dopamine","score_opus":0.03767528659713356,"score_gpt":0.33650048451509695,"score_spread":0.2988251979179634,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283590852","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9815378,0.0018662418,0.0059609353,0.008117085,0.00043454109,0.0015224246,0.000061904895,0.00017581169,0.00032325485],"genre_scores_gemma":[0.99259466,0.000035465677,0.004257177,0.0006436402,0.0004749945,0.00024921214,0.00037261218,0.00009111014,0.001281107],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9966196,0.00033221967,0.0003442374,0.0006667964,0.0012231363,0.00081400096],"domain_scores_gemma":[0.99798024,0.00055957504,0.000086748056,0.00045567084,0.00023253837,0.00068525755],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023123422,0.00022130004,0.00038657786,0.00059023773,0.0009797623,0.000071121154,0.0003236441,0.00008983188,0.0003854191],"category_scores_gemma":[0.0006831354,0.00020370858,0.0002795918,0.0009110658,0.00020450699,0.000067230576,0.00014813141,0.0020571102,0.0000029741063],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0053931684,0.0012878536,0.027020415,0.0009561098,0.00024507023,0.0011765199,0.001431938,0.0008790763,0.7897542,0.00006677702,0.024869855,0.14691903],"study_design_scores_gemma":[0.010394247,0.0024250268,0.0309831,0.0005007477,0.00021422956,0.00020184462,0.0012653655,0.20683596,0.035451572,0.0006112981,0.71033084,0.00078575313],"about_ca_topic_score_codex":0.000044632066,"about_ca_topic_score_gemma":0.000003047152,"teacher_disagreement_score":0.7543026,"about_ca_system_score_codex":0.0002736818,"about_ca_system_score_gemma":0.00024981712,"threshold_uncertainty_score":0.8937234},"labels":[],"label_agreement":null},{"id":"W4283719804","doi":"10.1002/nbm.4792","title":"Molecular subtype classification of low‐grade gliomas using magnetic resonance imaging‐based radiomics and machine learning","year":2022,"lang":"en","type":"article","venue":"NMR in Biomedicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":72,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Ministry of Science and Technology, Taiwan; Ministry of Education","keywords":"Radiomics; Magnetic resonance imaging; Nuclear magnetic resonance; Medicine; Radiology; Physics","score_opus":0.01664403943182456,"score_gpt":0.28429682454755917,"score_spread":0.2676527851157346,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283719804","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96346545,0.027943915,0.0026167743,0.005150824,0.00017410367,0.000362075,0.00001040624,0.00005493592,0.00022151077],"genre_scores_gemma":[0.9948535,0.00014200146,0.00387959,0.0008216717,0.00007478193,0.000017484534,0.00010195908,0.000049311628,0.000059693397],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979579,0.00019534836,0.00053136516,0.00041170281,0.0005760267,0.00032764577],"domain_scores_gemma":[0.99913394,0.00013064977,0.00021084132,0.0003012181,0.00006079847,0.0001625429],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009872937,0.0001988427,0.00046271025,0.0007461385,0.0001294105,0.000010460168,0.00015110399,0.000052062496,0.0001234691],"category_scores_gemma":[0.00038825945,0.00019241731,0.000060985454,0.0010932247,0.00037827712,0.000040936084,0.00009844212,0.0007814284,7.890426e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033429058,0.00031536198,0.35712463,0.0003161219,0.000015421596,0.00068005547,0.00039298408,0.0017110929,0.5814557,0.00026674717,0.0000966645,0.057290897],"study_design_scores_gemma":[0.0052944017,0.0004971535,0.08608008,0.00030772292,0.000094205614,0.0005271914,0.00025009835,0.89345205,0.0022778658,0.00009068365,0.010918115,0.00021042164],"about_ca_topic_score_codex":0.00035306346,"about_ca_topic_score_gemma":0.000002610751,"teacher_disagreement_score":0.891741,"about_ca_system_score_codex":0.00018505602,"about_ca_system_score_gemma":0.00014572377,"threshold_uncertainty_score":0.78465503},"labels":[],"label_agreement":null},{"id":"W4283756506","doi":"10.1177/08465371221109921","title":"Radiomic Features Based on MRI Predict Progression-Free Survival in Pediatric Diffuse Midline Glioma/Diffuse Intrinsic Pontine Glioma","year":2022,"lang":"en","type":"article","venue":"Canadian Association of Radiologists Journal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hospital for Sick Children; University of Toronto","funders":"","keywords":"Medicine; Concordance; Fluid-attenuated inversion recovery; Glioma; Progression-free survival; Radiomics; Biopsy; Radiology; Magnetic resonance imaging; Oncology; Nuclear medicine; Internal medicine; Overall survival","score_opus":0.007260140200687481,"score_gpt":0.2578143506225821,"score_spread":0.25055421042189463,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283756506","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9727385,0.0007431761,0.00012449615,0.023435479,0.0015743789,0.00046139464,0.00012897122,0.000053896296,0.00073969795],"genre_scores_gemma":[0.99574184,0.00016354003,0.0011047899,0.0011557207,0.0011612531,0.000030247513,0.00014825434,0.000054351018,0.00044001517],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99587446,0.0008337501,0.0008650583,0.00040118457,0.0012254899,0.00080004],"domain_scores_gemma":[0.9969303,0.00062047306,0.0009404915,0.00043805383,0.00020622672,0.00086446555],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0037975658,0.00030166103,0.00077469565,0.0020408863,0.0004712272,0.000051473056,0.00057984225,0.0002255476,0.00023554271],"category_scores_gemma":[0.0067330184,0.0002748227,0.00026761272,0.0011457173,0.000115199466,0.000087451685,0.000073443065,0.002296925,0.0000033572824],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00057651964,0.00060429686,0.9086308,0.00005902854,0.00012074236,0.0037182434,0.00023556879,0.0023839888,0.00036885985,0.000106372216,0.08104039,0.0021551885],"study_design_scores_gemma":[0.018137135,0.0012659765,0.96302414,0.00010431253,0.00018738702,0.0019219244,0.00009839064,0.008726459,0.00003984116,0.00018924882,0.005933774,0.00037138653],"about_ca_topic_score_codex":0.0018645948,"about_ca_topic_score_gemma":0.0018198835,"teacher_disagreement_score":0.07510662,"about_ca_system_score_codex":0.003400572,"about_ca_system_score_gemma":0.0019173156,"threshold_uncertainty_score":0.9999704},"labels":[],"label_agreement":null},{"id":"W4283765531","doi":"10.3390/jpm12071092","title":"Prediction of Incomplete Response of Primary Tumour Based on Clinical and Radiomics Features in Inoperable Head and Neck Cancers after Definitive Treatment","year":2022,"lang":"en","type":"article","venue":"Journal of Personalized Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Uniwersytet Medyczny im. Karola Marcinkowskiego w Poznaniu","keywords":"Medicine; Radiomics; Stage (stratigraphy); Head and neck; Radiation therapy; Radiology; Head and neck cancer; Radiation treatment planning; Retrospective cohort study; Internal medicine; Surgery","score_opus":0.03613203817168795,"score_gpt":0.3318843217355877,"score_spread":0.2957522835638997,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283765531","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9877884,0.004259871,0.000060132053,0.007231661,0.000224815,0.00021845866,0.00003299289,0.0000036803278,0.00018001224],"genre_scores_gemma":[0.9944071,0.0014892189,0.0018060363,0.0019724257,0.00019127794,0.000010134784,0.0000109329,0.000017414139,0.000095415664],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99781895,0.0005028321,0.00080994016,0.00017799089,0.00054003776,0.00015023048],"domain_scores_gemma":[0.9983677,0.0007804308,0.00043803875,0.000105833606,0.00010698292,0.00020097691],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002485492,0.00014750822,0.00092382304,0.0004420158,0.000048100857,0.0000030607403,0.000056202785,0.000056635672,0.000092876246],"category_scores_gemma":[0.00090920506,0.00010400803,0.00010707013,0.00019481186,0.0004743118,0.000040032686,0.000027047725,0.00068536185,4.4834852e-8],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.14019018,0.0010494798,0.8016431,0.00046075386,0.00044791956,0.0013107097,0.007341786,0.0008635582,0.02635272,0.00008625777,0.001955071,0.018298514],"study_design_scores_gemma":[0.03548862,0.018978395,0.93125623,0.001544317,0.00037181232,0.0008940972,0.0012528417,0.0056838547,0.000118924116,0.000046469708,0.0042725764,0.000091868395],"about_ca_topic_score_codex":0.00024013693,"about_ca_topic_score_gemma":0.000006367735,"teacher_disagreement_score":0.12961318,"about_ca_system_score_codex":0.00038422024,"about_ca_system_score_gemma":0.000594151,"threshold_uncertainty_score":0.42413244},"labels":[],"label_agreement":null},{"id":"W4285391730","doi":"10.3389/fonc.2022.920393","title":"Predicting Adverse Radiation Effects in Brain Tumors After Stereotactic Radiotherapy With Deep Learning and Handcrafted Radiomics","year":2022,"lang":"en","type":"article","venue":"Frontiers in Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Université de Sherbrooke","funders":"FP7 Research for the Benefit of SMEs; Eurostars; H2020 Marie Skłodowska-Curie Actions; H2020 European Research Council; European Commission; Universität Zürich; Interreg; European Research Council; KWF Kankerbestrijding","keywords":"Radiomics; Radiation therapy; Adverse effect; Medicine; Radiosurgery; Stereotactic radiotherapy; Radiology; Medical physics; Internal medicine","score_opus":0.0027530864370255014,"score_gpt":0.2538780681305184,"score_spread":0.2511249816934929,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285391730","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98434484,0.0029938559,0.00834424,0.0027793848,0.0005741459,0.00062892167,8.5331766e-7,0.000050793,0.00028297878],"genre_scores_gemma":[0.9813642,0.00019694536,0.015571508,0.0022804933,0.000110150395,0.00021501306,0.000022104958,0.00005088638,0.00018872562],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9981109,0.0005909568,0.00032277516,0.00038136318,0.00021966339,0.00037436676],"domain_scores_gemma":[0.99920905,0.00036392052,0.00015445118,0.00012107696,0.000013966894,0.00013751122],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00089981366,0.0001765694,0.00052715343,0.0005643735,0.00011887091,0.000012120331,0.000079123005,0.00009247285,0.000033939657],"category_scores_gemma":[0.00044973133,0.00017083852,0.000038751015,0.0004087285,0.00013680795,0.00009278457,0.000056379085,0.0013185298,4.062846e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001621825,0.00012013561,0.87926805,0.00007289372,0.00006401096,0.0013746388,0.0030719212,0.0028776878,0.0002356888,0.0000087182225,0.00022728236,0.11105717],"study_design_scores_gemma":[0.016363284,0.0027810703,0.49669337,0.00015732997,0.00007118161,0.0008927597,0.0020354672,0.45165208,0.00001747294,0.00008025656,0.028967656,0.00028807772],"about_ca_topic_score_codex":0.00009312955,"about_ca_topic_score_gemma":0.000034378125,"teacher_disagreement_score":0.4487744,"about_ca_system_score_codex":0.0010452074,"about_ca_system_score_gemma":0.00015912011,"threshold_uncertainty_score":0.69665927},"labels":[],"label_agreement":null},{"id":"W4285505036","doi":"10.1007/978-3-031-09002-8_37","title":"Multi-institutional Travelling Model for Tumor Segmentation in MRI Datasets","year":2022,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Children's Hospital; Hotchkiss Brain Institute; University of Calgary","funders":"","keywords":"Artificial intelligence; Computer science; Machine learning; Segmentation; Conditional random field; Dice; Implementation; Big data; Random forest; Deep learning; Forgetting; Data mining","score_opus":0.027595564054971454,"score_gpt":0.30947514045646696,"score_spread":0.2818795764014955,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285505036","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00044625992,0.00020198303,0.9970626,0.0009048562,0.0005426117,0.0006040316,0.000086374326,0.000026687077,0.00012454424],"genre_scores_gemma":[0.05154566,0.00005339312,0.9435547,0.0035872997,0.00031115775,0.00003791561,0.0006924756,0.000035316614,0.00018206201],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99809045,0.000011774839,0.00035426658,0.0006916449,0.00054137124,0.0003105203],"domain_scores_gemma":[0.99924994,0.00019868933,0.0001206892,0.0002795386,0.000045162826,0.000105986095],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00079161953,0.00023712714,0.00034751496,0.00049728784,0.00020733933,0.00005333314,0.00035175725,0.00007660514,0.00004388963],"category_scores_gemma":[0.00016050453,0.0002095904,0.00007595068,0.00015616941,0.0003545828,0.00013444413,0.00016071409,0.00086892204,0.0000022445593],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031413972,0.00004741629,0.00013547824,0.00009865785,0.000007649283,0.00010970866,0.0005720896,0.88974875,0.00067895744,0.000879953,0.000026065654,0.10766385],"study_design_scores_gemma":[0.0010760764,0.0000660963,0.00007971718,0.00028469795,0.000017318649,0.00009124208,4.5254515e-7,0.9931944,0.00012459593,0.0036384468,0.0012244507,0.0002025063],"about_ca_topic_score_codex":0.000039911338,"about_ca_topic_score_gemma":0.00004061814,"teacher_disagreement_score":0.10746135,"about_ca_system_score_codex":0.000403982,"about_ca_system_score_gemma":0.00059875054,"threshold_uncertainty_score":0.8546849},"labels":[],"label_agreement":null},{"id":"W4285602699","doi":"10.1016/j.media.2022.102532","title":"Cardiac MRI segmentation with sparse annotations: Ensembling deep learning uncertainty and shape priors","year":2022,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":39,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Sunnybrook Health Science Centre","funders":"Canadian Institutes of Health Research; GE Healthcare; National Natural Science Foundation of China; Ontario Research Foundation","keywords":"Artificial intelligence; Prior probability; Segmentation; Computer science; Pattern recognition (psychology); Computer vision; Machine learning; Bayesian probability","score_opus":0.006567144916448316,"score_gpt":0.2791082115076999,"score_spread":0.27254106659125155,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285602699","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9097169,0.0012137443,0.08030285,0.00764321,0.00008237988,0.0002791263,0.0000051309166,0.00013239312,0.000624269],"genre_scores_gemma":[0.9844522,0.000586821,0.011909439,0.0018855776,0.00015783611,0.0000809915,0.00042412273,0.00003598684,0.00046701205],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99724007,0.0003341675,0.00036543098,0.00045938036,0.0012786887,0.0003222597],"domain_scores_gemma":[0.99882096,0.0002828329,0.00015309037,0.00020800823,0.00011256875,0.0004225164],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0013764335,0.00018005542,0.0005340747,0.00047721516,0.00053851184,0.00006783676,0.00011336289,0.000051273284,0.0020070595],"category_scores_gemma":[0.0009360243,0.00014817607,0.00018588032,0.0014898092,0.00022500273,0.00011156345,0.00012630982,0.0010262066,0.0000070819133],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003809637,0.00039452547,0.46423838,0.00017794085,0.0056691603,0.0015870086,0.006890787,0.050466258,0.004419563,0.00010237214,0.0010632473,0.4646098],"study_design_scores_gemma":[0.0014249792,0.0002671816,0.018358594,0.000044331646,0.0034523476,0.00009830687,0.00537073,0.96550256,0.000045433797,0.00002027793,0.0051785246,0.0002367455],"about_ca_topic_score_codex":0.00027055191,"about_ca_topic_score_gemma":0.000018113955,"teacher_disagreement_score":0.91503626,"about_ca_system_score_codex":0.00011706833,"about_ca_system_score_gemma":0.00012397478,"threshold_uncertainty_score":0.99890524},"labels":[],"label_agreement":null},{"id":"W4285717408","doi":"10.1007/978-3-030-59719-1","title":"Medical Image Computing and Computer Assisted Intervention – MICCAI 2020","year":2020,"lang":"en","type":"book","venue":"Lecture notes in computer science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; University of Toronto","funders":"","keywords":"Computer science; Computer graphics (images); Multimedia; Human–computer interaction","score_opus":0.008707190340137857,"score_gpt":0.2952506030000074,"score_spread":0.28654341265986955,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285717408","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022567296,0.0006423503,0.9849844,0.009360256,0.0014751042,0.00035960614,0.0000028115116,0.00014390254,0.0007748574],"genre_scores_gemma":[0.1866248,0.00019923893,0.77581936,0.028035391,0.008375911,0.0000073590904,0.00019929584,0.00016875975,0.0005698547],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961841,0.00010753695,0.0006784116,0.0012168437,0.0012724807,0.0005406062],"domain_scores_gemma":[0.9980394,0.00054290507,0.00026321926,0.00040026644,0.00015325221,0.00060094206],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0013373869,0.00043500526,0.0008565347,0.00035898734,0.0001752987,0.00027216776,0.00066395925,0.00036650588,0.00008133395],"category_scores_gemma":[0.0008129207,0.00037543397,0.00018033145,0.0005379405,0.0012509036,0.0001305724,0.0010091418,0.0024437278,0.00002323369],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026543194,0.000073745476,0.00079361245,0.00048191764,0.000041365976,0.0011210497,0.00049417483,0.00029698273,0.00017010336,0.00004714529,0.0022615714,0.99419177],"study_design_scores_gemma":[0.0013826232,0.0003409312,0.003588866,0.0029244944,0.000054359174,0.0012788131,5.001302e-7,0.9851738,0.000059520014,0.0011008459,0.003715274,0.00037994268],"about_ca_topic_score_codex":0.00002659312,"about_ca_topic_score_gemma":0.00000935025,"teacher_disagreement_score":0.99381185,"about_ca_system_score_codex":0.00027681846,"about_ca_system_score_gemma":0.0007684714,"threshold_uncertainty_score":0.99986976},"labels":[],"label_agreement":null},{"id":"W4285717795","doi":"10.1007/978-3-030-59713-9","title":"Medical Image Computing and Computer Assisted Intervention – MICCAI 2020","year":2020,"lang":"en","type":"book","venue":"Lecture notes in computer science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Okanagan University College; University of British Columbia, Okanagan Campus; University of British Columbia; Canada Research Chairs; University of Toronto","funders":"","keywords":"Computer science; Computer graphics (images)","score_opus":0.008707190340137857,"score_gpt":0.2952506030000074,"score_spread":0.28654341265986955,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285717795","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022567296,0.0006423503,0.9849844,0.009360256,0.0014751042,0.00035960614,0.0000028115116,0.00014390254,0.0007748574],"genre_scores_gemma":[0.1866248,0.00019923893,0.77581936,0.028035391,0.008375911,0.0000073590904,0.00019929584,0.00016875975,0.0005698547],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961841,0.00010753695,0.0006784116,0.0012168437,0.0012724807,0.0005406062],"domain_scores_gemma":[0.9980394,0.00054290507,0.00026321926,0.00040026644,0.00015325221,0.00060094206],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0013373869,0.00043500526,0.0008565347,0.00035898734,0.0001752987,0.00027216776,0.00066395925,0.00036650588,0.00008133395],"category_scores_gemma":[0.0008129207,0.00037543397,0.00018033145,0.0005379405,0.0012509036,0.0001305724,0.0010091418,0.0024437278,0.00002323369],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026543194,0.000073745476,0.00079361245,0.00048191764,0.000041365976,0.0011210497,0.00049417483,0.00029698273,0.00017010336,0.00004714529,0.0022615714,0.99419177],"study_design_scores_gemma":[0.0013826232,0.0003409312,0.003588866,0.0029244944,0.000054359174,0.0012788131,5.001302e-7,0.9851738,0.000059520014,0.0011008459,0.003715274,0.00037994268],"about_ca_topic_score_codex":0.00002659312,"about_ca_topic_score_gemma":0.00000935025,"teacher_disagreement_score":0.99381185,"about_ca_system_score_codex":0.00027681846,"about_ca_system_score_gemma":0.0007684714,"threshold_uncertainty_score":0.99986976},"labels":[],"label_agreement":null},{"id":"W4285751350","doi":"10.1007/978-3-030-59710-8","title":"Medical Image Computing and Computer Assisted Intervention – MICCAI 2020","year":2020,"lang":"en","type":"book","venue":"Lecture notes in computer science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":154,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Okanagan University College; University of British Columbia, Okanagan Campus; University of British Columbia; Canada Research Chairs; University of Toronto","funders":"","keywords":"Computer science; Multimedia; Data science; Computer graphics (images)","score_opus":0.008707190340137857,"score_gpt":0.2952506030000074,"score_spread":0.28654341265986955,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285751350","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022567296,0.0006423503,0.9849844,0.009360256,0.0014751042,0.00035960614,0.0000028115116,0.00014390254,0.0007748574],"genre_scores_gemma":[0.1866248,0.00019923893,0.77581936,0.028035391,0.008375911,0.0000073590904,0.00019929584,0.00016875975,0.0005698547],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961841,0.00010753695,0.0006784116,0.0012168437,0.0012724807,0.0005406062],"domain_scores_gemma":[0.9980394,0.00054290507,0.00026321926,0.00040026644,0.00015325221,0.00060094206],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0013373869,0.00043500526,0.0008565347,0.00035898734,0.0001752987,0.00027216776,0.00066395925,0.00036650588,0.00008133395],"category_scores_gemma":[0.0008129207,0.00037543397,0.00018033145,0.0005379405,0.0012509036,0.0001305724,0.0010091418,0.0024437278,0.00002323369],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026543194,0.000073745476,0.00079361245,0.00048191764,0.000041365976,0.0011210497,0.00049417483,0.00029698273,0.00017010336,0.00004714529,0.0022615714,0.99419177],"study_design_scores_gemma":[0.0013826232,0.0003409312,0.003588866,0.0029244944,0.000054359174,0.0012788131,5.001302e-7,0.9851738,0.000059520014,0.0011008459,0.003715274,0.00037994268],"about_ca_topic_score_codex":0.00002659312,"about_ca_topic_score_gemma":0.00000935025,"teacher_disagreement_score":0.99381185,"about_ca_system_score_codex":0.00027681846,"about_ca_system_score_gemma":0.0007684714,"threshold_uncertainty_score":0.99986976},"labels":[],"label_agreement":null},{"id":"W4286256866","doi":"10.1016/j.media.2022.102554","title":"Task relevance driven adversarial learning for simultaneous detection, size grading, and quantification of hepatocellular carcinoma via integrating multi-modality MRI","year":2022,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":19,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"China Scholarship Council","keywords":"Computer science; Modality (human–computer interaction); Artificial intelligence; Pattern recognition (psychology); Machine learning","score_opus":0.008804619070751366,"score_gpt":0.2814590973556853,"score_spread":0.27265447828493394,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4286256866","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38900223,0.00016602046,0.60894364,0.0014678445,0.00009459709,0.0002552748,0.0000068871173,0.000047973248,0.000015522548],"genre_scores_gemma":[0.98487025,0.00005417228,0.01427556,0.00020442175,0.00014420474,0.00006482204,0.00012902795,0.000031878826,0.0002256461],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99727327,0.00034327747,0.0006950784,0.00056164176,0.00081925665,0.000307485],"domain_scores_gemma":[0.99722856,0.0015308732,0.00038773066,0.0003033765,0.00024600854,0.00030342705],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0017580288,0.00019734795,0.0007001719,0.00026957472,0.00048386608,0.000027393584,0.00018765376,0.0000996215,0.00023849816],"category_scores_gemma":[0.015004864,0.00018424196,0.00035149176,0.00089255586,0.00029499395,0.00007484159,0.00012822691,0.0009689351,0.0000012113808],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00083683856,0.0008737455,0.46406874,0.0006867037,0.0027497222,0.00050899276,0.0034499913,0.025354385,0.3812259,0.000086590495,0.00020075332,0.119957626],"study_design_scores_gemma":[0.0017125562,0.00023991933,0.003876003,0.000026560443,0.0016282543,0.000050837345,0.0005257485,0.9881822,0.0019726588,0.000057728706,0.0015616682,0.00016585125],"about_ca_topic_score_codex":0.0009434396,"about_ca_topic_score_gemma":0.000049230763,"teacher_disagreement_score":0.9628278,"about_ca_system_score_codex":0.00013073096,"about_ca_system_score_gemma":0.00010615567,"threshold_uncertainty_score":0.99329215},"labels":[],"label_agreement":null},{"id":"W4286294457","doi":"10.1200/jco.2022.40.16_suppl.e17570","title":"Evaluating the use of machine learning use in ovarian cancer: A systematic review.","year":2022,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Health Science Centre; Health Sciences Centre; University Health Network","funders":"","keywords":"Medicine; Malignancy; Machine learning; Ovarian cancer; Cancer; Artificial intelligence; Oncology; Internal medicine; Computer science","score_opus":0.2857747185906214,"score_gpt":0.5445571691338327,"score_spread":0.25878245054321125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4286294457","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9165583,0.024245875,0.0005534897,0.055494536,0.0017329471,0.0012607197,0.000004945584,0.000011438295,0.00013771583],"genre_scores_gemma":[0.9485425,0.015222754,0.01010609,0.024521664,0.00056142,0.00005583694,0.0000049654136,0.00004306576,0.00094170053],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99082,0.004529554,0.0035743346,0.00014679469,0.0007372619,0.00019205864],"domain_scores_gemma":[0.98566324,0.009968295,0.003696287,0.00023604135,0.00027034135,0.00016582724],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0217785,0.00010663517,0.0021534394,0.00013677895,0.000092295086,0.000010665508,0.00025406355,0.000078350444,0.00023798853],"category_scores_gemma":[0.081150085,0.00006193942,0.00043314003,0.00031498354,0.00012860015,0.00009751281,0.0001490949,0.0035611019,0.0000011223934],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0054334784,0.0033900114,0.74062806,0.06007502,0.002033603,0.0027913554,0.0013989594,0.06256231,0.0012859813,0.00046772146,0.008171682,0.1117618],"study_design_scores_gemma":[0.023068395,0.033235386,0.11441183,0.10078072,0.007989086,0.005558551,0.00055992877,0.6321619,0.000009774442,0.00025290696,0.08152222,0.00044932103],"about_ca_topic_score_codex":0.00039246143,"about_ca_topic_score_gemma":0.000029198318,"teacher_disagreement_score":0.62621623,"about_ca_system_score_codex":0.00019662366,"about_ca_system_score_gemma":0.001105912,"threshold_uncertainty_score":0.99873775},"labels":[],"label_agreement":null},{"id":"W4286472114","doi":"10.5489/cuaj.7918","title":"Artificial intelligence for prostate cancer histopathology diagnostics","year":2022,"lang":"en","type":"article","venue":"Canadian Urological Association Journal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Histopathology; Prostate cancer; Cancer; Medicine; Artificial intelligence; Pathology; Computer science; Internal medicine","score_opus":0.01777015220008449,"score_gpt":0.28467879234658616,"score_spread":0.2669086401465017,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4286472114","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5582587,0.0018585358,0.007891071,0.42634156,0.003750045,0.0007626303,0.00021463544,0.00006343849,0.0008593851],"genre_scores_gemma":[0.97963893,0.00022054561,0.00090611645,0.017531501,0.0007904111,0.00010631349,0.000034980734,0.000015936606,0.0007552771],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99868226,0.00014167673,0.00031700477,0.00016258298,0.00026021095,0.00043628967],"domain_scores_gemma":[0.99879086,0.00031433709,0.00020261585,0.000060956452,0.00015867344,0.00047255226],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0011851367,0.00008496143,0.0002020696,0.00014564919,0.00065757456,0.00003911418,0.00011420495,0.00007502263,0.0010316711],"category_scores_gemma":[0.003194567,0.000077047574,0.00010361855,0.00015062511,0.00003845398,0.000026253803,0.000023022492,0.000998556,0.000007254603],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019551354,0.00013499447,0.7063361,0.0000128023585,0.000077878,0.0005223208,0.0007250529,0.0044205002,0.00026508837,0.004330917,0.07909632,0.20388252],"study_design_scores_gemma":[0.0003608313,0.00084215746,0.107143015,0.000008071567,0.0001357196,0.00070078234,0.00021786652,0.014499708,0.000017593262,0.017060574,0.8588176,0.00019609445],"about_ca_topic_score_codex":0.00060270086,"about_ca_topic_score_gemma":0.00016643111,"teacher_disagreement_score":0.77972126,"about_ca_system_score_codex":0.001584328,"about_ca_system_score_gemma":0.00068163674,"threshold_uncertainty_score":0.9998815},"labels":[],"label_agreement":null},{"id":"W4286487934","doi":"10.1038/s41598-022-16375-0","title":"Minimising multi-centre radiomics variability through image normalisation: a pilot study","year":2022,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"European Regional Development Fund; Institució Catalana de Recerca i Estudis Avançats; Ministerio de Economía y Competitividad; European Commission; Ministerio de Ciencia e Innovación; British Heart Foundation; Horizon 2020; Engineering and Physical Sciences Research Council; National Institute for Health and Care Research; Barts Charity; Ministerio de Ciencia, Innovación y Universidades","keywords":"Pattern recognition (psychology); Artificial intelligence; Histogram; Feature (linguistics); Computer science; Matching (statistics); Radiomics; Similarity (geometry); Magnetic resonance imaging; Image (mathematics); Medicine; Radiology; Pathology","score_opus":0.030609341154608435,"score_gpt":0.30938925962800173,"score_spread":0.2787799184733933,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4286487934","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9820033,0.00006575814,0.005286703,0.0017367675,0.0075424192,0.0010680569,0.0000035443672,0.00016269487,0.0021308123],"genre_scores_gemma":[0.97991365,0.000001208889,0.01621891,0.0003113412,0.0001577403,0.000037551476,0.000104697,0.000032011456,0.0032229007],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9964766,0.0003302424,0.0007338068,0.0009967093,0.0010559645,0.00040668165],"domain_scores_gemma":[0.99806,0.000093531075,0.00033646825,0.0011331332,0.00017453851,0.00020231897],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0058198688,0.0001851954,0.00035408113,0.00013739048,0.0011296397,0.00022288924,0.00016377878,0.000020130128,0.00093689404],"category_scores_gemma":[0.0013148333,0.0001738412,0.00010476891,0.0006804132,0.00029960225,0.00021333157,0.00027821996,0.00058421085,0.000010874543],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004826284,0.020429458,0.74947643,0.00030602614,0.0003893388,0.01542819,0.033353005,0.0022695165,0.09261515,0.00021588664,0.07512638,0.009907958],"study_design_scores_gemma":[0.020820744,0.00506397,0.13211852,0.00027891502,0.0018179175,0.02352471,0.032423377,0.19808923,0.005644252,0.010219382,0.56704265,0.002956336],"about_ca_topic_score_codex":0.00017621012,"about_ca_topic_score_gemma":0.0000061980604,"teacher_disagreement_score":0.6173579,"about_ca_system_score_codex":0.00028571568,"about_ca_system_score_gemma":0.0003577025,"threshold_uncertainty_score":0.9999764},"labels":[],"label_agreement":null},{"id":"W4286586888","doi":"10.3390/curroncol29080410","title":"Novel Harmonization Method for Multi-Centric Radiomic Studies in Non-Small Cell Lung Cancer","year":2022,"lang":"en","type":"article","venue":"Current Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine; Lung cancer; Radiomics; Stage (stratigraphy); Positron emission tomography; Radiology; Harmonization; Cohen's kappa; Nuclear medicine; Artificial intelligence; Medical physics; Machine learning; Oncology; Computer science","score_opus":0.14779681242154452,"score_gpt":0.4811446969137781,"score_spread":0.33334788449223357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4286586888","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26201808,0.0295664,0.6961488,0.0037148497,0.006505868,0.0018651903,0.00003269509,0.00005838814,0.000089728645],"genre_scores_gemma":[0.5450729,0.009718714,0.4313696,0.004080727,0.0021852052,0.004863754,0.0004236185,0.00020624064,0.0020792256],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987225,0.0001324504,0.00033602177,0.0003416591,0.0001353806,0.0003320132],"domain_scores_gemma":[0.999229,0.00029641594,0.00016209338,0.00012333423,0.000094728406,0.000094402196],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00083382224,0.00013948833,0.00045450323,0.00027189974,0.0001484497,0.000005554414,0.00012767829,0.00004815564,0.000054239932],"category_scores_gemma":[0.00036004267,0.00013192916,0.00008536883,0.00033906018,0.000051104103,0.000024048348,0.00013568097,0.00060911354,0.0000011984616],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007173707,0.0063375137,0.24665438,0.003128225,0.00038436468,0.00011351033,0.01411701,0.022144949,0.036266584,0.0002576005,0.04422513,0.6256534],"study_design_scores_gemma":[0.012792871,0.00025122683,0.005791177,0.0000840725,0.0002450495,0.000052435753,0.0007423901,0.8813644,0.0002502327,0.0000143758,0.09824779,0.00016397897],"about_ca_topic_score_codex":0.000064258675,"about_ca_topic_score_gemma":0.000013991964,"teacher_disagreement_score":0.85921943,"about_ca_system_score_codex":0.0010788848,"about_ca_system_score_gemma":0.0003054822,"threshold_uncertainty_score":0.5379915},"labels":[],"label_agreement":null},{"id":"W4286592278","doi":"10.1016/j.media.2022.102531","title":"Estimating medical image registration error and confidence: A taxonomy and scoping review","year":2022,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":24,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Montreal Neurological Institute and Hospital","funders":"","keywords":"Image registration; Computer science; Taxonomy (biology); Field (mathematics); Artificial intelligence; Estimation; Systematic error; Data mining; Machine learning; Data science; Image (mathematics); Statistics; Mathematics","score_opus":0.02076406305091679,"score_gpt":0.35695223752247734,"score_spread":0.3361881744715606,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4286592278","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.085533,0.06453639,0.6373446,0.20265463,0.00041757277,0.0026788872,0.000018037179,0.00039433505,0.0064225234],"genre_scores_gemma":[0.6470918,0.028904863,0.22862676,0.08922455,0.0017837915,0.0014939714,0.0008349836,0.00018322271,0.0018560609],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9959987,0.00033353874,0.0007977807,0.0006000893,0.0019150412,0.00035487927],"domain_scores_gemma":[0.9979668,0.0004205879,0.00026917242,0.00035631112,0.00010081094,0.0008862882],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0041880016,0.00021674452,0.00092856365,0.00026839072,0.0004082608,0.000079330166,0.00020953294,0.000088767934,0.0073324614],"category_scores_gemma":[0.010222549,0.00018754002,0.00019053537,0.0008859837,0.00061996945,0.00016034942,0.00033292908,0.0011716163,0.000006845425],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027530425,0.0012529439,0.07268988,0.039372288,0.0060829767,0.017147169,0.001614795,0.00010976035,0.0023978977,0.0011855813,0.069500506,0.7883709],"study_design_scores_gemma":[0.0022495128,0.00023680659,0.0024031813,0.015743485,0.0048993938,0.0022472464,0.00037716367,0.96717983,0.000023482273,0.00013998823,0.004006168,0.0004937262],"about_ca_topic_score_codex":0.00028739573,"about_ca_topic_score_gemma":0.00002881608,"teacher_disagreement_score":0.9670701,"about_ca_system_score_codex":0.00005759785,"about_ca_system_score_gemma":0.0004797829,"threshold_uncertainty_score":0.99811476},"labels":[],"label_agreement":null},{"id":"W4286785473","doi":"10.33448/rsd-v11i9.31721","title":"Development of a customized three-dimensional airway model","year":2022,"lang":"en","type":"article","venue":"Research Society and Development","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto General Hospital","funders":"","keywords":"Intraclass correlation; Confidence interval; Computed tomography; Nuclear medicine; Airway; Replicate; Software; 3d model; Biomedical engineering; Computer science; Artificial intelligence; Medicine; Mathematics; Radiology; Statistics; Surgery","score_opus":0.06439441190661042,"score_gpt":0.3658855524025116,"score_spread":0.30149114049590114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4286785473","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98841375,0.00059954607,0.0076841796,0.002013284,0.00004962837,0.0004139746,0.000002447874,0.000036433965,0.00078672543],"genre_scores_gemma":[0.5001331,0.000045468143,0.49748892,0.0005445609,0.000030512469,0.00015910764,0.000044542954,0.000023886934,0.0015298992],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99750036,0.000070023765,0.00035374757,0.00028994193,0.0013879181,0.00039800064],"domain_scores_gemma":[0.999288,0.00013877457,0.000054231023,0.00013856775,0.00015116579,0.00022924376],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034988634,0.000110391484,0.00027357606,0.00009595024,0.00089873,0.00001262056,0.00011769765,0.00004430306,0.00022168884],"category_scores_gemma":[0.00010197813,0.00009495192,0.0000716162,0.00025050383,0.0001853733,0.000030113299,0.00058823713,0.00083166995,0.0000065611644],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022847045,0.002927119,0.014818859,0.0018930393,0.0018661662,0.00012521852,0.08116356,0.012850326,0.09450415,0.0031350197,0.08134384,0.703088],"study_design_scores_gemma":[0.009930383,0.00023360494,0.009398088,0.0002662246,0.00003370268,0.00011417076,0.0040952507,0.7098765,0.008117542,0.00064235396,0.25675386,0.0005383427],"about_ca_topic_score_codex":0.000011299602,"about_ca_topic_score_gemma":0.0000019544477,"teacher_disagreement_score":0.70254964,"about_ca_system_score_codex":0.0002927378,"about_ca_system_score_gemma":0.0021887748,"threshold_uncertainty_score":0.69123954},"labels":[],"label_agreement":null},{"id":"W4288081623","doi":"10.18280/ts.390311","title":"Diagnosis of Paratuberculosis in Histopathological Images Based on Explainable Artificial Intelligence and Deep Learning","year":2022,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Burdur Mehmet Akif Ersoy Üniversitesi","keywords":"Artificial intelligence; Paratuberculosis; Computer science; Deep learning; Class (philosophy); Pattern recognition (psychology); Machine learning; Pathology; Medicine","score_opus":0.021821587864354924,"score_gpt":0.2747688151998343,"score_spread":0.25294722733547936,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4288081623","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9895352,0.00036524888,0.0064531746,0.0025982503,0.00005429007,0.00027446751,0.0000034495156,0.000032675125,0.0006832517],"genre_scores_gemma":[0.997762,0.000062004176,0.001301932,0.0006219458,0.00004256177,0.00014758493,0.00001753675,0.000012654799,0.000031775915],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986231,0.00020550875,0.00032836027,0.0002689102,0.00035612605,0.00021799821],"domain_scores_gemma":[0.9994419,0.0002795761,0.00008243246,0.00008793332,0.000021627367,0.00008652709],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008768923,0.00011739602,0.00026571823,0.00019763551,0.00014173638,0.000012626584,0.00007824748,0.000029278557,0.0012070696],"category_scores_gemma":[0.00022119853,0.000106726715,0.000060620558,0.00020570353,0.000110446985,0.000030515033,0.00005491013,0.00054228434,0.0000019071226],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010823625,0.0022538241,0.37450254,0.0002655071,0.000031196956,0.0008709047,0.0017184148,0.1594701,0.011021701,0.0018926074,0.00026793533,0.4466229],"study_design_scores_gemma":[0.0017111542,0.004555254,0.14487042,0.00028387,0.00014085247,0.00008663021,0.002419428,0.8300578,0.009164292,0.0010301437,0.0052352306,0.0004449228],"about_ca_topic_score_codex":0.00004273235,"about_ca_topic_score_gemma":0.0000014257085,"teacher_disagreement_score":0.6705877,"about_ca_system_score_codex":0.00010057899,"about_ca_system_score_gemma":0.000027261667,"threshold_uncertainty_score":0.999706},"labels":[],"label_agreement":null},{"id":"W4288175377","doi":"10.1007/s00261-022-03616-z","title":"CT, MRI, and radiomics studies of liver metastasis histopathological growth patterns: an up-to-date review","year":2022,"lang":"en","type":"review","venue":"Abdominal Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Medicine; Radiomics; Magnetic resonance imaging; Radiology; Risk stratification; Computed tomography; Hepatology; Pathology; Internal medicine","score_opus":0.09952492923845635,"score_gpt":0.4068780122306997,"score_spread":0.30735308299224334,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4288175377","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00080823665,0.99611,0.00036929734,0.0006936302,0.0005718091,0.0012424027,0.00005730664,0.000045870354,0.00010139972],"genre_scores_gemma":[0.00007292983,0.99203134,0.004032194,0.0028531104,0.0002856869,0.00024967117,0.00022976565,0.00008471111,0.00016057883],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9951535,0.0016174964,0.0013527421,0.0010102448,0.00034111523,0.0005249],"domain_scores_gemma":[0.9969832,0.0011158963,0.000699614,0.0006822166,0.000102908765,0.0004161754],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0027259365,0.0006447125,0.0057913433,0.00042629847,0.00014465275,0.000009332449,0.0004793828,0.00015532799,0.00043726293],"category_scores_gemma":[0.002890565,0.00046531597,0.0006175861,0.0003559842,0.00056844833,0.000055872628,0.00043506644,0.0014131874,0.000014024183],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006701797,0.000074576,0.00007376822,0.054297,0.00063090207,0.0020456556,0.00024374072,6.173364e-7,0.000003292864,0.00026934478,0.0044613294,0.9378328],"study_design_scores_gemma":[0.00055342744,0.0011790124,0.000051072995,0.01325007,0.0061833286,0.018824907,0.00010318433,0.00005366121,8.1251846e-7,0.000036407433,0.9593419,0.0004222337],"about_ca_topic_score_codex":0.000061544975,"about_ca_topic_score_gemma":0.0000020233047,"teacher_disagreement_score":0.95488054,"about_ca_system_score_codex":0.00020734918,"about_ca_system_score_gemma":0.00021408728,"threshold_uncertainty_score":0.9997799},"labels":[],"label_agreement":null},{"id":"W4288757744","doi":"10.1016/j.bspc.2022.104021","title":"A multi-branch hierarchical attention network for medical target segmentation","year":2022,"lang":"en","type":"article","venue":"Biomedical Signal Processing and Control","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Six Talent Peaks Project in Jiangsu Province; Natural Science Foundation of Jiangsu Province; National Natural Science Foundation of China","keywords":"Computer science; Feature (linguistics); Segmentation; Artificial intelligence; Upsampling; Context (archaeology); Pattern recognition (psychology); Perspective (graphical); Market segmentation; Feature extraction; Set (abstract data type); Computer vision; Image (mathematics)","score_opus":0.008804817647696066,"score_gpt":0.28516545703788565,"score_spread":0.27636063939018957,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4288757744","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04646381,0.0017132609,0.93340796,0.017361725,0.00029448126,0.0005857481,0.000021446853,0.00011463285,0.000036945552],"genre_scores_gemma":[0.9756253,0.000016585744,0.016542768,0.0059686317,0.0011131967,0.00029104544,0.00018000616,0.00002966827,0.00023283449],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977127,0.00015055927,0.00040973438,0.00038523634,0.00091152557,0.0004302467],"domain_scores_gemma":[0.9989906,0.00022102901,0.00011561814,0.00007420325,0.00005795928,0.0005405804],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001517621,0.00015934223,0.0003622756,0.00009130186,0.0006771373,0.000047479592,0.00011396302,0.000109768815,0.0003616115],"category_scores_gemma":[0.00023401713,0.00013101942,0.00011058769,0.0002220968,0.00027512532,0.00005322658,0.00004609886,0.00068144535,0.0000019290906],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013712671,0.0007958951,0.010321367,0.00045796033,0.00016260738,0.00009958562,0.00023642478,0.0001612788,0.028031828,0.00010878918,0.006382081,0.9518709],"study_design_scores_gemma":[0.012811933,0.00083109696,0.0037104047,0.00016435036,0.00016237846,0.00031091264,0.00009141998,0.9432808,0.00002175814,0.00076175784,0.037641663,0.0002115375],"about_ca_topic_score_codex":0.000013328899,"about_ca_topic_score_gemma":3.6337968e-7,"teacher_disagreement_score":0.9516594,"about_ca_system_score_codex":0.000061041166,"about_ca_system_score_gemma":0.00029674303,"threshold_uncertainty_score":0.53428173},"labels":[],"label_agreement":null},{"id":"W4288860568","doi":"10.1007/978-3-030-32248-9","title":"Medical Image Computing and Computer Assisted Intervention – MICCAI 2019","year":2019,"lang":"en","type":"book","venue":"Lecture notes in computer science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":540,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Intervention (counseling); Medical imaging; Multimedia; Data science; Medical physics; Human–computer interaction; Artificial intelligence; Medicine","score_opus":0.00762688133724588,"score_gpt":0.29620353554551576,"score_spread":0.2885766542082699,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4288860568","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005746935,0.000794697,0.98666686,0.0025673702,0.0025218157,0.00046421756,0.0000032602154,0.00011000432,0.0011248334],"genre_scores_gemma":[0.19734566,0.00026646804,0.7694582,0.019843446,0.0073685576,0.000007788326,0.0003320354,0.00024841586,0.005129466],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961548,0.00010387462,0.0006620598,0.0011714288,0.0012990874,0.00060875627],"domain_scores_gemma":[0.99788105,0.0006766481,0.00029024226,0.0005761737,0.0001865358,0.00038935337],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00197853,0.00043926304,0.0008708394,0.00064420234,0.00014695311,0.00026320035,0.0006771563,0.0004418535,0.000081167826],"category_scores_gemma":[0.00048287588,0.00036940345,0.0001821354,0.00039908197,0.0011296878,0.00015713244,0.0009136457,0.0022200383,0.000047948393],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023212418,0.000095256764,0.0015535435,0.0004719191,0.00004055993,0.00033954563,0.00031900458,0.0005758296,0.00015582323,0.000067781766,0.002424519,0.993933],"study_design_scores_gemma":[0.0017378572,0.0003428956,0.0073579075,0.0043233484,0.0000515188,0.0012213285,3.6810206e-7,0.9803883,0.000053081498,0.00088506786,0.0032074556,0.00043087127],"about_ca_topic_score_codex":0.000050035018,"about_ca_topic_score_gemma":0.0000093931885,"teacher_disagreement_score":0.99350214,"about_ca_system_score_codex":0.0003418039,"about_ca_system_score_gemma":0.0008546401,"threshold_uncertainty_score":0.9998758},"labels":[],"label_agreement":null},{"id":"W4289223926","doi":"10.1002/cam4.5086","title":"<scp>CT</scp> radiomics identifying non‐responders to neoadjuvant chemoradiotherapy among patients with locally advanced rectal cancer","year":2022,"lang":"en","type":"article","venue":"Cancer Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"SKiN Health","funders":"Natural Science Foundation of Hunan Province","keywords":"Medicine; Radiomics; Logistic regression; Chemoradiotherapy; Colorectal cancer; Cohort; Radiology; Radiation therapy; Area under the curve; Internal medicine; Oncology; Cancer","score_opus":0.008908421548570923,"score_gpt":0.29274444254115745,"score_spread":0.28383602099258654,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4289223926","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98258513,0.003425819,0.0033045097,0.006001358,0.002129255,0.0013651635,0.000037213802,0.00015134663,0.0010001992],"genre_scores_gemma":[0.9724359,0.0010177342,0.0018825801,0.017684596,0.0012518684,0.000851259,0.00015887545,0.0002349141,0.0044822637],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9963666,0.00009679916,0.00057568285,0.00082444825,0.0013272928,0.00080914487],"domain_scores_gemma":[0.9979077,0.00019488562,0.00031312383,0.0005348035,0.00026408298,0.00078543345],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006018685,0.00045061565,0.0009938562,0.0004364987,0.00041031794,0.000028709079,0.00040418154,0.000052101062,0.00077256496],"category_scores_gemma":[0.0005060898,0.00035948693,0.00011110025,0.0011055431,0.00036401013,0.0001531278,0.0001328685,0.0011758739,0.0000055329274],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017713516,0.00042484305,0.569775,0.00046433773,0.00085328036,0.0008211885,0.009631947,0.02236732,0.015948016,0.00003366743,0.11532211,0.26258695],"study_design_scores_gemma":[0.044983223,0.004326992,0.459432,0.0034418474,0.00084836024,0.00019929213,0.004958271,0.019513825,0.0023905688,0.000050823062,0.45908067,0.0007741047],"about_ca_topic_score_codex":0.0010423658,"about_ca_topic_score_gemma":0.000064501364,"teacher_disagreement_score":0.34375855,"about_ca_system_score_codex":0.0011591333,"about_ca_system_score_gemma":0.00051647896,"threshold_uncertainty_score":0.99988574},"labels":[],"label_agreement":null},{"id":"W4289821910","doi":"10.2139/ssrn.4169782","title":"Open-Source Image Analysis Tool for the Identification and Quantification of Cortical Interruptions and Bone Erosions in High-Resolution Peripheral Quantitative Computed Tomography Images of Patients with Rheumatoid Arthritis","year":2022,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Quantitative computed tomography; Rheumatoid arthritis; Peripheral; Medicine; Identification (biology); Computed tomography; High resolution; Radiology; Resolution (logic); Subchondral bone; Artificial intelligence; Pathology; Internal medicine; Computer science; Osteoarthritis; Bone density; Osteoporosis; Remote sensing","score_opus":0.007797446014168867,"score_gpt":0.27515224705129027,"score_spread":0.2673548010371214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4289821910","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.67554593,0.0012086637,0.32205272,0.0008364558,0.000021138587,0.00030913454,0.000020805903,0.000004017914,0.0000011116346],"genre_scores_gemma":[0.99560946,0.0013857109,0.0028182263,0.000021132424,0.000006755658,0.000036878417,0.0000932042,0.000011302086,0.000017334942],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9986449,0.00017126637,0.00047173604,0.00017342262,0.00022320826,0.00031549623],"domain_scores_gemma":[0.999098,0.00021075868,0.0003548122,0.00012316136,0.00017607065,0.000037196296],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016468816,0.00008169752,0.0002843769,0.00028424285,0.00032551916,0.000047443267,0.00011265871,0.000019247373,0.000009684695],"category_scores_gemma":[0.00021757431,0.00006131504,0.00006616518,0.00052501424,0.00022898031,0.00013584126,0.00007135422,0.0006953851,4.154271e-8],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0031421636,0.0015504548,0.84289247,0.00008702344,0.0021192823,0.0000021826067,0.0027237157,0.0077741235,0.03683953,0.05309459,0.00010263692,0.049671825],"study_design_scores_gemma":[0.003549379,0.0009849339,0.9030276,0.00007272534,0.00032876086,0.00005599132,0.0028549172,0.08745671,0.00008730346,0.0014483162,0.000039526924,0.00009382114],"about_ca_topic_score_codex":0.00022349965,"about_ca_topic_score_gemma":0.00016769454,"teacher_disagreement_score":0.3200635,"about_ca_system_score_codex":0.00011115952,"about_ca_system_score_gemma":0.00016836806,"threshold_uncertainty_score":0.3021141},"labels":[],"label_agreement":null},{"id":"W4289878624","doi":"10.1093/noajnl/vdac078.071","title":"NEIM-04 LEVERAGING NOVEL NEUROIMAGING TECHNIQUES TO LINK BRAIN METASTASES AND LOCAL GENE EXPRESSION","year":2022,"lang":"en","type":"article","venue":"Neuro-Oncology Advances","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Brain Institute; University of Toronto","funders":"","keywords":"Neuroimaging; Melanoma; Brain metastasis; Brain atlas; Biology; Pathology; Medicine; Neuroscience; Metastasis; Cancer research; Cancer; Genetics","score_opus":0.01738463253737988,"score_gpt":0.3262553710472035,"score_spread":0.3088707385098236,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4289878624","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47116548,0.004572151,0.33887,0.17887054,0.0018588692,0.001430468,0.00004225274,0.0008186429,0.002371602],"genre_scores_gemma":[0.83199716,0.0002251006,0.09484912,0.07192803,0.00053626945,0.00019718139,0.0000342964,0.00008420363,0.00014863106],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99796754,0.0002572982,0.0003472214,0.000651587,0.00034930801,0.00042701777],"domain_scores_gemma":[0.9985293,0.000725639,0.00014004255,0.00027791364,0.00004511632,0.00028197473],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006410607,0.00023310194,0.00046487842,0.0002652753,0.0004702855,0.000027624834,0.00020150823,0.000046932557,0.00008831165],"category_scores_gemma":[0.0008751109,0.0002172752,0.00007063544,0.00028523203,0.00022643388,0.0001732658,0.0005095559,0.0010797664,0.000003011156],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018380604,0.000111148416,0.0028019557,0.00004062896,0.0000119462975,0.0004545194,0.0002867765,0.0013287633,0.67200613,0.0000750603,0.002661706,0.32003757],"study_design_scores_gemma":[0.0014672118,0.001186596,0.0009988127,0.00004664671,0.00007238904,0.0023340867,0.000407868,0.005961967,0.07894584,0.00022991127,0.9080763,0.00027238173],"about_ca_topic_score_codex":0.000022899441,"about_ca_topic_score_gemma":0.0000015572796,"teacher_disagreement_score":0.9054146,"about_ca_system_score_codex":0.00010775228,"about_ca_system_score_gemma":0.00011765514,"threshold_uncertainty_score":0.88602257},"labels":[],"label_agreement":null},{"id":"W4290673092","doi":"10.3174/ajnr.a7591","title":"Stable and Discriminatory Radiomic Features from the Tumor and Its Habitat Associated with Progression-Free Survival in Glioblastoma: A Multi-Institutional Study","year":2022,"lang":"en","type":"article","venue":"American Journal of Neuroradiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Northern Alberta Institute of Technology","funders":"DOD Peer Reviewed Cancer Research Program; National Center for Research Resources; National Institute of Biomedical Imaging and Bioengineering; Pharmacyclics; National Institutes of Health; Apollomics; Voyager Therapeutics; Incyte; U.S. Department of Veterans Affairs; Varian Medical Systems; AstraZeneca; Bristol-Myers Squibb; V Foundation for Cancer Research; Dana Foundation; Wallace H. Coulter Foundation; ViewRay; U.S. Department of Defense; Novocure; National Cancer Institute; Case Western Reserve University; National Science Foundation","keywords":"Medicine; Fluid-attenuated inversion recovery; Glioblastoma; Hyperintensity; Magnetic resonance imaging; Brain tumor; Radiology; Survival analysis; Radiomics; Nuclear medicine; Pathology; Internal medicine; Cancer research","score_opus":0.011435899987350921,"score_gpt":0.28001671865394917,"score_spread":0.2685808186665983,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4290673092","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9940965,0.0012097808,0.000031525076,0.004190108,0.00019205156,0.00024649347,0.000016137292,0.000009840861,0.0000075297426],"genre_scores_gemma":[0.9987808,0.000036977955,0.00032806827,0.000728442,0.00007702252,0.000013654874,0.0000029041123,0.000019004341,0.000013112351],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99802625,0.000861851,0.00030278377,0.00022672593,0.0003595254,0.00022288486],"domain_scores_gemma":[0.9984976,0.0007911872,0.00036957406,0.00013841104,0.000057991172,0.00014522344],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008301549,0.00015254629,0.00058010005,0.0001492429,0.00026001912,0.000013781645,0.00020872173,0.000014670536,0.000009225506],"category_scores_gemma":[0.0012278439,0.00008788991,0.000039786053,0.00025393162,0.00066712516,0.0000633556,0.00015615094,0.0011255136,9.5815274e-8],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013862378,0.0005539338,0.9883136,0.0000055849728,0.00019096516,0.0036502075,0.0019118348,0.00026140094,0.0011507728,0.000034607056,0.00034057003,0.0022002643],"study_design_scores_gemma":[0.005252968,0.0056862864,0.97834074,0.00005401574,0.00012990991,0.005417913,0.0032215826,0.0016205566,0.0000066597972,0.000023695942,0.00015026923,0.000095406984],"about_ca_topic_score_codex":0.000109725224,"about_ca_topic_score_gemma":0.000077252975,"teacher_disagreement_score":0.009972886,"about_ca_system_score_codex":0.000084962616,"about_ca_system_score_gemma":0.00022200741,"threshold_uncertainty_score":0.4889859},"labels":[],"label_agreement":null},{"id":"W4290997069","doi":"10.1136/annrheumdis-2022-eular.2161","title":"POS0111 MORE METICULOUSLY FOLLOWING TREAT-TO-TARGET IN RA DOES NOT LEAD TO LESS RADIOGRAPHIC PROGRESSION: A LONGITUDINAL ANALYSIS IN BIODAM","year":2022,"lang":"en","type":"article","venue":"Annals of the Rheumatic Diseases","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary; Centre Intégré Universitaire de Santé et de Services Sociaux du Saguenay–Lac-Saint-Jean; McMaster University; Southlake Regional Health Center; Centre Intégré Universitaire de Santé et de Services Sociaux du Centre-Sud-de-l'Île-de-Montréal; University of Toronto; Centre Hospitalier Universitaire de Sherbrooke; University of Alberta","funders":"Assistance publique-Hôpitaux de Paris; Université Paris Descartes; Università degli Studi di Ferrara; Institut National de la Santé et de la Recherche Médicale; Università degli Studi di Verona; Université de Bordeaux; Centre Hospitalier Régional Universitaire de Montpellier; Johns Hopkins University; Université de Sherbrooke; Pfizer; Diakonhjemmet; Eli Lilly and Company","keywords":"Medicine; Radiography; Lead (geology); Surgery","score_opus":0.027653749450616334,"score_gpt":0.3500600052131559,"score_spread":0.32240625576253956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4290997069","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9682497,0.0013388643,0.00011421767,0.029382186,0.00013817205,0.00065309013,0.0000414095,0.00003174955,0.00005064753],"genre_scores_gemma":[0.9970368,0.000066751374,0.00087296794,0.001638692,0.00002105855,0.00019129617,0.000027239299,0.000025720536,0.00011948467],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9974067,0.00029829837,0.0006326471,0.00040590874,0.00083719124,0.0004192526],"domain_scores_gemma":[0.99869746,0.00023481474,0.00017392878,0.00055364164,0.000047238012,0.0002929353],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00086892524,0.00022395106,0.00084986223,0.0011938044,0.0001538262,0.00003300544,0.00043958958,0.00002981755,0.00009805302],"category_scores_gemma":[0.0010252954,0.000138553,0.00068598153,0.0031356693,0.000094787036,0.0000646348,0.00028329,0.00029748603,0.0000020666394],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032894846,0.00079773297,0.96264553,0.00020063382,0.0006688834,0.0002245118,0.0014168655,0.009190864,0.00014225418,0.00002844802,0.00048643255,0.023868887],"study_design_scores_gemma":[0.0011829049,0.00026609984,0.98038435,0.001090005,0.0008301926,0.000017145258,0.0011456766,0.01428365,0.00022199916,0.0002389701,0.00010093726,0.0002380551],"about_ca_topic_score_codex":0.0009010219,"about_ca_topic_score_gemma":0.000059980375,"teacher_disagreement_score":0.028787127,"about_ca_system_score_codex":0.0000494746,"about_ca_system_score_gemma":0.00010350719,"threshold_uncertainty_score":0.5650028},"labels":[],"label_agreement":null},{"id":"W4291020878","doi":"10.1016/j.ccell.2022.06.004","title":"Human and machine: Better at pathology together?","year":2022,"lang":"en","type":"letter","venue":"Cancer Cell","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mount Sinai Hospital","funders":"","keywords":"Computer science; Histopathology; Cancer; Big data; Pathology; Computational biology; Artificial intelligence; Data science; Bioinformatics; Medicine; Biology; Data mining; Internal medicine","score_opus":0.014945251818002186,"score_gpt":0.28447579693497216,"score_spread":0.26953054511696994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4291020878","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06689719,0.01709414,0.00002920132,0.8876245,0.0013431271,0.0004131036,0.00009503437,0.00011467417,0.026389046],"genre_scores_gemma":[0.0025361574,0.00089003384,0.00025595244,0.9326143,0.004058854,0.00011665936,0.0005615022,0.00014153543,0.05882498],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99832004,0.00011934279,0.00025713976,0.00057559146,0.0003120515,0.00041583113],"domain_scores_gemma":[0.9992378,0.000056222514,0.00015285188,0.00041191906,0.000023102279,0.000118149364],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00017818256,0.0003004561,0.00054432015,0.00008140859,0.00021711185,0.000020181875,0.00016881389,0.00036968332,0.013043218],"category_scores_gemma":[0.000015627598,0.00026515845,0.00012920625,0.000055964294,0.00018091389,0.000021886503,0.00026769692,0.0030644822,0.000023244793],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014248661,0.000015244963,0.004691349,0.00042288844,0.000052095707,0.0026612678,0.0002003861,0.000002648964,0.001717222,0.0000018407071,0.9856573,0.004563522],"study_design_scores_gemma":[0.00093590765,0.00014315605,0.0005470221,0.000055353303,0.0002269764,0.0003133927,0.000010079465,0.0001224273,0.000098836565,0.000041405747,0.9972391,0.00026630773],"about_ca_topic_score_codex":0.00055977673,"about_ca_topic_score_gemma":0.000013443252,"teacher_disagreement_score":0.064361036,"about_ca_system_score_codex":0.0003735223,"about_ca_system_score_gemma":0.00006458262,"threshold_uncertainty_score":0.99998003},"labels":[],"label_agreement":null},{"id":"W4291163701","doi":"10.1016/j.acra.2022.07.016","title":"Comparison of Feature Selection Methods and Machine Learning Classifiers for Predicting Chronic Obstructive Pulmonary Disease Using Texture-Based CT Lung Radiomic Features","year":2022,"lang":"en","type":"article","venue":"Academic Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":33,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Zoo; McGill University Health Centre; Western University; University of British Columbia; Royal Victoria Hospital; Toronto Metropolitan University","funders":"","keywords":"COPD; Feature selection; Medicine; Receiver operating characteristic; Artificial intelligence; Support vector machine; Obstructive lung disease; Feature (linguistics); Pattern recognition (psychology); Radiology; Computer science; Internal medicine","score_opus":0.025600398894179928,"score_gpt":0.38075428306320913,"score_spread":0.3551538841690292,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4291163701","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90940267,0.032435473,0.053654283,0.002648053,0.0006301958,0.0009855848,0.000037918682,0.00013571017,0.00007013821],"genre_scores_gemma":[0.9749282,0.00018807905,0.02340842,0.0003547648,0.0004927475,0.00009139095,0.00022592666,0.00006822661,0.00024224601],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997286,0.00085847947,0.0004965911,0.00060844654,0.00025158408,0.0004988762],"domain_scores_gemma":[0.9980292,0.0009724298,0.00050555624,0.00017044568,0.00005631122,0.00026609813],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0013264675,0.00029069145,0.0008354488,0.00064006256,0.000713478,0.0000068831814,0.00019044951,0.00019558973,0.00003326753],"category_scores_gemma":[0.0012673942,0.00027627824,0.00018066065,0.0005764569,0.0003863016,0.00007347162,0.000108309716,0.0037206674,8.033199e-8],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011870931,0.000051762752,0.7755823,0.0004976858,0.00023536434,0.000040334533,0.000461065,0.06679,0.13049501,0.00022480506,0.0011120867,0.023322478],"study_design_scores_gemma":[0.001723471,0.0003423833,0.07818992,0.00007984085,0.00057213934,0.0019134284,0.0002684316,0.9082894,0.0012950093,0.00015597737,0.0069445716,0.00022547055],"about_ca_topic_score_codex":0.000079925856,"about_ca_topic_score_gemma":7.983382e-7,"teacher_disagreement_score":0.8414994,"about_ca_system_score_codex":0.00051469763,"about_ca_system_score_gemma":0.00037729196,"threshold_uncertainty_score":0.99996895},"labels":[],"label_agreement":null},{"id":"W4291392550","doi":"10.3390/curroncol29080449","title":"Towards Precision Oncology: Enhancing Cancer Screening, Diagnosis and Theragnosis Using Artificial Intelligence","year":2022,"lang":"en","type":"editorial","venue":"Current Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; University of Toronto; Sunnybrook Health Science Centre","funders":"","keywords":"Medicine; Precision oncology; Precision medicine; Clinical Oncology; Medical physics; Cancer imaging; Cancer; Oncology; Internal medicine; Pathology","score_opus":0.12033411933773674,"score_gpt":0.47606769805611443,"score_spread":0.3557335787183777,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4291392550","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012989309,0.027308103,0.017741214,0.0035444985,0.93657696,0.0010654036,0.0001340342,0.00013923476,0.0005012171],"genre_scores_gemma":[0.0049658413,0.06851163,0.009792207,0.00048682166,0.9142299,0.0010958295,0.0005707053,0.00022852654,0.000118491895],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9956379,0.000582431,0.0009906575,0.0010801579,0.0010249784,0.0006839031],"domain_scores_gemma":[0.99563575,0.0025720561,0.00067695626,0.0003934538,0.00031187918,0.00040989142],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0019042591,0.0005219375,0.0014729954,0.000439753,0.0004287926,0.00006773558,0.00038319483,0.000922344,0.0018807367],"category_scores_gemma":[0.0047459453,0.00047884614,0.00025165037,0.00036051474,0.00038405697,0.00008461128,0.0006786411,0.0046545365,0.0000071212644],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002353561,0.00045868556,0.00092598196,0.00025205084,0.0001447636,0.00010193274,0.00059296243,0.000108149994,0.00007594434,0.000037522845,0.27342862,0.72363806],"study_design_scores_gemma":[0.00055498036,0.0012804769,0.00008916351,0.0010190171,0.00083060673,0.000040689247,0.00031172796,0.010241392,0.00016109868,0.00042700875,0.9846236,0.0004202079],"about_ca_topic_score_codex":0.00077899196,"about_ca_topic_score_gemma":0.00013257269,"teacher_disagreement_score":0.72321784,"about_ca_system_score_codex":0.0018776275,"about_ca_system_score_gemma":0.0024896257,"threshold_uncertainty_score":0.99976635},"labels":[],"label_agreement":null},{"id":"W4291415397","doi":"10.3390/brainsci12081067","title":"A Novel Deep Learning Radiomics Model to Discriminate AD, MCI and NC: An Exploratory Study Based on Tau PET Scans from ADNI","year":2022,"lang":"en","type":"article","venue":"Brain Sciences","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Key Laboratory of Nuclear Medicine and Molecular Imaging of Sichuan Province; Pfizer; Novartis Pharmaceuticals Corporation; Biogen; Eli Lilly and Company; Bristol-Myers Squibb; BioClinica; U.S. Department of Defense; Meso Scale Diagnostics; Alzheimer's Disease Neuroimaging Initiative; Eisai; National Institute on Aging; Alzheimer's Association","keywords":"Alzheimer's Disease Neuroimaging Initiative; Artificial intelligence; Positron emission tomography; Neuroimaging; Cognitive impairment; Radiomics; Support vector machine; Nuclear medicine; Deep learning; Pattern recognition (psychology); Machine learning; Computer science; Psychology; Medicine; Cognition; Neuroscience","score_opus":0.0394434818300856,"score_gpt":0.3239879280370927,"score_spread":0.2845444462070071,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4291415397","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9360197,0.000070764734,0.056130107,0.0068111033,0.00015603872,0.0004006618,0.000012839616,0.00007823793,0.00032052744],"genre_scores_gemma":[0.97919005,0.0000046304526,0.01408237,0.0063545727,0.000070234484,0.00007248709,0.00002183243,0.000026294061,0.00017749789],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99769413,0.00022917289,0.00023373144,0.0006948219,0.00079249614,0.00035562835],"domain_scores_gemma":[0.9989499,0.00029748082,0.00008637044,0.00026233593,0.000030806797,0.00037310758],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021420806,0.00018086654,0.00028942394,0.00030305833,0.0008928856,0.00011378017,0.00034970275,0.000018378703,0.000057640147],"category_scores_gemma":[0.00084674964,0.00015423,0.000044692304,0.00048765997,0.0002674398,0.00016627787,0.00019558547,0.00055418134,0.0000023092766],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002276109,0.0009261064,0.018748762,0.000015487469,0.000021278996,0.00014151377,0.023450531,0.9143647,0.009684798,0.00017176781,0.0005807947,0.03166665],"study_design_scores_gemma":[0.001367044,0.0016849913,0.007361344,0.000026882948,0.00003463887,0.000022378908,0.021683166,0.9669405,0.000021438149,0.0000761688,0.00058799726,0.00019342726],"about_ca_topic_score_codex":0.00020828686,"about_ca_topic_score_gemma":0.00009072406,"teacher_disagreement_score":0.052575827,"about_ca_system_score_codex":0.00008693458,"about_ca_system_score_gemma":0.00018563442,"threshold_uncertainty_score":0.68674445},"labels":[],"label_agreement":null},{"id":"W4292658234","doi":"10.1007/s10278-022-00681-0","title":"Myocardial Function Prediction After Coronary Artery Bypass Grafting Using MRI Radiomic Features and Machine Learning Algorithms","year":2022,"lang":"en","type":"article","venue":"Journal of Digital Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Université de Genève; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; Iran University of Medical Sciences","keywords":"Support vector machine; Algorithm; Artificial intelligence; Medicine; Scad; Voxel; Pattern recognition (psychology); Computer science; Internal medicine","score_opus":0.008327456235253619,"score_gpt":0.2393555609946139,"score_spread":0.23102810475936025,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4292658234","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97418404,0.0044160928,0.018416323,0.0011952767,0.0012184441,0.000147796,0.000019376572,0.000058870184,0.00034375643],"genre_scores_gemma":[0.99646914,0.000070731076,0.0018016378,0.00048871536,0.0009016538,0.000003935488,0.000029949333,0.000052856314,0.00018138633],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99818707,0.00010301713,0.0005342398,0.00024079738,0.00063155533,0.00030332367],"domain_scores_gemma":[0.9991164,0.00009390009,0.0003563887,0.000106294094,0.000102990525,0.00022401894],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006929186,0.00020371491,0.00040313174,0.00038998076,0.00040669387,0.00017361,0.00008317257,0.000033684773,0.00004656255],"category_scores_gemma":[0.00018050466,0.00018664687,0.00020868216,0.00020081659,0.00011857911,0.00078954303,0.00015256043,0.0015248128,8.68349e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011718393,0.00014320272,0.88792,0.000057128644,0.00048678572,0.0026773352,0.00085997616,0.005259655,0.0070028403,0.000005477362,0.0007546095,0.09366114],"study_design_scores_gemma":[0.007920192,0.0013698374,0.3733073,0.0003602129,0.0011693205,0.17936876,0.0016680176,0.42060062,0.00010048248,0.00037308192,0.013206304,0.0005558716],"about_ca_topic_score_codex":0.000009745791,"about_ca_topic_score_gemma":9.0531664e-8,"teacher_disagreement_score":0.51461273,"about_ca_system_score_codex":0.00022740752,"about_ca_system_score_gemma":0.000111649926,"threshold_uncertainty_score":0.76112384},"labels":[],"label_agreement":null},{"id":"W4292809017","doi":"10.1016/s2589-7500(22)00129-7","title":"Clinical validation of deep learning algorithms for radiotherapy targeting of non-small-cell lung cancer: an observational study","year":2022,"lang":"en","type":"article","venue":"The Lancet Digital Health","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":70,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"National Institute of Dental and Craniofacial Research; National Cancer Institute; European Research Council; National Institutes of Health; H2020 European Research Council; AstraZeneca","keywords":"Radiogenomics; Medicine; Artificial intelligence; Deep learning; Machine learning; Medical physics; Computer science; Radiomics","score_opus":0.09656590138697817,"score_gpt":0.4382112454634817,"score_spread":0.34164534407650354,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4292809017","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9748961,0.00078447926,0.020120528,0.0027991724,0.00023166207,0.0010043794,0.00003342911,0.000029911387,0.00010036124],"genre_scores_gemma":[0.99093187,0.00016597856,0.006914341,0.00093752815,0.0006421667,0.000083445266,0.00020479728,0.000029548317,0.00009029688],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99832726,0.00022676741,0.0006398066,0.00021519503,0.00033900802,0.00025193952],"domain_scores_gemma":[0.99862343,0.0004919481,0.0004899701,0.00019950021,0.00009686126,0.00009828297],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029275706,0.00009776936,0.00054077385,0.00004701721,0.00023042683,0.000021028107,0.00020054211,0.000021432832,0.00002801497],"category_scores_gemma":[0.00023650048,0.000075750875,0.00009499819,0.00017426902,0.000055440858,0.0000985046,0.000053315347,0.00048736724,1.14714716e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034522003,0.0006975521,0.8330949,0.00034609568,0.00008961493,0.0000014476537,0.0029713581,0.010362426,0.00014804848,0.00004083003,0.00052791205,0.15137461],"study_design_scores_gemma":[0.0073156767,0.0043911226,0.20719463,0.000093414325,0.00007487389,0.000008807685,0.0041530067,0.7724367,0.0000862369,0.00012568025,0.0039527277,0.00016715498],"about_ca_topic_score_codex":0.00018388427,"about_ca_topic_score_gemma":0.000002378188,"teacher_disagreement_score":0.76207423,"about_ca_system_score_codex":0.000082821796,"about_ca_system_score_gemma":0.0002757135,"threshold_uncertainty_score":0.3089031},"labels":[],"label_agreement":null},{"id":"W4292830146","doi":"10.23919/annsim55834.2022.9859361","title":"Multi-Modality Breast MRI Segmentation Using NNU-NET For Preoperative Planning Of Robotic Surgery Navigation","year":2022,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University; Queen's University","funders":"Old Dominion University","keywords":"Segmentation; Modality (human–computer interaction); Artificial intelligence; Computer science; Surgical planning; Imaging phantom; Pattern recognition (psychology); Computer vision; Radiology; Medicine","score_opus":0.04169311690336048,"score_gpt":0.354860956335024,"score_spread":0.31316783943166354,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4292830146","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6403291,0.00004758108,0.3578314,0.0011034885,0.00019075308,0.0004157861,0.000014017632,0.000029968196,0.000037884467],"genre_scores_gemma":[0.9484894,0.0000016807275,0.050608683,0.0002779796,0.000071661976,0.000039865157,0.0003215062,0.000018083063,0.00017111804],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989834,0.00010230989,0.00031681563,0.00019338717,0.00024845393,0.0001556274],"domain_scores_gemma":[0.9993657,0.00022092025,0.00015189998,0.00010648721,0.00008787027,0.00006714888],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00073227653,0.00009126641,0.00026170578,0.00009231429,0.0001958712,0.0000125164015,0.000041734867,0.000024039702,0.00010852818],"category_scores_gemma":[0.00011639715,0.0000836944,0.000086869804,0.00014974359,0.000044683202,0.00008926113,0.000039389197,0.0001981703,4.037125e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039365285,0.0004720787,0.34869188,0.00058652763,0.00020109006,0.000024070881,0.0036828576,0.5188305,0.118298806,0.0002123099,0.0013847344,0.007221493],"study_design_scores_gemma":[0.0010547339,0.00007959228,0.045779627,0.00010076961,0.00010098817,0.0001664721,0.0013330845,0.9495536,0.0016337229,0.000047512363,0.000048390306,0.00010150466],"about_ca_topic_score_codex":0.00023516647,"about_ca_topic_score_gemma":7.770969e-7,"teacher_disagreement_score":0.4307231,"about_ca_system_score_codex":0.00012914962,"about_ca_system_score_gemma":0.00011931641,"threshold_uncertainty_score":0.34129587},"labels":[],"label_agreement":null},{"id":"W4292935249","doi":"10.1007/978-3-642-23629-7","title":"Medical Image Computing and Computer-Assisted Intervention – MICCAI 2011","year":2011,"lang":"en","type":"book","venue":"Lecture notes in computer science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Hospital; Queen's University","funders":"","keywords":"Computer science; Set (abstract data type); Intervention (counseling); Multimedia; Medicine; Nursing","score_opus":0.011788956385331005,"score_gpt":0.29178293543071643,"score_spread":0.2799939790453854,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4292935249","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005114376,0.0008777425,0.98870075,0.0012786112,0.001875322,0.00036356156,0.0000021861374,0.00013864401,0.0016488256],"genre_scores_gemma":[0.19974847,0.00024370365,0.7852788,0.008547442,0.004523069,0.000008748731,0.00012563658,0.0001687232,0.0013553813],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99634093,0.000105039995,0.0007006068,0.0011527322,0.0010740509,0.0006266249],"domain_scores_gemma":[0.99800557,0.00043519787,0.000310005,0.00054861006,0.00019341373,0.0005071887],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0019449623,0.0004551426,0.0008263336,0.00067670055,0.00019551822,0.00018012743,0.0007395483,0.0004308609,0.00018639311],"category_scores_gemma":[0.00038695347,0.00038770444,0.00017647582,0.00029827468,0.0016189947,0.00015263385,0.00092459196,0.002106072,0.000037139027],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024108685,0.000131614,0.001051374,0.00035449848,0.000035659992,0.00051896356,0.000549893,0.00006671566,0.00009493483,0.00010092666,0.0008082029,0.9962631],"study_design_scores_gemma":[0.0019414702,0.00056813227,0.009743091,0.004473743,0.00008208948,0.0021507002,6.469559e-7,0.9740052,0.00014901604,0.0037368573,0.002552445,0.00059656997],"about_ca_topic_score_codex":0.00011839486,"about_ca_topic_score_gemma":0.000023325667,"teacher_disagreement_score":0.99566656,"about_ca_system_score_codex":0.00027437037,"about_ca_system_score_gemma":0.0007245329,"threshold_uncertainty_score":0.9998575},"labels":[],"label_agreement":null},{"id":"W4293053502","doi":"10.1158/1538-7445.am2022-4087","title":"Abstract 4087: Developing a standardized framework for curating oncology datasets generated by manual abstraction and artificial intelligence","year":2022,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto; University Health Network","funders":"","keywords":"Consistency (knowledge bases); Computer science; Population; Test (biology); Lung cancer; Medicine; Artificial intelligence; Data mining; Machine learning; Oncology; Biology","score_opus":0.13042506893935205,"score_gpt":0.5168611613552492,"score_spread":0.38643609241589716,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293053502","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85537726,0.001820973,0.11620277,0.02377943,0.0006684287,0.0011736632,0.00069858157,0.00007008378,0.00020881827],"genre_scores_gemma":[0.97254455,0.00055824535,0.024039377,0.00081681117,0.0006101194,0.00061311375,0.00068872917,0.00004435485,0.0000847068],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981239,0.00015240735,0.00031963867,0.00038295906,0.0005741053,0.00044701697],"domain_scores_gemma":[0.9986817,0.0007425653,0.00008898892,0.00015736066,0.00016189808,0.00016747895],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002615355,0.000103788036,0.00024081825,0.00014848744,0.0008011648,0.000074904834,0.0001314232,0.000077625235,0.00045996427],"category_scores_gemma":[0.0012874973,0.00010070035,0.000031485746,0.0003019319,0.00017776905,0.000073885705,0.00014428693,0.0015615203,0.0000030708925],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017159565,0.00014177825,0.00029115466,0.00029926162,0.00012256566,0.00011946381,0.0009627387,0.0006254283,0.14682396,0.005368238,0.036642022,0.80688745],"study_design_scores_gemma":[0.002100797,0.0015345226,0.0013892512,0.0005569956,0.00010123083,0.0002431892,0.007583724,0.04123869,0.06843687,0.02420325,0.8519102,0.00070131605],"about_ca_topic_score_codex":0.0003160688,"about_ca_topic_score_gemma":0.000016804448,"teacher_disagreement_score":0.81526816,"about_ca_system_score_codex":0.0006572257,"about_ca_system_score_gemma":0.00078020536,"threshold_uncertainty_score":0.67841154},"labels":[],"label_agreement":null},{"id":"W4293148110","doi":"10.1055/s-0042-1746471","title":"PET/CT radiomics potentially improves progression-free survival (PFS) and overall survival (OS) prognostication beyond UICC TNM staging in oropharyngeal squamous cell carcinoma (OPSCC) patients","year":2022,"lang":"en","type":"article","venue":"Laryngo-Rhino-Otologie","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre","funders":"","keywords":"Radiomics; Medicine; Stage (stratigraphy); Radiology; Overall survival; Progression-free survival; Head and neck squamous-cell carcinoma; Oncology; PET-CT; Internal medicine; Nuclear medicine; Head and neck cancer; Radiation therapy; Positron emission tomography","score_opus":0.01021151053313887,"score_gpt":0.2620116976425053,"score_spread":0.25180018710936647,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293148110","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99021256,0.0011125111,0.00018801588,0.0029678082,0.0014484843,0.0019064832,0.000108019274,0.00023675343,0.0018193471],"genre_scores_gemma":[0.993421,0.00012285188,0.004021372,0.00086242036,0.00024710177,0.00023793482,0.0006640001,0.00012217624,0.0003011086],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9949475,0.0005820105,0.00092471304,0.0011723017,0.0012705653,0.0011028936],"domain_scores_gemma":[0.9974576,0.00058892573,0.0004189628,0.00091088534,0.0001607626,0.00046282605],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0014293749,0.00056886434,0.0009736995,0.00041372626,0.0005285831,0.00013675232,0.0007389692,0.00007151433,0.00014869672],"category_scores_gemma":[0.0015505226,0.0005318521,0.00018776231,0.0004449727,0.0002806333,0.00031025542,0.0011593349,0.0016953092,0.0000074961717],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008499192,0.001414596,0.9656608,0.000523353,0.000056207078,0.0032003962,0.00050427235,0.0001627157,0.0054817703,0.00041413432,0.0014145642,0.02031725],"study_design_scores_gemma":[0.01984631,0.0024802983,0.9319145,0.000117980744,0.0003860288,0.00066900987,0.0007293875,0.03580323,0.0010930189,0.0012541537,0.004430184,0.0012759055],"about_ca_topic_score_codex":0.0008508911,"about_ca_topic_score_gemma":0.00004750284,"teacher_disagreement_score":0.03564051,"about_ca_system_score_codex":0.0004181613,"about_ca_system_score_gemma":0.0004169855,"threshold_uncertainty_score":0.9997133},"labels":[],"label_agreement":null},{"id":"W4293195708","doi":"10.21608/mjeer.2022.218823","title":"Using X-ray Image Processing Techniques to Improve Pneumonia Diagnosis based on Machine Learning Algorithms","year":2022,"lang":"en","type":"article","venue":"Menoufia Journal of Electronic Engineering Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institute for Advanced Research","keywords":"Computer science; Image processing; Artificial intelligence; Pneumonia; Algorithm; Image (mathematics); Machine learning; Computer vision; Medicine; Internal medicine","score_opus":0.019350474548745944,"score_gpt":0.34977696398635516,"score_spread":0.3304264894376092,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293195708","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.78002125,0.005141946,0.19745226,0.014203905,0.0005085787,0.0016825225,0.000011005607,0.00032972835,0.0006487761],"genre_scores_gemma":[0.9603213,0.00010287519,0.03846973,0.0002865931,0.00043463902,0.00008824062,0.00000557419,0.0001244664,0.000166577],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99596864,0.00027721032,0.00055050413,0.00034140513,0.0017525738,0.0011096771],"domain_scores_gemma":[0.99839526,0.00039406374,0.00017800076,0.00024790416,0.00038499065,0.00039979577],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.006064391,0.00024215205,0.00049922266,0.0014293937,0.00052029174,0.00010805869,0.00040981162,0.000060060527,0.0001396928],"category_scores_gemma":[0.0016168668,0.00022066578,0.00015678126,0.0011452693,0.00005194456,0.000118280186,0.00017230633,0.00544201,0.0000027069136],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004815922,0.0005231275,0.0014292966,0.00030744498,0.00012629903,0.0007320269,0.00042903665,0.2985204,0.60092896,0.000066749766,0.00027863574,0.09617641],"study_design_scores_gemma":[0.0011323873,0.0059931627,0.0002613398,0.000487407,0.0000638177,0.00042877425,0.00009956235,0.9334734,0.019734552,0.000032228603,0.038035564,0.00025777836],"about_ca_topic_score_codex":0.000052772935,"about_ca_topic_score_gemma":4.0474123e-7,"teacher_disagreement_score":0.634953,"about_ca_system_score_codex":0.0017474106,"about_ca_system_score_gemma":0.0008812117,"threshold_uncertainty_score":0.99685246},"labels":[],"label_agreement":null},{"id":"W4293213030","doi":"10.3390/biomedicines10092075","title":"Associations of Texture Features of Proton Density Fat Fraction Maps between Lumbar Vertebral Bone Marrow and Paraspinal Musculature","year":2022,"lang":"en","type":"article","venue":"Biomedicines","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Saint Mary's University","funders":"","keywords":"Medicine; Lumbar; Kurtosis; Texture (cosmology); Magnetic resonance imaging; Logistic regression; Anatomy; Nuclear medicine; Radiology; Internal medicine; Mathematics","score_opus":0.012476584142922971,"score_gpt":0.2913221956485938,"score_spread":0.27884561150567083,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293213030","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99156445,0.0015420149,0.00020464366,0.005621922,0.00021995525,0.0005328791,0.000070832044,0.00003456925,0.00020876032],"genre_scores_gemma":[0.9979586,0.00005839144,0.0006578622,0.0003084153,0.00042747246,0.000022076147,0.0003512176,0.000016464795,0.00019949458],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99867123,0.000087779445,0.00031518607,0.00021222445,0.0005448291,0.00016876851],"domain_scores_gemma":[0.9992735,0.0000629515,0.00027278624,0.00017639276,0.000099293386,0.00011510208],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041770976,0.00013283019,0.0005098413,0.00021610058,0.00015281522,0.0000052616606,0.00007131907,0.00009921142,0.000057181867],"category_scores_gemma":[0.00035410016,0.00010483823,0.00009038717,0.00034492658,0.00018962038,0.000045335528,0.000074355994,0.00055936567,4.200499e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010200358,0.00016976502,0.86145175,0.00050119753,0.00023428813,0.00003721284,0.00060823665,0.0000044956673,0.0986482,0.00014128366,0.014689452,0.023412146],"study_design_scores_gemma":[0.0014550453,0.00048743538,0.9894456,0.00012413609,0.0002891513,0.00009103274,0.00028850773,0.0002158876,0.0013696977,0.00028760295,0.005848548,0.00009733115],"about_ca_topic_score_codex":0.00032167253,"about_ca_topic_score_gemma":0.000005112874,"teacher_disagreement_score":0.12799391,"about_ca_system_score_codex":0.0000621947,"about_ca_system_score_gemma":0.00005674709,"threshold_uncertainty_score":0.4275179},"labels":[],"label_agreement":null},{"id":"W4293216290","doi":"10.1002/jum.16086","title":"Tumor Microenvironment, Radiology, and Artificial Intelligence: Should We Consider Tumor Periphery?","year":2022,"lang":"en","type":"article","venue":"Journal of Ultrasound in Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier de l’Université de Montréal","funders":"","keywords":"Medicine; Contouring; Lymph node; Malignancy; Radiology; Receiver operating characteristic; Radiomics; Breast cancer; Lymph; Breast tumor; Medical imaging; Pathology; Cancer; Computer science; Internal medicine","score_opus":0.03272608251244951,"score_gpt":0.32152600743359594,"score_spread":0.2887999249211464,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293216290","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9426585,0.0095329955,0.0015388973,0.044481896,0.0009837184,0.0002381593,0.000003931782,0.0000126003315,0.00054929976],"genre_scores_gemma":[0.9863224,0.0020867602,0.00279109,0.00775397,0.0008541155,0.0000073678507,0.0000062744816,0.00003167345,0.000146341],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.997558,0.00024948822,0.0010185149,0.0002443683,0.0005979253,0.00033170416],"domain_scores_gemma":[0.9981897,0.00085137115,0.0004460321,0.00017814491,0.00004799135,0.00028677282],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0022932594,0.00020299859,0.0007798815,0.0003647637,0.00015349638,0.000014433938,0.0001794941,0.00004034505,0.0028842897],"category_scores_gemma":[0.0023235206,0.00015130364,0.00009552714,0.00025623236,0.0007455204,0.00007455358,0.00006786829,0.0018287948,0.0000034008906],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003100633,0.0017094673,0.2668962,0.0005062898,0.0006814219,0.013421552,0.012867539,0.0025643052,0.47607067,0.0033093588,0.117582195,0.10129037],"study_design_scores_gemma":[0.00912355,0.010905824,0.08832884,0.0017190574,0.0010643384,0.26614922,0.05235157,0.0058806245,0.002416632,0.023751738,0.53730625,0.0010023527],"about_ca_topic_score_codex":0.00004752489,"about_ca_topic_score_gemma":0.0000028249738,"teacher_disagreement_score":0.47365406,"about_ca_system_score_codex":0.0002188669,"about_ca_system_score_gemma":0.00013932888,"threshold_uncertainty_score":0.9980272},"labels":[],"label_agreement":null},{"id":"W4293225645","doi":"10.21203/rs.3.rs-1340117/v1","title":"Combination of FDG PET/CT Radiomics and Clinical Parameters for Outcome Prediction in Patients with Hodgkin’s Lymphoma","year":2022,"lang":"en","type":"preprint","venue":"Research Square","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; Health Sciences Centre; University of Toronto; Sunnybrook Health Science Centre","funders":"","keywords":"Radiomics; Medicine; Lymphoma; Hodgkin lymphoma; Positron emission tomography; Radiology; Nuclear medicine; Medical physics; Internal medicine","score_opus":0.058180837147521425,"score_gpt":0.4308830362879806,"score_spread":0.37270219914045916,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293225645","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99537295,0.00011581418,0.0004366645,0.00087598176,0.00032738177,0.0025513812,0.0001384016,0.000029860414,0.00015156543],"genre_scores_gemma":[0.9948068,0.00016583712,0.0036300113,0.00006021507,0.000059031085,0.00022652734,0.0008470163,0.000054145607,0.00015038629],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9965653,0.00054188556,0.00077193626,0.00059200183,0.0011411217,0.0003877804],"domain_scores_gemma":[0.9976315,0.0010866848,0.00023237619,0.00045833146,0.00037647318,0.0002146631],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0042743506,0.00019088607,0.0006929209,0.0006388871,0.000113665985,0.000040185867,0.00019949308,0.00006152434,0.00003282332],"category_scores_gemma":[0.0029461265,0.00016381954,0.00015409158,0.0002723441,0.0003397929,0.000052439045,0.000415303,0.0015985379,7.495558e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011193738,0.00084242184,0.97514206,0.0014872443,0.000119384604,0.00006140971,0.00009577756,0.0002623327,0.000001604791,0.000121582416,0.00036896794,0.020377822],"study_design_scores_gemma":[0.009830672,0.0025042046,0.9427765,0.0006592135,0.00008174471,0.00001971517,0.0001909751,0.042598113,0.000003804475,0.00041910305,0.0007804855,0.00013547002],"about_ca_topic_score_codex":0.00033117502,"about_ca_topic_score_gemma":0.000008807949,"teacher_disagreement_score":0.04233578,"about_ca_system_score_codex":0.00048666145,"about_ca_system_score_gemma":0.0003730534,"threshold_uncertainty_score":0.69449407},"labels":[],"label_agreement":null},{"id":"W4293242817","doi":"10.21203/rs.3.rs-1975379/v1","title":"Prognostic Value of [18F]-FDG PET/CT Radiomics combined with Sarcopenia Status among Patients with Advanced Gastroesophageal Cancer","year":2022,"lang":"en","type":"preprint","venue":"Research Square","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Radiomics; Sarcopenia; Medicine; Cancer; Internal medicine; Radiology; Value (mathematics); Oncology; Statistics; Mathematics","score_opus":0.013835063654797988,"score_gpt":0.3479037019784545,"score_spread":0.3340686383236565,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293242817","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99271643,0.00088586274,0.0001689202,0.0005450486,0.000222387,0.0043745213,0.00032817762,0.00009861381,0.00066002284],"genre_scores_gemma":[0.991215,0.0005338595,0.0051093865,0.00006775647,0.00012053536,0.00090680463,0.0013335502,0.00020639511,0.0005067197],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9929551,0.0006908562,0.00062343536,0.0010744475,0.003281801,0.0013743575],"domain_scores_gemma":[0.9960976,0.0005455549,0.00042535673,0.0010747424,0.0010638251,0.0007929116],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0012715986,0.000524074,0.0011805193,0.0006561354,0.00033167785,0.000094410534,0.0005978109,0.00004193468,0.0006512908],"category_scores_gemma":[0.0010647723,0.00039136157,0.00017026643,0.00079967885,0.0008883189,0.000116270865,0.0010236974,0.005038153,0.000004118927],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003793276,0.0007783085,0.96964407,0.0030577763,0.00046379436,0.0022496216,0.0003329369,0.014355641,0.00002549589,0.00007512013,0.00052155164,0.004702383],"study_design_scores_gemma":[0.010101396,0.0061758794,0.96152544,0.0048836893,0.0003029548,0.00007446726,0.00047584917,0.0148184495,0.000070580994,0.00007459484,0.0010439665,0.00045273718],"about_ca_topic_score_codex":0.0018439793,"about_ca_topic_score_gemma":0.00007233943,"teacher_disagreement_score":0.008118659,"about_ca_system_score_codex":0.0009574289,"about_ca_system_score_gemma":0.002411476,"threshold_uncertainty_score":0.99985385},"labels":[],"label_agreement":null},{"id":"W4293659595","doi":"10.3390/cancers14174150","title":"Lung Cancer Recurrence Risk Prediction through Integrated Deep Learning Evaluation","year":2022,"lang":"en","type":"article","venue":"Cancers","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Cancer Institute","keywords":"Medicine; Stage (stratigraphy); Lung cancer; TNM staging system; Risk stratification; Lung; Radiology; Internal medicine; Oncology; Receiver operating characteristic; Cancer; Neoplasm staging","score_opus":0.016889479717872292,"score_gpt":0.33807506791085057,"score_spread":0.32118558819297827,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293659595","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95245886,0.0137544945,0.020684266,0.0016318128,0.0034417147,0.00094100734,0.000045348082,0.0002783575,0.0067641316],"genre_scores_gemma":[0.9953969,0.001785183,0.00073475845,0.00059716275,0.00031886296,0.00043042883,0.00018424219,0.000028998744,0.00052343233],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983394,0.00029481135,0.00021909304,0.000313151,0.0005992252,0.00023430631],"domain_scores_gemma":[0.9993929,0.000059441754,0.00017043808,0.00015123514,0.00013456073,0.00009139013],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00093716354,0.00011782459,0.00018085937,0.00007480624,0.00046261965,0.000018082164,0.00009227434,0.00003615774,0.0022557902],"category_scores_gemma":[0.0006794891,0.00011228861,0.00006466578,0.0004230988,0.0000688725,0.000096235715,0.00004652854,0.0012622068,0.0000033381734],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016164231,0.000017459839,0.13375024,0.000054939806,0.00013926215,0.000010640192,0.0031775667,0.5020877,0.0005720949,0.00005170393,0.01260252,0.34737423],"study_design_scores_gemma":[0.0011668721,0.0001434436,0.0076398547,0.00009210859,0.00029583566,0.000025468082,0.0010042996,0.9167918,0.000054070206,0.00007627507,0.072603986,0.00010596289],"about_ca_topic_score_codex":0.0030551802,"about_ca_topic_score_gemma":0.000028706349,"teacher_disagreement_score":0.4147041,"about_ca_system_score_codex":0.0037422671,"about_ca_system_score_gemma":0.0008632621,"threshold_uncertainty_score":0.9986563},"labels":[],"label_agreement":null},{"id":"W4294085647","doi":"10.1038/s41598-022-18994-z","title":"High-dimensional multinomial multiclass severity scoring of COVID-19 pneumonia using CT radiomics features and machine learning algorithms","year":2022,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Coronavirus disease 2019 (COVID-19); Radiomics; Pneumonia; 2019-20 coronavirus outbreak; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Computer science; Artificial intelligence; Multinomial distribution; Machine learning; Algorithm; Medicine; Pathology; Mathematics; Internal medicine; Statistics; Disease","score_opus":0.020902288552456797,"score_gpt":0.2936704474289249,"score_spread":0.2727681588764681,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4294085647","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9929659,0.00061231456,0.0010214471,0.0007935544,0.004132497,0.00034786478,0.000010754274,0.00008531335,0.00003035485],"genre_scores_gemma":[0.98009646,0.000008420853,0.01850487,0.00022493888,0.0001335488,0.000009524294,0.00012642446,0.000036398567,0.000859411],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99697834,0.00020195992,0.0006369068,0.0008429795,0.0009490398,0.00039074407],"domain_scores_gemma":[0.9983351,0.0001495574,0.0005134455,0.00044431415,0.00009561961,0.0004619592],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032474818,0.00021369504,0.0004930469,0.0003427527,0.0012154845,0.00009481169,0.000112838476,0.000039483326,0.00012988286],"category_scores_gemma":[0.0016176535,0.00020325242,0.00012889231,0.00044334558,0.0004984741,0.00010200343,0.00041413508,0.0009417864,5.7174924e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002969102,0.00046892313,0.22783206,0.0004889194,0.00022027676,0.009676587,0.0020599535,0.179993,0.54970527,0.000068704394,0.0020745147,0.027114894],"study_design_scores_gemma":[0.0027457473,0.00017654612,0.014805922,0.00010557138,0.00023651854,0.035052024,0.00038399707,0.9143893,0.0097182365,0.0005253394,0.021363646,0.0004971599],"about_ca_topic_score_codex":0.0018103438,"about_ca_topic_score_gemma":0.000009358143,"teacher_disagreement_score":0.7343963,"about_ca_system_score_codex":0.00030601505,"about_ca_system_score_gemma":0.00054494763,"threshold_uncertainty_score":0.9348647},"labels":[],"label_agreement":null},{"id":"W4294385376","doi":"10.5194/essd-2022-261-cc1","title":"Comment on essd-2022-261","year":2022,"lang":"en","type":"peer-review","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Memorial University of Newfoundland","funders":"","keywords":"Ice sheet; Ice stream; Antarctic ice sheet; Future sea level; Greenland ice sheet; Glacier mass balance; Geology; Sea ice; Climatology; Cryosphere; Ice core; Oceanography; Glacier; Geomorphology","score_opus":0.025318700481783557,"score_gpt":0.35502865081401935,"score_spread":0.3297099503322358,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4294385376","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000003706698,0.018378707,0.000127212,0.7314407,0.003538821,0.0005992902,0.000045027075,0.00012677483,0.24573973],"genre_scores_gemma":[0.000012978265,0.01488215,0.000530637,0.46654618,0.00073824544,0.00010129973,0.0022578086,0.00007041962,0.5148603],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99730223,0.00014123978,0.0004679671,0.0005322943,0.0011913676,0.0003648953],"domain_scores_gemma":[0.9984807,0.00021433995,0.00018159718,0.00076092995,0.00007063764,0.00029180813],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0010089302,0.00035496725,0.0010053582,0.0001805204,0.00014547042,0.000022221184,0.0003072913,0.00013157382,0.060566634],"category_scores_gemma":[0.0006769317,0.00027054976,0.00034732174,0.00020941085,0.000062713196,0.000013051437,0.00024902675,0.0028314623,0.00028746374],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014946177,0.00016892249,0.000019311832,0.002380538,0.00012280354,0.00019432927,0.000012855701,0.0000026741977,0.0000019185106,0.0007910288,0.9521196,0.044171087],"study_design_scores_gemma":[0.0006947423,0.0003280562,0.000017229539,0.0035662195,0.00038854103,0.00009806926,0.000012967264,0.0004012349,0.0000028973095,0.000054263106,0.9941767,0.0002590728],"about_ca_topic_score_codex":0.0002484024,"about_ca_topic_score_gemma":0.0000023497676,"teacher_disagreement_score":0.26912057,"about_ca_system_score_codex":0.00029805332,"about_ca_system_score_gemma":0.00023652351,"threshold_uncertainty_score":0.99997467},"labels":[],"label_agreement":null},{"id":"W4294636828","doi":"10.1177/08465371221125448","title":"CARJ Editor’s Award 2022","year":2022,"lang":"en","type":"editorial","venue":"Canadian Association of Radiologists Journal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; McGill University Health Centre","funders":"","keywords":"Medicine; Medical physics","score_opus":0.005725318117597947,"score_gpt":0.2701817489567926,"score_spread":0.2644564308391946,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4294636828","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00044415944,0.0013249237,0.00005619371,0.0077187503,0.9860926,0.00019497657,0.00044134018,0.000031185587,0.0036958219],"genre_scores_gemma":[0.0009396682,0.0020771315,0.0003487267,0.0005707456,0.9802608,0.000013526469,0.0009943694,0.00007726174,0.014717779],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99582416,0.00046448593,0.0008285341,0.00036112437,0.0017885492,0.0007331222],"domain_scores_gemma":[0.99529684,0.0009920025,0.0015526948,0.00031344895,0.00076685875,0.0010781545],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0040285685,0.0003070604,0.0010347151,0.0007496676,0.00042451092,0.00007796676,0.00047742872,0.0010295791,0.0017071142],"category_scores_gemma":[0.022638706,0.00030211353,0.0004630073,0.00029474404,0.00010926191,0.000071939445,0.000051489973,0.0062018135,0.000017213617],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000027584645,0.000020993002,0.009100391,0.000056101762,0.0004138816,0.00034833077,0.000112286,0.000057767535,0.0000119381975,0.000016295604,0.9882309,0.0016035672],"study_design_scores_gemma":[0.0012566246,0.00026921602,0.0014095005,0.00009541077,0.0002878218,0.00018454618,0.00010823942,0.00010489398,9.953171e-7,0.00007709907,0.99596214,0.00024351101],"about_ca_topic_score_codex":0.010841451,"about_ca_topic_score_gemma":0.0030800875,"teacher_disagreement_score":0.018610138,"about_ca_system_score_codex":0.01049735,"about_ca_system_score_gemma":0.009715884,"threshold_uncertainty_score":0.9999431},"labels":[],"label_agreement":null},{"id":"W4294699201","doi":"10.1007/978-3-319-66182-7","title":"Medical Image Computing and Computer Assisted Intervention − MICCAI 2017","year":2017,"lang":"en","type":"book","venue":"Lecture notes in computer science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":22,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; McGill University; Université de Sherbrooke","funders":"","keywords":"Computer science; Set (abstract data type); Volume (thermodynamics); Multimedia; Programming language","score_opus":0.013530093645760499,"score_gpt":0.3250767243462824,"score_spread":0.31154663070052185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4294699201","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003465871,0.0007253461,0.9876166,0.0032240814,0.002286962,0.00035815127,0.0000027850394,0.000103539955,0.0022166832],"genre_scores_gemma":[0.27075645,0.00030773925,0.70670164,0.009877998,0.009017041,0.000009826006,0.00018423909,0.00018351898,0.0029615464],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99630475,0.00008954161,0.00060593657,0.0011554371,0.001235605,0.0006087027],"domain_scores_gemma":[0.99757636,0.00047906803,0.0004364714,0.0008333426,0.0002006743,0.00047409284],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0022822744,0.00044012058,0.0008616109,0.00054688717,0.00042321117,0.0005175446,0.0010437913,0.0004424028,0.000048216163],"category_scores_gemma":[0.0010326889,0.00037085544,0.00018367631,0.00016927494,0.0021218616,0.00020466125,0.001131726,0.0022353004,0.000019579606],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018041274,0.00007640706,0.0010416198,0.0003393278,0.000035100365,0.00083367655,0.00028596338,0.00013169642,0.00008297219,0.000043558237,0.001730576,0.99538106],"study_design_scores_gemma":[0.0017497606,0.00027927908,0.012162779,0.0057057333,0.00006232981,0.0020831758,2.9912232e-7,0.97127247,0.000051277555,0.0018596784,0.00431397,0.0004592685],"about_ca_topic_score_codex":0.00006399525,"about_ca_topic_score_gemma":0.000023136634,"teacher_disagreement_score":0.9949218,"about_ca_system_score_codex":0.00029244728,"about_ca_system_score_gemma":0.0008508462,"threshold_uncertainty_score":0.99987435},"labels":[],"label_agreement":null},{"id":"W4294795930","doi":"10.1093/noajnl/vdac141","title":"Radiomics as an emerging tool in the management of brain metastases","year":2022,"lang":"en","type":"review","venue":"Neuro-Oncology Advances","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Montreal Neurological Institute and Hospital; University of Calgary; McGill University Health Centre; McGill University","funders":"Canadian Cancer Society Research Institute; Canadian Institutes of Health Research; Health Canada; Government of Canada; Fondation Brain Canada","keywords":"Radiomics; Medicine; Magnetic resonance imaging; Radiogenomics; Radiation therapy; Radiology; Medical imaging","score_opus":0.04012343667068052,"score_gpt":0.41197676277928097,"score_spread":0.37185332610860045,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4294795930","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00045179363,0.9923899,0.00008110302,0.0015925341,0.00071252737,0.0011560887,0.000014359772,0.000037583304,0.0035641165],"genre_scores_gemma":[0.000043007723,0.9937179,0.002648634,0.0028666214,0.00016992269,0.0002744374,0.00014389738,0.00005466652,0.00008087829],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9965958,0.0012229792,0.00083255745,0.000550181,0.00043561825,0.00036287808],"domain_scores_gemma":[0.99706316,0.0017523735,0.00052386825,0.0005803656,0.000015637672,0.00006456993],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017776319,0.0003425664,0.001673274,0.00033953233,0.00012337472,0.000013938434,0.00062600814,0.00011282939,0.00031120275],"category_scores_gemma":[0.0005099888,0.00023450384,0.000323353,0.0006103826,0.00021987062,0.000113189555,0.00017604526,0.0014714263,0.0000069063954],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037966805,0.00023527227,0.000017702405,0.00675204,0.00014213866,0.0017542533,0.00017480475,0.000049131835,0.000004914163,0.0022925057,0.0004262622,0.988113],"study_design_scores_gemma":[0.0007060049,0.0006318653,0.000007823773,0.00096991466,0.0011173752,0.0011152951,0.00049946323,0.00008922951,9.957558e-7,0.00033538023,0.99434805,0.00017863116],"about_ca_topic_score_codex":0.000012769573,"about_ca_topic_score_gemma":0.0000035458256,"teacher_disagreement_score":0.99392176,"about_ca_system_score_codex":0.00013836207,"about_ca_system_score_gemma":0.00024392556,"threshold_uncertainty_score":0.9562789},"labels":[],"label_agreement":null},{"id":"W4295747953","doi":"10.1007/978-3-031-16876-5","title":"Resource-Efficient Medical Image Analysis","year":2022,"lang":"en","type":"book","venue":"Lecture notes in computer science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Medical imaging; Resource (disambiguation); Image (mathematics); Image processing; Computer vision; Artificial intelligence; Data science; Computer network","score_opus":0.007137007011840505,"score_gpt":0.28133520751129265,"score_spread":0.27419820049945215,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4295747953","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001048609,0.0005136137,0.9787501,0.0065103094,0.00071369566,0.00029116313,0.0000053503663,0.00011283535,0.012054301],"genre_scores_gemma":[0.28162217,0.0003361661,0.59236574,0.086961105,0.010591728,0.00013566285,0.0011234031,0.00052418787,0.026339805],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9945414,0.000106220396,0.00053953304,0.001202785,0.0029568858,0.000653198],"domain_scores_gemma":[0.99761397,0.000658133,0.00019655557,0.00092577346,0.00010111879,0.00050445396],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0026994792,0.00035735808,0.0008846146,0.0017338045,0.00028356994,0.00012784736,0.0011789469,0.0002482942,0.001817392],"category_scores_gemma":[0.0013880252,0.00029818833,0.00034675872,0.002594593,0.0012541246,0.00003796166,0.0009764474,0.0029323047,0.000021085301],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000053296342,0.00029043452,0.0015987656,0.0002001289,0.0003623309,0.0033093758,0.0013198752,0.23385112,0.000086915235,0.00025252072,0.00448977,0.75418544],"study_design_scores_gemma":[0.0004889886,0.00013524805,0.0006467588,0.00021550045,0.00029527888,0.00023811523,6.3301604e-7,0.9538311,0.000025673426,0.00073721755,0.043065026,0.00032050474],"about_ca_topic_score_codex":0.000036096673,"about_ca_topic_score_gemma":0.000009473777,"teacher_disagreement_score":0.75386494,"about_ca_system_score_codex":0.00077353156,"about_ca_system_score_gemma":0.0021087443,"threshold_uncertainty_score":0.999947},"labels":[],"label_agreement":null},{"id":"W4295776058","doi":"10.1200/cci.22.00014","title":"Natural Language Processing of Computed Tomography Reports to Label Metastatic Phenotypes With Prognostic Significance in Patients With Colorectal Cancer","year":2022,"lang":"en","type":"article","venue":"JCO Clinical Cancer Informatics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"National Cancer Institute","keywords":"Medicine; Pelvis; Radiology; Metastasis; Colorectal cancer; Abdomen; Proportional hazards model; Hazard ratio; Thorax (insect anatomy); Cancer; Retrospective cohort study; Cancer staging; Internal medicine; Confidence interval","score_opus":0.013926613170619566,"score_gpt":0.3387138888290905,"score_spread":0.32478727565847093,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4295776058","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99709105,0.00047373326,0.0005104306,0.00038704352,0.0002680153,0.0010749173,0.000025379424,0.00004561922,0.00012381052],"genre_scores_gemma":[0.9794129,0.0000074977447,0.018497804,0.0016909462,0.00005060708,0.00022347401,0.000059586328,0.000027069214,0.000030103038],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9976141,0.00007242986,0.0010478356,0.00020439096,0.0007558363,0.0003054445],"domain_scores_gemma":[0.9985502,0.00021785167,0.00063258124,0.00018568827,0.0002357385,0.00017797],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00063094235,0.00018139326,0.00060651347,0.00018473042,0.00008837542,0.000022911117,0.00013840261,0.000030908002,0.0000412611],"category_scores_gemma":[0.0003210754,0.00012626321,0.000055148357,0.00094532804,0.00016674271,0.00012516048,0.00009289959,0.00081071263,4.7710506e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001235005,0.00048795712,0.92551756,0.0005452085,0.000122047546,0.000056605673,0.0030162365,0.00604426,0.000013814752,0.000004213931,0.00027163734,0.06268544],"study_design_scores_gemma":[0.006759981,0.0028862646,0.91026664,0.0011120506,0.00037216456,0.000029157636,0.0013932603,0.075799145,0.00007199997,0.000009947647,0.0009053377,0.0003940723],"about_ca_topic_score_codex":0.00026235264,"about_ca_topic_score_gemma":0.00010964034,"teacher_disagreement_score":0.06975488,"about_ca_system_score_codex":0.000119579665,"about_ca_system_score_gemma":0.0005392169,"threshold_uncertainty_score":0.51488644},"labels":[],"label_agreement":null},{"id":"W4295793620","doi":"10.1007/978-3-031-16431-6_9","title":"Feature Robustness and Sex Differences in Medical Imaging: A Case Study in MRI-Based Alzheimer’s Disease Detection","year":2022,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":33,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research; University of California, Los Angeles; University of California, San Diego; National Institutes of Health; Northern California Institute for Research and Education","keywords":"Computer science; Robustness (evolution); Artificial intelligence; Convolutional neural network; Logistic regression; Pattern recognition (psychology); Spurious relationship; Feature selection; Machine learning; Medical imaging; Regression; Training set; Statistics","score_opus":0.018122556531423632,"score_gpt":0.2913809454110273,"score_spread":0.2732583888796037,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4295793620","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31731257,0.004618712,0.6582628,0.015762908,0.0015881952,0.0021181062,0.0000072088346,0.00013541807,0.00019411845],"genre_scores_gemma":[0.99449176,0.00004279929,0.0036133307,0.0015106384,0.00023259477,0.00003448522,0.0000073833417,0.000036001922,0.000031035073],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967026,0.00012641553,0.00037691285,0.0011421539,0.00120497,0.00044694604],"domain_scores_gemma":[0.9984583,0.00050608744,0.00013207205,0.00044710175,0.00004478259,0.00041162985],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0013625519,0.00039834477,0.0006461634,0.001108663,0.00019202454,0.00011355459,0.0004125941,0.00015598013,0.00007470484],"category_scores_gemma":[0.0003675786,0.0003345593,0.0000653062,0.00050483405,0.00072765443,0.00011205846,0.00039135496,0.0026342254,4.28809e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008830903,0.00028255928,0.15984787,0.000099753204,0.00001946044,0.05972493,0.0011857026,0.016889572,0.0000073579017,0.000017109836,0.000007022238,0.76183033],"study_design_scores_gemma":[0.0017259315,0.00019059483,0.013586476,0.0005286696,0.00006469391,0.0020255917,0.000014077571,0.9809759,0.0000052218425,0.00034764365,0.00018068973,0.00035447354],"about_ca_topic_score_codex":0.0004767076,"about_ca_topic_score_gemma":0.00091638917,"teacher_disagreement_score":0.96408635,"about_ca_system_score_codex":0.00024304361,"about_ca_system_score_gemma":0.0007093447,"threshold_uncertainty_score":0.99991065},"labels":[],"label_agreement":null},{"id":"W4295873038","doi":"10.1109/jbhi.2022.3195561","title":"Guest Editorial Artificial Intelligence in Pre-DICOM","year":2022,"lang":"en","type":"editorial","venue":"IEEE Journal of Biomedical and Health Informatics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"DICOM; Computer science; Workflow; Medical imaging; Image processing; Artificial intelligence; Computer vision; Database; Image (mathematics)","score_opus":0.02249628013211143,"score_gpt":0.36507766530839325,"score_spread":0.34258138517628184,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4295873038","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00049095484,0.00094341696,0.0027330373,0.0061862688,0.98923874,0.00027519328,0.000046316898,0.000017111288,0.00006896511],"genre_scores_gemma":[0.0002511774,0.0064342185,0.0029055842,0.0007282994,0.9894725,0.0000062437844,0.00012377276,0.000032560994,0.000045619465],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9927823,0.0001257695,0.003592637,0.00014916706,0.0028109415,0.0005391784],"domain_scores_gemma":[0.99590683,0.0006673213,0.0019788442,0.00020346438,0.00027515486,0.0009683729],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.005209164,0.00030019574,0.0013175497,0.0008140316,0.00016900597,0.0000726485,0.00035441737,0.00065517955,0.00008953794],"category_scores_gemma":[0.0023436416,0.00023302193,0.00017188577,0.00039871485,0.00033563768,0.00016458746,0.00012124581,0.0063620005,0.000005226878],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024223396,0.00024841755,0.000031723936,0.0015658581,0.00005483518,0.00010119192,0.0020793423,0.000013200107,0.00000197765,0.000020704092,0.93552357,0.060116973],"study_design_scores_gemma":[0.00095624465,0.0023266198,0.000027316923,0.0017783782,0.00006954853,0.0002122357,0.00041325376,0.0030839983,0.0000016129873,0.0004423205,0.9905053,0.00018317872],"about_ca_topic_score_codex":0.00016712345,"about_ca_topic_score_gemma":0.000008345723,"teacher_disagreement_score":0.059933793,"about_ca_system_score_codex":0.00047557612,"about_ca_system_score_gemma":0.0034581684,"threshold_uncertainty_score":0.9959304},"labels":[],"label_agreement":null},{"id":"W4295915720","doi":"10.1007/978-3-031-16452-1_47","title":"CRISP - Reliable Uncertainty Estimation for Medical Image Segmentation","year":2022,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Segmentation; Computer science; Artificial intelligence; Probabilistic logic; Pixel; Image (mathematics); Image segmentation; Pattern recognition (psychology); Estimation; Machine learning","score_opus":0.01105213752361479,"score_gpt":0.3077883532308969,"score_spread":0.29673621570728215,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4295915720","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00020345255,0.00017689068,0.98836994,0.0071166586,0.0011521059,0.00062998245,0.0000067604833,0.00007458704,0.002269625],"genre_scores_gemma":[0.019210927,0.0001409564,0.9683827,0.009592428,0.0010586154,0.0000736667,0.00033314258,0.000085870066,0.0011216727],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99728644,0.000017429189,0.000412562,0.00069715397,0.0012299911,0.0003564176],"domain_scores_gemma":[0.99865156,0.0004565221,0.00017606397,0.00036918945,0.00013647077,0.00021016122],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014552776,0.0002485637,0.0004024567,0.00037946156,0.00025995827,0.00009256535,0.000414435,0.0001740481,0.0006585421],"category_scores_gemma":[0.00097623706,0.00021848641,0.00010946139,0.00019513212,0.0004699465,0.0001475863,0.00022371404,0.0010552295,0.000009022807],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000055823806,0.000041580326,0.00006649995,0.00022242208,0.000019279238,0.00010756777,0.00032588368,0.07671959,0.0002947651,0.0023028294,0.00071208895,0.9191317],"study_design_scores_gemma":[0.0008199749,0.00025373112,0.00003366311,0.00036740204,0.000038858845,0.00013108876,4.6061263e-7,0.9666054,0.00016877317,0.022373209,0.00898972,0.00021771176],"about_ca_topic_score_codex":0.00006449469,"about_ca_topic_score_gemma":0.000007864409,"teacher_disagreement_score":0.91891396,"about_ca_system_score_codex":0.00045800925,"about_ca_system_score_gemma":0.0007485574,"threshold_uncertainty_score":0.89096177},"labels":[],"label_agreement":null},{"id":"W4295996195","doi":"10.1007/s00261-022-03656-5","title":"Correction: SAR user guide to the rectal MR synoptic report (primary staging)","year":2022,"lang":"en","type":"erratum","venue":"Abdominal Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Medicine; Hepatology; Internal medicine; Primary (astronomy); Medical physics; Radiology; General surgery","score_opus":0.007553801676233853,"score_gpt":0.2919705736386915,"score_spread":0.2844167719624576,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4295996195","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008272134,0.0076006046,0.0066917096,0.088387154,0.3585601,0.0022583131,0.00004090443,0.0005127073,0.5276764],"genre_scores_gemma":[0.0011209756,0.0009965634,0.0036294407,0.02166353,0.013349001,0.00015203965,0.0013780575,0.0002036032,0.9575068],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99581414,0.0004909752,0.0010230389,0.0010947814,0.00075942377,0.00081765285],"domain_scores_gemma":[0.996923,0.00071711,0.0004915037,0.0012965187,0.00016436633,0.0004074802],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002262512,0.0005482125,0.0013766928,0.0003763649,0.0005012112,0.000048217033,0.0006478658,0.00047015015,0.0025610838],"category_scores_gemma":[0.004247137,0.00040872244,0.00042430032,0.00045872794,0.00034046703,0.000045884855,0.0004407337,0.005237899,0.00017670501],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035448594,0.000058095262,0.00068178785,0.00009964432,0.0003406883,0.00805078,0.00025573096,0.00016298897,0.00015365159,0.000035242756,0.9725122,0.017294703],"study_design_scores_gemma":[0.00061993476,0.0006879366,0.0034272035,0.00019270228,0.0005297102,0.05309485,0.00021436639,0.0021530616,0.0000052579658,0.000017005526,0.93867314,0.00038482912],"about_ca_topic_score_codex":0.0005756209,"about_ca_topic_score_gemma":0.00001670598,"teacher_disagreement_score":0.4298304,"about_ca_system_score_codex":0.00090996973,"about_ca_system_score_gemma":0.0012935903,"threshold_uncertainty_score":0.99983644},"labels":[],"label_agreement":null},{"id":"W4296007404","doi":"10.1016/j.phro.2022.09.004","title":"Radiomics artificial intelligence modelling for prediction of local control for colorectal liver metastases treated with radiotherapy","year":2022,"lang":"en","type":"article","venue":"Physics and Imaging in Radiation Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"National Cancer Institute; National Institutes of Health","keywords":"Medicine; Radiomics; Radiation therapy; Random forest; Artificial intelligence; Multivariate analysis; Radiology; Progression-free survival; Overall survival; Oncology; Internal medicine; Computer science","score_opus":0.020672080356171543,"score_gpt":0.30229933827705285,"score_spread":0.28162725792088134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4296007404","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13296688,0.0005794952,0.86448693,0.00093135785,0.00010327877,0.0007513279,0.00014730071,0.000018835522,0.000014582158],"genre_scores_gemma":[0.984208,0.00014482718,0.014665556,0.00030506263,0.00018386633,0.00026778004,0.00019387469,0.00002593422,0.0000050958465],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990557,0.00008233592,0.00031477088,0.00023710278,0.00011971796,0.00019036175],"domain_scores_gemma":[0.99916446,0.0004426546,0.0001795143,0.0000728023,0.000083254745,0.00005730973],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004960217,0.00011297051,0.00036393086,0.00012641193,0.00013230795,0.0000109214025,0.000049205177,0.000027020065,0.000006706325],"category_scores_gemma":[0.000036485177,0.00010605605,0.00006482828,0.00015797371,0.00015588813,0.000073331474,0.000010010129,0.00018136878,5.2350007e-8],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0028332889,0.0004124452,0.008614363,0.00008385704,0.00011560914,0.000007674177,0.0007004047,0.46018288,0.0039804904,0.0073828893,0.00010894809,0.51557714],"study_design_scores_gemma":[0.0029241268,0.0013714513,0.00056762295,0.000015038142,0.00014208161,0.000046707362,0.00030475896,0.98955417,0.0011418582,0.0015094914,0.002335864,0.000086843625],"about_ca_topic_score_codex":0.000079746686,"about_ca_topic_score_gemma":0.00000195522,"teacher_disagreement_score":0.8512411,"about_ca_system_score_codex":0.0002385832,"about_ca_system_score_gemma":0.00015342275,"threshold_uncertainty_score":0.43248403},"labels":[],"label_agreement":null},{"id":"W4296768816","doi":"10.1016/j.jtho.2022.07.140","title":"MA11.07 The ELIC Distributed Database and Computation Environment for Analyses of Lung Cancer Screening LDCTs Across the World","year":2022,"lang":"en","type":"article","venue":"Journal of Thoracic Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Foundation; BC Cancer Agency","funders":"","keywords":"Medicine; Computation; Lung cancer; Database; Internal medicine; Computer science; Programming language","score_opus":0.04923301866737189,"score_gpt":0.4950152684430194,"score_spread":0.4457822497756475,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4296768816","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.84171295,0.0053194724,0.102596946,0.049467504,0.0003739044,0.00037965443,0.00011375546,0.000005197832,0.0000306227],"genre_scores_gemma":[0.99082106,0.00021046016,0.0074615395,0.0011093498,0.00025142665,0.000019584497,0.000035738078,0.000011143282,0.00007971808],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99880207,0.00026120737,0.000400078,0.000098233984,0.00027889735,0.0001595361],"domain_scores_gemma":[0.99840367,0.0007473458,0.0006076116,0.00010918147,0.000059434915,0.00007274382],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018816164,0.00007672226,0.00031204862,0.00006612017,0.00034774432,0.000012744159,0.00014434449,0.000020235495,0.000075893986],"category_scores_gemma":[0.00020915532,0.00004267185,0.00009601212,0.00014112068,0.00019218982,0.000043586828,0.00013772375,0.0005647922,1.2303155e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004465485,0.00047532166,0.03191195,0.00027860334,0.0016152548,0.00019974736,0.002330201,0.1084256,0.016344737,0.000072587056,0.026712812,0.8071677],"study_design_scores_gemma":[0.004667185,0.002445164,0.12447978,0.00035927485,0.0040583746,0.0019266789,0.00498663,0.5064735,0.0016789403,0.00028698245,0.34837636,0.0002611292],"about_ca_topic_score_codex":0.000053645108,"about_ca_topic_score_gemma":0.000011108984,"teacher_disagreement_score":0.8069066,"about_ca_system_score_codex":0.0001349205,"about_ca_system_score_gemma":0.000103643804,"threshold_uncertainty_score":0.26746032},"labels":[],"label_agreement":null},{"id":"W4297415352","doi":"10.5281/zenodo.7115804","title":"ReproVIP: Enhancing Reproducibility of Scientific Results in Medical Imaging","year":2022,"lang":"en","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Agence Nationale de la Recherche","keywords":"Reproducibility; Computer science; Medical physics; Medical imaging; Medicine; Artificial intelligence; Statistics; Mathematics","score_opus":0.013427528846719175,"score_gpt":0.2860361465398409,"score_spread":0.2726086176931217,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297415352","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86864734,0.0022468749,0.0137547655,0.06390161,0.0010234031,0.0009780785,0.000059487353,0.00025218836,0.049136236],"genre_scores_gemma":[0.9746314,0.00025223067,0.018389614,0.00021712182,0.000054446507,0.00006290897,0.0007601785,0.00005971831,0.0055723437],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98765004,0.0056928378,0.0016859724,0.002837096,0.0016260252,0.00050800777],"domain_scores_gemma":[0.9878757,0.0019921644,0.0009667309,0.0072478917,0.0015345361,0.00038300428],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06703273,0.00032505317,0.000802183,0.00056050817,0.00030882252,0.00016949525,0.0011777712,0.00022183696,0.0005497994],"category_scores_gemma":[0.0650955,0.0003405573,0.00030495296,0.0008628554,0.0008006278,0.00009039575,0.0028144908,0.0026819673,0.000007180837],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004516337,0.0057438705,0.2238886,0.003976355,0.00029135097,0.0005398102,0.046003714,0.00059590937,0.037936576,0.013976348,0.0066861487,0.65990967],"study_design_scores_gemma":[0.011853786,0.0000055967207,0.21038842,0.03461813,0.00045212626,0.00048342385,0.00204207,0.4974256,0.14005686,0.0125346705,0.08773723,0.0024020758],"about_ca_topic_score_codex":0.0032421774,"about_ca_topic_score_gemma":0.0007687794,"teacher_disagreement_score":0.6575076,"about_ca_system_score_codex":0.00032883996,"about_ca_system_score_gemma":0.001647952,"threshold_uncertainty_score":0.99990463},"labels":[],"label_agreement":null},{"id":"W4297900355","doi":"10.1002/pro6.1171","title":"Knowledge domain and emerging trends in brachytherapy: A scientometric analysis","year":2022,"lang":"en","type":"article","venue":"Precision Radiation Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Brachytherapy; Domain (mathematical analysis); Citation; Medical physics; Data science; Computer science; Knowledge management; Medicine; Library science; Radiation therapy; Radiology; Mathematics","score_opus":0.01721502294734006,"score_gpt":0.38856581387132705,"score_spread":0.371350790923987,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297900355","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98105514,0.0027119545,0.0034844226,0.006097106,0.00033119798,0.00014479298,0.000003251868,0.000037773945,0.0061343415],"genre_scores_gemma":[0.9956819,0.0001981595,0.0023735564,0.0007177201,0.00007472762,0.000048534992,0.000053273798,0.000011503321,0.00084064924],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9984763,0.00036250308,0.0003281148,0.00033177427,0.00028829023,0.00021299298],"domain_scores_gemma":[0.9991822,0.0003679219,0.00012357949,0.0001568537,0.000030469619,0.00013894413],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0020942297,0.00008902892,0.00036092848,0.0062824176,0.00018783883,0.00001759175,0.0000908181,0.00004984855,0.0013223155],"category_scores_gemma":[0.0003081883,0.00008517582,0.000089963396,0.008809487,0.000052112897,0.000056245666,0.0001072633,0.00042217592,0.0000045788497],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000092100876,0.00021480951,0.13516752,0.0000037209636,0.00007256808,0.00002697498,0.001816679,0.0015694906,0.00030586068,0.00020536965,0.00094055536,0.85958433],"study_design_scores_gemma":[0.0029106608,0.00042099942,0.51605517,0.0000039130537,0.00012971583,0.00006680541,0.00027936604,0.18904617,0.0000060873863,0.00031227604,0.29066852,0.00010032741],"about_ca_topic_score_codex":0.00004357596,"about_ca_topic_score_gemma":0.00001882495,"teacher_disagreement_score":0.859484,"about_ca_system_score_codex":0.00043111143,"about_ca_system_score_gemma":0.000092440576,"threshold_uncertainty_score":0.99959064},"labels":[],"label_agreement":null},{"id":"W4297925391","doi":"10.48550/arxiv.1703.08516","title":"Radiomics strategies for risk assessment of tumour failure in head-and-neck cancer","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hôpital Maisonneuve-Rosemont; Centre Hospitalier Universitaire de Sherbrooke; Jewish General Hospital; Centre Hospitalier de l’Université de Montréal; McGill University","funders":"","keywords":"Radiomics; Medicine; Head and neck cancer; Oncology; Radiation therapy; Head and neck; Internal medicine; Risk assessment; Radiology; Surgery; Computer science","score_opus":0.049851560516637736,"score_gpt":0.2831586493096029,"score_spread":0.23330708879296513,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297925391","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9684058,0.00021644666,0.028506942,0.00073327014,0.0002607127,0.0005738118,0.000070712624,0.00003105371,0.0012012658],"genre_scores_gemma":[0.9932192,0.0022039996,0.0039192075,0.000055676715,0.00013191601,0.0000045460497,0.000036153775,0.000030455334,0.00039884372],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987466,0.00006618042,0.00024814784,0.0005862702,0.000083324645,0.00026951687],"domain_scores_gemma":[0.99863505,0.00011421541,0.0004652135,0.00049717,0.00013138918,0.0001569404],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00040917596,0.0002463574,0.00067712675,0.00023991056,0.00010904345,0.000054109227,0.00031257916,0.00024706672,0.000020340127],"category_scores_gemma":[0.00015202844,0.00025216563,0.0001838323,0.000083833605,0.00023052124,0.000115236304,0.0002834102,0.0010934699,5.065677e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036947857,0.0002672511,0.7772462,0.0021607084,0.00054314773,0.00033362713,0.0004964132,0.18007666,0.0007087007,0.03433365,0.0007764485,0.002687742],"study_design_scores_gemma":[0.0048186416,0.00018736468,0.21769692,0.0015340729,0.000655734,0.000010631517,0.0005291614,0.7505505,0.000039406765,0.022202818,0.0013810378,0.0003936814],"about_ca_topic_score_codex":0.0023450549,"about_ca_topic_score_gemma":0.00053893856,"teacher_disagreement_score":0.57047385,"about_ca_system_score_codex":0.00022120778,"about_ca_system_score_gemma":0.0007803464,"threshold_uncertainty_score":0.9999931},"labels":[],"label_agreement":null},{"id":"W4298009675","doi":"10.18280/ts.390434","title":"Robust Identification of Subtypes in Non-Small Cell Lung Cancer Using Radiomics","year":2022,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Key Research and Development Program of China; National Science Foundation","keywords":"Robustness (evolution); Radiomics; Pattern recognition (psychology); Feature (linguistics); Cluster analysis; Artificial intelligence; Stability (learning theory); Computer science; Lung cancer; Machine learning; Medicine; Biology; Oncology; Gene","score_opus":0.01988599877769713,"score_gpt":0.27707107505333495,"score_spread":0.2571850762756378,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4298009675","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97996217,0.0004755821,0.01835599,0.0004463041,0.00019742937,0.0003578777,0.0000116430565,0.000014537498,0.00017848347],"genre_scores_gemma":[0.99764484,0.00004641325,0.0017074245,0.00024550705,0.0001162201,0.000040528543,0.00003106354,0.000022064367,0.00014595887],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988056,0.00006223704,0.00043001625,0.00020995218,0.00029836313,0.0001938199],"domain_scores_gemma":[0.9995546,0.00003786619,0.00018273792,0.00012206187,0.000036945137,0.0000658406],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00068853504,0.000099862584,0.00022582494,0.0001960984,0.000088071734,0.000011886938,0.00011911476,0.000025396483,0.0005395023],"category_scores_gemma":[0.000016032838,0.00010314455,0.0000659626,0.00025419935,0.000039068746,0.000040530183,0.00004954575,0.00030977742,6.4436426e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016491537,0.00043236747,0.22780165,0.00038424053,0.00006162834,0.000046627658,0.0018603676,0.3590418,0.40526047,0.00008076598,0.0005840306,0.0042811157],"study_design_scores_gemma":[0.0020204354,0.00007597038,0.047345668,0.00007577482,0.00013151758,0.000017440998,0.0003518856,0.9423159,0.0071572703,0.000015223193,0.00037063676,0.00012231099],"about_ca_topic_score_codex":0.00042326903,"about_ca_topic_score_gemma":0.000007968836,"teacher_disagreement_score":0.58327407,"about_ca_system_score_codex":0.0002448925,"about_ca_system_score_gemma":0.00013645503,"threshold_uncertainty_score":0.5907172},"labels":[],"label_agreement":null},{"id":"W4298092917","doi":"","title":"Intelligent Application of Breast Cancer Trials Data in the Clinic","year":2015,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Health Science Centre","funders":"","keywords":"Breast cancer; Cancer; Medicine; Medical physics; Oncology; Internal medicine","score_opus":0.5095791378614924,"score_gpt":0.650938820829825,"score_spread":0.14135968296833257,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4298092917","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9243343,0.04281004,0.010582298,0.012788261,0.0012199963,0.0024287105,0.00020931635,0.000032582084,0.0055944812],"genre_scores_gemma":[0.98558366,0.012247077,0.00037660333,0.0011025673,0.00045714053,0.0000466451,0.000057005564,0.000028322887,0.00010096445],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9966143,0.000663881,0.0013741772,0.00033440616,0.0007980991,0.000215143],"domain_scores_gemma":[0.99659497,0.0008432558,0.0011366009,0.0009419999,0.0002633968,0.00021980585],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.013920118,0.00016610768,0.0009833875,0.00037794953,0.000048833146,0.00019516036,0.0027621405,0.000074983465,0.001934556],"category_scores_gemma":[0.003128051,0.00010545766,0.00011744157,0.00071770744,0.00015477344,0.0005860171,0.00064967194,0.0006191608,0.000009829481],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00056620076,0.00045507395,0.6966171,0.00012191725,0.0001869718,0.000018204011,0.0004088914,0.00013600185,0.009276097,0.000050768176,0.06494158,0.22722115],"study_design_scores_gemma":[0.0023707647,0.00002420589,0.9323904,0.001038267,0.00042059695,0.00009532984,0.0004920789,0.006230829,0.0016562985,0.0031570839,0.05186646,0.00025767434],"about_ca_topic_score_codex":0.0034211709,"about_ca_topic_score_gemma":0.000056230278,"teacher_disagreement_score":0.23577327,"about_ca_system_score_codex":0.00007811373,"about_ca_system_score_gemma":0.00035021425,"threshold_uncertainty_score":0.99897784},"labels":[],"label_agreement":null},{"id":"W4300031334","doi":"10.1007/978-3-642-23626-6","title":"Medical Image Computing and Computer-Assisted Intervention – MICCAI 2011","year":2011,"lang":"en","type":"book","venue":"Lecture notes in computer science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":261,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Robarts Clinical Trials; Sunnybrook Hospital; Queen's University","funders":"","keywords":"Computer science; Intervention (counseling); Medicine; Nursing","score_opus":0.011788956385331005,"score_gpt":0.29178293543071643,"score_spread":0.2799939790453854,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4300031334","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005114376,0.0008777425,0.98870075,0.0012786112,0.001875322,0.00036356156,0.0000021861374,0.00013864401,0.0016488256],"genre_scores_gemma":[0.19974847,0.00024370365,0.7852788,0.008547442,0.004523069,0.000008748731,0.00012563658,0.0001687232,0.0013553813],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99634093,0.000105039995,0.0007006068,0.0011527322,0.0010740509,0.0006266249],"domain_scores_gemma":[0.99800557,0.00043519787,0.000310005,0.00054861006,0.00019341373,0.0005071887],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0019449623,0.0004551426,0.0008263336,0.00067670055,0.00019551822,0.00018012743,0.0007395483,0.0004308609,0.00018639311],"category_scores_gemma":[0.00038695347,0.00038770444,0.00017647582,0.00029827468,0.0016189947,0.00015263385,0.00092459196,0.002106072,0.000037139027],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024108685,0.000131614,0.001051374,0.00035449848,0.000035659992,0.00051896356,0.000549893,0.00006671566,0.00009493483,0.00010092666,0.0008082029,0.9962631],"study_design_scores_gemma":[0.0019414702,0.00056813227,0.009743091,0.004473743,0.00008208948,0.0021507002,6.469559e-7,0.9740052,0.00014901604,0.0037368573,0.002552445,0.00059656997],"about_ca_topic_score_codex":0.00011839486,"about_ca_topic_score_gemma":0.000023325667,"teacher_disagreement_score":0.99566656,"about_ca_system_score_codex":0.00027437037,"about_ca_system_score_gemma":0.0007245329,"threshold_uncertainty_score":0.9998575},"labels":[],"label_agreement":null},{"id":"W4300177118","doi":"10.1007/978-3-030-00928-1","title":"Medical Image Computing and Computer Assisted Intervention – MICCAI 2018","year":2018,"lang":"en","type":"book","venue":"Lecture notes in computer science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":34,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Image quality; Artificial intelligence; Computer vision; Medical physics; Medical imaging; Image processing; Image (mathematics); Data science; Medicine","score_opus":0.00976282647887128,"score_gpt":0.30470891768569547,"score_spread":0.2949460912068242,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4300177118","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005614013,0.00047878982,0.9875262,0.002286631,0.0024676945,0.0003419805,0.0000024212682,0.000126508,0.0011557908],"genre_scores_gemma":[0.10928625,0.0001229354,0.86525613,0.013231818,0.010227115,0.000006861194,0.00014070513,0.00015922962,0.0015689277],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961292,0.0001156104,0.000678028,0.0011785668,0.0012707626,0.0006278175],"domain_scores_gemma":[0.9979014,0.0005632051,0.00028754905,0.00055065216,0.00022900749,0.00046821655],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002334185,0.00043881286,0.0007820093,0.0006250512,0.00023021213,0.000276094,0.00068260863,0.00043742676,0.00012051727],"category_scores_gemma":[0.0007050235,0.0003675221,0.00016368288,0.00043700618,0.0023567106,0.00015005372,0.00094944425,0.0017876044,0.000034681358],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025562595,0.00010566808,0.00089718716,0.00036891567,0.000042340558,0.00040702286,0.00041711004,0.00009105732,0.00012971701,0.00004415167,0.0045002997,0.99297094],"study_design_scores_gemma":[0.0015396618,0.0005061781,0.004979487,0.0045214603,0.000057923335,0.0015530402,4.2181986e-7,0.97914976,0.000095754694,0.0019714944,0.0051787305,0.00044609688],"about_ca_topic_score_codex":0.000042960404,"about_ca_topic_score_gemma":0.00001938014,"teacher_disagreement_score":0.99252486,"about_ca_system_score_codex":0.00035814903,"about_ca_system_score_gemma":0.0007202379,"threshold_uncertainty_score":0.9998777},"labels":[],"label_agreement":null},{"id":"W4300687540","doi":"10.1016/j.semradonc.2022.06.005","title":"Artificial Intelligence for Outcome Modeling in Radiotherapy","year":2022,"lang":"en","type":"review","venue":"Seminars in Radiation Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":17,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre","funders":"National Institutes of Health","keywords":"Medicine; Radiation therapy; Outcome (game theory); Medical physics; Personalized medicine; Modality (human–computer interaction); Artificial intelligence; Radiation oncology; Machine learning; Precision medicine; Bioinformatics; Computer science; Radiology; Pathology","score_opus":0.13324693764365686,"score_gpt":0.47202144759648335,"score_spread":0.3387745099528265,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4300687540","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000058363654,0.97956836,0.016384253,0.0008998657,0.0010873695,0.0015892567,0.000010402813,0.000033702054,0.00036843139],"genre_scores_gemma":[0.000052539992,0.98935664,0.008464969,0.00053115486,0.0004358245,0.0006835132,0.00027298235,0.00007353552,0.00012887127],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99711263,0.00032233883,0.0014496518,0.0005064421,0.00020879031,0.0004001288],"domain_scores_gemma":[0.9980091,0.0012670878,0.0003470302,0.00025858358,0.000017523109,0.00010071308],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0021794771,0.00028158166,0.0018574566,0.00093173556,0.00006318824,0.000013799702,0.00023561779,0.00040360258,0.00028614694],"category_scores_gemma":[0.0014077564,0.00027288406,0.0003147905,0.0005785888,0.00005852708,0.000040451734,0.000044091074,0.0014298043,0.000005664813],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051103674,0.00016082129,0.00010228912,0.0019373444,0.00003087528,0.00008831756,0.00034634478,0.003602813,4.1686906e-7,0.0004984659,0.00013901148,0.9930422],"study_design_scores_gemma":[0.0002249157,0.00025041273,0.0000011907571,0.0010857435,0.00010096467,0.00009943337,0.000074914584,0.26205412,1.0653378e-7,0.0004538724,0.7354867,0.00016762361],"about_ca_topic_score_codex":0.000046689078,"about_ca_topic_score_gemma":0.00001523202,"teacher_disagreement_score":0.99287456,"about_ca_system_score_codex":0.002268847,"about_ca_system_score_gemma":0.00074368017,"threshold_uncertainty_score":0.99997234},"labels":[],"label_agreement":null},{"id":"W4301973583","doi":"","title":"Liver Imaging Reporting and Data System: an expert consensus statement","year":2017,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Statement (logic); Computer science; Data science; Medical physics; Data mining; Medicine; Political science; Law","score_opus":0.37441055508334486,"score_gpt":0.6164975053962095,"score_spread":0.24208695031286465,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4301973583","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9680016,0.021571526,0.001000235,0.0021041199,0.0008371081,0.0005883342,0.000027636359,0.00006967091,0.005799759],"genre_scores_gemma":[0.9904455,0.005112261,0.0031554203,0.0005648997,0.0004227067,0.000010773779,0.000037354504,0.000059727958,0.00019135288],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99642634,0.00020134098,0.0015879439,0.0006843048,0.0006995021,0.00040056286],"domain_scores_gemma":[0.99360365,0.00018734622,0.0035312115,0.0018643663,0.00026646038,0.00054698694],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0054764585,0.0002702315,0.00090953073,0.00031612176,0.00076918217,0.002209672,0.0022487508,0.00005614488,0.0007376422],"category_scores_gemma":[0.004025521,0.00022397311,0.00007612579,0.00010550702,0.00034308652,0.0018064204,0.0022942077,0.0005715684,0.0000034499117],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015597345,0.00014666088,0.80025744,0.00039852408,0.00022554214,0.0021074456,0.00033366156,0.000012286084,0.041999556,0.000047881756,0.03653875,0.11777629],"study_design_scores_gemma":[0.0019669707,0.000020120373,0.9177367,0.0034009626,0.00031767026,0.001490968,0.0008531764,0.045649786,0.0023867455,0.00023274568,0.025420384,0.0005237366],"about_ca_topic_score_codex":0.005058029,"about_ca_topic_score_gemma":0.000022111766,"teacher_disagreement_score":0.1174793,"about_ca_system_score_codex":0.0000966538,"about_ca_system_score_gemma":0.00019516046,"threshold_uncertainty_score":0.99882615},"labels":[],"label_agreement":null},{"id":"W4302009409","doi":"10.1016/j.compbiomed.2022.106165","title":"Two-step machine learning to diagnose and predict involvement of lungs in COVID-19 and pneumonia using CT radiomics","year":2022,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":36,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; BC Cancer Agency","funders":"The Research Council","keywords":"Coronavirus disease 2019 (COVID-19); Radiomics; Pneumonia; 2019-20 coronavirus outbreak; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Artificial intelligence; Machine learning; Computer science; Betacoronavirus; Medicine; Virology; Pathology; Internal medicine; Infectious disease (medical specialty)","score_opus":0.018678742155388568,"score_gpt":0.3385732267878109,"score_spread":0.3198944846324223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4302009409","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98065567,0.006855593,0.0037480008,0.008005786,0.00028346747,0.00039312252,0.0000046349546,0.000020241205,0.000033487355],"genre_scores_gemma":[0.9869508,0.0018744661,0.0049919304,0.006003308,0.00009264435,0.00001715024,0.000043784567,0.000014567858,0.000011310951],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99854785,0.0002583451,0.00041560605,0.00039311973,0.00012562855,0.0002594419],"domain_scores_gemma":[0.9989119,0.0005110743,0.00011155506,0.00012673328,0.000014092771,0.00032465422],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014237654,0.0001662519,0.00058343844,0.0005018162,0.00012810095,0.0000045069087,0.00008825714,0.000039298964,0.000018834427],"category_scores_gemma":[0.0006367636,0.00014199934,0.000018645584,0.00028455319,0.0004312112,0.000027972568,0.00034360818,0.00065506366,5.1127312e-8],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023890735,0.00007847975,0.95899236,0.00023419793,0.00004267106,0.00028067495,0.0028289822,0.00134494,0.0066226902,0.0005724903,0.00016228802,0.028601306],"study_design_scores_gemma":[0.025816115,0.0042845486,0.1472797,0.0012988504,0.00018961256,0.0025271152,0.0029715202,0.79081666,0.00005706335,0.0013167014,0.022954121,0.00048801277],"about_ca_topic_score_codex":0.0018097608,"about_ca_topic_score_gemma":0.000058459103,"teacher_disagreement_score":0.8117127,"about_ca_system_score_codex":0.00013043886,"about_ca_system_score_gemma":0.00007378489,"threshold_uncertainty_score":0.5790565},"labels":[],"label_agreement":null},{"id":"W4302362399","doi":"10.32920/21287934","title":"Measurement Variability Following MRI System Upgrade","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; Université de Montréal; Institut Universitaire de Gériatrie de Montréal; Toronto Metropolitan University; Montreal Neurological Institute and Hospital; Douglas Mental Health University Institute; McGill University","funders":"Pfizer Canada; Fonds de Recherche du Québec - Santé; Alzheimer's Society; Consortium canadien en neurodégénérescence associée au vieillissement; Pfizer","keywords":"Fluid-attenuated inversion recovery; Upgrade; Hyperintensity; Siemens; Context (archaeology); Magnetic resonance imaging; Nuclear medicine; Medicine; White matter; Radiology; Computer science; Physics; Biology","score_opus":0.02312085841303735,"score_gpt":0.2983654682356776,"score_spread":0.27524460982264026,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4302362399","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16424043,0.0030876577,0.30749425,0.033184342,0.02090531,0.005460016,0.000026749669,0.003260317,0.46234092],"genre_scores_gemma":[0.9859358,0.000023344255,0.011408199,0.00080045144,0.00048849586,0.00018055816,0.0000624397,0.0000681043,0.001032614],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99611706,0.00036232566,0.00061836146,0.00083230564,0.0016707671,0.00039919704],"domain_scores_gemma":[0.99825484,0.000077147415,0.00018024565,0.0010659627,0.000098641416,0.00032316145],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.005351361,0.00034086683,0.00083951163,0.00015140763,0.00019345607,0.00006513253,0.00033355725,0.00019977459,0.0006133925],"category_scores_gemma":[0.0008815674,0.00029080734,0.00061815634,0.00013931647,0.000042428386,0.00002299354,0.00095671194,0.0025205105,0.000019942632],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007817445,0.003945918,0.64069855,0.0511079,0.013650962,0.006781751,0.004229506,0.026271623,0.006970531,0.04962108,0.11990501,0.07603543],"study_design_scores_gemma":[0.010031992,0.0006779734,0.059924603,0.009878435,0.0068366467,0.00068667857,0.0037133724,0.5281765,0.0003913226,0.004013937,0.37211818,0.003550353],"about_ca_topic_score_codex":0.00045002202,"about_ca_topic_score_gemma":0.0000017548306,"teacher_disagreement_score":0.8216954,"about_ca_system_score_codex":0.0016015441,"about_ca_system_score_gemma":0.00060370687,"threshold_uncertainty_score":0.9999544},"labels":[],"label_agreement":null},{"id":"W4302362400","doi":"10.32920/21287934.v1","title":"Measurement Variability Following MRI System Upgrade","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; Université de Montréal; Institut Universitaire de Gériatrie de Montréal; Toronto Metropolitan University; Montreal Neurological Institute and Hospital; Douglas Mental Health University Institute; McGill University","funders":"Pfizer Canada; Fonds de Recherche du Québec - Santé; Alzheimer's Society; Consortium canadien en neurodégénérescence associée au vieillissement; Pfizer","keywords":"Fluid-attenuated inversion recovery; Upgrade; Hyperintensity; Context (archaeology); Siemens; Nuclear medicine; Magnetic resonance imaging; Medicine; White matter; Radiology; Computer science; Physics; Biology","score_opus":0.02312085841303735,"score_gpt":0.2983654682356776,"score_spread":0.27524460982264026,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4302362400","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16424043,0.0030876577,0.30749425,0.033184342,0.02090531,0.005460016,0.000026749669,0.003260317,0.46234092],"genre_scores_gemma":[0.9859358,0.000023344255,0.011408199,0.00080045144,0.00048849586,0.00018055816,0.0000624397,0.0000681043,0.001032614],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99611706,0.00036232566,0.00061836146,0.00083230564,0.0016707671,0.00039919704],"domain_scores_gemma":[0.99825484,0.000077147415,0.00018024565,0.0010659627,0.000098641416,0.00032316145],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.005351361,0.00034086683,0.00083951163,0.00015140763,0.00019345607,0.00006513253,0.00033355725,0.00019977459,0.0006133925],"category_scores_gemma":[0.0008815674,0.00029080734,0.00061815634,0.00013931647,0.000042428386,0.00002299354,0.00095671194,0.0025205105,0.000019942632],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007817445,0.003945918,0.64069855,0.0511079,0.013650962,0.006781751,0.004229506,0.026271623,0.006970531,0.04962108,0.11990501,0.07603543],"study_design_scores_gemma":[0.010031992,0.0006779734,0.059924603,0.009878435,0.0068366467,0.00068667857,0.0037133724,0.5281765,0.0003913226,0.004013937,0.37211818,0.003550353],"about_ca_topic_score_codex":0.00045002202,"about_ca_topic_score_gemma":0.0000017548306,"teacher_disagreement_score":0.8216954,"about_ca_system_score_codex":0.0016015441,"about_ca_system_score_gemma":0.00060370687,"threshold_uncertainty_score":0.9999544},"labels":[],"label_agreement":null},{"id":"W4303646098","doi":"10.28991/hij-2022-03-03-07","title":"DeepImageTranslator V2: Analysis of Multimodal Medical Images using Semantic Segmentation Maps Generated through Deep Learning","year":2022,"lang":"en","type":"article","venue":"HighTech and Innovation Journal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University Health Network; Centre Hospitalier Universitaire de Sherbrooke; Université de Sherbrooke; Université de Montréal","funders":"","keywords":"Deep learning; Artificial intelligence; Computer science; Segmentation; Software; Convolutional neural network; Pattern recognition (psychology); Computer vision","score_opus":0.016163102574423816,"score_gpt":0.3137297475267964,"score_spread":0.29756664495237256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4303646098","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.71222174,0.00057212805,0.28533122,0.0015007184,0.00014916425,0.00007889625,0.0000035503017,0.00002439321,0.000118203585],"genre_scores_gemma":[0.96145684,0.00027725747,0.037011705,0.00086181547,0.00015982527,0.0000038336034,0.00015070499,0.000019112422,0.00005888411],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99804574,0.00017267108,0.0006379736,0.00018173677,0.00076815614,0.00019373214],"domain_scores_gemma":[0.99912417,0.00005252265,0.0003604736,0.00008165962,0.00028231184,0.00009888344],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0011513904,0.00011962737,0.00035236825,0.0010380733,0.0004761371,0.000042811153,0.00007833413,0.000057341967,0.0009672003],"category_scores_gemma":[0.00022265951,0.00010584778,0.00008440913,0.002882677,0.00009440483,0.00017723207,0.000042938816,0.0009970526,4.7673356e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039469506,0.0004499324,0.17578088,0.00015973234,0.0029552074,0.0004464156,0.0030948424,0.022064634,0.6431406,0.0029702336,0.00084410806,0.14769872],"study_design_scores_gemma":[0.0041673156,0.0004253235,0.025117898,0.00009404731,0.0012960943,0.0015975201,0.0010003048,0.9495887,0.011714289,0.0003833782,0.004324322,0.0002907698],"about_ca_topic_score_codex":0.000039209644,"about_ca_topic_score_gemma":6.581548e-7,"teacher_disagreement_score":0.9275241,"about_ca_system_score_codex":0.000075898235,"about_ca_system_score_gemma":0.00012855082,"threshold_uncertainty_score":0.99994606},"labels":[],"label_agreement":null},{"id":"W4304608970","doi":"10.5194/essd-2022-281-rc1","title":"Comment on essd-2022-281","year":2022,"lang":"en","type":"peer-review","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Environment and Climate Change Canada","funders":"Earth Sciences Division; Goddard Space Flight Center; National Aeronautics and Space Administration","keywords":"Computer science","score_opus":0.02534678214350791,"score_gpt":0.35553206841769336,"score_spread":0.3301852862741855,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4304608970","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000037494367,0.018297173,0.00012681381,0.72931254,0.0035258676,0.0005956503,0.000044696102,0.00012622261,0.2479673],"genre_scores_gemma":[0.000012851463,0.015215873,0.0005322925,0.46735182,0.000737673,0.000101212005,0.002254779,0.00007023577,0.51372325],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99730486,0.00014150621,0.0004675039,0.00053160446,0.0011898859,0.00036461814],"domain_scores_gemma":[0.9984811,0.00021509598,0.00018123622,0.00076023076,0.00007063489,0.0002917319],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0010127593,0.00035447656,0.001003085,0.00018031259,0.00014295225,0.000021709022,0.00030723357,0.00013158827,0.060400017],"category_scores_gemma":[0.00068007736,0.00026975165,0.00034712296,0.00020936165,0.000061597886,0.000013046082,0.00024893106,0.0028297259,0.00028697948],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014941875,0.00016883267,0.000023443014,0.002373237,0.00012272988,0.00018143479,0.000012447637,0.0000026087678,0.0000018660209,0.00078775705,0.9522476,0.0440631],"study_design_scores_gemma":[0.0006935166,0.00032773128,0.000017389795,0.003551595,0.00038835863,0.000093091425,0.000015403262,0.0003588452,0.000002456537,0.000054867218,0.99423784,0.00025893093],"about_ca_topic_score_codex":0.00024288631,"about_ca_topic_score_gemma":0.0000019036734,"teacher_disagreement_score":0.26575598,"about_ca_system_score_codex":0.0002970443,"about_ca_system_score_gemma":0.00023338574,"threshold_uncertainty_score":0.99997544},"labels":[],"label_agreement":null},{"id":"W4304633187","doi":"10.1016/j.jaac.2022.07.734","title":"32.2 The Caribou-2 Study: A Stepped-Wedge Cluster-Hybrid Effectiveness-Implementation Randomized Controlled Trial","year":2022,"lang":"en","type":"article","venue":"Journal of the American Academy of Child & Adolescent Psychiatry","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Cluster randomised controlled trial; Randomized controlled trial; Wedge (geometry); Cluster (spacecraft); Psychology; Medicine; Environmental science; Computer science; Physics; Internal medicine; Optics","score_opus":0.008134445984473404,"score_gpt":0.3275856112447588,"score_spread":0.31945116526028544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4304633187","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9026926,0.001169923,0.00054181647,0.08676248,0.0022451526,0.0064737615,0.000008574937,0.00001373634,0.000091948845],"genre_scores_gemma":[0.98412794,0.0001397868,0.00011246364,0.014090156,0.0013482996,0.00011439303,0.0000021878488,0.00003827986,0.000026511954],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.9919648,0.0045145764,0.0016074058,0.0002326026,0.0013770134,0.00030359792],"domain_scores_gemma":[0.9950366,0.0007301415,0.003744231,0.0002642842,0.00007385399,0.00015089652],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.007927237,0.00026690756,0.002156997,0.00023531822,0.0004627702,0.000028617764,0.00066774234,0.00002424802,0.00004294461],"category_scores_gemma":[0.0005122483,0.0001376826,0.0014387548,0.00042997397,0.0004719935,0.00006643633,0.00022679963,0.0026804293,7.632382e-7],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.9440338,0.0017129898,0.03671977,0.000076374985,0.001711117,0.000004512299,0.00034580243,0.00090736896,0.000111735266,0.00009644684,0.010767741,0.0035123331],"study_design_scores_gemma":[0.8967892,0.0012585385,0.09389524,0.0002954196,0.0023476388,0.00041045898,0.0017696667,0.0005729624,0.00004385108,0.00021151388,0.0022617737,0.00014377119],"about_ca_topic_score_codex":0.000040478517,"about_ca_topic_score_gemma":0.0000010157016,"teacher_disagreement_score":0.081435315,"about_ca_system_score_codex":0.00015725258,"about_ca_system_score_gemma":0.00031352183,"threshold_uncertainty_score":0.99962044},"labels":[],"label_agreement":null},{"id":"W4306165391","doi":"10.1088/978-0-7503-3599-7ch12","title":"Radiomics, deep learning, and breast cancer detection","year":2022,"lang":"en","type":"book-chapter","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Radiomics; Breast cancer; Medicine; Cancer; Artificial intelligence; Computer science; Internal medicine","score_opus":0.006647337309633499,"score_gpt":0.2574672881476039,"score_spread":0.2508199508379704,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4306165391","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009860824,0.006921654,0.0013245129,0.004902495,0.0009364974,0.0004654521,0.00001743303,0.00032503717,0.98412085],"genre_scores_gemma":[0.020400953,0.014153924,0.000429242,0.0013249222,0.0009533518,0.000025351923,0.00007305738,0.00016851668,0.9624707],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987556,0.000020021882,0.00025355807,0.00043191918,0.00032194052,0.00021701315],"domain_scores_gemma":[0.9993606,0.00005120555,0.00015034275,0.00015879185,0.000049961796,0.0002290784],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00021923748,0.00027161642,0.0004576964,0.00020732534,0.00020243553,0.000029663515,0.000063548374,0.0001883296,0.016403163],"category_scores_gemma":[0.00004293365,0.00024574663,0.0001275538,0.000027956474,0.0001365989,0.000039358205,0.000107850305,0.0018272427,0.000023472181],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014999053,0.00002055867,0.0020061836,0.00021320362,0.00036855252,0.00017334615,0.00012312754,0.00004115946,0.00048372892,0.010372095,0.0017223305,0.9843257],"study_design_scores_gemma":[0.0008554904,0.00012985537,0.0009326362,0.000116517025,0.00032491944,0.0016541168,0.00002255458,0.0074639297,0.000011834759,0.0004890044,0.9876995,0.00029960342],"about_ca_topic_score_codex":0.00030682122,"about_ca_topic_score_gemma":0.000032130887,"teacher_disagreement_score":0.98597723,"about_ca_system_score_codex":0.00022173503,"about_ca_system_score_gemma":0.00006905711,"threshold_uncertainty_score":0.99999946},"labels":[],"label_agreement":null},{"id":"W4306655460","doi":"10.2196/43025","title":"Correction: Cost-Effectiveness of Lung Cancer Screening Using Low-Dose Computed Tomography Based on Start Age and Interval in China: Modeling Study","year":2022,"lang":"en","type":"erratum","venue":"JMIR Public Health and Surveillance","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computed tomography; Lung cancer; Medicine; Cancer; China; Interval (graph theory); Medical physics; Nuclear medicine; Statistics; Radiology; Oncology; Mathematics; Internal medicine; History","score_opus":0.03361989791050028,"score_gpt":0.359911556826976,"score_spread":0.3262916589164757,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4306655460","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94945383,0.007595986,0.01923503,0.002483199,0.013990704,0.0063143466,0.00010230222,0.00016682559,0.0006577843],"genre_scores_gemma":[0.997031,0.00037565414,0.00022812298,0.0009663277,0.00037298995,0.00027902971,0.00046614074,0.000077739234,0.00020300367],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9958504,0.0014645229,0.00072285446,0.0007491474,0.00060849555,0.0006046036],"domain_scores_gemma":[0.9982713,0.00038255317,0.00035973877,0.00032484753,0.00012184296,0.0005397606],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0038528875,0.00038304075,0.0013794863,0.0008812592,0.00028193448,0.00007637858,0.0001391808,0.00016939746,0.000027183458],"category_scores_gemma":[0.00040050395,0.0003670689,0.00010657285,0.0008921008,0.000110196816,0.000079401456,0.00013692524,0.0023818566,3.0364806e-8],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011958919,0.0009454904,0.91033036,0.006185809,0.00018381985,0.00022501081,0.0014742122,0.023635216,0.0000038319927,0.0000041051917,0.010956617,0.04485967],"study_design_scores_gemma":[0.002707651,0.0005316758,0.24418615,0.0015306385,0.0000056960803,0.00001628767,0.00022202612,0.74704987,2.6457627e-8,9.983762e-7,0.0035429571,0.00020599416],"about_ca_topic_score_codex":0.003546648,"about_ca_topic_score_gemma":0.00029372965,"teacher_disagreement_score":0.72341466,"about_ca_system_score_codex":0.00037286576,"about_ca_system_score_gemma":0.0012682785,"threshold_uncertainty_score":0.9999197},"labels":[],"label_agreement":null},{"id":"W4306871420","doi":"10.1111/rth2.12812","title":"Abstracts from the CanVECTOR 2022 Annual Conference October 14th, 2022","year":2022,"lang":"en","type":"article","venue":"Research and Practice in Thrombosis and Haemostasis","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Mount Sinai Hospital; Western University; University of Calgary; Windsor Regional Hospital; University of Windsor; Thrombosis and Atherosclerosis Research Institute; Queen's University; Schwartz/Reisman Emergency Medicine Institute; McMaster University","funders":"","keywords":"Political science","score_opus":0.11532734918048539,"score_gpt":0.43349131557014964,"score_spread":0.31816396638966427,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4306871420","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86653215,0.0050515668,0.000009587275,0.12198495,0.00013879423,0.0004396957,0.00016015081,0.000017777655,0.005665335],"genre_scores_gemma":[0.98309875,0.012840581,0.00044832175,0.002886233,0.00017843701,0.000086664135,0.000066668494,0.00002422515,0.00037012174],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9967392,0.0010096827,0.00029309298,0.00045402607,0.0010097572,0.0004942542],"domain_scores_gemma":[0.993297,0.0057835267,0.00010059869,0.00032248997,0.00020628706,0.00029009336],"candidate_categories":["research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00489209,0.00014481353,0.00030434103,0.00014221917,0.0008521649,0.00018820397,0.00020156804,0.000059302583,0.0016979217],"category_scores_gemma":[0.004935502,0.00010839368,0.0000365996,0.00049215474,0.0004133497,0.00027134432,0.0004871388,0.0023795194,0.000008851828],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0037432008,0.0022660263,0.10689893,0.0002098599,0.00082600967,0.0012408565,0.048180487,0.00006390599,0.007906657,0.0032485928,0.3001586,0.5252569],"study_design_scores_gemma":[0.0029618929,0.0010396724,0.24520315,0.0001245459,0.00014109068,0.0004156659,0.05608546,0.0014671584,0.00018805289,0.0020273363,0.6900338,0.00031215613],"about_ca_topic_score_codex":0.012442418,"about_ca_topic_score_gemma":0.00028194409,"teacher_disagreement_score":0.5249447,"about_ca_system_score_codex":0.00009887286,"about_ca_system_score_gemma":0.00030588228,"threshold_uncertainty_score":0.99992204},"labels":[],"label_agreement":null},{"id":"W4306880438","doi":"10.1177/14604582221135427","title":"Machine learning based survival prediction in Glioma using large-scale registry data","year":2022,"lang":"en","type":"article","venue":"Health Informatics Journal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Cancer Institute; BC Cancer Agency; National Institutes of Health","keywords":"Concordance; Glioma; Random forest; Medicine; Support vector machine; Proportional hazards model; Predictive modelling; Glioblastoma; Machine learning; Artificial intelligence; Scale (ratio); Oncology; Internal medicine; Computer science","score_opus":0.04777481628623458,"score_gpt":0.35172637378234173,"score_spread":0.30395155749610714,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4306880438","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.64590967,0.0016805076,0.33171695,0.014165934,0.0029573108,0.0007500249,0.00030976112,0.00019120895,0.002318643],"genre_scores_gemma":[0.9021918,0.00035259378,0.08620471,0.008413329,0.0009367688,0.000010960149,0.0015033729,0.00009070784,0.00029571788],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968902,0.00031827565,0.0012430947,0.00013167232,0.0008734733,0.000543319],"domain_scores_gemma":[0.9983263,0.00008591245,0.0007296742,0.00040442476,0.00005728327,0.0003963912],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.006985269,0.00014277434,0.00038321427,0.0004331036,0.00093139015,0.00007146456,0.00032210146,0.00004810678,0.00036337404],"category_scores_gemma":[0.0005745884,0.00013594852,0.00005710493,0.00046625856,0.000037625367,0.00029903773,0.00027901505,0.0031004748,0.000004268224],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00073705846,0.0008701369,0.540166,0.0018965564,0.00011370669,0.0006506082,0.009960901,0.39065707,0.00014514262,0.00009664086,0.014647906,0.040058285],"study_design_scores_gemma":[0.0028412195,0.00024485638,0.0034216177,0.00017382506,0.00001914152,0.002939756,0.0020778775,0.8974276,0.0000015150779,0.000018834307,0.090742856,0.00009085459],"about_ca_topic_score_codex":0.00012021626,"about_ca_topic_score_gemma":0.000010164899,"teacher_disagreement_score":0.53674436,"about_ca_system_score_codex":0.0005438038,"about_ca_system_score_gemma":0.0010709662,"threshold_uncertainty_score":0.9991994},"labels":[],"label_agreement":null},{"id":"W4306914348","doi":"10.1109/tmi.2022.3213983","title":"Learn2Reg: comprehensive multi-task medical image registration challenge, dataset and evaluation in the era of deep learning","year":2023,"lang":"en","type":"article","venue":"University of Birmingham Research Portal (University of Birmingham)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":229,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Menzies Centre for Australian Studies, King's College London, University of London; Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology; Stanford Bio-X; Gillings School of Public Health; Haute école Spécialisée de Suisse Occidentale; Nanjing University; Concordia University; Nvidia; Radboud Universitair Medisch Centrum; Uppsala Universitet; Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital; Centre National de la Recherche Scientifique; Tel Aviv University; Imperial College London; Centre d'Imagerie BioMédicale; Universität zu Lübeck; Université Paris-Saclay; Tsinghua University; University of North Carolina at Chapel Hill; Nanjing University of Information Science and Technology; Wuhan National Laboratory for Optoelectronics; Elekta; Radboud Universiteit; Chinese University of Hong Kong; Bundesministerium für Bildung und Forschung; Huazhong University of Science and Technology; Institut Gustave-Roussy; Vanderbilt University; King's College London; Institut National de la Santé et de la Recherche Médicale; Akademia Górniczo-Hutnicza im. Stanislawa Staszica; Massachusetts General Hospital","keywords":"Image registration; Artificial intelligence; Computer science; Deep learning; Task (project management); Computer vision; Medical imaging; Image (mathematics); Engineering","score_opus":0.06673218546828867,"score_gpt":0.3641202994435485,"score_spread":0.2973881139752598,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4306914348","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9904842,0.00030881178,0.00092676416,0.0052395873,0.000036682333,0.0006432902,0.00005420433,0.000037872996,0.0022685942],"genre_scores_gemma":[0.9958972,0.0017364823,0.001548438,0.000020764126,0.000024652685,2.105704e-7,0.0004789032,0.000013519237,0.00027987995],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99634725,0.00069283595,0.00026460114,0.00042041225,0.0018965101,0.00037838524],"domain_scores_gemma":[0.9978568,0.00069803704,0.00029160274,0.00036790702,0.00057248794,0.00021317405],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004631351,0.00014550974,0.00044803187,0.00070977234,0.00035893975,0.0000112977405,0.0004817271,0.00018812786,0.00036886378],"category_scores_gemma":[0.0012127092,0.00015610071,0.0001088844,0.0010154251,0.0016198882,0.00026309738,0.00036858977,0.0013953531,0.000012169826],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0031395473,0.003442811,0.09597633,0.004741004,0.0010534796,0.012305144,0.10180967,0.0016888945,0.053426627,0.0027691629,0.030359557,0.6892878],"study_design_scores_gemma":[0.010492514,0.0014982611,0.19779707,0.0014439841,0.0003172856,0.00019944504,0.29267985,0.47119734,0.00015561715,0.00017972209,0.023606325,0.00043256948],"about_ca_topic_score_codex":0.004003164,"about_ca_topic_score_gemma":0.0011116761,"teacher_disagreement_score":0.6888552,"about_ca_system_score_codex":0.00004698464,"about_ca_system_score_gemma":0.0003471225,"threshold_uncertainty_score":0.63656026},"labels":[],"label_agreement":null},{"id":"W4306938191","doi":"10.3390/cancers14205133","title":"Impact of Tumour Segmentation Accuracy on Efficacy of Quantitative MRI Biomarkers of Radiotherapy Outcome in Brain Metastasis","year":2022,"lang":"en","type":"article","venue":"Cancers","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; Sunnybrook Health Science Centre; University of Toronto; York University","funders":"Terry Fox Foundation; Lotte and John Hecht Memorial Foundation","keywords":"Radiomics; Segmentation; Medicine; Radiation therapy; Dice; Brain metastasis; Magnetic resonance imaging; Radiology; Computer science; Metastasis; Artificial intelligence; Cancer; Internal medicine","score_opus":0.03162233176784656,"score_gpt":0.40228783207095814,"score_spread":0.3706655003031116,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4306938191","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9972139,0.00041298146,0.0008383551,0.0009158248,0.000105436884,0.00031452585,0.000045163444,0.000006908751,0.00014691138],"genre_scores_gemma":[0.99681556,0.00007830735,0.0027971966,0.0002207597,0.000011641694,0.000013688592,0.000025384034,0.000017154456,0.000020286127],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9988262,0.0001598719,0.0004267293,0.00015358387,0.00030079953,0.00013283479],"domain_scores_gemma":[0.9988368,0.000563235,0.00035958903,0.00014640794,0.000036948983,0.00005702609],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006046318,0.00009806374,0.00042373766,0.0003123335,0.00002309248,0.0000019240663,0.000097404016,0.00001706817,0.00027293834],"category_scores_gemma":[0.000631017,0.00008358022,0.00017847755,0.0004522656,0.00011207244,0.000037048314,0.000017198307,0.00020666943,2.264043e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0045581455,0.00033675737,0.29235408,0.0003159424,0.0012556959,0.00003023259,0.0071011856,0.16328979,0.48565802,0.0003750099,0.0029662068,0.041758943],"study_design_scores_gemma":[0.018117271,0.0060761375,0.89022666,0.0003635584,0.00022832585,0.000019693112,0.0047698957,0.059832875,0.01950204,0.00006548996,0.00049483345,0.00030320178],"about_ca_topic_score_codex":0.0020633931,"about_ca_topic_score_gemma":0.000004683582,"teacher_disagreement_score":0.5978726,"about_ca_system_score_codex":0.00096901366,"about_ca_system_score_gemma":0.00038294191,"threshold_uncertainty_score":0.34083024},"labels":[],"label_agreement":null},{"id":"W4307144613","doi":"10.1016/j.ijrobp.2022.07.930","title":"Prediction of Brain Metastasis Response to Stereotactic Radiosurgery Using MRI and Machine Learning: Effects of Primary Cancer Site and Metastasis Volume","year":2022,"lang":"en","type":"article","venue":"International Journal of Radiation Oncology*Biology*Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Niagara Health System; Ottawa Regional Cancer Foundation; Western University","funders":"","keywords":"Medicine; Radiosurgery; Brain metastasis; Magnetic resonance imaging; Receiver operating characteristic; Metastasis; Clinical endpoint; Radiomics; Cancer; Colorectal cancer; Breast cancer; Primary tumor; Nuclear medicine; Radiology; Oncology; Internal medicine; Radiation therapy; Clinical trial","score_opus":0.021805428122840045,"score_gpt":0.31747714297109025,"score_spread":0.2956717148482502,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4307144613","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9743895,0.002361966,0.016343718,0.005565934,0.0009681838,0.00022014795,0.00012289127,0.0000133491985,0.000014326509],"genre_scores_gemma":[0.9928368,0.00074942596,0.004917233,0.0010069774,0.00035495876,0.00001051147,0.000046933783,0.000027811031,0.000049369944],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9973782,0.001138688,0.0007217764,0.00021463481,0.00038427807,0.00016246646],"domain_scores_gemma":[0.99669456,0.0015782338,0.0011461847,0.000099528566,0.00032541662,0.00015605334],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023025146,0.00015479635,0.00068280596,0.0004281432,0.00011139942,0.000012593806,0.00013670229,0.000072764065,0.000045634606],"category_scores_gemma":[0.0017616069,0.00014722232,0.00014947893,0.0002409382,0.00020082334,0.00016217184,0.00014179118,0.0007427059,3.4432705e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0031506557,0.0003270143,0.65804464,0.00011543584,0.0014792325,0.00008022176,0.0013814082,0.007796098,0.16345513,0.00015225346,0.0005393394,0.16347857],"study_design_scores_gemma":[0.025121873,0.012278188,0.6277489,0.00063093955,0.0032121919,0.003911029,0.00047017197,0.19883935,0.013011722,0.001292157,0.11282408,0.0006593652],"about_ca_topic_score_codex":0.00009033184,"about_ca_topic_score_gemma":7.949362e-7,"teacher_disagreement_score":0.19104326,"about_ca_system_score_codex":0.0005185261,"about_ca_system_score_gemma":0.0004150551,"threshold_uncertainty_score":0.6003552},"labels":[],"label_agreement":null},{"id":"W4307223069","doi":"10.32920/21290982.v1","title":"Quantitative ultrasound radiomics in predicting response to neoadjuvant chemotherapy in patients with locally advanced breast cancer: Results from multi-institutional study","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research; Terry Fox Foundation","keywords":"Radiomics; Medicine; Breast cancer; Neoadjuvant therapy; Ultrasound; Radiology; Internal medicine; Cancer","score_opus":0.012571028919624673,"score_gpt":0.31353278593176476,"score_spread":0.30096175701214006,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4307223069","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98788935,0.00010664375,0.0038232987,0.003018297,0.0005270067,0.0034478093,0.0010003808,0.000097833836,0.00008936276],"genre_scores_gemma":[0.96740067,0.00008432394,0.03012748,0.0010806016,0.00008613517,0.00033391052,0.00066230225,0.000083448635,0.00014113638],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99567044,0.00048528763,0.0010580274,0.0013151236,0.0009708761,0.0005002496],"domain_scores_gemma":[0.99758166,0.00092889916,0.00035590617,0.00063461374,0.00019972381,0.00029917317],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0016550055,0.00053439674,0.001044951,0.00061579735,0.00013547133,0.000058014306,0.0003861297,0.00015939819,0.00014593216],"category_scores_gemma":[0.0017532109,0.00042983657,0.00009368278,0.00057461654,0.00013862776,0.00010262095,0.00033068095,0.0023876983,0.0000030133842],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.077370204,0.002258018,0.7452857,0.00003313847,0.00021743748,0.00021167278,0.007520869,0.15874138,0.0002598725,0.0000073918613,0.000043118285,0.008051229],"study_design_scores_gemma":[0.039869,0.001165842,0.9179301,0.0012113467,0.000057489433,0.000008840157,0.0024718705,0.0366778,0.000009262556,0.00001377338,0.0001531306,0.00043151146],"about_ca_topic_score_codex":0.012096017,"about_ca_topic_score_gemma":0.0019393766,"teacher_disagreement_score":0.17264447,"about_ca_system_score_codex":0.0016481496,"about_ca_system_score_gemma":0.0012359419,"threshold_uncertainty_score":0.9999138},"labels":[],"label_agreement":null},{"id":"W4307223901","doi":"10.32920/21290982","title":"Quantitative ultrasound radiomics in predicting response to neoadjuvant chemotherapy in patients with locally advanced breast cancer: Results from multi-institutional study","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research; Terry Fox Foundation","keywords":"Radiomics; Breast cancer; Medicine; Neoadjuvant therapy; Ultrasound; Internal medicine; Radiology; Cancer","score_opus":0.012571028919624673,"score_gpt":0.31353278593176476,"score_spread":0.30096175701214006,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4307223901","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98788935,0.00010664375,0.0038232987,0.003018297,0.0005270067,0.0034478093,0.0010003808,0.000097833836,0.00008936276],"genre_scores_gemma":[0.96740067,0.00008432394,0.03012748,0.0010806016,0.00008613517,0.00033391052,0.00066230225,0.000083448635,0.00014113638],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99567044,0.00048528763,0.0010580274,0.0013151236,0.0009708761,0.0005002496],"domain_scores_gemma":[0.99758166,0.00092889916,0.00035590617,0.00063461374,0.00019972381,0.00029917317],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0016550055,0.00053439674,0.001044951,0.00061579735,0.00013547133,0.000058014306,0.0003861297,0.00015939819,0.00014593216],"category_scores_gemma":[0.0017532109,0.00042983657,0.00009368278,0.00057461654,0.00013862776,0.00010262095,0.00033068095,0.0023876983,0.0000030133842],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.077370204,0.002258018,0.7452857,0.00003313847,0.00021743748,0.00021167278,0.007520869,0.15874138,0.0002598725,0.0000073918613,0.000043118285,0.008051229],"study_design_scores_gemma":[0.039869,0.001165842,0.9179301,0.0012113467,0.000057489433,0.000008840157,0.0024718705,0.0366778,0.000009262556,0.00001377338,0.0001531306,0.00043151146],"about_ca_topic_score_codex":0.012096017,"about_ca_topic_score_gemma":0.0019393766,"teacher_disagreement_score":0.17264447,"about_ca_system_score_codex":0.0016481496,"about_ca_system_score_gemma":0.0012359419,"threshold_uncertainty_score":0.9999138},"labels":[],"label_agreement":null},{"id":"W4307228966","doi":"10.1002/cam4.5341","title":"Clustering on longitudinal quality‐of‐life measurements using growth mixture models for clinical prognosis: Implementation on <scp>CCTG</scp>/<scp>AGITG CO</scp>.20 trial","year":2022,"lang":"en","type":"article","venue":"Cancer Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; Princess Margaret Cancer Centre; Ottawa Hospital; University of Ottawa; Western University; Public Health Ontario; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Princess Margaret Cancer Foundation","keywords":"Proportional hazards model; Quality of life (healthcare); Longitudinal study; Cetuximab; Medicine; Oncology; Survival analysis; Internal medicine; Randomized controlled trial; Repeated measures design; Log-rank test; Placebo; Cancer; Colorectal cancer; Statistics; Mathematics; Pathology","score_opus":0.2769192114288026,"score_gpt":0.4900335824736043,"score_spread":0.2131143710448017,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4307228966","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9625313,0.0017783723,0.023466019,0.0045097936,0.003388682,0.0031630332,0.0001331543,0.00010784135,0.00092179934],"genre_scores_gemma":[0.9868437,0.0002613724,0.0011099243,0.0065860795,0.003838368,0.0006887586,0.00029284795,0.00011291347,0.0002660345],"study_design_codex":"observational","study_design_gemma":"randomized_trial","domain_scores_codex":[0.99443275,0.0005025681,0.0016941718,0.0008298903,0.0018761316,0.0006645012],"domain_scores_gemma":[0.9960929,0.0016532062,0.0009618238,0.0004056744,0.0003669061,0.00051947305],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.004580311,0.00041539816,0.0012879976,0.00035775715,0.0003875934,0.000023746816,0.00032116368,0.00014383107,0.000076504555],"category_scores_gemma":[0.0042093745,0.00035104412,0.00031974114,0.00042829974,0.00025862487,0.00011408806,0.00011033491,0.0011253967,0.0000014742266],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.024695124,0.0036758748,0.5325895,0.004274924,0.004345093,0.00011699952,0.008383212,0.038274303,0.013921689,0.0012215801,0.32988936,0.038612362],"study_design_scores_gemma":[0.4768619,0.03347267,0.06281924,0.0051410613,0.004682697,0.0001033163,0.016913427,0.33930397,0.003943673,0.0015437575,0.05447797,0.00073632307],"about_ca_topic_score_codex":0.0004864224,"about_ca_topic_score_gemma":0.000027433245,"teacher_disagreement_score":0.46977025,"about_ca_system_score_codex":0.0004913701,"about_ca_system_score_gemma":0.0005882978,"threshold_uncertainty_score":0.99989414},"labels":[],"label_agreement":null},{"id":"W4307264735","doi":"10.3389/fonc.2022.952763","title":"Prognostic value of PET/CT and MR-based baseline radiomics among patients with non-metastatic nasopharyngeal carcinoma","year":2022,"lang":"en","type":"article","venue":"Frontiers in Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; Women's College Hospital; University of Toronto; University Health Network; Mount Sinai Hospital","funders":"","keywords":"Medicine; Nasopharyngeal carcinoma; Radiomics; PET-CT; Radiology; Radiation therapy; Nuclear medicine; Magnetic resonance imaging; Proportional hazards model; Overall survival; Progression-free survival; Retrospective cohort study; Positron emission tomography; Oncology; Internal medicine","score_opus":0.005413627188174206,"score_gpt":0.2503483817863246,"score_spread":0.24493475459815042,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4307264735","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9924622,0.00028855092,0.004964993,0.0007497973,0.0005779389,0.00069812324,0.000022290413,0.00001715407,0.00021892371],"genre_scores_gemma":[0.9540916,0.0000122757,0.044809524,0.0007460961,0.00003542863,0.00007832246,0.00014476139,0.000034435263,0.00004754379],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99837756,0.00029227004,0.00038468145,0.00032480815,0.00031269348,0.00030798867],"domain_scores_gemma":[0.9991109,0.00027256345,0.00020509832,0.00019342976,0.000055034947,0.00016298247],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00071555976,0.000165997,0.0006337124,0.00035408651,0.000090591006,0.000005281573,0.00012937518,0.00001144807,0.00005027686],"category_scores_gemma":[0.00039975572,0.0001465224,0.000050880586,0.00030837517,0.00034629536,0.000040569223,0.00007779815,0.0006326731,3.4066392e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00066660735,0.00058964745,0.98341763,0.00015051362,0.00006557805,0.001780399,0.00015553336,0.0023286163,0.000025509431,0.000014177777,0.0028322549,0.007973534],"study_design_scores_gemma":[0.010950619,0.002788004,0.60013324,0.00006269438,0.000250035,0.0002701017,0.0003401963,0.38311553,0.000024850893,0.000051943887,0.0018488109,0.00016400375],"about_ca_topic_score_codex":0.00014706748,"about_ca_topic_score_gemma":0.0000057300654,"teacher_disagreement_score":0.38328442,"about_ca_system_score_codex":0.00030209564,"about_ca_system_score_gemma":0.00041520622,"threshold_uncertainty_score":0.59750104},"labels":[],"label_agreement":null},{"id":"W4307357561","doi":"10.1101/2022.10.21.513161","title":"PiDeeL: Pathway-Informed Deep Learning Model for Survival Analysis and Pathological Classification of Gliomas","year":2022,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Bilim Akademisi; Centre National de la Recherche Scientifique","keywords":"Computer science; Artificial intelligence; Deep learning; Concordance; Machine learning; Recall; Pathological; Data mining; Medicine; Pathology; Internal medicine; Psychology; Cognitive psychology","score_opus":0.026144701592407088,"score_gpt":0.28104915761931615,"score_spread":0.25490445602690903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4307357561","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8142949,0.00057709066,0.1833814,0.00040401012,0.0002708843,0.00073827914,0.000087794775,0.00021971244,0.000025966834],"genre_scores_gemma":[0.9677673,0.00036486657,0.031178126,0.00012797218,0.0001649579,0.0002799092,0.0000088657425,0.00009017294,0.00001780707],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970463,0.00018792928,0.0008240566,0.0008986986,0.000579849,0.00046319977],"domain_scores_gemma":[0.99742347,0.00033495732,0.00073655206,0.00075203093,0.0004218299,0.00033113573],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0017615793,0.00042229766,0.0011717818,0.0007133698,0.0002384699,0.00007579033,0.00029255057,0.00040445675,0.00004860143],"category_scores_gemma":[0.0023182975,0.00041071087,0.00041089964,0.0008224518,0.00021794738,0.00007488953,0.00042943525,0.0014150073,0.0000012573977],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00057756866,0.00053596235,0.3751108,0.0030403559,0.002597733,0.00011966913,0.00021929809,0.02652769,0.5864634,0.004451887,0.00006835838,0.00028728956],"study_design_scores_gemma":[0.0009872153,0.00014576326,0.27701545,0.00010239618,0.0013737201,6.1885444e-8,0.000024602428,0.71685594,0.0022347234,0.000009368039,0.00085628335,0.00039445754],"about_ca_topic_score_codex":0.000029323472,"about_ca_topic_score_gemma":0.0000024440762,"teacher_disagreement_score":0.69032824,"about_ca_system_score_codex":0.0002306899,"about_ca_system_score_gemma":0.00051721046,"threshold_uncertainty_score":0.9998345},"labels":[],"label_agreement":null},{"id":"W4307891591","doi":"10.1038/s41597-022-01770-z","title":"Publisher Correction: An analysis-ready and quality controlled resource for pediatric brain white-matter research","year":2022,"lang":"en","type":"erratum","venue":"Scientific Data","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Université de Montréal; Institut Universitaire en Santé Mentale de Québec; Western University; Polytechnique Montréal; Concordia University; University of Toronto","funders":"","keywords":"White matter; Resource (disambiguation); Quality (philosophy); White paper; Computer science; Data science; Medicine; Political science; Physics","score_opus":0.10684226474260987,"score_gpt":0.43110366615052953,"score_spread":0.32426140140791965,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4307891591","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0054038274,0.012528478,0.007504659,0.16756643,0.48491696,0.013663516,0.018792586,0.00086549396,0.28875807],"genre_scores_gemma":[0.00041307457,0.000029592144,0.00048122063,0.0015083478,0.0030222808,0.00013215162,0.15543292,0.00006938552,0.838911],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.992256,0.0013777466,0.0008602189,0.0025183316,0.0021993925,0.00078831596],"domain_scores_gemma":[0.99217296,0.0017718861,0.00041946615,0.0044926424,0.0005698627,0.00057317445],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.033612125,0.0003226309,0.0012888883,0.0021087916,0.0013694316,0.001946962,0.001753943,0.0003009458,0.0027758959],"category_scores_gemma":[0.014294455,0.00027322673,0.00021454283,0.0027908203,0.00063037477,0.0004683096,0.0015258021,0.0031309589,0.000029105724],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031235386,0.0001861759,0.015752716,0.00026094637,0.00033763843,0.000012824673,0.0002307278,0.000013189475,0.0000026550977,0.000022094617,0.9813814,0.0014872813],"study_design_scores_gemma":[0.0026195077,0.00012540637,0.010398758,0.000027660226,0.001475435,0.000015595693,0.00057580945,0.036285266,4.160761e-8,0.000059666076,0.94815,0.00026687636],"about_ca_topic_score_codex":0.000416779,"about_ca_topic_score_gemma":0.0002453346,"teacher_disagreement_score":0.55015296,"about_ca_system_score_codex":0.00016594729,"about_ca_system_score_gemma":0.0008716256,"threshold_uncertainty_score":0.999972},"labels":[],"label_agreement":null},{"id":"W4307931638","doi":"10.32920/21288258.v1","title":"Medical Augmentation (Med-Aug) for Optimal Data Augmentation in Medical Deep Learning Networks","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Toronto Metropolitan University; St. Michael's Hospital","funders":"","keywords":"Generalizability theory; Computer science; Artificial intelligence; Segmentation; Medical imaging; Machine learning; CMA-ES; Adaptation (eye); Set (abstract data type); Deep learning; Selection (genetic algorithm); Population; Variety (cybernetics); Evolution strategy; Mathematics; Medicine; Evolutionary algorithm","score_opus":0.0309639871549168,"score_gpt":0.38649467759675654,"score_spread":0.3555306904418397,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4307931638","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06689708,0.001649597,0.8925668,0.029227858,0.0032715613,0.0024563873,0.000028963203,0.00039187283,0.0035098726],"genre_scores_gemma":[0.7887283,0.0067977477,0.09720084,0.017771114,0.0063261385,0.001869148,0.07551312,0.0005110751,0.0052825385],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9938067,0.00042557943,0.0012168222,0.0013255078,0.002543501,0.0006818849],"domain_scores_gemma":[0.9970189,0.0009159457,0.00037901112,0.0008677708,0.000087362125,0.0007310529],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0057549486,0.00043340516,0.0008870849,0.00039010373,0.00023218417,0.00010066631,0.001141532,0.0007266084,0.01154529],"category_scores_gemma":[0.0055901324,0.0004122919,0.00018812934,0.00029006787,0.00019111496,0.0001508891,0.0026352592,0.0054109306,0.00000960982],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011669489,0.0009038454,0.038075116,0.0012959726,0.00062701304,0.0010910658,0.0013279273,0.17286202,0.000026878854,0.0008929904,0.023404283,0.75832593],"study_design_scores_gemma":[0.0048806407,0.00020674129,0.0037015649,0.00054461736,0.00021942302,0.00013549808,0.000737772,0.9693563,0.0000040871737,0.000115012794,0.019732429,0.0003658887],"about_ca_topic_score_codex":0.00072954915,"about_ca_topic_score_gemma":0.00016795896,"teacher_disagreement_score":0.7964943,"about_ca_system_score_codex":0.00046161655,"about_ca_system_score_gemma":0.001041074,"threshold_uncertainty_score":0.99983287},"labels":[],"label_agreement":null},{"id":"W4307931723","doi":"10.32920/21288258","title":"Medical Augmentation (Med-Aug) for Optimal Data Augmentation in Medical Deep Learning Networks","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Toronto Metropolitan University; St. Michael's Hospital","funders":"","keywords":"Generalizability theory; Computer science; Artificial intelligence; Segmentation; Medical imaging; Machine learning; CMA-ES; Set (abstract data type); Adaptation (eye); Deep learning; Selection (genetic algorithm); Population; Variety (cybernetics); Data mining; Evolution strategy; Mathematics; Medicine; Evolutionary algorithm","score_opus":0.0309639871549168,"score_gpt":0.38649467759675654,"score_spread":0.3555306904418397,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4307931723","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06689708,0.001649597,0.8925668,0.029227858,0.0032715613,0.0024563873,0.000028963203,0.00039187283,0.0035098726],"genre_scores_gemma":[0.7887283,0.0067977477,0.09720084,0.017771114,0.0063261385,0.001869148,0.07551312,0.0005110751,0.0052825385],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9938067,0.00042557943,0.0012168222,0.0013255078,0.002543501,0.0006818849],"domain_scores_gemma":[0.9970189,0.0009159457,0.00037901112,0.0008677708,0.000087362125,0.0007310529],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0057549486,0.00043340516,0.0008870849,0.00039010373,0.00023218417,0.00010066631,0.001141532,0.0007266084,0.01154529],"category_scores_gemma":[0.0055901324,0.0004122919,0.00018812934,0.00029006787,0.00019111496,0.0001508891,0.0026352592,0.0054109306,0.00000960982],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011669489,0.0009038454,0.038075116,0.0012959726,0.00062701304,0.0010910658,0.0013279273,0.17286202,0.000026878854,0.0008929904,0.023404283,0.75832593],"study_design_scores_gemma":[0.0048806407,0.00020674129,0.0037015649,0.00054461736,0.00021942302,0.00013549808,0.000737772,0.9693563,0.0000040871737,0.000115012794,0.019732429,0.0003658887],"about_ca_topic_score_codex":0.00072954915,"about_ca_topic_score_gemma":0.00016795896,"teacher_disagreement_score":0.7964943,"about_ca_system_score_codex":0.00046161655,"about_ca_system_score_gemma":0.001041074,"threshold_uncertainty_score":0.99983287},"labels":[],"label_agreement":null},{"id":"W4307942647","doi":"10.3390/cancers14215314","title":"Prognostic Value of [18F]-FDG PET/CT Radiomics Combined with Sarcopenia Status among Patients with Advanced Gastroesophageal Cancer","year":2022,"lang":"en","type":"article","venue":"Cancers","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; Toronto General Hospital; University of Toronto; University Health Network","funders":"","keywords":"Medicine; Sarcopenia; Radiomics; Proportional hazards model; Internal medicine; Esophageal cancer; Cancer; Oncology; Overall survival; Radiology","score_opus":0.00391748552763938,"score_gpt":0.24071555050142096,"score_spread":0.23679806497378159,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4307942647","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9974733,0.00035125503,0.0001851902,0.00021222439,0.00028797748,0.00097549654,0.00007953699,0.000058183643,0.0003768209],"genre_scores_gemma":[0.9958928,0.00006602728,0.0028066232,0.00048279442,0.000047994294,0.00024991756,0.00014493924,0.00007813289,0.0002307536],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99800515,0.00007963474,0.0002966182,0.00039870685,0.0006866811,0.00053318456],"domain_scores_gemma":[0.9988789,0.00007666738,0.00028335783,0.0003051299,0.00013377906,0.00032215932],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015739306,0.00024002994,0.00050663564,0.0001270917,0.00018873987,0.000014826358,0.00017728991,0.0000064378964,0.00027648907],"category_scores_gemma":[0.00008864054,0.00018703335,0.00006184976,0.00041325486,0.00033414876,0.00009984189,0.00007410493,0.0006218153,8.47075e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0023684627,0.00009462497,0.9188258,0.00014648717,0.00021349367,0.000479726,0.00025721514,0.07218995,0.000078571735,0.000045162924,0.0005793387,0.004721189],"study_design_scores_gemma":[0.022204507,0.0064526773,0.9272745,0.0006116718,0.0006173013,0.00019215106,0.00065476494,0.03771365,0.00025157712,0.000018007138,0.0035304604,0.00047872774],"about_ca_topic_score_codex":0.0010768528,"about_ca_topic_score_gemma":0.000046492634,"teacher_disagreement_score":0.034476303,"about_ca_system_score_codex":0.0014349974,"about_ca_system_score_gemma":0.0013312156,"threshold_uncertainty_score":0.76269984},"labels":[],"label_agreement":null},{"id":"W4307993096","doi":"10.32920/21291015","title":"Comparison of methods for texture analysis of QUS parametric images in the characterization of breast lesions","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University; Health Sciences Centre; University of Waterloo; University of Toronto; Sunnybrook Health Science Centre","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Terry Fox Foundation; California HIV/AIDS Research Program","keywords":"Breast cancer; Medicine; Linear discriminant analysis; Malignancy; Parametric statistics; Grading (engineering); Nuclear medicine; Radiology; Mathematics; Pathology; Cancer; Statistics; Internal medicine; Biology","score_opus":0.04968786595113791,"score_gpt":0.4663154014217416,"score_spread":0.4166275354706037,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4307993096","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49027717,0.0004584884,0.5050663,0.002346381,0.00014625382,0.0008760671,0.00023466925,0.000013337164,0.0005813415],"genre_scores_gemma":[0.9577466,0.00014534543,0.040773127,0.00010334286,0.00002712759,0.00005068483,0.0010366905,0.000014017192,0.00010305213],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9981582,0.0003994466,0.0008091758,0.00024188899,0.00027414522,0.00011713953],"domain_scores_gemma":[0.9976065,0.0009714395,0.0007634497,0.00046384556,0.00015857085,0.000036158784],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019580335,0.00013714236,0.0012027402,0.0011860951,0.000027925358,0.0000070731257,0.0002831364,0.000119909375,0.00023888198],"category_scores_gemma":[0.0009800822,0.000090700545,0.00041501355,0.0016696649,0.00009841757,0.000015173195,0.00017579725,0.00070456095,4.6954227e-8],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029496476,0.0018523133,0.48092946,0.0025399104,0.0027535453,0.0000022525303,0.0033248249,0.01504119,0.1116593,0.0010603081,0.00040609096,0.38013583],"study_design_scores_gemma":[0.00042207591,0.000097589305,0.6293261,0.00011620708,0.0029778732,0.0000034502314,0.0007030746,0.36448368,0.0012232382,0.00008863373,0.00047131185,0.00008677786],"about_ca_topic_score_codex":0.00043533917,"about_ca_topic_score_gemma":0.0000039963843,"teacher_disagreement_score":0.46746945,"about_ca_system_score_codex":0.000031941625,"about_ca_system_score_gemma":0.00010126145,"threshold_uncertainty_score":0.3698661},"labels":[],"label_agreement":null},{"id":"W4307993097","doi":"10.32920/21291015.v1","title":"Comparison of methods for texture analysis of QUS parametric images in the characterization of breast lesions","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University; Health Sciences Centre; University of Waterloo; University of Toronto; Sunnybrook Health Science Centre","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Terry Fox Foundation; California HIV/AIDS Research Program","keywords":"Medicine; Breast cancer; Grading (engineering); Malignancy; Linear discriminant analysis; Parametric statistics; Nuclear medicine; Radiology; Mathematics; Pathology; Cancer; Statistics; Internal medicine; Biology","score_opus":0.04968786595113791,"score_gpt":0.4663154014217416,"score_spread":0.4166275354706037,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4307993097","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49027717,0.0004584884,0.5050663,0.002346381,0.00014625382,0.0008760671,0.00023466925,0.000013337164,0.0005813415],"genre_scores_gemma":[0.9577466,0.00014534543,0.040773127,0.00010334286,0.00002712759,0.00005068483,0.0010366905,0.000014017192,0.00010305213],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9981582,0.0003994466,0.0008091758,0.00024188899,0.00027414522,0.00011713953],"domain_scores_gemma":[0.9976065,0.0009714395,0.0007634497,0.00046384556,0.00015857085,0.000036158784],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019580335,0.00013714236,0.0012027402,0.0011860951,0.000027925358,0.0000070731257,0.0002831364,0.000119909375,0.00023888198],"category_scores_gemma":[0.0009800822,0.000090700545,0.00041501355,0.0016696649,0.00009841757,0.000015173195,0.00017579725,0.00070456095,4.6954227e-8],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029496476,0.0018523133,0.48092946,0.0025399104,0.0027535453,0.0000022525303,0.0033248249,0.01504119,0.1116593,0.0010603081,0.00040609096,0.38013583],"study_design_scores_gemma":[0.00042207591,0.000097589305,0.6293261,0.00011620708,0.0029778732,0.0000034502314,0.0007030746,0.36448368,0.0012232382,0.00008863373,0.00047131185,0.00008677786],"about_ca_topic_score_codex":0.00043533917,"about_ca_topic_score_gemma":0.0000039963843,"teacher_disagreement_score":0.46746945,"about_ca_system_score_codex":0.000031941625,"about_ca_system_score_gemma":0.00010126145,"threshold_uncertainty_score":0.3698661},"labels":[],"label_agreement":null},{"id":"W4307995537","doi":"10.1007/s00259-022-06001-6","title":"Joint EANM/SNMMI guideline on radiomics in nuclear medicine","year":2022,"lang":"en","type":"letter","venue":"European Journal of Nuclear Medicine and Molecular Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":151,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Universitätsklinikum Essen; National Cancer Institute; Society of Nuclear Medicine and Molecular Imaging","keywords":"Radiomics; Guideline; Medical physics; Medicine; Computer science; Radiology; Pathology","score_opus":0.017796059599483084,"score_gpt":0.2732405385382184,"score_spread":0.2554444789387353,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4307995537","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035066318,0.0036406782,0.0002975036,0.96680444,0.0012645893,0.0002933001,0.0000043217683,0.00006115245,0.02412738],"genre_scores_gemma":[0.011991402,0.0019755564,0.0025985583,0.97615594,0.0065772175,8.2835584e-7,0.00009061949,0.0004914833,0.000118389675],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99353266,0.0011355026,0.002315023,0.000698085,0.0016202794,0.00069847907],"domain_scores_gemma":[0.9970636,0.00018237486,0.001315507,0.00069195277,0.00025624677,0.00049036584],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004775106,0.00070115115,0.0018353069,0.0017993202,0.00019122925,0.000051615883,0.0005834518,0.0001272365,0.0014162041],"category_scores_gemma":[0.002199407,0.0005450988,0.00034188776,0.0004427154,0.0007093148,0.00010810403,0.00029821362,0.00796758,0.00002455465],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021901623,0.000058653335,0.00004791609,0.0002008737,0.00017336455,0.07831584,0.0013476572,0.00004299855,0.00508986,0.00007206949,0.9038738,0.0105579635],"study_design_scores_gemma":[0.0063104015,0.0021305284,0.00014360198,0.0033870728,0.00055379316,0.008476072,0.0010460606,0.002514857,0.0000058829464,0.00006654013,0.97494227,0.00042289862],"about_ca_topic_score_codex":0.000055060795,"about_ca_topic_score_gemma":1.309262e-7,"teacher_disagreement_score":0.0710685,"about_ca_system_score_codex":0.00028936868,"about_ca_system_score_gemma":0.000120382334,"threshold_uncertainty_score":0.99970007},"labels":[],"label_agreement":null},{"id":"W4308090756","doi":"10.1109/ccece49351.2022.9918266","title":"Ultrasound Operator Variance Classification for Agency in Artificial Intelligence Support of Cyber-Physical Systems","year":2022,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Artificial intelligence; Deep learning; Machine learning; Leverage (statistics); Operator (biology)","score_opus":0.03712047651019929,"score_gpt":0.3356277662203763,"score_spread":0.29850728971017704,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4308090756","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8114615,0.00006930942,0.179399,0.0031762777,0.000724898,0.001093686,0.000027196465,0.000052196494,0.003995901],"genre_scores_gemma":[0.9965527,0.000010821109,0.0020964325,0.0002543978,0.0001752179,0.00016721514,0.000053581098,0.000016079992,0.00067356025],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99887294,0.000064661384,0.00038762565,0.0002345831,0.00026289627,0.00017729253],"domain_scores_gemma":[0.99936426,0.00021923563,0.00009134476,0.00019155662,0.0000605397,0.00007304076],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006407746,0.00008409486,0.00026067114,0.00009397874,0.00007662345,0.00001416599,0.00012190759,0.000025976015,0.00019595449],"category_scores_gemma":[0.00035620318,0.0000755726,0.00006501273,0.00025794553,0.00005988882,0.000043431286,0.000028605555,0.00027237023,0.000005885027],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00050650764,0.0022503978,0.013234546,0.00056043256,0.00010093443,0.000054658598,0.0044903844,0.010720471,0.44368076,0.46883288,0.006879106,0.048688926],"study_design_scores_gemma":[0.00097608287,0.0014144172,0.015072854,0.00008848624,0.00012877969,0.0002573776,0.0039662165,0.94279325,0.00781927,0.005054068,0.021996588,0.00043260172],"about_ca_topic_score_codex":0.00011392873,"about_ca_topic_score_gemma":0.0000021496717,"teacher_disagreement_score":0.93207276,"about_ca_system_score_codex":0.000088868794,"about_ca_system_score_gemma":0.00014801108,"threshold_uncertainty_score":0.3081761},"labels":[],"label_agreement":null},{"id":"W4308378595","doi":"10.1136/jitc-2022-sitc2022.0052","title":"52 Digital pathology training effectiveness for the evaluation of PD-L1 expression in multiple tumor indications","year":2022,"lang":"en","type":"article","venue":"Regular and Young Investigator Award Abstracts","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"National Cancer Institute; Government of Ontario; Ontario Institute for Cancer Research","keywords":"Digital pathology; Concordance; Medicine; Digital image analysis; Test (biology); Medical physics; Artificial intelligence; Computer science; Pathology; Computer vision; Internal medicine","score_opus":0.04122079206106776,"score_gpt":0.3111353124665198,"score_spread":0.26991452040545205,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4308378595","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.996677,0.0005454302,0.00067377905,0.0009607605,0.00020143583,0.00080176606,0.000024386389,0.0000192719,0.00009620954],"genre_scores_gemma":[0.9986697,0.000009114213,0.00067974126,0.00017315324,0.000060564158,0.0002982336,0.00007408601,0.0000195187,0.000015893705],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9986905,0.00018838688,0.00029406667,0.00023501823,0.00040978627,0.00018223781],"domain_scores_gemma":[0.9988901,0.0005387266,0.0001687382,0.00018645987,0.00007402511,0.000141953],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025630083,0.00010479307,0.00023683916,0.000117474665,0.00023270062,0.000021317419,0.00009321195,0.000039655723,0.000009777903],"category_scores_gemma":[0.0039693913,0.00008114587,0.00006439478,0.0001463731,0.00023381345,0.00008292159,0.000055922752,0.00032583706,3.7476937e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00064008427,0.0006165301,0.411416,0.00073682604,0.00018454234,0.00010307297,0.011119444,0.025733238,0.4573691,0.00085820485,0.00080659916,0.09041639],"study_design_scores_gemma":[0.003708653,0.00020654086,0.9216999,0.00026555112,0.00017212266,0.00034056517,0.001620122,0.05809037,0.009514578,0.00239805,0.0018352346,0.00014835883],"about_ca_topic_score_codex":0.000024782117,"about_ca_topic_score_gemma":0.000002924384,"teacher_disagreement_score":0.5102839,"about_ca_system_score_codex":0.00007670996,"about_ca_system_score_gemma":0.0003287919,"threshold_uncertainty_score":0.4752019},"labels":[],"label_agreement":null},{"id":"W4308460469","doi":"10.1117/1.jmi.9.6.066001","title":"Predicting recurrence risks in lung cancer patients using multimodal radiomics and random survival forests","year":2022,"lang":"en","type":"article","venue":"Journal of Medical Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"National Cancer Institute","keywords":"Medicine; Concordance; Cohort; Stage (stratigraphy); Radiology; Lung cancer; Nomogram; Cancer; Oncology; Internal medicine","score_opus":0.018243162863232416,"score_gpt":0.3565861531020472,"score_spread":0.3383429902388148,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4308460469","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98422533,0.0036920349,0.005631044,0.00445408,0.0017268877,0.00020679148,0.00000534288,0.000012963186,0.00004551529],"genre_scores_gemma":[0.997078,0.00057168026,0.0011124549,0.00062565174,0.0005641152,0.0000063925345,0.0000044879253,0.00003177677,0.00000541857],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99636495,0.00030804824,0.0008729996,0.00023539578,0.0018226819,0.00039591047],"domain_scores_gemma":[0.9983393,0.00042481802,0.00050239376,0.00010840663,0.00013657736,0.000488517],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003776478,0.00017257784,0.00059390784,0.00036947112,0.0002117086,0.000042897846,0.00026308783,0.00005684463,0.00015829311],"category_scores_gemma":[0.0030893348,0.00014846477,0.0001200993,0.0003021174,0.00016733402,0.00019891554,0.0002557329,0.0022918126,1.1740002e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031999053,0.00017121035,0.9186307,0.0000914161,0.000055061562,0.0005005059,0.00063127244,0.0016345314,0.00010644931,0.000006437112,0.000197558,0.07765485],"study_design_scores_gemma":[0.0106091825,0.0000480144,0.19166975,0.00070978946,0.000116054725,0.0007175575,0.0003101046,0.7953534,0.000007933494,0.000031741914,0.00030990652,0.00011654052],"about_ca_topic_score_codex":0.00080793834,"about_ca_topic_score_gemma":0.00001671241,"teacher_disagreement_score":0.7937189,"about_ca_system_score_codex":0.00037375288,"about_ca_system_score_gemma":0.0004944475,"threshold_uncertainty_score":0.99569124},"labels":[],"label_agreement":null},{"id":"W4308662651","doi":"10.1007/s00330-022-09229-w","title":"Deep learning–based harmonization of CT reconstruction kernels towards improved clinical task performance","year":2022,"lang":"en","type":"article","venue":"European Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Basic and Applied Basic Research Foundation of Guangdong Province; China Scholarship Council; Postdoctoral Research Foundation of China; National Natural Science Foundation of China","keywords":"Medicine; Convolutional neural network; Artificial intelligence; Neuroradiology; Feature (linguistics); Kernel (algebra); Deep learning; Radiology; Pattern recognition (psychology); Nuclear medicine; Computer science; Mathematics","score_opus":0.01696325247613244,"score_gpt":0.286316956899957,"score_spread":0.26935370442382456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4308662651","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97737163,0.00020534162,0.016011976,0.0008071634,0.0009985458,0.00018790209,0.0000021309265,0.000104559695,0.004310748],"genre_scores_gemma":[0.99495167,0.00012540745,0.0030695267,0.000874309,0.00033365918,0.0000066090684,0.000107495034,0.00004248537,0.0004888329],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975884,0.0011514605,0.0005618414,0.00032347263,0.00015302206,0.00022180499],"domain_scores_gemma":[0.999178,0.00010744799,0.00030801765,0.00022604439,0.000065970205,0.00011450078],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018898168,0.00012282874,0.0003668711,0.00013259369,0.00017781288,0.000006231324,0.00015578564,0.000025454512,0.00038879766],"category_scores_gemma":[0.0008276266,0.00011578999,0.00012452937,0.00018866918,0.00024532917,0.000036863257,0.00009113838,0.0010119227,0.000017870761],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040020695,0.00015751529,0.28877506,0.000082479106,0.00010328839,0.00013655971,0.00020137709,0.013227727,0.007391089,0.000042237745,0.00074532104,0.68873715],"study_design_scores_gemma":[0.0031759387,0.001877933,0.26179788,0.000029642884,0.000099704,0.0017246,0.00009587074,0.6928759,0.0002782666,0.000009613954,0.037860803,0.00017386352],"about_ca_topic_score_codex":0.000010983181,"about_ca_topic_score_gemma":1.2994589e-7,"teacher_disagreement_score":0.6885633,"about_ca_system_score_codex":0.00006293771,"about_ca_system_score_gemma":0.00009847442,"threshold_uncertainty_score":0.47217786},"labels":[],"label_agreement":null},{"id":"W4308806081","doi":"10.1016/j.jocd.2022.11.001","title":"Automatic Soft Tissue Detection Failure in DXA: The 4% Fat Error","year":2022,"lang":"en","type":"article","venue":"Journal of Clinical Densitometry","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba; University of Calgary","funders":"","keywords":"Medicine; Soft tissue; Pathology","score_opus":0.03065922261214789,"score_gpt":0.4028190268195757,"score_spread":0.37215980420742784,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4308806081","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9808819,0.000354302,0.0020112358,0.014521924,0.0019435693,0.00013406071,5.7278186e-7,0.000018875506,0.00013350854],"genre_scores_gemma":[0.9943238,0.00003528302,0.0017600238,0.0024358653,0.0012527836,0.0000028429388,8.523135e-7,0.000020518144,0.00016806542],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9970337,0.0005041071,0.0013133377,0.00014879,0.0007921273,0.00020790625],"domain_scores_gemma":[0.9974908,0.0013390051,0.0006408278,0.00021852368,0.00011344348,0.00019739695],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.004434013,0.00010813065,0.00061368255,0.00035854222,0.00014521742,0.000026574098,0.00023196392,0.00008679076,0.00034204996],"category_scores_gemma":[0.00647492,0.00006935725,0.00027939386,0.00070944085,0.00011056033,0.00007141373,0.000115956165,0.0029491566,0.000014457124],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00060280465,0.0007812066,0.27194515,0.00010889301,0.0002927237,0.002508064,0.00040487762,0.0011204815,0.0038381598,0.00002985864,0.01723141,0.7011364],"study_design_scores_gemma":[0.006884731,0.0026006545,0.76632136,0.00027115532,0.0004119465,0.008092749,0.001664112,0.093323685,0.0003605436,0.0008531582,0.11895871,0.00025717393],"about_ca_topic_score_codex":0.000014961113,"about_ca_topic_score_gemma":0.000009391006,"teacher_disagreement_score":0.7008792,"about_ca_system_score_codex":0.00009585101,"about_ca_system_score_gemma":0.00013156405,"threshold_uncertainty_score":0.9993511},"labels":[],"label_agreement":null},{"id":"W4308977915","doi":"10.1093/neuonc/noac209.200","title":"RADT-10. THE LOST METASTASES: DEEP LEARNING’S POTENTIAL IN RADIOSURGERY QUALITY ASSURANCE","year":2022,"lang":"en","type":"article","venue":"Neuro-Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Montreal Neurological Institute and Hospital; Centre Hospitalier de l’Université de Montréal; Centre intégré de santé et de services sociaux de la Montérégie-Centre; Centre intégré de santé et de services sociaux de Chaudière-Appalaches; Centre Intégré de Santé et de Services Sociaux des Laurentides; GDI Integrated Facility Services (Canada)","funders":"","keywords":"Medicine; Radiosurgery; False positive paradox; Radiology; Quality assurance; Medical physics; Radiation therapy; Nuclear medicine; Artificial intelligence; Computer science; Pathology","score_opus":0.017400297816076417,"score_gpt":0.32343560148428885,"score_spread":0.3060353036682124,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4308977915","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92401254,0.0015428478,0.0011619241,0.05999844,0.0026410974,0.0007017691,0.00001243497,0.00013927571,0.009789665],"genre_scores_gemma":[0.98782957,0.00019988773,0.000379231,0.0103388,0.00038468928,0.000083157036,0.00004661883,0.000045796547,0.00069225684],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99514014,0.0027061263,0.0006046043,0.00048442467,0.0005495736,0.0005151223],"domain_scores_gemma":[0.9971725,0.0019319394,0.00028047658,0.0003886655,0.000052556014,0.00017389334],"candidate_categories":["research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0030466905,0.00020063439,0.0006539385,0.00018685551,0.0003505396,0.000023500737,0.0003096042,0.00008356578,0.0024434868],"category_scores_gemma":[0.003250208,0.00015920655,0.0002100179,0.000469237,0.0002606901,0.000057125915,0.0002561301,0.0024628257,0.00007559815],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00393953,0.0024351054,0.13344826,0.0002568798,0.00039507702,0.013515029,0.0035803816,0.044690315,0.18315704,0.0011447042,0.10474672,0.50869095],"study_design_scores_gemma":[0.0031631398,0.0007976694,0.022527525,0.000010553175,0.000107583546,0.0014519487,0.0007433897,0.015413967,0.0001820708,0.000100244455,0.9553032,0.0001987194],"about_ca_topic_score_codex":0.00021437622,"about_ca_topic_score_gemma":0.00002579145,"teacher_disagreement_score":0.8505565,"about_ca_system_score_codex":0.00030365438,"about_ca_system_score_gemma":0.0003716488,"threshold_uncertainty_score":0.99983853},"labels":[],"label_agreement":null},{"id":"W4309321702","doi":"10.1148/ryai.220028","title":"Generalizability of Machine Learning Models: Quantitative Evaluation of Three Methodological Pitfalls","year":2022,"lang":"en","type":"article","venue":"Radiology Artificial Intelligence","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":131,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Jewish General Hospital; Montreal General Hospital; McGill University Health Centre; University of Calgary","funders":"National Institutes of Health; Fondation de l'Association des radiologistes du Québec","keywords":"Generalizability theory; Computer science; Machine learning; Artificial intelligence; Wilcoxon signed-rank test; Random forest; Overfitting; Feature selection; Artificial neural network; Data mining; Statistics; Mathematics","score_opus":0.38306536606431396,"score_gpt":0.44256822241720156,"score_spread":0.0595028563528876,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4309321702","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6120318,0.001431336,0.38465223,0.0007371339,0.0002205247,0.0003307601,0.000009071054,0.0000274512,0.000559691],"genre_scores_gemma":[0.9668601,0.00007201919,0.032767396,0.00013947467,0.00004650734,0.000045951074,0.000034464316,0.000014368122,0.000019681596],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9953931,0.0025879464,0.0007916331,0.00038267137,0.00060374226,0.00024089818],"domain_scores_gemma":[0.9977637,0.0011609957,0.0003704182,0.0002753542,0.00034842297,0.00008113873],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01018057,0.00014372834,0.000624999,0.00017346352,0.00016975994,0.0000031972818,0.00021754969,0.00008780934,0.0013213361],"category_scores_gemma":[0.0049775452,0.00012624923,0.0001713369,0.00036015958,0.00057532813,0.000048433463,0.00014157461,0.0008010471,0.000003901308],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00073879596,0.0003888506,0.013406813,0.000059559756,0.00015781862,0.000011044318,0.0013796767,0.7387374,0.04099403,0.117296666,0.000041198346,0.08678812],"study_design_scores_gemma":[0.0001305366,0.00095175894,0.0016936265,0.000012061152,0.00016777168,0.00007545032,0.0004379895,0.8822901,0.005764395,0.108294964,0.00008241535,0.00009890389],"about_ca_topic_score_codex":0.00028433348,"about_ca_topic_score_gemma":0.000015831916,"teacher_disagreement_score":0.35482833,"about_ca_system_score_codex":0.000113824535,"about_ca_system_score_gemma":0.00018471241,"threshold_uncertainty_score":0.9995916},"labels":[],"label_agreement":null},{"id":"W4309405648","doi":"10.17879/freeneuropathology-2021-3671","title":"61st Annual Meeting of the Canadian Association of Neuropathologists Association canadienne des neuropathologistes (CANP-ACNP) - Meeting Abstracts.","year":2021,"lang":"en","type":"article","venue":"PubMed","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Neuropathology; Presentation (obstetrics); Library science; Psychology; Medicine; Pathology; Computer science; Surgery","score_opus":0.013007381882669677,"score_gpt":0.2257707000156529,"score_spread":0.21276331813298321,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4309405648","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9774467,0.00015349346,0.0000036266192,0.0056384364,0.0005583652,0.0002581304,0.000047098394,0.000027469649,0.015866691],"genre_scores_gemma":[0.9974554,0.000045147634,0.00034385262,0.0007051954,0.00013568296,0.000035691246,0.000017156584,0.000024253679,0.0012376265],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9977178,0.00039964909,0.00053223106,0.0002553265,0.00040803626,0.00068693515],"domain_scores_gemma":[0.99771976,0.00041915223,0.0007500716,0.0002467553,0.00057617,0.00028805796],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0034077205,0.00013125867,0.000346022,0.00010288663,0.00020923311,0.000030210993,0.00015746363,0.00013880788,0.000007712984],"category_scores_gemma":[0.040372778,0.00010946885,0.000129933,0.00041634942,0.00012445636,0.000069333415,0.000066336965,0.0005069903,9.0740235e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008299959,0.000041311832,0.9784658,0.00009217775,0.00004320926,0.00012872284,0.0005422974,0.000441204,0.0033689113,0.000039168783,0.00035018532,0.016478745],"study_design_scores_gemma":[0.00039274976,0.000018408844,0.99302965,0.00007376472,0.000116425814,0.00005772451,0.0001831735,0.00023396169,0.003481304,0.00006136354,0.0022641341,0.00008735587],"about_ca_topic_score_codex":0.13738193,"about_ca_topic_score_gemma":0.30575797,"teacher_disagreement_score":0.16837604,"about_ca_system_score_codex":0.0011074945,"about_ca_system_score_gemma":0.0003797391,"threshold_uncertainty_score":0.96771055},"labels":[],"label_agreement":null},{"id":"W4309535738","doi":"10.18280/rces.090301","title":"Auto-Diagnosis of Lung Cancer with the Proposed Feature Fusion-Based Hybrid Deep Model","year":2022,"lang":"en","type":"article","venue":"Review of Computer Engineering Studies","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Artificial intelligence; Computer science; Pattern recognition (psychology); Classifier (UML); Cluster analysis","score_opus":0.007933937557527589,"score_gpt":0.28334890313191613,"score_spread":0.27541496557438855,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4309535738","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.037602607,0.74031323,0.18374786,0.036410484,0.0003731433,0.0013825354,0.000017060042,0.00011664411,0.000036417932],"genre_scores_gemma":[0.7949268,0.11540776,0.080999136,0.007358796,0.00035722513,0.00070164644,0.000026832748,0.000102595295,0.00011920272],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990706,0.000037897702,0.00022418304,0.0001543433,0.0003691654,0.00014381691],"domain_scores_gemma":[0.9992914,0.00017417104,0.00013757586,0.00022481299,0.00013443035,0.000037598493],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035798567,0.00014686376,0.0005842756,0.000058928108,0.00008142611,0.0000030383956,0.00014899345,0.000009204522,0.000014296119],"category_scores_gemma":[0.00006973028,0.00008486606,0.00011881252,0.00021975405,0.000057650406,0.000015425167,0.000121283454,0.00033225404,8.439609e-8],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002232546,0.00008948097,0.0024684346,0.030340414,0.000669411,0.00002543293,0.00034499876,0.91749144,0.000102246515,0.00008669646,0.024028072,0.024331056],"study_design_scores_gemma":[0.0004366032,0.000122056575,0.000632221,0.009189399,0.00036096587,0.000017369865,0.000007954337,0.98109263,0.00011429564,0.0000016999678,0.007928192,0.000096621894],"about_ca_topic_score_codex":0.0000059414274,"about_ca_topic_score_gemma":2.4687665e-7,"teacher_disagreement_score":0.7573242,"about_ca_system_score_codex":0.000065620436,"about_ca_system_score_gemma":0.000084077474,"threshold_uncertainty_score":0.34607372},"labels":[],"label_agreement":null},{"id":"W4309563912","doi":"10.1038/s41746-022-00709-3","title":"Improving the repeatability of deep learning models with Monte Carlo dropout","year":2022,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":90,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"National Eye Institute; Natural Sciences and Engineering Research Council of Canada; Eunice Kennedy Shriver National Institute of Child Health and Human Development; Genentech; Mitacs; National Cancer Institute; National Institutes of Health; U.S. Department of Health and Human Services; Polytechnique Montréal; Research to Prevent Blindness; Foundation for the National Institutes of Health","keywords":"Dropout (neural networks); Monte Carlo method; Repeatability; Computer science; Deep learning; Artificial intelligence; Machine learning; Statistics; Mathematics","score_opus":0.011748409491715036,"score_gpt":0.24371177153516085,"score_spread":0.2319633620434458,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4309563912","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9575963,0.001251958,0.011498598,0.0069574183,0.0002215306,0.00055134937,0.000007589055,0.00013942985,0.021775829],"genre_scores_gemma":[0.9977105,0.000015783702,0.0003527315,0.0005813985,0.00019494862,0.000035698486,0.000026083959,0.000041436437,0.0010413895],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978965,0.00008769244,0.00043621432,0.00036256033,0.0009045686,0.00031244228],"domain_scores_gemma":[0.9986767,0.00028824768,0.00023627654,0.00049509865,0.00012414962,0.00017948127],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008788048,0.00018813567,0.000487541,0.000101257436,0.0002762426,0.000019895924,0.00023354785,0.00003074327,0.00014302786],"category_scores_gemma":[0.0011840365,0.00010709345,0.00008610076,0.00034646952,0.00052856153,0.0001662945,0.00020719058,0.0011050513,0.0000013695895],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0020817823,0.0005882133,0.18723878,0.00069150876,0.00045702312,0.00052981597,0.011793653,0.058051027,0.0035439867,0.002434112,0.0007920764,0.731798],"study_design_scores_gemma":[0.0053853556,0.0050682095,0.0076485234,0.0003073425,0.00039138464,0.0011414308,0.012403209,0.95352226,0.0000967554,0.0007209414,0.0129491165,0.0003654497],"about_ca_topic_score_codex":0.00037367787,"about_ca_topic_score_gemma":0.000003763721,"teacher_disagreement_score":0.8954713,"about_ca_system_score_codex":0.00011155392,"about_ca_system_score_gemma":0.000088298184,"threshold_uncertainty_score":0.4800959},"labels":[],"label_agreement":null},{"id":"W4309688772","doi":"10.3389/fbioe.2022.1082794","title":"MRI-based machine learning model: A potential modality for predicting cognitive dysfunction in patients with type 2 diabetes mellitus","year":2022,"lang":"en","type":"article","venue":"Frontiers in Bioengineering and Biotechnology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Health Commission of Shanxi Province","keywords":"Type 2 Diabetes Mellitus; Receiver operating characteristic; Cognition; Logistic regression; Artificial intelligence; Support vector machine; Montreal Cognitive Assessment; Medicine; Magnetic resonance imaging; Machine learning; Dementia; Internal medicine; Diabetes mellitus; Computer science; Disease; Radiology; Psychiatry","score_opus":0.0035824906698849273,"score_gpt":0.19814010800240578,"score_spread":0.19455761733252086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4309688772","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7774484,0.0006882712,0.22016582,0.0009553333,0.00024704158,0.00035168877,0.000015591293,0.00012384886,0.000003966168],"genre_scores_gemma":[0.97926086,0.0000564578,0.02029684,0.000098198034,0.00001966811,0.000060876686,0.00016471258,0.000029143903,0.000013269007],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989898,0.000031920456,0.00019843382,0.0003185002,0.00014348909,0.00031781042],"domain_scores_gemma":[0.9997361,0.000030961353,0.000060354065,0.000089327084,0.000032605916,0.00005067738],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031242057,0.00014646669,0.0002955226,0.0004888457,0.00010949909,0.000009184554,0.00006087727,0.00012877055,0.000002739522],"category_scores_gemma":[0.00019288438,0.0001358196,0.000029039142,0.0003684035,0.00009128343,0.00003285307,0.000056354627,0.00085822993,6.634438e-8],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00079459854,0.0001525597,0.689722,0.00013476018,0.000058174002,0.000010025673,0.000067972556,0.28378654,0.00049040886,0.000022446095,0.00003070492,0.024729846],"study_design_scores_gemma":[0.0043447698,0.00097160204,0.016901301,0.00008606999,0.000048198417,0.0000030280082,0.00011730165,0.97685826,0.00025371608,0.00007121019,0.00020245112,0.00014208125],"about_ca_topic_score_codex":0.000026655494,"about_ca_topic_score_gemma":0.0000015597632,"teacher_disagreement_score":0.6930717,"about_ca_system_score_codex":0.00012044964,"about_ca_system_score_gemma":0.000035650373,"threshold_uncertainty_score":0.55385625},"labels":[],"label_agreement":null},{"id":"W4309778459","doi":"10.1002/prm2.12089","title":"Using ensemble learning and genetic algorithm on magnetic resonance imaging radiomics to classify molecular subtypes of breast cancer","year":2022,"lang":"en","type":"article","venue":"Precision Medical Sciences","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"National Science and Technology Council; Ministry of Science and Technology, Taiwan; Ministry of Education","keywords":"Magnetic resonance imaging; Breast cancer; Triple-negative breast cancer; Ensemble learning; Progesterone receptor; Radiomics; Cancer; Estrogen receptor; Medicine; Artificial intelligence; Algorithm; Oncology; Machine learning; Internal medicine; Computer science; Radiology","score_opus":0.017540075607773223,"score_gpt":0.3318394478027785,"score_spread":0.3142993721950053,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4309778459","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95965594,0.008800791,0.019875512,0.010562811,0.00039019305,0.0002582549,0.0000063125003,0.000036197343,0.00041400053],"genre_scores_gemma":[0.9475053,0.0006162848,0.04951803,0.0020493853,0.00013707335,0.00002198151,0.0000018013393,0.000023279954,0.00012686905],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99688524,0.00020874028,0.0003455813,0.0004992378,0.0016997644,0.00036145945],"domain_scores_gemma":[0.9990101,0.00027412406,0.0000987666,0.00013427442,0.000049245453,0.0004335153],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013851356,0.00014178696,0.00031009526,0.00024179435,0.00040778605,0.000035216293,0.00028047292,0.000040403334,0.0007115248],"category_scores_gemma":[0.0007754816,0.00011435465,0.00005595125,0.0006833617,0.00044612508,0.000042349886,0.00031605907,0.0006042935,0.0000020815635],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005534696,0.000057027537,0.038918026,0.00001525939,0.000004013389,0.00015096423,0.00015432216,0.0025002547,0.008323097,0.00008324777,0.00018405428,0.9495544],"study_design_scores_gemma":[0.0010935888,0.0006623922,0.054307286,0.00042456522,0.000049615395,0.0012822634,0.00029292222,0.9256435,0.0005772736,0.00047725832,0.014953566,0.00023576018],"about_ca_topic_score_codex":0.00021646704,"about_ca_topic_score_gemma":0.0000014496849,"teacher_disagreement_score":0.94931865,"about_ca_system_score_codex":0.00009026754,"about_ca_system_score_gemma":0.00030474568,"threshold_uncertainty_score":0.7790697},"labels":[],"label_agreement":null},{"id":"W4309855388","doi":"10.3390/curroncol29120711","title":"Stratification of Length of Stay Prediction following Surgical Cytoreduction in Advanced High-Grade Serous Ovarian Cancer Patients Using Artificial Intelligence; the Leeds L-AI-OS Score","year":2022,"lang":"en","type":"article","venue":"Current Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine; Serous ovarian cancer; Ovarian cancer; Serous fluid; Risk stratification; Internal medicine; Oncology; Cancer; Pathology","score_opus":0.0781115393051682,"score_gpt":0.40614089463307523,"score_spread":0.328029355327907,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4309855388","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9923941,0.00030726867,0.002654726,0.00094134524,0.0031118344,0.00052742875,0.000022465,0.000016920721,0.00002389925],"genre_scores_gemma":[0.99914616,0.000079420424,0.00032219276,0.000021023798,0.00022301445,0.000070325535,0.00011971104,0.000014389756,0.0000037433242],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982442,0.00030307562,0.0006312255,0.0002447218,0.00038113844,0.0001955948],"domain_scores_gemma":[0.99926364,0.00010219151,0.00032278374,0.00016121147,0.000095592666,0.00005460124],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00064165884,0.00011068198,0.0003288489,0.00018403304,0.00013349792,0.0000053984413,0.00011644366,0.00006247346,0.00006929407],"category_scores_gemma":[0.00014135893,0.0000915964,0.00008805387,0.00042035623,0.00013223164,0.00007711485,0.00005716646,0.00069121283,2.3816229e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00083758624,0.0025754937,0.30805612,0.00015572835,0.00011987465,0.000017618378,0.002802467,0.04245616,0.010244617,0.003782818,0.000055992852,0.6288955],"study_design_scores_gemma":[0.0076573375,0.004841535,0.42490512,0.00077247876,0.0010003395,0.00010620059,0.007310582,0.5308323,0.007626298,0.0062713255,0.008097388,0.0005790941],"about_ca_topic_score_codex":0.00029287755,"about_ca_topic_score_gemma":0.000027486449,"teacher_disagreement_score":0.6283164,"about_ca_system_score_codex":0.00049712945,"about_ca_system_score_gemma":0.0002956688,"threshold_uncertainty_score":0.37351927},"labels":[],"label_agreement":null},{"id":"W4310122300","doi":"10.1212/wnl.0000000000201596","title":"Radiomics-Derived Brain Age Predicts Functional Outcome After Acute Ischemic Stroke","year":2022,"lang":"en","type":"article","venue":"Neurology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Institute of Biomedical Imaging and Bioengineering; National Institute of Neurological Disorders and Stroke; National Heart, Lung, and Blood Institute; Agence Nationale de la Recherche","keywords":"Stroke (engine); Medicine; Radiomics; Ischemic stroke; Outcome (game theory); Cardiology; Brain ischemia; Internal medicine; Acute stroke; Ischemia; Radiology; Tissue plasminogen activator","score_opus":0.012024480884135538,"score_gpt":0.26386423888626104,"score_spread":0.2518397580021255,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4310122300","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95532674,0.00010943785,0.0008899532,0.039831284,0.0012486454,0.00020681428,0.000031196567,0.00012864328,0.0022273047],"genre_scores_gemma":[0.9433706,0.000009056918,0.00034881514,0.05245374,0.00035075526,0.00010249565,0.00010863424,0.000045031953,0.003210914],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99841195,0.00015258811,0.00029936185,0.0004150283,0.0003384624,0.0003826098],"domain_scores_gemma":[0.9992429,0.00016354473,0.000083371255,0.00030063334,0.000021028352,0.00018852222],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000291216,0.0001655144,0.00033769815,0.00016347825,0.0001524734,0.000012303747,0.00014984334,0.000083587314,0.0018469496],"category_scores_gemma":[0.00019637414,0.00016120753,0.00014282999,0.000120509096,0.00015892215,0.000037556434,0.00022742675,0.0014362179,0.000039688934],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.007306084,0.00043817988,0.4733278,0.00008123019,0.0005115129,0.012119632,0.00050555216,0.0007333438,0.38446912,0.00022054854,0.11362566,0.0066613588],"study_design_scores_gemma":[0.006247984,0.0020887002,0.40046337,0.0000038096296,0.00028916987,0.005464093,0.000016181533,0.011665247,0.0003535805,0.00009987783,0.5730167,0.0002913142],"about_ca_topic_score_codex":0.000023189745,"about_ca_topic_score_gemma":0.0000018285909,"teacher_disagreement_score":0.45939103,"about_ca_system_score_codex":0.000045593013,"about_ca_system_score_gemma":0.00007543999,"threshold_uncertainty_score":0.9990655},"labels":[],"label_agreement":null},{"id":"W4310370526","doi":"10.1148/rg.220066","title":"Universal Liver Imaging Lexicon: Imaging Atlas for Research and Clinical Practice","year":2022,"lang":"en","type":"article","venue":"Radiographics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; University of Toronto","funders":"Department of Science and Technology of Sichuan Province; National Natural Science Foundation of China","keywords":"Medicine; Atlas (anatomy); Lexicon; Medical physics; Clinical Practice; Clinical imaging; Radiology; Artificial intelligence; Family medicine; Anatomy","score_opus":0.05836767890696545,"score_gpt":0.4268881700065081,"score_spread":0.36852049109954266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4310370526","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5963043,0.041842803,0.043483626,0.2732898,0.004645649,0.0050097057,0.00009739355,0.00089017133,0.034436565],"genre_scores_gemma":[0.9571735,0.0029217743,0.03276517,0.0050552594,0.0010359036,0.00006246799,0.000071428854,0.00010134661,0.0008131162],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99741846,0.0004149501,0.00037789895,0.0005409916,0.0007077264,0.0005399589],"domain_scores_gemma":[0.99646574,0.0024108875,0.00012175163,0.000340643,0.0003160289,0.000344948],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005626636,0.00015090077,0.00031235447,0.0005990789,0.0008929305,0.00008571516,0.00020524021,0.00004402232,0.00005042198],"category_scores_gemma":[0.0019986257,0.00015436987,0.00020060732,0.0008062239,0.00072385377,0.0002032797,0.00027912747,0.0019269064,0.0000022221768],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016169309,0.0011266607,0.62504166,0.00025749922,0.00054000074,0.0025646957,0.0013824317,0.000044374276,0.0004889433,0.052225944,0.106185935,0.2085249],"study_design_scores_gemma":[0.0037318068,0.0005972337,0.0132889245,0.000058995436,0.00029408268,0.0020960618,0.0029677018,0.13534254,0.0000076231704,0.0017612719,0.8396025,0.00025131434],"about_ca_topic_score_codex":0.00018157401,"about_ca_topic_score_gemma":0.0000023112455,"teacher_disagreement_score":0.7334165,"about_ca_system_score_codex":0.00010500403,"about_ca_system_score_gemma":0.00025232075,"threshold_uncertainty_score":0.8371557},"labels":[],"label_agreement":null},{"id":"W4310693661","doi":"10.1016/j.neuroimage.2022.119787","title":"Single-timepoint low-dimensional characterization and classification of acute versus chronic multiple sclerosis lesions using machine learning","year":2022,"lang":"en","type":"article","venue":"NeuroImage","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; NeuroRx Research (Canada); Montreal Neurological Institute and Hospital","funders":"Biogen","keywords":"Lesion; Medicine; Magnetic resonance imaging; Multiple sclerosis; Artificial intelligence; Radiology; Pattern recognition (psychology); Pathology; Computer science","score_opus":0.05474468099063359,"score_gpt":0.2821085431625266,"score_spread":0.227363862171893,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4310693661","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9962017,0.00009718555,0.0019675442,0.0010876125,0.00027945597,0.00020798332,0.00003115242,0.00006128926,0.000066076675],"genre_scores_gemma":[0.9975694,0.00005230343,0.0015512755,0.00020401912,0.000082916056,0.0000092086275,0.00034210226,0.00003933137,0.00014946373],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99874234,0.0001459163,0.00028218704,0.00030357786,0.00033932875,0.00018665417],"domain_scores_gemma":[0.99933064,0.00012686843,0.0002068834,0.00017797085,0.000052744228,0.00010488228],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002290691,0.0001275059,0.00023156423,0.00015497576,0.0003392178,0.000020128087,0.00006672818,0.00003163292,0.00014595817],"category_scores_gemma":[0.00024251305,0.00013038258,0.00006595984,0.00022269717,0.000106022395,0.000092937735,0.00016429432,0.00055542827,0.0000026674286],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000255277,0.00013211217,0.00585392,0.000040807998,0.00003747666,0.000023629756,0.00007875655,0.0006366357,0.9802619,0.000018329127,0.00001725392,0.01264385],"study_design_scores_gemma":[0.0030032613,0.00064648397,0.13301185,0.000078306446,0.00016763284,0.00012569096,0.000021173099,0.84937006,0.011250179,0.0000023895975,0.002190261,0.00013268515],"about_ca_topic_score_codex":0.000037838145,"about_ca_topic_score_gemma":0.0000010376408,"teacher_disagreement_score":0.9690118,"about_ca_system_score_codex":0.00013479426,"about_ca_system_score_gemma":0.00008065448,"threshold_uncertainty_score":0.53168476},"labels":[],"label_agreement":null},{"id":"W4310704956","doi":"10.1016/j.radonc.2022.11.023","title":"External validation of a CT-based radiomics signature in oropharyngeal cancer: Assessing sources of variation","year":2022,"lang":"en","type":"article","venue":"Radiotherapy and Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"London Health Sciences Foundation","keywords":"Radiomics; Variation (astronomy); Signature (topology); Medicine; Radiology; Mathematics; Physics","score_opus":0.011840340378337371,"score_gpt":0.32738614361029356,"score_spread":0.3155458032319562,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4310704956","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9854238,0.0040594405,0.008338081,0.0017290981,0.0001944181,0.00016207038,0.000005171435,0.000008293898,0.000079634905],"genre_scores_gemma":[0.9928528,0.00043642175,0.005782169,0.0007573831,0.000106474625,0.000018374985,0.000010605473,0.000013328547,0.000022460934],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990664,0.00021872291,0.0002814867,0.00015034204,0.00016725832,0.00011576917],"domain_scores_gemma":[0.99942714,0.0001886166,0.00023655962,0.00007909686,0.000025750029,0.000042850217],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005841407,0.00007604802,0.00037844444,0.00019253339,0.00005655199,0.0000053730214,0.00006200345,0.00004448112,0.0002005436],"category_scores_gemma":[0.00004178238,0.0000716349,0.000044491582,0.00018362445,0.00008523814,0.000043815606,0.00001326467,0.00035795927,2.9304804e-8],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00095213327,0.0005492331,0.20318858,0.00023684459,0.000096668846,0.0001519081,0.0028557994,0.028180806,0.5675136,0.00039193893,0.00010467808,0.19577785],"study_design_scores_gemma":[0.026097387,0.0038804684,0.2977314,0.0003923017,0.00028662122,0.0008742704,0.0007603246,0.60987884,0.045430094,0.00063955976,0.013596541,0.00043217948],"about_ca_topic_score_codex":0.0003281796,"about_ca_topic_score_gemma":0.0000051130014,"teacher_disagreement_score":0.58169806,"about_ca_system_score_codex":0.00031425068,"about_ca_system_score_gemma":0.00030814586,"threshold_uncertainty_score":0.29211864},"labels":[],"label_agreement":null},{"id":"W4310941112","doi":"10.1038/s41598-022-25389-7","title":"Performance sensitivity analysis of brain metastasis stereotactic radiosurgery outcome prediction using MRI radiomics","year":2022,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"London Health Sciences Centre; Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Western University; London Health Sciences Foundation; Government of Ontario","keywords":"Radiomics; Radiosurgery; Brain metastasis; Sensitivity (control systems); Medicine; Metastasis; Radiology; Internal medicine; Cancer; Radiation therapy","score_opus":0.025826411412497724,"score_gpt":0.29996463761299413,"score_spread":0.27413822620049644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4310941112","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99116045,0.00008522892,0.0035481448,0.0004981206,0.0042041107,0.00024385272,0.000018786975,0.000060204817,0.00018108852],"genre_scores_gemma":[0.99706334,0.0000050513304,0.0017929763,0.00016626084,0.00006181194,0.000007899383,0.00017944499,0.000022417697,0.0007007912],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966772,0.00026883424,0.00095502374,0.0006724389,0.0010983838,0.00032810878],"domain_scores_gemma":[0.99796396,0.00018053547,0.0006574658,0.00087258476,0.00014157656,0.00018385859],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0082736155,0.00016047947,0.0007086715,0.0012293083,0.00055492757,0.00006436149,0.00006932018,0.000037503167,0.00024705668],"category_scores_gemma":[0.0007301601,0.00015345353,0.0004162973,0.0026586957,0.00025670766,0.00017671601,0.0001343733,0.0004318032,7.942414e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044017932,0.00015941623,0.8808493,0.00009277862,0.0009845367,0.000899943,0.000365676,0.07635551,0.034729306,0.0000056472304,0.0016552365,0.003858627],"study_design_scores_gemma":[0.0002938025,0.000061183426,0.1064216,0.00002660586,0.0027161227,0.0031290643,0.00015666125,0.87873876,0.0012656483,0.000019493013,0.0070054345,0.00016559602],"about_ca_topic_score_codex":0.00009945731,"about_ca_topic_score_gemma":0.000002421148,"teacher_disagreement_score":0.8023833,"about_ca_system_score_codex":0.00028380012,"about_ca_system_score_gemma":0.00024786935,"threshold_uncertainty_score":0.6257653},"labels":[],"label_agreement":null},{"id":"W4311115345","doi":"10.1038/s41467-022-32329-6","title":"Author Correction: A deep learning system accurately classifies primary and metastatic cancers using passenger mutation patterns","year":2022,"lang":"en","type":"erratum","venue":"Nature Communications","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"SickKids Foundation; BC Cancer Agency; University of British Columbia; Prostate Cancer Canada; Université de Montréal; Hospital for Sick Children; Lunenfeld-Tanenbaum Research Institute; Mount Sinai Hospital; University of Calgary; Princess Margaret Cancer Centre; Simon Fraser University; University of Ottawa; McGill University; McGill University and Génome Québec Innovation Centre; Toronto General Hospital; University of Toronto; University Health Network; Genome Canada; Canada's Michael Smith Genome Sciences Centre; Vector Institute; Institute of Cancer Research; Ontario Institute for Cancer Research","funders":"Medical Research Council","keywords":"Mutation; Computer science; Deep learning; Primary (astronomy); Artificial intelligence; Computational biology; Bioinformatics; Biology; Genetics; Gene","score_opus":0.04290191066007118,"score_gpt":0.3581553867686085,"score_spread":0.31525347610853727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4311115345","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02132153,0.5005294,0.034056712,0.075351976,0.21203901,0.008402497,0.0004868503,0.0038748188,0.1439372],"genre_scores_gemma":[0.8488471,0.01292116,0.01876522,0.0027880091,0.0020770256,0.00057699654,0.012744532,0.00043091396,0.10084908],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972882,0.0007625352,0.0005539661,0.00047571937,0.0005994947,0.00032008716],"domain_scores_gemma":[0.99714184,0.00065152324,0.00059662055,0.0011626743,0.00025212305,0.00019520016],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0007279951,0.00036759832,0.00072248443,0.00041569123,0.0011862803,0.0001472345,0.0005063033,0.0005130241,0.00009476056],"category_scores_gemma":[0.0009219907,0.0003582106,0.0001636164,0.00048569829,0.00020158094,0.00014042328,0.0004841366,0.010847944,0.0000032433868],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016251174,0.00026347156,0.0057882736,0.0060080276,0.0020175318,0.00040397714,0.005198815,0.0023885283,0.00034133613,0.001095668,0.902733,0.07359884],"study_design_scores_gemma":[0.00053840195,0.00009571716,0.006136624,0.0013299905,0.0011476167,0.0011676069,0.0038992711,0.40425095,0.0000018465223,0.000007689812,0.58105993,0.0003643649],"about_ca_topic_score_codex":0.0003979563,"about_ca_topic_score_gemma":0.0002163106,"teacher_disagreement_score":0.82752556,"about_ca_system_score_codex":0.0015770163,"about_ca_system_score_gemma":0.00075153663,"threshold_uncertainty_score":0.999887},"labels":[],"label_agreement":null},{"id":"W4311281764","doi":"10.1007/s00330-022-09323-z","title":"Prediction of incident cardiovascular events using machine learning and CMR radiomics","year":2022,"lang":"en","type":"article","venue":"European Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Engineering and Physical Sciences Research Council; Universitat de Barcelona; British Heart Foundation; Medical Research Council; National Institute for Health and Care Research","keywords":"Medicine; Cardiology; Ventricle; Internal medicine; Atrial fibrillation; Neuroradiology; Magnetic resonance imaging; Heart failure; Myocardial infarction; Stroke (engine); Radiology; Neurology","score_opus":0.019407958486170208,"score_gpt":0.2529520359804782,"score_spread":0.233544077494308,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4311281764","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9891392,0.005930561,0.0030136348,0.00017096015,0.00040107875,0.00018704844,0.000012049631,0.000061474624,0.0010840166],"genre_scores_gemma":[0.9966434,0.00048650315,0.002112721,0.00019242869,0.0002325104,0.000003351373,0.00007071585,0.000050396215,0.00020792043],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9978463,0.0010117627,0.00034857925,0.0003083354,0.0002623479,0.00022264812],"domain_scores_gemma":[0.99942106,0.00006190809,0.00014769589,0.00021702786,0.00003069241,0.00012159107],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00172691,0.00013352981,0.00043882584,0.00018491021,0.00022997998,0.0000045297825,0.000104851024,0.000027617527,0.00008382325],"category_scores_gemma":[0.00031165808,0.00013145852,0.00016497466,0.00015210833,0.0001236094,0.000030674517,0.00024580327,0.00073634303,0.0000022659679],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029010364,0.00015192229,0.87946856,0.0001686689,0.0011416816,0.000818837,0.0012913833,0.029103262,0.055356547,0.00020221545,0.0003078926,0.031698942],"study_design_scores_gemma":[0.008242642,0.0019029111,0.42164937,0.000110040855,0.0011596567,0.023076791,0.00051346957,0.31507865,0.00023449083,0.000116225,0.22746944,0.00044632034],"about_ca_topic_score_codex":0.000079804246,"about_ca_topic_score_gemma":2.6371387e-7,"teacher_disagreement_score":0.45781916,"about_ca_system_score_codex":0.00010524213,"about_ca_system_score_gemma":0.000039992025,"threshold_uncertainty_score":0.5360723},"labels":[],"label_agreement":null},{"id":"W4311488877","doi":"10.1177/08465371221135782","title":"A Brief Review of Artificial Intelligence in Genitourinary Oncological Imaging","year":2022,"lang":"en","type":"review","venue":"Canadian Association of Radiologists Journal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre","funders":"","keywords":"Medicine; Genitourinary system; Malignancy; Cancer imaging; Medical imaging; Prostate cancer; Medical physics; Robustness (evolution); Radiology; Artificial intelligence; Cancer; Pathology; Computer science; Internal medicine","score_opus":0.04823056226934392,"score_gpt":0.3692305095963146,"score_spread":0.3209999473269707,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4311488877","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000014843185,0.9949026,0.00016883062,0.0019630925,0.0005719481,0.0004684881,0.00004100506,0.000008458874,0.0018607051],"genre_scores_gemma":[0.00007533699,0.99738073,0.0010036723,0.00086563453,0.00039821662,0.00002016718,0.00009824448,0.000028607974,0.00012937155],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9959163,0.000992241,0.0018342694,0.0002730625,0.00051133684,0.00047279196],"domain_scores_gemma":[0.9962267,0.0007823381,0.002173292,0.00021554917,0.0001616974,0.00044038115],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004988636,0.00025794917,0.0023610746,0.0008102631,0.000102472026,0.000016514048,0.00038523486,0.00024183196,0.0011886634],"category_scores_gemma":[0.0099855885,0.00022065252,0.0006918904,0.000671779,0.00013423209,0.000048344995,0.00005101078,0.0025320863,0.0000044680132],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000065685126,0.00005548098,0.0009861274,0.012119581,0.00012506935,0.0008808696,0.000030326244,0.0000057461175,2.451197e-7,0.00016668659,0.0073879627,0.97823536],"study_design_scores_gemma":[0.00012379489,0.00015012106,0.00028762323,0.031254325,0.00048720496,0.0026675928,0.000033480428,0.00014896871,8.424452e-8,0.00016217255,0.964509,0.00017562753],"about_ca_topic_score_codex":0.0015574305,"about_ca_topic_score_gemma":0.00040921965,"teacher_disagreement_score":0.9780597,"about_ca_system_score_codex":0.0045534987,"about_ca_system_score_gemma":0.004441005,"threshold_uncertainty_score":0.9997691},"labels":[],"label_agreement":null},{"id":"W4311681152","doi":"10.22215/etd/2022-15210","title":"Characterization and Classification of Fibrillar Collagen Networks using Gray-Level Texture Analysis","year":2022,"lang":"en","type":"dissertation","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Extracellular matrix; Gray level; Principal component analysis; Fibrillogenesis; Artificial intelligence; Cell biology; Computer science; Biomedical engineering; Computational biology; Biological system; Pattern recognition (psychology); Biology; Medicine; Biochemistry; In vitro; Image (mathematics)","score_opus":0.020365803429106592,"score_gpt":0.31293069348765845,"score_spread":0.29256489005855185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4311681152","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9460809,0.0004883774,0.051008444,0.00017784412,0.00028730067,0.00037819575,0.000032692646,0.000038111157,0.0015080832],"genre_scores_gemma":[0.97065455,0.0005530328,0.0015250421,0.00015435652,0.00017403137,0.0000110337005,0.017779153,0.00004717802,0.009101624],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986943,0.00006969761,0.0004218236,0.00032704617,0.0003433352,0.00014376752],"domain_scores_gemma":[0.9990409,0.000046423036,0.0004471328,0.00023010731,0.00013931746,0.000096126765],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027440453,0.00018506871,0.00059107976,0.00045568479,0.00012327425,0.000027642,0.000065587454,0.00021708064,0.0005375753],"category_scores_gemma":[0.00011834257,0.00016901139,0.00015673868,0.0008692231,0.000033459906,0.000045939338,0.000021300802,0.0002734065,4.3963357e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007485732,0.00025371922,0.20231652,0.0019655176,0.0059242877,0.000044562054,0.0029755423,0.006478012,0.6223431,0.0013465587,0.0008658006,0.15473777],"study_design_scores_gemma":[0.00032021754,0.000046989346,0.45871747,0.00008798349,0.0029352051,0.0000128160855,0.00046994546,0.5341088,0.00016401024,0.000007470995,0.00296449,0.00016455672],"about_ca_topic_score_codex":0.00011231981,"about_ca_topic_score_gemma":0.000032791733,"teacher_disagreement_score":0.6221791,"about_ca_system_score_codex":0.00006693453,"about_ca_system_score_gemma":0.00010846702,"threshold_uncertainty_score":0.6892084},"labels":[],"label_agreement":null},{"id":"W4311960301","doi":"10.3390/app122412614","title":"Lung Nodules Localization and Report Analysis from Computerized Tomography (CT) Scan Using a Novel Machine Learning Approach","year":2022,"lang":"en","type":"article","venue":"Applied Sciences","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":53,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"","keywords":"Nodule (geology); Lung cancer; Radiology; Computed tomography; Computer science; Medicine; Tomography; Artificial intelligence; Pathology","score_opus":0.017104199214363524,"score_gpt":0.2753790537237313,"score_spread":0.25827485450936777,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4311960301","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5862787,0.0002558196,0.41165906,0.00026984626,0.000056420264,0.00015958954,0.0000049088994,0.00006708698,0.0012486193],"genre_scores_gemma":[0.9151718,0.00000949662,0.08386289,0.00062760327,0.00006406529,0.00001509847,0.00021356033,0.000011825326,0.00002366486],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99821883,0.000058113794,0.00030206982,0.000574955,0.00060964434,0.00023637307],"domain_scores_gemma":[0.99940145,0.000072027186,0.0002077279,0.0001665287,0.000023184379,0.00012907099],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011273085,0.00013888176,0.00036833689,0.000464036,0.0010089154,0.00010480023,0.00016126395,0.000018173769,0.000066271066],"category_scores_gemma":[0.0000540862,0.00012064139,0.00008962339,0.001995748,0.00035757202,0.00005918062,0.00020722163,0.00035493658,1.9819512e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007260706,0.00025854094,0.56913567,0.000053333322,0.0006672668,0.000096651,0.0012975157,0.38559797,0.032318756,0.0013766303,0.00010390315,0.0090211565],"study_design_scores_gemma":[0.0006213056,0.000031827512,0.008697629,0.000007209295,0.0004228941,0.00019043818,0.00051388756,0.9874234,0.00004292239,0.00008231903,0.0018247908,0.00014135441],"about_ca_topic_score_codex":0.0011634484,"about_ca_topic_score_gemma":0.0000038502703,"teacher_disagreement_score":0.6018254,"about_ca_system_score_codex":0.00004850802,"about_ca_system_score_gemma":0.00006738724,"threshold_uncertainty_score":0.7759863},"labels":[],"label_agreement":null},{"id":"W4312086585","doi":"10.1002/alz.067980","title":"TRIAD multi‐dimensional biobank for biomarker discovery","year":2022,"lang":"en","type":"article","venue":"Alzheimer s & Dementia","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Douglas Mental Health University Institute; McGill University; McGill University Health Centre","funders":"","keywords":"Biobank; Biomarker; Cohort; Dementia; Medicine; Cohort study; Urine; Oncology; Biomarker discovery; Disease; Internal medicine; Pathology; Bioinformatics; Biology","score_opus":0.03784395397338416,"score_gpt":0.3227765898987711,"score_spread":0.284932635925387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312086585","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5522006,0.31518304,0.06317288,0.04658648,0.012401653,0.0061633326,0.00042388652,0.0007446752,0.0031234226],"genre_scores_gemma":[0.977498,0.000017621449,0.017779516,0.0037332932,0.00017433925,0.00019047834,0.00031440463,0.00004848308,0.00024388508],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99856585,0.000068045534,0.00030547107,0.00035559115,0.0003682772,0.00033675408],"domain_scores_gemma":[0.99935216,0.00011074695,0.0001011293,0.00025838873,0.000041140753,0.00013641622],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00057659467,0.00015767108,0.0002515692,0.00012476135,0.0003610355,0.00003506945,0.00014074576,0.000033975582,0.0007113917],"category_scores_gemma":[0.00009515487,0.00014089588,0.00020625256,0.00016437334,0.000075386386,0.00009660254,0.0001805137,0.00026347043,0.000018959161],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0026067097,0.0025921774,0.037439328,0.000064182634,0.047597013,0.00028257913,0.0004897074,0.00065940333,0.084179536,0.0033657812,0.3801142,0.44060937],"study_design_scores_gemma":[0.013063407,0.0006378601,0.02739578,0.000037029524,0.022471594,0.00022752928,0.00015194023,0.09145955,0.0035932763,0.00035317574,0.8400066,0.00060228206],"about_ca_topic_score_codex":0.0000680467,"about_ca_topic_score_gemma":0.0000014803035,"teacher_disagreement_score":0.45989236,"about_ca_system_score_codex":0.0000132803825,"about_ca_system_score_gemma":0.000105349005,"threshold_uncertainty_score":0.778924},"labels":[],"label_agreement":null},{"id":"W4312087161","doi":"10.1002/alz.067924","title":"TRIAD multi‐dimensional biobank for biomarker discovery","year":2022,"lang":"en","type":"article","venue":"Alzheimer s & Dementia","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Douglas Mental Health University Institute; McGill University; McGill University Health Centre","funders":"","keywords":"Biobank; Biomarker; Cohort; Dementia; Medicine; Cohort study; Biomarker discovery; Oncology; Urine; Internal medicine; Disease; Bioinformatics; Biology","score_opus":0.03784395397338416,"score_gpt":0.3227765898987711,"score_spread":0.284932635925387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312087161","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5522006,0.31518304,0.06317288,0.04658648,0.012401653,0.0061633326,0.00042388652,0.0007446752,0.0031234226],"genre_scores_gemma":[0.977498,0.000017621449,0.017779516,0.0037332932,0.00017433925,0.00019047834,0.00031440463,0.00004848308,0.00024388508],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99856585,0.000068045534,0.00030547107,0.00035559115,0.0003682772,0.00033675408],"domain_scores_gemma":[0.99935216,0.00011074695,0.0001011293,0.00025838873,0.000041140753,0.00013641622],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00057659467,0.00015767108,0.0002515692,0.00012476135,0.0003610355,0.00003506945,0.00014074576,0.000033975582,0.0007113917],"category_scores_gemma":[0.00009515487,0.00014089588,0.00020625256,0.00016437334,0.000075386386,0.00009660254,0.0001805137,0.00026347043,0.000018959161],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0026067097,0.0025921774,0.037439328,0.000064182634,0.047597013,0.00028257913,0.0004897074,0.00065940333,0.084179536,0.0033657812,0.3801142,0.44060937],"study_design_scores_gemma":[0.013063407,0.0006378601,0.02739578,0.000037029524,0.022471594,0.00022752928,0.00015194023,0.09145955,0.0035932763,0.00035317574,0.8400066,0.00060228206],"about_ca_topic_score_codex":0.0000680467,"about_ca_topic_score_gemma":0.0000014803035,"teacher_disagreement_score":0.45989236,"about_ca_system_score_codex":0.0000132803825,"about_ca_system_score_gemma":0.000105349005,"threshold_uncertainty_score":0.778924},"labels":[],"label_agreement":null},{"id":"W4312140644","doi":"10.3390/cancers14246217","title":"Implementation of Non-Invasive Quantitative Ultrasound in Clinical Cancer Imaging","year":2022,"lang":"en","type":"review","venue":"Cancers","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; University of Toronto; Sunnybrook Health Science Centre","funders":"","keywords":"Medicine; Ultrasound; Breast cancer; Radiomics; Backscatter (email); Pathology; Radiology; Cancer; Internal medicine; Computer science","score_opus":0.07443612754212037,"score_gpt":0.4967813706287568,"score_spread":0.42234524308663646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312140644","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00091582414,0.99644005,0.00009892085,0.00009543187,0.0009219253,0.0008000536,0.000074228315,0.000014430946,0.0006391498],"genre_scores_gemma":[0.0003245628,0.9979787,0.0005733423,0.00033514158,0.00020395758,0.00026108028,0.00019778789,0.000057157977,0.000068279965],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99769324,0.00022397228,0.0010782848,0.00042583104,0.0003029494,0.00027571927],"domain_scores_gemma":[0.9975486,0.0013476963,0.0006940731,0.00024228556,0.000044947683,0.00012244518],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008535039,0.00024421662,0.0016023449,0.0002759753,0.000045889275,0.0000098882,0.00017051648,0.000075041185,0.0012690078],"category_scores_gemma":[0.0006926691,0.00021606742,0.00043150777,0.00045548187,0.00018922242,0.000049458205,0.00005542992,0.0010760701,0.00000389968],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015275647,0.0000131379675,0.0068407306,0.0063051325,0.00021458046,0.00006245541,0.0003866567,0.00003739418,0.0000035108446,0.00003541363,0.0020485164,0.9840372],"study_design_scores_gemma":[0.0011249619,0.00012284482,0.00088797725,0.008503395,0.000912342,0.000036581358,0.0015503366,0.0002078897,0.0000022881372,0.000012224247,0.986408,0.00023117954],"about_ca_topic_score_codex":0.0048320754,"about_ca_topic_score_gemma":0.00029518543,"teacher_disagreement_score":0.98435944,"about_ca_system_score_codex":0.0021643192,"about_ca_system_score_gemma":0.0054745567,"threshold_uncertainty_score":0.999644},"labels":[],"label_agreement":null},{"id":"W4312367094","doi":"10.20517/2394-4722.2022.57","title":"Radiomics in sarcoma trials: a complement to RECIST for patient assessment","year":2022,"lang":"en","type":"article","venue":"Journal of Cancer Metastasis and Treatment","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; Princess Margaret Cancer Centre; Public Health Ontario; Ontario Institute for Cancer Research; University of Toronto","funders":"Sarcoma Alliance for Research through Collaboration; University of Michigan","keywords":"Radiomics; Medicine; Sarcoma; Response Evaluation Criteria in Solid Tumors; Radiological weapon; Radiology; Clinical trial; Pathology","score_opus":0.07312827792909614,"score_gpt":0.4287091341180272,"score_spread":0.35558085618893104,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312367094","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9672325,0.006551601,0.0028247645,0.02126542,0.00063374825,0.0012270027,0.00014240235,0.0000046405185,0.000117870964],"genre_scores_gemma":[0.959026,0.0016065327,0.037271824,0.0013961884,0.00021199933,0.00036924152,0.000014763519,0.000022338323,0.00008114342],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99824035,0.00023162461,0.0008107123,0.00015735748,0.0003707399,0.00018921983],"domain_scores_gemma":[0.99894494,0.00025668865,0.00041125604,0.00010467193,0.000072050694,0.00021039862],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018131197,0.00013364805,0.00082723284,0.00025944304,0.00011491997,0.000025540863,0.00005640495,0.000011808784,0.0001589963],"category_scores_gemma":[0.00011717317,0.00009090017,0.00024179107,0.00014056193,0.000016529797,0.000028021717,0.000042085667,0.00017594415,1.05023936e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014221843,0.0008761507,0.015742393,0.000027099175,0.0008243487,0.00013762599,0.0008377471,0.0018891873,0.00065455405,0.00026414497,0.0027192128,0.9746053],"study_design_scores_gemma":[0.017741865,0.010691765,0.014196394,0.0001435395,0.0012082331,0.00031433316,0.0014994716,0.004058388,0.0005379968,0.00022855656,0.94920635,0.00017308662],"about_ca_topic_score_codex":0.00023775504,"about_ca_topic_score_gemma":0.00003931661,"teacher_disagreement_score":0.9744323,"about_ca_system_score_codex":0.0010969914,"about_ca_system_score_gemma":0.00028312716,"threshold_uncertainty_score":0.37068015},"labels":[],"label_agreement":null},{"id":"W4312452303","doi":"10.1136/ijgc-2022-esgo.221","title":"2022-RA-648-ESGO Interpretable deep learning provides clues for prognostic refinement of the molecular endometrial cancer classification","year":2022,"lang":"en","type":"article","venue":"International Journal of Gynecological Cancer","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Health Science Centre","funders":"","keywords":"Receiver operating characteristic; Artificial intelligence; Cancer; Endometrial cancer; Computational biology; Biology; Oncology; Computer science; Internal medicine; Medicine","score_opus":0.021602683434326423,"score_gpt":0.34456503909149955,"score_spread":0.32296235565717313,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312452303","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96517867,0.0033756415,0.007387836,0.019687455,0.0032971376,0.0006329499,0.000024764695,0.000014274503,0.00040125515],"genre_scores_gemma":[0.99614054,0.00039586524,0.0011500447,0.0012343841,0.00046084344,0.00023963368,0.00000954847,0.000015736612,0.0003533834],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979591,0.00018094805,0.0006211063,0.00017425275,0.0008865181,0.00017807953],"domain_scores_gemma":[0.9977775,0.00063956156,0.0008055063,0.000092079455,0.0006066893,0.00007866582],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00094910763,0.00011244997,0.00032550225,0.0001734549,0.00012880395,0.000026578504,0.00045748285,0.00004565452,0.0013714904],"category_scores_gemma":[0.005000238,0.000072659896,0.0002773821,0.0002071541,0.00012517633,0.00006506238,0.00018091127,0.0007319521,3.80634e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004395782,0.0011966571,0.4229191,0.00017307291,0.0019339817,0.00008905146,0.0009205669,0.051738974,0.15786555,0.0038890077,0.0043793176,0.35049894],"study_design_scores_gemma":[0.019238323,0.0068092924,0.30533966,0.0009946455,0.0015772902,0.0004135481,0.0022810127,0.18800586,0.01126587,0.0037754758,0.45964634,0.0006526641],"about_ca_topic_score_codex":0.00005584777,"about_ca_topic_score_gemma":0.000010646708,"teacher_disagreement_score":0.45526704,"about_ca_system_score_codex":0.0005933385,"about_ca_system_score_gemma":0.0003280085,"threshold_uncertainty_score":0.9995414},"labels":[],"label_agreement":null},{"id":"W4312646446","doi":"10.52766/beul1278","title":"Efectividad, eficacia y seguridad de la citología con evaluación in situ en punción aspiración con aguja fina y biopsia con aguja gruesa ecoguiadas","year":2022,"lang":"es","type":"book","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Humanities; Medicine; Art","score_opus":0.0109092233144967,"score_gpt":0.31893275153968864,"score_spread":0.30802352822519197,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312646446","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3984677,0.007833025,0.0010681247,0.0069737574,0.0042631575,0.0043074475,0.00023619353,0.0009283141,0.5759223],"genre_scores_gemma":[0.9078355,0.0036448154,0.001559244,0.0068781585,0.0028453553,0.00049182196,0.0017127589,0.00065586047,0.07437649],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.98495734,0.004403463,0.0026313122,0.002889283,0.0025292546,0.0025893492],"domain_scores_gemma":[0.98854613,0.0066043045,0.0013813839,0.0018970927,0.00034577746,0.0012253068],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow","research_integrity"],"category_scores_codex":[0.010169798,0.0022470753,0.004036207,0.0018892835,0.0006648751,0.00042483225,0.001608506,0.0024623647,0.00742481],"category_scores_gemma":[0.0075391573,0.0021776613,0.0011451584,0.0009737653,0.0016705532,0.00031458808,0.0010952165,0.010209087,0.00068289903],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0041374746,0.005271243,0.33201617,0.009530965,0.005281406,0.028643297,0.0067080497,0.002540441,0.06667347,0.100461826,0.17115189,0.26758376],"study_design_scores_gemma":[0.015289531,0.002554851,0.09460683,0.003659267,0.0023983193,0.0023881863,0.0009077396,0.015237072,0.0015562477,0.0038076031,0.854136,0.0034583749],"about_ca_topic_score_codex":0.002370994,"about_ca_topic_score_gemma":0.00019920751,"teacher_disagreement_score":0.68298405,"about_ca_system_score_codex":0.0035975752,"about_ca_system_score_gemma":0.0056516333,"threshold_uncertainty_score":0.9999854},"labels":[],"label_agreement":null},{"id":"W4312726348","doi":"10.1109/access.2022.3232561","title":"UNet Deep Learning Architecture for Segmentation of Vascular and Non-Vascular Images: A Microscopic Look at UNet Components Buffered With Pruning, Explainable Artificial Intelligence, and Bias","year":2022,"lang":"en","type":"article","venue":"IEEE Access","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":85,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Pruning; Segmentation; Artificial intelligence; Ranking (information retrieval); Pattern recognition (psychology)","score_opus":0.025057970598052176,"score_gpt":0.29941610951536884,"score_spread":0.27435813891731664,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312726348","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8796728,0.00056031824,0.11864249,0.00022639209,0.00008731469,0.0007455726,0.000007229886,0.000025935069,0.000031928303],"genre_scores_gemma":[0.9927679,0.00013180489,0.0064567635,0.00019842174,0.00006662832,0.000118053424,0.00012847569,0.0000404648,0.000091505426],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99861485,0.0001188079,0.00029395282,0.0003700524,0.0003328874,0.00026947926],"domain_scores_gemma":[0.99931794,0.00014075493,0.00018954786,0.0001755109,0.00005651194,0.00011974954],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00049051526,0.00017963674,0.00037953636,0.00018865433,0.00038269925,0.00007245264,0.00014246762,0.000043082924,0.000039502924],"category_scores_gemma":[0.000087614695,0.00015397604,0.000059969265,0.00021132774,0.00017875919,0.00009764933,0.00015576894,0.00039721018,4.0169974e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021964544,0.00065745664,0.3479426,0.004172687,0.0012435998,0.00017341728,0.011579776,0.1500802,0.35922655,0.00008779958,0.0005285413,0.12211091],"study_design_scores_gemma":[0.017157378,0.007760949,0.094867595,0.0021936863,0.0025207126,0.00070079387,0.010107203,0.58640116,0.25306177,0.0026318291,0.020530837,0.0020661105],"about_ca_topic_score_codex":0.00034857958,"about_ca_topic_score_gemma":0.00002137535,"teacher_disagreement_score":0.43632093,"about_ca_system_score_codex":0.000063757274,"about_ca_system_score_gemma":0.00003915194,"threshold_uncertainty_score":0.6278961},"labels":[],"label_agreement":null},{"id":"W4312778519","doi":"10.1016/j.hpb.2022.05.209","title":"Volumetric Based Quantification of Histopathological Growth Patterns Is Most Predictive of Progression Free Survival Following Resection of Colorectal Liver Metastases","year":2022,"lang":"en","type":"article","venue":"HPB","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre; McGill University","funders":"","keywords":"Medicine; Colorectal cancer; Hepatectomy; Lesion; Pathological; Multivariate analysis; Multivariate statistics; Resection; Radiology; Internal medicine; Oncology; Pathology; Surgery; Cancer","score_opus":0.022406368293407954,"score_gpt":0.2971468056866461,"score_spread":0.2747404373932381,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312778519","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9685986,0.00031839128,0.03001895,0.00014080325,0.00034886287,0.00031065487,0.00012223839,0.00002453985,0.00011697547],"genre_scores_gemma":[0.99529773,0.000018530793,0.0044146944,0.00004230982,0.000029565459,0.00003120674,0.00011984505,0.000014357761,0.000031744687],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9982478,0.00029382837,0.000386282,0.00023341381,0.00071031327,0.00012838667],"domain_scores_gemma":[0.99898833,0.0002460641,0.0003329767,0.0002226869,0.00015302621,0.000056914836],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010779478,0.00009355781,0.00036083395,0.00030062252,0.00008254916,0.0000029585965,0.00013935575,0.00004580073,0.00018578972],"category_scores_gemma":[0.0015650347,0.000080356345,0.0001548204,0.0005945663,0.000105699226,0.00004315241,0.00010296682,0.00029178118,3.4348267e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016238092,0.0013188695,0.84188026,0.00056311284,0.00013437531,0.0000894243,0.0007524728,0.00031792215,0.13420063,0.00010196521,0.0013218673,0.017695284],"study_design_scores_gemma":[0.003622003,0.0051736427,0.6552051,0.00028830496,0.00050924864,0.000030062944,0.00062825915,0.28837028,0.04567877,0.000037726997,0.000286433,0.00017017504],"about_ca_topic_score_codex":0.0003251524,"about_ca_topic_score_gemma":0.0000027107503,"teacher_disagreement_score":0.28805235,"about_ca_system_score_codex":0.000080783386,"about_ca_system_score_gemma":0.00008439015,"threshold_uncertainty_score":0.32768366},"labels":[],"label_agreement":null},{"id":"W4313064726","doi":"10.1161/atvb.42.suppl_1.349","title":"Abstract 349: Segmentation Of Atherosclerotic Plaque Features From Histopathology Images Using Novel Deep Learning Techniques","year":2022,"lang":"en","type":"article","venue":"Arteriosclerosis Thrombosis and Vascular Biology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University; McGill University Health Centre","funders":"","keywords":"Calcification; Histopathology; Segmentation; Fibrosis; Medicine; Artificial intelligence; H&E stain; Ground truth; Pathology; Radiology; Computer science; Immunohistochemistry","score_opus":0.02569909218517987,"score_gpt":0.30212958090932734,"score_spread":0.2764304887241475,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313064726","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9887991,0.000301598,0.009817148,0.00048953015,0.00016234657,0.00026627918,0.000024854477,0.00007106061,0.000068085894],"genre_scores_gemma":[0.974119,0.0009859198,0.02407918,0.00052048964,0.00008300491,0.000042333722,0.00012994734,0.0000367778,0.0000033541967],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9985912,0.00018433499,0.00037174296,0.00042506823,0.00016318796,0.00026448636],"domain_scores_gemma":[0.9992901,0.00010592201,0.00024346018,0.0002269223,0.000044602522,0.00008895705],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046304727,0.00020077686,0.00054573204,0.00014914852,0.00031894218,0.00001856727,0.0001173895,0.0001140601,0.0002685425],"category_scores_gemma":[0.00007508244,0.00018561698,0.00016315642,0.00012093777,0.0002729126,0.000060872553,0.00017027526,0.00051732064,9.730925e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000076925035,0.00014189018,0.12445506,0.000032032,0.00010405797,2.540777e-7,0.00054674374,0.000046424295,0.8717931,0.00008071182,0.00001566194,0.002776411],"study_design_scores_gemma":[0.0010235579,0.0004449539,0.98982614,0.00007613897,0.00020788613,0.000008796483,0.00045984768,0.0008305081,0.005895765,0.00007828814,0.0009584495,0.0001896496],"about_ca_topic_score_codex":0.0006817114,"about_ca_topic_score_gemma":0.000006160147,"teacher_disagreement_score":0.8658973,"about_ca_system_score_codex":0.00008540887,"about_ca_system_score_gemma":0.000029560173,"threshold_uncertainty_score":0.7569241},"labels":[],"label_agreement":null},{"id":"W4313406680","doi":"10.21873/anticanres.16170","title":"Exploring Hypoxia in Prostate Cancer With T2-weighted Magnetic Resonance Imaging Radiomics and Pimonidazole Scoring","year":2022,"lang":"en","type":"article","venue":"Anticancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Trinity College","funders":"","keywords":"Prostate cancer; Medicine; Magnetic resonance imaging; Prostatectomy; Prostate; Receiver operating characteristic; Radiomics; Nomogram; Logistic regression; Radiology; Nuclear medicine; Oncology; Cancer; Internal medicine","score_opus":0.06635758642984597,"score_gpt":0.35693567031850015,"score_spread":0.2905780838886542,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313406680","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9742067,0.01677559,0.000017430593,0.0073710987,0.00012383421,0.00058730383,0.000006083391,0.0000487764,0.00086322054],"genre_scores_gemma":[0.9908456,0.006378992,0.0010284004,0.00035075028,0.00014517178,0.00064522173,0.000005795322,0.00006722269,0.0005328055],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99708295,0.00020180618,0.0002774525,0.00058590376,0.0009984998,0.0008534115],"domain_scores_gemma":[0.99911344,0.00018293549,0.00004303023,0.0003223865,0.00011019141,0.00022803392],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014217815,0.00016949202,0.0003300904,0.0005216939,0.00045427683,0.00007855688,0.0001949007,0.00001495578,0.00016422411],"category_scores_gemma":[0.00011799202,0.0001515294,0.000028806993,0.0012069149,0.0004028592,0.00021494305,0.00032530897,0.0016732122,0.000003349754],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007853423,0.00011025096,0.67304385,0.0001607937,0.000015507421,0.0010526923,0.0018659593,0.00023476958,0.0044463584,0.00034253698,0.0003012977,0.31764063],"study_design_scores_gemma":[0.007856639,0.00082675705,0.77298635,0.0013895887,0.000055745375,0.00057782925,0.0040054345,0.14307278,0.0015574992,0.0003968696,0.06666423,0.00061028346],"about_ca_topic_score_codex":0.0028818995,"about_ca_topic_score_gemma":0.00006599558,"teacher_disagreement_score":0.31703034,"about_ca_system_score_codex":0.00043960795,"about_ca_system_score_gemma":0.00040908466,"threshold_uncertainty_score":0.72693676},"labels":[],"label_agreement":null},{"id":"W4313457532","doi":"10.21203/rs.3.rs-2393890/v1","title":"Impact of harmonization and oversampling methods on radiomics analysis of multi-center imbalanced datasets: Application to PET-based prediction of lung cancer subtypes","year":2023,"lang":"en","type":"preprint","venue":"Research Square","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Occupational Cancer Research Centre","funders":"Basic and Applied Basic Research Foundation of Guangdong Province; Science and Technology Planning Project of Guangdong Province; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Oversampling; Logistic regression; Artificial intelligence; Harmonization; Random forest; Support vector machine; Linear discriminant analysis; Computer science; Machine learning; Radiomics; Cutoff; Medicine","score_opus":0.0736727508529272,"score_gpt":0.5064170616909489,"score_spread":0.43274431083802173,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313457532","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6631137,0.00033113276,0.33067414,0.000361426,0.00007457726,0.0011604925,0.004245829,0.000031848966,0.000006837576],"genre_scores_gemma":[0.9697693,0.0008450232,0.022518791,0.000017749606,0.00006584565,0.000108554275,0.006618954,0.00004302367,0.000012759369],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976282,0.0003536203,0.000547965,0.0005088988,0.0007070584,0.00025423558],"domain_scores_gemma":[0.99765974,0.00059932,0.00033694756,0.0006366491,0.00058244076,0.00018488069],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002346031,0.00017340663,0.00073926884,0.001638605,0.000050938113,0.00001845786,0.00017750684,0.00013223206,0.000020756659],"category_scores_gemma":[0.0018330056,0.00015020689,0.00022741205,0.0013918824,0.00013233807,0.000031913132,0.00021259865,0.0007168308,3.5414052e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00073500955,0.00043889842,0.70347124,0.0027849078,0.002034928,0.0000036087895,0.00041257238,0.24553202,0.0329147,0.000018630666,0.0004782983,0.011175198],"study_design_scores_gemma":[0.0008926188,0.00015132656,0.3557244,0.0009340888,0.00043863145,3.7729984e-7,0.00003048392,0.64037514,0.0013659113,0.000005913168,0.000024038822,0.00005705254],"about_ca_topic_score_codex":0.0027782018,"about_ca_topic_score_gemma":0.000026890979,"teacher_disagreement_score":0.39484313,"about_ca_system_score_codex":0.00037983753,"about_ca_system_score_gemma":0.00034984585,"threshold_uncertainty_score":0.61252594},"labels":[],"label_agreement":null},{"id":"W4313489242","doi":"10.1007/s12350-022-03196-x","title":"Correction to: Integration of coronary artery calcium scoring from CT attenuation scans by machine learning improves prediction of adverse cardiovascular events in patients undergoing SPECT/CT myocardial perfusion imaging","year":2023,"lang":"en","type":"erratum","venue":"Journal of Nuclear Cardiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"National Heart, Lung, and Blood Institute","keywords":"Medicine; Myocardial perfusion imaging; Correction for attenuation; Perfusion; Perfusion scanning; Coronary artery calcium; Radiology; Adverse effect; Cardiology; Coronary artery disease; Internal medicine; Nuclear medicine; Positron emission tomography","score_opus":0.009687535748003163,"score_gpt":0.2418681542144526,"score_spread":0.23218061846644944,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313489242","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.963355,0.0010342969,0.0026653684,0.00019866272,0.03167799,0.0004865409,0.000068581685,0.000044397962,0.00046916763],"genre_scores_gemma":[0.9952949,0.0014274026,0.00017683799,0.0000689132,0.0017768341,0.0000037630837,0.0007337006,0.00012425399,0.00039339278],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99631,0.0006396374,0.0013567896,0.00044729424,0.0009145048,0.00033176516],"domain_scores_gemma":[0.99777704,0.0002539566,0.0011458412,0.0003063553,0.00035077354,0.00016602135],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0014612206,0.0003507248,0.0016830448,0.00089754426,0.00009602447,0.000008155468,0.00018847147,0.00011548373,0.000013451965],"category_scores_gemma":[0.002106388,0.0003328408,0.0009508231,0.00036181824,0.00009451144,0.00020868503,0.00013239252,0.0024669736,0.0000057390257],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015979251,0.00021600693,0.7704625,0.0003301472,0.0028505346,0.0007665006,0.0008785528,0.021291126,0.023021596,0.0000011224723,0.09935445,0.07922954],"study_design_scores_gemma":[0.005016011,0.0017996447,0.92553025,0.004956994,0.0016793908,0.0010541466,0.00105326,0.052236717,0.00013963864,0.000019111063,0.0061785053,0.00033632867],"about_ca_topic_score_codex":0.0009049748,"about_ca_topic_score_gemma":0.00001642156,"teacher_disagreement_score":0.15506776,"about_ca_system_score_codex":0.00070547004,"about_ca_system_score_gemma":0.00026278096,"threshold_uncertainty_score":0.9999124},"labels":[],"label_agreement":null},{"id":"W4313543537","doi":"10.1371/journal.pcbi.1010778","title":"Ten quick tips for computational analysis of medical images","year":2023,"lang":"en","type":"article","venue":"PLoS Computational Biology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Medical imaging; Data science; Artificial intelligence; Computational model; Asset (computer security); Software deployment; Deep learning; Intervention (counseling); Disease; Medical physics; Machine learning; Medicine; Pathology; Computer security; Software engineering","score_opus":0.028024318771403236,"score_gpt":0.36079273962925834,"score_spread":0.33276842085785513,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313543537","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.62722564,0.00014344999,0.33518335,0.035978958,0.00021247278,0.00037821362,0.00021135963,0.00020266825,0.0004639069],"genre_scores_gemma":[0.9724394,0.000019004263,0.02181013,0.0014619812,0.00016742376,0.000027864136,0.003961979,0.000015661237,0.00009657821],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986453,0.000064489876,0.00038724943,0.00025590323,0.000445539,0.0002015371],"domain_scores_gemma":[0.9977939,0.0016112888,0.00011698714,0.00008753321,0.0002489787,0.00014127191],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00054490054,0.000100045334,0.00044757404,0.0005756441,0.00006608034,0.0000073665706,0.00013952887,0.00011087117,0.00024187613],"category_scores_gemma":[0.0011355538,0.00008350756,0.00019447894,0.0008078033,0.0002248919,0.000020535766,0.000060412374,0.00017379822,0.000028350783],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003523092,0.00076651364,0.39678714,0.00043393738,0.009901958,0.000064444015,0.00048728316,0.44157627,0.0018560471,0.07540705,0.03281238,0.03955467],"study_design_scores_gemma":[0.0009146885,0.00012498081,0.12442444,0.000025586914,0.00044326906,0.00001541229,0.000024193601,0.86354345,0.000021085772,0.00931238,0.001077625,0.00007289859],"about_ca_topic_score_codex":0.000020576399,"about_ca_topic_score_gemma":0.0000011395658,"teacher_disagreement_score":0.42196715,"about_ca_system_score_codex":0.000022882981,"about_ca_system_score_gemma":0.00019262628,"threshold_uncertainty_score":0.34053397},"labels":[],"label_agreement":null},{"id":"W4315474725","doi":"10.1016/j.mex.2023.102009","title":"Generating post-hoc explanation from deep neural networks for multi-modal medical image analysis tasks","year":2023,"lang":"en","type":"article","venue":"MethodsX","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Simon Fraser University","funders":"Alliance de recherche numérique du Canada; BC Cancer Foundation; Simon Fraser University; Nvidia","keywords":"Modal; Computer science; Artificial neural network; Artificial intelligence; Feature (linguistics); Kernel (algebra); Machine learning; Pattern recognition (psychology); Mathematics","score_opus":0.03783489869419684,"score_gpt":0.39982060812181575,"score_spread":0.36198570942761893,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4315474725","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21344258,0.0002513225,0.78158796,0.0038121052,0.00044092338,0.0002273425,0.000015353378,0.00018798969,0.000034446904],"genre_scores_gemma":[0.12911579,0.000054521504,0.86403334,0.0034446723,0.0014297361,0.00007830416,0.0015773274,0.000058395,0.00020791808],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978338,0.00034799648,0.00044972514,0.0004524091,0.0004914477,0.00042463583],"domain_scores_gemma":[0.9980105,0.0010900653,0.00012753962,0.00028524623,0.00014506781,0.00034158872],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023691456,0.00018850241,0.0005288993,0.00031875967,0.00019472251,0.00005979438,0.00017326264,0.00018241692,0.00023850445],"category_scores_gemma":[0.0046802987,0.00015889193,0.0003177132,0.0007887736,0.00009775296,0.00008205353,0.000079141864,0.0005435193,0.000010663374],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025570055,0.00011192845,0.010419484,0.000061086175,0.00121957,0.00030492005,0.0013201769,0.04437775,0.01413317,0.00009121794,0.0014631711,0.9262418],"study_design_scores_gemma":[0.001596183,0.000089417044,0.011378799,0.000018486464,0.0006987151,0.000011272412,0.0001679262,0.9850184,0.00011644127,0.000060375576,0.0006871493,0.00015685137],"about_ca_topic_score_codex":0.00034830446,"about_ca_topic_score_gemma":0.000056799636,"teacher_disagreement_score":0.9406406,"about_ca_system_score_codex":0.00004745778,"about_ca_system_score_gemma":0.000043977372,"threshold_uncertainty_score":0.6479424},"labels":[],"label_agreement":null},{"id":"W4316362920","doi":"10.18280/ts.390639","title":"Development of Medical Image Analytics by Deep Learning Model for Prediction and Classification of CT Image Diseases","year":2022,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Lung cancer; Convolutional neural network; Residual neural network; Adenocarcinoma; Artificial intelligence; Cancer; Computed tomography; Artificial neural network; Medicine; Deep learning; Lung; Disease; Computer science; Radiology; Pattern recognition (psychology); Pathology; Internal medicine","score_opus":0.018903515097542054,"score_gpt":0.29235189010711043,"score_spread":0.27344837500956837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4316362920","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4889075,0.00018123043,0.50943166,0.0009594936,0.000030978757,0.0003061439,0.00006645579,0.00002836598,0.00008821577],"genre_scores_gemma":[0.9778747,0.0000431756,0.021308174,0.00010172412,0.000040913455,0.00007458106,0.00045737147,0.000019097377,0.00008025052],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983102,0.00004983881,0.00048698584,0.00020475409,0.0007940381,0.000154176],"domain_scores_gemma":[0.9994054,0.00009088412,0.00019649524,0.00007734611,0.00007227975,0.00015762186],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00080450135,0.00010217318,0.000248703,0.00010388194,0.00015970801,0.000009745834,0.00009490887,0.000021825792,0.00025013502],"category_scores_gemma":[0.00017778204,0.00009630186,0.000064559455,0.000098500364,0.00012115147,0.000055097044,0.00006398087,0.00023877536,2.4830007e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011745401,0.0026778742,0.055970203,0.0021756731,0.00076201395,0.000028089802,0.006151393,0.011446195,0.580317,0.001733719,0.009832682,0.3277306],"study_design_scores_gemma":[0.0019593288,0.00018868045,0.010811088,0.000048221533,0.00016762433,0.000012446056,0.00050378154,0.9831739,0.0007742527,0.000057806203,0.0022266181,0.000076225864],"about_ca_topic_score_codex":0.0000038745925,"about_ca_topic_score_gemma":5.978171e-7,"teacher_disagreement_score":0.9717277,"about_ca_system_score_codex":0.00007197863,"about_ca_system_score_gemma":0.0001614836,"threshold_uncertainty_score":0.39270762},"labels":[],"label_agreement":null},{"id":"W4317862744","doi":"10.1200/jco.2023.41.4_suppl.252","title":"AI-powered multi-omic signature to predict treatment response of patients with colorectal cancer liver metastasis.","year":2023,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre; University of British Columbia; McGill University","funders":"","keywords":"Medicine; Colorectal cancer; Metastasis; Liquid biopsy; Biomarker; Transcriptome; Oncology; Cancer; Internal medicine; Pathology; Bioinformatics; Gene; Biology; Gene expression","score_opus":0.05747260751210537,"score_gpt":0.4507144880441809,"score_spread":0.39324188053207554,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317862744","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9825574,0.00023325192,0.00023191991,0.015610347,0.0009009599,0.00036196984,0.00003094733,0.000016288524,0.000056910703],"genre_scores_gemma":[0.99041474,0.0004946352,0.0050397054,0.0033189151,0.00038580684,0.000010382803,0.000008990249,0.000026496662,0.0003003452],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99699384,0.0006533523,0.0014079098,0.00021374684,0.000466112,0.00026500967],"domain_scores_gemma":[0.9955805,0.0022365486,0.00097367173,0.00014659186,0.0005184923,0.00054417626],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028153674,0.00016136012,0.0014298678,0.00026581454,0.000035393263,0.0000057508396,0.00015343331,0.0002501319,0.00015971977],"category_scores_gemma":[0.0056674373,0.000094475436,0.00035509898,0.00031963462,0.0001971794,0.000057455305,0.000049338123,0.0009348144,0.000016045205],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.10010385,0.004154266,0.64962304,0.000054504515,0.0020929596,0.001695218,0.0007948591,0.00097190513,0.0017440184,0.000009701295,0.023507534,0.21524817],"study_design_scores_gemma":[0.016216662,0.02990179,0.9010085,0.00016626662,0.0006756155,0.000039550894,0.000051403727,0.001851701,0.00022320567,0.000007016656,0.04976539,0.00009290548],"about_ca_topic_score_codex":0.00004263257,"about_ca_topic_score_gemma":0.000026343243,"teacher_disagreement_score":0.25138548,"about_ca_system_score_codex":0.0002556217,"about_ca_system_score_gemma":0.0015839624,"threshold_uncertainty_score":0.67848617},"labels":[],"label_agreement":null},{"id":"W4317863163","doi":"10.1200/jco.2023.41.4_suppl.793","title":"Use of positron emission tomography-computed tomography (PET-CT) scan in patients with gastrointestinal (GI) cancer at the University Hospital of Montreal (CHUM).","year":2023,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Centre Hospitalier de l’Université de Montréal; Université de Montréal","funders":"","keywords":"Medicine; Positron emission tomography; Computed tomography; Nuclear medicine; Radiology; Cancer; Retrospective cohort study; Internal medicine","score_opus":0.02291272173716744,"score_gpt":0.3394756930266791,"score_spread":0.31656297128951166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317863163","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9963587,0.000047433026,0.00006499207,0.002960538,0.0002689893,0.00015991986,0.000007925878,0.000008433026,0.00012305148],"genre_scores_gemma":[0.9975773,0.00009038753,0.0019567546,0.00016603214,0.00010606598,3.378166e-7,0.000006988891,0.000011469466,0.00008462879],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99782616,0.0003181754,0.0010371185,0.00016301942,0.00043597692,0.00021957271],"domain_scores_gemma":[0.9966162,0.0012876187,0.0013212285,0.00015418496,0.0003675633,0.00025320772],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011798338,0.00011570655,0.0008555571,0.0003198665,0.00004542652,0.000004174663,0.0001958211,0.000042320895,0.00003294992],"category_scores_gemma":[0.0009738636,0.00006959292,0.00034112824,0.00060871977,0.0004899117,0.0000890627,0.00009726821,0.00088393997,4.5302738e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003636273,0.0008850124,0.9650137,0.000028622453,0.00015007702,0.00064023456,0.00006747028,0.00041839152,0.00011111925,0.000005592581,0.002966569,0.026076948],"study_design_scores_gemma":[0.0058846,0.007210625,0.9827539,0.0005055335,0.00020116015,0.000107459586,0.00007642195,0.0017798286,0.000025047759,0.000014778117,0.0013800381,0.000060620605],"about_ca_topic_score_codex":0.0005829808,"about_ca_topic_score_gemma":0.00012644057,"teacher_disagreement_score":0.026016327,"about_ca_system_score_codex":0.00010716062,"about_ca_system_score_gemma":0.0004580633,"threshold_uncertainty_score":0.38403285},"labels":[],"label_agreement":null},{"id":"W4317884676","doi":"10.1186/s40364-023-00455-y","title":"Radiogenomic association of deep MR imaging features with genomic profiles and clinical characteristics in breast cancer","year":2023,"lang":"en","type":"article","venue":"Biomarker Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"CancerCare Manitoba; Research Institute in Oncology and Hematology; Western University; University of Manitoba","funders":"University of Manitoba; Canada Research Chairs; CancerCare Manitoba Foundation; Manitoba Medical Service Foundation","keywords":"Medicine; Breast cancer; Magnetic resonance imaging; Cancer; Estrogen receptor; Radiomics; Oncology; Internal medicine; Computational biology; Pathology; Bioinformatics; Radiology; Biology","score_opus":0.03291726753668087,"score_gpt":0.4004187287449019,"score_spread":0.367501461208221,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317884676","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.989022,0.00045972978,0.00001407075,0.009747559,0.00008969167,0.00033884821,0.000025841407,0.000029862202,0.0002723803],"genre_scores_gemma":[0.997343,0.0014764423,0.00027120483,0.0000926416,0.00018970208,0.000026739508,0.000039541424,0.000031713724,0.00052901503],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99817514,0.0002860064,0.00034515894,0.00029842943,0.0004776584,0.000417611],"domain_scores_gemma":[0.9989231,0.00047416045,0.000109382236,0.00017165593,0.00016930861,0.00015234886],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037937611,0.00009898337,0.0003284382,0.0004256011,0.00007308091,0.00003686733,0.000102961094,0.00008147612,0.00005456859],"category_scores_gemma":[0.00055255176,0.00007683852,0.000043912572,0.00055133045,0.00023830905,0.00004412212,0.000105660714,0.00058461126,0.00000957927],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039933898,0.00005344202,0.90920484,0.00012907677,0.000086965505,0.000091582355,0.00013241393,8.8642327e-7,0.015071904,0.000012815208,0.0022334678,0.072583266],"study_design_scores_gemma":[0.0013608126,0.000041766383,0.9802082,0.00019852664,0.000028954071,0.000059543887,0.0001178048,0.017086884,0.00005964572,0.00001480712,0.00074581977,0.00007719218],"about_ca_topic_score_codex":0.00048939727,"about_ca_topic_score_gemma":0.00003493419,"teacher_disagreement_score":0.07250608,"about_ca_system_score_codex":0.00025670277,"about_ca_system_score_gemma":0.00020999365,"threshold_uncertainty_score":0.3133384},"labels":[],"label_agreement":null},{"id":"W4317934266","doi":"10.3389/fonc.2023.1065402","title":"Role of artificial intelligence in risk prediction, prognostication, and therapy response assessment in colorectal cancer: current state and future directions","year":2023,"lang":"en","type":"review","venue":"Frontiers in Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Colorectal cancer; Medicine; Artificial intelligence; Probabilistic logic; Applications of artificial intelligence; Machine learning; Cancer; Oncology; Computer science; Internal medicine","score_opus":0.022956053906608303,"score_gpt":0.39698551409917043,"score_spread":0.3740294601925621,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317934266","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015131976,0.98111063,0.00046003022,0.0005484221,0.0013211236,0.0013214982,0.000066365305,0.000019335474,0.00002060855],"genre_scores_gemma":[0.00027268034,0.99652326,0.0023847749,0.000010801578,0.00019666084,0.00053693634,0.00003653243,0.000026944012,0.000011428289],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975806,0.0008281666,0.0008354671,0.00039038114,0.00013815479,0.00022725116],"domain_scores_gemma":[0.9988905,0.00053128577,0.000334353,0.0001084381,0.00004897575,0.00008641737],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016260518,0.00019406337,0.0011415551,0.0008254142,0.00003902585,0.000009659438,0.000081481405,0.00020008444,0.000006488039],"category_scores_gemma":[0.0005566326,0.00016631228,0.000054186887,0.0007264697,0.00024465244,0.00003191289,0.000046202516,0.0013308804,4.738243e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002559273,0.0002019182,0.045521915,0.0007497954,0.000058590693,0.000014955189,0.0009910604,0.0000138939995,0.000002689215,0.000018648505,0.00015657287,0.952014],"study_design_scores_gemma":[0.00048804175,0.0004543241,0.10021568,0.003391219,0.00016100638,0.000027172235,0.0005046907,0.010353483,0.0000010900228,0.0011289724,0.88312006,0.00015426199],"about_ca_topic_score_codex":0.00023260374,"about_ca_topic_score_gemma":0.0002760195,"teacher_disagreement_score":0.9518598,"about_ca_system_score_codex":0.0005256437,"about_ca_system_score_gemma":0.0010885629,"threshold_uncertainty_score":0.6782018},"labels":[],"label_agreement":null},{"id":"W4318260395","doi":"10.2139/ssrn.4327775","title":"Alzheimer's and Vascular Disease Classification Using Regional Texture Biomarkers in Flair MRI","year":2023,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Health Science Centre; University of Toronto; Health Sciences Centre; Toronto Metropolitan University","funders":"","keywords":"Fluid-attenuated inversion recovery; Medicine; Disease; Texture (cosmology); Neuroscience; Pathology; Radiology; Magnetic resonance imaging; Artificial intelligence; Psychology; Computer science","score_opus":0.03612856821361381,"score_gpt":0.32172543935201947,"score_spread":0.28559687113840565,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318260395","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7779779,0.10920432,0.050697166,0.059040353,0.001367412,0.0013191525,0.000011529622,0.00022150998,0.00016069757],"genre_scores_gemma":[0.96049327,0.03636111,0.0012613592,0.00043694198,0.0010147078,0.000017577586,0.00013383731,0.000117807,0.00016338073],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99688536,0.00018055137,0.00047580356,0.0005345159,0.00053237577,0.0013913673],"domain_scores_gemma":[0.99887055,0.00006494445,0.00029029662,0.00033307087,0.00008536793,0.0003557398],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0024255987,0.00029994693,0.00044244423,0.0004888495,0.00015763557,0.0000832993,0.00020706428,0.0002582339,0.000009761291],"category_scores_gemma":[0.00027562183,0.00026755233,0.00024386843,0.00022879077,0.00015257698,0.00007232386,0.0001587811,0.006450752,0.000005792444],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0024219225,0.001177474,0.58786774,0.001785884,0.028907286,0.0016452769,0.0018854592,0.018825145,0.004140355,0.045153983,0.006838037,0.29935142],"study_design_scores_gemma":[0.004493509,0.00019088881,0.27401382,0.0029123279,0.0033704464,0.0016833077,0.0014600263,0.51403946,0.0000037290713,0.19169356,0.005161509,0.0009774468],"about_ca_topic_score_codex":0.00022775338,"about_ca_topic_score_gemma":0.000077511744,"teacher_disagreement_score":0.49521428,"about_ca_system_score_codex":0.0009861372,"about_ca_system_score_gemma":0.0042752856,"threshold_uncertainty_score":0.99997765},"labels":[],"label_agreement":null},{"id":"W4318485927","doi":"10.3390/curroncol30020125","title":"Artificial Intelligence for Cancer Detection—A Bibliometric Analysis and Avenues for Future Research","year":2023,"lang":"en","type":"review","venue":"Current Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Research Foundation of Korea; Science and Technology Commission of Shanghai Municipality; National Natural Science Foundation of China; Universität Duisburg-Essen; National Cancer Institute; National Key Research and Development Program of China; National Research Foundation; European Regional Development Fund; European Commission; Fundamental Research Funds for the Central Universities; National Institute for Health and Care Research; U.S. Department of Health and Human Services; National Institutes of Health; Japan Society for the Promotion of Science; Cancer Research UK; Canadian Institutes of Health Research; National Science Foundation","keywords":"Artificial intelligence; Cancer; Medical research; Medicine; Data science; Disease; Cancer detection; Computer science; Pathology","score_opus":0.49138321571910776,"score_gpt":0.6236155400401707,"score_spread":0.13223232432106297,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318485927","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000053567306,0.9736797,0.021111976,0.0006571021,0.0026880049,0.0016425804,0.00010891129,0.000046187284,0.000011921492],"genre_scores_gemma":[0.00002589057,0.9926579,0.0006101357,0.000018280181,0.0045166668,0.0017760628,0.0002086181,0.000052950003,0.00013349323],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978718,0.00021383732,0.00060836034,0.00056269375,0.00027723162,0.00046603844],"domain_scores_gemma":[0.99642205,0.002518732,0.00024133563,0.00021939482,0.00039349106,0.00020501982],"candidate_categories":["bibliometrics"],"consensus_categories":["bibliometrics"],"category_scores_codex":[0.0023973922,0.00021677013,0.0016425474,0.044681504,0.0002226202,0.00004758642,0.00017386171,0.00034832576,0.000024409097],"category_scores_gemma":[0.0028251186,0.0001689381,0.00054187904,0.05870386,0.0001933155,0.000022175174,0.00008970518,0.0011340795,0.000011439395],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029472672,0.000072383584,0.0000490634,0.015031003,0.0006647654,0.0000042329157,0.000058713853,0.0000010304209,5.658977e-7,0.00010384762,0.001034128,0.9829508],"study_design_scores_gemma":[0.00009454786,0.00034516526,0.00006503679,0.0016416045,0.00486218,0.000013691532,0.000049852813,0.002873922,0.0000016718141,0.0006411594,0.98927146,0.00013968161],"about_ca_topic_score_codex":0.000028682689,"about_ca_topic_score_gemma":0.00008935946,"teacher_disagreement_score":0.9882374,"about_ca_system_score_codex":0.00033141577,"about_ca_system_score_gemma":0.00051716587,"threshold_uncertainty_score":0.96614623},"labels":[],"label_agreement":null},{"id":"W4318577082","doi":"10.1093/ecco-jcc/jjac190.0907","title":"P777 Deployment of an artificial intelligence tool for precision medicine in ulcerative colitis: Preliminary data from 8 globally distributed clinical sites","year":2023,"lang":"en","type":"article","venue":"Journal of Crohn s and Colitis","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Artificial intelligence; Confusion matrix; Computer science; Machine learning; Population; Convolutional neural network; Automated method; Robustness (evolution); Confusion; Pattern recognition (psychology); Medicine","score_opus":0.07356560167312096,"score_gpt":0.40746066890673727,"score_spread":0.3338950672336163,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318577082","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9733988,0.00032961363,0.021241037,0.003950685,0.00029820218,0.00035626363,0.0003866351,0.000012020586,0.000026747077],"genre_scores_gemma":[0.9926871,0.0008405666,0.0049749524,0.00031299924,0.000736945,0.0000053130025,0.0004092306,0.00001462178,0.000018240093],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99766195,0.00017317334,0.00126724,0.00025729008,0.00042543607,0.00021493004],"domain_scores_gemma":[0.9977359,0.0010910311,0.00041795918,0.00026452373,0.0002647936,0.00022576736],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024210582,0.0001230717,0.0006361587,0.00012765995,0.000062884865,0.000040002185,0.00026767733,0.00009457008,0.00005734329],"category_scores_gemma":[0.0032473502,0.000093339266,0.000073211384,0.00021939908,0.00027623013,0.00018613407,0.00013618673,0.00034894387,9.522988e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.04608385,0.0012026435,0.033920564,0.00027884435,0.00042896712,0.0018097954,0.0017041791,0.0003914209,0.00046880892,0.0025596905,0.019341711,0.8918095],"study_design_scores_gemma":[0.0015730511,0.0033457545,0.88851976,0.0011052607,0.00018622626,0.00013073721,0.0008645147,0.090899505,0.00017118281,0.011189673,0.0019096007,0.00010475539],"about_ca_topic_score_codex":0.0001862773,"about_ca_topic_score_gemma":0.000112213944,"teacher_disagreement_score":0.8917048,"about_ca_system_score_codex":0.00004181902,"about_ca_system_score_gemma":0.00020468592,"threshold_uncertainty_score":0.3887616},"labels":[],"label_agreement":null},{"id":"W4318818646","doi":"10.12688/f1000research.127142.1","title":"Med-ImageTools: An open-source Python package for robust data processing pipelines and curating medical imaging data","year":2023,"lang":"en","type":"preprint","venue":"F1000Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; Kingston Health Sciences Centre; Princess Margaret Cancer Centre; University Health Network; University of Toronto; Queen's University","funders":"Canadian Institutes of Health Research; Canadian Cancer Society","keywords":"Python (programming language); Leverage (statistics); Computer science; Artificial intelligence; Software; Data science; Machine learning; Operating system","score_opus":0.2811147060090144,"score_gpt":0.4959639366269276,"score_spread":0.21484923061791322,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318818646","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012575444,0.010074042,0.8152099,0.14641207,0.0016728278,0.007920398,0.0023041477,0.002012787,0.0018183686],"genre_scores_gemma":[0.12884797,0.009220014,0.6524951,0.008427769,0.02422552,0.0013378832,0.15355577,0.0036001853,0.018289795],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99175835,0.000531548,0.0010788215,0.0029887499,0.0024210261,0.001221487],"domain_scores_gemma":[0.9908845,0.0015419363,0.0003589994,0.0053303107,0.00058404135,0.0013002319],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","open_science","research_integrity"],"consensus_categories":["open_science"],"category_scores_codex":[0.016201207,0.00056659145,0.0011444706,0.00047814468,0.00069145847,0.0021465395,0.007774547,0.00041188282,0.00014247313],"category_scores_gemma":[0.035451517,0.00049013644,0.00006126009,0.00043955588,0.0007320315,0.001241672,0.037023164,0.004326941,0.00002193878],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026996428,0.0002871359,0.0082182335,0.005058127,0.00016247827,0.0006808984,0.0006369224,0.00013556457,0.0008908452,0.000037734186,0.16369607,0.819926],"study_design_scores_gemma":[0.0018153909,0.00008004656,0.001216233,0.0037063458,0.00019677758,0.00023770684,0.0009389028,0.94201034,0.00002756299,0.00047822067,0.04881032,0.00048212663],"about_ca_topic_score_codex":0.0015566628,"about_ca_topic_score_gemma":0.00016589093,"teacher_disagreement_score":0.9418748,"about_ca_system_score_codex":0.00010495384,"about_ca_system_score_gemma":0.0024139858,"threshold_uncertainty_score":0.999755},"labels":[],"label_agreement":null},{"id":"W4319020042","doi":"10.3389/fonc.2023.898854","title":"A radiomic biomarker for prognosis of resected colorectal cancer liver metastases generalizes across MRI contrast agents","year":2023,"lang":"en","type":"article","venue":"Frontiers in Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; University of Ottawa; University of Toronto; Sunnybrook Health Science Centre","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto","keywords":"Medicine; Cohort; Colorectal cancer; Logistic regression; Retrospective cohort study; Biomarker; Magnetic resonance imaging; Radiology; Cancer; Oncology; Nuclear medicine; Internal medicine","score_opus":0.035761439448138796,"score_gpt":0.3816494517805568,"score_spread":0.345888012332418,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319020042","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9880163,0.0018414382,0.0037752287,0.003087011,0.0018222698,0.0010753814,0.0001812353,0.00007837446,0.00012273522],"genre_scores_gemma":[0.97115916,0.0023978814,0.023976417,0.0006611824,0.0002440523,0.00071834086,0.00025060645,0.00005853082,0.00053381873],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9983344,0.00018115716,0.00044008938,0.00030721878,0.00018878389,0.00054831954],"domain_scores_gemma":[0.9991726,0.0002716233,0.0001740988,0.00012986193,0.000111205605,0.00014056641],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008261292,0.00016548343,0.00074520934,0.00031978736,0.000076694574,0.000010281566,0.00016106822,0.00017938577,0.00006745001],"category_scores_gemma":[0.000734564,0.00014453461,0.00015553132,0.0005896245,0.00037260985,0.00004704351,0.00006907738,0.000244393,0.000003098584],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0024754256,0.00035791897,0.38576934,0.00031052032,0.00077794184,0.00026301222,0.0020375194,0.0002466386,0.025149358,0.000034677683,0.4397147,0.14286293],"study_design_scores_gemma":[0.01883007,0.0016202104,0.46324196,0.00032471973,0.00052361446,0.00009631586,0.001761999,0.29773432,0.010677162,0.00021994149,0.20453472,0.0004349745],"about_ca_topic_score_codex":0.000478621,"about_ca_topic_score_gemma":0.00012412218,"teacher_disagreement_score":0.29748768,"about_ca_system_score_codex":0.0002944158,"about_ca_system_score_gemma":0.00025952182,"threshold_uncertainty_score":0.58939505},"labels":[],"label_agreement":null},{"id":"W4320016403","doi":"10.1016/j.ctro.2023.100590","title":"Artificial intelligence to predict outcomes of head and neck radiotherapy","year":2023,"lang":"en","type":"article","venue":"Clinical and Translational Radiation Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Polytechnique Montréal; Centre Hospitalier de l’Université de Montréal","funders":"","keywords":"Radiation therapy; Head and neck cancer; Medicine; Context (archaeology); Radiomics; Medical physics; Clinical trial; Head and neck; Radiology; Surgery; Pathology","score_opus":0.06672294476985431,"score_gpt":0.45334468492906127,"score_spread":0.386621740159207,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4320016403","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92737156,0.00022994007,0.014174989,0.057373077,0.00026509192,0.00023091034,0.00001016815,0.0000397644,0.0003045192],"genre_scores_gemma":[0.9895377,0.00078766263,0.007290574,0.0020140363,0.00024966357,0.000009066118,0.0000336853,0.000009082062,0.00006848969],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9989516,0.000072883675,0.0005197898,0.00019809493,0.00014304793,0.00011459187],"domain_scores_gemma":[0.9985937,0.0010486151,0.000064431086,0.00006611864,0.00003956002,0.00018761224],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006629229,0.00007152515,0.0003349792,0.0001201756,0.000045745335,0.0000058164756,0.00003390112,0.00010584989,0.000055643253],"category_scores_gemma":[0.0005339423,0.00005881405,0.00006155428,0.0001834785,0.00020978542,0.000032028827,0.0000089829,0.00019106915,0.000008683524],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014843432,0.000074806674,0.4653022,0.000014006876,0.00004569495,0.0000047834005,0.00016659364,0.00017058378,0.000055855035,0.0061565554,0.0001271406,0.5277333],"study_design_scores_gemma":[0.0005403282,0.0006374565,0.92767894,0.000017355305,0.00003459348,0.000012516992,0.000018572762,0.04484874,0.000016350328,0.0064426116,0.019697107,0.000055401346],"about_ca_topic_score_codex":0.000009692494,"about_ca_topic_score_gemma":0.000004097515,"teacher_disagreement_score":0.52767795,"about_ca_system_score_codex":0.0000066759203,"about_ca_system_score_gemma":0.00008942868,"threshold_uncertainty_score":0.23983674},"labels":[],"label_agreement":null},{"id":"W4320064976","doi":"10.14309/01.ajg.0000859688.90886.39","title":"S762 Evaluation of Clinical Variables, Radiological Visual Analog Scoring, and Radiomics Features on MR Enterography for Characterizing Severe Inflammation and Fibrosis in Stricturing Crohn’s Disease","year":2022,"lang":"en","type":"article","venue":"The American Journal of Gastroenterology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Medicine; Fibrosis; Radiology; Stenosis; Radiomics; Histopathology; Inflammation; Pathology; Internal medicine","score_opus":0.021727642054996776,"score_gpt":0.33901215649134364,"score_spread":0.31728451443634687,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4320064976","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99643284,0.00016024284,0.0005215248,0.0024487155,0.00015569989,0.00026511314,0.000008713686,0.000004210774,0.000002946538],"genre_scores_gemma":[0.99737406,0.00026702113,0.0013470165,0.0007364002,0.00023529657,0.000015912228,0.000011753681,0.000011266346,0.0000012939587],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99777067,0.000890919,0.0006504162,0.00017919621,0.00030448442,0.00020434607],"domain_scores_gemma":[0.9983834,0.0003875104,0.0008963308,0.00010581475,0.00008399953,0.00014295227],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034673535,0.00011607217,0.00060456333,0.00028365833,0.000092098024,0.000013752284,0.00011571899,0.000021779766,0.0000072861326],"category_scores_gemma":[0.0006490345,0.00008231199,0.00012885417,0.00011568256,0.0003278466,0.00005120188,0.00007746934,0.00061635254,2.0879675e-8],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.028553138,0.0001801593,0.9145249,0.000041757336,0.00021719637,0.00004118882,0.00029537315,0.0022157787,0.0026212991,0.000034773315,0.00005755606,0.051216837],"study_design_scores_gemma":[0.003744203,0.008120113,0.9730641,0.00008461637,0.00027086868,0.00052562857,0.00026807113,0.013660461,0.000017724304,0.00013376094,0.00006522412,0.00004521606],"about_ca_topic_score_codex":0.000012351773,"about_ca_topic_score_gemma":0.0000012513876,"teacher_disagreement_score":0.05853917,"about_ca_system_score_codex":0.00005777666,"about_ca_system_score_gemma":0.000063081876,"threshold_uncertainty_score":0.33565855},"labels":[],"label_agreement":null},{"id":"W4320926269","doi":"10.2196/preprints.44779","title":"A Scalable Radiomics- and Natural Language Processing–Based Machine Learning Pipeline to Distinguish Between Painful and Painless Thoracic Spinal Bone Metastases: Retrospective Algorithm Development and Validation Study (Preprint)","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre","funders":"","keywords":"Medicine; Artificial intelligence; Receiver operating characteristic; Radiomics; Machine learning; Radiology; Computer science; Algorithm; Internal medicine","score_opus":0.015382863830155481,"score_gpt":0.3273828008388075,"score_spread":0.31199993700865203,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4320926269","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9223817,0.003692749,0.06999417,0.0012898665,0.00012870297,0.0021177786,0.00003947429,0.00025404876,0.00010151558],"genre_scores_gemma":[0.9023681,0.000033628563,0.09546018,0.00037907,0.00024868935,0.00017546632,0.0006416218,0.000088034816,0.00060520973],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99598587,0.00051656883,0.0008017748,0.0014359659,0.0007750479,0.000484752],"domain_scores_gemma":[0.9983335,0.00020248235,0.00041075327,0.00037346283,0.00020274577,0.00047703148],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.004354186,0.000596129,0.0012348383,0.0004885175,0.00056911615,0.00036120892,0.00017319393,0.00013763661,0.00006695591],"category_scores_gemma":[0.002001696,0.0005305709,0.00007397763,0.000343001,0.00015109792,0.00008506015,0.0013617382,0.0025715525,0.000001136933],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027215778,0.00027928475,0.35153356,0.0010933991,0.00024755448,0.00031723286,0.005562239,0.00023337685,0.00014179319,0.0000047040544,0.00004264906,0.6402721],"study_design_scores_gemma":[0.0065178555,0.001667119,0.38810894,0.0018817062,0.0016200842,0.00029194372,0.009925522,0.58310986,0.0008940478,0.000095605,0.0039831963,0.0019041466],"about_ca_topic_score_codex":0.0007975019,"about_ca_topic_score_gemma":0.000030771647,"teacher_disagreement_score":0.6383679,"about_ca_system_score_codex":0.00036758432,"about_ca_system_score_gemma":0.0002978051,"threshold_uncertainty_score":0.9997296},"labels":[],"label_agreement":null},{"id":"W4321378818","doi":"10.1016/j.phrs.2023.106706","title":"Artificial intelligence in liver cancers: Decoding the impact of machine learning models in clinical diagnosis of primary liver cancers and liver cancer metastases","year":2023,"lang":"en","type":"article","venue":"Pharmacological Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":82,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Princess Margaret Cancer Centre; Toronto General Hospital; University Health Network","funders":"","keywords":"Medicine; Liver cancer; Cancer; Artificial intelligence; Nanomedicine; Deep learning; Hepatocellular carcinoma; Machine learning; Bioinformatics; Computer science; Internal medicine","score_opus":0.3352209438622157,"score_gpt":0.5326769615742459,"score_spread":0.19745601771203025,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321378818","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98856944,0.009461547,0.00013198925,0.0008029137,0.00007163491,0.000634892,0.000023880642,0.000022344284,0.00028134836],"genre_scores_gemma":[0.8975746,0.10173862,0.00022005526,0.00013500304,0.000118408454,0.00015206498,0.000008648675,0.000018023393,0.00003456857],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99621975,0.0012447042,0.0007624641,0.00044263582,0.00069057336,0.0006398917],"domain_scores_gemma":[0.99380684,0.0054802694,0.00014548273,0.00013889546,0.00018398506,0.00024455105],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0069507235,0.00017267157,0.00064569945,0.00047499666,0.00010600939,0.000020691885,0.00029112684,0.000115079674,0.0006025119],"category_scores_gemma":[0.0029632885,0.000108500644,0.000170053,0.0013960794,0.0009437805,0.00012091604,0.00039004258,0.002236693,0.0000055355445],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017051909,0.00041070627,0.32890132,0.00031755288,0.00024044463,0.00070349104,0.0015011282,0.09090801,0.005099378,0.00020085355,0.0008802516,0.5691317],"study_design_scores_gemma":[0.0005726596,0.0005579417,0.1363541,0.00030602494,0.00006641047,0.000006717243,0.00022123069,0.86000186,0.0012583772,0.00045617824,0.00008572395,0.00011275379],"about_ca_topic_score_codex":0.03412233,"about_ca_topic_score_gemma":0.00064162724,"teacher_disagreement_score":0.7690939,"about_ca_system_score_codex":0.000689004,"about_ca_system_score_gemma":0.0006911933,"threshold_uncertainty_score":0.9723095},"labels":[],"label_agreement":null},{"id":"W4321498667","doi":"10.1038/s41746-023-00769-z","title":"Author Correction: Prostate cancer therapy personalization via multi-modal deep learning on randomized phase III clinical trials","year":2023,"lang":"en","type":"erratum","venue":"npj Digital Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre; Nova Scotia Cancer Centre; Centre Hospitalier de l’Université de Montréal; Horizon Health Network; Occupational Cancer Research Centre; Saint John Regional Hospital","funders":"","keywords":"Personalization; Prostate cancer; Randomized controlled trial; Modal; Phase (matter); Medicine; Medical physics; Cancer; Computer science; Internal medicine; World Wide Web; Physics; Materials science","score_opus":0.08889351755534235,"score_gpt":0.4632223718861051,"score_spread":0.37432885433076274,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321498667","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010089265,0.043982107,0.12719311,0.115760244,0.5994443,0.024862764,0.0002514868,0.005067731,0.07334895],"genre_scores_gemma":[0.03456843,0.022617644,0.00014650702,0.0042906106,0.03089746,0.0007484232,0.0075560617,0.0005394789,0.8986354],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99157506,0.0016199299,0.0031438977,0.0012505014,0.0016741878,0.0007364012],"domain_scores_gemma":[0.9915565,0.0047232816,0.0019057436,0.00050102227,0.0005004427,0.0008130041],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.010798087,0.000906355,0.0053902906,0.00066467206,0.00030678554,0.0001546057,0.00027284437,0.00093756476,0.0009078507],"category_scores_gemma":[0.049853683,0.0005963828,0.0011047777,0.0007040446,0.0010084745,0.00018110318,0.00007292652,0.0051973187,0.00012138686],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.05247386,0.00051324535,0.00022619106,0.00021537665,0.001097744,0.00023232866,0.0012270412,0.00006889094,0.000037235368,0.000013251289,0.48428127,0.45961356],"study_design_scores_gemma":[0.31803933,0.0022183731,0.00017358808,0.0041035954,0.00095693854,0.00008023717,0.00033379567,0.22397217,0.0000039882966,0.000053457326,0.44956118,0.00050331897],"about_ca_topic_score_codex":0.00025753985,"about_ca_topic_score_gemma":0.000009572211,"teacher_disagreement_score":0.82528645,"about_ca_system_score_codex":0.0002731861,"about_ca_system_score_gemma":0.00056887383,"threshold_uncertainty_score":0.99964875},"labels":[],"label_agreement":null},{"id":"W4321596314","doi":"10.3390/curroncol30030203","title":"Artificial Intelligence in Brain Tumor Imaging: A Step toward Personalized Medicine","year":2023,"lang":"en","type":"review","venue":"Current Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":110,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine; Personalized medicine; Precision medicine; Brain tumor; Process (computing); Artificial intelligence; Neuroimaging; Medical physics; Bioinformatics; Computer science; Pathology","score_opus":0.2583166340393449,"score_gpt":0.5171610595604317,"score_spread":0.2588444255210868,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321596314","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000008426279,0.98077655,0.0030215273,0.010205896,0.003623807,0.0012393976,0.0000119958995,0.00018194583,0.00093044614],"genre_scores_gemma":[0.000011761118,0.99566245,0.00046883285,0.00069655303,0.002137266,0.00024949858,0.00030310225,0.00012814508,0.00034239312],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.995573,0.0006246899,0.0016597089,0.00089815503,0.00050314545,0.0007413252],"domain_scores_gemma":[0.9969788,0.0015521185,0.0005546103,0.00041692524,0.00009700335,0.00040053314],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.002171798,0.000585535,0.0036316453,0.0010407682,0.000061113744,0.000020738178,0.0004453221,0.00024125777,0.00049944787],"category_scores_gemma":[0.0049299216,0.00044091936,0.00048526525,0.0010851847,0.00075612863,0.00003809069,0.00021651927,0.0028309864,0.00040004618],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037063284,0.00022586148,0.00005576187,0.013876012,0.00007408962,0.0010845594,0.0004474765,3.836798e-7,6.6407307e-7,0.0015549451,0.013413691,0.9692295],"study_design_scores_gemma":[0.0004358,0.000239803,0.000010096859,0.026988443,0.0006950687,0.0006956838,0.0002664899,0.0039679087,7.097706e-8,0.00063753437,0.96572864,0.00033448334],"about_ca_topic_score_codex":0.0000697383,"about_ca_topic_score_gemma":0.000014148411,"teacher_disagreement_score":0.968895,"about_ca_system_score_codex":0.0008226142,"about_ca_system_score_gemma":0.0012906386,"threshold_uncertainty_score":0.99980426},"labels":[],"label_agreement":null},{"id":"W4321597208","doi":"10.3389/fnagi.2022.943566","title":"Patterns of structure-function association in normal aging and in Alzheimer's disease: Screening for mild cognitive impairment and dementia with ML regression and classification models","year":2023,"lang":"en","type":"article","venue":"Frontiers in Aging Neuroscience","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; United Arab Emirates University; Eisai; Northern California Institute for Research and Education; F. Hoffmann-La Roche; University of Southern California; Biogen; BioClinica; Novartis Pharmaceuticals Corporation; Pfizer; Eli Lilly and Company; Bristol-Myers Squibb; U.S. Department of Defense; Meso Scale Diagnostics; National Institute on Aging; Alzheimer's Association; Foundation for the National Institutes of Health","keywords":"Dementia; Cognition; Neuropsychology; Psychology; Alzheimer's disease; Cognitive test; Population; Neuroimaging; Brain Structure and Function; Audiology; Disease; Association (psychology); Neuropsychological test; Medicine; Neuroscience; Internal medicine","score_opus":0.02277172886540402,"score_gpt":0.288650684834036,"score_spread":0.265878955968632,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321597208","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93702364,0.00044954507,0.061232142,0.00078689714,0.00012968,0.00035118806,0.000008980308,0.000014664624,0.000003245497],"genre_scores_gemma":[0.9973389,0.00024078137,0.0021738727,0.00017858416,0.000014041862,0.000018158484,0.000017503786,0.000009940772,0.000008215978],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9990259,0.00005461061,0.00018398491,0.00031672168,0.00021496904,0.00020382396],"domain_scores_gemma":[0.9996546,0.00007102145,0.00012063403,0.000055482044,0.00002411631,0.00007415283],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00050456356,0.000090085094,0.0001612015,0.00035085226,0.000067138746,0.000029140827,0.000033458855,0.00002875036,2.2799055e-7],"category_scores_gemma":[0.000149558,0.00007821001,0.000009719425,0.000300758,0.00006430635,0.00022808547,0.000039432565,0.00018343833,8.3354195e-9],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015372012,0.000015703987,0.9840322,0.00007113734,0.0000060011325,0.000007570168,0.00043442802,0.0012526417,0.0011558674,0.000008273849,0.000023512637,0.012838928],"study_design_scores_gemma":[0.0010006425,0.000042850228,0.57711554,0.00046109632,0.000035256457,0.0000016066683,0.00024408993,0.42088598,0.00006260749,0.00010174468,0.000004258145,0.000044345798],"about_ca_topic_score_codex":0.000042138872,"about_ca_topic_score_gemma":0.000013496576,"teacher_disagreement_score":0.41963333,"about_ca_system_score_codex":0.000034733974,"about_ca_system_score_gemma":0.000026365138,"threshold_uncertainty_score":0.31893116},"labels":[],"label_agreement":null},{"id":"W4322627798","doi":"10.17691/stm2023.15.1.01","title":"Radiomics in Determining Tumor-to-Normal Brain SUV Ratio Based on 11C-Methionine PET/CT in Glioblastoma","year":2023,"lang":"en","type":"article","venue":"Sovremennye tehnologii v medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Ministry of Science and Higher Education of the Russian Federation","keywords":"Radiomics; Glioblastoma; Medicine; Nuclear medicine; Correlation; Magnetic resonance imaging; Radiology; Mathematics","score_opus":0.016601632978346596,"score_gpt":0.31024220346253556,"score_spread":0.29364057048418896,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4322627798","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.920979,0.000091174996,0.0007370746,0.073469445,0.0006840219,0.0008391169,0.000004028704,0.0005180297,0.002678114],"genre_scores_gemma":[0.97959936,0.00004650442,0.0019794176,0.01690924,0.00039331653,0.00011529318,0.00006016986,0.00009169008,0.00080503256],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99579823,0.0002744323,0.001057375,0.0008589077,0.00087639847,0.0011346606],"domain_scores_gemma":[0.9975035,0.0010467718,0.00019851682,0.00072347576,0.000077122604,0.00045060436],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0036958044,0.0004784405,0.0010685839,0.00278576,0.00012730683,0.000024445484,0.0004260254,0.000066276465,0.0003255655],"category_scores_gemma":[0.009157571,0.00039983052,0.00010960184,0.0031288553,0.00037381283,0.00010093708,0.00013785802,0.0017681791,0.00018070948],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003701203,0.001195913,0.5835369,0.0009492846,0.00018424839,0.0922763,0.0033001513,0.036265787,0.07211776,0.0020559465,0.058739558,0.1456769],"study_design_scores_gemma":[0.025440613,0.007008206,0.19869182,0.0041590454,0.000103460115,0.0016552942,0.0025085954,0.74086356,0.002547088,0.0005989383,0.015367427,0.0010559373],"about_ca_topic_score_codex":0.00021473621,"about_ca_topic_score_gemma":0.00016973719,"teacher_disagreement_score":0.7045978,"about_ca_system_score_codex":0.00041275192,"about_ca_system_score_gemma":0.0002862087,"threshold_uncertainty_score":0.9998454},"labels":[],"label_agreement":null},{"id":"W4322719121","doi":"10.1177/08465371231157592","title":"Risk Stratification for Oropharyngeal Squamous Cell Carcinoma Using Texture Analysis on CT – A Step Beyond HPV Status","year":2023,"lang":"en","type":"article","venue":"Canadian Association of Radiologists Journal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University; University of Calgary","funders":"","keywords":"Medicine; Radiomics; Internal medicine; Oncology; Multivariate analysis; Human papillomavirus; Risk stratification; Radiology; Basal cell; Stage (stratigraphy)","score_opus":0.01384157575553129,"score_gpt":0.2849268866943049,"score_spread":0.2710853109387736,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4322719121","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99126184,0.00020760372,0.0042572957,0.002080912,0.00043711485,0.0003268606,0.00030501425,0.000030688912,0.0010926512],"genre_scores_gemma":[0.99601847,0.000101760575,0.0019756784,0.00038145523,0.000403471,0.000005945254,0.00030354806,0.00002517629,0.0007844962],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99807477,0.00023321129,0.00049795967,0.0002521665,0.0003683113,0.0005735617],"domain_scores_gemma":[0.9975688,0.00046443124,0.00082976546,0.0001918901,0.0003110397,0.00063407654],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016381469,0.00016092895,0.0005128277,0.0009519558,0.00035138353,0.0000619623,0.00012838934,0.00013626587,0.00008855143],"category_scores_gemma":[0.0024721648,0.00014535646,0.00031602872,0.00084278104,0.0000547754,0.00006680317,0.000006650356,0.0006896633,0.000006493383],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009485136,0.00005662474,0.92588675,0.00006173715,0.0005654381,0.00017850428,0.0004453359,0.017555557,0.00088237814,0.00016125814,0.034098316,0.020013278],"study_design_scores_gemma":[0.0024755765,0.00042836723,0.7819749,0.000012874226,0.0014669303,0.000070602866,0.00038735484,0.20674172,0.0000938133,0.0002242624,0.0059198174,0.00020379064],"about_ca_topic_score_codex":0.007777287,"about_ca_topic_score_gemma":0.004330342,"teacher_disagreement_score":0.18918617,"about_ca_system_score_codex":0.0019202381,"about_ca_system_score_gemma":0.0010348188,"threshold_uncertainty_score":0.99883},"labels":[],"label_agreement":null},{"id":"W4322774167","doi":"10.1158/1538-7445.sabcs22-p2-11-34","title":"Abstract P2-11-34: Mitotic spindle hotspot counting using deep learning networks is highly associated with clinical outcomes in patients with early-stage triple-negative breast cancer who did not receive systemic therapy","year":2023,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Triple-negative breast cancer; Medicine; Cohort; Oncology; Breast cancer; Internal medicine; Hazard ratio; Stage (stratigraphy); Proportional hazards model; Cancer; Biology","score_opus":0.06003398759239935,"score_gpt":0.40805212454070355,"score_spread":0.3480181369483042,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4322774167","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9965441,0.0002360656,0.000067368135,0.0012965545,0.00032448984,0.0012977073,0.00004115207,0.000121059355,0.00007146344],"genre_scores_gemma":[0.9968205,0.0010302542,0.00005183504,0.00038212712,0.00036046235,0.00014833015,0.000042443866,0.0001488958,0.001015121],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9947243,0.00065574044,0.0007790638,0.0008477966,0.0017038953,0.001289201],"domain_scores_gemma":[0.9965099,0.001421861,0.0004365181,0.00036122047,0.0008977358,0.00037277603],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0034481229,0.00037189867,0.0010506744,0.00051619735,0.00044430495,0.00016437916,0.00031280768,0.00026935755,0.0001659374],"category_scores_gemma":[0.0011357367,0.00026586142,0.00013417628,0.0018806347,0.0004767559,0.00023709032,0.00012988946,0.0033043989,0.000011842885],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016276981,0.00016605911,0.9765842,0.0001121279,0.00045796242,0.00013466012,0.0012789809,0.011129067,0.00010665344,0.0000027000435,0.00016254334,0.008237343],"study_design_scores_gemma":[0.008400211,0.00040105783,0.947011,0.0033856286,0.000055408957,0.000003701285,0.00059587165,0.03973305,0.000033363325,0.0000026424125,0.00006916978,0.00030892066],"about_ca_topic_score_codex":0.012213658,"about_ca_topic_score_gemma":0.00076259766,"teacher_disagreement_score":0.02957323,"about_ca_system_score_codex":0.0011960441,"about_ca_system_score_gemma":0.0006568457,"threshold_uncertainty_score":0.9999794},"labels":[],"label_agreement":null},{"id":"W4322774420","doi":"10.1002/ima.22868","title":"Prediction of drug amount in Parkinson's disease using hybrid machine learning systems and radiomics features","year":2023,"lang":"en","type":"article","venue":"International Journal of Imaging Systems and Technology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Teck (Canada); University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Levodopa; Computer science; Feature selection; Artificial intelligence; Feature (linguistics); Machine learning; Parkinson's disease; Medicine; Disease; Internal medicine","score_opus":0.008606671960631952,"score_gpt":0.26686609019464835,"score_spread":0.2582594182340164,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4322774420","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9814984,0.012324868,0.0012651014,0.0035478538,0.001130798,0.000132929,0.000022904736,0.00005103398,0.000026089683],"genre_scores_gemma":[0.9978907,0.0014746031,0.0002559188,0.000027319402,0.00023709303,0.000002954848,0.0000136097415,0.000019832469,0.000077951976],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987032,0.000063200125,0.0005623376,0.00016555404,0.0003450674,0.00016065747],"domain_scores_gemma":[0.99902207,0.00008626536,0.00044531358,0.000086212385,0.0002581355,0.00010203109],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00081094966,0.00011977371,0.00037607993,0.0013359104,0.000045960212,0.000057696587,0.0001322379,0.00004341979,0.000001102842],"category_scores_gemma":[0.00050666794,0.00010115976,0.00004554498,0.0002398122,0.00016319238,0.00012525062,0.0000801774,0.0005636844,2.8432154e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013654631,0.000045120138,0.9779518,0.00024612632,0.00017236396,0.0012547104,0.00020832938,0.0027965032,0.0076819314,0.0010393095,0.00043228953,0.008034948],"study_design_scores_gemma":[0.0030534095,0.00008618553,0.07626738,0.0026577606,0.0001226921,0.010910353,0.0012583487,0.8896512,0.00017362808,0.0003377301,0.0153381685,0.00014317223],"about_ca_topic_score_codex":0.0003436653,"about_ca_topic_score_gemma":0.000001341782,"teacher_disagreement_score":0.90168446,"about_ca_system_score_codex":0.00010292475,"about_ca_system_score_gemma":0.00007704695,"threshold_uncertainty_score":0.41251755},"labels":[],"label_agreement":null},{"id":"W4322775415","doi":"10.1158/1538-7445.sabcs22-p6-01-18","title":"Abstract P6-01-18: Predicting response of triple negative breast cancer to neoadjuvant chemotherapy using a deep convolutional neural network-based artificial intelligence tool","year":2023,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Triple-negative breast cancer; Receiver operating characteristic; Breast cancer; Artificial intelligence; Convolutional neural network; Medicine; Stage (stratigraphy); Cancer; Deep learning; Oncology; Internal medicine; Machine learning; Pathology; Computer science; Biology","score_opus":0.10682659218930736,"score_gpt":0.44550141574931906,"score_spread":0.3386748235600117,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4322775415","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9823043,0.0002921063,0.0042556636,0.01166097,0.0004987822,0.0007928549,0.000082499275,0.00008363362,0.000029239582],"genre_scores_gemma":[0.99614847,0.00008956654,0.0015068608,0.0007254158,0.0011718964,0.00015174359,0.00001590807,0.000057839534,0.00013227404],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967124,0.00030286997,0.0005316601,0.00047820408,0.0011007522,0.00087413186],"domain_scores_gemma":[0.99772555,0.00094785966,0.00012688918,0.0002958499,0.0005679781,0.00033589234],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0033195214,0.00018738507,0.00040571328,0.00041847676,0.00036029413,0.000064853324,0.00025486248,0.00010448371,0.0011326312],"category_scores_gemma":[0.0013925263,0.00016965896,0.0001172771,0.0018504603,0.00049521547,0.00008388469,0.000099455814,0.001009677,0.000014924042],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.022645155,0.00020590462,0.036275063,0.00033784605,0.00021889972,0.00021076672,0.0023848899,0.49906954,0.23669304,0.00012889337,0.0046419175,0.19718806],"study_design_scores_gemma":[0.0010018363,0.00022310231,0.14503908,0.0009190473,0.000027681297,0.000021803518,0.00039864934,0.84193,0.009658498,0.00027028282,0.00031130877,0.00019875393],"about_ca_topic_score_codex":0.0034077317,"about_ca_topic_score_gemma":0.00010398566,"teacher_disagreement_score":0.3428604,"about_ca_system_score_codex":0.0005530946,"about_ca_system_score_gemma":0.0016940698,"threshold_uncertainty_score":0.9997805},"labels":[],"label_agreement":null},{"id":"W4323034702","doi":"10.1002/9781119790686.ch32","title":"Clinical Applications of AI in Diagnostic Imaging","year":2023,"lang":"en","type":"other","venue":"AI in Clinical Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vancouver General Hospital; University of British Columbia","funders":"","keywords":"Food and drug administration; Patient care; Computer science; Order (exchange); Medical physics; Artificial intelligence; Data science; Medicine; Risk analysis (engineering); Business; Nursing; Finance","score_opus":0.03428021774779144,"score_gpt":0.4690402770489881,"score_spread":0.43476005930119666,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4323034702","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0039629485,0.024242846,0.01764352,0.3770984,0.015562253,0.010026207,0.00006959929,0.0023831397,0.54901105],"genre_scores_gemma":[0.29268533,0.11058129,0.009611301,0.15383032,0.04147322,0.0015222221,0.0007913949,0.0073859137,0.382119],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9941096,0.00037859753,0.0035290583,0.0008804883,0.000617423,0.00048488542],"domain_scores_gemma":[0.984568,0.013179699,0.0007247426,0.0009833861,0.000091894304,0.00045227894],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.005500427,0.00036675506,0.002284691,0.00088578847,0.000017412238,0.00000544976,0.00040182896,0.00060989714,0.0007286503],"category_scores_gemma":[0.04266275,0.00029388833,0.00029752523,0.000936461,0.0013459936,0.000028353496,0.00015575842,0.0041594063,0.00018460014],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033236665,0.0004036125,0.5083953,0.00029720034,0.000065076354,0.00030430747,0.000026951973,0.0000018643168,0.0000021346616,0.00023561422,0.2968509,0.19338378],"study_design_scores_gemma":[0.006421463,0.0003659262,0.2906578,0.010340396,0.00029313547,0.000024892375,0.000057840727,0.0019309012,3.45532e-7,0.001387894,0.68823415,0.00028527871],"about_ca_topic_score_codex":0.0017921631,"about_ca_topic_score_gemma":0.000558735,"teacher_disagreement_score":0.39138326,"about_ca_system_score_codex":0.000067256056,"about_ca_system_score_gemma":0.00030194817,"threshold_uncertainty_score":0.9999513},"labels":[],"label_agreement":null},{"id":"W4323035249","doi":"10.1002/9781119790686.ch34","title":"AI for Medical Image Processing","year":2023,"lang":"en","type":"other","venue":"AI in Clinical Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; University of Toronto","funders":"","keywords":"Convolutional neural network; Computer science; Scope (computer science); Quality assurance; Medical imaging; Image quality; Image processing; Medical physics; Artificial intelligence; Artificial neural network; Quality (philosophy); Image (mathematics); Computer vision; Medicine; Pathology","score_opus":0.04139267117788451,"score_gpt":0.4816122287065652,"score_spread":0.4402195575286807,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4323035249","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00011028062,0.0054854825,0.02259967,0.6661513,0.008632717,0.003246804,0.000026484226,0.0026579376,0.29108936],"genre_scores_gemma":[0.002403908,0.008784832,0.009885133,0.20628002,0.035762914,0.00043912072,0.00039297735,0.005267673,0.7307834],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99517477,0.00014976392,0.0018420338,0.0009529891,0.0011920274,0.00068842614],"domain_scores_gemma":[0.99580157,0.0021655809,0.0004217366,0.000605995,0.00013455594,0.0008705389],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0048257387,0.00046051905,0.0020204538,0.00058442925,0.00004793135,0.000018056859,0.00041159685,0.0012052268,0.0026461312],"category_scores_gemma":[0.03188475,0.0003324741,0.0003068347,0.0005069746,0.0011601764,0.000042486987,0.000120448734,0.0033486444,0.0001945741],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009695561,0.00017091718,0.0034736565,0.0008853035,0.00008820775,0.00052148674,0.000035868587,1.6390582e-7,0.000005217174,0.0001252083,0.787071,0.20752603],"study_design_scores_gemma":[0.00847913,0.00074318325,0.0029516637,0.0149977,0.00031399424,0.0000808977,0.00003855811,0.009923042,9.29173e-7,0.0008450078,0.9612839,0.00034197487],"about_ca_topic_score_codex":0.00038448707,"about_ca_topic_score_gemma":0.0002662294,"teacher_disagreement_score":0.45987123,"about_ca_system_score_codex":0.000078557176,"about_ca_system_score_gemma":0.0006510703,"threshold_uncertainty_score":0.99991274},"labels":[],"label_agreement":null},{"id":"W4323035346","doi":"10.1002/9781119790686.ch31","title":"Introduction to AI in Radiology","year":2023,"lang":"en","type":"other","venue":"AI in Clinical Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vancouver General Hospital","funders":"","keywords":"Workflow; Mammography; Radiology; Medical physics; Medicine; Artificial intelligence; Computed tomography; Field (mathematics); Computer science; Database","score_opus":0.03116321682672671,"score_gpt":0.44040142423520884,"score_spread":0.40923820740848216,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4323035346","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018974934,0.001639255,0.0007835389,0.8920205,0.014354051,0.0014370716,0.0000037844777,0.0007215551,0.0871427],"genre_scores_gemma":[0.007877717,0.009571858,0.0021302395,0.15939374,0.08153696,0.0001761675,0.00021105449,0.002226823,0.7368754],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.996463,0.0002976776,0.0014196123,0.0009166726,0.0003972255,0.0005058076],"domain_scores_gemma":[0.99772394,0.0009411359,0.00020292898,0.00066810317,0.00004195964,0.00042191573],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003290439,0.00032107322,0.0016951481,0.0011437546,0.000013987202,0.0000047568865,0.00023207648,0.0007277093,0.0019059473],"category_scores_gemma":[0.017623417,0.0002484397,0.00012026078,0.00084730313,0.0004372739,0.00001996092,0.00009480381,0.0031748957,0.00066564855],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012141559,0.00012009577,0.022169176,0.00011238866,0.000054793163,0.00046621962,0.00006485193,0.000008662866,0.000029162946,0.00017498079,0.8949532,0.08172503],"study_design_scores_gemma":[0.0036038093,0.0008716479,0.0511775,0.002303281,0.00008126124,0.00007674355,0.00003150344,0.00056378386,6.547273e-7,0.00031691854,0.94076496,0.00020795065],"about_ca_topic_score_codex":0.0014911364,"about_ca_topic_score_gemma":0.00087913324,"teacher_disagreement_score":0.7326268,"about_ca_system_score_codex":0.0001393779,"about_ca_system_score_gemma":0.00013355193,"threshold_uncertainty_score":0.9999968},"labels":[],"label_agreement":null},{"id":"W4323039578","doi":"10.1016/s0735-1097(23)02614-1","title":"THE IMPACT OF EARLY-STAGE BREAST CANCER ON CARDIAC STRUCTURE AND FUNCTION","year":2023,"lang":"en","type":"article","venue":"Journal of the American College of Cardiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian VIGOUR Centre","funders":"","keywords":"Medicine; Stage (stratigraphy); Breast cancer; Oncology; Internal medicine; Cardiac function curve; Cancer; Cardiology; Heart failure","score_opus":0.007343788769887969,"score_gpt":0.3002347333485616,"score_spread":0.29289094457867365,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4323039578","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9951065,0.0003045907,0.00003252171,0.0036725434,0.00050438946,0.00009141429,0.00011818185,0.000003930124,0.00016590513],"genre_scores_gemma":[0.9983486,0.00090211857,0.000022914774,0.000091773305,0.00046117266,9.4515144e-7,5.2006465e-7,0.000012008365,0.00015997291],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9990356,0.00022292386,0.00027848725,0.00007707823,0.00023333597,0.00015259064],"domain_scores_gemma":[0.99871963,0.00029047846,0.00056778284,0.0001913835,0.00015533433,0.0000753653],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004897289,0.00008972512,0.0006152126,0.00010113065,0.00007331023,0.0000033718075,0.0001301034,0.000032214193,0.0000058130368],"category_scores_gemma":[0.00021444687,0.00004073235,0.0003676635,0.00034869334,0.00053061417,0.000019660689,0.00004571305,0.00040849316,2.3894043e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0028276702,0.000010920447,0.91939884,0.000032747197,0.002016997,0.00006195409,0.00009521655,0.0134442365,0.020355783,0.0001557195,0.016389975,0.025209947],"study_design_scores_gemma":[0.00049990043,0.000936654,0.9946889,0.00005299624,0.00018002128,0.00038433494,0.00024130555,0.0005445624,0.00009445201,0.00012032376,0.0022179962,0.000038517726],"about_ca_topic_score_codex":0.00013467047,"about_ca_topic_score_gemma":0.0000012244604,"teacher_disagreement_score":0.0752901,"about_ca_system_score_codex":0.000057921785,"about_ca_system_score_gemma":0.00017783347,"threshold_uncertainty_score":0.19550699},"labels":[],"label_agreement":null},{"id":"W4323309616","doi":"10.1117/12.2670246","title":"Changes in 3D radiomic texture descriptors in Alzheimer’s disease stages","year":2023,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Foothills Medical Centre; University of Calgary","funders":"","keywords":"Gray level; Texture (cosmology); Pattern recognition (psychology); Atrophy; Artificial intelligence; Cognitive impairment; Dementia; Computer science; Disease; Medicine; Pathology","score_opus":0.025620398329723862,"score_gpt":0.3106098661419697,"score_spread":0.2849894678122459,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4323309616","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9668232,0.0014594978,0.00008043282,0.028695302,0.0003490738,0.00038846492,0.0000041926533,0.00023666331,0.0019631363],"genre_scores_gemma":[0.994301,0.0005974355,0.0004928616,0.0023760563,0.00017482288,0.0000330409,0.000050297636,0.00003416632,0.0019403126],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.998866,0.000054160704,0.0001940661,0.00028207223,0.0002248863,0.00037878146],"domain_scores_gemma":[0.9994142,0.00007864082,0.000029073306,0.0002081204,0.0000131635215,0.00025682568],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042751277,0.00013955722,0.00026510746,0.00052068045,0.00002789964,0.000019447136,0.00010035846,0.00006160932,0.00029607484],"category_scores_gemma":[0.00033702067,0.0001120938,0.0000429738,0.0006433932,0.00006709108,0.00005259555,0.000051287443,0.00042220447,0.000082730716],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001088599,0.00010858936,0.89941376,0.000085830885,0.00003695538,0.0013238809,0.00062837836,0.0002656444,0.0017637836,0.00029966814,0.015633617,0.08033101],"study_design_scores_gemma":[0.00219295,0.00006502718,0.9090424,0.0003111209,0.000065061424,0.000015242163,0.00034689903,0.067455515,0.00014200805,0.00020291015,0.019934934,0.00022594488],"about_ca_topic_score_codex":0.00029298704,"about_ca_topic_score_gemma":0.00022832105,"teacher_disagreement_score":0.08010507,"about_ca_system_score_codex":0.000061760555,"about_ca_system_score_gemma":0.00007748105,"threshold_uncertainty_score":0.45710525},"labels":[],"label_agreement":null},{"id":"W4323309668","doi":"10.1117/12.2670071","title":"The transfer learning gap: quantifying transfer learning in a medical image case","year":2023,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary; Alberta Health Services","funders":"","keywords":"Transfer of learning; Computer science; Artificial intelligence; Machine learning; Metric (unit); Set (abstract data type); Deep learning; Transfer (computing); Engineering","score_opus":0.03321456330584407,"score_gpt":0.3445732235422464,"score_spread":0.31135866023640235,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4323309668","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9541871,0.0002696377,0.0103112105,0.024004556,0.00025878666,0.00032974998,4.843872e-7,0.00065545546,0.009982996],"genre_scores_gemma":[0.99316674,0.00090448954,0.00024592428,0.0008246206,0.00022693456,0.00003636258,0.000020128842,0.00007820841,0.0044965995],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969379,0.00036623015,0.0005915201,0.00045049714,0.00083978707,0.00081408216],"domain_scores_gemma":[0.99815184,0.0011280365,0.0000185706,0.0002269865,0.000060253606,0.00041431628],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0035749362,0.00024944614,0.00043051975,0.00028817388,0.0005792061,0.00010981528,0.00019193091,0.00018716537,0.0007178444],"category_scores_gemma":[0.0023880322,0.00016600736,0.00017152292,0.0009144078,0.00027992824,0.000112953654,0.000051882496,0.0029591883,0.00021097276],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00069655094,0.00035779088,0.100913145,0.0007705341,0.00039158264,0.13392152,0.013271142,0.00540552,0.03252424,0.009997166,0.003950614,0.6978002],"study_design_scores_gemma":[0.0073834406,0.00052345166,0.0108203795,0.00079409184,0.0001547041,0.013757186,0.00929286,0.8520011,0.0006793602,0.00016159868,0.103738315,0.0006935156],"about_ca_topic_score_codex":0.0004669848,"about_ca_topic_score_gemma":0.00025095727,"teacher_disagreement_score":0.8465956,"about_ca_system_score_codex":0.00005906519,"about_ca_system_score_gemma":0.0001911202,"threshold_uncertainty_score":0.999341},"labels":[],"label_agreement":null},{"id":"W4323350964","doi":"10.1093/jcag/gwac036.125","title":"A125 TANDEM STUDY DESIGN IS LESS LIKELY TO DEMONSTRATE IMPROVED ADENOMA DETECTION RATE THAN PARALLEL STUDY DESIGN IN THE ASSESSMENT OF ARTIFICIAL INTELLIGENCE-ASSISTED COLONOSCOPY","year":2023,"lang":"en","type":"article","venue":"Journal of the Canadian Association of Gastroenterology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University Health Network","funders":"","keywords":"Colonoscopy; Randomized controlled trial; Medicine; MEDLINE; Systematic review; Meta-analysis; Adenoma; Internal medicine; Colorectal cancer; Cancer","score_opus":0.04306039274843064,"score_gpt":0.3270081790283978,"score_spread":0.28394778627996714,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4323350964","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96178335,0.000003041449,0.022453448,0.014142886,0.00042144657,0.0011794516,0.000004229451,0.0000049756454,0.0000071626714],"genre_scores_gemma":[0.9976589,0.0000065474114,0.0013073628,0.000873555,0.00008177037,0.000024505343,8.7759696e-7,0.000014183879,0.000032270094],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99561465,0.002459858,0.0009519081,0.00016214087,0.0004473665,0.0003640647],"domain_scores_gemma":[0.997757,0.00042054927,0.0011357081,0.0001921425,0.00031571672,0.0001788531],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007825085,0.00013932635,0.000531854,0.00051663985,0.00014481286,0.00003603367,0.0003754655,0.00009157963,0.000008038013],"category_scores_gemma":[0.0009566134,0.0000963664,0.00013448113,0.00055857777,0.000053338743,0.000050860912,0.000031200398,0.0006763701,0.0000011031688],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00091586745,0.00047768786,0.98453593,0.00000834048,0.00040308436,0.0000589925,0.0025548781,0.00521641,0.003107897,0.000003904825,0.00050239416,0.002214628],"study_design_scores_gemma":[0.001363989,0.0073184497,0.968945,0.000048452544,0.0002419555,0.000033861517,0.004577926,0.017173365,0.00014758598,0.000090799156,0.00001005438,0.000048541948],"about_ca_topic_score_codex":0.0035082698,"about_ca_topic_score_gemma":0.1094407,"teacher_disagreement_score":0.10593243,"about_ca_system_score_codex":0.00085223257,"about_ca_system_score_gemma":0.00064901024,"threshold_uncertainty_score":0.9068097},"labels":[],"label_agreement":null},{"id":"W4323657894","doi":"10.18280/isi.280125","title":"Prediction of Lungs Cancer in Medical Images Using Deep Learning Approach","year":2023,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Deep learning; Artificial intelligence; Cancer; Lung cancer; Computer science; Medicine; Medical physics; Pathology; Internal medicine","score_opus":0.018086639121720538,"score_gpt":0.28526311006785454,"score_spread":0.267176470946134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4323657894","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9452947,0.00023385618,0.04791617,0.00020020464,0.00026342738,0.00030283368,0.0000109703415,0.00020764174,0.00557019],"genre_scores_gemma":[0.9970427,0.00034319528,0.0021205877,0.00011159728,0.00011363477,0.000032144675,0.0001511202,0.000016771864,0.0000682059],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99833584,0.000068527275,0.00063593255,0.00011823191,0.0005645762,0.00027688613],"domain_scores_gemma":[0.9993377,0.00006338231,0.00022194732,0.00011464831,0.00013656479,0.0001257754],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010901927,0.00012310041,0.00029690302,0.000549574,0.00010036156,0.000033575103,0.00009392463,0.00014367633,0.00008726088],"category_scores_gemma":[0.0012945523,0.00011190658,0.00006415042,0.0008536524,0.0001687615,0.0006926389,0.00005765348,0.00047228427,0.000011060646],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001487408,0.000084068175,0.378734,0.0031387913,0.00012526702,0.00003518789,0.014464168,0.067425005,0.004152948,0.00043155314,0.0004936559,0.5307666],"study_design_scores_gemma":[0.00093290524,0.000052417345,0.11279743,0.0006933999,0.00003359847,0.00009512922,0.0010484142,0.8832195,0.00028508742,0.00012635314,0.000627649,0.00008812985],"about_ca_topic_score_codex":0.00042789298,"about_ca_topic_score_gemma":0.00000303154,"teacher_disagreement_score":0.81579447,"about_ca_system_score_codex":0.0002269777,"about_ca_system_score_gemma":0.00016008952,"threshold_uncertainty_score":0.45634177},"labels":[],"label_agreement":null},{"id":"W4324121721","doi":"10.1007/978-3-031-27324-7","title":"Lesion Segmentation in Surgical and Diagnostic Applications","year":2023,"lang":"en","type":"book","venue":"Lecture notes in computer science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Segmentation; Artificial intelligence; Computer vision","score_opus":0.01371909370450642,"score_gpt":0.31025898794153856,"score_spread":0.29653989423703214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4324121721","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003547188,0.0007165068,0.9917508,0.0021212464,0.00034847367,0.0006821753,0.0000019986276,0.00007218317,0.0007594608],"genre_scores_gemma":[0.5825767,0.0066650435,0.38305807,0.0071585546,0.0065004304,0.0005757979,0.0006131992,0.00032766882,0.012524531],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985975,0.00002608352,0.00024014662,0.00052103173,0.00037591404,0.00023929817],"domain_scores_gemma":[0.99826235,0.001311407,0.0000654396,0.000213961,0.000036000045,0.000110821966],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005769171,0.00014961208,0.00027081053,0.0004723051,0.00007233887,0.000059495233,0.00017052119,0.00012605423,0.000005458314],"category_scores_gemma":[0.00037004126,0.00012806596,0.000028561351,0.0005389209,0.00037082072,0.000053361087,0.00016131892,0.0006929612,0.000013538692],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005649491,0.000028703413,0.004025177,0.00012829603,0.0000030322203,0.00023708398,0.00023150553,0.0047917217,0.00008637927,0.00014328079,0.000070332986,0.99024886],"study_design_scores_gemma":[0.0028402142,0.00034917032,0.03306852,0.0037072215,0.00006512035,0.0006679498,0.0000020252296,0.8951105,0.00021381142,0.04804334,0.0151644135,0.0007677064],"about_ca_topic_score_codex":0.000022016915,"about_ca_topic_score_gemma":0.00001943524,"teacher_disagreement_score":0.98948115,"about_ca_system_score_codex":0.00021394652,"about_ca_system_score_gemma":0.00032026536,"threshold_uncertainty_score":0.52223784},"labels":[],"label_agreement":null},{"id":"W4324136996","doi":"10.1200/jco.2023.41.6_suppl.299","title":"Patient-level data meta-analysis of a multi-modal artificial intelligence (MMAI) prognostic biomarker in high-risk prostate cancer: Results from six NRG/RTOG phase III randomized trials.","year":2023,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Saint John Regional Hospital","funders":"","keywords":"Medicine; Prostate cancer; Biomarker; Oncology; Internal medicine; Radiation therapy; Cohort; Randomized controlled trial; Prostate; Cumulative incidence; Cancer","score_opus":0.4715789308372614,"score_gpt":0.5536479833131753,"score_spread":0.08206905247591395,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4324136996","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9671418,0.0016286677,0.010645663,0.015983608,0.0017761737,0.0012778203,0.0014979518,0.000023749684,0.000024546493],"genre_scores_gemma":[0.9792789,0.0035186314,0.015690023,0.00056428637,0.0004077316,0.0000357093,0.00042358568,0.000028295253,0.000052810105],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.97908086,0.0065196687,0.012458182,0.00064364314,0.0008833386,0.00041428296],"domain_scores_gemma":[0.9288459,0.059053846,0.010189487,0.000741854,0.0006409016,0.0005280057],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.057553932,0.00028698164,0.010881008,0.0009516011,0.000054656495,0.000025322728,0.0005493459,0.00038985495,0.00026642645],"category_scores_gemma":[0.2878852,0.00017468087,0.0027031372,0.0014999278,0.0006446138,0.00015542537,0.00027084816,0.0019405701,0.000008913937],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.3191654,0.0033495275,0.0031243018,0.00002256518,0.10861854,0.0009987922,0.0007678174,0.0036837615,0.00025245245,0.000030795654,0.0011841215,0.55880195],"study_design_scores_gemma":[0.21549504,0.0021081183,0.0100538945,0.0001017793,0.26220727,0.000012327596,0.0002561728,0.50695914,0.00006306266,0.0010180232,0.00152004,0.00020515207],"about_ca_topic_score_codex":0.0041771447,"about_ca_topic_score_gemma":0.00081260654,"teacher_disagreement_score":0.5585968,"about_ca_system_score_codex":0.00008219919,"about_ca_system_score_gemma":0.0015174989,"threshold_uncertainty_score":0.9704465},"labels":[],"label_agreement":null},{"id":"W4324149157","doi":"10.3390/cancers15061751","title":"Machine Learning of Multi-Modal Tumor Imaging Reveals Trajectories of Response to Precision Treatment","year":2023,"lang":"en","type":"article","venue":"Cancers","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre","funders":"","keywords":"Sunitinib; Medicine; Artificial intelligence; Medical imaging; Computer science; Machine learning; Nuclear medicine; Radiology; Cancer; Internal medicine","score_opus":0.019238679406179293,"score_gpt":0.3311693829214438,"score_spread":0.31193070351526453,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4324149157","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9962313,0.00058298325,0.0012439888,0.0010865063,0.00024450725,0.00031180927,0.000017886949,0.00008549658,0.00019550373],"genre_scores_gemma":[0.9944734,0.000113334136,0.0032586309,0.00013733888,0.00007154061,0.000024152714,0.000016551157,0.000032602522,0.0018724424],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99881077,0.00011702652,0.00033232133,0.00023679038,0.00026278722,0.000240289],"domain_scores_gemma":[0.99910027,0.00030767714,0.00013039714,0.000208754,0.00008224428,0.00017067796],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006872535,0.00013482937,0.00041271708,0.00026765146,0.00005680915,0.000006181416,0.00008352728,0.00002410217,0.000049977003],"category_scores_gemma":[0.0015953658,0.00010919649,0.0001085995,0.00046616452,0.00009272252,0.000034654568,0.00003729417,0.00017233775,0.0000091580505],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004698135,0.00007222699,0.26491657,0.0002826644,0.00015536878,0.00020748474,0.0069713164,0.03161738,0.57562083,0.00004364779,0.0011441337,0.11427025],"study_design_scores_gemma":[0.011273536,0.0030098776,0.37809026,0.002140217,0.0003329027,0.0001074875,0.0026545322,0.4892409,0.06416223,0.00007743265,0.048353348,0.0005572471],"about_ca_topic_score_codex":0.00081379496,"about_ca_topic_score_gemma":0.0000064892015,"teacher_disagreement_score":0.5114586,"about_ca_system_score_codex":0.0005323726,"about_ca_system_score_gemma":0.00032547273,"threshold_uncertainty_score":0.44529036},"labels":[],"label_agreement":null},{"id":"W4327768895","doi":"10.1007/978-3-031-27420-6","title":"Head and Neck Tumor Segmentation and Outcome Prediction","year":2023,"lang":"en","type":"book","venue":"Lecture notes in computer science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":23,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Texas MD Anderson Cancer Center; Universitätsspital Zürich; Centre Hospitalier Universitaire de Poitiers; Université de Rouen; Université de Bretagne Occidentale; Siemens Healthineers; Cleveland Clinic Foundation; Centre Hospitalier Universitaire Vaudois; Université de Sherbrooke; Cleveland Clinic","keywords":"Computer science; Head and neck; Segmentation; Focus (optics); Artificial intelligence; Head (geology); Outcome (game theory); Image segmentation; Computer vision; Medicine; Surgery; Optics","score_opus":0.015493607312169389,"score_gpt":0.3092354911410024,"score_spread":0.29374188382883304,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4327768895","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0880011,0.0005733813,0.90521204,0.003092247,0.0017618154,0.0006058479,0.0000081101225,0.00019110847,0.00055435946],"genre_scores_gemma":[0.43051794,0.00078573346,0.5235237,0.02317475,0.00578415,0.00006491203,0.00025131018,0.00028255407,0.01561498],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984866,0.000018937275,0.00026888936,0.0005621478,0.00041626993,0.0002471587],"domain_scores_gemma":[0.9993143,0.00020584042,0.00008634941,0.00019705847,0.000046287445,0.00015017204],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00053782563,0.00018579893,0.0003170784,0.00036580605,0.00011863226,0.00010916255,0.000117996846,0.000096568154,0.000004679155],"category_scores_gemma":[0.00028044562,0.00015455167,0.000028254295,0.00026966314,0.00044885752,0.0000971905,0.00017335759,0.0006732354,0.0000048163365],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028764882,0.00003089007,0.12640482,0.00058233313,0.000022869322,0.00024981232,0.0011709438,0.00277496,0.000678633,0.00007756122,0.0004567735,0.86752164],"study_design_scores_gemma":[0.0015946053,0.00047772517,0.116377234,0.0015130399,0.000066025714,0.00059953466,0.0000013792527,0.86885846,0.00011594992,0.008717683,0.0013378141,0.00034058056],"about_ca_topic_score_codex":0.000025541847,"about_ca_topic_score_gemma":0.000011322007,"teacher_disagreement_score":0.86718106,"about_ca_system_score_codex":0.00015789465,"about_ca_system_score_gemma":0.00021351149,"threshold_uncertainty_score":0.6302434},"labels":[],"label_agreement":null},{"id":"W4327769465","doi":"10.1007/978-3-031-27420-6_7","title":"Fusion-Based Automated Segmentation in Head and Neck Cancer via Advance Deep Learning Techniques","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Segmentation; Computer science; Artificial intelligence; Deep learning; Image segmentation; Pattern recognition (psychology); Dice; Artificial neural network; Computer vision","score_opus":0.0096705353155577,"score_gpt":0.30704406289582503,"score_spread":0.2973735275802673,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4327769465","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008552449,0.0007309643,0.9862674,0.002442743,0.0005205157,0.0005492871,0.0000014771632,0.0006121436,0.0003230407],"genre_scores_gemma":[0.3161074,0.001105363,0.67499286,0.0060107135,0.0008204556,0.00007725386,0.00007279574,0.00016998094,0.0006431731],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99809176,0.000028897104,0.00033968396,0.00069395005,0.0004938291,0.00035189933],"domain_scores_gemma":[0.9991132,0.00029198587,0.00015927269,0.00022344809,0.00008801194,0.00012408286],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005529054,0.0002754457,0.00041796223,0.0006826764,0.00012687643,0.00006861202,0.00020389128,0.00018811168,0.0000218474],"category_scores_gemma":[0.00021671037,0.00024551916,0.000042989534,0.00041144557,0.00038024623,0.00009585481,0.00014472542,0.0011437823,0.00000443334],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025774627,0.00001606742,0.0077594197,0.00015857948,0.0000059367094,0.00015723358,0.00032490047,0.042991135,0.003791117,0.000027006548,0.0000062303006,0.9447366],"study_design_scores_gemma":[0.00058038573,0.00017993516,0.004617302,0.0023896438,0.000013858996,0.000028185179,4.3568858e-7,0.98785746,0.0016982259,0.0018195806,0.00054962886,0.0002653706],"about_ca_topic_score_codex":0.0001994934,"about_ca_topic_score_gemma":0.00018734358,"teacher_disagreement_score":0.9448663,"about_ca_system_score_codex":0.00028483197,"about_ca_system_score_gemma":0.00021100097,"threshold_uncertainty_score":0.9999997},"labels":[],"label_agreement":null},{"id":"W4327770221","doi":"10.1007/978-3-031-27420-6_1","title":"Overview of the HECKTOR Challenge at MICCAI 2022: Automatic Head and Neck Tumor Segmentation and Outcome Prediction in PET/CT","year":2023,"lang":"en","type":"article","venue":"Lecture notes in computer science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":61,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"National Institute of Dental and Craniofacial Research; National Cancer Institute; Siemens Healthineers; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Computer science; Segmentation; Sørensen–Dice coefficient; Head and neck; Artificial intelligence; Head and neck cancer; Concordance; Medicine; Nuclear medicine; Image segmentation; Radiology; Radiation therapy; Surgery; Internal medicine","score_opus":0.02474895169134162,"score_gpt":0.32345832665877344,"score_spread":0.29870937496743183,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4327770221","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9858536,0.0005205072,0.008682303,0.004331812,0.00032600795,0.00024886426,0.0000013845244,0.000029653322,0.00000583278],"genre_scores_gemma":[0.9915686,0.000103615545,0.0074791764,0.000786628,0.000043467957,0.0000061001206,0.0000017168777,0.0000060768702,0.0000045890542],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989811,0.000048398142,0.00023353825,0.00026446566,0.00029400378,0.0001784857],"domain_scores_gemma":[0.9995281,0.00016320418,0.000065667286,0.00016799197,0.000018641897,0.000056372162],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00065023825,0.00008700967,0.00018858036,0.00017479877,0.000080226826,0.000022827087,0.00011539966,0.000008368008,0.0000072925045],"category_scores_gemma":[0.0002747719,0.000058888763,0.000021685086,0.00071088836,0.0002377641,0.000082808794,0.00019617447,0.00021782897,0.0000013578192],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008678758,0.000043296786,0.8237127,0.0004700528,0.000005043343,0.000095924086,0.0015226939,0.002272238,0.0041796877,0.000018876612,0.000018502215,0.16765228],"study_design_scores_gemma":[0.00045724146,0.00005795034,0.4472579,0.0002943044,0.0000047883736,0.00018294343,0.0000029834725,0.5511243,0.00031245383,0.0002570389,0.000012806841,0.000035338908],"about_ca_topic_score_codex":0.00006332104,"about_ca_topic_score_gemma":0.000049874758,"teacher_disagreement_score":0.548852,"about_ca_system_score_codex":0.00008272983,"about_ca_system_score_gemma":0.000045359797,"threshold_uncertainty_score":0.2401414},"labels":[],"label_agreement":null},{"id":"W4327770651","doi":"10.1007/978-3-031-27420-6_10","title":"A U-Net Convolutional Neural Network with Multiclass Dice Loss for Automated Segmentation of Tumors and Lymph Nodes from Head and Neck Cancer PET/CT Images","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Dice; Segmentation; Computer science; Test set; Artificial intelligence; Convolutional neural network; Pattern recognition (psychology); Encoder; Head and neck; Medicine; Mathematics","score_opus":0.01221877756972753,"score_gpt":0.2889093639235616,"score_spread":0.27669058635383403,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4327770651","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.54311186,0.0013530074,0.4514171,0.0024188492,0.0006206257,0.00075022207,0.00010274656,0.00018143353,0.000044202836],"genre_scores_gemma":[0.8284417,0.00012967057,0.16983151,0.00096358755,0.0003919678,0.000019361267,0.00007687212,0.00004257053,0.00010278871],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998531,0.000016539305,0.00026425594,0.0005444664,0.00036803377,0.0002757353],"domain_scores_gemma":[0.9988276,0.00060140045,0.00018209382,0.00015126672,0.00012083795,0.00011683881],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025808837,0.00023059404,0.00042640825,0.00014694325,0.00012033595,0.000063875625,0.00013534035,0.000028904551,0.00000554577],"category_scores_gemma":[0.00009490159,0.00017780378,0.000033684297,0.00014397527,0.0009702202,0.00008841762,0.000114088514,0.00027772205,3.4469173e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00063032977,0.00007749015,0.23944639,0.0011498278,0.00027602797,0.0011484702,0.0010140543,0.47231933,0.0026897937,0.0005397425,0.00020331501,0.28050524],"study_design_scores_gemma":[0.0015510828,0.00012797772,0.06363514,0.0014856444,0.00006170523,0.00026370556,9.1424454e-7,0.9310614,0.00011489954,0.0014934893,0.000023088543,0.00018099489],"about_ca_topic_score_codex":0.0004770328,"about_ca_topic_score_gemma":0.000058035508,"teacher_disagreement_score":0.45874202,"about_ca_system_score_codex":0.00008356844,"about_ca_system_score_gemma":0.00021986607,"threshold_uncertainty_score":0.7250628},"labels":[],"label_agreement":null},{"id":"W4327770666","doi":"10.1007/978-3-031-27420-6_23","title":"Deep Learning and Machine Learning Techniques for Automated PET/CT Segmentation and Survival Prediction in Head and Neck Cancer","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Artificial intelligence; Segmentation; Computer science; Deep learning; Random forest; Image segmentation; Machine learning; Pattern recognition (psychology)","score_opus":0.015039465974612993,"score_gpt":0.30848395687472047,"score_spread":0.2934444909001075,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4327770666","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09327521,0.002754927,0.8984742,0.002088834,0.0007725354,0.0014020524,0.0000101108,0.0008634749,0.000358622],"genre_scores_gemma":[0.7350256,0.0056120246,0.25580603,0.00084812817,0.0007606262,0.00010933197,0.00017793098,0.00018928004,0.0014710987],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99840677,0.000037813596,0.00029949215,0.0006579466,0.00030677073,0.00029123528],"domain_scores_gemma":[0.9992029,0.0003841565,0.00013824069,0.0000943608,0.0000658046,0.00011452894],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008861487,0.00025233233,0.00041363953,0.0005189672,0.0002006894,0.00011747312,0.00008205625,0.000058026326,0.0000059730824],"category_scores_gemma":[0.0003300121,0.00022720115,0.000027423317,0.00019092763,0.00034808353,0.00011780393,0.00015834572,0.0009940478,3.775385e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000059808506,0.000013499593,0.09128561,0.00044403627,0.00002452004,0.00017205946,0.00061594025,0.0104049295,0.0011846296,0.000102308404,0.00000464573,0.895688],"study_design_scores_gemma":[0.00084548874,0.0003299042,0.01033629,0.0012070953,0.000031473,0.00028713414,0.000002395539,0.98501676,0.000156394,0.0010439929,0.00054093724,0.0002021025],"about_ca_topic_score_codex":0.000248682,"about_ca_topic_score_gemma":0.00022080923,"teacher_disagreement_score":0.9746119,"about_ca_system_score_codex":0.00012733795,"about_ca_system_score_gemma":0.000081043705,"threshold_uncertainty_score":0.9264994},"labels":[],"label_agreement":null},{"id":"W4327771498","doi":"10.1007/978-3-031-27420-6_19","title":"Combining nnUNet and AutoML for Automatic Head and Neck Tumor Segmentation and Recurrence-Free Survival Prediction in PET/CT Images","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Segmentation; Concordance; Head and neck; Computer science; Sørensen–Dice coefficient; Primary tumor; Medicine; Artificial intelligence; Radiology; Image segmentation; Metastasis; Surgery; Internal medicine; Cancer","score_opus":0.017141594213212496,"score_gpt":0.2916601097041119,"score_spread":0.2745185154908994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4327771498","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4538906,0.001493164,0.53285986,0.0056107813,0.0027691205,0.0022902621,0.00006525633,0.00034281696,0.00067814684],"genre_scores_gemma":[0.68420684,0.00061127095,0.31208012,0.0015048854,0.0006366896,0.00006886098,0.0001187707,0.00012227216,0.00065027084],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982747,0.000027812182,0.00035547052,0.0006661911,0.0003811914,0.0002946474],"domain_scores_gemma":[0.99877703,0.0006645316,0.00014073591,0.00022912593,0.000055462933,0.00013310603],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010349775,0.00024865032,0.00044977257,0.00046621737,0.00013775408,0.00015559456,0.0001610197,0.00003405192,0.0000040025507],"category_scores_gemma":[0.00062404096,0.00022203063,0.00002808765,0.00017807765,0.00054105173,0.00015348564,0.00023883897,0.0005823801,7.2275316e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049984632,0.000039750023,0.03298215,0.0012391803,0.0000311461,0.00048812007,0.0013654109,0.0014058219,0.00036785923,0.0007378933,0.0001381995,0.96115446],"study_design_scores_gemma":[0.0020635175,0.0004173329,0.03913657,0.0024329142,0.000038966875,0.00068858196,0.0000041861717,0.9358759,0.000053585198,0.018963676,0.00008356473,0.00024120267],"about_ca_topic_score_codex":0.00007025377,"about_ca_topic_score_gemma":0.000053112013,"teacher_disagreement_score":0.9609133,"about_ca_system_score_codex":0.00008489635,"about_ca_system_score_gemma":0.0001346117,"threshold_uncertainty_score":0.9054147},"labels":[],"label_agreement":null},{"id":"W4327780894","doi":"10.1007/978-3-031-27420-6_22","title":"Head and Neck Tumor Segmentation with 3D UNet and Survival Prediction with Multiple Instance Neural Network","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Sunnybrook Health Science Centre","funders":"","keywords":"Segmentation; Softmax function; Head and neck squamous-cell carcinoma; Computer science; Lymph node; Positron emission tomography; Medicine; Artificial intelligence; Head and neck cancer; Radiology; Artificial neural network; Radiation therapy; Internal medicine","score_opus":0.011300363624939901,"score_gpt":0.25475463167472057,"score_spread":0.24345426804978065,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4327780894","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1385784,0.00039983305,0.8580869,0.0011720668,0.00070864946,0.000588136,0.0000070162437,0.00013605255,0.0003229585],"genre_scores_gemma":[0.6976422,0.00019781875,0.29708925,0.0029581855,0.001378483,0.000017277242,0.00006789767,0.000110177716,0.00053872366],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983087,0.000018439678,0.00020504599,0.00065108837,0.00050587306,0.00031086194],"domain_scores_gemma":[0.99920106,0.00023563043,0.0001243552,0.00021463844,0.000071818846,0.00015251883],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035608513,0.00025724331,0.0003511429,0.00017029379,0.00016854376,0.00011722154,0.00011265603,0.00007677512,0.0000027208564],"category_scores_gemma":[0.00005963741,0.0001821242,0.000015907626,0.00024845838,0.000670177,0.0001394678,0.000104015046,0.00069171505,8.283353e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041115118,0.00002682006,0.24868791,0.000292048,0.000055244032,0.00049807393,0.0009130008,0.2050523,0.00013961719,0.00027587588,0.00004703231,0.5436009],"study_design_scores_gemma":[0.00182766,0.00084487145,0.056480438,0.0015156806,0.000044976267,0.00040412077,0.0000013211032,0.9375107,0.000016772237,0.0006475373,0.00044714348,0.00025873256],"about_ca_topic_score_codex":0.00006590783,"about_ca_topic_score_gemma":0.00027170766,"teacher_disagreement_score":0.7324585,"about_ca_system_score_codex":0.00006715291,"about_ca_system_score_gemma":0.00012571401,"threshold_uncertainty_score":0.7426809},"labels":[],"label_agreement":null},{"id":"W4353015179","doi":"10.1038/s41592-023-02150-0","title":"Understanding metric-related pitfalls in image analysis validation","year":2024,"lang":"en","type":"review","venue":"Nature Methods","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":175,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Health Science Centre; Vector Institute; Princess Margaret Cancer Centre; Mila - Quebec Artificial Intelligence Institute; University of Toronto; University Health Network; McGill University","funders":"National Cancer Institute; Centre For Medical Engineering, King’s College London; Engineering and Physical Sciences Research Council; Natural Sciences and Engineering Research Council of Canada; Sydäntutkimussäätiö; National Institute of General Medical Sciences; Bundesministerium für Bildung und Forschung; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Cancer Research UK; Wellcome Trust; Innosuisse - Schweizerische Agentur für Innovationsförderung; Alzheimer's Society; NIH Clinical Center; Agence Nationale de la Recherche; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; Oulun Yliopisto; Silicon Valley Community Foundation; European Commission; National Institutes of Health; National Institute of Neurological Disorders and Stroke; Canadian Institute for Advanced Research; Royal Academy of Engineering; Novo Nordisk Fonden; Foundation for Cardiovascular Research; National Science Foundation","keywords":"Computer science; Data science; Multidisciplinary approach; Strengths and weaknesses; Bridging (networking); Metric (unit); Process (computing); Key (lock); Information retrieval; Artificial intelligence; Data mining; Psychology","score_opus":0.10400175250386598,"score_gpt":0.5138637104579991,"score_spread":0.40986195795413305,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4353015179","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[9.955234e-7,0.87257034,0.12003207,0.00036989062,0.00093427615,0.00049443945,0.000007912083,0.00012702774,0.005463077],"genre_scores_gemma":[0.000022078102,0.8435957,0.15451735,0.00011442972,0.00019177895,0.000021708001,0.00035977314,0.00009423847,0.0010829796],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9959958,0.0013452638,0.0009877256,0.00078190805,0.0005052117,0.000384045],"domain_scores_gemma":[0.99764395,0.0012549621,0.0003287626,0.0005243668,0.000056868495,0.00019110594],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.005831076,0.00049176376,0.0029781028,0.004719186,0.000051694846,0.00012240688,0.0002465522,0.0014500614,0.00019044225],"category_scores_gemma":[0.00399896,0.0003458612,0.0013839619,0.010156699,0.000074701646,0.000071342336,0.000107917935,0.0069853733,0.00004043831],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005329237,0.000050971314,0.000032123193,0.01224919,0.0040592514,0.00037656556,0.00009223287,0.000012610627,0.0000075540916,0.0023915393,0.0016017483,0.9791209],"study_design_scores_gemma":[0.00037470736,0.000035301364,0.00001928493,0.010137282,0.04467811,0.00013442592,0.000030693885,0.0056939404,0.0000038651224,0.0019544358,0.93649286,0.00044509812],"about_ca_topic_score_codex":0.000020300955,"about_ca_topic_score_gemma":0.0000015016554,"teacher_disagreement_score":0.9786758,"about_ca_system_score_codex":0.0010575776,"about_ca_system_score_gemma":0.00026554367,"threshold_uncertainty_score":0.9998993},"labels":[],"label_agreement":null},{"id":"W4353048885","doi":"10.1053/j.ro.2023.02.002","title":"Introduction to Radiomics and Artificial Intelligence: A Primer for Radiologists","year":2023,"lang":"en","type":"article","venue":"Seminars in Roentgenology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre","funders":"","keywords":"Radiomics; Medicine; Clearance; Applications of artificial intelligence; Radiology; Field (mathematics); Medical imaging; Artificial intelligence; Data science; Health informatics; Deep learning; Medical physics; Informatics; Pathology; Computer science; Public health","score_opus":0.02281702351473435,"score_gpt":0.33400486023377374,"score_spread":0.3111878367190394,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4353048885","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92769706,0.0004241744,0.015165899,0.055020116,0.00089690194,0.00061824033,0.0000033663964,0.00009833879,0.00007588114],"genre_scores_gemma":[0.95987016,0.0015368097,0.033048045,0.0018540381,0.0021474378,0.00019052906,0.00012285136,0.00005612918,0.0011740178],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988172,0.000041694988,0.00029044444,0.00038752533,0.00008419209,0.00037891197],"domain_scores_gemma":[0.9994773,0.00013693469,0.000044047672,0.00018938472,0.000035406858,0.000116925265],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006628663,0.00011299437,0.00029537024,0.00040867008,0.000056545337,0.000009945147,0.00008073508,0.00011780588,0.000027432925],"category_scores_gemma":[0.0014169067,0.00010681377,0.00004010913,0.00041541382,0.00016163616,0.000022989965,0.000064712,0.00026028443,0.000034127035],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009951417,0.00014355363,0.018252999,0.00016727952,0.00008839045,0.00016221603,0.0025729153,0.0020254692,0.05536146,0.010643703,0.045745667,0.8638412],"study_design_scores_gemma":[0.0038235534,0.0072071743,0.061594643,0.00061079237,0.00040056388,0.0034675654,0.0059724497,0.2840519,0.04232917,0.08107942,0.50795734,0.0015054427],"about_ca_topic_score_codex":0.00001737749,"about_ca_topic_score_gemma":0.000005500585,"teacher_disagreement_score":0.86233574,"about_ca_system_score_codex":0.00008160218,"about_ca_system_score_gemma":0.00003971947,"threshold_uncertainty_score":0.4355739},"labels":[],"label_agreement":null},{"id":"W4360981867","doi":"10.1109/isbi53787.2023.10230482","title":"Reproducibility of Tumor Segmentation Outcomes with a Deep Learning Model","year":2023,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"LabEx PRIMES; Agence Nationale de la Recherche","keywords":"Reproducibility; Segmentation; Pipeline (software); Computer science; Benchmark (surveying); Stability (learning theory); Dice; Deep learning; Artificial intelligence; Hausdorff distance; Range (aeronautics); Image segmentation; Pattern recognition (psychology); Machine learning; Statistics; Mathematics; Cartography; Engineering; Geography","score_opus":0.019935324962827204,"score_gpt":0.31981805489365206,"score_spread":0.2998827299308249,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4360981867","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9703681,0.000012692642,0.023955029,0.0023553357,0.00002771602,0.000178718,3.0315158e-7,0.0001885357,0.0029135835],"genre_scores_gemma":[0.97259355,0.000008355732,0.022541199,0.0003802484,0.000019828336,0.000009688586,0.000017350641,0.000016184771,0.00441361],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989624,0.00002963078,0.0001997587,0.00041689223,0.00025035694,0.00014098546],"domain_scores_gemma":[0.99929184,0.00006762692,0.000070660986,0.00043718203,0.00006206449,0.00007064641],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010890666,0.00007479128,0.00022530818,0.00008903203,0.00004225147,0.0000061960013,0.00004019096,0.000016473197,0.000055687746],"category_scores_gemma":[0.0012092188,0.000048556336,0.000046815094,0.00024308871,0.00006052411,0.000043878452,0.000028091375,0.00020633628,0.000014488707],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000093963325,0.000072728755,0.9204172,0.00015669494,0.00006725436,0.000028705143,0.00096389203,0.042385478,0.011945674,0.00024647728,0.00024436755,0.023377568],"study_design_scores_gemma":[0.0009940179,0.00014607277,0.17430378,0.000041030133,0.000054038665,0.000019551677,0.0005641334,0.821211,0.0023190095,0.0002165397,0.000059267415,0.000071556235],"about_ca_topic_score_codex":0.000071229355,"about_ca_topic_score_gemma":0.000004106063,"teacher_disagreement_score":0.7788255,"about_ca_system_score_codex":0.000021623488,"about_ca_system_score_gemma":0.000041074785,"threshold_uncertainty_score":0.19800699},"labels":[],"label_agreement":null},{"id":"W4361010773","doi":"10.1016/j.adro.2023.101227","title":"Do Dosiomic Features Extracted From Planned 3-Dimensional Dose Distribution Improve Biochemical Failure-Free Survival Prediction: an Analysis Based on a Large Multi-Institutional Data Set","year":2023,"lang":"en","type":"article","venue":"Advances in Radiation Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Lethbridge; University of Alberta; University of Calgary","funders":"Alberta Innovates; Alberta Heritage Foundation for Medical Research","keywords":"Medicine; Feature selection; Prostate cancer; Concordance; Radiation treatment planning; Log-rank test; Statistics; Random forest; Survival analysis; Radiation therapy; Internal medicine; Artificial intelligence; Cancer; Computer science; Mathematics","score_opus":0.01906622294379008,"score_gpt":0.36288891228827047,"score_spread":0.3438226893444804,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4361010773","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9384948,0.0008573541,0.034383252,0.008353164,0.0022874647,0.0007554282,0.01432991,0.00042061092,0.00011802462],"genre_scores_gemma":[0.8822909,0.00015528119,0.0043016556,0.0005990254,0.00054633885,0.000045255423,0.1120219,0.00001735112,0.00002226418],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975734,0.00026424584,0.0004765992,0.00079098705,0.00052059,0.00037423152],"domain_scores_gemma":[0.9979289,0.0007800506,0.00020238828,0.00077966345,0.00008076187,0.00022824178],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009347825,0.00022573204,0.00049944397,0.00042072,0.0001743995,0.000028868191,0.00035658237,0.00029106965,0.000120219505],"category_scores_gemma":[0.0018263893,0.00019537885,0.00009755,0.0010166074,0.00015938663,0.00038306246,0.00012696211,0.0006896696,0.000019312085],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.009369913,0.005222138,0.55189025,0.000160244,0.0012078749,0.0011915311,0.000611672,0.28716508,0.035898954,0.0022362478,0.028006151,0.077039935],"study_design_scores_gemma":[0.006308375,0.0002774835,0.31702343,0.00003566427,0.00021371909,0.000008351145,0.0000704176,0.65498424,0.0001014389,0.000101974416,0.020736884,0.00013803013],"about_ca_topic_score_codex":0.00012488132,"about_ca_topic_score_gemma":0.0003174152,"teacher_disagreement_score":0.36781916,"about_ca_system_score_codex":0.0004521255,"about_ca_system_score_gemma":0.00033952377,"threshold_uncertainty_score":0.7967318},"labels":[],"label_agreement":null},{"id":"W4361267463","doi":"10.3390/cancers15072056","title":"Combination of FDG PET/CT Radiomics and Clinical Parameters for Outcome Prediction in Patients with Hodgkin’s Lymphoma","year":2023,"lang":"en","type":"article","venue":"Cancers","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario; William Osler Health System; Princess Margaret Cancer Centre; Women's College Hospital; University of Toronto; University Health Network; Mount Sinai Hospital","funders":"","keywords":"Medicine; Logistic regression; Radiomics; Confidence interval; Nuclear medicine; Univariate analysis; Hazard ratio; Univariate; Proportional hazards model; Internal medicine; Radiology; Multivariate analysis; Multivariate statistics; Mathematics; Statistics","score_opus":0.021628350972083623,"score_gpt":0.3281461251854436,"score_spread":0.30651777421336,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4361267463","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99834156,0.000018073593,0.00039053414,0.0003555315,0.00035417313,0.0004263879,0.000015159773,0.00003313263,0.00006545405],"genre_scores_gemma":[0.99817044,0.000058211484,0.00132394,0.00021793197,0.000027117221,0.000023024346,0.00008233729,0.000017612649,0.00007936999],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9991808,0.000027574728,0.00031379852,0.00018098389,0.0001533869,0.0001434331],"domain_scores_gemma":[0.99948406,0.00017377987,0.0001036786,0.000105610736,0.000049900413,0.00008296407],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042629725,0.00007540084,0.00025990003,0.00013407832,0.00002586183,0.000006362672,0.00003831076,0.000014366,0.0000026257774],"category_scores_gemma":[0.00040105957,0.00006263663,0.000044896442,0.0001841445,0.00012562155,0.000045657325,0.000012232584,0.00010339003,8.0107486e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031433592,0.00003358519,0.9718599,0.000090787915,0.000042809672,0.000010861868,0.00005098231,0.00044643003,0.0000047821372,0.000043988104,0.00056992506,0.026531652],"study_design_scores_gemma":[0.009283364,0.00063914276,0.89791316,0.00010945292,0.00006724179,0.000008171851,0.00006713728,0.09128196,0.000011616736,0.00005926264,0.0004987782,0.000060726834],"about_ca_topic_score_codex":0.00010724591,"about_ca_topic_score_gemma":0.0000066621683,"teacher_disagreement_score":0.09083553,"about_ca_system_score_codex":0.00031114093,"about_ca_system_score_gemma":0.00012856055,"threshold_uncertainty_score":0.25542477},"labels":[],"label_agreement":null},{"id":"W4361807280","doi":"10.5281/zenodo.7788447","title":"ATR phosphoproteomics - DHX9 validation","year":2023,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Phosphoproteomics; Computational biology; Computer science; Biology; Cell biology; Phosphorylation","score_opus":0.03071640401644935,"score_gpt":0.28334439559242836,"score_spread":0.252627991575979,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4361807280","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7195295,0.00011514498,0.018383158,0.020501912,0.0006054932,0.0014583216,0.000099167635,0.0059937774,0.23331353],"genre_scores_gemma":[0.98555803,0.00024395621,0.0014474407,0.0007130924,0.0004991012,8.506097e-8,0.0041211606,0.0018088258,0.005608276],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99869144,0.000115849194,0.00020333285,0.00030250303,0.0003710418,0.00031582676],"domain_scores_gemma":[0.9991178,0.000022497634,0.00006641671,0.00032756032,0.00025679774,0.00020896009],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00085928227,0.000103519014,0.00014456901,0.00023921097,0.001104732,0.00029816278,0.0003274734,0.000056902547,0.0070068445],"category_scores_gemma":[0.001331229,0.000103221704,0.000059314953,0.0007235643,0.00011168502,0.000115759256,0.0004284516,0.0003720506,0.011652091],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012555395,0.000122006015,0.00010135426,0.00015890702,0.00007950221,0.000097844146,0.001036598,0.00027923347,0.028766891,0.0025220716,0.61168844,0.3550216],"study_design_scores_gemma":[0.00080112024,0.00016418239,0.00279392,0.000050504234,0.000025561614,0.00019900712,0.00015153858,0.008438009,0.0017144318,0.00021663935,0.98532146,0.00012362227],"about_ca_topic_score_codex":0.000013175652,"about_ca_topic_score_gemma":1.8122932e-8,"teacher_disagreement_score":0.37363303,"about_ca_system_score_codex":0.00010412196,"about_ca_system_score_gemma":0.0000050745,"threshold_uncertainty_score":0.9939009},"labels":[],"label_agreement":null},{"id":"W4361855185","doi":"10.1109/icpeca56706.2023.10075772","title":"Comparison of CNN Models in Non-small Lung Cancer Diagnosis","year":2023,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Convolutional neural network; Computer science; Artificial intelligence; Residual neural network; Deep learning; Pattern recognition (psychology); Field (mathematics); Contextual image classification; Task (project management); Artificial neural network; Machine learning; Image (mathematics); Mathematics","score_opus":0.03871486614095278,"score_gpt":0.38313718102195593,"score_spread":0.34442231488100317,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4361855185","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9835195,0.000393094,0.0030547618,0.0047286577,0.00014627296,0.00019474,0.0000018182424,0.000062062136,0.007899077],"genre_scores_gemma":[0.9965553,0.00045975906,0.0012421564,0.0004402374,0.000064813554,0.000093110255,0.000010223719,0.000016064616,0.0011183296],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991857,0.000016522454,0.0002598,0.00015015135,0.0001863197,0.00020153409],"domain_scores_gemma":[0.99957365,0.000118721495,0.00004690773,0.00013334538,0.00003558713,0.00009176339],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027265755,0.000075085016,0.0003161028,0.00020156876,0.000017656088,0.0000059224626,0.00007726994,0.00004792601,0.00022684084],"category_scores_gemma":[0.00010764019,0.000060616352,0.00005039885,0.00042536348,0.000035831952,0.00003232839,0.000046049558,0.0002511517,0.000009752399],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014091876,0.000088834706,0.9457391,0.00017212737,0.000026929793,0.00001796852,0.0008650222,0.01419909,0.0005898651,0.00025764984,0.019429803,0.01859955],"study_design_scores_gemma":[0.0007439382,0.000029414048,0.13186327,0.00026049226,0.00003075619,8.413593e-7,0.00015748925,0.8651716,0.0009571543,0.0001054497,0.00061889505,0.000060679235],"about_ca_topic_score_codex":0.0017874488,"about_ca_topic_score_gemma":0.000096177115,"teacher_disagreement_score":0.85097253,"about_ca_system_score_codex":0.00004060959,"about_ca_system_score_gemma":0.000047842794,"threshold_uncertainty_score":0.27021},"labels":[],"label_agreement":null},{"id":"W4361871076","doi":"10.1158/0008-5472.22384635","title":"Supplementary Figures 1-2, Methods from Novel Matrix Metalloproteinase Inhibitor [&lt;sup&gt;18&lt;/sup&gt;F]Marimastat-Aryltrifluoroborate as a Probe for &lt;i&gt;In vivo&lt;/i&gt; Positron Emission Tomography Imaging in Cancer","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency; TRIUMF; University of British Columbia","funders":"","keywords":"Matrix metalloproteinase; In vivo; Chemistry; Matrix metalloproteinase inhibitor; Molecular biology; Pharmacology; Biology; Biochemistry; Genetics","score_opus":0.02217782514863558,"score_gpt":0.3564033686740014,"score_spread":0.3342255435253658,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4361871076","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38322133,0.03924567,0.45103082,0.06697834,0.007311971,0.03336106,0.012733593,0.0023578703,0.0037593734],"genre_scores_gemma":[0.065275215,0.0038947377,0.8929779,0.0038239115,0.0031725608,0.00682528,0.011481416,0.0012046021,0.011344391],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9884744,0.00087127613,0.0030661873,0.0034616368,0.0018055667,0.0023208836],"domain_scores_gemma":[0.9942056,0.0012899806,0.001106815,0.0017382858,0.00050510996,0.0011542202],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.0050230664,0.001972289,0.0031800165,0.002805516,0.00035958455,0.00042580615,0.0012422468,0.0009323358,0.0034125668],"category_scores_gemma":[0.001595781,0.0017885524,0.001288437,0.0016762932,0.00039220462,0.0004071649,0.0017849574,0.0033763372,0.000018171357],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0020880697,0.0012833845,0.005980595,0.0027821583,0.0010431785,0.00072930433,0.0015377254,0.0046633305,0.90110135,0.00053637003,0.053162064,0.025092468],"study_design_scores_gemma":[0.032108806,0.0011488639,0.006181687,0.016804669,0.0038571618,0.00015912637,0.0006922681,0.4412783,0.1310513,0.011677561,0.34934714,0.005693103],"about_ca_topic_score_codex":0.013809822,"about_ca_topic_score_gemma":0.001675387,"teacher_disagreement_score":0.77005005,"about_ca_system_score_codex":0.0012526884,"about_ca_system_score_gemma":0.0016179023,"threshold_uncertainty_score":0.999302},"labels":[],"label_agreement":null},{"id":"W4361879578","doi":"10.1158/1055-9965.22437189","title":"Supplementary Figure 1, Tables 1-2 from Differences in Natural History between Breast Cancers in &lt;i&gt;BRCA1&lt;/i&gt; and &lt;i&gt;BRCA2&lt;/i&gt; Mutation Carriers and Effects of MRI Screening-MRISC, MARIBS, and Canadian Studies Combined","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Natural history; Oncology; Stage (stratigraphy); Internal medicine; Medicine; Cancer research; Biology","score_opus":0.01424431569744997,"score_gpt":0.2582859498811009,"score_spread":0.2440416341836509,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4361879578","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9467429,0.042422555,0.00006310619,0.0063846344,0.0011057433,0.0016508958,0.0013079527,0.000079743215,0.00024250514],"genre_scores_gemma":[0.98632646,0.0066795447,0.0014741363,0.00043627035,0.00030472,0.00013737638,0.0035168913,0.00010913351,0.001015485],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99535364,0.00037845544,0.0011483618,0.0013888623,0.0007832203,0.0009474652],"domain_scores_gemma":[0.9965826,0.0014417368,0.00048956234,0.000497957,0.00017623675,0.00081185333],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010037761,0.0008852002,0.0021883491,0.001328587,0.0002063482,0.000079703306,0.0003438414,0.00052898965,0.00015247613],"category_scores_gemma":[0.00065006135,0.00081425154,0.00013779101,0.00035375156,0.0010818705,0.00017471731,0.00061768433,0.0015789407,9.1396896e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007545394,0.00012372737,0.8937364,0.005821664,0.0044251545,0.0012768751,0.015806291,0.00033434184,0.008640746,0.000698849,0.0456309,0.022750506],"study_design_scores_gemma":[0.0075966152,0.00040340316,0.96041995,0.004646609,0.0009970138,0.000036494588,0.0013233799,0.014526657,0.0000903884,0.0007806117,0.008117814,0.0010610712],"about_ca_topic_score_codex":0.22752719,"about_ca_topic_score_gemma":0.53385717,"teacher_disagreement_score":0.30632997,"about_ca_system_score_codex":0.0018365497,"about_ca_system_score_gemma":0.0010206325,"threshold_uncertainty_score":0.99943084},"labels":[],"label_agreement":null},{"id":"W4361889402","doi":"10.1158/1078-0432.22478832","title":"Supplementary Data from Determining the Optimal Adjuvant Therapy for Improving Survival in Elderly Patients with Glioblastoma: A Systematic Review and Network Meta-analysis","year":2023,"lang":"en","type":"review","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Randomized controlled trial; Meta-analysis; Medicine; Consistency (knowledge bases); Table (database); Internal medicine; Computer science; Data mining; Artificial intelligence","score_opus":0.09439674381392273,"score_gpt":0.3742277136457929,"score_spread":0.27983096983187017,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4361889402","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000040277057,0.9898272,0.0013166253,0.00029670476,0.000071655166,0.007377024,0.0010307723,0.000035241887,0.0000044962185],"genre_scores_gemma":[0.000026918015,0.9860216,0.004423198,0.0007987104,0.00013424951,0.00096523354,0.0074158665,0.00012251206,0.00009173829],"study_design_codex":"systematic_review","study_design_gemma":"meta_analysis","domain_scores_codex":[0.9958232,0.00062002183,0.0015855794,0.0009408689,0.00054916285,0.00048117418],"domain_scores_gemma":[0.99507964,0.0023281751,0.00088172,0.0014685933,0.00009374413,0.00014814337],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0031871556,0.0006050281,0.008582823,0.00021734428,0.00013318102,0.0001071828,0.0007148998,0.00011042864,0.0001914058],"category_scores_gemma":[0.00060358335,0.00026700573,0.00092981337,0.0008759727,0.00006979466,0.00008888323,0.00035536266,0.00064598024,0.0000024908156],"study_design_candidate":"meta_analysis","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000054860455,0.00012738295,0.00072976,0.7259744,0.1812364,0.000032917895,0.000058122885,0.000015388197,6.511687e-9,0.0000044919707,0.0012921535,0.09047411],"study_design_scores_gemma":[0.0015524732,0.000467607,0.00006792659,0.06386026,0.9095585,0.00000604029,0.000039770537,0.005591086,5.2327405e-9,0.0000026933023,0.018425839,0.00042784234],"about_ca_topic_score_codex":0.0004566793,"about_ca_topic_score_gemma":0.00047154241,"teacher_disagreement_score":0.728322,"about_ca_system_score_codex":0.000055781813,"about_ca_system_score_gemma":0.0001526485,"threshold_uncertainty_score":0.9999782},"labels":[],"label_agreement":null},{"id":"W4361938418","doi":"10.1158/1078-0432.22478832.v1","title":"Supplementary Data from Determining the Optimal Adjuvant Therapy for Improving Survival in Elderly Patients with Glioblastoma: A Systematic Review and Network Meta-analysis","year":2023,"lang":"en","type":"review","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Randomized controlled trial; Meta-analysis; Medicine; Consistency (knowledge bases); Table (database); Statistics; Internal medicine; Computer science; Data mining; Mathematics","score_opus":0.09439674381392273,"score_gpt":0.3742277136457929,"score_spread":0.27983096983187017,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4361938418","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000040277057,0.9898272,0.0013166253,0.00029670476,0.000071655166,0.007377024,0.0010307723,0.000035241887,0.0000044962185],"genre_scores_gemma":[0.000026918015,0.9860216,0.004423198,0.0007987104,0.00013424951,0.00096523354,0.0074158665,0.00012251206,0.00009173829],"study_design_codex":"systematic_review","study_design_gemma":"meta_analysis","domain_scores_codex":[0.9958232,0.00062002183,0.0015855794,0.0009408689,0.00054916285,0.00048117418],"domain_scores_gemma":[0.99507964,0.0023281751,0.00088172,0.0014685933,0.00009374413,0.00014814337],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0031871556,0.0006050281,0.008582823,0.00021734428,0.00013318102,0.0001071828,0.0007148998,0.00011042864,0.0001914058],"category_scores_gemma":[0.00060358335,0.00026700573,0.00092981337,0.0008759727,0.00006979466,0.00008888323,0.00035536266,0.00064598024,0.0000024908156],"study_design_candidate":"meta_analysis","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000054860455,0.00012738295,0.00072976,0.7259744,0.1812364,0.000032917895,0.000058122885,0.000015388197,6.511687e-9,0.0000044919707,0.0012921535,0.09047411],"study_design_scores_gemma":[0.0015524732,0.000467607,0.00006792659,0.06386026,0.9095585,0.00000604029,0.000039770537,0.005591086,5.2327405e-9,0.0000026933023,0.018425839,0.00042784234],"about_ca_topic_score_codex":0.0004566793,"about_ca_topic_score_gemma":0.00047154241,"teacher_disagreement_score":0.728322,"about_ca_system_score_codex":0.000055781813,"about_ca_system_score_gemma":0.0001526485,"threshold_uncertainty_score":0.9999782},"labels":[],"label_agreement":null},{"id":"W4361943830","doi":"10.1158/1078-0432.c.6518304","title":"Data from A Pilot Study of Volume Measurement as a Method of Tumor Response Evaluation to Aid Biomarker Development","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Pyrogenesis (Canada)","funders":"National Cancer Institute; Memorial Sloan-Kettering Cancer Center","keywords":"Biomarker; Gefitinib; Receiver operating characteristic; Lung cancer; Medicine; Epidermal growth factor receptor; Nuclear medicine; Cancer; Pathology; Chemistry; Internal medicine","score_opus":0.3107020680321585,"score_gpt":0.45577032411890595,"score_spread":0.14506825608674745,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4361943830","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89721894,0.00012932894,0.09551619,0.0027436358,0.00057153055,0.0033676531,0.000070824295,0.000088886954,0.00029298064],"genre_scores_gemma":[0.8068974,0.0000049466603,0.19137682,0.00032333325,0.00007267373,0.00022193395,0.00037856607,0.00006723588,0.00065710844],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9929644,0.0014170179,0.0012592229,0.001044351,0.003037759,0.00027728005],"domain_scores_gemma":[0.9960918,0.00041298685,0.00047222627,0.0019266021,0.00085030054,0.00024607524],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.024493141,0.00030130154,0.0009377673,0.00051922846,0.000047003276,0.000023110866,0.00070387946,0.0000671797,0.0005705386],"category_scores_gemma":[0.013757094,0.00025256767,0.000059120513,0.00031667686,0.00003690839,0.00003853004,0.0024324842,0.00053244235,0.00007173247],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.057340242,0.018126642,0.056303564,0.0024168661,0.013631543,0.00040067875,0.019672185,0.0045575006,0.3284332,0.000016590673,0.07200773,0.42709327],"study_design_scores_gemma":[0.008761154,0.0038933377,0.76627827,0.002912088,0.0023207362,0.000015971644,0.0025990913,0.20283641,0.0025731525,0.00029209311,0.006924785,0.0005929245],"about_ca_topic_score_codex":0.006206876,"about_ca_topic_score_gemma":0.00036207604,"teacher_disagreement_score":0.7099747,"about_ca_system_score_codex":0.0003667396,"about_ca_system_score_gemma":0.0021657373,"threshold_uncertainty_score":0.99999267},"labels":[],"label_agreement":null},{"id":"W4361975492","doi":"10.2196/44779","title":"A Scalable Radiomics- and Natural Language Processing–Based Machine Learning Pipeline to Distinguish Between Painful and Painless Thoracic Spinal Bone Metastases: Retrospective Algorithm Development and Validation Study","year":2023,"lang":"en","type":"article","venue":"JMIR AI","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre","funders":"Fonds de Recherche du Québec - Santé; McGill University Health Centre; Faculty of Medicine and Health, University of Sydney; McGill University","keywords":"Medicine; Artificial intelligence; Receiver operating characteristic; Radiomics; Radiology; Machine learning; Retrospective cohort study; Random forest; Computer science; Surgery; Internal medicine","score_opus":0.013661754956650488,"score_gpt":0.34180601000543387,"score_spread":0.32814425504878336,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4361975492","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.985312,0.00096753106,0.010486892,0.0020835898,0.00004644867,0.0008631658,0.000012919813,0.00020732344,0.000020153617],"genre_scores_gemma":[0.9859706,0.000009029492,0.012621287,0.00044625835,0.00021305625,0.00007241156,0.00021503553,0.000045190263,0.0004071347],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99823433,0.00016384876,0.0003472141,0.0005294658,0.00038181638,0.00034331376],"domain_scores_gemma":[0.9992505,0.00010681273,0.00012101689,0.00013105545,0.000110629975,0.00028001223],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017350446,0.00024547626,0.00050156034,0.0003063211,0.00033137764,0.00016546219,0.00005861289,0.000055720153,0.0000059928534],"category_scores_gemma":[0.0008883398,0.00020827795,0.00002736892,0.00052878616,0.00009161427,0.00009861036,0.00013205361,0.0006321973,0.0000031253971],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001420112,0.00011199771,0.34940708,0.00034584696,0.00006795186,0.00025224726,0.0046857423,0.000017651631,0.0005124779,0.0000024155427,0.0001765459,0.64427805],"study_design_scores_gemma":[0.0041277297,0.00095876795,0.6742295,0.00068955007,0.00029979614,0.0001093947,0.0029594065,0.31123105,0.0007216524,0.000025588966,0.004081382,0.0005661766],"about_ca_topic_score_codex":0.00010347858,"about_ca_topic_score_gemma":0.000010668405,"teacher_disagreement_score":0.64371186,"about_ca_system_score_codex":0.00008657665,"about_ca_system_score_gemma":0.00007982967,"threshold_uncertainty_score":0.8493328},"labels":[],"label_agreement":null},{"id":"W4362425403","doi":"10.1158/1055-9965.22437189.v1","title":"Supplementary Figure 1, Tables 1-2 from Differences in Natural History between Breast Cancers in &lt;i&gt;BRCA1&lt;/i&gt; and &lt;i&gt;BRCA2&lt;/i&gt; Mutation Carriers and Effects of MRI Screening-MRISC, MARIBS, and Canadian Studies Combined","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Natural history; Oncology; Stage (stratigraphy); Internal medicine; Medicine; Cancer research; Biology","score_opus":0.01424431569744997,"score_gpt":0.2582859498811009,"score_spread":0.2440416341836509,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362425403","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9467429,0.042422555,0.00006310619,0.0063846344,0.0011057433,0.0016508958,0.0013079527,0.000079743215,0.00024250514],"genre_scores_gemma":[0.98632646,0.0066795447,0.0014741363,0.00043627035,0.00030472,0.00013737638,0.0035168913,0.00010913351,0.001015485],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99535364,0.00037845544,0.0011483618,0.0013888623,0.0007832203,0.0009474652],"domain_scores_gemma":[0.9965826,0.0014417368,0.00048956234,0.000497957,0.00017623675,0.00081185333],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010037761,0.0008852002,0.0021883491,0.001328587,0.0002063482,0.000079703306,0.0003438414,0.00052898965,0.00015247613],"category_scores_gemma":[0.00065006135,0.00081425154,0.00013779101,0.00035375156,0.0010818705,0.00017471731,0.00061768433,0.0015789407,9.1396896e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007545394,0.00012372737,0.8937364,0.005821664,0.0044251545,0.0012768751,0.015806291,0.00033434184,0.008640746,0.000698849,0.0456309,0.022750506],"study_design_scores_gemma":[0.0075966152,0.00040340316,0.96041995,0.004646609,0.0009970138,0.000036494588,0.0013233799,0.014526657,0.0000903884,0.0007806117,0.008117814,0.0010610712],"about_ca_topic_score_codex":0.22752719,"about_ca_topic_score_gemma":0.53385717,"teacher_disagreement_score":0.30632997,"about_ca_system_score_codex":0.0018365497,"about_ca_system_score_gemma":0.0010206325,"threshold_uncertainty_score":0.99943084},"labels":[],"label_agreement":null},{"id":"W4362458848","doi":"10.59275/j.melba.2022-354b","title":"QU-BraTS: MICCAI BraTS 2020 Challenge on Quantifying Uncertainty in Brain Tumor Segmentation – Analysis of Ranking Scores and Benchmarking Results","year":2022,"lang":"en","type":"article","venue":"The Journal of Machine Learning for Biomedical Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":53,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute; McGill University","funders":"National Institutes of Health; National Cancer Institute; Instituto Tecnológico de Costa Rica; Natural Sciences and Engineering Research Council of Canada; National Institute of Neurological Disorders and Stroke; Canadian Institute for Advanced Research","keywords":"Benchmarking; Segmentation; Computer science; Benchmark (surveying); Artificial intelligence; Machine learning; Task (project management); Ranking (information retrieval); Reliability (semiconductor); Data mining","score_opus":0.01864686215268765,"score_gpt":0.32309564876986147,"score_spread":0.30444878661717384,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362458848","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9580169,0.0023657694,0.006875873,0.031894714,0.00035027898,0.00037285083,0.000024329738,0.000025281379,0.000074008385],"genre_scores_gemma":[0.99618423,0.00027308642,0.0017556528,0.00133473,0.00024947576,0.000008127273,0.00013071905,0.000037588925,0.000026396245],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99621254,0.00081842847,0.0012530406,0.00030842703,0.0010065136,0.00040106356],"domain_scores_gemma":[0.99577296,0.002545381,0.0011724345,0.00019626749,0.00011872284,0.00019424432],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008495643,0.00024063404,0.0008211284,0.0012244545,0.00044098857,0.000042625405,0.00030181892,0.00003847337,0.00006551982],"category_scores_gemma":[0.003202766,0.00017448104,0.00028112595,0.0012487671,0.00028351755,0.00012174218,0.00017785268,0.0018355193,2.1845372e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.013175489,0.0014800989,0.16897699,0.0008844918,0.003101543,0.00086255866,0.022291502,0.34172866,0.060879316,0.00035924008,0.0029632885,0.38329685],"study_design_scores_gemma":[0.006483148,0.0016076561,0.017544419,0.0006471961,0.0011021966,0.00044012192,0.002340989,0.9661822,0.00010696178,0.00014424234,0.0031842592,0.00021661306],"about_ca_topic_score_codex":0.00040065593,"about_ca_topic_score_gemma":0.000025198411,"teacher_disagreement_score":0.62445354,"about_ca_system_score_codex":0.00018702346,"about_ca_system_score_gemma":0.00013159527,"threshold_uncertainty_score":0.79745203},"labels":[],"label_agreement":null},{"id":"W4362462021","doi":"10.1158/0008-5472.22384635.v1","title":"Supplementary Figures 1-2, Methods from Novel Matrix Metalloproteinase Inhibitor [&lt;sup&gt;18&lt;/sup&gt;F]Marimastat-Aryltrifluoroborate as a Probe for &lt;i&gt;In vivo&lt;/i&gt; Positron Emission Tomography Imaging in Cancer","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency; TRIUMF; University of British Columbia","funders":"","keywords":"Matrix metalloproteinase; In vivo; Positron emission tomography; Matrix metalloproteinase inhibitor; Chemistry; Nuclear medicine; Medicine; Biology; Biochemistry; Genetics","score_opus":0.02217782514863558,"score_gpt":0.3564033686740014,"score_spread":0.3342255435253658,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362462021","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38322133,0.03924567,0.45103082,0.06697834,0.007311971,0.03336106,0.012733593,0.0023578703,0.0037593734],"genre_scores_gemma":[0.065275215,0.0038947377,0.8929779,0.0038239115,0.0031725608,0.00682528,0.011481416,0.0012046021,0.011344391],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9884744,0.00087127613,0.0030661873,0.0034616368,0.0018055667,0.0023208836],"domain_scores_gemma":[0.9942056,0.0012899806,0.001106815,0.0017382858,0.00050510996,0.0011542202],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.0050230664,0.001972289,0.0031800165,0.002805516,0.00035958455,0.00042580615,0.0012422468,0.0009323358,0.0034125668],"category_scores_gemma":[0.001595781,0.0017885524,0.001288437,0.0016762932,0.00039220462,0.0004071649,0.0017849574,0.0033763372,0.000018171357],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0020880697,0.0012833845,0.005980595,0.0027821583,0.0010431785,0.00072930433,0.0015377254,0.0046633305,0.90110135,0.00053637003,0.053162064,0.025092468],"study_design_scores_gemma":[0.032108806,0.0011488639,0.006181687,0.016804669,0.0038571618,0.00015912637,0.0006922681,0.4412783,0.1310513,0.011677561,0.34934714,0.005693103],"about_ca_topic_score_codex":0.013809822,"about_ca_topic_score_gemma":0.001675387,"teacher_disagreement_score":0.77005005,"about_ca_system_score_codex":0.0012526884,"about_ca_system_score_gemma":0.0016179023,"threshold_uncertainty_score":0.999302},"labels":[],"label_agreement":null},{"id":"W4362489579","doi":"10.1117/12.2652661","title":"Observer study-based evaluation of TGAN architecture used to generate oncological PET images","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Wilcoxon signed-rank test; Computer science; Artificial intelligence; Observer (physics); Pattern recognition (psychology); Computer vision; Mathematics; Statistics","score_opus":0.1263281906966972,"score_gpt":0.43350874135922324,"score_spread":0.30718055066252603,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362489579","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97464746,0.000042712898,0.009612267,0.011594368,0.00062572415,0.0024578075,0.000018793538,0.00021473615,0.00078611076],"genre_scores_gemma":[0.9750429,0.0000045945,0.021848178,0.0011183402,0.00038661173,0.00021616106,0.00021762666,0.000062523104,0.0011030622],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.9963566,0.00059360586,0.00058135623,0.0007169971,0.0014547141,0.0002967478],"domain_scores_gemma":[0.9980842,0.00025796352,0.00020419779,0.0007032369,0.00047452212,0.00027591502],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036983653,0.00032870128,0.0008541804,0.0003211199,0.000053727566,0.000044597567,0.0002886197,0.0001607545,0.00053355296],"category_scores_gemma":[0.0024561351,0.00023311125,0.00023960398,0.0002675079,0.000079077094,0.000012231529,0.00041381406,0.0012669058,0.000042980988],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006330446,0.0027167147,0.14759003,0.0011064194,0.0010772415,0.0009004061,0.0022806113,0.74214166,0.024371192,0.00005118311,0.019011445,0.058120046],"study_design_scores_gemma":[0.008540358,0.002039427,0.58344835,0.00086444645,0.0023207085,0.000036956466,0.0004853061,0.39619195,0.003165647,0.0012098094,0.00095648126,0.00074053474],"about_ca_topic_score_codex":0.00034234265,"about_ca_topic_score_gemma":0.00007715521,"teacher_disagreement_score":0.43585834,"about_ca_system_score_codex":0.0001880775,"about_ca_system_score_gemma":0.0007272875,"threshold_uncertainty_score":0.9506001},"labels":[],"label_agreement":null},{"id":"W4362530952","doi":"10.1158/1541-7786.22527308","title":"Table S1 from Mitochondrial Aconitase ACO2 Links Iron Homeostasis with Tumorigenicity in Non–Small Cell Lung Cancer","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre; University of Toronto; University Health Network; University of Ottawa; Princess Margaret Cancer Centre; Hospital for Sick Children","funders":"Natural Sciences and Engineering Research Council of Canada; Scheme for Promotion of Academic and Research Collaboration; Canada Research Chairs; Genome Canada; Canadian Institutes of Health Research; Genome British Columbia","keywords":"Aconitase; Iron homeostasis; Homeostasis; Lung cancer; Cancer research; Cell; Cancer; Lung; Table (database); Mitochondrion; Internal medicine; Biology; Medicine; Pathology; Chemistry; Metabolism; Cell biology; Biochemistry","score_opus":0.01395078512850692,"score_gpt":0.28781494941727637,"score_spread":0.2738641642887695,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362530952","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9810071,0.001358982,0.006494552,0.003987244,0.0027844543,0.0017056421,0.0003262954,0.0002509082,0.0020848506],"genre_scores_gemma":[0.9001947,0.00403845,0.054073874,0.0038810365,0.0066807983,0.0011127884,0.0034551278,0.0005905729,0.025972635],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965675,0.00010292466,0.0006907495,0.0012574388,0.0006038833,0.00077754],"domain_scores_gemma":[0.9979311,0.00025955145,0.00030433096,0.00089263084,0.00013342651,0.00047893877],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00031419148,0.0006092288,0.0012008226,0.00035244387,0.000097012744,0.00013012797,0.00045220242,0.00079587,0.0015589573],"category_scores_gemma":[0.00020112246,0.00048346317,0.00020096736,0.0003743659,0.00012330533,0.000061384395,0.000643944,0.005359487,0.00013077042],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0036042354,0.0018962589,0.703124,0.0077027665,0.0018243385,0.0071238596,0.0062477994,0.06165164,0.037773393,0.000034833192,0.14831005,0.02070686],"study_design_scores_gemma":[0.04228313,0.001002244,0.15466438,0.016732432,0.0065547745,0.00007115525,0.0021546737,0.7204848,0.028454678,0.0008560551,0.021044059,0.0056976187],"about_ca_topic_score_codex":0.059875507,"about_ca_topic_score_gemma":0.0035556268,"teacher_disagreement_score":0.65883315,"about_ca_system_score_codex":0.00039550822,"about_ca_system_score_gemma":0.0010796036,"threshold_uncertainty_score":0.9997617},"labels":[],"label_agreement":null},{"id":"W4362541076","doi":"10.1158/1538-7445.am2023-5705","title":"Abstract 5705: Digital pathology based prognostic &amp; predictive biomarkers in metastatic non-small cell lung cancer","year":2023,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Roche (Canada)","funders":"","keywords":"Atezolizumab; Medicine; Tumor microenvironment; Oncology; Immunotherapy; Lung cancer; Carboplatin; Internal medicine; Paclitaxel; Docetaxel; Immune system; Cancer; Cancer research; Nivolumab; Chemotherapy; Immunology; Cisplatin","score_opus":0.0501117867464615,"score_gpt":0.40735712356758724,"score_spread":0.35724533682112575,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362541076","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99027133,0.001465166,0.00047774104,0.00383981,0.00027248092,0.0011751057,0.000089974186,0.00009884944,0.0023095522],"genre_scores_gemma":[0.9968033,0.00051124213,0.00028141605,0.00023174367,0.00018842466,0.00085913035,0.00013165244,0.00006685285,0.0009262638],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9973463,0.00014188199,0.00033722335,0.0005564893,0.00068836287,0.00092976243],"domain_scores_gemma":[0.99820334,0.00084546866,0.000065191794,0.000320052,0.00022190691,0.00034401973],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016114437,0.00018683575,0.00036823802,0.0007702678,0.00011513487,0.000077003926,0.0002404191,0.00009350802,0.0005381931],"category_scores_gemma":[0.001220786,0.00016035659,0.0000896179,0.0014140116,0.00033588498,0.0000946319,0.00011979966,0.0012553192,0.00009970717],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00087016134,0.00045837602,0.8721078,0.0027571379,0.0003458163,0.0032103432,0.00194042,0.004796716,0.03752745,0.0000098103155,0.034745682,0.041230306],"study_design_scores_gemma":[0.008748776,0.00047141014,0.78024966,0.0034658627,0.00020786059,0.00003870843,0.0009907179,0.19158322,0.0023214205,0.0002558394,0.011044973,0.0006215541],"about_ca_topic_score_codex":0.0010752835,"about_ca_topic_score_gemma":0.00018961399,"teacher_disagreement_score":0.1867865,"about_ca_system_score_codex":0.00042465894,"about_ca_system_score_gemma":0.0012425735,"threshold_uncertainty_score":0.6539152},"labels":[],"label_agreement":null},{"id":"W4362541147","doi":"10.1158/1538-7445.am2023-5618","title":"Abstract 5618: Multi-institutional validation of a radiomics-based artificial intelligence method for predicting response to PD-1/PD-L1 immune checkpoint inhibitor (ICI) therapy in stage IV NSCLC","year":2023,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Radiomics; Medicine; Response Evaluation Criteria in Solid Tumors; Oncology; Internal medicine; Stage (stratigraphy); Immunohistochemistry; Radiology; Clinical trial; Phases of clinical research","score_opus":0.15828938373078166,"score_gpt":0.48826919582315303,"score_spread":0.32997981209237137,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362541147","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90788573,0.00020749301,0.08350483,0.006379145,0.00030087304,0.0015613512,0.000066013745,0.000064304055,0.000030273364],"genre_scores_gemma":[0.9812724,0.000106854175,0.017212398,0.00014160885,0.00037551756,0.0005394007,0.000072348295,0.000048680886,0.00023078802],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9969338,0.00037951555,0.0007602987,0.0004895002,0.0008338689,0.00060300436],"domain_scores_gemma":[0.99715126,0.0017050755,0.00012969693,0.00033799466,0.00044636714,0.00022963513],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011901394,0.00017512917,0.00041473858,0.0010123171,0.00020554278,0.000046132343,0.00025251784,0.0001255999,0.000121041194],"category_scores_gemma":[0.005405624,0.00015351112,0.00015083484,0.0013660605,0.00027677676,0.00008933539,0.000076637756,0.00085214805,0.0000161007],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.010710762,0.00021559457,0.0014475831,0.00028173934,0.00004568796,0.000042518044,0.0017680619,0.032878194,0.8655197,0.00014120254,0.00009606233,0.08685289],"study_design_scores_gemma":[0.0023398919,0.0006371146,0.02119133,0.0009727934,0.000010921826,0.000003265012,0.0009825424,0.3064832,0.6652875,0.000187217,0.0017231173,0.00018111663],"about_ca_topic_score_codex":0.0014319639,"about_ca_topic_score_gemma":0.00004486834,"teacher_disagreement_score":0.27360502,"about_ca_system_score_codex":0.0005697235,"about_ca_system_score_gemma":0.0014022072,"threshold_uncertainty_score":0.6471427},"labels":[],"label_agreement":null},{"id":"W4362541217","doi":"10.1158/1538-7445.am2023-1400","title":"Abstract 1400: Novel expression biomarkers via prediction of response to FOLFIRINOX (FFX) treatment for PDAC","year":2023,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Logistic regression; Gene; Gene expression; False discovery rate; Transcriptome; Biology; Fold change; Gene expression profiling; Regression; Oncology; Computational biology; Medicine; Genetics; Internal medicine; Statistics; Mathematics","score_opus":0.11563292099657263,"score_gpt":0.4629144595931316,"score_spread":0.34728153859655897,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362541217","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9841948,0.00015581548,0.0025161705,0.011239283,0.00028073517,0.001125278,0.00012815412,0.00008120884,0.0002785223],"genre_scores_gemma":[0.9950613,0.00020888557,0.0014167714,0.00008635737,0.00030933367,0.0006095035,0.000061905055,0.000044185905,0.002201753],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9982596,0.000072591305,0.00026263564,0.00034351344,0.0006041599,0.0004574729],"domain_scores_gemma":[0.998421,0.0006575416,0.000045709967,0.0003223755,0.00024280963,0.00031055676],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002006637,0.000111234,0.0002371757,0.0005299919,0.00014509066,0.00001712589,0.00012446809,0.00008079631,0.00011688068],"category_scores_gemma":[0.001087261,0.000086824526,0.00010011251,0.00064332347,0.000114233524,0.00004450798,0.00006472858,0.00022708786,0.000027499022],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004882798,0.00012475377,0.001891377,0.00015627,0.00007900546,0.00001583822,0.00043827202,0.00016392389,0.9307175,0.0000082391925,0.018921584,0.042600423],"study_design_scores_gemma":[0.010532948,0.003327011,0.2752056,0.001710204,0.00008077434,0.000019411747,0.0005802823,0.014104268,0.5260788,0.0002352086,0.16787827,0.0002472078],"about_ca_topic_score_codex":0.000393166,"about_ca_topic_score_gemma":0.0000066782886,"teacher_disagreement_score":0.4046387,"about_ca_system_score_codex":0.00040130227,"about_ca_system_score_gemma":0.00033917002,"threshold_uncertainty_score":0.35406014},"labels":[],"label_agreement":null},{"id":"W4362542641","doi":"10.1158/1538-7445.am2023-5622","title":"Abstract 5622: Integrative cross-platform characterisation of mammographic screen-detected breast cancer","year":2023,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Ontario Institute for Cancer Research; Health Sciences Centre; Sunnybrook Health Science Centre","funders":"","keywords":"Breast cancer; Medicine; Oncology; Internal medicine; Cancer; Mammography; Cohort; Disease; Stage (stratigraphy); Pathology; Biology","score_opus":0.06041375774035328,"score_gpt":0.44233841650912764,"score_spread":0.38192465876877435,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362542641","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9945358,0.00023300087,0.000035928297,0.0033420883,0.00022283668,0.00040975993,0.00014807447,0.00010914917,0.00096334313],"genre_scores_gemma":[0.9963971,0.0016935589,0.000040144627,0.0000944575,0.00043406474,0.00015980144,0.00009641678,0.000042997253,0.0010414828],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.997812,0.00006876304,0.00033968766,0.0003457735,0.000886547,0.0005472815],"domain_scores_gemma":[0.9983821,0.00023484386,0.000107821645,0.0002927463,0.0007411564,0.00024131555],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001611188,0.00014778187,0.00032102765,0.0006795358,0.0001787269,0.000055942688,0.00020772114,0.00011952987,0.0015219245],"category_scores_gemma":[0.00043379492,0.0001133988,0.00010970176,0.0016491729,0.00054475514,0.00016291333,0.000085367756,0.0012059473,0.000052434883],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009124593,0.00009836657,0.3509715,0.0005324545,0.0002425143,0.00008640859,0.0011609171,0.00005497341,0.41270763,0.00020623149,0.005438656,0.22758788],"study_design_scores_gemma":[0.0009824189,0.00008038121,0.98527586,0.0007726881,0.000018924007,0.000015833695,0.00021973588,0.0018863414,0.009099146,0.00017236914,0.0013640661,0.000112248716],"about_ca_topic_score_codex":0.0037289688,"about_ca_topic_score_gemma":0.00013911712,"teacher_disagreement_score":0.63430434,"about_ca_system_score_codex":0.00020730046,"about_ca_system_score_gemma":0.00045080326,"threshold_uncertainty_score":0.99939084},"labels":[],"label_agreement":null},{"id":"W4362603602","doi":"10.1117/12.2654439","title":"Transferring deep convolutional network representations from SPECT to improve PET cardiac outcome prediction","year":2023,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; University of Calgary","funders":"","keywords":"Computer science; Outcome (game theory); Convolutional neural network; Artificial intelligence; Mathematics","score_opus":0.01701106928495215,"score_gpt":0.3125445172782557,"score_spread":0.29553344799330356,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362603602","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8698355,0.00009475948,0.09450423,0.015432603,0.0030977563,0.00075109437,0.00009472056,0.0008758221,0.015313493],"genre_scores_gemma":[0.98501956,0.00003984643,0.0075574247,0.0009937208,0.0021065169,0.00005845243,0.00039796808,0.000034528635,0.003791981],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9986328,0.000043600154,0.0003205109,0.00034589134,0.00033937016,0.0003178557],"domain_scores_gemma":[0.9992151,0.00020004662,0.000023360148,0.0002464938,0.000045152414,0.00026982639],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003659742,0.00011827514,0.0002646226,0.00010742569,0.00014510856,0.000029645833,0.000072848605,0.00003288686,0.0004062301],"category_scores_gemma":[0.00031317642,0.00010567321,0.0001474424,0.00039683667,0.000040313833,0.000063420746,0.000040415474,0.00031720934,0.00026709837],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000888563,0.00004354185,0.9288037,0.00003253534,0.00028949592,0.0001346431,0.0004541051,0.015740342,0.007555502,0.0024060283,0.03469208,0.009759196],"study_design_scores_gemma":[0.0010291714,0.00009512205,0.79507965,0.00004832957,0.00016413993,0.000019600606,0.00025622742,0.19094929,0.00015752281,0.0007480303,0.011298515,0.00015439963],"about_ca_topic_score_codex":0.0005312096,"about_ca_topic_score_gemma":0.00001767559,"teacher_disagreement_score":0.17520894,"about_ca_system_score_codex":0.00007726953,"about_ca_system_score_gemma":0.000043056913,"threshold_uncertainty_score":0.44479346},"labels":[],"label_agreement":null},{"id":"W4362604024","doi":"10.1117/12.2654042","title":"Feasibility of simulated realistic textured XCAT phantoms for assessment of radiomic feature stability","year":2023,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Feature (linguistics); Stability (learning theory); Artificial intelligence; Radiomics; Computer vision; Machine learning","score_opus":0.058420634521169204,"score_gpt":0.4081755462280355,"score_spread":0.3497549117068663,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362604024","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98390526,0.000059865786,0.010212798,0.0026376774,0.00020438907,0.0011632974,0.00007329503,0.00014560479,0.0015978212],"genre_scores_gemma":[0.9934523,0.00002353071,0.0055155596,0.00012182174,0.00006194808,0.0000098192495,0.00024220377,0.00002395992,0.000548841],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99850786,0.00008136717,0.00046350944,0.000335657,0.00034629003,0.0002653424],"domain_scores_gemma":[0.99831504,0.00060129614,0.00018092897,0.0005028703,0.00024755427,0.00015233204],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012975709,0.00015023483,0.0006141905,0.00013250983,0.00004317072,0.000006732657,0.00012934706,0.00011894737,0.00014369942],"category_scores_gemma":[0.0016217573,0.000111459434,0.0002083192,0.0004567572,0.0001936941,0.00003544262,0.000045173245,0.00027752205,0.0000012177029],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012629007,0.0011139786,0.5414719,0.0046352176,0.00051214785,0.00002695985,0.00076495414,0.0024266394,0.4119579,0.0020257987,0.018716022,0.0150855705],"study_design_scores_gemma":[0.004604159,0.00038167863,0.34498277,0.00014943807,0.00022321037,0.000010308164,0.00025094915,0.6420544,0.0059331213,0.00083029916,0.00043301418,0.00014667516],"about_ca_topic_score_codex":0.00013944469,"about_ca_topic_score_gemma":0.0000070254036,"teacher_disagreement_score":0.63962775,"about_ca_system_score_codex":0.00010769919,"about_ca_system_score_gemma":0.00019971332,"threshold_uncertainty_score":0.45451838},"labels":[],"label_agreement":null},{"id":"W4362694169","doi":"10.1117/12.2654320","title":"Clinician-interactive AI for RECIST measurements in CT imaging","year":2023,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Minimum bounding box; Ground truth; Artificial intelligence; Computer science; Bounding overwatch; Gold standard (test); Pipeline (software); Cancer; Annotation; Nuclear medicine; Medicine; Pattern recognition (psychology); Radiology; Image (mathematics)","score_opus":0.05309886227224365,"score_gpt":0.41353058357336475,"score_spread":0.3604317213011211,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362694169","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.66002333,0.00025997462,0.033736322,0.15294845,0.0039516767,0.0027509814,0.000012205347,0.0010174684,0.14529958],"genre_scores_gemma":[0.9825599,0.000023279266,0.0028551854,0.008274562,0.00024728576,0.00005097321,0.000040475556,0.00003529879,0.005913046],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989155,0.000033610268,0.00029130257,0.00025233685,0.0002179856,0.0002892739],"domain_scores_gemma":[0.99937767,0.00024396308,0.00004867113,0.00015463235,0.00007390271,0.00010116896],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010379469,0.00009765071,0.00023644703,0.00021731944,0.00004766426,0.00002431888,0.00007526027,0.00001629391,0.00009321683],"category_scores_gemma":[0.0016263656,0.00008159056,0.00009340056,0.00026994385,0.000035133966,0.00007783828,0.000032696407,0.00031381266,0.000099651814],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002988278,0.00017499382,0.5217385,0.000112945745,0.00008762065,0.00018404855,0.0003855553,0.00009202822,0.0041840253,0.00023176192,0.09906788,0.3734418],"study_design_scores_gemma":[0.012967265,0.000270657,0.1946423,0.0011211663,0.00014405245,0.00014925847,0.0012703111,0.5120611,0.0030325863,0.0034271902,0.2703682,0.00054590614],"about_ca_topic_score_codex":0.00017337443,"about_ca_topic_score_gemma":0.000022702001,"teacher_disagreement_score":0.5119691,"about_ca_system_score_codex":0.00008704299,"about_ca_system_score_gemma":0.00006098213,"threshold_uncertainty_score":0.33271664},"labels":[],"label_agreement":null},{"id":"W4362700591","doi":"10.21203/rs.3.rs-2761751/v1","title":"Image based prognosis in head and neck cancer using convolutional neural networks: a case study in reproducibility and optimization","year":2023,"lang":"en","type":"preprint","venue":"Research Square","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Alzheimer Nederland; Universiteit Maastricht; ZonMw; Polytechnique Montréal","keywords":"Reproducibility; Convolutional neural network; Computer science; Head and neck; Artificial intelligence; Image processing; Machine learning; Artificial neural network; Deep learning; Image (mathematics); Pattern recognition (psychology); Statistics; Medicine; Mathematics; Surgery","score_opus":0.1259586696414143,"score_gpt":0.4706214594763021,"score_spread":0.34466278983488774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362700591","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99109346,0.001308719,0.0012795345,0.0032831056,0.00011562727,0.0028499549,0.000016739668,0.00004696599,0.000005903661],"genre_scores_gemma":[0.9933302,0.00023137273,0.0057028434,0.00004368126,0.00021105606,0.0003556292,0.00006317646,0.000046060948,0.00001602532],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960602,0.0009153728,0.00046801465,0.0014556444,0.00060353824,0.00049722666],"domain_scores_gemma":[0.998392,0.00042935324,0.00007884202,0.000579536,0.0003018806,0.00021839756],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0066413484,0.000201258,0.00048388878,0.0006296937,0.00014314575,0.00012205862,0.000083641215,0.00016798245,0.000023456048],"category_scores_gemma":[0.003613162,0.00018962317,0.000042252712,0.0006867217,0.00029648247,0.000074393865,0.0005765394,0.0024425369,2.2065011e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014700394,0.00029895088,0.6898623,0.0008447861,0.000017769104,0.003734319,0.00047018938,0.30289626,0.000011011553,6.1065293e-7,0.000028774668,0.00168803],"study_design_scores_gemma":[0.0015448864,0.00015401904,0.290342,0.0011739191,0.000019978617,0.00013321002,0.00066601724,0.7058442,7.893645e-7,0.000017094471,0.000001942468,0.00010191637],"about_ca_topic_score_codex":0.028700791,"about_ca_topic_score_gemma":0.0021697173,"teacher_disagreement_score":0.40294796,"about_ca_system_score_codex":0.00043505424,"about_ca_system_score_gemma":0.00049578544,"threshold_uncertainty_score":0.99985886},"labels":[],"label_agreement":null},{"id":"W4362702913","doi":"","title":"Application of Radiomics in Radiotherapy: Challenges and Future Prospects","year":2022,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre","funders":"","keywords":"Radiomics; Radiation therapy; Computer science; Medical physics; Environmental science; Medicine; Artificial intelligence; Internal medicine","score_opus":0.09178884809594068,"score_gpt":0.49749248264261503,"score_spread":0.40570363454667435,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362702913","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7887018,0.20337677,0.00042741955,0.004566846,0.00030938158,0.000799032,0.000008987433,0.000022160986,0.0017876258],"genre_scores_gemma":[0.87053293,0.12749477,0.0009934658,0.00045659393,0.00033147,0.00007377041,0.000010502706,0.000045069377,0.00006142432],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.998169,0.00018271395,0.00057201314,0.00033348543,0.0005243601,0.00021844574],"domain_scores_gemma":[0.9987697,0.00013791346,0.0005245533,0.00032486254,0.000077941586,0.00016500836],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015341534,0.00017515292,0.00071253884,0.00064563117,0.000114756214,0.00008155771,0.00072363985,0.00005982877,0.0008547469],"category_scores_gemma":[0.0001101151,0.00016100495,0.00008536102,0.00053679344,0.00011766193,0.00034044153,0.0003472446,0.00070664263,3.2050565e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00051900523,0.00050951587,0.41526356,0.00040097407,0.00018443534,0.000059396458,0.0015351806,0.00030612713,0.098206975,0.0013835843,0.0025301445,0.4791011],"study_design_scores_gemma":[0.002340285,0.00005582395,0.91190475,0.00019485826,0.00007123772,0.00016792624,0.00045598904,0.005268337,0.0016736882,0.0033956997,0.074218005,0.00025337067],"about_ca_topic_score_codex":0.00020742658,"about_ca_topic_score_gemma":0.0000068542017,"teacher_disagreement_score":0.4966412,"about_ca_system_score_codex":0.00013500857,"about_ca_system_score_gemma":0.00010583248,"threshold_uncertainty_score":0.93588793},"labels":[],"label_agreement":null},{"id":"W4365148828","doi":"10.3389/fonc.2023.1160167","title":"A scoping review of natural language processing of radiology reports in breast cancer","year":2023,"lang":"en","type":"review","venue":"Frontiers in Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hamilton Health Sciences; McMaster University; Population Health Research Institute","funders":"McMaster University","keywords":"Medicine; Breast cancer; Context (archaeology); Workflow; Medical physics; Artificial intelligence; Mammography; Machine learning; Breast imaging; MEDLINE; Clinical trial; Computer science; Radiology; Cancer; Natural language processing; Data science; Pathology; Internal medicine","score_opus":0.02232465808672918,"score_gpt":0.4267644868069733,"score_spread":0.40443982872024414,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4365148828","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000032147884,0.9962877,0.000040268438,0.00050529384,0.0014939408,0.001279217,0.000008156273,0.000021753372,0.00033152255],"genre_scores_gemma":[0.000040305997,0.9964269,0.0026009264,0.00033498096,0.00018202004,0.00017297849,0.00007318131,0.00005258199,0.000116117946],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.9968973,0.0003804344,0.0017645117,0.0004210799,0.00019197924,0.00034469747],"domain_scores_gemma":[0.9980843,0.00018939123,0.0013029918,0.00028487277,0.00006757216,0.00007086275],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015869621,0.0002523705,0.0044742413,0.0007055419,0.000012268089,0.0000019752947,0.00017345778,0.0003601434,0.000032984914],"category_scores_gemma":[0.0010975124,0.00020070521,0.00026758376,0.0008666378,0.00025145034,0.00003061139,0.00008569719,0.0012104742,6.8703235e-7],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012535278,0.00003670688,0.0013159642,0.3639674,0.000048340647,0.00093162095,0.0001268646,0.0000014513948,9.1638327e-7,6.5540104e-7,0.0029620503,0.6305955],"study_design_scores_gemma":[0.0004945953,0.00006070339,0.0001730717,0.94963366,0.00052644586,0.0028652109,0.00007552551,0.00029495475,2.7198735e-7,0.000008829993,0.045694787,0.00017192343],"about_ca_topic_score_codex":0.00021576726,"about_ca_topic_score_gemma":0.000026234206,"teacher_disagreement_score":0.6304236,"about_ca_system_score_codex":0.0005215777,"about_ca_system_score_gemma":0.0023573558,"threshold_uncertainty_score":0.8184521},"labels":[],"label_agreement":null},{"id":"W4366084601","doi":"10.21203/rs.3.rs-2762043/v1","title":"Radiomics analysis of baseline computed tomography to predict oncological outcomes in patients treated for resectable colorectal cancer liver metastasis","year":2023,"lang":"en","type":"preprint","venue":"Research Square","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; Ericsson (Canada); Polytechnique Montréal; Centre Hospitalier de l’Université de Montréal","funders":"Institute of Cancer Research; Institut Du Cancer de Montréal; Fonds de Recherche du Québec - Santé; Fondation de l'Association des radiologistes du Québec; Institut de Valorisation des Données; Université de Montréal","keywords":"Medicine; Radiomics; Colorectal cancer; Overall survival; Internal medicine; Oncology; Metastasis; Radiology; Cancer","score_opus":0.06986523791998318,"score_gpt":0.4234468085377938,"score_spread":0.35358157061781065,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366084601","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98992556,0.00033778162,0.0014165236,0.0018697316,0.0002256482,0.0039219167,0.0021383862,0.0001129494,0.00005150387],"genre_scores_gemma":[0.99026805,0.00040838908,0.004556251,0.000119483775,0.00014003742,0.0010800344,0.0030796824,0.00008155322,0.00026650305],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9948175,0.0008325103,0.00092286314,0.0009956086,0.0015343026,0.0008972076],"domain_scores_gemma":[0.994736,0.0025369776,0.00020712445,0.00057628175,0.0014247372,0.0005188602],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.004309626,0.00035945937,0.0020087631,0.004794093,0.00011931074,0.00005622875,0.00048588027,0.00041894673,0.00014389417],"category_scores_gemma":[0.0056391903,0.000286094,0.00081707834,0.004842818,0.00023040279,0.000037001893,0.00079817034,0.0017739292,0.0000043226964],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019114908,0.001100662,0.9635888,0.0010796876,0.0039137667,0.0000698108,0.0003245121,0.016003579,0.00011796917,0.00001529235,0.004729636,0.0071448083],"study_design_scores_gemma":[0.0024152165,0.0012091127,0.74738467,0.0006768313,0.0010996726,3.3367684e-7,0.000059921706,0.24632736,0.0001601784,0.000027733895,0.0004468179,0.00019216737],"about_ca_topic_score_codex":0.005826927,"about_ca_topic_score_gemma":0.0009649014,"teacher_disagreement_score":0.23032378,"about_ca_system_score_codex":0.0007049755,"about_ca_system_score_gemma":0.00047577554,"threshold_uncertainty_score":0.9999591},"labels":[],"label_agreement":null},{"id":"W4366496639","doi":"10.1016/j.jmir.2023.03.014","title":"Predicting tumour and normal tissue response during radiotherapy using radiomic analysis from on-board imaging: a systematic review","year":2023,"lang":"en","type":"review","venue":"Journal of medical imaging and radiation sciences","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency","funders":"","keywords":"Medical physics; Radiation therapy; Medicine; Radiology; Nuclear medicine","score_opus":0.027712343929103527,"score_gpt":0.39699907097459186,"score_spread":0.3692867270454883,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366496639","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0069185323,0.98513937,0.0011197466,0.0057087704,0.0005085488,0.0005408151,0.000010032352,0.000046790046,0.0000073783503],"genre_scores_gemma":[0.0009803458,0.9961649,0.00090638973,0.0008876717,0.00095966633,0.000009198616,0.0000084362255,0.00004987152,0.000033526438],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.9932073,0.001233256,0.0021935345,0.00057092664,0.0023593039,0.00043571595],"domain_scores_gemma":[0.99386287,0.0027449226,0.0022290722,0.00026272223,0.0001262772,0.00077415677],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.011002673,0.0004472699,0.0037225697,0.001860166,0.00040191453,0.00030327245,0.00049521896,0.00014864975,0.000047979942],"category_scores_gemma":[0.009533612,0.00028895045,0.00055934023,0.0017398739,0.0005857669,0.00028814978,0.00009489613,0.0013489873,0.0000029420517],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015745881,0.00013056477,0.0042213467,0.4523487,0.0044008135,0.0029519019,0.0010141653,0.000103462764,0.00013105782,0.000012716427,0.000938194,0.5335896],"study_design_scores_gemma":[0.0017715718,0.00015655448,0.0010329845,0.7856892,0.022601541,0.0076092286,0.0005104426,0.16583514,0.000002913295,0.0000140472885,0.01421114,0.0005652784],"about_ca_topic_score_codex":0.000111673784,"about_ca_topic_score_gemma":8.9658147e-7,"teacher_disagreement_score":0.5330243,"about_ca_system_score_codex":0.00024003796,"about_ca_system_score_gemma":0.00092757423,"threshold_uncertainty_score":0.99995625},"labels":[],"label_agreement":null},{"id":"W4366548311","doi":"10.1016/j.jmir.2023.03.023","title":"Machine Learning Radiotherapy Automated Planning: Transition to an Ultra-hypofractionated Prostate Model","year":2023,"lang":"en","type":"article","venue":"Journal of medical imaging and radiation sciences","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Juravinski Cancer Centre; University of Toronto; Princess Margaret Cancer Centre; University Health Network","funders":"","keywords":"Radiation therapy; Medical physics; Prostate; Radiation treatment planning; Computer science; Medicine; Radiology; Internal medicine","score_opus":0.019221520386680603,"score_gpt":0.36693479413197816,"score_spread":0.34771327374529754,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366548311","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.82407475,0.0021643816,0.030989323,0.14157031,0.00049090444,0.00016295,0.000002528997,0.00035896146,0.00018586931],"genre_scores_gemma":[0.9899839,0.002259658,0.0030269134,0.004215396,0.00038385767,0.000002353604,0.000017594522,0.000017291635,0.00009304383],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99759287,0.00013397039,0.00045786815,0.00021437986,0.0013403749,0.00026051296],"domain_scores_gemma":[0.99879825,0.00019397243,0.00021396091,0.000059000085,0.00012691591,0.0006079199],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0035935596,0.000118596115,0.00027935256,0.000641429,0.00031359436,0.00012328551,0.00015257529,0.000060933624,0.000041726307],"category_scores_gemma":[0.001266501,0.00008503229,0.000058484355,0.0007728426,0.00021430686,0.00052122877,0.000007682604,0.00060617,0.0000031489847],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029113243,0.00020536449,0.031193279,0.00008999272,0.00010344615,0.0005280937,0.01012795,0.4793078,0.027073715,0.00017132249,0.017308472,0.43359944],"study_design_scores_gemma":[0.0012985136,0.000270713,0.0073202704,0.00018285662,0.000029038045,0.00089542323,0.00090497144,0.9821088,0.00012753042,0.00010874284,0.006654682,0.000098480334],"about_ca_topic_score_codex":0.00002868767,"about_ca_topic_score_gemma":2.2671142e-7,"teacher_disagreement_score":0.502801,"about_ca_system_score_codex":0.00004599664,"about_ca_system_score_gemma":0.00029140033,"threshold_uncertainty_score":0.3467516},"labels":[],"label_agreement":null},{"id":"W4366605609","doi":"10.21203/rs.3.rs-2787380/v1","title":"A Priori Prediction of Breast Cancer Response to Neoadjuvant Chemotherapy using Quantitative Ultrasound, Texture Derivative and Molecular Subtype","year":2023,"lang":"en","type":"preprint","venue":"Research Square","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University; Health Sciences Centre; Sunnybrook Health Science Centre","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto; Canadian Institutes of Health Research; Terry Fox Foundation","keywords":"Margin (machine learning); Breast cancer; Texture (cosmology); Ultrasound; Computer science; Derivative (finance); Support vector machine; Chemotherapy; Oncology; Cancer; Medicine; Pattern recognition (psychology); Artificial intelligence; Internal medicine; Radiology; Machine learning","score_opus":0.060008790841925334,"score_gpt":0.4362547686208418,"score_spread":0.37624597777891644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366605609","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97838277,0.0012001995,0.0059798546,0.011996865,0.00019398378,0.0016383061,0.0004907023,0.000080051366,0.000037242953],"genre_scores_gemma":[0.9914275,0.0012855488,0.006259777,0.00023927278,0.00020920599,0.00011541981,0.00008642336,0.00012383173,0.00025304826],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9964305,0.0007221928,0.00040182823,0.000715102,0.0012079832,0.000522399],"domain_scores_gemma":[0.9971324,0.0007661116,0.00016051122,0.00050401356,0.0010532266,0.00038374594],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002698554,0.00027899691,0.00063008745,0.0007411818,0.00014789002,0.00006983659,0.00019967006,0.00030056998,0.00005968503],"category_scores_gemma":[0.0034888182,0.00024287245,0.00012642764,0.00079725205,0.00037570344,0.000048803733,0.00036778787,0.0020469625,0.000005894574],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0106806075,0.00025973356,0.07847,0.0033021301,0.0008216499,0.00039374927,0.012379544,0.002987431,0.8732522,0.00017823419,0.0015377899,0.015736917],"study_design_scores_gemma":[0.0025762732,0.001170075,0.93037575,0.010794785,0.00014286666,0.00018009482,0.0030600636,0.044745356,0.004655866,0.0008233411,0.0010784551,0.00039704825],"about_ca_topic_score_codex":0.002694391,"about_ca_topic_score_gemma":0.000020120977,"teacher_disagreement_score":0.8685964,"about_ca_system_score_codex":0.00043203292,"about_ca_system_score_gemma":0.0010575912,"threshold_uncertainty_score":0.9904051},"labels":[],"label_agreement":null},{"id":"W4367172051","doi":"10.1016/j.carpath.2023.107539","title":"Pathology Musings - Society for Cardiovascular Pathology Distinguished Achievement awardee lecture 2023","year":2023,"lang":"en","type":"article","venue":"Cardiovascular Pathology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Pathology; Medicine","score_opus":0.016236632372791354,"score_gpt":0.27229719929411844,"score_spread":0.25606056692132706,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367172051","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5858073,0.039686378,0.34985685,0.008186987,0.008991255,0.0039865933,0.00018527402,0.0017571434,0.0015422083],"genre_scores_gemma":[0.8546042,0.010641846,0.089789435,0.017084472,0.012114097,0.0032169847,0.0050099315,0.0012792764,0.0062597604],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99443805,0.00060309726,0.00079486583,0.0017652555,0.0008217713,0.0015769744],"domain_scores_gemma":[0.9965879,0.00032065267,0.0001751739,0.0020953733,0.00041174013,0.00040918068],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.005528161,0.0006638682,0.0023918988,0.00035135576,0.00050060404,0.00004989335,0.0004322736,0.0008132953,0.000046925757],"category_scores_gemma":[0.0026524062,0.0006104048,0.008812705,0.00087156764,0.0007053838,0.000067774155,0.00040110332,0.0012439789,0.00015961402],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00086910045,0.0010471214,0.023044094,0.00404864,0.06212248,0.08464673,0.0080587575,0.042262495,0.05625872,0.0018795362,0.18397078,0.53179157],"study_design_scores_gemma":[0.01098041,0.0008502842,0.022111882,0.00016346213,0.00768359,0.013084877,0.0004657292,0.009642203,0.0005378296,0.0021386687,0.93107873,0.0012623129],"about_ca_topic_score_codex":0.000041307332,"about_ca_topic_score_gemma":0.0000027863605,"teacher_disagreement_score":0.747108,"about_ca_system_score_codex":0.0002031734,"about_ca_system_score_gemma":0.00022688956,"threshold_uncertainty_score":0.99963474},"labels":[],"label_agreement":null},{"id":"W4367302458","doi":"10.1212/wnl.0000000000203939","title":"Deep Learning Reconstruction of Lesion-Free Representations of the Brain in Multiple Sclerosis Patients (P11-3.006)","year":2023,"lang":"en","type":"article","venue":"Neurology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"NeuroRx Research (Canada)","funders":"","keywords":"Lesion; Multiple sclerosis; Voxel; Medicine; Nuclear medicine; Radiology; Pathology","score_opus":0.026482668272512323,"score_gpt":0.27839783590353046,"score_spread":0.2519151676310181,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367302458","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9923057,0.00001405193,0.00010629309,0.006691052,0.00033072842,0.00016086463,0.0000015038028,0.000026768304,0.00036305885],"genre_scores_gemma":[0.99920344,0.000039710558,0.00020770404,0.00041913855,0.00003084273,0.000007913663,0.000009770231,0.000012382921,0.000069097805],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9990361,0.00020855645,0.00029063245,0.00016706687,0.00015804176,0.00013960134],"domain_scores_gemma":[0.99900436,0.00050852966,0.0001489005,0.00025169496,0.000053014475,0.00003350096],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026022337,0.00005841013,0.00018342862,0.00017425204,0.00005371462,0.0000020365035,0.00012023353,0.00006691072,0.000027328191],"category_scores_gemma":[0.0049304194,0.000046012552,0.00006230879,0.00043125535,0.00017539079,0.00002746983,0.00010746219,0.00041887444,0.0000039676697],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000086892105,0.000044386623,0.9520157,0.000024038489,0.000008584453,0.0000028494974,0.00031046738,0.0030839052,0.009821828,0.00003631703,0.0003970454,0.034168012],"study_design_scores_gemma":[0.001632693,0.00020636577,0.95321906,0.000039444705,0.000012657338,0.000011920659,0.00003971819,0.043861177,0.00046218955,0.00022741672,0.00025794533,0.000029439478],"about_ca_topic_score_codex":0.00030023337,"about_ca_topic_score_gemma":0.00006471752,"teacher_disagreement_score":0.040777273,"about_ca_system_score_codex":0.000007765931,"about_ca_system_score_gemma":0.00002315882,"threshold_uncertainty_score":0.5902529},"labels":[],"label_agreement":null},{"id":"W4367604149","doi":"10.1164/ajrccm-conference.2023.207.1_meetingabstracts.a3310","title":"Association of Pre-pandemic CT Interstitial Lung Abnormalities and High Attenuation Areas With COVID-19 Hospitalization: The C4R Study","year":2023,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Coronavirus disease 2019 (COVID-19); Pandemic; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); 2019-20 coronavirus outbreak; Attenuation; Medicine; Lung; Association (psychology); Pathology; Internal medicine; Physics; Outbreak; Psychology; Disease; Optics","score_opus":0.010859077506225364,"score_gpt":0.30310576858810956,"score_spread":0.29224669108188417,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367604149","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9831337,0.000027837876,0.0068460554,0.0088585615,0.00011438978,0.00047748606,0.0000030393926,0.00011114456,0.00042783827],"genre_scores_gemma":[0.9961062,0.000038415783,0.000056732344,0.0007721887,0.0001090619,0.00002357339,0.000054316137,0.000011327059,0.0028281983],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99910265,0.00009327035,0.00019612601,0.00014106566,0.00034751938,0.00011938506],"domain_scores_gemma":[0.9993076,0.00029166305,0.00012947523,0.000117321404,0.00007839118,0.000075585514],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008474818,0.00007974128,0.00016452749,0.00007986035,0.00010753615,0.000028354127,0.00005193044,0.000022543394,0.00006929985],"category_scores_gemma":[0.00087477826,0.000047478567,0.00002084817,0.00022353725,0.0000680591,0.0000768933,0.000035876095,0.00014341177,0.0000018473986],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007482086,0.000040369796,0.9899178,0.0000761054,0.00014935083,0.000012425897,0.0038086332,0.00052116934,0.000018579882,0.0004099159,0.0040270644,0.00094375387],"study_design_scores_gemma":[0.002532446,0.0005287323,0.9523551,0.000065666674,0.00029706443,0.00004036117,0.005652874,0.037331767,0.000015444251,0.0001706596,0.000912691,0.000097207165],"about_ca_topic_score_codex":0.00089582504,"about_ca_topic_score_gemma":0.00009201276,"teacher_disagreement_score":0.037562724,"about_ca_system_score_codex":0.00011203358,"about_ca_system_score_gemma":0.000085669744,"threshold_uncertainty_score":0.19361198},"labels":[],"label_agreement":null},{"id":"W4367604434","doi":"10.1164/ajrccm-conference.2023.207.1_meetingabstracts.a6489","title":"Microscopic Validation of Deep Learning Based Texture Classification of Idiopathic Pulmonary Fibrosis Patterns Visible on Thoracic Computed Tomography","year":2023,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computed tomography; Texture (cosmology); Medicine; Radiology; Artificial intelligence; Pulmonary fibrosis; Idiopathic pulmonary fibrosis; Pathology; Computer science; Fibrosis; Lung; Internal medicine; Image (mathematics)","score_opus":0.016118199274496803,"score_gpt":0.30514889476351476,"score_spread":0.28903069548901794,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367604434","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93997765,0.000100362646,0.057670563,0.0011157612,0.000114368166,0.0002533919,0.000004359223,0.00017812762,0.0005854209],"genre_scores_gemma":[0.99811244,0.000028925813,0.0012073747,0.00015088101,0.000066697714,0.000010163772,0.00028708237,0.00002902426,0.00010739735],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99858725,0.0001534143,0.00041698923,0.00027435186,0.00037404217,0.00019392643],"domain_scores_gemma":[0.9991161,0.0001609829,0.00023996946,0.0002621028,0.00013125193,0.00008955734],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005675816,0.00014093512,0.0003397505,0.0005294133,0.00007281816,0.000014205077,0.00010660906,0.000114770206,0.000076213444],"category_scores_gemma":[0.00019142448,0.0001198797,0.00013956366,0.00089809444,0.00007131056,0.000050122133,0.000027505657,0.0004116467,0.000014306893],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013838788,0.00020931872,0.48753896,0.0011782304,0.000046080826,0.000012282084,0.00017526305,0.004750744,0.43823776,0.000077668876,0.00008936436,0.06754596],"study_design_scores_gemma":[0.00039305887,0.00029750538,0.49533316,0.0008017989,0.000056832294,0.000004442103,0.00013820645,0.44284713,0.059920333,0.000028264232,0.00009040712,0.000088861685],"about_ca_topic_score_codex":0.000035841218,"about_ca_topic_score_gemma":6.6440197e-7,"teacher_disagreement_score":0.43809637,"about_ca_system_score_codex":0.000023867662,"about_ca_system_score_gemma":0.00003852085,"threshold_uncertainty_score":0.48885524},"labels":[],"label_agreement":null},{"id":"W4367605503","doi":"10.1164/ajrccm-conference.2023.207.1_meetingabstracts.a6543","title":"Texture-based Computed Tomography Radiomics With Machine Learning Improves Predicting Chronic Obstructive Pulmonary Disease Outcomes","year":2023,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Paul's Hospital; Toronto Metropolitan University","funders":"","keywords":"Radiomics; Pulmonary disease; Computed tomography; Computer science; Artificial intelligence; Medicine; Radiology; Machine learning; Internal medicine","score_opus":0.006648788197670256,"score_gpt":0.24708826222657695,"score_spread":0.2404394740289067,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367605503","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96350265,0.0009793198,0.017358286,0.011560023,0.00048093568,0.0010476501,0.000021290263,0.0024825572,0.002567298],"genre_scores_gemma":[0.9935337,0.000025538995,0.0034358914,0.0009035056,0.00030244884,0.00004138054,0.00037697415,0.00010421751,0.0012764017],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99773,0.000094460745,0.00037654003,0.0006120603,0.0005547818,0.00063216366],"domain_scores_gemma":[0.9984591,0.00030672713,0.00016616171,0.0003871234,0.00010073652,0.0005801786],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003657521,0.0003794594,0.00054875837,0.0005192533,0.0003312341,0.000070651804,0.00019283198,0.000092647715,0.000064169835],"category_scores_gemma":[0.00035649043,0.00026645034,0.00023943743,0.0010478692,0.000213033,0.00012410761,0.00009272237,0.00106179,0.00002081747],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034119238,0.00011745461,0.9511563,0.00033151408,0.00025562666,0.0006610481,0.00010517502,0.008801004,0.0028987047,0.00014078585,0.00018239713,0.03500877],"study_design_scores_gemma":[0.0015058784,0.00017926688,0.43715015,0.00014119812,0.00015992891,0.00004259532,0.00007589399,0.5587245,0.000095402385,0.000047759404,0.0016633067,0.00021411323],"about_ca_topic_score_codex":0.0001123289,"about_ca_topic_score_gemma":0.0000074462205,"teacher_disagreement_score":0.5499235,"about_ca_system_score_codex":0.00013446156,"about_ca_system_score_gemma":0.00026788967,"threshold_uncertainty_score":0.9999788},"labels":[],"label_agreement":null},{"id":"W4367605835","doi":"10.1164/ajrccm-conference.2023.207.1_meetingabstracts.a4014","title":"Inspiration-Expiration CT Texture-Based Delta Radiomics: A New Biomarker Associated With COPD Symptoms?","year":2023,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Paul's Hospital; Toronto Metropolitan University","funders":"","keywords":"Radiomics; Expiration; COPD; Biomarker; Texture (cosmology); Medicine; Delta; Computer science; Radiology; Artificial intelligence; Internal medicine; Engineering; Chemistry; Image (mathematics)","score_opus":0.01856777235313417,"score_gpt":0.28285299767316985,"score_spread":0.2642852253200357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367605835","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9183315,0.00010926725,0.048512284,0.023235772,0.00028634103,0.00068652566,0.0000065522713,0.0011590781,0.007672702],"genre_scores_gemma":[0.98464686,0.000014661642,0.0009997678,0.008172843,0.00017848483,0.000020313846,0.00063917594,0.00005919889,0.0052687107],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983239,0.00006698835,0.00032093463,0.00033564406,0.0006143826,0.00033816107],"domain_scores_gemma":[0.99893403,0.00020355688,0.00012005855,0.00027683657,0.000109028835,0.000356476],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00057625957,0.00019979427,0.00030771986,0.000294306,0.00013237474,0.00007506954,0.00012080693,0.0000951685,0.00057230744],"category_scores_gemma":[0.0011684529,0.00014624587,0.00008511075,0.00095300627,0.000077281686,0.000113139715,0.000023666973,0.0003291205,0.00012127736],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000536947,0.00053776073,0.4670924,0.00016327699,0.0010313288,0.001194118,0.00049293326,0.0036109055,0.008597314,0.0024761392,0.21750331,0.29676357],"study_design_scores_gemma":[0.0074318787,0.00038350184,0.111933045,0.00042043877,0.00017010167,0.00007988998,0.000045576387,0.8552119,0.00067287363,0.00011991516,0.023171041,0.00035980422],"about_ca_topic_score_codex":0.00031378563,"about_ca_topic_score_gemma":0.00013377254,"teacher_disagreement_score":0.851601,"about_ca_system_score_codex":0.00012588553,"about_ca_system_score_gemma":0.0006689408,"threshold_uncertainty_score":0.6266365},"labels":[],"label_agreement":null},{"id":"W4367608413","doi":"10.1164/ajrccm-conference.2023.207.1_meetingabstracts.a2297","title":"A Deep Learning Algorithm to Predict Lung Density in Healthy Subjects Based on Tracheal Shape","year":2023,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Deep learning; Artificial intelligence; Algorithm","score_opus":0.011697187936109195,"score_gpt":0.3019320449723028,"score_spread":0.2902348570361936,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367608413","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9164918,0.000050545837,0.055254113,0.021741832,0.00034838959,0.0007351439,0.0000014170696,0.0006963852,0.004680368],"genre_scores_gemma":[0.9797351,0.000019878837,0.009530773,0.00984702,0.00024756606,0.00003121771,0.0000564783,0.000045421748,0.00048655015],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980455,0.00013808806,0.0003108833,0.0004412015,0.00048659128,0.0005777296],"domain_scores_gemma":[0.9988819,0.00032537238,0.000044048822,0.00021093454,0.00004344339,0.0004943137],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011533339,0.0001767288,0.00036446797,0.00051746395,0.00011989833,0.000025787345,0.000098248165,0.00010176608,0.00019834773],"category_scores_gemma":[0.0010526902,0.00015477379,0.00008095538,0.0008933667,0.00003500303,0.000038365022,0.000044153396,0.0010132333,0.00014728517],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00088532065,0.0003233077,0.31234348,0.00027952975,0.000033044525,0.0012151008,0.0011138618,0.018477531,0.0004928949,0.00007288206,0.0036740322,0.661089],"study_design_scores_gemma":[0.0017404665,0.00063166674,0.19754124,0.00012202764,0.000014333558,0.000019593961,0.00011919958,0.79870695,0.00003626923,0.000010602144,0.0009436976,0.00011392518],"about_ca_topic_score_codex":0.0002805974,"about_ca_topic_score_gemma":0.000043718344,"teacher_disagreement_score":0.78022945,"about_ca_system_score_codex":0.00018268425,"about_ca_system_score_gemma":0.000113844944,"threshold_uncertainty_score":0.6311492},"labels":[],"label_agreement":null},{"id":"W4367848976","doi":"10.32920/22734368","title":"Interactive segmentation using U-Net with weight map and dynamic user interactions","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Segmentation; Computer science; Function (biology); Artificial intelligence; Net (polyhedron); Artificial neural network; Pattern recognition (psychology); Mathematics","score_opus":0.018087074210372055,"score_gpt":0.34696621910191416,"score_spread":0.32887914489154213,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367848976","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8205965,0.00010497252,0.16679847,0.008519985,0.0015973506,0.00074276136,0.000016341519,0.0002889605,0.0013346213],"genre_scores_gemma":[0.88361377,0.00021496149,0.098886736,0.0010082402,0.00034810544,0.000060681195,0.00051602,0.00013732347,0.015214147],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99883354,0.000050190993,0.0002531813,0.00045144922,0.00022299965,0.00018864879],"domain_scores_gemma":[0.99923307,0.0001315,0.00016495568,0.00024058459,0.000087405984,0.00014246706],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001504484,0.00023165449,0.00034433388,0.0002693335,0.000081444814,0.00009257526,0.00006489934,0.000095241165,0.00019392913],"category_scores_gemma":[0.00006678708,0.0001741649,0.000060300168,0.000088452536,0.00009241753,0.00010834539,0.00025570142,0.0012391643,0.000027135147],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0054183425,0.0023831185,0.53658164,0.0134964185,0.016717838,0.0043755393,0.03210964,0.033998407,0.09372439,0.0023323344,0.06372188,0.19514045],"study_design_scores_gemma":[0.0020850585,0.00017978548,0.025866665,0.0034191143,0.00094178354,0.00055409066,0.0021213368,0.9580156,0.00034582894,0.00079980295,0.005123402,0.00054749486],"about_ca_topic_score_codex":0.00059128524,"about_ca_topic_score_gemma":0.00009088243,"teacher_disagreement_score":0.92401725,"about_ca_system_score_codex":0.0002263351,"about_ca_system_score_gemma":0.00011259061,"threshold_uncertainty_score":0.71022385},"labels":[],"label_agreement":null},{"id":"W4367849079","doi":"10.32920/22734368.v1","title":"Interactive segmentation using U-Net with weight map and dynamic user interactions","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Segmentation; Computer science; Function (biology); Artificial intelligence; Artificial neural network; Net (polyhedron); Pattern recognition (psychology); Mathematics","score_opus":0.018087074210372055,"score_gpt":0.34696621910191416,"score_spread":0.32887914489154213,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367849079","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8205965,0.00010497252,0.16679847,0.008519985,0.0015973506,0.00074276136,0.000016341519,0.0002889605,0.0013346213],"genre_scores_gemma":[0.88361377,0.00021496149,0.098886736,0.0010082402,0.00034810544,0.000060681195,0.00051602,0.00013732347,0.015214147],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99883354,0.000050190993,0.0002531813,0.00045144922,0.00022299965,0.00018864879],"domain_scores_gemma":[0.99923307,0.0001315,0.00016495568,0.00024058459,0.000087405984,0.00014246706],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001504484,0.00023165449,0.00034433388,0.0002693335,0.000081444814,0.00009257526,0.00006489934,0.000095241165,0.00019392913],"category_scores_gemma":[0.00006678708,0.0001741649,0.000060300168,0.000088452536,0.00009241753,0.00010834539,0.00025570142,0.0012391643,0.000027135147],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0054183425,0.0023831185,0.53658164,0.0134964185,0.016717838,0.0043755393,0.03210964,0.033998407,0.09372439,0.0023323344,0.06372188,0.19514045],"study_design_scores_gemma":[0.0020850585,0.00017978548,0.025866665,0.0034191143,0.00094178354,0.00055409066,0.0021213368,0.9580156,0.00034582894,0.00079980295,0.005123402,0.00054749486],"about_ca_topic_score_codex":0.00059128524,"about_ca_topic_score_gemma":0.00009088243,"teacher_disagreement_score":0.92401725,"about_ca_system_score_codex":0.0002263351,"about_ca_system_score_gemma":0.00011259061,"threshold_uncertainty_score":0.71022385},"labels":[],"label_agreement":null},{"id":"W4372267725","doi":"10.1109/icassp49357.2023.10094986","title":"Spatio-Temporal Hybrid Fusion of CAE and SWin Transformers for Lung Cancer Malignancy Prediction","year":2023,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Health Sciences Centre; Sunnybrook Health Science Centre; Concordia University","funders":"","keywords":"Malignancy; Computer science; Lung cancer; Radiology; Artificial intelligence; Transformer; Computed tomography; Medicine; Pathology; Engineering","score_opus":0.011460131725364763,"score_gpt":0.30462520972106694,"score_spread":0.2931650779957022,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4372267725","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9636484,0.00029253864,0.028833138,0.005398253,0.0002679688,0.0005110367,0.000038753205,0.000097505166,0.0009124524],"genre_scores_gemma":[0.9962942,0.0005987708,0.0010867664,0.00018929859,0.00012777069,0.00004505396,0.0001675817,0.000017944316,0.0014726075],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99933094,0.000010075294,0.00020306473,0.00015167217,0.00015002713,0.00015421446],"domain_scores_gemma":[0.99972576,0.00004066781,0.00004253939,0.000053038235,0.000045314784,0.00009266054],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002540887,0.000074738346,0.00017806016,0.00010511823,0.000053777083,0.00000556796,0.000021881046,0.00003299386,0.000102964754],"category_scores_gemma":[0.000059666436,0.000058990783,0.000052838397,0.0001212929,0.000044122648,0.00004959993,0.000009193433,0.0000956439,6.128237e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00050269964,0.00008814797,0.5941736,0.0022575415,0.0001886638,0.00002750208,0.0011079804,0.00037750896,0.032414,0.00040507354,0.054783467,0.31367382],"study_design_scores_gemma":[0.0032364167,0.000282879,0.07612085,0.00048318986,0.00019796024,0.000026431084,0.00018566614,0.9018918,0.0075053377,0.00013276031,0.009811155,0.0001255549],"about_ca_topic_score_codex":0.00052328105,"about_ca_topic_score_gemma":0.00002590831,"teacher_disagreement_score":0.9015143,"about_ca_system_score_codex":0.000023928005,"about_ca_system_score_gemma":0.000057349574,"threshold_uncertainty_score":0.24055743},"labels":[],"label_agreement":null},{"id":"W4375955872","doi":"10.1177/08465371231176726","title":"Editor’s Corner: November 2023","year":2023,"lang":"en","type":"editorial","venue":"Canadian Association of Radiologists Journal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; University of Calgary","funders":"","keywords":"Medicine","score_opus":0.008199140696649109,"score_gpt":0.2820522178087452,"score_spread":0.27385307711209605,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4375955872","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00020531662,0.00037564783,0.00006990073,0.0059789037,0.98879546,0.00015936309,0.00035824993,0.000053832387,0.0040033553],"genre_scores_gemma":[0.00041182674,0.0016685554,0.00031389584,0.00034080708,0.9621844,0.0000068671893,0.0007458029,0.000096653566,0.03423115],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.996446,0.00022741903,0.0008616401,0.00034392942,0.0013037362,0.0008172903],"domain_scores_gemma":[0.99409384,0.0019273962,0.0014090734,0.00028866288,0.0011043446,0.0011767078],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.0033204928,0.00031882507,0.0010391528,0.0007302138,0.00021612464,0.00009902584,0.00037329821,0.0016321979,0.00034674787],"category_scores_gemma":[0.0424412,0.00029431714,0.0004171915,0.00037320182,0.00013233,0.00007241533,0.000031524058,0.0041667437,0.00019731365],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000021137643,0.000015009061,0.004504711,0.00007227573,0.00044692057,0.0003260688,0.00004105822,0.00004070401,0.000011600628,0.000012800915,0.99310267,0.0014050192],"study_design_scores_gemma":[0.0012515531,0.00015428608,0.003282762,0.00033742643,0.00025789512,0.000069089874,0.00002729863,0.00024093833,0.0000011803296,0.000098831464,0.9940363,0.00024242805],"about_ca_topic_score_codex":0.0110906,"about_ca_topic_score_gemma":0.011043467,"teacher_disagreement_score":0.039120708,"about_ca_system_score_codex":0.004472236,"about_ca_system_score_gemma":0.0060578226,"threshold_uncertainty_score":0.9999509},"labels":[],"label_agreement":null},{"id":"W4376109086","doi":"10.1088/1361-6560/acd431","title":"Radiomic analysis for early differentiation of lung cancer recurrence from fibrosis in patients treated with lung stereotactic ablative radiotherapy","year":2023,"lang":"en","type":"article","venue":"Physics in Medicine and Biology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Spinal Cord Injury BC; BC Cancer Agency; Kelowna General Hospital; Okanagan University College; BC Cancer Foundation; University of British Columbia, Okanagan Campus; University of British Columbia","funders":"BC Cancer Foundation","keywords":"SABR volatility model; Feature selection; Medicine; Radiomics; Receiver operating characteristic; Radiation therapy; Lung cancer; Random forest; Artificial intelligence; Radiology; Gradient boosting; Nuclear medicine; Computer science; Oncology; Mathematics; Internal medicine","score_opus":0.05087793102815174,"score_gpt":0.3743703719346559,"score_spread":0.32349244090650414,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4376109086","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9947094,0.0004757592,0.0037825021,0.0005319306,0.00006399051,0.00037661614,0.00003229022,0.000013399937,0.00001414978],"genre_scores_gemma":[0.9982121,0.0008332018,0.00023401862,0.0001121768,0.00010510364,0.000049091203,0.00042869287,0.000012326698,0.000013289391],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99907196,0.00008048245,0.00028603247,0.00027871845,0.00009256121,0.00019026358],"domain_scores_gemma":[0.9992214,0.00038436038,0.00016187398,0.00011780381,0.00006358223,0.000050999177],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017144157,0.00013137712,0.0006160163,0.00033096335,0.000023999828,0.000003356454,0.000054127126,0.0000618675,0.000016515147],"category_scores_gemma":[0.00009038907,0.00008796843,0.00004363307,0.0009247053,0.0001476274,0.000043388052,0.000012535397,0.00018326343,8.794053e-8],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004329978,0.00006253919,0.9876349,0.000067333436,0.0005890713,0.0000011477224,0.001321434,0.00010655709,0.0020722265,0.00003743883,0.00004983351,0.0076245083],"study_design_scores_gemma":[0.004604035,0.00046041433,0.8724839,0.0003009789,0.00046546728,1.4816584e-7,0.000039577382,0.12126139,0.00012411359,0.00017145806,0.000008965718,0.0000795381],"about_ca_topic_score_codex":0.002530462,"about_ca_topic_score_gemma":0.000059679733,"teacher_disagreement_score":0.12115483,"about_ca_system_score_codex":0.00006907519,"about_ca_system_score_gemma":0.000024842015,"threshold_uncertainty_score":0.38253185},"labels":[],"label_agreement":null},{"id":"W4376115904","doi":"10.3390/cancers15102677","title":"Assessment of Variabilities in Lung-Contouring Methods on CBCT Preclinical Radiomics Outputs","year":2023,"lang":"en","type":"article","venue":"Cancers","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Medical Research Council; National Centre for the Replacement, Refinement and Reduction of Animals in Research; Health Research Board; Health Service Executive; Wellcome Trust; Canadian Institute for Theoretical Astrophysics","keywords":"Contouring; Radiomics; Intraclass correlation; Percentile; Cone beam computed tomography; Software; Medicine; Reliability (semiconductor); Computer science; Jaccard index; Artificial intelligence; Pattern recognition (psychology); Nuclear medicine; Medical physics; Radiology; Reproducibility; Computed tomography; Statistics; Mathematics","score_opus":0.03901864092069651,"score_gpt":0.43883298214935457,"score_spread":0.39981434122865805,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4376115904","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9533418,0.00031073982,0.015230149,0.0027948604,0.0013955982,0.000467781,0.000005720739,0.00013705698,0.026316313],"genre_scores_gemma":[0.970661,0.0002968599,0.027556753,0.00054984004,0.00023257475,0.000034036133,0.000011705575,0.000026152298,0.00063109974],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987327,0.00013929255,0.00039193835,0.00026044494,0.00022137583,0.0002542447],"domain_scores_gemma":[0.99842125,0.0010709869,0.000092011855,0.0002633972,0.000032246156,0.00012010739],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019091616,0.00010949239,0.00041902196,0.00020154277,0.000025213356,0.000008487552,0.00010547182,0.00007622893,0.000046957844],"category_scores_gemma":[0.001589067,0.000096793374,0.00010003792,0.00029728241,0.00011847205,0.000030238065,0.000040389972,0.0004780584,0.0000023925054],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004181968,0.00016608229,0.6155663,0.0020490584,0.00045929418,0.00020618847,0.0028181185,0.07975365,0.015217255,0.021387072,0.011004919,0.25095385],"study_design_scores_gemma":[0.00392457,0.0004120845,0.4748172,0.0010871395,0.00011154926,0.000011307418,0.0005463454,0.5034728,0.002024678,0.0010254176,0.012305893,0.00026105752],"about_ca_topic_score_codex":0.00024551078,"about_ca_topic_score_gemma":0.000009433937,"teacher_disagreement_score":0.42371914,"about_ca_system_score_codex":0.00088146713,"about_ca_system_score_gemma":0.0008720697,"threshold_uncertainty_score":0.39471194},"labels":[],"label_agreement":null},{"id":"W4376225924","doi":"10.1080/09553002.2023.2214206","title":"Radiomics and dosiomics-based prediction of radiotherapy-induced xerostomia in head and neck cancer patients","year":2023,"lang":"en","type":"article","venue":"International Journal of Radiation Biology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Radiomics; Medicine; Receiver operating characteristic; Head and neck cancer; Radiation therapy; Nuclear medicine; Radiology; Internal medicine","score_opus":0.013383039435826841,"score_gpt":0.3317751365918355,"score_spread":0.31839209715600864,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4376225924","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99423045,0.0004665921,0.00036709383,0.003976246,0.0008203723,0.000093791816,0.000022696577,0.000008017399,0.0000147638175],"genre_scores_gemma":[0.99637616,0.0022976669,0.00053202675,0.0004944629,0.00023658629,0.000002673959,0.00004312799,0.0000097752,0.0000075238668],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9991677,0.000054380896,0.00042182655,0.00010561935,0.00015577285,0.00009472807],"domain_scores_gemma":[0.99928176,0.00012693349,0.00031339232,0.000042131505,0.00016374793,0.00007204125],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034595095,0.00007302863,0.00023027335,0.0005430975,0.000016145477,0.000009837335,0.000070419774,0.000082261504,0.000013487129],"category_scores_gemma":[0.00029170446,0.00006247193,0.000040777406,0.00013668554,0.000065899876,0.00007033023,0.000013820916,0.00019896468,3.1559884e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003640555,0.000059952836,0.87291676,0.000011758114,0.00008342564,0.000007635752,0.00021777792,0.0003187208,0.02946646,0.00008254304,0.00020581328,0.09626513],"study_design_scores_gemma":[0.006688379,0.00044648588,0.93825775,0.0001332075,0.000019721057,0.000037868216,0.000013157081,0.05120042,0.0012473463,0.00010907717,0.0017989207,0.00004766651],"about_ca_topic_score_codex":0.000099449215,"about_ca_topic_score_gemma":0.0000052726577,"teacher_disagreement_score":0.09621746,"about_ca_system_score_codex":0.00012818782,"about_ca_system_score_gemma":0.00010558663,"threshold_uncertainty_score":0.25475314},"labels":[],"label_agreement":null},{"id":"W4377004088","doi":"10.59275/j.melba.2022-2d93","title":"Rethinking Generalization: The Impact of Annotation Style on Medical Image Segmentation","year":2022,"lang":"en","type":"article","venue":"The Journal of Machine Learning for Biomedical Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"NeuroRx Research (Canada); McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"Genentech; MedDay Pharmaceuticals; Royal Academy of Engineering; International Progressive MS Alliance; Compute Canada; Western Canada Research Grid; Canadian Institute for Advanced Research; Teva Pharmaceutical Industries; Biogen","keywords":"Annotation; Computer science; Context (archaeology); Segmentation; Generalization; Artificial intelligence; Machine learning; Style (visual arts); Ground truth; Automatic image annotation; Image (mathematics); Natural language processing; Image retrieval; Information retrieval; Mathematics; Geography","score_opus":0.013424928776439223,"score_gpt":0.33384529284453457,"score_spread":0.3204203640680953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4377004088","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7485507,0.0014445983,0.18443535,0.063624,0.00081049645,0.0006674146,0.000017890672,0.000058639584,0.00039090347],"genre_scores_gemma":[0.99475497,0.00012839958,0.0027819902,0.0014718222,0.00059154833,0.000010167501,0.00009895772,0.00004563849,0.00011649313],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99618953,0.00082636427,0.00083121407,0.00015012208,0.0017109764,0.0002918118],"domain_scores_gemma":[0.99718904,0.0011787725,0.00095686544,0.0002049443,0.00026576148,0.00020458893],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007355106,0.00018219333,0.00039086255,0.00029549567,0.00071834476,0.000036567093,0.00045546453,0.00004273121,0.00054564414],"category_scores_gemma":[0.0034293523,0.000095912634,0.0003541499,0.0005020382,0.00038312864,0.00011299658,0.00013734555,0.0019058317,0.0000014259085],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.007996956,0.0022193512,0.06173733,0.00054988806,0.0021167141,0.00046290117,0.033700194,0.14210358,0.1403581,0.0013800958,0.053284854,0.55409],"study_design_scores_gemma":[0.0048272144,0.0023940755,0.0063949716,0.00025875669,0.0003599918,0.0026482644,0.0010760345,0.9730359,0.00046620113,0.0011630222,0.007201214,0.0001743977],"about_ca_topic_score_codex":0.00015443403,"about_ca_topic_score_gemma":5.09462e-7,"teacher_disagreement_score":0.83093226,"about_ca_system_score_codex":0.00021679742,"about_ca_system_score_gemma":0.00034251984,"threshold_uncertainty_score":0.82799965},"labels":[],"label_agreement":null},{"id":"W4377004358","doi":"10.59275/j.melba.2022-a1cc","title":"Image quality assessment by overlapping task-specific and task-agnostic measures: application to prostate multiparametric MR images for cancer segmentation","year":2022,"lang":"en","type":"article","venue":"The Journal of Machine Learning for Biomedical Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; CRIS Cancer Foundation; University of Manchester; National Cancer Institute; University College London; National Institutes of Health; Wellcome / EPSRC Centre for Interventional and Surgical Sciences; Engineering and Physical Sciences Research Council; Prostate Cancer Foundation; University of Cambridge; Cancer Research UK; Knight Cancer Institute, Oregon Health and Science University; Oregon Health and Science University","keywords":"Task (project management); Computer science; Image quality; Quality (philosophy); Artificial intelligence; Segmentation; Image (mathematics)","score_opus":0.016699404896214097,"score_gpt":0.3522393019801811,"score_spread":0.33553989708396703,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4377004358","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10092634,0.004659513,0.8616635,0.030495225,0.00038370874,0.001662496,0.00013344146,0.000052988642,0.00002275045],"genre_scores_gemma":[0.9403094,0.000926034,0.05525534,0.0021724424,0.00045244227,0.00035066466,0.00026116066,0.000089762434,0.00018274187],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99678355,0.00047780827,0.0009116972,0.00034447166,0.0010259005,0.000456593],"domain_scores_gemma":[0.99669707,0.0015890588,0.0008348412,0.00019576824,0.00032191206,0.00036136134],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006535632,0.00025280667,0.0005515207,0.0004226456,0.0008499187,0.00010220631,0.00028811817,0.000036150785,0.000032123222],"category_scores_gemma":[0.0022395928,0.00018709438,0.00017329626,0.0005567205,0.00022226582,0.00016392366,0.00016128071,0.0012404151,8.2869576e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001172044,0.00035587157,0.014454657,0.00037363876,0.00023453761,0.000011551929,0.0016213144,0.0041221487,0.58338666,0.000037488728,0.016670994,0.3775591],"study_design_scores_gemma":[0.009867566,0.0015564375,0.011311098,0.00030086635,0.0006869336,0.00051920896,0.0020560827,0.56795335,0.0009301468,0.00031920066,0.40397516,0.0005239626],"about_ca_topic_score_codex":0.00024728756,"about_ca_topic_score_gemma":9.942406e-7,"teacher_disagreement_score":0.83938307,"about_ca_system_score_codex":0.0004053439,"about_ca_system_score_gemma":0.0001666227,"threshold_uncertainty_score":0.76294875},"labels":[],"label_agreement":null},{"id":"W4377094556","doi":"10.1007/s11604-023-01445-8","title":"Radioproteomics modeling of metformin-enhanced radiosensitivity: an animal study","year":2023,"lang":"en","type":"article","venue":"Japanese Journal of Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency","funders":"Ahvaz Jundishapur University of Medical Sciences","keywords":"Metformin; Radiosensitivity; Radiation tolerance; Radiation therapy; Medicine; Computer science; Oncology; Internal medicine","score_opus":0.0258712725299627,"score_gpt":0.32741021627927247,"score_spread":0.3015389437493098,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4377094556","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9947788,0.00007901369,0.003777959,0.0006373114,0.00025505773,0.00028189147,8.005352e-7,0.000046090277,0.0001430757],"genre_scores_gemma":[0.9955394,0.00007278132,0.0037334424,0.00014614467,0.00043777443,0.000003793078,0.0000041513626,0.000030708496,0.000031775497],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99789464,0.00028148806,0.0008634571,0.00022039519,0.00038083154,0.0003592099],"domain_scores_gemma":[0.998498,0.00021830651,0.00040730587,0.0002799368,0.00030052554,0.00029592073],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028456468,0.0001757225,0.0009601125,0.00053115544,0.00008217708,0.000010609225,0.00020521066,0.00009666868,0.000022133088],"category_scores_gemma":[0.0010532206,0.0001331068,0.00019866365,0.0004910193,0.00014477962,0.00022147346,0.00004407885,0.00063386397,0.0000058389987],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0023624664,0.00067962334,0.025224172,0.00006259014,0.00046089943,0.0016637474,0.01029506,0.034999426,0.91399026,0.00010244271,0.00008660558,0.010072724],"study_design_scores_gemma":[0.008860036,0.009800984,0.03721092,0.00010236599,0.00039558357,0.026934782,0.012626738,0.89505875,0.00824575,0.0004166387,0.00004793255,0.00029949486],"about_ca_topic_score_codex":0.000037875518,"about_ca_topic_score_gemma":0.000001975286,"teacher_disagreement_score":0.9057445,"about_ca_system_score_codex":0.000065708125,"about_ca_system_score_gemma":0.00012821468,"threshold_uncertainty_score":0.5427938},"labels":[],"label_agreement":null},{"id":"W4377989430","doi":"10.1148/ryai.220232","title":"A Guide to Cross-Validation for Artificial Intelligence in Medical Imaging","year":2023,"lang":"en","type":"review","venue":"Radiology Artificial Intelligence","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":207,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Society of Nuclear Medicine and Molecular Imaging","keywords":"Hyperparameter; Convolutional neural network; Artificial intelligence; Machine learning; Field (mathematics); Artificial neural network; Selection (genetic algorithm); Medicine; Computer science","score_opus":0.10014074641117186,"score_gpt":0.4829447736101836,"score_spread":0.38280402719901174,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4377989430","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00006206585,0.49961552,0.4889828,0.0039716163,0.00309086,0.0033764285,0.000050254574,0.00034707383,0.0005033814],"genre_scores_gemma":[0.00024110645,0.984997,0.0077819703,0.001139873,0.0032109474,0.001082319,0.00039864535,0.00026489262,0.00088327186],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99300414,0.0004260108,0.0032070517,0.0014889808,0.00067103404,0.0012028044],"domain_scores_gemma":[0.9952793,0.002570184,0.00048055963,0.00074267236,0.00025488692,0.0006723619],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0048467014,0.0007153359,0.002696137,0.001286846,0.00023064933,0.00013675544,0.00092971977,0.0008400144,0.00049621],"category_scores_gemma":[0.01658091,0.0006418227,0.00071087736,0.0015594783,0.0006416354,0.00010599176,0.00026940447,0.0018982849,0.0014482078],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000996504,0.00011960443,0.000023849887,0.0028780038,0.00009559378,0.00043271005,0.00016451176,0.00031238978,0.000008816275,0.013640197,0.0010804654,0.9811442],"study_design_scores_gemma":[0.00007127442,0.00028028947,0.00000876888,0.014085573,0.000512269,0.0012401727,0.0001864769,0.07954095,0.00014061571,0.015059906,0.88785976,0.0010139614],"about_ca_topic_score_codex":0.00017697722,"about_ca_topic_score_gemma":0.00007053543,"teacher_disagreement_score":0.98013026,"about_ca_system_score_codex":0.0004918005,"about_ca_system_score_gemma":0.0012322798,"threshold_uncertainty_score":0.99960333},"labels":[],"label_agreement":null},{"id":"W4378349117","doi":"10.3390/curroncol30050372","title":"Radiomics and Radiogenomics in Pelvic Oncology: Current Applications and Future Directions","year":2023,"lang":"en","type":"review","venue":"Current Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Radiogenomics; Radiomics; Medicine; Precision medicine; Medical physics; Bioinformatics; Intensive care medicine; Internal medicine; Pathology; Radiology","score_opus":0.10403937062574724,"score_gpt":0.46463487696997413,"score_spread":0.3605955063442269,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378349117","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00009212596,0.9928879,0.00015605624,0.0013775737,0.002978668,0.0018743287,0.000051028434,0.00012411327,0.0004581897],"genre_scores_gemma":[0.0000019817853,0.9949825,0.00059767545,0.000059341663,0.0029868323,0.0007899266,0.00041285262,0.00009560712,0.00007331298],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973352,0.00032536197,0.0009076413,0.00079751195,0.00015184097,0.00048243217],"domain_scores_gemma":[0.99808675,0.0006601042,0.00040880882,0.00036911553,0.00005711354,0.00041812615],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0007751339,0.00046653577,0.0023931076,0.00081656483,0.00016084901,0.00003197426,0.00018669042,0.00054860057,0.000016773354],"category_scores_gemma":[0.00018290844,0.00040538667,0.00024181153,0.00071095186,0.00038487744,0.000040013172,0.0002170172,0.002612319,0.000041015915],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010046727,0.00028918378,0.00022233797,0.00934097,0.00010339525,0.000035622477,0.00022537468,2.6532194e-7,2.391017e-7,0.000626981,0.0015370187,0.98760855],"study_design_scores_gemma":[0.0011194327,0.00015263632,0.00016388037,0.00266353,0.0012298333,0.00096769683,0.000072547955,0.00039423766,1.4192197e-8,0.00016792167,0.99275976,0.00030852214],"about_ca_topic_score_codex":0.000011106288,"about_ca_topic_score_gemma":0.00002363636,"teacher_disagreement_score":0.99122274,"about_ca_system_score_codex":0.001041151,"about_ca_system_score_gemma":0.0011219956,"threshold_uncertainty_score":0.9998398},"labels":[],"label_agreement":null},{"id":"W4378516260","doi":"10.3390/diagnostics13101696","title":"Deep versus Handcrafted Tensor Radiomics Features: Prediction of Survival in Head and Neck Cancer Using Machine Learning and Fusion Techniques","year":2023,"lang":"en","type":"article","venue":"Diagnostics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":83,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Random forest; Artificial intelligence; Pattern recognition (psychology); Computer science; Radiomics; Tensor (intrinsic definition); Perceptron; Feature selection; Mathematics; Machine learning; Artificial neural network","score_opus":0.020869223679700014,"score_gpt":0.31942667448123385,"score_spread":0.29855745080153384,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378516260","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9953064,0.0027963459,0.00052192574,0.0006202851,0.00029624777,0.00024982693,0.000018510833,0.00010962202,0.00008083662],"genre_scores_gemma":[0.9608949,0.032700285,0.0057874834,0.00010548764,0.0002414833,0.000016793107,0.00012473878,0.00004996876,0.00007885181],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990555,0.000059183014,0.00024396875,0.00022448914,0.00020009054,0.00021673557],"domain_scores_gemma":[0.99908245,0.0005673003,0.00008441928,0.00009112456,0.00006179375,0.00011290219],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033050662,0.00013641559,0.00032819484,0.00025629852,0.00008377976,0.000018285808,0.00003649727,0.00011912121,0.000007293642],"category_scores_gemma":[0.0021949525,0.0001241786,0.000028222576,0.00034933048,0.000117207754,0.00004466397,0.00007358375,0.0004709657,3.6274818e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003244762,0.00004985968,0.95914704,0.00020956586,0.00003901637,0.00008575316,0.00059391104,0.00054368743,0.0082736965,0.00003814091,0.00010776141,0.030587103],"study_design_scores_gemma":[0.004231758,0.00043604046,0.47748986,0.0010368738,0.0001707407,0.000049030088,0.00026938648,0.51213425,0.0013589567,0.000050160343,0.002603445,0.00016948697],"about_ca_topic_score_codex":0.0009275351,"about_ca_topic_score_gemma":0.0001495366,"teacher_disagreement_score":0.5115906,"about_ca_system_score_codex":0.00005946477,"about_ca_system_score_gemma":0.00004207592,"threshold_uncertainty_score":0.50638556},"labels":[],"label_agreement":null},{"id":"W4378527617","doi":"10.32920/22734398","title":"A Novel Focal Tversky Loss Function with Improved Attention U-Net for Lesion Segmentation","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Segmentation; Dice; Pyramid (geometry); Function (biology); Image (mathematics); Artificial intelligence; Image segmentation; Computer science; Pattern recognition (psychology); Mathematics; Statistics; Geometry; Biology","score_opus":0.03454703525850763,"score_gpt":0.3225866770157166,"score_spread":0.288039641757209,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378527617","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11115694,0.000018333345,0.88122064,0.0043473975,0.0010939118,0.0015445829,0.000019278334,0.0003239597,0.0002749477],"genre_scores_gemma":[0.75786,0.00019148679,0.20561309,0.0023690823,0.0022912,0.0009915421,0.007426234,0.0003306406,0.022926731],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984125,0.000021856544,0.0003438012,0.0005980457,0.00034829677,0.00027553205],"domain_scores_gemma":[0.99907476,0.00008759207,0.0002201222,0.0002896629,0.00018048317,0.00014736375],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047216332,0.00026127367,0.00037667598,0.00019399704,0.00010880893,0.000067691195,0.00008114034,0.00025438398,0.00003628408],"category_scores_gemma":[0.00013760148,0.00019899389,0.0001758277,0.00011464552,0.000065677865,0.00006564194,0.00012375526,0.00066300307,0.000019467714],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.009619847,0.0013654435,0.026540084,0.008293996,0.0023850554,0.000081828555,0.0006372038,0.0067281146,0.65724057,0.0018955384,0.028708043,0.25650427],"study_design_scores_gemma":[0.015539912,0.0023957929,0.06468819,0.0019285331,0.00197559,0.00014372013,0.00065746205,0.9042438,0.0018371119,0.0013847186,0.004368674,0.00083649246],"about_ca_topic_score_codex":0.00037207748,"about_ca_topic_score_gemma":0.000038829654,"teacher_disagreement_score":0.8975157,"about_ca_system_score_codex":0.00017926787,"about_ca_system_score_gemma":0.00016124245,"threshold_uncertainty_score":0.8114735},"labels":[],"label_agreement":null},{"id":"W4378574305","doi":"10.1093/noajnl/vdad064","title":"Dual-center validation of using magnetic resonance imaging radiomics to predict stereotactic radiosurgery outcomes","year":2023,"lang":"en","type":"article","venue":"Neuro-Oncology Advances","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"London Health Sciences Centre; Cancer Care Ontario; Western University","funders":"Natural Sciences and Engineering Research Council of Canada; London Health Sciences Foundation; Government of Ontario","keywords":"Receiver operating characteristic; Random forest; Artificial intelligence; Radiomics; Radiosurgery; Computer science; Pooling; Magnetic resonance imaging; Machine learning; Medical physics; Medicine; Radiology; Radiation therapy","score_opus":0.01885037955117271,"score_gpt":0.3303753260081721,"score_spread":0.3115249464569994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378574305","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98883265,0.0016180649,0.0007448048,0.0059999297,0.0017946162,0.0004383504,0.000013326509,0.00017894772,0.0003792855],"genre_scores_gemma":[0.9903711,0.0006075528,0.0049941167,0.0034284927,0.00030929313,0.000030614337,0.000028946737,0.00006797818,0.0001618773],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9979529,0.00019107536,0.00058185996,0.00045338258,0.00035732862,0.0004634584],"domain_scores_gemma":[0.9982393,0.0008928174,0.00022175378,0.00034156424,0.000096557545,0.00020801017],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005714918,0.00021815661,0.00063026877,0.00044618302,0.000108429565,0.000017922093,0.0001342048,0.000071841736,0.00004369934],"category_scores_gemma":[0.0017380724,0.00019748344,0.00013212844,0.0006090041,0.00019843306,0.00022305365,0.00010495189,0.00039926922,0.0000261175],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019742738,0.00011827365,0.8475926,0.000113673996,0.00001797407,0.00051227765,0.0002432609,0.0011757538,0.04454115,0.00003666347,0.0009808363,0.10447009],"study_design_scores_gemma":[0.008725715,0.0012174597,0.45724222,0.0005692692,0.00046134568,0.0027219509,0.00040194273,0.08877991,0.01197044,0.00038599744,0.42674395,0.0007798074],"about_ca_topic_score_codex":0.00001740652,"about_ca_topic_score_gemma":0.0000012073405,"teacher_disagreement_score":0.4257631,"about_ca_system_score_codex":0.00015097704,"about_ca_system_score_gemma":0.00013807093,"threshold_uncertainty_score":0.8053141},"labels":[],"label_agreement":null},{"id":"W4378611118","doi":"10.1101/2023.05.23.23290415","title":"Artificial intelligence-based histopathology image analysis identifies a novel subset of endometrial cancers with distinct genomic features and unfavourable outcome","year":2023,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; Vancouver General Hospital; BC Cancer Agency; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Michael Smith Health Research BC","keywords":"Histopathology; Cohort; Internal medicine; Oncology; Endometrial cancer; Cancer; Biology; Computational biology; Pathology; Medicine","score_opus":0.04559969035330126,"score_gpt":0.33031756896404,"score_spread":0.2847178786107388,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378611118","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9366313,0.0004480132,0.05948092,0.0018371425,0.0008052575,0.00044808857,0.00015524744,0.00009686272,0.000097136755],"genre_scores_gemma":[0.9920019,0.000081164006,0.00670229,0.000104119375,0.0002709944,0.000051431598,0.0002884038,0.00006650285,0.00043320967],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99732625,0.00012509247,0.00086326274,0.0007966024,0.0004961503,0.0003926163],"domain_scores_gemma":[0.99788314,0.000524322,0.0005796344,0.0006358761,0.00016661464,0.0002104159],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0014062342,0.0003779222,0.0014698592,0.0013584223,0.00009990106,0.00007334866,0.00029950918,0.00022937352,0.000077326826],"category_scores_gemma":[0.0019672145,0.00029711353,0.00035778276,0.0009262472,0.0007433613,0.000029333603,0.00024487943,0.0012150201,0.0000052634327],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011807323,0.00015284213,0.95502096,0.0011841588,0.0013654367,0.00054270204,0.00056931056,0.010582724,0.026654469,0.00014481947,0.00016909387,0.0024327564],"study_design_scores_gemma":[0.0011808668,0.00031978727,0.94622433,0.00039125187,0.0064321673,0.000083756815,0.00022977663,0.040020056,0.0036199577,0.0007386356,0.00015473267,0.0006046757],"about_ca_topic_score_codex":0.0028026649,"about_ca_topic_score_gemma":0.00081820774,"teacher_disagreement_score":0.055370554,"about_ca_system_score_codex":0.00023750088,"about_ca_system_score_gemma":0.000403616,"threshold_uncertainty_score":0.9999481},"labels":[],"label_agreement":null},{"id":"W4378801059","doi":"10.1016/s2589-7500(23)00082-1","title":"Predicting benefit from immune checkpoint inhibitors in patients with non-small-cell lung cancer by CT-based ensemble deep learning: a retrospective study","year":2023,"lang":"en","type":"article","venue":"The Lancet Digital Health","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":109,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of Biomedical Imaging and Bioengineering; National Cancer Institute; NGM Biopharmaceuticals; Novartis Institutes for BioMedical Research; University of Texas MD Anderson Cancer Center; EMD Serono; AstraZeneca; Genentech; NIH Clinical Center; Sun Pharma; Amgen; STCube; Daiichi Sankyo Europe; Innovent Biologics; European Society for Medical Oncology; Université de Montréal; Clovis Oncology; Bayer HealthCare; Astellas Pharma; Rexanna's Foundation; Seagen; MacroGenics; Jounce Therapeutics; ViewRay; Ribon Therapeutics; BeiGene; Helsinn; Mirati Therapeutics; American College of Radiology Imaging Network; Society for Immunotherapy of Cancer; Jazz Pharmaceuticals; Conquer Cancer Foundation; National Institutes of Health; Natera; RefleXion Medical; Regeneron Pharmaceuticals; McGill University; Merck KGaA; Varian Medical Systems; Damon Runyon Cancer Research Foundation; ECOG-ACRIN Cancer Research Group; Eli Lilly and Company; Calithera Biosciences; Gilead Sciences; Exelixis; Sanofi; Arrowhead Pharmaceuticals; Foundation Medicine; GlaxoSmithKline; Bristol-Myers Squibb; Moderna; Pfizer","keywords":"Medicine; Context (archaeology); Immune checkpoint; Lung cancer; Oncology; Internal medicine; Univariate analysis; Cancer; Retrospective cohort study; Multivariate analysis; Immunotherapy; Biology","score_opus":0.008714826560307552,"score_gpt":0.27456030735523634,"score_spread":0.2658454807949288,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378801059","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9942808,0.0004399527,0.00010497758,0.0028383727,0.00015847455,0.001245057,0.000047049914,0.00019061739,0.0006946963],"genre_scores_gemma":[0.9983934,0.000054753342,0.00006107496,0.0005580079,0.0002576404,0.00008830988,0.00025945326,0.00006769933,0.0002596553],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9978032,0.000074074516,0.00048485567,0.00044692008,0.0005142309,0.00067671173],"domain_scores_gemma":[0.9989226,0.00016550909,0.00028944798,0.00035169336,0.00007022125,0.00020056355],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00069975044,0.00024138814,0.000676003,0.00011126226,0.00021117483,0.00008829986,0.00019019413,0.000035971974,0.000011787894],"category_scores_gemma":[0.00019715916,0.00016403383,0.00006420188,0.0006028001,0.00006455849,0.00010390353,0.0000943148,0.0010885982,0.000010635458],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031886992,0.00039822594,0.9863337,0.00011068213,0.000057089484,0.00002342249,0.0024051028,0.0011717014,0.000031422267,0.000001068856,0.0003993256,0.008749391],"study_design_scores_gemma":[0.0080049895,0.0009450278,0.9480462,0.00060087146,0.00003590765,9.683184e-7,0.0010695098,0.040880647,0.00007325732,0.00002598533,0.00014264391,0.00017400582],"about_ca_topic_score_codex":0.004653665,"about_ca_topic_score_gemma":0.00025462956,"teacher_disagreement_score":0.039708942,"about_ca_system_score_codex":0.0003711421,"about_ca_system_score_gemma":0.00018764062,"threshold_uncertainty_score":0.703498},"labels":[],"label_agreement":null},{"id":"W4378831192","doi":"10.51642/ppmj.v27i3.122","title":"DIAGNOSTIC ADEQUACY AND SAFETY OF IMAGE GUIDED TRU-CUT BIOPSY","year":2016,"lang":"en","type":"article","venue":"Pakistan Postgraduate Medical Journal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Continental (Canada)","funders":"","keywords":"Medicine; Biopsy; Radiology; Retrospective cohort study; Surgery","score_opus":0.012462856506459057,"score_gpt":0.32330337826764555,"score_spread":0.3108405217611865,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378831192","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8587778,0.0013015986,0.04327202,0.09187221,0.0007209872,0.00032750575,0.000028998315,0.000081906896,0.0036169668],"genre_scores_gemma":[0.98867947,0.004336292,0.0045167385,0.0012378641,0.00066410546,0.0000036669603,0.0000074681097,0.00005069926,0.0005037187],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99664193,0.00020639683,0.0010662492,0.00030535914,0.0012586282,0.000521424],"domain_scores_gemma":[0.99638855,0.0014000928,0.0003307636,0.00027214296,0.00026104003,0.0013474287],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0019759808,0.00024914226,0.000631112,0.00020799301,0.00015789113,0.0000434592,0.0002477414,0.00014315285,0.0010476677],"category_scores_gemma":[0.012230658,0.00014265912,0.00018775451,0.00019512602,0.0008824334,0.000134684,0.00010632032,0.0008174264,0.00003068951],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012257991,0.00061369495,0.11076869,0.00052072015,0.0006144736,0.009069989,0.0007983204,5.8207e-7,0.04100773,0.004399663,0.020445349,0.810535],"study_design_scores_gemma":[0.064227834,0.0035304402,0.55696636,0.020827072,0.0018978855,0.17376366,0.0009081467,0.0041259145,0.009659839,0.021870954,0.13996476,0.0022571061],"about_ca_topic_score_codex":0.000039180315,"about_ca_topic_score_gemma":0.0000017803229,"teacher_disagreement_score":0.8082779,"about_ca_system_score_codex":0.00009864978,"about_ca_system_score_gemma":0.00040926924,"threshold_uncertainty_score":0.99986553},"labels":[],"label_agreement":null},{"id":"W4379280924","doi":"10.1200/jco.2023.41.16_suppl.e21076","title":"Serum tumor biomarkers as a surrogate for radiographic assessment of non-small cell lung cancer.","year":2023,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"London Health Sciences Centre; Western University","funders":"","keywords":"Medicine; Internal medicine; Lung cancer; Surrogate endpoint; Stage (stratigraphy); Response Evaluation Criteria in Solid Tumors; Population; Gastroenterology; Cancer; Oncology; Regimen; Progressive disease; Surgery; Disease","score_opus":0.0543517897463957,"score_gpt":0.4895864810916594,"score_spread":0.4352346913452637,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379280924","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97566926,0.0005369861,0.0017099397,0.017327204,0.0025322987,0.0004093674,0.000008071076,0.000018675184,0.0017881775],"genre_scores_gemma":[0.9783435,0.0025732475,0.015251488,0.0023739499,0.0010509886,0.000017349399,0.0000041562503,0.000035714354,0.0003496127],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9965992,0.000282521,0.0021744785,0.00021650056,0.00037228764,0.00035498952],"domain_scores_gemma":[0.99365956,0.003276412,0.0019727356,0.00017760189,0.0004186407,0.00049504265],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0075188763,0.0001479526,0.0015592366,0.00039193244,0.00005258705,0.000008663271,0.00024143637,0.00021274776,0.00008067253],"category_scores_gemma":[0.0028431076,0.00010930172,0.0009095193,0.0004716411,0.00023971044,0.00004934234,0.000057911573,0.0010840219,0.0000025974034],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016930235,0.0010077874,0.84682506,0.00069821475,0.0014185279,0.0011053081,0.00011620932,0.00043526303,0.003480218,0.00006825013,0.025981221,0.11717091],"study_design_scores_gemma":[0.020345803,0.010750435,0.80770385,0.00076993223,0.0014905663,0.0002856684,0.0002624941,0.11342451,0.00023175999,0.00029537643,0.04424648,0.00019314898],"about_ca_topic_score_codex":0.00007231598,"about_ca_topic_score_gemma":0.000011578772,"teacher_disagreement_score":0.11697776,"about_ca_system_score_codex":0.00010179552,"about_ca_system_score_gemma":0.0027363517,"threshold_uncertainty_score":0.48541704},"labels":[],"label_agreement":null},{"id":"W4379280931","doi":"10.1200/jco.2023.41.16_suppl.e18824","title":"Utility of Brock model for risk stratification in patients with high-risk pulmonary nodules: A single center study.","year":2023,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Medicine; Nodule (geology); Malignancy; Lung cancer; Lung cancer screening; Radiology; Radiological weapon; Population; Lung; Receiver operating characteristic; Internal medicine","score_opus":0.07433639514919821,"score_gpt":0.4188765587079318,"score_spread":0.34454016355873357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379280931","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9937342,0.000012176227,0.004693453,0.0006748885,0.00030205867,0.00045000287,0.00001721922,0.000009005328,0.00010699031],"genre_scores_gemma":[0.99348795,0.00007094454,0.0060146865,0.00013827323,0.0001861435,0.000004838093,0.000016031798,0.000015942993,0.000065190026],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9969826,0.00040484307,0.0018708978,0.00020086393,0.0003592361,0.00018160028],"domain_scores_gemma":[0.9959632,0.0014402601,0.0018121618,0.00019094802,0.0004183039,0.00017514007],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027383498,0.0000999843,0.0009454762,0.00015906927,0.000033300686,0.0000048958923,0.00013301166,0.0001544067,0.00000939743],"category_scores_gemma":[0.0060294634,0.00006673332,0.00018468245,0.00018697354,0.00012783533,0.00007787364,0.000031915188,0.0009766631,0.0000017638063],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0042052763,0.0075162738,0.86698526,0.000033214674,0.00011894294,0.000022836328,0.00014652804,0.0012850385,0.00001615714,0.000005524641,0.0005944089,0.11907052],"study_design_scores_gemma":[0.010172834,0.009062699,0.849559,0.0000739879,0.00021002258,0.000005938341,0.00016743498,0.12998788,0.0000026264786,0.0005163298,0.00019138194,0.00004984166],"about_ca_topic_score_codex":0.000048380134,"about_ca_topic_score_gemma":0.000058363992,"teacher_disagreement_score":0.12870285,"about_ca_system_score_codex":0.000043650172,"about_ca_system_score_gemma":0.0002981229,"threshold_uncertainty_score":0.7218266},"labels":[],"label_agreement":null},{"id":"W4379281468","doi":"10.1200/jco.2023.41.16_suppl.6005","title":"Dose expansion results of the bifunctional EGFR/TGFβ inhibitor BCA101 with pembrolizumab in patients with recurrent, metastatic head and neck squamous cell carcinoma.","year":2023,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre","funders":"","keywords":"Medicine; Pembrolizumab; Internal medicine; Clinical endpoint; Oncology; Head and neck squamous-cell carcinoma; Cohort; Progression-free survival; Response Evaluation Criteria in Solid Tumors; Head and neck cancer; Progressive disease; Chemotherapy; Cancer; Clinical trial; Immunotherapy","score_opus":0.044206503035995014,"score_gpt":0.3784376208988284,"score_spread":0.3342311178628334,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379281468","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99340636,0.00011275623,0.000024806135,0.005086885,0.00068324234,0.00023534533,0.000005502694,0.000006259773,0.0004388325],"genre_scores_gemma":[0.9974028,0.00005539818,0.0015607128,0.00055310735,0.00026532452,0.000002386335,0.000008152291,0.000018132578,0.00013400232],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9969894,0.00044294042,0.0015381031,0.00021110114,0.0005985683,0.00021983442],"domain_scores_gemma":[0.9962861,0.0016865677,0.001292388,0.0001787906,0.00030569694,0.00025046166],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021574234,0.00013525199,0.0009021252,0.00019613406,0.00004578803,0.0000068589025,0.000117807125,0.00011782166,0.000011369929],"category_scores_gemma":[0.0033160509,0.00006747955,0.00013697355,0.000384115,0.0003103173,0.000079612466,0.0000661454,0.0013235116,0.0000023036084],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.033376664,0.0018902221,0.9271731,0.00012437285,0.00006554203,0.00028913657,0.0003126288,0.00043779422,0.000053345262,0.000012265005,0.0037366885,0.032528237],"study_design_scores_gemma":[0.0477602,0.01752898,0.9293714,0.0002727166,0.00020282192,0.00009920522,0.00010786338,0.001243961,0.000014175279,0.000046721743,0.0032797374,0.000072193645],"about_ca_topic_score_codex":0.00004701794,"about_ca_topic_score_gemma":0.000037873328,"teacher_disagreement_score":0.032456044,"about_ca_system_score_codex":0.00007997608,"about_ca_system_score_gemma":0.00095614797,"threshold_uncertainty_score":0.57500726},"labels":[],"label_agreement":null},{"id":"W4379281866","doi":"10.1200/jco.2023.41.16_suppl.5023","title":"Clinical analysis of optimized neural network risk models to predict clinically significant prostate cancer and avoid unnecessary prostate biopsies.","year":2023,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University; University of Calgary; University of Alberta; Princess Margaret Cancer Centre; University of Toronto; University Health Network","funders":"Prostate Cancer Canada","keywords":"Medicine; Overdiagnosis; Prostate cancer; Cohort; Cancer; Internal medicine; Artificial neural network; Oncology; Artificial intelligence","score_opus":0.07760661196714504,"score_gpt":0.4543973577004853,"score_spread":0.37679074573334026,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379281866","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9722059,0.0005596374,0.0018614787,0.022372102,0.0019960105,0.0006016721,0.000053443084,0.00005193651,0.00029784776],"genre_scores_gemma":[0.94401735,0.02776885,0.021107651,0.0046264376,0.0019847744,0.0000210661,0.000024386867,0.000056592522,0.0003928618],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98885196,0.0017342571,0.0074007004,0.0006043485,0.0007765299,0.0006322208],"domain_scores_gemma":[0.9829201,0.009983931,0.0044473168,0.00041744404,0.0008183988,0.0014128104],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.02483762,0.00029536997,0.0044277175,0.0005684158,0.00010536442,0.000027952956,0.0003791733,0.0005295242,0.0000637479],"category_scores_gemma":[0.014571856,0.00020480841,0.0013849827,0.0017273689,0.0008474694,0.00015862969,0.00028103436,0.0031785981,0.00000594904],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008582975,0.0005473251,0.52433276,0.000051800445,0.0035247712,0.00045844575,0.00024635138,0.27532628,0.000021560138,0.000015123158,0.009469282,0.17742333],"study_design_scores_gemma":[0.008144374,0.0073729404,0.41264966,0.00022617642,0.0056053433,0.000027885428,0.00013665274,0.560079,0.0000014720114,0.00046017903,0.005120368,0.00017594975],"about_ca_topic_score_codex":0.0001372348,"about_ca_topic_score_gemma":0.000018224973,"teacher_disagreement_score":0.28475273,"about_ca_system_score_codex":0.000066674846,"about_ca_system_score_gemma":0.0014980226,"threshold_uncertainty_score":0.9991211},"labels":[],"label_agreement":null},{"id":"W4379282977","doi":"10.1200/jco.2023.41.16_suppl.tps5103","title":"SWOG S1823/CCTG GCC1: Translational observational investigational study of the liquid biomarker microRNA 371a-3p in newly diagnosed germ cell tumours—Real-world trial design, rapid accrual, and robust secondary use of data opportunities.","year":2023,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of British Columbia; University Health Network","funders":"","keywords":"Medicine; Observational study; Interim analysis; Biomarker; Oncology; Interim; Internal medicine; Clinical trial; Seminoma; Chemotherapy","score_opus":0.5887588118999613,"score_gpt":0.48082834315819845,"score_spread":0.10793046874176282,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379282977","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97888553,0.00014568084,0.0002690985,0.018910898,0.00088491786,0.0006727744,0.00006082338,0.000008562221,0.00016174192],"genre_scores_gemma":[0.98621815,0.0008344889,0.009706227,0.002053587,0.0007961785,0.000009729157,0.00013131565,0.00003229538,0.0002180239],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99341005,0.0017014069,0.0035274625,0.00031196047,0.0008096886,0.00023940713],"domain_scores_gemma":[0.98276746,0.01361301,0.0025020663,0.00036502138,0.00041583166,0.00033662794],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00954286,0.0001906374,0.0013372363,0.00042294626,0.00007206386,0.000019184266,0.00049173285,0.00022535212,0.00018843931],"category_scores_gemma":[0.0076587508,0.00013502667,0.00023508945,0.00053424167,0.0006634665,0.000386766,0.00020089763,0.00141781,9.161367e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0877814,0.010885484,0.73222345,0.00028622744,0.0010923464,0.0013340296,0.0017743785,0.0078322105,0.0029916398,0.00023612226,0.07614675,0.07741599],"study_design_scores_gemma":[0.057765234,0.0053158505,0.91312534,0.00018200709,0.00036780996,0.000055426794,0.00034510548,0.015152217,0.000033969864,0.00020108541,0.0073269573,0.00012898378],"about_ca_topic_score_codex":0.0001678127,"about_ca_topic_score_gemma":0.00014947118,"teacher_disagreement_score":0.18090193,"about_ca_system_score_codex":0.000054719592,"about_ca_system_score_gemma":0.0047823805,"threshold_uncertainty_score":0.91687936},"labels":[],"label_agreement":null},{"id":"W4379285617","doi":"10.1200/jco.2023.41.16_suppl.e13616","title":"Design, reporting, and disparities of advanced non–small cell lung cancer phase 3 clinical trials in the era of immunotherapy.","year":2023,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kingston Health Sciences Centre","funders":"","keywords":"Medicine; Clinical trial; Lung cancer; Population; Internal medicine; Ethnic group; Oncology; Family medicine; Environmental health","score_opus":0.21021761547945003,"score_gpt":0.5775891799436152,"score_spread":0.3673715644641652,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379285617","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9804824,0.0030134015,0.002422571,0.012460695,0.0010489434,0.0003849731,0.0000019327758,0.0000051416782,0.00017994145],"genre_scores_gemma":[0.96692765,0.021788187,0.008249814,0.0021548711,0.00074488146,0.000009822827,0.0000015431683,0.000018557575,0.00010467418],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9863124,0.0030412772,0.009909947,0.00017734418,0.00034208316,0.00021693346],"domain_scores_gemma":[0.9600056,0.026693434,0.012579491,0.00023659709,0.00029956436,0.00018534875],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.080951765,0.00011985089,0.003103958,0.00012884311,0.00002769299,0.000006989175,0.00020913588,0.00026627164,0.000040077237],"category_scores_gemma":[0.06536782,0.000068412985,0.00060418417,0.00022173846,0.00040963409,0.000051568903,0.000042822885,0.0020484019,3.7934012e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0061478484,0.0018101766,0.33927667,0.00022097763,0.0003747153,0.00068035204,0.0008257054,0.00042218462,0.004746552,0.000019728544,0.0044685067,0.6410066],"study_design_scores_gemma":[0.07287901,0.023256758,0.84792113,0.0023679107,0.001479034,0.00039500874,0.0013504962,0.028899794,0.0009544462,0.0010194636,0.019206846,0.00027010805],"about_ca_topic_score_codex":0.00007731251,"about_ca_topic_score_gemma":0.000008814609,"teacher_disagreement_score":0.64073646,"about_ca_system_score_codex":0.000027479973,"about_ca_system_score_gemma":0.0012868774,"threshold_uncertainty_score":0.94635355},"labels":[],"label_agreement":null},{"id":"W4379328789","doi":"10.1200/jco.2023.41.16_suppl.1557","title":"An intelligent machine learning model for real-time early detection of undesirable cancer events: AIM2REDUCE.","year":2023,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Princess Margaret Cancer Centre","funders":"","keywords":"Medicine; Interquartile range; Cohort; Cancer registry; Cancer; Nomogram; Internal medicine","score_opus":0.12583964316569932,"score_gpt":0.494114734523482,"score_spread":0.3682750913577827,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379328789","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9586933,0.00013912625,0.03655091,0.0032988633,0.0008359383,0.00020402961,0.0000036010013,0.00003506595,0.00023915208],"genre_scores_gemma":[0.98773706,0.0024974938,0.006832141,0.00037182219,0.0008917566,0.000007899059,0.000007022059,0.000036235386,0.001618584],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971346,0.00032229465,0.0017704173,0.0001871037,0.0003273148,0.0002582347],"domain_scores_gemma":[0.99636525,0.0013344015,0.0013701874,0.00013930336,0.00042502026,0.00036585832],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0055381632,0.00011787696,0.0010931017,0.00022608979,0.0000656611,0.0000062496574,0.00016587964,0.00025620928,0.00006409141],"category_scores_gemma":[0.0044267825,0.000089657755,0.00041346613,0.00021391344,0.000110213135,0.000111676185,0.000031157157,0.0011571796,0.000009425306],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0054699066,0.0013180784,0.052587297,0.00016342806,0.00064192864,0.00008460845,0.000523186,0.0835761,0.06618474,0.00008927633,0.0010571684,0.78830427],"study_design_scores_gemma":[0.0035657194,0.008960066,0.023719817,0.0001749794,0.00036890362,0.00005528981,0.00008066813,0.9566592,0.0007027427,0.0013701747,0.0042469073,0.00009554049],"about_ca_topic_score_codex":0.00019411644,"about_ca_topic_score_gemma":0.000016254296,"teacher_disagreement_score":0.8730831,"about_ca_system_score_codex":0.00013611517,"about_ca_system_score_gemma":0.0008115041,"threshold_uncertainty_score":0.5299592},"labels":[],"label_agreement":null},{"id":"W4379332778","doi":"10.1200/jco.2023.41.16_suppl.5035","title":"Digital histopathology-based multimodal artificial intelligence scores predict risk of progression in a randomized phase III trial in patients with nonmetastatic castration-resistant prostate cancer.","year":2023,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier de l’Université de Montréal","funders":"Janssen Biotech","keywords":"Medicine; Prostate cancer; Placebo; Internal medicine; Proportional hazards model; Randomized controlled trial; Biopsy; Oncology; Androgen deprivation therapy; Cancer; Urology; Pathology","score_opus":0.04946033413308798,"score_gpt":0.45113482799378074,"score_spread":0.40167449386069276,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379332778","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99539596,0.00006908289,0.0012193413,0.0013529729,0.00062060077,0.0012744159,0.000021682083,0.000009826361,0.000036136717],"genre_scores_gemma":[0.99576896,0.00010726797,0.0037527604,0.00008249127,0.00019436078,0.000041526353,0.000024157796,0.000015856975,0.000012623249],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.99451,0.0009406451,0.0035295128,0.00022752312,0.0005383281,0.0002539825],"domain_scores_gemma":[0.993091,0.003610382,0.002697264,0.00012376238,0.00026898977,0.00020858625],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0071889474,0.00015068006,0.0021361818,0.00043889275,0.000028815428,0.000012393849,0.00012362379,0.00016073791,0.000020962661],"category_scores_gemma":[0.017313732,0.00009259711,0.00029682546,0.00039136692,0.0006700073,0.00011607559,0.000026201846,0.0012183496,0.000001312952],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.643854,0.0031835304,0.11683323,0.000041712607,0.00006706727,0.00051339075,0.00021400854,0.0022771477,0.000043550765,0.000007957347,0.000019652438,0.23294471],"study_design_scores_gemma":[0.7900711,0.02203001,0.11132552,0.0008187462,0.00035724964,0.00000906434,0.00010156412,0.0747437,0.00002977263,0.0003469928,0.000057856767,0.00010841906],"about_ca_topic_score_codex":0.00007113377,"about_ca_topic_score_gemma":0.0000726624,"teacher_disagreement_score":0.23283629,"about_ca_system_score_codex":0.00012963782,"about_ca_system_score_gemma":0.0019090095,"threshold_uncertainty_score":0.9909639},"labels":[],"label_agreement":null},{"id":"W4379333134","doi":"10.1200/jco.2023.41.16_suppl.5001","title":"Development and validation of an AI-derived digital pathology-based biomarker to predict benefit of long-term androgen deprivation therapy with radiotherapy in men with localized high-risk prostate cancer across multiple phase III NRG/RTOG trials.","year":2023,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Saint John Regional Hospital","funders":"","keywords":"Medicine; Prostate cancer; Biomarker; Oncology; Radiation therapy; Androgen deprivation therapy; Internal medicine; Randomized controlled trial; Cumulative incidence; Biopsy; Cancer; Cohort","score_opus":0.06611430162671936,"score_gpt":0.4499989975432892,"score_spread":0.3838846959165698,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379333134","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99072295,0.0001534231,0.006343053,0.0018964742,0.00012011825,0.0007250838,0.000021958704,0.000013900792,0.000003011412],"genre_scores_gemma":[0.98594886,0.0009970715,0.01243821,0.0003903253,0.000109636385,0.000028106275,0.000051374576,0.000027399441,0.0000090346775],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9964836,0.00041558224,0.0022340305,0.0002555062,0.00038507566,0.00022617962],"domain_scores_gemma":[0.9959084,0.001299734,0.0020416738,0.0001501706,0.00032891502,0.0002711252],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005995306,0.0001645331,0.0015893169,0.00023211123,0.00004123948,0.000016332684,0.00011155426,0.00018778574,0.000012470412],"category_scores_gemma":[0.0020341536,0.00009997555,0.00010007424,0.0003288726,0.0002783734,0.00015397812,0.000022306354,0.00043872933,1.8077496e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.04039095,0.0008334741,0.525813,0.000029272134,0.00033172118,0.00020449208,0.00090197724,0.0015661519,0.005222002,5.051647e-7,0.000016476011,0.42468998],"study_design_scores_gemma":[0.119356,0.013362478,0.84201604,0.0005427338,0.00015626472,0.00009109108,0.00015639882,0.01074796,0.012810931,0.000021364744,0.0005843826,0.00015434352],"about_ca_topic_score_codex":0.00006173137,"about_ca_topic_score_gemma":0.00008440214,"teacher_disagreement_score":0.42453563,"about_ca_system_score_codex":0.00009224046,"about_ca_system_score_gemma":0.0008570708,"threshold_uncertainty_score":0.40768847},"labels":[],"label_agreement":null},{"id":"W4379346499","doi":"10.1200/jco.2023.41.16_suppl.e18691","title":"Use of positron emission tomography-computed tomography (PET-CT) scan in cancer patients: A single Canadian academic oncology center experience.","year":2023,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Centre Hospitalier de l’Université de Montréal; Université de Montréal; Cegep regional de Lanaudiere","funders":"","keywords":"Medicine; Positron emission tomography; Nuclear medicine; Computed tomography; Radiology; Positron Emission Tomography-Computed Tomography; Medical physics","score_opus":0.08845606377034693,"score_gpt":0.44941031402596304,"score_spread":0.3609542502556161,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379346499","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9859578,0.00023105938,0.00001800547,0.010967302,0.002122188,0.00021809986,0.000009009514,0.000017275475,0.0004592698],"genre_scores_gemma":[0.99314415,0.00084070495,0.0012613017,0.0041547245,0.0004824545,0.0000068017066,0.000015964706,0.000025672121,0.00006820658],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9956373,0.00055985706,0.0025480553,0.0002826644,0.00044583433,0.00052631483],"domain_scores_gemma":[0.99563223,0.0014139531,0.0013901506,0.00017175364,0.00038103815,0.0010108738],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020221833,0.00017898603,0.0014256733,0.0012513441,0.000052513795,0.000010883033,0.00029722156,0.0002313825,0.00009631049],"category_scores_gemma":[0.0036201777,0.00013836593,0.00048262448,0.0010448237,0.00038669026,0.0001873021,0.00007917134,0.0022906074,0.0000028633788],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00071172504,0.0010427763,0.85659593,0.000028582042,0.0001212988,0.0012113757,0.0003456918,0.000079632526,0.0008928123,0.000009274218,0.010288094,0.12867282],"study_design_scores_gemma":[0.006029589,0.005450798,0.8330496,0.0006662475,0.000119786455,0.0002703391,0.00017606904,0.0020756365,0.00014432345,0.0000723249,0.15179996,0.00014530217],"about_ca_topic_score_codex":0.009252065,"about_ca_topic_score_gemma":0.0037461892,"teacher_disagreement_score":0.14151187,"about_ca_system_score_codex":0.00048649922,"about_ca_system_score_gemma":0.001994052,"threshold_uncertainty_score":0.9973454},"labels":[],"label_agreement":null},{"id":"W4379521484","doi":"10.1136/annrheumdis-2023-eular.2963","title":"POS0371 DEVELOPMENT AND EVALUATION OF A TEXT-ANALYTICS ALGORITHM FOR AUTOMATED APPLICATION OF NATIONAL COVID-19 SHIELDING CRITERIA IN RHEUMATOLOGY PATIENTS","year":2023,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Faculty of Pharmaceutical Sciences, University of British Columbia; National Institute for Health and Care Research; Engineering and Physical Sciences Research Council; National Institutes of Health; University of British Columbia; Department of Health and Social Care","keywords":"Medicine; Rheumatology; Coronavirus disease 2019 (COVID-19); Analytics; 2019-20 coronavirus outbreak; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Internal medicine; Algorithm; Medical physics; Data science; Computer science; Virology; Disease","score_opus":0.046441659797947066,"score_gpt":0.4104471494833002,"score_spread":0.3640054896853531,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379521484","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9152655,0.000020258682,0.08283432,0.0010318293,0.000045591685,0.00059226155,0.0000069181656,0.00006234587,0.00014098865],"genre_scores_gemma":[0.9599174,0.0000072530656,0.03960705,0.00014568918,0.000004983153,0.000059330454,0.0002326859,0.000007462843,0.000018091112],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989663,0.000041094667,0.00039032224,0.00014079832,0.00036492693,0.000096593845],"domain_scores_gemma":[0.99919796,0.00024262977,0.00012811228,0.000054399035,0.00031554044,0.00006134402],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016036914,0.000057509937,0.00020214313,0.0002928301,0.00002725647,0.0000035704436,0.000035027828,0.000051624687,0.000017715012],"category_scores_gemma":[0.0017365523,0.00005187735,0.000019283374,0.0002620298,0.000040786315,0.000026500262,0.000023564793,0.00005203417,9.781721e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012102797,0.00045265458,0.41788828,0.0016069089,0.0002308594,0.0000014488453,0.003741486,0.0036824923,0.003797003,0.0030561301,0.0032461134,0.5621756],"study_design_scores_gemma":[0.0021203957,0.000035734705,0.08639141,0.000041629148,0.000028060593,0.0000034916636,0.00010293718,0.91021234,0.00021708777,0.0005514708,0.00025368336,0.00004176206],"about_ca_topic_score_codex":0.00006709066,"about_ca_topic_score_gemma":0.0000060054617,"teacher_disagreement_score":0.90652984,"about_ca_system_score_codex":0.00010946038,"about_ca_system_score_gemma":0.00030532246,"threshold_uncertainty_score":0.2115497},"labels":[],"label_agreement":null},{"id":"W4379522696","doi":"10.21428/594757db.8bee12fd","title":"Parameter-Efficient Methods for Metastases Detection fromClinical Notes","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada; Vector Institute","keywords":"Leverage (statistics); Computer science; Transfer of learning; Domain adaptation; Artificial intelligence; F1 score; Task (project management); Machine learning; Recall; Adaptation (eye)","score_opus":0.11368822940772111,"score_gpt":0.47841145460647544,"score_spread":0.36472322519875433,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379522696","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02763022,0.0003003023,0.96225834,0.0052424283,0.0027296704,0.0011430435,0.00003041867,0.000514194,0.00015139658],"genre_scores_gemma":[0.16375229,0.00010679561,0.8325812,0.0011181869,0.000809184,0.00036074317,0.00025117764,0.000115976065,0.00090441905],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99756414,0.00027385456,0.0007022694,0.0008045476,0.0002728383,0.0003823421],"domain_scores_gemma":[0.9927055,0.0060226847,0.00023030295,0.0006146742,0.00014887561,0.00027794956],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0030245064,0.00031678876,0.0008913493,0.00025453942,0.00009931326,0.000076946715,0.00018594615,0.00036575092,0.00009853305],"category_scores_gemma":[0.019631526,0.00024478722,0.00066427724,0.00013307268,0.00013017596,0.000012290214,0.00039243462,0.0013724219,0.000040467297],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025027536,0.0003016723,0.00046900104,0.00065947,0.0006949099,0.000025531153,0.00009499036,0.006356644,0.004182906,0.00017753743,0.0012669988,0.98552006],"study_design_scores_gemma":[0.0012638943,0.00031211157,0.0014126345,0.0003114917,0.0010403967,0.00002884483,0.000033931494,0.96671474,0.011615721,0.005242301,0.011685445,0.00033850624],"about_ca_topic_score_codex":0.00026118747,"about_ca_topic_score_gemma":0.0000065387085,"teacher_disagreement_score":0.98518157,"about_ca_system_score_codex":0.000081806334,"about_ca_system_score_gemma":0.00014840263,"threshold_uncertainty_score":0.99821335},"labels":[],"label_agreement":null},{"id":"W4379524175","doi":"10.1136/annrheumdis-2023-eular.2251","title":"POS0920 QUANTIFICATION OF TENOSYNOVITIS IN RA FROM WRIST MRIs, BASED ON DEEP LEARNING","year":2023,"lang":"en","type":"article","venue":"Annals of the Rheumatic Diseases","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Arthritis Society; Gilead Sciences; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Dutch Arthritis Society; Pfizer; Eli Lilly and Company; Bristol-Myers Squibb","keywords":"Medicine; Wrist; Tenosynovitis; Physical medicine and rehabilitation; Physical therapy; Artificial intelligence; Radiology; Surgery; Computer science","score_opus":0.030284115569071058,"score_gpt":0.3261604761007173,"score_spread":0.29587636053164623,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379524175","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98912096,0.0005985628,0.00040601488,0.009076852,0.00011374785,0.00021938978,0.000026863268,0.000050608644,0.00038701252],"genre_scores_gemma":[0.9986591,0.00045613316,0.0001596189,0.0004693962,0.00002046329,0.000010937895,0.0001056608,0.000019719806,0.000098979326],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9986953,0.00016097506,0.00040904837,0.0001685313,0.00039852445,0.00016760537],"domain_scores_gemma":[0.9985626,0.00067209295,0.0002508098,0.00035830823,0.00006793025,0.0000882903],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039997025,0.00010376764,0.00033607634,0.00017753428,0.00005183294,0.000011382093,0.00017834269,0.000035437,0.00009548109],"category_scores_gemma":[0.0035138824,0.00007333296,0.00015548454,0.00042538514,0.00012247541,0.000035109122,0.0000384071,0.00018854906,0.000021533015],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005744202,0.0012220317,0.5100308,0.0016963709,0.00024983383,0.000033881,0.0009900507,0.058677215,0.0029958095,0.0006007125,0.008348351,0.41458052],"study_design_scores_gemma":[0.00068669853,0.000087049295,0.6993981,0.0018488666,0.000059705333,6.1873214e-7,0.00018458492,0.2957622,0.00080886873,0.0008612618,0.00023052946,0.00007153848],"about_ca_topic_score_codex":0.00049731875,"about_ca_topic_score_gemma":0.000003705511,"teacher_disagreement_score":0.414509,"about_ca_system_score_codex":0.000009791158,"about_ca_system_score_gemma":0.00006240308,"threshold_uncertainty_score":0.42066994},"labels":[],"label_agreement":null},{"id":"W4379600079","doi":"10.17879/freeneuropathology-2022-4121","title":"5th Asian Oceanian Congress of Neuropathology along with the 5th Annual Conference of the Neuropathology Society of India - Meeting Abstracts, September 24–26, 2021","year":2022,"lang":"en","type":"article","venue":"PubMed","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Neuropathology; Library science; Brain research; Medicine; Political science; Psychology; Medical education; Neuroscience; Pathology; Computer science; Disease","score_opus":0.01355968534102345,"score_gpt":0.23975802600539517,"score_spread":0.22619834066437172,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379600079","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9867307,0.000119257,0.000030779713,0.006400549,0.00044085045,0.00060171704,0.000039386014,0.000019139514,0.005617652],"genre_scores_gemma":[0.99800205,0.000024034143,0.00019966942,0.0011406669,0.000079709615,0.00008296896,0.000007386788,0.000038775386,0.00042471077],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9977727,0.0005630744,0.00049909553,0.0002983732,0.00048313633,0.0003836227],"domain_scores_gemma":[0.9983433,0.00021273331,0.0006969228,0.00045322286,0.0001938141,0.0001000083],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015089263,0.00016591528,0.00047413778,0.00005730933,0.00015839678,0.0000093896815,0.00042841694,0.000059277667,0.00006793894],"category_scores_gemma":[0.00047844357,0.00010001861,0.00015698558,0.0003292531,0.0008936719,0.000046360277,0.00032422255,0.0010321696,6.868975e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00051547505,0.0007257146,0.9071588,0.00081422576,0.0004094505,0.0006070533,0.018807998,0.0027710162,0.00779279,0.00042721754,0.018444339,0.0415259],"study_design_scores_gemma":[0.0011894177,0.00018146027,0.98682374,0.000041072773,0.00017450622,0.00064666936,0.0030372753,0.0008008853,0.0009904958,0.000017795694,0.00598892,0.00010773933],"about_ca_topic_score_codex":0.00007140873,"about_ca_topic_score_gemma":0.000008537178,"teacher_disagreement_score":0.07966494,"about_ca_system_score_codex":0.000024435936,"about_ca_system_score_gemma":0.00016189094,"threshold_uncertainty_score":0.44843203},"labels":[],"label_agreement":null},{"id":"W4379646000","doi":"10.1200/jco.2023.41.17_suppl.lba1","title":"INDIGO: A global, randomized, double-blinded, phase 3 study of vorasidenib versus placebo in patients with residual or recurrent grade 2 glioma with an IDH1/2 mutation.","year":2023,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University Health Network","funders":"Servier","keywords":"Medicine; Glioma; Internal medicine; Clinical endpoint; Interim analysis; Oligodendroglioma; Placebo; Randomization; Hazard ratio; Randomized controlled trial; Surgery; Oncology; Astrocytoma; Pathology; Confidence interval","score_opus":0.12675541746533447,"score_gpt":0.5069442630659087,"score_spread":0.3801888456005742,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379646000","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9955151,0.00003909993,0.00009096287,0.002017983,0.00086890644,0.0013218888,0.000003886364,0.000019938567,0.00012222015],"genre_scores_gemma":[0.9970385,0.000044912977,0.0022773785,0.0001638143,0.000400232,0.000020868772,0.000015775999,0.000024375418,0.000014130899],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.99434435,0.0012782807,0.0027066108,0.0003043708,0.0010484883,0.00031789122],"domain_scores_gemma":[0.9929451,0.0035415103,0.0022861394,0.00024055461,0.0005200949,0.0004666186],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0064637004,0.00020945983,0.0023209762,0.0004192842,0.000049633618,0.000019347757,0.00024439392,0.00020868632,0.000036025573],"category_scores_gemma":[0.006178341,0.00011545187,0.00016103993,0.0009094266,0.00039535703,0.00018769523,0.000053354837,0.0013415357,0.0000037972045],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.85002315,0.010902595,0.102912195,0.000031818647,0.0007240699,0.0033384517,0.00077293394,0.0004143608,0.0000012091461,0.000023917302,0.00035581682,0.0304995],"study_design_scores_gemma":[0.80890256,0.0984575,0.08869707,0.00021336827,0.00081750884,0.00016985895,0.0016795899,0.0007245635,0.0000031215204,0.00006467458,0.00015151236,0.00011867713],"about_ca_topic_score_codex":0.00013984728,"about_ca_topic_score_gemma":0.0003621304,"teacher_disagreement_score":0.08755491,"about_ca_system_score_codex":0.00016323644,"about_ca_system_score_gemma":0.0017173523,"threshold_uncertainty_score":0.7396498},"labels":[],"label_agreement":null},{"id":"W4379653782","doi":"10.1158/2767-9764.c.6684845","title":"Data from Multi-institutional Prognostic Modeling in Head and Neck Cancer: Evaluating Impact and Generalizability of Deep Learning and Radiomics","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto","funders":"","keywords":"Generalizability theory; Radiomics; Artificial intelligence; Machine learning; Computer science; Deep learning; Artificial neural network; Medical imaging; Medicine; Medical physics; Statistics","score_opus":0.1442536740209812,"score_gpt":0.4354463554961185,"score_spread":0.2911926814751373,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379653782","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9538221,0.009434368,0.035246525,0.0005657254,0.00015070314,0.0005762807,0.00012884285,0.000059091424,0.00001641094],"genre_scores_gemma":[0.9211101,0.004814874,0.07293025,0.00006098432,0.0001519869,0.00002429042,0.00084985775,0.000038563696,0.000019111589],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977294,0.00017020843,0.0006110821,0.00089631224,0.0003196448,0.00027331314],"domain_scores_gemma":[0.99875313,0.0003758293,0.00018169392,0.00037943185,0.00009055024,0.00021934579],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015978126,0.00029876418,0.0007856891,0.00018202867,0.00010195783,0.000063734085,0.00014865663,0.00020932627,0.000025992706],"category_scores_gemma":[0.0032701108,0.00024118875,0.000047757883,0.00010686453,0.000237119,0.00009399024,0.0011950837,0.0012790689,3.2450606e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000792743,0.000052400406,0.7867679,0.0006171173,0.00014528034,0.00001820201,0.0004283791,0.16915579,0.0007692173,0.0000074024165,0.0000062574613,0.041952796],"study_design_scores_gemma":[0.001948624,0.00005747486,0.15978216,0.0010332712,0.00018451715,0.000021974683,0.0000830159,0.83638686,0.000004251649,0.00031456313,0.000009426321,0.00017386745],"about_ca_topic_score_codex":0.017680913,"about_ca_topic_score_gemma":0.00096036826,"teacher_disagreement_score":0.6672311,"about_ca_system_score_codex":0.00012913565,"about_ca_system_score_gemma":0.0003680108,"threshold_uncertainty_score":0.9888604},"labels":[],"label_agreement":null},{"id":"W4379796979","doi":"10.3389/fnagi.2023.1149871","title":"A cross-sectional study of explainable machine learning in Alzheimer’s disease: diagnostic classification using MR radiomic features","year":2023,"lang":"en","type":"article","venue":"Frontiers in Aging Neuroscience","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Eisai; Northern California Institute for Research and Education; F. Hoffmann-La Roche; University of Southern California; Biogen; Eli Lilly and Company; Bristol-Myers Squibb; BioClinica; U.S. Department of Defense; Meso Scale Diagnostics; Alzheimer's Disease Neuroimaging Initiative; Novartis Pharmaceuticals Corporation; Pfizer; National Institute on Aging; Alzheimer's Association","keywords":"Entorhinal cortex; Disease; Neuropsychology; Neuroimaging; Psychology; Neurodegeneration; Cognition; Medicine; Artificial intelligence; Pathology; Machine learning; Neuroscience; Hippocampus; Computer science","score_opus":0.03996497671780305,"score_gpt":0.33960830359615857,"score_spread":0.2996433268783555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379796979","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99557275,0.000658105,0.0017787289,0.00028598518,0.0011166045,0.00045343878,0.0000026486107,0.000097293785,0.000034430555],"genre_scores_gemma":[0.9986389,0.00011766113,0.00074999727,0.00012338384,0.000058132682,0.000029716846,0.00001341117,0.000027430633,0.00024133771],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9978331,0.00018396825,0.00043318083,0.00057170365,0.00056437275,0.00041368164],"domain_scores_gemma":[0.9991834,0.0002204377,0.00015619615,0.00024589922,0.000038658072,0.00015541658],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010678874,0.00015922922,0.00030880212,0.000902176,0.00022894389,0.000053806216,0.0002455698,0.000043494427,0.000004728446],"category_scores_gemma":[0.0030777429,0.00015763054,0.000052347517,0.0016932487,0.0002841232,0.00020245055,0.000100823265,0.0006960211,0.0000012511706],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000060012924,0.00019959192,0.93613183,0.000037917744,0.0000049782884,0.00034731938,0.00054446957,0.058232307,0.0035508545,0.000009184134,0.00009770015,0.0007838526],"study_design_scores_gemma":[0.00079487794,0.000060130154,0.61164236,0.00006700957,0.000016820604,0.000024205368,0.00019187744,0.38699427,0.000030342855,0.000026332771,0.00007252504,0.00007921729],"about_ca_topic_score_codex":0.00038257215,"about_ca_topic_score_gemma":0.0000054790444,"teacher_disagreement_score":0.32876197,"about_ca_system_score_codex":0.00013359636,"about_ca_system_score_gemma":0.0001593138,"threshold_uncertainty_score":0.64279866},"labels":[],"label_agreement":null},{"id":"W4379798163","doi":"10.1158/2767-9764.crc-22-0152","title":"Multi-institutional Prognostic Modeling in Head and Neck Cancer: Evaluating Impact and Generalizability of Deep Learning and Radiomics","year":2023,"lang":"en","type":"article","venue":"Cancer Research Communications","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":46,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sciencetech (Canada); Princess Margaret Cancer Centre; Artificial Intelligence in Medicine (Canada); University of Toronto","funders":"National Institute of General Medical Sciences; Canadian Institutes of Health Research; Canadian HIV Trials Network, Canadian Institutes of Health Research","keywords":"Generalizability theory; Radiomics; Artificial intelligence; Machine learning; Computer science; Deep learning; Artificial neural network; Medicine; Medical physics; Statistics","score_opus":0.22343244065220885,"score_gpt":0.5324583583627135,"score_spread":0.30902591771050464,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379798163","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9725049,0.02258783,0.0006211599,0.0037424131,0.000016890881,0.00043813512,0.000008906733,0.000028362068,0.000051368635],"genre_scores_gemma":[0.95532936,0.035218596,0.009152948,0.000028172517,0.00002808724,0.00017201864,0.00003243719,0.000015289243,0.000023065819],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998503,0.0004018256,0.00027400348,0.00023498847,0.00029882893,0.00028729884],"domain_scores_gemma":[0.9986019,0.00059796,0.000047965284,0.00032683864,0.0002487095,0.00017662301],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025524476,0.00009492493,0.00024863897,0.0002856506,0.0004065552,0.000035414232,0.00014848604,0.00005287992,0.000011428635],"category_scores_gemma":[0.0027322243,0.00008207912,0.000026532083,0.00056085945,0.00067059003,0.00008494225,0.00038936504,0.00089216995,4.2122292e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000055848788,0.000067556684,0.8251425,0.00027691605,0.00004996106,0.000003149619,0.0018589633,0.03139553,0.009257633,0.00015180235,0.000011156064,0.13172895],"study_design_scores_gemma":[0.0011101078,0.00007188767,0.16253415,0.0003670651,0.000018560635,0.000011021757,0.00023351297,0.83529186,0.000011563046,0.00016575666,0.00012649652,0.00005801205],"about_ca_topic_score_codex":0.004619095,"about_ca_topic_score_gemma":0.00068374013,"teacher_disagreement_score":0.8038963,"about_ca_system_score_codex":0.00021402836,"about_ca_system_score_gemma":0.00038613685,"threshold_uncertainty_score":0.6982721},"labels":[],"label_agreement":null},{"id":"W4380149805","doi":"10.1016/j.jval.2023.03.2254","title":"SA38 Approaches to Comparing Treatments from Meta-Analyses of Single-Arm Studies from a Systematic Literature Review: Case Example of Non-Surgical Technologies for Treatment of Lung Cancer","year":2023,"lang":"en","type":"article","venue":"Value in Health","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"EVERSANA (Canada)","funders":"","keywords":"Medicine; Microwave ablation; Radiofrequency ablation; Lung cancer; Meta-analysis; Ablation; Radiology; Systematic review; Medical physics; Surgery; Oncology; MEDLINE; Internal medicine","score_opus":0.48189212663009995,"score_gpt":0.4685687475370384,"score_spread":0.013323379093061527,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4380149805","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.56332326,0.4320623,0.00015591636,0.0020780638,0.00006565129,0.002074232,0.00019443294,0.000038905604,0.000007216633],"genre_scores_gemma":[0.937364,0.050264344,0.011298832,0.000059307127,0.000040311734,0.0007898344,0.00011571008,0.000026241622,0.000041414736],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.997781,0.00021927214,0.0011624598,0.0003464843,0.00025650312,0.0002342742],"domain_scores_gemma":[0.9975348,0.0013454008,0.00053511374,0.00042353428,0.00008227994,0.00007887204],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00068372744,0.00021624028,0.0029497908,0.0002952901,0.000040499024,0.0000055416804,0.0000946494,0.0000618648,0.000003525779],"category_scores_gemma":[0.0005919007,0.00012997707,0.00032799307,0.00067704986,0.00007180028,0.00002609399,0.000047687096,0.00008746816,3.0747836e-7],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00075372256,0.005759507,0.057837408,0.7747995,0.05733377,0.0015460149,0.045764472,0.02831921,0.0033361805,0.0002719027,0.001599476,0.022678835],"study_design_scores_gemma":[0.015168727,0.007782774,0.0030533185,0.48449817,0.05445186,0.0003082336,0.012072397,0.4070708,0.013383438,0.0008107956,0.00054854347,0.00085093],"about_ca_topic_score_codex":0.017518943,"about_ca_topic_score_gemma":0.00008352816,"teacher_disagreement_score":0.38179797,"about_ca_system_score_codex":0.00026911413,"about_ca_system_score_gemma":0.00008639889,"threshold_uncertainty_score":0.9890235},"labels":[],"label_agreement":null},{"id":"W4380562664","doi":"10.21203/rs.3.rs-2572595/v1","title":"The autoPET challenge: Towards fully automated lesion segmentation in oncologic PET/CT imaging","year":2023,"lang":"en","type":"preprint","venue":"Research Square","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":60,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Segmentation; Radiology; Computer vision; Artificial intelligence; Lesion; Medicine; Computer science; Medical physics; Nuclear medicine; Pathology","score_opus":0.1042630212947119,"score_gpt":0.4800272377192123,"score_spread":0.3757642164245004,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4380562664","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.76255804,0.0054101087,0.00044482975,0.20670299,0.0023729957,0.0058954814,0.00004922015,0.0027997438,0.013766554],"genre_scores_gemma":[0.98696965,0.007539479,0.0012097104,0.00018580034,0.00048281392,0.00053893705,0.0004409618,0.00011939681,0.0025132583],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99461514,0.0011787037,0.0006107797,0.00079708395,0.0018179044,0.0009804156],"domain_scores_gemma":[0.99744976,0.000956976,0.00015704588,0.00075615314,0.00040406996,0.0002760142],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.00798505,0.00030373418,0.0005301853,0.0006994352,0.00047990846,0.00028770775,0.0005553179,0.00006603438,0.000071528506],"category_scores_gemma":[0.0038744435,0.00021082742,0.00018254136,0.0006499863,0.00033814186,0.0000687478,0.001331695,0.0045916573,0.0001789867],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000728461,0.0009890827,0.03222572,0.006773248,0.000326472,0.037974007,0.002741965,0.0062577706,0.0019469669,0.0009203002,0.07528757,0.83382845],"study_design_scores_gemma":[0.0026151354,0.00042815538,0.12533884,0.0048494567,0.000053944415,0.00041109222,0.003878109,0.8407211,0.00016550261,0.003537211,0.017559184,0.00044231594],"about_ca_topic_score_codex":0.0016245336,"about_ca_topic_score_gemma":0.00013590434,"teacher_disagreement_score":0.8344633,"about_ca_system_score_codex":0.0011833628,"about_ca_system_score_gemma":0.0012581149,"threshold_uncertainty_score":0.9977048},"labels":[],"label_agreement":null},{"id":"W4380576500","doi":"10.1007/s11604-023-01458-3","title":"Construction of prediction model for KRAS mutation status of colorectal cancer based on CT radiomics","year":2023,"lang":"en","type":"article","venue":"Japanese Journal of Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"National Natural Science Foundation of China","keywords":"KRAS; Radiomics; Medicine; Receiver operating characteristic; Colorectal cancer; Stage (stratigraphy); Internal medicine; Oncology; Area under the curve; Radiology; Cancer; Biology","score_opus":0.015092560126399446,"score_gpt":0.3111056901805981,"score_spread":0.29601313005419866,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4380576500","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9794968,0.000051971463,0.018932821,0.00077009766,0.00046036852,0.00019700867,0.000026265501,0.000016008284,0.00004868086],"genre_scores_gemma":[0.9903309,0.00016277177,0.009190526,0.00010667032,0.00014221322,0.000009938319,0.000028916671,0.00001450839,0.000013594149],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99884146,0.00007494849,0.00056727265,0.000107590844,0.00020533043,0.00020341897],"domain_scores_gemma":[0.9986109,0.00038436745,0.0005296394,0.00007582326,0.00027814877,0.00012113229],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006774784,0.000088128036,0.00043370484,0.0003895073,0.000037345926,0.0000024211533,0.000057997895,0.000058319794,0.000013005202],"category_scores_gemma":[0.0009474931,0.00006966129,0.0001447204,0.00022871654,0.00019074931,0.000059060963,0.000005494733,0.0002262416,3.4700798e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003592546,0.0001269621,0.09428799,0.00019843777,0.00020693235,0.000038391343,0.0014537964,0.66269547,0.22058025,0.00032710136,0.00075641763,0.01573571],"study_design_scores_gemma":[0.0038621332,0.001249764,0.031566698,0.00008681109,0.00012713719,0.0011260555,0.00035101344,0.95646477,0.004735717,0.00032792377,0.000054777473,0.00004719341],"about_ca_topic_score_codex":0.000031573687,"about_ca_topic_score_gemma":0.0000015716718,"teacher_disagreement_score":0.29376933,"about_ca_system_score_codex":0.00012084829,"about_ca_system_score_gemma":0.00028098852,"threshold_uncertainty_score":0.28407052},"labels":[],"label_agreement":null},{"id":"W4380885478","doi":"10.21203/rs.3.rs-2973121/v1","title":"Radiomics Predictive Modeling from Dual-Time-Point FDG PET Ki Parametric Maps: Application to Chemotherapy Response in Lymphoma","year":2023,"lang":"en","type":"preprint","venue":"Research Square","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Occupational Cancer Research Centre","funders":"Canadian Institutes of Health Research","keywords":"Univariate; Multivariate statistics; Spearman's rank correlation coefficient; Radiomics; Rank correlation; Parametric statistics; Feature selection; Correlation; Computer science; Multivariate analysis; Artificial intelligence; Mathematics; Statistics; Machine learning","score_opus":0.03840616752110747,"score_gpt":0.38693702497844384,"score_spread":0.34853085745733636,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4380885478","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92510694,0.00055145007,0.051005244,0.018422535,0.0002535702,0.0037442853,0.00027681826,0.00036485677,0.00027430523],"genre_scores_gemma":[0.9824273,0.0010077571,0.011223279,0.0005373737,0.0009448346,0.0012903867,0.0013460059,0.00029562647,0.00092744053],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99316067,0.0012240127,0.00087914465,0.0016148806,0.0020365843,0.0010846861],"domain_scores_gemma":[0.9946285,0.0023045857,0.00015971863,0.0015699517,0.0005808459,0.000756389],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.008020973,0.00047437672,0.0010267643,0.002953765,0.00018065932,0.0001945542,0.00061367487,0.00046543824,0.00009253006],"category_scores_gemma":[0.0068894257,0.0004690946,0.00025803866,0.0022956908,0.00017541315,0.00007915986,0.0009925314,0.0029073446,0.00047484998],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.04845418,0.0020837726,0.021087153,0.0028920465,0.0012577566,0.003809117,0.013680084,0.7329552,0.023395544,0.00015946972,0.034933116,0.11529256],"study_design_scores_gemma":[0.0028099585,0.00048410235,0.025794823,0.0021442422,0.00003958546,0.000034134893,0.00064320513,0.961659,0.00018276929,0.004338411,0.0014768941,0.00039288116],"about_ca_topic_score_codex":0.003843086,"about_ca_topic_score_gemma":0.000016537799,"teacher_disagreement_score":0.2287038,"about_ca_system_score_codex":0.0021453057,"about_ca_system_score_gemma":0.0012607527,"threshold_uncertainty_score":0.99977607},"labels":[],"label_agreement":null},{"id":"W4381326147","doi":"10.1186/s13058-023-01659-8","title":"Meeting Abstracts from the British Society of Breast Radiology Annual Scientific Meeting 2022","year":2023,"lang":"en","type":"article","venue":"Breast Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Thomas Hospital","funders":"Royal Commission for the Exhibition of 1851","keywords":"Surgical oncology; Medicine; Medical physics; Breast cancer; General surgery; Internal medicine; Cancer","score_opus":0.03197477290872929,"score_gpt":0.36981267542791024,"score_spread":0.33783790251918094,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4381326147","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9681825,0.001568402,0.000010082451,0.027111871,0.00045657795,0.00031381904,0.00052556477,0.00009255664,0.0017386265],"genre_scores_gemma":[0.9949794,0.0007017785,0.0002578297,0.0003446014,0.0013815225,0.000055452692,0.00013636507,0.000049429786,0.0020936197],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9966153,0.0003217313,0.00040965373,0.00054799695,0.001278107,0.0008272481],"domain_scores_gemma":[0.9977527,0.00089636986,0.0001193688,0.0004070567,0.0005849281,0.00023955933],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0061656716,0.00012765976,0.00032996736,0.000106067346,0.0011327731,0.0002478232,0.0004479089,0.00011119942,0.0003214438],"category_scores_gemma":[0.0006006214,0.00010539344,0.0001723657,0.0013397172,0.001200557,0.00008997911,0.0003535165,0.0013247525,0.0000435062],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022020045,0.00016759391,0.1630808,0.00027398864,0.00033148212,0.00019013918,0.003045233,0.0009113383,0.07473379,0.00003521559,0.5425418,0.2144684],"study_design_scores_gemma":[0.0015450125,0.000043797085,0.9482626,0.0015440283,0.000051309617,0.0011067804,0.0040534767,0.013333506,0.00051808683,0.00025283036,0.029097239,0.00019138487],"about_ca_topic_score_codex":0.04224502,"about_ca_topic_score_gemma":0.0005205792,"teacher_disagreement_score":0.78518176,"about_ca_system_score_codex":0.00014871646,"about_ca_system_score_gemma":0.0006328043,"threshold_uncertainty_score":0.9641327},"labels":[],"label_agreement":null},{"id":"W4381739476","doi":"10.30978/tb2023-2-28","title":"Ways of transformation of typical X-ray signs of community acquired pneumonia of viral etiology (COVID-19) according to radiomics data","year":2023,"lang":"en","type":"article","venue":"Tuberculosis Lung Diseases HIV Infection","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Pneumonia; Viral pneumonia; Medicine; Radiology; Coronavirus disease 2019 (COVID-19); Parenchyma; Lung; Pathological; Radiomics; Lung cancer; Pathology; Disease; Internal medicine; Infectious disease (medical specialty)","score_opus":0.06276501737141756,"score_gpt":0.35792580135779495,"score_spread":0.2951607839863774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4381739476","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.972344,0.00005510105,0.022835286,0.0038197495,0.00015194788,0.0004051287,0.00022238566,0.00007867864,0.00008773303],"genre_scores_gemma":[0.997797,0.0001807256,0.00027597026,0.0006287875,0.000081475235,0.000014287222,0.0009967955,0.000021641574,0.0000033061756],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9982388,0.00038871038,0.0007142971,0.00017439731,0.0002840838,0.00019972524],"domain_scores_gemma":[0.9980607,0.0007012385,0.0002812076,0.00062438124,0.00013065629,0.00020179298],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009191365,0.00014556757,0.00059043197,0.00043236546,0.000094168165,0.000004815745,0.00023138034,0.00012771535,0.000031315503],"category_scores_gemma":[0.0022173533,0.0001375087,0.00017301292,0.00063451164,0.0002226591,0.00018530489,0.00013468161,0.00028297605,0.000003304451],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013149341,0.00084282295,0.5221434,0.005032687,0.0005072396,0.0000060895304,0.0028968987,0.0136554865,0.44040406,0.0005659925,0.003473303,0.009157042],"study_design_scores_gemma":[0.0032164734,0.0013019096,0.8146398,0.00058477576,0.0017236918,0.000037962312,0.00089023245,0.16882999,0.0071359975,0.0005396532,0.0007837896,0.0003157241],"about_ca_topic_score_codex":0.00070829934,"about_ca_topic_score_gemma":0.0000059064873,"teacher_disagreement_score":0.43326807,"about_ca_system_score_codex":0.00010634696,"about_ca_system_score_gemma":0.0001480248,"threshold_uncertainty_score":0.56074417},"labels":[],"label_agreement":null},{"id":"W4381891171","doi":"10.1101/2023.06.20.545422","title":"Deep learning, data ramping, and uncertainty estimation for detecting artifacts in large, imbalanced databases of MRI images","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; NeuroRx Research (Canada); Montreal Neurological Institute and Hospital","funders":"Canada First Research Excellence Fund; Mitacs; McGill University","keywords":"Computer science; Artificial intelligence; Artifact (error); Transfer of learning; Neuroimaging; Inference; Deep learning; Data quality; Machine learning; Data mining; Pattern recognition (psychology)","score_opus":0.02935411437173368,"score_gpt":0.3075618536484199,"score_spread":0.27820773927668624,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4381891171","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.791887,0.0013896164,0.2032521,0.00075704313,0.0005985756,0.0013878187,0.0003250379,0.00039944047,0.0000033986582],"genre_scores_gemma":[0.9387483,0.000705458,0.059948545,0.000101406855,0.0002250377,0.000103028455,0.000031747473,0.00012965706,0.0000068192358],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971538,0.00013664163,0.0007255174,0.0010745043,0.00035145518,0.00055809016],"domain_scores_gemma":[0.99721533,0.00048433978,0.00060244213,0.0012145573,0.0002597752,0.00022353731],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0023484207,0.0003896505,0.0008347899,0.00041229176,0.00013933827,0.00009039493,0.00037657048,0.00023203986,0.000010048118],"category_scores_gemma":[0.008846236,0.00040169258,0.00007879902,0.00037052543,0.000140414,0.00018570069,0.0009060562,0.0012505065,0.000004317255],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005811226,0.00061735784,0.47450262,0.014308298,0.0007776348,0.00027847308,0.00017959211,0.047129434,0.4593853,0.000380563,0.00094078854,0.0009187984],"study_design_scores_gemma":[0.0019876077,0.00008598699,0.17216372,0.0025131612,0.00023897753,1.203638e-7,0.000023500052,0.80649745,0.01451947,0.0000064032242,0.0015094039,0.00045421347],"about_ca_topic_score_codex":0.00026218273,"about_ca_topic_score_gemma":0.000021620092,"teacher_disagreement_score":0.759368,"about_ca_system_score_codex":0.0001218066,"about_ca_system_score_gemma":0.0003143157,"threshold_uncertainty_score":0.9998435},"labels":[],"label_agreement":null},{"id":"W4382011697","doi":"10.1007/s00330-023-09768-w","title":"Assessment of RadiomIcS rEsearch (ARISE): a brief guide for authors, reviewers, and readers from the Scientific Editorial Board of European Radiology","year":2023,"lang":"en","type":"editorial","venue":"European Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":24,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University Health Network","funders":"","keywords":"Radiomics; Interventional radiology; Medicine; Editorial board; Neuroradiology; Medical physics; Radiology; Library science; Computer science; Neurology","score_opus":0.04102919910272119,"score_gpt":0.3912275068145799,"score_spread":0.3501983077118587,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382011697","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001807388,0.005038378,0.0013756839,0.0022784108,0.984481,0.0014348519,0.00066550646,0.00010803844,0.0028107797],"genre_scores_gemma":[0.0006904065,0.005937254,0.0076588043,0.00012873973,0.9797035,0.00003395935,0.0028674095,0.0003429182,0.0026370403],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9866073,0.00734145,0.001982919,0.0015806011,0.0014614676,0.0010262273],"domain_scores_gemma":[0.9822852,0.0133546395,0.0010731652,0.0016671881,0.0012328789,0.00038689666],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.028556818,0.0005438754,0.0020571938,0.0005351524,0.0004414923,0.00009922792,0.0013804454,0.00062300486,0.000025534247],"category_scores_gemma":[0.04209692,0.0004071398,0.00045287213,0.0005831799,0.0039664316,0.00005641208,0.0006814389,0.0040084403,0.000018415125],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028053406,0.00006318732,0.0005580892,0.00055359927,0.0005263383,0.00011759881,0.0006467765,0.00001713289,0.0020993333,0.0002755732,0.9908817,0.0039801816],"study_design_scores_gemma":[0.0030966871,0.0009776145,0.0029319648,0.0009710108,0.0005500121,0.00004087534,0.0001901648,0.0004613543,0.000009580585,0.00014953437,0.99031603,0.00030518926],"about_ca_topic_score_codex":0.0003825842,"about_ca_topic_score_gemma":0.000012387509,"teacher_disagreement_score":0.013540104,"about_ca_system_score_codex":0.00022043198,"about_ca_system_score_gemma":0.0012315525,"threshold_uncertainty_score":0.99983805},"labels":[],"label_agreement":null},{"id":"W4382182054","doi":"10.1148/radiol.231066","title":"Reliability of LI-RADS for MRI and CT: Is Excellence Achievable?","year":2023,"lang":"en","type":"letter","venue":"Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre","funders":"","keywords":"Medicine; Excellence; Nuclear medicine; Medical physics; Magnetic resonance imaging; Radiology","score_opus":0.015292840500447623,"score_gpt":0.2982801387123396,"score_spread":0.282987298211892,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382182054","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022531437,0.0014731342,0.0027923994,0.9700997,0.0013755558,0.0008124031,0.00008505748,0.00011670924,0.0007136176],"genre_scores_gemma":[0.023325732,0.0047570686,0.010752174,0.9282831,0.00890096,0.00019956552,0.0006917033,0.00027557733,0.0228141],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99807113,0.00012709068,0.0004935849,0.00065144873,0.0001947845,0.0004619292],"domain_scores_gemma":[0.99796516,0.0010445028,0.00022747788,0.00056293764,0.00009494467,0.0001049994],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007690283,0.00026993893,0.0010521313,0.0001835558,0.00006636012,0.000007803139,0.00020492161,0.00049576635,0.000070503156],"category_scores_gemma":[0.0014124231,0.00022165336,0.00020227584,0.0001229924,0.0005647375,0.000022996262,0.000086692715,0.0017860051,0.0000145988415],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051925294,0.000017971732,0.0042910986,0.0016946461,0.0000972347,0.00019573224,0.00012923671,0.000008016305,0.00026627138,0.0000340249,0.9906675,0.002546297],"study_design_scores_gemma":[0.0010360056,0.00046881565,0.0028610155,0.00029850344,0.00025955783,0.0006541565,0.000012920245,0.005519625,0.000048902966,0.001528343,0.987095,0.00021717783],"about_ca_topic_score_codex":0.000103674276,"about_ca_topic_score_gemma":5.5642886e-7,"teacher_disagreement_score":0.041816566,"about_ca_system_score_codex":0.000053763626,"about_ca_system_score_gemma":0.00013452058,"threshold_uncertainty_score":0.9038762},"labels":[],"label_agreement":null},{"id":"W4382182335","doi":"10.1148/radiol.222855","title":"A Multicenter Assessment of Interreader Reliability of LI-RADS Version 2018 for MRI and CT","year":2023,"lang":"en","type":"article","venue":"Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"National Institute of Biomedical Imaging and Bioengineering; National Institutes of Health; Fonds de Recherche du Québec - Santé; Fondation de l'Association des radiologistes du Québec; Radiological Society of North America","keywords":"Medicine; Intraclass correlation; Malignancy; Radiology; Nuclear medicine; Multicenter study; Surgery; Internal medicine","score_opus":0.015119001399827107,"score_gpt":0.3520147720061128,"score_spread":0.3368957706062857,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382182335","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9894191,0.00009074157,0.005895431,0.0037042508,0.0003275965,0.0002646517,0.00000838751,0.000023702296,0.00026614586],"genre_scores_gemma":[0.9919743,0.00014397611,0.0074126692,0.00018551486,0.000064456966,0.000010263919,0.00003105235,0.000009643233,0.00016813615],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9993173,0.000057761932,0.00023463082,0.00017380477,0.0000732613,0.00014323367],"domain_scores_gemma":[0.9993639,0.00028492283,0.000082977866,0.00016221857,0.000045342316,0.000060612278],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005401495,0.00006652171,0.00031894384,0.0000907536,0.000019381814,0.0000013371749,0.000051082017,0.00004343754,0.000027728083],"category_scores_gemma":[0.0004776643,0.000051305255,0.00006619023,0.00007114285,0.00021300752,0.00001860582,0.000044059845,0.00014224094,0.0000017332947],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00043219945,0.00022687012,0.91796774,0.0012333693,0.0001753409,0.000026207721,0.00076724414,0.0002401196,0.034336217,0.0005348526,0.032875504,0.011184315],"study_design_scores_gemma":[0.004825745,0.0011906837,0.62029403,0.00025806308,0.00015874882,0.00010598847,0.0002929156,0.34866896,0.000974939,0.0003194661,0.022800952,0.000109521316],"about_ca_topic_score_codex":0.000039290666,"about_ca_topic_score_gemma":5.8289197e-7,"teacher_disagreement_score":0.34842885,"about_ca_system_score_codex":0.000028848719,"about_ca_system_score_gemma":0.00003191775,"threshold_uncertainty_score":0.20921676},"labels":[],"label_agreement":null},{"id":"W4382395114","doi":"10.18280/ts.400348","title":"Minimizing False Negatives in Metastasis Prediction for Breast Cancer Patients Through a Deep Stacked Ensemble Analysis of Whole Slide Images","year":2023,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Breast cancer; Metastasis; Artificial intelligence; Medicine; Statistics; Cancer; Pattern recognition (psychology); Computer science; Mathematics; Internal medicine","score_opus":0.019945750481059663,"score_gpt":0.3116689980367016,"score_spread":0.29172324755564194,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382395114","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.978444,0.00010397339,0.018458067,0.0016180119,0.00008455751,0.00055672793,0.0005993929,0.000058188867,0.00007712305],"genre_scores_gemma":[0.9957939,0.000093651186,0.0031559723,0.00023015754,0.00007900267,0.0001412833,0.00040778148,0.000024155206,0.00007412706],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99841785,0.000074409814,0.0005148607,0.00030212602,0.0003845388,0.0003062136],"domain_scores_gemma":[0.9992654,0.00020084057,0.00018133412,0.000118232776,0.0001481523,0.0000860874],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046257145,0.00015661176,0.0005116738,0.00047610834,0.000068823036,0.000019238534,0.000081639344,0.000043257394,0.0001708511],"category_scores_gemma":[0.000119281154,0.0001349597,0.00021517651,0.0011091006,0.00007361602,0.00015804771,0.0000301852,0.00014055175,0.0000019943936],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001105224,0.0012595182,0.67568344,0.0006775426,0.0052229157,0.00002795315,0.010694601,0.03455951,0.08447713,0.00013287188,0.0035793702,0.18257995],"study_design_scores_gemma":[0.004890245,0.0002860995,0.7628569,0.00022662395,0.002303769,0.0000014493784,0.0013283255,0.22321491,0.0038599262,0.00013486041,0.000729113,0.00016775729],"about_ca_topic_score_codex":0.00024068769,"about_ca_topic_score_gemma":0.000051735075,"teacher_disagreement_score":0.18865539,"about_ca_system_score_codex":0.00008867624,"about_ca_system_score_gemma":0.000047368652,"threshold_uncertainty_score":0.5503497},"labels":[],"label_agreement":null},{"id":"W4382395237","doi":"10.18280/ts.400317","title":"Enhanced Pneumonia Diagnosis Using Chest X-Ray Image Features and Multilayer Perceptron and k-NN Machine Learning Algorithms","year":2023,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Multilayer perceptron; Pneumonia; X-ray; Computer science; Artificial intelligence; Image (mathematics); Algorithm; Machine learning; Pattern recognition (psychology); Medicine; Artificial neural network; Physics; Internal medicine; Optics","score_opus":0.016625839246991306,"score_gpt":0.29170422331988705,"score_spread":0.27507838407289575,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382395237","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99148697,0.0005595686,0.0048982203,0.002215726,0.00009944074,0.00034766234,0.000008509313,0.00019233908,0.00019156733],"genre_scores_gemma":[0.9896972,0.0007633031,0.008259157,0.00042503807,0.00032017005,0.000037058366,0.000059716833,0.000056006174,0.00038233152],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9983913,0.00008786507,0.000282057,0.0004518173,0.00036065571,0.00042634094],"domain_scores_gemma":[0.9993008,0.00017949753,0.00008733963,0.0001140134,0.00004629079,0.0002720657],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00053525734,0.00026019476,0.00037589137,0.00019542374,0.00028532493,0.00009982987,0.00007082353,0.00008334554,0.00030412694],"category_scores_gemma":[0.00016213483,0.00022042755,0.000071980234,0.00020485537,0.00017623122,0.00012650805,0.00009566019,0.0006043056,0.000012741079],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011743164,0.00014989245,0.054984104,0.00031136072,0.00016253306,0.00022406808,0.0034054024,0.00092178537,0.7688064,0.000019409446,0.0006019142,0.17029573],"study_design_scores_gemma":[0.0037724094,0.00046437877,0.494281,0.00035286794,0.0002809952,0.00015821998,0.00082122453,0.48945066,0.006543304,0.000024041472,0.0034165906,0.00043430077],"about_ca_topic_score_codex":0.00017851903,"about_ca_topic_score_gemma":0.000005051324,"teacher_disagreement_score":0.76226306,"about_ca_system_score_codex":0.000043402415,"about_ca_system_score_gemma":0.000026791351,"threshold_uncertainty_score":0.8988775},"labels":[],"label_agreement":null},{"id":"W4382989504","doi":"10.3390/books978-3-0365-7931-3","title":"Breast Cancer Imaging and Therapy","year":2023,"lang":"en","type":"book","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Breast cancer; Medicine; Cancer; Oncology; Internal medicine","score_opus":0.01135806879778843,"score_gpt":0.3024717021785121,"score_spread":0.29111363338072366,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382989504","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00051538844,0.013796032,0.00018566495,0.038526773,0.001007308,0.00048463573,0.000042040927,0.00060849637,0.94483364],"genre_scores_gemma":[0.0002730647,0.015487631,0.00018482428,0.0039242627,0.0011418699,0.00001389814,0.000052066982,0.000110769135,0.9788116],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.999061,0.000010454387,0.00016837567,0.0003109038,0.0002352969,0.00021400016],"domain_scores_gemma":[0.99945986,0.00006574301,0.000060724822,0.00018545295,0.000049976326,0.00017823678],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016328198,0.00020272026,0.000369278,0.00013712591,0.000054317978,0.00003536523,0.00006270626,0.00009532876,0.00081881136],"category_scores_gemma":[0.000016524737,0.00014794435,0.00007925115,0.000046896825,0.00012795959,0.00002568029,0.000051861134,0.0006402723,0.00006314497],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002627113,0.000009428987,0.003341355,0.000114662456,0.00011830432,0.00015425745,0.00004933368,7.625155e-7,0.00006415352,0.0004682083,0.39037606,0.6052772],"study_design_scores_gemma":[0.0018722919,0.000030739506,0.013194441,0.0012527294,0.00016148077,0.0012987625,0.000024324729,0.0053451518,0.000005609351,0.002394449,0.9740186,0.00040145408],"about_ca_topic_score_codex":0.00013764936,"about_ca_topic_score_gemma":0.0000026174125,"teacher_disagreement_score":0.60487574,"about_ca_system_score_codex":0.00007090701,"about_ca_system_score_gemma":0.00029003454,"threshold_uncertainty_score":0.89654106},"labels":[],"label_agreement":null},{"id":"W4383058796","doi":"10.1177/08465371231184780","title":"MRI-Based End-To-End Pediatric Low-Grade Glioma Segmentation and Classification","year":2023,"lang":"en","type":"article","venue":"Canadian Association of Radiologists Journal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; Hospital for Sick Children; University of Toronto","funders":"Canadian Cancer Society","keywords":"Medicine; Segmentation; Radiomics; Artificial intelligence; Pipeline (software); Radiogenomics; Test set; Confidence interval; Pattern recognition (psychology); Radiology; Computer science; Internal medicine","score_opus":0.016924216120486238,"score_gpt":0.2914020034199517,"score_spread":0.2744777872994655,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383058796","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96423644,0.000116225994,0.0021206588,0.03230792,0.0004883522,0.00022864703,0.000028934153,0.00004682358,0.00042598258],"genre_scores_gemma":[0.99560374,0.0002693061,0.0020195502,0.001083976,0.0005077387,0.00000797663,0.00010506718,0.000018631234,0.00038398567],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9985519,0.00015673754,0.0003865519,0.00018383873,0.00036507053,0.0003558783],"domain_scores_gemma":[0.998418,0.00025034323,0.00037725797,0.00010656527,0.00018088991,0.0006669746],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001560112,0.000112648726,0.00025485072,0.0009060555,0.00018887584,0.000054176428,0.00009138555,0.00013918777,0.0000746302],"category_scores_gemma":[0.0019453828,0.00010738382,0.000076312215,0.00066980324,0.000048644004,0.00007377082,0.000007929414,0.00040870774,0.00003103468],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030960873,0.000030258761,0.9041272,0.0000722662,0.00008799359,0.00015835557,0.0003622416,0.0009898344,0.008165125,0.00020298894,0.071045265,0.014727542],"study_design_scores_gemma":[0.001587827,0.00015593552,0.9763985,0.000043373544,0.00010578314,0.00015276115,0.00014679166,0.01543301,0.00017771784,0.00013655193,0.005525715,0.00013600771],"about_ca_topic_score_codex":0.0007078015,"about_ca_topic_score_gemma":0.0006345202,"teacher_disagreement_score":0.072271354,"about_ca_system_score_codex":0.0010050286,"about_ca_system_score_gemma":0.00070672255,"threshold_uncertainty_score":0.43789852},"labels":[],"label_agreement":null},{"id":"W4383497937","doi":"10.1016/j.cmpb.2023.107714","title":"Fusion-based tensor radiomics using reproducible features: Application to survival prediction in head and neck cancer","year":2023,"lang":"en","type":"article","venue":"Computer Methods and Programs in Biomedicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":79,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency; University of British Columbia; Spinal Cord Injury BC","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Radiomics; Artificial intelligence; Preprocessor; Random forest; Computer science; Positron emission tomography; Pattern recognition (psychology); Intraclass correlation; Principal component analysis; Machine learning; Medicine; Nuclear medicine; Mathematics; Statistics","score_opus":0.05711053530185036,"score_gpt":0.41405591728672053,"score_spread":0.3569453819848702,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383497937","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.78048533,0.0010851546,0.2085209,0.008210138,0.0006170092,0.0009372146,0.000003370318,0.00012098906,0.000019908097],"genre_scores_gemma":[0.13426507,0.0006206125,0.86177665,0.001757457,0.0011557754,0.00015289997,0.00013367156,0.000053362,0.00008452488],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981874,0.00018469864,0.00040047456,0.00067257026,0.00021706766,0.00033779506],"domain_scores_gemma":[0.9991175,0.00020041186,0.00007339689,0.00031087376,0.00005792608,0.00023992381],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027113173,0.00018389696,0.00047561465,0.0006414019,0.0000720035,0.00003339056,0.00007756579,0.00011872422,0.0000036923261],"category_scores_gemma":[0.00020451372,0.00014858432,0.000030798834,0.0015734007,0.00014645209,0.000039497503,0.000091250426,0.00038078098,7.5051236e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012103893,0.00007435571,0.21318118,0.0002190777,0.0000141716555,0.000030107252,0.00052164553,0.0005610071,0.008140037,0.000018510957,0.00017316817,0.7769457],"study_design_scores_gemma":[0.0026914794,0.00042767578,0.34068465,0.0009435167,0.00003780696,0.000057657675,0.00008214568,0.64338785,0.00012362981,0.00016081578,0.011254975,0.00014778921],"about_ca_topic_score_codex":0.00094385055,"about_ca_topic_score_gemma":0.00003056965,"teacher_disagreement_score":0.7767979,"about_ca_system_score_codex":0.000085137726,"about_ca_system_score_gemma":0.000065297376,"threshold_uncertainty_score":0.6059093},"labels":[],"label_agreement":null},{"id":"W4383620828","doi":"10.1038/s41598-023-38076-y","title":"Radiomics approaches to predict PD-L1 and PFS in advanced non-small cell lung patients treated with immunotherapy: a multi-institutional study","year":2023,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; Institut universitaire de cardiologie et de pneumologie de Québec; Centre Hospitalier de l’Université de Montréal; Université du Québec à Trois-Rivières","funders":"Fonds de Recherche du Québec - Santé; Institut universitaire de cardiologie et de pneumologie de Québec, Université Laval","keywords":"Feature selection; Machine learning; Artificial intelligence; Radiomics; Lasso (programming language); Feature (linguistics); Computer science; Logistic regression; Random forest; Support vector machine; Feature engineering; Medicine; Oncology; Deep learning","score_opus":0.02265149217189024,"score_gpt":0.2580068320196793,"score_spread":0.23535533984778903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383620828","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.996094,0.00008493399,0.0007001247,0.00013374064,0.0007558681,0.0018194893,0.0000028880715,0.00010238204,0.00030661182],"genre_scores_gemma":[0.99496454,0.000007927324,0.0029437477,0.00005219519,0.00003178694,0.00011830393,0.00014151122,0.00003211751,0.0017078854],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99777883,0.00004586633,0.0004647351,0.0008356734,0.00050013023,0.00037477317],"domain_scores_gemma":[0.9990102,0.000034420344,0.0001489203,0.0004891687,0.000080373444,0.00023688514],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012383378,0.00021088487,0.00035692772,0.0004917216,0.00023839797,0.00011412982,0.0000902505,0.000051699408,0.0000069728885],"category_scores_gemma":[0.00016997827,0.00015298837,0.000046285768,0.0010653521,0.00018681241,0.00010239674,0.00007450664,0.0002628408,0.00000534548],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013607713,0.0007920328,0.98560673,0.000064108244,0.00004125407,0.0008783879,0.0024929722,0.0023109375,0.0020913603,0.0000014421377,0.00037729723,0.0052073994],"study_design_scores_gemma":[0.0048675127,0.0003715739,0.94271594,0.00021106705,0.00005455702,0.000115508316,0.0005643186,0.04899555,0.0004820628,0.000012402694,0.0013795594,0.00022995452],"about_ca_topic_score_codex":0.00009435262,"about_ca_topic_score_gemma":0.00002892497,"teacher_disagreement_score":0.046684615,"about_ca_system_score_codex":0.000115770694,"about_ca_system_score_gemma":0.00020552146,"threshold_uncertainty_score":0.62386847},"labels":[],"label_agreement":null},{"id":"W4383820687","doi":"10.3390/cancers15143553","title":"Machine Learning Integrating 99mTc Sestamibi SPECT/CT and Radiomics Data Achieves Optimal Characterization of Renal Oncocytic Tumors","year":2023,"lang":"en","type":"article","venue":"Cancers","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"VINNOVA","keywords":"Radiomics; Medicine; Technetium Tc 99m Sestamibi; Radiology; Nuclear medicine; Computer science; Radionuclide imaging","score_opus":0.021199625387563252,"score_gpt":0.29930040645965195,"score_spread":0.2781007810720887,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383820687","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9958493,0.00022376406,0.0023587677,0.000634616,0.00018174252,0.00017510673,0.00004171238,0.00012946264,0.00040553825],"genre_scores_gemma":[0.9953401,0.00082218135,0.0016787057,0.00018027556,0.00023888389,0.000005029334,0.0010691554,0.00004522053,0.00062045536],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987414,0.00006372054,0.00033176146,0.00036682189,0.00023464648,0.00026166413],"domain_scores_gemma":[0.99919444,0.00010908564,0.00019638609,0.00031494373,0.000032774456,0.00015235534],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000577946,0.00016034789,0.00037673747,0.00018665844,0.00011318142,0.00003310966,0.00017811562,0.000017440823,0.0000420012],"category_scores_gemma":[0.0007824207,0.00014147084,0.000040612056,0.00039799846,0.00018134368,0.00015418357,0.00016037749,0.0005702159,0.0000056770987],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006133302,0.00005540807,0.11697745,0.00128906,0.0005109009,0.0017628883,0.0029273955,0.02202536,0.53211296,0.000852388,0.0011827056,0.31969017],"study_design_scores_gemma":[0.0011055432,0.00017564587,0.01014043,0.0005361097,0.000100357625,0.000462708,0.00044196766,0.9800528,0.0016959988,0.000010213635,0.0051155784,0.00016263442],"about_ca_topic_score_codex":0.00029883604,"about_ca_topic_score_gemma":0.000008811013,"teacher_disagreement_score":0.9580275,"about_ca_system_score_codex":0.0002801502,"about_ca_system_score_gemma":0.0003907291,"threshold_uncertainty_score":0.5769014},"labels":[],"label_agreement":null},{"id":"W4384408089","doi":"10.1007/s00261-023-03999-7","title":"CT radiomics analysis of primary colon cancer patients with or without liver metastases: a correlative study with [18F]FDG PET uptake values","year":2023,"lang":"en","type":"article","venue":"Abdominal Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Medicine; Nuclear medicine; Positron emission tomography; Radiomics; PET-CT; Standardized uptake value; Univariate analysis; Radiology; Colorectal cancer; Cancer; Multivariate analysis; Internal medicine","score_opus":0.015589999359016586,"score_gpt":0.3070448330398589,"score_spread":0.29145483368084235,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384408089","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9972042,0.00022935715,0.0007827436,0.00020409937,0.00014231741,0.001064953,0.00006642843,0.0000776378,0.00022828163],"genre_scores_gemma":[0.99540335,0.00018875468,0.002877967,0.00045563717,0.00006928533,0.00011638118,0.00024991948,0.000056084697,0.0005826362],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9974986,0.0003547468,0.0005452392,0.0006081083,0.0005160237,0.0004773202],"domain_scores_gemma":[0.99804556,0.00064196414,0.00042627248,0.0004070342,0.00025679998,0.00022238836],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00069523184,0.00034308792,0.0016994085,0.0007397624,0.00012943953,0.000013563935,0.00021005738,0.000044345703,0.00021518861],"category_scores_gemma":[0.00032569477,0.00020687364,0.00016257507,0.0018380207,0.00057084457,0.00008874371,0.00007357116,0.0005123614,0.000008949661],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.01157712,0.00081494485,0.9592258,0.00009552365,0.009365327,0.0018728406,0.0030414357,0.0032595813,0.00012891888,0.000021172129,0.0011535565,0.009443782],"study_design_scores_gemma":[0.010154782,0.007932281,0.90409636,0.00014508002,0.01347301,0.00040820974,0.002349805,0.06050737,0.000024188956,0.0000067866376,0.00056532817,0.00033682218],"about_ca_topic_score_codex":0.0009756843,"about_ca_topic_score_gemma":0.00028813427,"teacher_disagreement_score":0.057247788,"about_ca_system_score_codex":0.00019859493,"about_ca_system_score_gemma":0.0003834234,"threshold_uncertainty_score":0.84360623},"labels":[],"label_agreement":null},{"id":"W4384518571","doi":"10.1109/icetci57876.2023.10176365","title":"A Novel Neural Network Based on Transformer for Polyp Image Segmentation","year":2023,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Artificial intelligence; Computer science; Segmentation; Convolutional neural network; Image segmentation; Transformer; Pattern recognition (psychology); Feature extraction; Artificial neural network; Computer vision; Scale-space segmentation; Deep learning; Engineering","score_opus":0.018617483014226856,"score_gpt":0.3210129090600855,"score_spread":0.3023954260458587,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384518571","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.113601595,0.00001584338,0.81862646,0.052644532,0.00067624176,0.0011519864,0.000012945042,0.00049800565,0.012772362],"genre_scores_gemma":[0.8769484,0.000011042848,0.09277788,0.023461118,0.00096509844,0.00013129342,0.0004028402,0.000072529234,0.005229807],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99925745,0.000009143455,0.00014214446,0.0001605579,0.00017224066,0.00025844827],"domain_scores_gemma":[0.9995984,0.00015294849,0.000022601864,0.00009796663,0.000025223651,0.000102894235],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026964516,0.00008796777,0.00013535409,0.00007706676,0.00007982477,0.000019195615,0.00003826152,0.000032791937,0.00013256102],"category_scores_gemma":[0.00009059224,0.000066835135,0.00009385147,0.00021424923,0.000029058061,0.000038194263,0.0000029206724,0.00014163303,0.00003145592],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015850115,0.00045044298,0.007946629,0.00050782174,0.0001438828,0.0000630906,0.000489224,0.04947699,0.42976332,0.0022836532,0.19822675,0.30906317],"study_design_scores_gemma":[0.0031558818,0.0002789564,0.0071272645,0.000046230907,0.00004545963,0.000007663771,0.00004926467,0.9825499,0.0013585782,0.000063415566,0.0052304016,0.00008696597],"about_ca_topic_score_codex":0.000024386254,"about_ca_topic_score_gemma":0.0000018558187,"teacher_disagreement_score":0.9330729,"about_ca_system_score_codex":0.000022272363,"about_ca_system_score_gemma":0.00003108673,"threshold_uncertainty_score":0.27254575},"labels":[],"label_agreement":null},{"id":"W4384925218","doi":"10.1002/mp.16615","title":"Information fusion for fully automated segmentation of head and neck tumors from PET and CT images","year":2023,"lang":"en","type":"article","venue":"Medical Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Head and neck; Medical imaging; Nuclear medicine; Segmentation; Positron emission tomography; Medicine; Medical physics; Image registration; Image fusion; Image segmentation; Radiology; Computer vision; Computer science","score_opus":0.008871945584463657,"score_gpt":0.30287402971431554,"score_spread":0.2940020841298519,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384925218","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98455334,0.000039506496,0.012005551,0.0027786165,0.00009264805,0.00022482125,0.000025301366,0.00015850563,0.00012169208],"genre_scores_gemma":[0.99673766,0.0001269541,0.0017281712,0.00065387937,0.00014571403,0.000012832718,0.0005610044,0.000010418097,0.000023388442],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99920243,0.000017057146,0.00022975424,0.000092294664,0.00033486617,0.00012359218],"domain_scores_gemma":[0.9994786,0.00016929112,0.000083748,0.00007358038,0.000046822388,0.00014797713],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002501182,0.00007755332,0.00020473696,0.000047463713,0.000053947148,0.000015356118,0.00003475858,0.000023181836,0.000021431313],"category_scores_gemma":[0.0005636715,0.00006413306,0.000028229095,0.00013353788,0.00014098638,0.00013189123,0.00004327808,0.00014122648,0.0000052264995],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019255525,0.00011778814,0.039032724,0.00102457,0.00009229913,0.000051322222,0.002004128,0.000043354965,0.0101317745,0.00024130073,0.017902166,0.929166],"study_design_scores_gemma":[0.008180133,0.00053210213,0.30991414,0.0010782635,0.00016337329,0.00007539898,0.0006144631,0.66251236,0.010522371,0.0043286188,0.0018332441,0.00024552428],"about_ca_topic_score_codex":0.00010923091,"about_ca_topic_score_gemma":7.598238e-7,"teacher_disagreement_score":0.9289205,"about_ca_system_score_codex":0.000012016189,"about_ca_system_score_gemma":0.000053753276,"threshold_uncertainty_score":0.26152703},"labels":[],"label_agreement":null},{"id":"W4385069929","doi":"10.3389/fonc.2023.1196414","title":"Generalization optimizing machine learning to improve CT scan radiomics and assess immune checkpoint inhibitors’ response in non-small cell lung cancer: a multicenter cohort study","year":2023,"lang":"en","type":"article","venue":"Frontiers in Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier Universitaire de Sherbrooke; Jewish General Hospital; Université du Québec à Trois-Rivières; Université Laval; Institut universitaire de cardiologie et de pneumologie de Québec; Centre Hospitalier de l’Université de Montréal","funders":"Institute of Cancer Research; Institut universitaire de cardiologie et de pneumologie de Québec, Université Laval; Fonds de Recherche du Québec - Santé; Fondation pour la Recherche Nuovo-Soldati; Cancer Research Society","keywords":"Medicine; Radiomics; Cohort; Generalizability theory; Oncology; Machine learning; Artificial intelligence; Response Evaluation Criteria in Solid Tumors; Lung cancer; Internal medicine; Biomarker; Clinical trial; Radiology; Computer science; Phases of clinical research; Statistics","score_opus":0.008816274189204606,"score_gpt":0.30414132138880956,"score_spread":0.29532504719960495,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385069929","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9870059,0.00073859433,0.0063893353,0.0020657473,0.0017241349,0.0018850915,0.0000035761161,0.00007587456,0.00011174569],"genre_scores_gemma":[0.97862405,0.0008419928,0.01904265,0.00039490874,0.00018136282,0.00030935297,0.00004346886,0.000073443254,0.0004887995],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973521,0.00057664956,0.0007057066,0.0006042524,0.00021208248,0.00054919824],"domain_scores_gemma":[0.9991078,0.000184714,0.00019649597,0.00023481231,0.00005605038,0.00022013746],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.003237701,0.00025108445,0.0007949178,0.00093440595,0.00010567517,0.00003786999,0.00015117468,0.0001222584,0.000010380857],"category_scores_gemma":[0.0007777221,0.00025208166,0.00006475339,0.0007471419,0.000074096846,0.000074081516,0.00021924068,0.0009919588,0.0000021301287],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014484833,0.00027553545,0.934688,0.00010015217,0.000072348725,0.0005915608,0.0054027527,0.024589913,0.021636164,3.9449768e-7,0.0005642907,0.010630437],"study_design_scores_gemma":[0.0062720375,0.0006355397,0.3705434,0.00014943958,0.00008758643,0.000017643968,0.0023055808,0.6179692,0.0006780874,0.00000238314,0.0011370742,0.00020199583],"about_ca_topic_score_codex":0.0022211524,"about_ca_topic_score_gemma":0.00018839401,"teacher_disagreement_score":0.5933793,"about_ca_system_score_codex":0.0011817564,"about_ca_system_score_gemma":0.0002558306,"threshold_uncertainty_score":0.99999315},"labels":[],"label_agreement":null},{"id":"W4385265014","doi":"10.1186/s13550-023-01022-0","title":"Radiomics predictive modeling from dual-time-point FDG PET Ki parametric maps: application to chemotherapy response in lymphoma","year":2023,"lang":"en","type":"article","venue":"EJNMMI Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Canadian Institutes of Health Research","keywords":"Univariate; Medicine; Multivariate statistics; Radiomics; Spearman's rank correlation coefficient; Rank correlation; Parametric statistics; Feature selection; Correlation; Multivariate analysis; Nuclear medicine; Artificial intelligence; Statistics; Computer science; Mathematics; Internal medicine; Radiology","score_opus":0.03205149463030872,"score_gpt":0.37490463200880725,"score_spread":0.34285313737849854,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385265014","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9646933,0.00014062383,0.01213559,0.020869702,0.00009288766,0.0011432187,0.000027135515,0.00020915117,0.0006883861],"genre_scores_gemma":[0.9920654,0.0002630535,0.0046212208,0.00072205934,0.00040494328,0.00027183504,0.00018158721,0.00009578769,0.0013740744],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962105,0.000605783,0.00042165187,0.0007424329,0.0012065781,0.00081305264],"domain_scores_gemma":[0.99693555,0.0016153713,0.000050300012,0.0006948751,0.00023609195,0.00046784355],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.006659127,0.00020176664,0.00043611196,0.0019279432,0.00016714804,0.000083118444,0.0003084197,0.00012818837,0.00010538501],"category_scores_gemma":[0.003954793,0.00019196559,0.00008996097,0.003843742,0.00012922315,0.00009698454,0.00019428854,0.0008386694,0.00094583904],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.050889224,0.0015891474,0.033835616,0.0003481963,0.0006067506,0.0033537925,0.01708958,0.16924852,0.2717442,0.00038743927,0.14019746,0.31071007],"study_design_scores_gemma":[0.0028908476,0.00039626108,0.024296774,0.00017364553,0.000011361618,0.000035304838,0.0005727332,0.9638892,0.00072185503,0.0012869434,0.0055443547,0.00018074966],"about_ca_topic_score_codex":0.00078800356,"about_ca_topic_score_gemma":0.000004922354,"teacher_disagreement_score":0.79464066,"about_ca_system_score_codex":0.0006791014,"about_ca_system_score_gemma":0.0003780314,"threshold_uncertainty_score":0.99983203},"labels":[],"label_agreement":null},{"id":"W4385280943","doi":"","title":"Poster \"Cycle de vie de la donnée\" - printemps de la données 2023 à l'IUEM","year":2023,"lang":"fr","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Rimouski","funders":"","keywords":"Art","score_opus":0.014761865608624816,"score_gpt":0.2764366943702006,"score_spread":0.2616748287615758,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385280943","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45503902,0.0055026854,0.1877523,0.10755399,0.00148235,0.0010998765,0.00010407676,0.0009022275,0.24056347],"genre_scores_gemma":[0.85333335,0.009810337,0.06221102,0.0012273681,0.00051516976,0.00016928348,0.00045369964,0.00027178586,0.07200798],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9782255,0.017853528,0.0009064583,0.0010993809,0.0006821609,0.0012329365],"domain_scores_gemma":[0.9857385,0.00966527,0.00057667564,0.0022531264,0.000852499,0.0009139157],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.028011123,0.00060378795,0.0007819013,0.00033991595,0.00058134185,0.00074487925,0.0016611305,0.00084373413,0.0005554052],"category_scores_gemma":[0.014348684,0.0006419975,0.0004785882,0.0005619677,0.0013867998,0.00013442719,0.0018382034,0.0033849138,0.00040738226],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020246106,0.0035388405,0.28931028,0.0038469795,0.0013856438,0.0011046801,0.06471989,0.0030076173,0.040797353,0.24317123,0.03400988,0.31490517],"study_design_scores_gemma":[0.0037145864,0.0000054429797,0.20535809,0.025249377,0.0007175433,0.0008674062,0.001121876,0.23797417,0.023184974,0.02595207,0.47426182,0.0015926514],"about_ca_topic_score_codex":0.006431477,"about_ca_topic_score_gemma":0.0005888862,"teacher_disagreement_score":0.44025195,"about_ca_system_score_codex":0.0008551253,"about_ca_system_score_gemma":0.0016047441,"threshold_uncertainty_score":0.99960315},"labels":[],"label_agreement":null},{"id":"W4385284056","doi":"10.33393/jcb.2016.2066","title":"Novel blood test to predict neoplastic activity in healthy patients and metastatic recurrence after primary tumor resection","year":2016,"lang":"en","type":"article","venue":"Journal of Circulating Biomarkers","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; McGill University Health Centre","funders":"","keywords":"Medicine; Primary tumor; Resection; Blood test; Oncology; Internal medicine; Metastasis; Surgery; Cancer","score_opus":0.011512274793067014,"score_gpt":0.2757994128402182,"score_spread":0.2642871380471512,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385284056","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9930946,0.000104692925,0.0044634044,0.0017771566,0.0002709681,0.00021570087,0.0000061414053,0.000008708193,0.000058580245],"genre_scores_gemma":[0.9940317,0.000020062957,0.0053753387,0.00044810516,0.00009522452,0.000005112351,8.1343813e-7,0.000017461227,0.0000061773926],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9985492,0.000083556,0.00049881235,0.00019740668,0.00042561366,0.00024538714],"domain_scores_gemma":[0.99840766,0.0006940391,0.0003560844,0.00010181989,0.00013488179,0.00030548972],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009977353,0.0001278854,0.00033400598,0.00035027746,0.000046717505,0.000022683551,0.00005953129,0.00003252677,0.000009685247],"category_scores_gemma":[0.0047766357,0.00008597778,0.00006343997,0.00027470823,0.00007047715,0.00017812292,0.00003560397,0.00029594864,0.0000010372661],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014952795,0.0003948161,0.8762832,0.00022328358,0.00008465291,0.00012789197,0.00013298851,0.000011290473,0.07147683,6.4332903e-7,0.00006954483,0.049699564],"study_design_scores_gemma":[0.004884888,0.001547833,0.98967206,0.001714352,0.00011199604,0.00070125674,0.000016557255,0.0010082931,0.0001766927,0.0000180764,0.000049555587,0.00009842626],"about_ca_topic_score_codex":0.000030050229,"about_ca_topic_score_gemma":0.0000058580445,"teacher_disagreement_score":0.11338886,"about_ca_system_score_codex":0.00017381598,"about_ca_system_score_gemma":0.00017515299,"threshold_uncertainty_score":0.57184243},"labels":[],"label_agreement":null},{"id":"W4385286804","doi":"10.26481/dis.20230908mb","title":"Combining deep learning and radiomics-based machine learning to optimize predictions on medical images","year":2023,"lang":"en","type":"dissertation","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"L'Alliance Boviteq","funders":"","keywords":"Deep learning; Artificial intelligence; Machine learning; Feature (linguistics); Computer science; Radiomics; Workload; Focus (optics); Data science","score_opus":0.009140333739497021,"score_gpt":0.3082388569851575,"score_spread":0.2990985232456605,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385286804","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7000808,0.005478661,0.05985843,0.04415874,0.010604232,0.005765774,0.000057676476,0.009998079,0.16399759],"genre_scores_gemma":[0.74496967,0.0043938677,0.024874404,0.006572064,0.002011461,0.0004570623,0.010790772,0.0012281575,0.20470257],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960545,0.00023376313,0.00074997643,0.00097175787,0.0013093738,0.0006806769],"domain_scores_gemma":[0.9970993,0.0010719774,0.00025445884,0.0002899235,0.00016560568,0.0011187564],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0013047797,0.00060948747,0.0010601027,0.0010053865,0.0005996196,0.0001513916,0.00023115188,0.00059634825,0.0009098644],"category_scores_gemma":[0.006932056,0.0005498077,0.0002462088,0.00057657977,0.00011883255,0.000055777655,0.000080230464,0.0045234836,0.00016434296],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00672455,0.0015306147,0.061302558,0.004818446,0.0028407488,0.004085759,0.011366983,0.1330993,0.005258051,0.001227387,0.024569727,0.74317586],"study_design_scores_gemma":[0.0056084543,0.0017823608,0.009683834,0.0034843273,0.00062619115,0.00016672374,0.002617999,0.9500528,0.00039456852,0.00004221248,0.024587432,0.00095310155],"about_ca_topic_score_codex":0.000317143,"about_ca_topic_score_gemma":0.00007346534,"teacher_disagreement_score":0.8169535,"about_ca_system_score_codex":0.00015715296,"about_ca_system_score_gemma":0.00032143015,"threshold_uncertainty_score":0.99969536},"labels":[],"label_agreement":null},{"id":"W4385316612","doi":"","title":"Poster \"Principes FAIR\" - printemps de la données 2023 à l'IUEM","year":2023,"lang":"en","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Rimouski","funders":"","keywords":"Political science; Psychology","score_opus":0.01960215053709867,"score_gpt":0.279585489551915,"score_spread":0.2599833390148163,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385316612","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5933304,0.0016233282,0.089771174,0.1155791,0.00097105023,0.0012166469,0.00007492434,0.0014573003,0.19597608],"genre_scores_gemma":[0.89181906,0.0018262451,0.039082155,0.00074096944,0.00019431608,0.00011819034,0.0007022986,0.00017125727,0.06534548],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9935706,0.003949466,0.00058456784,0.0008297937,0.00055972196,0.0005057961],"domain_scores_gemma":[0.9941874,0.0022886398,0.0003724557,0.0018552988,0.0008970394,0.00039912932],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.008837345,0.00037885224,0.00056087965,0.00030037118,0.00026421808,0.0003970924,0.0009160218,0.00042938424,0.00021423215],"category_scores_gemma":[0.006259761,0.0003672078,0.00033224464,0.000312953,0.00045983604,0.00006801188,0.0017363677,0.0020038502,0.00018385865],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031630645,0.0043501514,0.26037434,0.0074643604,0.0023738495,0.0012190391,0.06259933,0.0010090052,0.038625,0.15753837,0.09194231,0.37218794],"study_design_scores_gemma":[0.0054970034,0.000006469981,0.29580513,0.03209952,0.00088235526,0.00058738724,0.0009130161,0.14344998,0.04298224,0.02535818,0.44976276,0.0026559632],"about_ca_topic_score_codex":0.0020040513,"about_ca_topic_score_gemma":0.00025502683,"teacher_disagreement_score":0.36953196,"about_ca_system_score_codex":0.00020379605,"about_ca_system_score_gemma":0.0005210153,"threshold_uncertainty_score":0.999878},"labels":[],"label_agreement":null},{"id":"W4385341337","doi":"10.1007/s10278-023-00886-x","title":"An Explainable MRI-Radiomic Quantum Neural Network to Differentiate Between Large Brain Metastases and High-Grade Glioma Using Quantum Annealing for Feature Selection","year":2023,"lang":"en","type":"article","venue":"Journal of Digital Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Cégep de Lévis","funders":"Saint Joseph University","keywords":"Feature selection; Glioma; Feature (linguistics); Artificial neural network; Computer science; Quantum annealing; Simulated annealing; Quantum; Magnetic resonance imaging; Artificial intelligence; Pattern recognition (psychology); Medicine; Radiology; Physics; Machine learning; Cancer research; Quantum computer; Quantum mechanics","score_opus":0.021029734044044374,"score_gpt":0.3243532784001797,"score_spread":0.3033235443561353,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385341337","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9203936,0.000422104,0.0706484,0.0076360167,0.00047390876,0.00026997426,0.00006442366,0.0000879924,0.0000035979983],"genre_scores_gemma":[0.99253404,0.0000148205345,0.005013831,0.0005020825,0.0016961087,0.0000033616188,0.0001260101,0.00008103238,0.000028690485],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99790055,0.000089331144,0.00056984514,0.00031867417,0.00038600643,0.000735572],"domain_scores_gemma":[0.99844587,0.00034559524,0.000367242,0.00014569439,0.0001818555,0.0005137509],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010554809,0.0002712697,0.0006942487,0.00058402086,0.00034849055,0.000519023,0.0001564579,0.00006016417,0.000002951095],"category_scores_gemma":[0.00054093666,0.00023000347,0.00019772256,0.0007067959,0.00005045163,0.0010205789,0.00007185932,0.0005464896,0.0000011123293],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012320237,0.00048276412,0.70804816,0.00085194147,0.001354328,0.0018662711,0.001963532,0.06222808,0.12730257,0.0010350357,0.049043417,0.04459189],"study_design_scores_gemma":[0.0037572028,0.00075921725,0.046363033,0.0005589322,0.00051407283,0.0018485306,0.0006136138,0.93891156,0.001075793,0.0023843437,0.002794646,0.00041907304],"about_ca_topic_score_codex":0.000026473588,"about_ca_topic_score_gemma":0.0000012535248,"teacher_disagreement_score":0.8766835,"about_ca_system_score_codex":0.00010292719,"about_ca_system_score_gemma":0.000075256576,"threshold_uncertainty_score":0.9379269},"labels":[],"label_agreement":null},{"id":"W4385348670","doi":"10.3390/cancers15153829","title":"A Radiomics-Clinical Model Predicts Overall Survival of Non-Small Cell Lung Cancer Patients Treated with Immunotherapy: A Multicenter Study","year":2023,"lang":"en","type":"article","venue":"Cancers","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier de l’Université de Montréal; Université du Québec à Trois-Rivières; Université Laval; Montreal Heart Institute","funders":"Fonds de Recherche du Québec - Santé; Institut universitaire de cardiologie et de pneumologie de Québec, Université Laval","keywords":"Radiomics; Medicine; Oncology; Lung cancer; Concordance; Internal medicine; Immunotherapy; Cohort; Survival analysis; Nomogram; Feature selection; Cancer; Machine learning; Radiology; Computer science","score_opus":0.018307564466483926,"score_gpt":0.3215356547024309,"score_spread":0.303228090235947,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385348670","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99704665,0.00014259548,0.0004983973,0.00012291712,0.00037372584,0.0011450745,0.00003311415,0.00007948656,0.0005580166],"genre_scores_gemma":[0.99713653,0.0004950924,0.00039081526,0.00037958595,0.00013685238,0.00010318697,0.000040241106,0.00007585221,0.0012418481],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99824226,0.000078820856,0.0004972476,0.00041886332,0.0003830379,0.00037980062],"domain_scores_gemma":[0.9989651,0.00010225776,0.00021758824,0.00033464245,0.00016327301,0.00021713901],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039038938,0.0002265922,0.0006012295,0.00014318165,0.000059811482,0.000015006266,0.00016981167,0.0000845891,0.000045818808],"category_scores_gemma":[0.00006173852,0.00017253983,0.00013087453,0.00029494753,0.0001306833,0.000052440755,0.000046744128,0.0004287699,0.000004478514],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012062306,0.00040128682,0.9706951,0.00014908865,0.00045612693,0.00003375801,0.002029098,0.020672979,0.00069775165,8.571493e-7,0.0019152752,0.0017424893],"study_design_scores_gemma":[0.016257996,0.0007360545,0.33285838,0.00024991555,0.00026074954,4.4376773e-7,0.0001761568,0.64906985,0.00009818305,0.0000010882708,0.00013248704,0.00015869999],"about_ca_topic_score_codex":0.0014123662,"about_ca_topic_score_gemma":0.000054778888,"teacher_disagreement_score":0.6378367,"about_ca_system_score_codex":0.0004893728,"about_ca_system_score_gemma":0.00068039325,"threshold_uncertainty_score":0.70359707},"labels":[],"label_agreement":null},{"id":"W4385349335","doi":"10.1007/s10489-023-04844-6","title":"A texture-based method for predicting molecular markers and survival outcome in lower grade glioma","year":2023,"lang":"en","type":"article","venue":"Applied Intelligence","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":17,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"Specific Research Project of Guangxi for Research Bases and Talents; National Natural Science Foundation of China","keywords":"Computer science; Artificial intelligence; Convolutional neural network; Random forest; Principal component analysis; Overfitting; Pattern recognition (psychology); Radiomics; Classifier (UML); Glioma; Artificial neural network; Medicine; Cancer research","score_opus":0.02462618237790694,"score_gpt":0.3534482330142754,"score_spread":0.3288220506363685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385349335","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28421,0.00009300453,0.71024287,0.0027850827,0.0002619512,0.00077244063,0.0000044427616,0.00017380988,0.0014563786],"genre_scores_gemma":[0.9543955,0.000013895217,0.044226307,0.0010373112,0.0000688593,0.00011818131,0.000021804526,0.00004240561,0.000075780794],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985414,0.000041055664,0.00036700492,0.00040961275,0.00025846416,0.0003824676],"domain_scores_gemma":[0.99884033,0.00068521395,0.00006948492,0.00022024581,0.000029696761,0.00015501693],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014234016,0.00017042896,0.000336548,0.00025501795,0.000059525388,0.000026961721,0.00012449245,0.00009637628,0.000021261541],"category_scores_gemma":[0.0007471128,0.00015259079,0.00007796904,0.0005578554,0.000091240734,0.000022314893,0.00005319398,0.00038686863,0.000011484539],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018311589,0.00042864835,0.15166306,0.0016544955,0.00028340466,0.0011686614,0.0013008673,0.014307661,0.20270513,0.031177668,0.0012266786,0.59225255],"study_design_scores_gemma":[0.0016655357,0.00023496286,0.013283488,0.00020175843,0.00010303357,0.000041844127,0.00062371994,0.9590652,0.016879238,0.0045005586,0.0030200013,0.0003806878],"about_ca_topic_score_codex":0.00006551109,"about_ca_topic_score_gemma":0.0000037508514,"teacher_disagreement_score":0.9447575,"about_ca_system_score_codex":0.000039888248,"about_ca_system_score_gemma":0.00004477552,"threshold_uncertainty_score":0.62224716},"labels":[],"label_agreement":null},{"id":"W4385406328","doi":"10.1007/s00330-023-09887-4","title":"Retraction Note: Biparametric MR signal characteristics can predict histopathological measures of prostate cancer","year":2023,"lang":"en","type":"retraction","venue":"European Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":true,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Medicine; Neuroradiology; Prostate cancer; Interventional radiology; Radiology; Ultrasound; Prostate; Cancer; Internal medicine; Neurology","score_opus":0.03715616725145055,"score_gpt":0.3095867693382692,"score_spread":0.27243060208681863,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385406328","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7702863,0.029368902,0.006891837,0.015924806,0.10053156,0.0062301955,0.0035048677,0.003465053,0.06379647],"genre_scores_gemma":[0.8285271,0.088064946,0.0015249895,0.0014442634,0.017602433,0.00009899929,0.0049208445,0.0007438035,0.05707265],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99607825,0.0010075864,0.0009931369,0.00075591233,0.0006240453,0.0005410527],"domain_scores_gemma":[0.9976129,0.0004270076,0.00096494466,0.00044093147,0.00028189248,0.00027230152],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.002038439,0.00043928102,0.0013055227,0.0008391364,0.000115099036,0.000020513202,0.00025949904,0.0007214039,0.00021433315],"category_scores_gemma":[0.0031812438,0.0003667848,0.00029056187,0.0006047993,0.00045382086,0.000038314123,0.00008654155,0.0038985948,0.00009452764],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001081902,0.0003880722,0.07618296,0.0020785264,0.0005691913,0.0051661623,0.00068861403,0.00020290483,0.011207537,0.000027523927,0.33935007,0.5630565],"study_design_scores_gemma":[0.001304343,0.001249106,0.39346793,0.00095650234,0.0008776132,0.0014922564,0.000020221876,0.0020151993,0.00007275161,0.000013000826,0.59803504,0.0004960623],"about_ca_topic_score_codex":0.00018547139,"about_ca_topic_score_gemma":0.0000049107457,"teacher_disagreement_score":0.5625605,"about_ca_system_score_codex":0.00047833653,"about_ca_system_score_gemma":0.00041696616,"threshold_uncertainty_score":0.9998784},"labels":[{"model":"gemma","categories":["research_integrity"],"domain":null,"study_design":"not_applicable","genre":"other","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":["research_integrity","metaresearch"],"domain":"evaluation","study_design":"not_applicable","genre":"editorial","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W4385406762","doi":"10.1016/j.ejro.2023.100511","title":"Delta-radiomics in cancer immunotherapy response prediction: A systematic review","year":2023,"lang":"en","type":"review","venue":"European Journal of Radiology Open","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sinai Health System; Women's College Hospital; University of Toronto; University Health Network","funders":"Università di Pisa; Ministero dell’Istruzione, dell’Università e della Ricerca; European Commission","keywords":"Medicine; Radiomics; Immunotherapy; MEDLINE; Complete response; Oncology; Cancer; Internal medicine; Radiology; Chemotherapy","score_opus":0.07088051166691318,"score_gpt":0.40540396369353876,"score_spread":0.3345234520266256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385406762","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00002956321,0.9944173,0.00010862274,0.0016820352,0.0009411172,0.002471197,0.00002185534,0.0000421146,0.00028618058],"genre_scores_gemma":[0.0000024881406,0.9957531,0.00057946594,0.0016959797,0.0005412335,0.00006736009,0.000026065685,0.00026230127,0.0010720033],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.98708826,0.008566437,0.0032796643,0.0003676717,0.00032077683,0.00037721172],"domain_scores_gemma":[0.9955314,0.0009758887,0.0024436796,0.0006394597,0.00015533423,0.00025428025],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.019610394,0.0004524738,0.0061121266,0.0006745757,0.000059186525,0.000064770386,0.0014945423,0.0001341136,0.00007044639],"category_scores_gemma":[0.003788769,0.00029840684,0.0007798131,0.0007082919,0.00015620673,0.00011672757,0.00021086526,0.0022219855,0.000066080676],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005554605,0.00010649667,0.000040531395,0.8110947,0.0025995611,0.010191425,0.00025098468,0.000015126167,0.0000030113313,0.000016461176,0.036951564,0.13817468],"study_design_scores_gemma":[0.0010425742,0.0003784441,0.00005221313,0.53859186,0.0020068341,0.01787807,0.000010801457,0.000023659826,1.9566228e-8,0.0000030361894,0.43986848,0.00014399385],"about_ca_topic_score_codex":0.0000117151385,"about_ca_topic_score_gemma":9.564023e-7,"teacher_disagreement_score":0.4029169,"about_ca_system_score_codex":0.00046370385,"about_ca_system_score_gemma":0.0011332283,"threshold_uncertainty_score":0.99994683},"labels":[],"label_agreement":null},{"id":"W4385547547","doi":"10.1200/go.2023.9.supplement_1.107","title":"The use of machine learning models to predict PFS and OS outcomes from waterfall plots in randomized clinical trials (MAP-OUTCOMES).","year":2023,"lang":"en","type":"article","venue":"JCO Global Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; Princess Margaret Cancer Centre; University of Toronto","funders":"","keywords":"Waterfall; Medicine; Clinical endpoint; Randomized controlled trial; Sample size determination; Clinical trial; Statistics; Artificial intelligence; Internal medicine; Computer science; Mathematics","score_opus":0.18007375931644573,"score_gpt":0.4453138155587777,"score_spread":0.26524005624233193,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385547547","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9563086,0.00038507965,0.0022284663,0.037781045,0.0012066202,0.0014947888,0.00005516575,0.00014777543,0.00039243506],"genre_scores_gemma":[0.98987824,0.0011931858,0.0036359478,0.0040571513,0.00021815624,0.0000963636,0.00008432663,0.00003687381,0.0007997495],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9926421,0.0039729564,0.0020493101,0.00045668107,0.00039741973,0.0004815091],"domain_scores_gemma":[0.9779588,0.02082285,0.00045635816,0.00033211068,0.000080237274,0.0003496258],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01421514,0.0002532515,0.0030655419,0.0001389011,0.000094791656,0.000040339943,0.00021803401,0.00028504396,0.00003355762],"category_scores_gemma":[0.034908757,0.00013970226,0.00043001914,0.00028125232,0.00037429002,0.000084422296,0.000308747,0.000810663,0.000032891716],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.03790479,0.0003036747,0.80162704,0.000036933736,0.0009800348,0.00028666502,0.0006758593,0.0065644225,0.00011238594,0.00096097216,0.006304842,0.14424238],"study_design_scores_gemma":[0.21477844,0.00090971217,0.19298583,0.00020290457,0.0007146828,0.000024971105,0.00016554509,0.520554,0.000007147197,0.0036612784,0.06569641,0.0002990528],"about_ca_topic_score_codex":0.002650185,"about_ca_topic_score_gemma":0.000322156,"teacher_disagreement_score":0.6086412,"about_ca_system_score_codex":0.00013889611,"about_ca_system_score_gemma":0.00018801521,"threshold_uncertainty_score":0.97322065},"labels":[],"label_agreement":null},{"id":"W4385548973","doi":"10.1038/s41598-023-39809-9","title":"A pilot radiometabolomics integration study for the characterization of renal oncocytic neoplasia","year":2023,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Karolinska Institutet; VINNOVA","keywords":"Computational biology; Computer science; Medicine; Biology","score_opus":0.02638634726898583,"score_gpt":0.3145105822504423,"score_spread":0.2881242349814565,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385548973","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97866726,0.000029709521,0.014274971,0.0009446786,0.004819421,0.001115473,0.0000021344933,0.00007131992,0.00007502855],"genre_scores_gemma":[0.9963409,0.0000092112605,0.00031040754,0.000047552898,0.00016491362,0.000068890644,0.00020266788,0.00001622999,0.0028392351],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985828,0.000037982703,0.000464793,0.0003312223,0.00040976255,0.00017344666],"domain_scores_gemma":[0.9988629,0.00013382471,0.00028569397,0.00046820263,0.00018320368,0.00006617436],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029233315,0.0000861037,0.00021461282,0.0002633333,0.00022693154,0.00008391078,0.0000792797,0.000019600933,0.00001854242],"category_scores_gemma":[0.0012657095,0.00005453947,0.00007799446,0.00092615985,0.00015472065,0.00007239375,0.00003196405,0.00014049903,0.0000051463653],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001409748,0.0003352541,0.017999427,0.00006866427,0.000112837726,0.00012588609,0.0021876672,0.00023029864,0.92535484,0.00012367356,0.006061417,0.04725905],"study_design_scores_gemma":[0.004232751,0.0021800282,0.39512995,0.00042801068,0.001083551,0.0010109044,0.0021235247,0.46724066,0.05018643,0.002618593,0.073314175,0.00045143501],"about_ca_topic_score_codex":0.0000230313,"about_ca_topic_score_gemma":0.0000058779724,"teacher_disagreement_score":0.87516844,"about_ca_system_score_codex":0.00003610214,"about_ca_system_score_gemma":0.00018274284,"threshold_uncertainty_score":0.2224055},"labels":[],"label_agreement":null},{"id":"W4385578285","doi":"10.1093/noajnl/vdad070.093","title":"SDPS-39 AN UPDATED VALIDATION OF PREDICTIVE ALGORITHMS FOR BRAIN METASTASES IN NON-SMALL CELL LUNG CANCER: SYSTEMATIC REVIEW AND INDEPENDENT COHORTVALIDATION ANALYSIS","year":2023,"lang":"en","type":"article","venue":"Neuro-Oncology Advances","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Medicine; Cohort; Logistic regression; Internal medicine; Lung cancer; Stage (stratigraphy); Algorithm; Oncology; Cohort study; Retrospective cohort study","score_opus":0.014349024156514682,"score_gpt":0.3522009977580432,"score_spread":0.3378519736015285,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385578285","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94659877,0.016893731,0.025529157,0.004584479,0.000346165,0.005645589,0.00017223624,0.00012949028,0.00010039028],"genre_scores_gemma":[0.9762051,0.014601754,0.003971871,0.0022152364,0.00009730515,0.0012353667,0.0015241358,0.000047693484,0.0001015467],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980926,0.0004291665,0.0006478883,0.0004005742,0.00021026575,0.00021949463],"domain_scores_gemma":[0.99837726,0.00068925414,0.000465394,0.00020884103,0.00015339704,0.000105879306],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015274916,0.00015973274,0.0010913654,0.00044755466,0.000059362566,0.000010847446,0.00010771491,0.00007909863,0.000025508094],"category_scores_gemma":[0.0008663241,0.00013401553,0.00009505037,0.0009402299,0.00007873934,0.00018090644,0.000038180402,0.0002354368,6.8184187e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007527072,0.0013140629,0.45903504,0.39312506,0.0036320705,0.00032429272,0.003557773,0.054083474,0.06434578,0.00013021342,0.0023669223,0.017332619],"study_design_scores_gemma":[0.008365102,0.0030345456,0.04347986,0.010692492,0.042288963,0.000086334694,0.001537185,0.8701881,0.018174814,0.00022782291,0.0012284192,0.00069635647],"about_ca_topic_score_codex":0.00006509047,"about_ca_topic_score_gemma":0.000043260985,"teacher_disagreement_score":0.81610465,"about_ca_system_score_codex":0.00008168191,"about_ca_system_score_gemma":0.00010447715,"threshold_uncertainty_score":0.5464995},"labels":[],"label_agreement":null},{"id":"W4385662575","doi":"10.1016/j.clon.2023.08.003","title":"Dual-Centre Harmonised Multimodal Positron Emission Tomography/Computed Tomography Image Radiomic Features and Machine Learning Algorithms for Non-small Cell Lung Cancer Histopathological Subtype Phenotype Decoding","year":2023,"lang":"en","type":"article","venue":"Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Medicine; Lung cancer; Positron emission tomography; Tomography; Computed tomography; Radiology; Algorithm; Nuclear medicine; Pathology; Computer science","score_opus":0.03157664954980143,"score_gpt":0.365516850826896,"score_spread":0.33394020127709456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385662575","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98181534,0.0024673592,0.006157748,0.006203619,0.0015714486,0.001048998,0.000022902901,0.00039165607,0.00032094645],"genre_scores_gemma":[0.92932767,0.0015095518,0.06380803,0.0017149859,0.0014510045,0.00008515314,0.00036678754,0.00011580818,0.0016209877],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9967455,0.00041521978,0.00088193896,0.0009537312,0.00023534776,0.00076821697],"domain_scores_gemma":[0.99657357,0.0019421641,0.00039256577,0.0002631359,0.00017366954,0.0006548792],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0018097571,0.0003830988,0.0011825939,0.000361951,0.00042453266,0.00003889281,0.0001938794,0.0005896599,0.000064069725],"category_scores_gemma":[0.0011807032,0.00031255808,0.0005015445,0.00050553534,0.00047463152,0.000062083614,0.00021367533,0.0018249776,0.000008054416],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0023065768,0.0009389771,0.7696937,0.0005582265,0.00029250173,0.0014549617,0.00081712013,0.0001576305,0.048455156,0.00002231005,0.017699132,0.15760373],"study_design_scores_gemma":[0.012353549,0.0019457192,0.52527887,0.00022771602,0.00070644217,0.0001783816,0.00009061937,0.44904727,0.0007391866,0.00007505223,0.008859193,0.00049800804],"about_ca_topic_score_codex":0.00010841156,"about_ca_topic_score_gemma":0.000009835634,"teacher_disagreement_score":0.4488896,"about_ca_system_score_codex":0.00013914425,"about_ca_system_score_gemma":0.0002625613,"threshold_uncertainty_score":0.99993265},"labels":[],"label_agreement":null},{"id":"W4385684613","doi":"10.1007/s13246-023-01260-5","title":"Radiomics based predictive modeling of rectal toxicity in prostate cancer patients undergoing radiotherapy: CT and MRI comparison","year":2023,"lang":"en","type":"article","venue":"Physical and Engineering Sciences in Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Isfahan University of Medical Sciences","keywords":"Medicine; Radiomics; Radiation therapy; Prostate cancer; Receiver operating characteristic; Logistic regression; Magnetic resonance imaging; Random forest; Radiology; Prostate; Nuclear medicine; Feature selection; Artificial intelligence; Cancer; Computer science; Internal medicine","score_opus":0.013213022220979496,"score_gpt":0.3015078261457329,"score_spread":0.28829480392475343,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385684613","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9954883,0.00049152,0.0021660568,0.0014471257,0.0001281146,0.0001893832,0.0000021003634,0.00003810822,0.000049310707],"genre_scores_gemma":[0.99828196,0.00056362373,0.0009341839,0.000095826865,0.000090630645,0.000012943648,0.000004927735,0.000011607634,0.0000043024675],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99888766,0.0000238307,0.00026483255,0.00027137002,0.00029527498,0.0002570043],"domain_scores_gemma":[0.9995108,0.0002656648,0.00004765558,0.000062638595,0.000020655018,0.0000925826],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00052530796,0.00012763671,0.00043194668,0.00030426902,0.00003989729,0.00000793864,0.00006726571,0.00001627406,0.0000016964553],"category_scores_gemma":[0.00032188176,0.0000963043,0.000020234866,0.0007341315,0.00027872316,0.00007878967,0.0000293443,0.0002872531,9.152345e-8],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000068487876,0.0001041013,0.33408815,0.00033021974,0.000015527055,0.000013919542,0.0025977043,0.6535816,0.003855101,0.00009149876,0.000031188658,0.0052224807],"study_design_scores_gemma":[0.0018249115,0.0003953933,0.05589085,0.0009545942,0.000013994978,0.0000027955189,0.00018197333,0.9404079,0.00012937275,0.00009847308,0.00001454157,0.00008524519],"about_ca_topic_score_codex":0.00025034903,"about_ca_topic_score_gemma":0.0000110186675,"teacher_disagreement_score":0.28682625,"about_ca_system_score_codex":0.000058084017,"about_ca_system_score_gemma":0.0000494216,"threshold_uncertainty_score":0.3927175},"labels":[],"label_agreement":null},{"id":"W4385692569","doi":"10.46254/sa04.20230079","title":"X-hance an interface that enhances x-ray images","year":2023,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Interface (matter); Computer science; Computer graphics (images); X-ray; Computer vision; Physics; Optics; Operating system","score_opus":0.020706849999188724,"score_gpt":0.34397301181106776,"score_spread":0.32326616181187906,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385692569","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9376286,0.00028568605,0.018033395,0.0117191365,0.0004936476,0.00015741248,0.000001333828,0.0007049478,0.030975837],"genre_scores_gemma":[0.97117233,0.00022555089,0.0041344385,0.0011825742,0.0002036849,0.000008403213,0.000013246072,0.000021800977,0.023037983],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991427,0.000029582945,0.000120196695,0.00024015199,0.00021775858,0.000249631],"domain_scores_gemma":[0.99947953,0.0000674656,0.00003183659,0.00023012707,0.000028235843,0.00016281927],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033382775,0.00010022583,0.00018014562,0.000089451205,0.00006300557,0.000037377387,0.00011783476,0.00003597221,0.00039245337],"category_scores_gemma":[0.00017743361,0.00007293249,0.000045017223,0.00020468689,0.000089022025,0.00012814222,0.00004632106,0.00024372416,0.00042593898],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012608028,0.0002283021,0.044612464,0.00024840204,0.00013195518,0.0003396381,0.0017881047,0.00040905937,0.5238621,0.0008158997,0.12594219,0.30149576],"study_design_scores_gemma":[0.0032587904,0.0010274332,0.24350084,0.0006298682,0.00014574785,0.00017179498,0.0036989523,0.1357921,0.38922146,0.0014473194,0.22023495,0.0008707484],"about_ca_topic_score_codex":0.000051860698,"about_ca_topic_score_gemma":0.000002969285,"teacher_disagreement_score":0.30062503,"about_ca_system_score_codex":0.000015421425,"about_ca_system_score_gemma":0.000026204722,"threshold_uncertainty_score":0.5474726},"labels":[],"label_agreement":null},{"id":"W4385798523","doi":"10.1002/jmri.28952","title":"Editorial for “Assessment of Hidden Blood Loss in Spinal Metastasis Surgery: A Comprehensive Approach with <scp>MRI</scp>‐Based Radiomics Models”","year":2023,"lang":"en","type":"letter","venue":"Journal of Magnetic Resonance Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Hamilton Health Sciences; Juravinski Hospital; Juravinski Cancer Centre","funders":"","keywords":"Radiomics; Medicine; Spinal surgery; Metastasis; Magnetic resonance imaging; Radiology; Blood loss; Brain metastasis; Surgery; Internal medicine; Cancer","score_opus":0.02742125829218028,"score_gpt":0.2992684089001247,"score_spread":0.2718471506079444,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385798523","genre_codex":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11082814,0.08632725,0.15551575,0.56127644,0.076048195,0.007949925,0.00062461005,0.00029195278,0.001137785],"genre_scores_gemma":[0.023017457,0.0057874564,0.608304,0.107160635,0.2525176,0.00039930517,0.000627763,0.0012994308,0.0008862744],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99435586,0.00030135384,0.0018235554,0.0006268399,0.0020100472,0.00088233734],"domain_scores_gemma":[0.99427146,0.0020879158,0.0018398871,0.00051601155,0.001055031,0.00022967457],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0020071284,0.00062508543,0.0024831484,0.0013486284,0.00008199961,0.0001036329,0.000523392,0.00034668605,0.000005368228],"category_scores_gemma":[0.00077872426,0.0005065897,0.0007208994,0.0006928065,0.00042135263,0.00020523857,0.00008113279,0.0039413776,5.2731355e-7],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042051836,0.00035771212,0.0068210447,0.002676368,0.00029518738,0.0045953384,0.00016626675,0.0024570315,0.00019725539,0.000014963331,0.96109575,0.020902563],"study_design_scores_gemma":[0.015129571,0.0019658755,0.0050094035,0.0077402275,0.0027679547,0.0036018665,0.0003003675,0.24580927,0.00007708369,0.0004704058,0.71661276,0.0005152237],"about_ca_topic_score_codex":0.00008859623,"about_ca_topic_score_gemma":0.0000011386434,"teacher_disagreement_score":0.45411578,"about_ca_system_score_codex":0.00025717382,"about_ca_system_score_gemma":0.0018577653,"threshold_uncertainty_score":0.9997386},"labels":[],"label_agreement":null},{"id":"W4385803217","doi":"10.3389/fonc.2023.892393","title":"Combination of clinical, radiomic, and “delta” radiomic features in survival prediction of metastatic gastroesophageal adenocarcinoma","year":2023,"lang":"en","type":"article","venue":"Frontiers in Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto General Hospital; Princess Margaret Cancer Centre; University Health Network; University of Toronto","funders":"","keywords":"Radiomics; Medicine; Adenocarcinoma; Esophageal adenocarcinoma; Overall survival; Oncology; Radiology; Internal medicine; Cancer","score_opus":0.02904183005862794,"score_gpt":0.3596349301148177,"score_spread":0.33059310005618975,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385803217","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9940555,0.001115975,0.0014944942,0.0011186876,0.0015813275,0.00034700625,0.000016474303,0.000026295253,0.00024423073],"genre_scores_gemma":[0.9877428,0.00084452255,0.01101575,0.00008352118,0.000086371874,0.000013891326,0.00008478074,0.000018808374,0.00010959583],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9979506,0.0004438085,0.00087581814,0.00027483888,0.00021088013,0.00024405822],"domain_scores_gemma":[0.9990074,0.00040001146,0.00028140002,0.00016229323,0.000047197882,0.000101685626],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023106753,0.00011863389,0.0009706408,0.0007019013,0.000022849952,0.000002674234,0.00010114191,0.00015095103,0.00000986296],"category_scores_gemma":[0.0010539319,0.000112951515,0.00008289683,0.0004667593,0.00044965034,0.00005698791,0.000047996928,0.000559833,7.8842993e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004837796,0.00025178288,0.968822,0.00016278768,0.000082744504,0.00020092598,0.0005714639,0.00014746163,0.00046966207,0.00012437029,0.0073582935,0.021324713],"study_design_scores_gemma":[0.0073955194,0.0009469711,0.948658,0.0000831215,0.00008558308,0.00007377717,0.0005337944,0.041252054,0.000060310966,0.0005848976,0.0002742656,0.000051705938],"about_ca_topic_score_codex":0.00013339285,"about_ca_topic_score_gemma":0.000013270771,"teacher_disagreement_score":0.041104592,"about_ca_system_score_codex":0.000118479824,"about_ca_system_score_gemma":0.00021484433,"threshold_uncertainty_score":0.4606029},"labels":[],"label_agreement":null},{"id":"W4385813836","doi":"10.1016/j.xcrm.2023.101173","title":"Deep learning integrates histopathology and proteogenomics at a pan-cancer level","year":2023,"lang":"en","type":"article","venue":"Cell Reports Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Mount Sinai Hospital","funders":"National Institute of Environmental Health Sciences; National Institute of General Medical Sciences; National Institute on Aging; National Cancer Institute; U.S. Department of Health and Human Services; National Institutes of Health; National Center for Advancing Translational Sciences; Government of South Australia; Clinical and Translational Science Institute, Boston University","keywords":"Proteogenomics; Interpretability; Proteomics; Transcriptome; Predictive power; Artificial intelligence; Generalizability theory; Cancer; Computer science; Biology; Computational biology; Bioinformatics; Machine learning; Pathology; Medicine; Internal medicine; Gene; Psychology","score_opus":0.02498740379555147,"score_gpt":0.3002621467212433,"score_spread":0.2752747429256918,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385813836","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97446376,0.005888714,0.0012567064,0.0092837745,0.000886503,0.0005034399,6.657646e-7,0.0002878813,0.007428543],"genre_scores_gemma":[0.9543274,0.0035810103,0.000921856,0.0013709541,0.00062459277,0.000083880186,0.00009571115,0.00007445662,0.038920116],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981268,0.00006291608,0.00054510555,0.00053208,0.00031467783,0.00041839367],"domain_scores_gemma":[0.9987836,0.00014851613,0.00029393568,0.00030040194,0.00009826539,0.00037529448],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001066,0.00023077085,0.0005713796,0.00025643437,0.00019613985,0.000009597591,0.00006090504,0.00012660472,0.00042545295],"category_scores_gemma":[0.0019544712,0.00016928722,0.000061407125,0.0003074065,0.00043836932,0.000034672183,0.00013255553,0.00069803424,0.000029822704],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017194527,0.00008499182,0.45621902,0.0007776312,0.000071284674,0.014637232,0.005399046,0.00022886402,0.32925883,0.000055178523,0.016808208,0.17628777],"study_design_scores_gemma":[0.0047684205,0.001330785,0.35366404,0.0013452683,0.00076013,0.01443159,0.0022196432,0.046623264,0.0056849495,0.00091071246,0.567423,0.0008381948],"about_ca_topic_score_codex":0.00018439622,"about_ca_topic_score_gemma":0.000011336508,"teacher_disagreement_score":0.5506148,"about_ca_system_score_codex":0.00016023229,"about_ca_system_score_gemma":0.00010268667,"threshold_uncertainty_score":0.69033325},"labels":[],"label_agreement":null},{"id":"W4385841855","doi":"10.5121/ijaia.2023.14404","title":"Segmentation of the Gastrointestinal Tract MRI Using Deep Learning","year":2023,"lang":"en","type":"article","venue":"International Journal of Artificial Intelligence & Applications","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Laurentian University","funders":"","keywords":"Computer science; Contouring; Segmentation; Artificial intelligence; Deep learning; Hausdorff distance; Sørensen–Dice coefficient; Gastrointestinal tract; Dice; Magnetic resonance imaging; Rendering (computer graphics); Market segmentation; Computer vision; Image segmentation; Radiology; Medicine; Computer graphics (images); Internal medicine; Mathematics","score_opus":0.03822823701453593,"score_gpt":0.3741652881450615,"score_spread":0.3359370511305256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385841855","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3136248,0.000042174153,0.68249345,0.0030491708,0.00032672592,0.00022726493,0.0000027209123,0.00002192423,0.0002117867],"genre_scores_gemma":[0.97883564,0.00006933219,0.020376487,0.000113877824,0.0005104704,0.000011580609,0.000008477652,0.000014611245,0.000059513895],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984524,0.000049285736,0.0006682244,0.00011092066,0.00058855524,0.00013060312],"domain_scores_gemma":[0.998423,0.00017723588,0.0005627321,0.0001133514,0.00064448133,0.000079231],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005513319,0.00008408828,0.000157651,0.00024404353,0.000104459046,0.00003578103,0.00033361587,0.000027327562,0.00008718482],"category_scores_gemma":[0.00048054263,0.0000638214,0.00017588884,0.00043745866,0.00015079424,0.00010184975,0.00005232568,0.00044595194,0.000021975256],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016783687,0.00046969304,0.075466335,0.000037993657,0.000118807395,0.00005051479,0.0010180937,0.1694227,0.31655556,0.0085882535,0.00011834799,0.42798588],"study_design_scores_gemma":[0.00040294923,0.0004409945,0.047800437,0.0009427025,0.0003435122,0.0046341037,0.0054446687,0.83675164,0.07694802,0.018100843,0.007896829,0.00029327642],"about_ca_topic_score_codex":0.000021858285,"about_ca_topic_score_gemma":0.0000024602798,"teacher_disagreement_score":0.66732895,"about_ca_system_score_codex":0.000095446594,"about_ca_system_score_gemma":0.00013030489,"threshold_uncertainty_score":0.26025608},"labels":[],"label_agreement":null},{"id":"W4385845941","doi":"10.21468/scipost.report.6087","title":"Report on scipost_202210_00002v1","year":2022,"lang":"en","type":"peer-review","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Labex UnivEarthS; Centro de Investigaciones Energéticas, Medioambientales y Tecnológicas; Ministerio de Ciencia e Innovación; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Science and Technology Facilities Council; Natural Sciences and Engineering Research Council of Canada; Istituto Nazionale di Fisica Nucleare; European Regional Development Fund; Fundacja na rzecz Nauki Polskiej; Fundação de Amparo à Pesquisa do Estado de São Paulo; Russian Science Foundation; National Science Foundation; Royal Society; Agence Nationale de la Recherche","keywords":"Computer science","score_opus":0.025960646518737748,"score_gpt":0.36666046586919265,"score_spread":0.3406998193504549,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385845941","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000020696969,0.015211514,0.000042860687,0.4230758,0.0047021215,0.0006008885,0.0000334993,0.00019985277,0.55611277],"genre_scores_gemma":[0.000022667085,0.006656727,0.00066122157,0.099927284,0.0010846392,0.00009473996,0.0036187926,0.00009712686,0.8878368],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9967706,0.00008811688,0.00061304093,0.00072471605,0.0014474788,0.00035602556],"domain_scores_gemma":[0.9981254,0.00013501012,0.00027363803,0.0010544696,0.00011463417,0.00029687496],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0013476792,0.00033988358,0.0009920457,0.00023588273,0.00015000142,0.000022367538,0.0002607535,0.00013766783,0.078043774],"category_scores_gemma":[0.0020058814,0.00026443606,0.00040577623,0.00031178858,0.000074768526,0.000016962887,0.00022666638,0.0027033186,0.0003491246],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015129868,0.0000984445,0.000053969245,0.0019534011,0.00011301403,0.005024066,0.000005087003,0.000003373053,0.0000025659901,0.00015457047,0.9663008,0.026275571],"study_design_scores_gemma":[0.00036431514,0.00025302812,0.00008331255,0.0029667658,0.00042252603,0.0036718424,0.0000041825856,0.00013587328,0.0000026115563,0.000032831165,0.9918063,0.00025636985],"about_ca_topic_score_codex":0.00019834751,"about_ca_topic_score_gemma":0.0000020609023,"teacher_disagreement_score":0.33172402,"about_ca_system_score_codex":0.00024870582,"about_ca_system_score_gemma":0.00055919366,"threshold_uncertainty_score":0.9999808},"labels":[],"label_agreement":null},{"id":"W4385880495","doi":"10.1016/j.isci.2023.107634","title":"Radiomics and deep learning models to differentiate lung adenosquamous carcinoma: A multicenter trial","year":2023,"lang":"en","type":"article","venue":"iScience","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Radiomics; Adenosquamous carcinoma; Receiver operating characteristic; Medicine; Artificial intelligence; Predictive value; Adenocarcinoma; Machine learning; Oncology; Internal medicine; Radiology; Computer science; Cancer","score_opus":0.027214784145448184,"score_gpt":0.2967170128891118,"score_spread":0.2695022287436636,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385880495","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9809981,0.00039444002,0.015267501,0.0018496929,0.00042176546,0.00042012383,8.69051e-7,0.0001431549,0.0005043484],"genre_scores_gemma":[0.996738,0.000085498716,0.0014326831,0.0005203583,0.00018182272,0.00002153636,0.0000055029013,0.00002137765,0.0009931786],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985574,0.00005034064,0.00020828634,0.00040845035,0.00035254346,0.0004230163],"domain_scores_gemma":[0.9992797,0.00010757402,0.000048523318,0.00017853684,0.000036706624,0.00034896442],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004883342,0.00013079698,0.0002405724,0.00021818654,0.0002159109,0.00008228021,0.00014854984,0.000046745405,0.000017847175],"category_scores_gemma":[0.00042052538,0.000107764914,0.000054695964,0.00044468426,0.00012605485,0.00011849155,0.00016502377,0.00036073625,0.000032524724],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.016164914,0.00076766656,0.2929065,0.0008458586,0.00019272514,0.0018801801,0.06056594,0.053092636,0.08251268,0.0026838658,0.0074909707,0.4808961],"study_design_scores_gemma":[0.010606567,0.00020894484,0.023670929,0.00005214685,0.000042434935,0.00003900019,0.00025149493,0.96401966,0.00008031674,0.00009625395,0.0007933236,0.0001389472],"about_ca_topic_score_codex":0.00007053094,"about_ca_topic_score_gemma":0.0000032160704,"teacher_disagreement_score":0.910927,"about_ca_system_score_codex":0.000049025723,"about_ca_system_score_gemma":0.00003832369,"threshold_uncertainty_score":0.4394526},"labels":[],"label_agreement":null},{"id":"W4385913284","doi":"10.1088/1361-6560/acf183","title":"Haralick texture analysis for microdosimetry: characterization of Monte Carlo generated 3D specific energy distributions","year":2023,"lang":"en","type":"article","venue":"Physics in Medicine and Biology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Voxel; Homogeneity (statistics); Monte Carlo method; Entropy (arrow of time); Computational physics; Physics; Statistical physics; Statistics; Mathematics; Computer science; Artificial intelligence","score_opus":0.09779118582444028,"score_gpt":0.3670391472049657,"score_spread":0.2692479613805254,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385913284","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8889357,0.00047375154,0.10517973,0.004819338,0.00019201293,0.0001695721,0.000120181285,0.000038500133,0.00007124252],"genre_scores_gemma":[0.99413204,0.001507865,0.00045773524,0.0005068586,0.00054524746,0.00002015557,0.0026551413,0.000011621883,0.00016335615],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991419,0.00005269722,0.0002942192,0.00024719542,0.000064259744,0.0001997681],"domain_scores_gemma":[0.99945724,0.000118045566,0.00011067792,0.00015068364,0.000095033996,0.0000683229],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027052287,0.00011612302,0.00052085426,0.0002715754,0.000047197398,0.000003611996,0.000057940855,0.000087927685,0.000017651284],"category_scores_gemma":[0.00012548828,0.000085420375,0.000069745656,0.0013294579,0.00021019139,0.000021835296,0.000027103331,0.00014785191,5.858168e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001031366,0.000097522905,0.09914032,0.00009519375,0.0004906315,0.000007711204,0.00032136697,0.00017231588,0.8364596,0.005887042,0.0022701279,0.054955047],"study_design_scores_gemma":[0.007501046,0.001160628,0.35209522,0.0003486663,0.0019472828,0.000021854354,0.00029268832,0.46913567,0.013871647,0.0029079528,0.15016058,0.0005567528],"about_ca_topic_score_codex":0.00017830236,"about_ca_topic_score_gemma":0.0000070695633,"teacher_disagreement_score":0.8225879,"about_ca_system_score_codex":0.000019198655,"about_ca_system_score_gemma":0.000020950678,"threshold_uncertainty_score":0.3483342},"labels":[],"label_agreement":null},{"id":"W4386014858","doi":"10.1007/978-3-662-67868-8_7","title":"Addressing Dataset Shift for Trustworthy Deep Learning Diagnostic Ultrasound Decision Support","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; McMaster University; St. Joseph’s Healthcare Hamilton","funders":"","keywords":"Computer science; Artificial intelligence; Deep learning; Modality (human–computer interaction); Leverage (statistics); Cluster analysis; Medical imaging; Medical diagnosis; Software portability; Software deployment; Machine learning; Pattern recognition (psychology); Data mining","score_opus":0.029851445197041387,"score_gpt":0.3275378091721294,"score_spread":0.29768636397508796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386014858","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00043697414,0.0003367169,0.9954341,0.00080100104,0.0016952924,0.000616938,0.00007343272,0.00014700566,0.0004585556],"genre_scores_gemma":[0.31111696,0.001108737,0.66237944,0.010318879,0.006046348,0.00009258305,0.006632776,0.00055824325,0.0017460304],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99655384,0.000026500817,0.00056799024,0.0011912602,0.0009481319,0.00071227096],"domain_scores_gemma":[0.9908083,0.007861225,0.00025263,0.00064670114,0.00011582194,0.00031534102],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0016890145,0.00044470126,0.00071128656,0.0006834579,0.00039344904,0.00028147406,0.00067327486,0.00030302655,0.00010463383],"category_scores_gemma":[0.0075885444,0.00038432216,0.00016058901,0.00033302605,0.0006678026,0.00015961482,0.00034869183,0.0017258069,0.000060778784],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048852497,0.000024377458,0.0014570061,0.00017326268,0.000027548023,0.00041657742,0.00036209225,0.031893734,0.000056754525,0.00028513325,0.00065366377,0.964601],"study_design_scores_gemma":[0.0033570887,0.001291871,0.005906473,0.0064427117,0.00035742891,0.0008957408,0.0000021973913,0.8172978,0.00018433081,0.077722296,0.084840365,0.0017016506],"about_ca_topic_score_codex":0.000018260527,"about_ca_topic_score_gemma":0.00003792175,"teacher_disagreement_score":0.9628993,"about_ca_system_score_codex":0.00018295224,"about_ca_system_score_gemma":0.00036549807,"threshold_uncertainty_score":0.9998609},"labels":[],"label_agreement":null},{"id":"W4386033160","doi":"10.1136/jnis-2023-esmint.5","title":"O05/57  Validation of a novel multiphase CTA perfusion tool compared to CTP in patients with suspected acute ischemic stroke","year":2023,"lang":"en","type":"article","venue":"Abstracts","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Circle Cardiovascular Imaging","funders":"","keywords":"Medicine; Perfusion; Perfusion scanning; Radiology; Angiography; Stroke (engine); Nuclear medicine; Occlusion; Internal medicine","score_opus":0.012810727761947983,"score_gpt":0.28555536533284304,"score_spread":0.27274463757089507,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386033160","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99797225,0.0000030991014,0.00017242356,0.00068003015,0.000080529455,0.00046069745,0.000024574356,0.00006979461,0.0005366257],"genre_scores_gemma":[0.99601823,0.0000031804273,0.003155567,0.00016778012,0.00003993371,0.000010188471,0.0003771909,0.000025048752,0.00020285204],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9987687,0.000013625396,0.00033944717,0.00024136185,0.00039243823,0.0002444615],"domain_scores_gemma":[0.99931836,0.00008007449,0.00012194146,0.00021865277,0.00012207466,0.00013891049],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021966767,0.00012862755,0.00026974667,0.00025091262,0.000032775548,0.000015856818,0.000074507414,0.000056637462,0.00003604182],"category_scores_gemma":[0.00038479277,0.000106348234,0.0000356908,0.00041136701,0.00003368575,0.00008120743,0.000044122862,0.00028182776,0.000028934819],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016136398,0.0010912529,0.45013416,0.000110556466,0.00007711661,0.000102954,0.00097583624,0.0062722946,0.53252697,0.00000872561,0.0019694767,0.005117019],"study_design_scores_gemma":[0.008030919,0.0002805877,0.9580389,0.00026823566,0.000060874718,0.000005811993,0.000057609395,0.00907883,0.023528637,0.0000011036103,0.0005139644,0.00013448232],"about_ca_topic_score_codex":0.00016820889,"about_ca_topic_score_gemma":0.0000067595884,"teacher_disagreement_score":0.50899833,"about_ca_system_score_codex":0.000056612676,"about_ca_system_score_gemma":0.00006558196,"threshold_uncertainty_score":0.4336755},"labels":[],"label_agreement":null},{"id":"W4386303854","doi":"10.4095/332136","title":"GSC at work 2022","year":2023,"lang":"en","type":"report","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Natural Resources Canada","funders":"","keywords":"Work (physics); Computer science; Engineering; Mechanical engineering","score_opus":0.05961919631591688,"score_gpt":0.38222866340046885,"score_spread":0.32260946708455196,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386303854","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003129955,0.0019998027,0.00019686026,0.006011137,0.004995345,0.00034501465,0.000007694055,0.00063544675,0.9826788],"genre_scores_gemma":[0.0013230478,0.005041388,0.0007607133,0.0011191509,0.002441647,0.00002691757,0.0006495398,0.00015909944,0.9884785],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974717,0.000027025035,0.00039671504,0.00045878885,0.0012674672,0.00037831903],"domain_scores_gemma":[0.9987386,0.00014772474,0.00014404664,0.0005138138,0.00015532848,0.00030050954],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0009882011,0.00025371424,0.0006587816,0.00021741248,0.00006603485,0.000022147633,0.0001341769,0.00031635576,0.0034727668],"category_scores_gemma":[0.0013318317,0.00019272535,0.00027815293,0.00036807178,0.00008212395,0.000012610265,0.0002362559,0.0012985287,0.0019098805],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018330995,0.000020645371,0.010942318,0.00033368467,0.00015234241,0.00070383656,0.000017548244,0.0000028245,0.000029380279,0.000013957285,0.94465613,0.04310902],"study_design_scores_gemma":[0.0003410668,0.000040780586,0.007840487,0.000784528,0.00021065834,0.00039051924,0.0000092929085,0.00016847815,0.00000875513,0.00003115662,0.9899703,0.00020395886],"about_ca_topic_score_codex":0.00027615475,"about_ca_topic_score_gemma":0.0000123123455,"teacher_disagreement_score":0.045314204,"about_ca_system_score_codex":0.00056786276,"about_ca_system_score_gemma":0.00070689566,"threshold_uncertainty_score":0.9988673},"labels":[],"label_agreement":null},{"id":"W4386317752","doi":"10.7759/cureus.44476","title":"The Use of Radiomic Features to Predict Human Papillomavirus (HPV) Status in Head and Neck Tumors: A Review","year":2023,"lang":"en","type":"review","venue":"Cureus","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; McMaster University Medical Centre","funders":"","keywords":"Medicine; Radiomics; Human papillomavirus; Head and neck; Head and neck cancer; Radiological weapon; Oncology; Radiology; Internal medicine; Radiation therapy; Surgery","score_opus":0.08611098655353801,"score_gpt":0.4034752758955136,"score_spread":0.3173642893419756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386317752","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004396912,0.99655825,0.0000035744658,0.00048748896,0.00020632135,0.002016861,0.000047293066,0.00006762322,0.00017289241],"genre_scores_gemma":[0.0000113995475,0.9969711,0.00039107396,0.0005915284,0.00023341854,0.0001639788,0.00014340422,0.000110620604,0.001383521],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972127,0.00028830706,0.0010505408,0.0005044134,0.00040983612,0.00053418346],"domain_scores_gemma":[0.9978262,0.0006075742,0.00037605155,0.0007627227,0.000056385863,0.00037106755],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008521347,0.00042611634,0.002455543,0.00020132386,0.00013073,0.000045142788,0.0002921247,0.00017950365,0.000027007763],"category_scores_gemma":[0.002702935,0.0002602975,0.0003233407,0.000596342,0.00021938582,0.000055002743,0.00020798748,0.0011454055,0.000020963173],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022164188,0.00006775353,0.0005051448,0.073076956,0.00028903878,0.0003739786,0.00014502606,0.0000011931688,0.000003454652,0.00016165031,0.06975874,0.8555949],"study_design_scores_gemma":[0.0003908918,0.00017450379,0.0019482577,0.14228652,0.0006123209,0.00022568085,0.000005846971,0.0000147301325,1.3105051e-7,0.000021798516,0.8541252,0.00019409733],"about_ca_topic_score_codex":0.00072341814,"about_ca_topic_score_gemma":0.00011091872,"teacher_disagreement_score":0.8554008,"about_ca_system_score_codex":0.00017899965,"about_ca_system_score_gemma":0.00034175723,"threshold_uncertainty_score":0.9999849},"labels":[],"label_agreement":null},{"id":"W4386392680","doi":"10.5770/cgj.26.685","title":"Radiomic Biomarkers as a Non-Invasive Tool for Assessing Biological Age","year":2023,"lang":"en","type":"article","venue":"Canadian Geriatrics Journal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine; Medical physics","score_opus":0.023365668771473277,"score_gpt":0.30730439103696544,"score_spread":0.28393872226549216,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386392680","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9822889,0.00030837784,0.0038099035,0.009238839,0.0017750062,0.00044137466,0.00002010953,0.00007542975,0.0020420756],"genre_scores_gemma":[0.98330915,0.0006808291,0.009283898,0.0035965536,0.0022141554,0.000022735754,0.00011334349,0.00006810509,0.00071121234],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99821895,0.00006238811,0.00039853473,0.00028168803,0.00023602377,0.0008024042],"domain_scores_gemma":[0.99794394,0.0003520546,0.00015034377,0.00017976196,0.00013767827,0.0012362357],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013412214,0.0001895747,0.00037033024,0.00094079983,0.00050351874,0.00029135728,0.00020686159,0.0001883741,0.000117108466],"category_scores_gemma":[0.003362848,0.00016067638,0.00026424899,0.0007659696,0.000108421846,0.0001116914,0.000024992669,0.00063295313,0.000085169086],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032833676,0.00009590345,0.11883165,0.00036671787,0.0010815688,0.030393861,0.0013822585,0.00035767682,0.044988845,0.0008513873,0.53780884,0.26351294],"study_design_scores_gemma":[0.017891863,0.0015335161,0.33908162,0.0009162647,0.00094495725,0.023887765,0.002460641,0.038866073,0.000801775,0.00929937,0.56211716,0.0021989832],"about_ca_topic_score_codex":0.0015768054,"about_ca_topic_score_gemma":0.0002513809,"teacher_disagreement_score":0.26131395,"about_ca_system_score_codex":0.00052653666,"about_ca_system_score_gemma":0.002522739,"threshold_uncertainty_score":0.65521926},"labels":[],"label_agreement":null},{"id":"W4386447283","doi":"10.1101/2023.09.04.23294952","title":"Foundation Models for Quantitative Biomarker Discovery in Cancer Imaging","year":2023,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"National Institutes of Health; European Commission","keywords":"Foundation (evidence); Computer science; Artificial intelligence; Machine learning; Deep learning; Biomarker; Biomarker discovery; Downstream (manufacturing); Data science; Biology; Proteomics; Engineering","score_opus":0.08922738024977103,"score_gpt":0.40257435187578167,"score_spread":0.31334697162601066,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386447283","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.63930553,0.0010486749,0.3371385,0.018109603,0.0023791755,0.00126128,0.000050827406,0.00016948541,0.0005369305],"genre_scores_gemma":[0.9849477,0.00078054785,0.010011489,0.00070636545,0.00032017005,0.00067987444,0.0004226631,0.00013395827,0.0019972702],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982235,0.00007238991,0.00044927772,0.00061035797,0.00029549704,0.00034897737],"domain_scores_gemma":[0.99893844,0.00033096183,0.00019313757,0.0003297368,0.00011078997,0.000096942014],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001010393,0.0002483338,0.00051104644,0.00040018075,0.000057972164,0.000099048964,0.00016713032,0.00011866944,0.000021525175],"category_scores_gemma":[0.0008093431,0.00022147624,0.00018564743,0.00020701824,0.00010517416,0.00017516715,0.00021590998,0.00071207667,0.000013297975],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010181556,0.00042494445,0.78169096,0.0049326406,0.0007397425,0.0003426393,0.0037099565,0.07434176,0.009209836,0.009665596,0.007047764,0.10687602],"study_design_scores_gemma":[0.0010808806,0.000022919972,0.06914095,0.0015003274,0.00011881738,0.0000043484615,0.00011858423,0.9078854,0.000060091512,0.01845116,0.0013758551,0.0002406655],"about_ca_topic_score_codex":0.0012235101,"about_ca_topic_score_gemma":0.00011198639,"teacher_disagreement_score":0.83354366,"about_ca_system_score_codex":0.00022808289,"about_ca_system_score_gemma":0.00030642183,"threshold_uncertainty_score":0.9031539},"labels":[],"label_agreement":null},{"id":"W4386462540","doi":"10.18280/rces.100202","title":"Automatic Segmentation of Cervical Precancerous Lesions in Colposcopy Image Using Pyramid Scene Parsing Network and Transfer Learning","year":2023,"lang":"en","type":"article","venue":"Review of Computer Engineering Studies","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Hebei University","keywords":"Colposcopy; Artificial intelligence; Pyramid (geometry); Parsing; Computer science; Segmentation; Transfer of learning; Computer vision; Medicine; Cervical cancer; Internal medicine; Mathematics","score_opus":0.02167566719883211,"score_gpt":0.33807243606759063,"score_spread":0.3163967688687585,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386462540","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8646007,0.07781984,0.05636807,0.00048146895,0.00020339106,0.00042336862,7.361182e-7,0.00009555388,0.0000068680993],"genre_scores_gemma":[0.71800286,0.13546596,0.14610149,0.00016256518,0.0001909118,0.000019888334,0.000010561756,0.00004096213,0.0000048160714],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989997,0.000052268948,0.00045435605,0.00014247322,0.0001670919,0.00018409318],"domain_scores_gemma":[0.9995405,0.00021290597,0.000061560764,0.00008240576,0.00005935028,0.00004325006],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00052957126,0.00012242909,0.0006536978,0.00011152523,0.000035829173,0.0000052508385,0.000040470055,0.000024562647,0.0000031800055],"category_scores_gemma":[0.00013125874,0.000107242566,0.000059977752,0.00043992256,0.00006006594,0.000044897326,0.00005000701,0.0002009169,4.2579373e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022996941,0.00009348784,0.018996954,0.1477981,0.0006006148,0.000066163804,0.0028812636,0.42401227,0.010421891,0.00011330201,0.0003407041,0.39465225],"study_design_scores_gemma":[0.00048731256,0.00009586973,0.022426592,0.051055156,0.00014529473,0.000021028955,0.000038763832,0.9253386,0.00017179383,0.0000083483155,0.00011744809,0.00009379311],"about_ca_topic_score_codex":0.000009128161,"about_ca_topic_score_gemma":3.5714837e-7,"teacher_disagreement_score":0.5013263,"about_ca_system_score_codex":0.000045925713,"about_ca_system_score_gemma":0.000023556744,"threshold_uncertainty_score":0.4373225},"labels":[],"label_agreement":null},{"id":"W4386532017","doi":"10.1177/08465371231201755","title":"CARJ Editor’s Award 2023","year":2023,"lang":"en","type":"editorial","venue":"Canadian Association of Radiologists Journal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hospital for Sick Children; University of Toronto","funders":"","keywords":"Medicine","score_opus":0.008217778371435319,"score_gpt":0.2866725250784702,"score_spread":0.27845474670703485,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386532017","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000267,0.0004521864,0.000068923895,0.008578186,0.9878818,0.00015828041,0.00036142766,0.000056821875,0.0021753858],"genre_scores_gemma":[0.00041515828,0.0020804913,0.00032490038,0.00024513656,0.97219485,0.0000072358584,0.0007009513,0.00009359033,0.02393769],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9963015,0.0002699682,0.0008501171,0.00034054517,0.0013981373,0.0008397574],"domain_scores_gemma":[0.99420553,0.0017973421,0.0013293944,0.0002875621,0.0011341933,0.0012459682],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.0036228455,0.00031605037,0.0010712075,0.00080557907,0.00023707823,0.00009602365,0.00039300867,0.001640374,0.00015808482],"category_scores_gemma":[0.04855831,0.00029479957,0.00044380568,0.00036700277,0.00012414427,0.00006875609,0.000030396037,0.0042322255,0.00014587773],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000017014658,0.000010776871,0.005250537,0.00008207064,0.00044944687,0.00036944696,0.00006715047,0.00004227926,0.000009515922,0.000009308694,0.99240935,0.0012831151],"study_design_scores_gemma":[0.0010783089,0.00016361133,0.0028529605,0.00033835162,0.00027390357,0.00006223481,0.00005543818,0.00015760718,0.0000011115642,0.00009632769,0.9946836,0.00023652255],"about_ca_topic_score_codex":0.015614899,"about_ca_topic_score_gemma":0.008900918,"teacher_disagreement_score":0.044935465,"about_ca_system_score_codex":0.005797853,"about_ca_system_score_gemma":0.0074126893,"threshold_uncertainty_score":0.9999504},"labels":[],"label_agreement":null},{"id":"W4386555777","doi":"10.48550/arxiv.2309.02555","title":"A Survey of the Impact of Self-Supervised Pretraining for Diagnostic Tasks with Radiological Images","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Machine learning; Generalization; Artificial intelligence; Computer science; Transfer of learning; Supervised learning; Feature (linguistics); Segmentation; Task (project management); Artificial neural network; Mathematics","score_opus":0.08888199189704302,"score_gpt":0.2588164170308586,"score_spread":0.1699344251338156,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386555777","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97813046,0.00007114894,0.020331228,0.000097877724,0.00012732929,0.00080551393,0.00016595726,0.0000797045,0.00019077811],"genre_scores_gemma":[0.99828875,0.00015815363,0.0011576053,0.000021778244,0.00004980672,0.0000027770045,0.00009229015,0.000038600752,0.0001902502],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99860847,0.00024879724,0.00026028097,0.000494854,0.00010907119,0.00027854886],"domain_scores_gemma":[0.9965256,0.0021139858,0.00034064613,0.0005969648,0.0002835419,0.00013926826],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00083254796,0.00024679984,0.00070151675,0.0001413921,0.000064906104,0.0000101814185,0.0004405586,0.00021505314,0.000022082564],"category_scores_gemma":[0.003209235,0.00015676943,0.00039490752,0.000431361,0.00034522745,0.00003087014,0.00032483955,0.00074173283,0.000001187058],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004339308,0.0001857903,0.9039547,0.000527497,0.0008614758,0.00009786494,0.00035868946,0.09211537,0.000190654,0.00018460493,0.0005905697,0.00049885485],"study_design_scores_gemma":[0.0015254114,0.00045602175,0.6523186,0.00054035994,0.00039625025,0.000009533466,0.00007085561,0.34409314,0.000041142026,0.00039673876,0.0000031072013,0.000148854],"about_ca_topic_score_codex":0.0014239374,"about_ca_topic_score_gemma":0.000018288292,"teacher_disagreement_score":0.25197777,"about_ca_system_score_codex":0.00011553721,"about_ca_system_score_gemma":0.00047202964,"threshold_uncertainty_score":0.6392872},"labels":[],"label_agreement":null},{"id":"W4386565864","doi":"10.1016/j.media.2023.102942","title":"Deep learning, data ramping, and uncertainty estimation for detecting artifacts in large, imbalanced databases of MRI images","year":2023,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre; McGill University; NeuroRx Research (Canada); Montreal Neurological Institute and Hospital","funders":"","keywords":"Computer science; Artificial intelligence; Artifact (error); Transfer of learning; Neuroimaging; Deep learning; Inference; Machine learning; Data quality; Pattern recognition (psychology); Data mining","score_opus":0.022595957263734208,"score_gpt":0.3643586328800441,"score_spread":0.3417626756163099,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386565864","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33880672,0.00036557735,0.6569595,0.0032468284,0.000055353386,0.00028546154,0.000037608013,0.00013085802,0.00011212517],"genre_scores_gemma":[0.96996635,0.0006318201,0.026286343,0.00031232368,0.00010117884,0.000024226125,0.0024985455,0.000028335444,0.00015089709],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977266,0.00013515593,0.0005781537,0.0005374179,0.00059878716,0.00042383958],"domain_scores_gemma":[0.9979655,0.00093190063,0.00020863947,0.00051913154,0.00010427543,0.00027054347],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0031359084,0.00016406024,0.0006826277,0.00063024426,0.000114854636,0.000034321925,0.00023554293,0.00008020211,0.0001922633],"category_scores_gemma":[0.022057282,0.00013926743,0.00012067514,0.0015252101,0.00019705365,0.00020755072,0.00029766062,0.0005147582,0.0000068508293],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028566804,0.00040927756,0.49836504,0.0013702059,0.0019013117,0.0004793132,0.0010718119,0.019645598,0.007568093,0.000067512105,0.0028059292,0.46603024],"study_design_scores_gemma":[0.0014927008,0.000052902986,0.044185653,0.00017628253,0.00080788386,0.000010778714,0.00036053386,0.9513507,0.0003400102,0.000050025672,0.0010498767,0.00012264577],"about_ca_topic_score_codex":0.00041534097,"about_ca_topic_score_gemma":0.00023847309,"teacher_disagreement_score":0.9317051,"about_ca_system_score_codex":0.00002908933,"about_ca_system_score_gemma":0.000078916426,"threshold_uncertainty_score":0.98618037},"labels":[],"label_agreement":null},{"id":"W4386609016","doi":"10.21203/rs.3.rs-3309060/v1","title":"Predicting MACE from [82Rb] PET: Can AI outperformmore traditional quantitative assessment of themyocardial perfusion ?","year":2023,"lang":"en","type":"preprint","venue":"Research Square","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Hasler Stiftung; Swiss Cancer Research Foundation; Centre Hospitalier Universitaire Vaudois; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Mace; Computer science; Myocardial perfusion imaging; Artificial intelligence; Machine learning; Medicine; Internal medicine; Cardiology; Perfusion; Myocardial infarction","score_opus":0.12591697840905247,"score_gpt":0.46424070436083187,"score_spread":0.3383237259517794,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386609016","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9736645,0.00035744044,0.0016533473,0.016742863,0.00089266145,0.0014196567,0.0013764533,0.00016870702,0.0037243294],"genre_scores_gemma":[0.98810357,0.0006300239,0.0060202572,0.00016610227,0.0012876227,0.00017800537,0.002990616,0.000117221534,0.0005065706],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99401253,0.0006730002,0.000654194,0.0008710821,0.0031043452,0.00068486226],"domain_scores_gemma":[0.99613106,0.0016815824,0.00022497395,0.0006904008,0.00084124977,0.00043071236],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.003290694,0.00033789754,0.00087358913,0.0006305687,0.00032625356,0.00010002011,0.000423976,0.00026358702,0.00043768255],"category_scores_gemma":[0.002522439,0.00028978373,0.00041001878,0.0003981711,0.00047655558,0.00005933199,0.0008796153,0.0057481523,0.000021095348],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011541037,0.0016815292,0.8843815,0.008476002,0.0023123228,0.0023972886,0.01295652,0.0144063,0.014710603,0.009966573,0.028818797,0.018738497],"study_design_scores_gemma":[0.001989819,0.000996144,0.4228356,0.0070955125,0.00019667853,0.000040833456,0.0038713582,0.5563064,0.00032996852,0.005138227,0.0008169939,0.00038248356],"about_ca_topic_score_codex":0.0044617527,"about_ca_topic_score_gemma":0.00007711295,"teacher_disagreement_score":0.5419001,"about_ca_system_score_codex":0.0005535028,"about_ca_system_score_gemma":0.0020030367,"threshold_uncertainty_score":0.9999554},"labels":[],"label_agreement":null},{"id":"W4386784411","doi":"10.1158/1557-3265.aacrahns23-po-043","title":"Abstract PO-043: Development of an automated multi-objective model utilizing delta radiomics to predict locoregional recurrence in head and neck cancer patients treated with primary radiation","year":2023,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Medicine; Radiation therapy; Head and neck squamous-cell carcinoma; Head and neck cancer; Radiomics; Cancer; Radiology; Internal medicine","score_opus":0.13507518765071339,"score_gpt":0.4879719196419132,"score_spread":0.35289673199119986,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386784411","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9979053,0.00019472024,0.00014034557,0.0005266392,0.00007487269,0.00094574667,0.000044875625,0.00010358591,0.0000639117],"genre_scores_gemma":[0.9937932,0.0006741076,0.0047553484,0.00018850763,0.000078018034,0.00022264342,0.00020370065,0.000039095077,0.00004540042],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9971716,0.00018347823,0.00072665454,0.00060752284,0.00079976104,0.00051097455],"domain_scores_gemma":[0.9983336,0.00040763113,0.00013310663,0.00021649628,0.00044038641,0.00046883404],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021325469,0.00016820022,0.00047777814,0.00044531407,0.00012593741,0.000025191906,0.00017291274,0.00014386434,0.000012462974],"category_scores_gemma":[0.0009276364,0.00013735812,0.000039515988,0.0010158222,0.0002993787,0.00013336593,0.00011821931,0.0009432492,0.0000032986486],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018086002,0.0005021251,0.7552671,0.00020449047,0.00006760245,0.000026178013,0.0009926022,0.004442541,0.0002923005,0.0000029617975,0.00047992813,0.23591362],"study_design_scores_gemma":[0.003358466,0.0003355605,0.65432787,0.00072752626,0.0000113895585,0.0000010920107,0.000048087928,0.34087417,0.00012823084,0.000006362921,0.000085971886,0.0000953013],"about_ca_topic_score_codex":0.0013426263,"about_ca_topic_score_gemma":0.0005698252,"teacher_disagreement_score":0.33643162,"about_ca_system_score_codex":0.0005113321,"about_ca_system_score_gemma":0.0015139944,"threshold_uncertainty_score":0.5601302},"labels":[],"label_agreement":null},{"id":"W4386784429","doi":"10.1158/1557-3265.aacrahns23-po-036","title":"Abstract PO-036: A deep learning alternative to regional molecular testing for HPV status","year":2023,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Medicine; Population; Digital pathology; Cancer; Pathology; Cohort; Oncology; Digital image analysis; Artificial intelligence; Internal medicine; Computer science","score_opus":0.29081775354541795,"score_gpt":0.5751571198133621,"score_spread":0.2843393662679442,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386784429","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96924293,0.0005453769,0.0024735194,0.022356266,0.00042002273,0.0010689349,0.000010285326,0.00020285058,0.0036798264],"genre_scores_gemma":[0.9879174,0.00042917609,0.005453109,0.002269599,0.001596683,0.00037837954,0.000059101283,0.00008913114,0.0018074097],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99648565,0.00024626928,0.0005560588,0.00065007014,0.0010217859,0.0010401565],"domain_scores_gemma":[0.9931498,0.004895415,0.00009158886,0.00027798826,0.00074006803,0.0008451377],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00536703,0.0001483887,0.00040692702,0.00032429016,0.00028196434,0.00006936884,0.00025640617,0.00010128022,0.00019871708],"category_scores_gemma":[0.029319834,0.00012992862,0.00018163444,0.0010175366,0.00029465609,0.000049169397,0.00021213178,0.0021602502,0.00018990529],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009781352,0.00016512722,0.092846915,0.00028762463,0.0001970672,0.00050177024,0.0005256639,0.0047834874,0.006101911,0.0003691388,0.019855062,0.8733881],"study_design_scores_gemma":[0.0059743975,0.002566388,0.5534354,0.0009979864,0.000077602024,0.000024749363,0.00081636116,0.12906379,0.00055933616,0.0036861452,0.30228958,0.00050828955],"about_ca_topic_score_codex":0.0008900142,"about_ca_topic_score_gemma":0.00002162447,"teacher_disagreement_score":0.8728798,"about_ca_system_score_codex":0.0001990153,"about_ca_system_score_gemma":0.00047774267,"threshold_uncertainty_score":0.9788566},"labels":[],"label_agreement":null},{"id":"W4386784868","doi":"10.1158/1557-3265.aacrahns23-po-040","title":"Abstract PO-040: Comparing digital image analysis with a manual scoring approach for quantification of p63 and BRCA1 protein expression in oropharyngeal squamous cell carcinoma","year":2023,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Tissue microarray; Biomarker; Context (archaeology); Immunohistochemistry; Medicine; Oncology; Digital image analysis; Digital pathology; Digital polymerase chain reaction; Rank correlation; Pathology; Internal medicine; Biology; Gene; Polymerase chain reaction; Computer science","score_opus":0.13791106912026352,"score_gpt":0.46955963288802705,"score_spread":0.3316485637677635,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386784868","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99565774,0.00022798333,0.002119844,0.00037959614,0.000024747585,0.00094568764,0.000016329926,0.00003064517,0.00059740973],"genre_scores_gemma":[0.9971851,0.000040636653,0.0020292203,0.0000114319755,0.00014737548,0.00020640314,0.00010460128,0.000030914285,0.00024430777],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99765635,0.000120160104,0.00061379786,0.0005697288,0.00060576113,0.00043420595],"domain_scores_gemma":[0.9983897,0.0007132136,0.00013773228,0.0003137328,0.00021563725,0.00022994784],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002872675,0.0001251116,0.00058229524,0.0005090365,0.00010039643,0.00007381692,0.00016901312,0.000095859905,0.000015009203],"category_scores_gemma":[0.0008689248,0.00009677631,0.00010911038,0.0010407659,0.000392082,0.00013547673,0.00013126254,0.000904408,0.0000025913253],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002043604,0.0004925522,0.94001913,0.0015662443,0.00006524501,0.00006370741,0.00030528996,0.0009279547,0.03847969,0.000015164192,0.00024357555,0.015777817],"study_design_scores_gemma":[0.0037242507,0.00046481908,0.88213605,0.00021730647,0.000087898785,0.0000023620119,0.0004982645,0.10682073,0.005825923,0.000031504307,0.00005697386,0.00013393565],"about_ca_topic_score_codex":0.0005174287,"about_ca_topic_score_gemma":0.00002718765,"teacher_disagreement_score":0.10589278,"about_ca_system_score_codex":0.000071769166,"about_ca_system_score_gemma":0.00019660873,"threshold_uncertainty_score":0.39464232},"labels":[],"label_agreement":null},{"id":"W4386807108","doi":"10.1101/2023.09.14.23295596","title":"ReMIND: The Brain Resection Multimodal Imaging Database","year":2023,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"National Institutes of Health; Brigham and Women's Hospital","keywords":"Resection; Computer science; Database; Medicine; Surgery","score_opus":0.03019763176483569,"score_gpt":0.3404068865910313,"score_spread":0.3102092548261956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386807108","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7942648,0.0009002593,0.013326113,0.18126208,0.005231788,0.0011474362,0.000049612354,0.00073964405,0.003078277],"genre_scores_gemma":[0.97830224,0.00033422306,0.0038013973,0.004981012,0.0032121844,0.0001470603,0.0006327214,0.00020548211,0.008383703],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99756813,0.00021951442,0.0004299694,0.0007204081,0.00063307234,0.00042889622],"domain_scores_gemma":[0.99770254,0.0005484745,0.00019817823,0.0012396184,0.000097993514,0.00021320133],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0026360245,0.00029528074,0.00041188658,0.00023144872,0.00022251719,0.0000988849,0.00042745858,0.00014943002,0.00010517276],"category_scores_gemma":[0.0044097514,0.00020302355,0.00021533051,0.00022949911,0.00021657409,0.00004909721,0.0008602253,0.003043062,0.00016385109],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004796166,0.00029016152,0.5306299,0.002169007,0.0006028343,0.002795041,0.0026186444,0.0018257294,0.045315582,0.0004571019,0.3166073,0.09620907],"study_design_scores_gemma":[0.0025346582,0.00008805936,0.24055538,0.0031524894,0.000498505,0.00054808863,0.00045519948,0.61800563,0.0017009181,0.0021180448,0.1295271,0.00081595156],"about_ca_topic_score_codex":0.0008042348,"about_ca_topic_score_gemma":0.0000320404,"teacher_disagreement_score":0.6161799,"about_ca_system_score_codex":0.00011272044,"about_ca_system_score_gemma":0.00019537676,"threshold_uncertainty_score":0.99925697},"labels":[],"label_agreement":null},{"id":"W4386826462","doi":"10.1016/j.media.2023.102972","title":"Automatic Head and Neck Tumor segmentation and outcome prediction relying on FDG-PET/CT images: Findings from the second edition of the HECKTOR challenge","year":2023,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"Hasler Stiftung; Siemens Healthineers; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Artificial intelligence; Positron emission tomography; Segmentation; Computer science; Population; Percentile; Medicine; Leverage (statistics); Medical physics; Machine learning; Radiology; Mathematics; Statistics","score_opus":0.014450067475993525,"score_gpt":0.3054342986791619,"score_spread":0.29098423120316835,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386826462","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98330635,0.00015163026,0.00050244335,0.015251214,0.00019218575,0.00025872327,0.00007101985,0.00009006145,0.00017635197],"genre_scores_gemma":[0.99641496,0.00020278081,0.000524074,0.0020523625,0.00024153963,0.000028406539,0.00018048726,0.000022460452,0.00033289965],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99783194,0.00017897718,0.00053211075,0.00035032898,0.00087976275,0.00022685903],"domain_scores_gemma":[0.9986135,0.00064979907,0.00017081278,0.00032297906,0.0000463456,0.0001965803],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011245644,0.00017090564,0.00045917375,0.00020590518,0.00024730497,0.000054636614,0.00014328209,0.000027743596,0.000887304],"category_scores_gemma":[0.0017886908,0.00009844298,0.00015930408,0.00073135586,0.00035010843,0.0001272308,0.000106916385,0.000575673,0.000014179328],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000108649845,0.00037553394,0.90590554,0.0009482419,0.0028159777,0.0010246874,0.0028547116,0.000039479128,0.010188844,0.00007794072,0.023665315,0.051995058],"study_design_scores_gemma":[0.0016615323,0.0001354047,0.7449335,0.00037811618,0.0015368541,0.000096157135,0.00094239647,0.24868129,0.00053658977,0.00017360957,0.0007984774,0.00012606132],"about_ca_topic_score_codex":0.0002694645,"about_ca_topic_score_gemma":0.00004381959,"teacher_disagreement_score":0.24864182,"about_ca_system_score_codex":0.000048760114,"about_ca_system_score_gemma":0.00004119544,"threshold_uncertainty_score":0.9715357},"labels":[],"label_agreement":null},{"id":"W4386865122","doi":"10.1148/radiol.232082","title":"Evaluating Diagnostic Performance of ChatGPT in Radiology: Delving into Methods","year":2023,"lang":"en","type":"letter","venue":"Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":18,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; London Health Sciences Centre","funders":"","keywords":"Medicine; Radiology; Medical imaging; Medical physics; Nuclear medicine","score_opus":0.039250532902971945,"score_gpt":0.41765546048312446,"score_spread":0.37840492758015254,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386865122","genre_codex":"empirical","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5719667,0.0068583214,0.0030112427,0.412443,0.0036503028,0.0010754119,0.0000070428264,0.00024198495,0.00074598106],"genre_scores_gemma":[0.08077362,0.010293912,0.2523728,0.63308847,0.016874759,0.00059504143,0.0015163866,0.000703026,0.0037820027],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9957735,0.0013622822,0.0010317762,0.0007367005,0.0003070707,0.0007886885],"domain_scores_gemma":[0.9913796,0.007357215,0.0004520677,0.0006092406,0.00009938596,0.00010247967],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0039275563,0.00040969474,0.0017510295,0.00084518566,0.00007371425,0.000007974779,0.00039082504,0.0011883588,0.00010108434],"category_scores_gemma":[0.015075822,0.0003640294,0.0002178523,0.0004906965,0.0004907432,0.000043959684,0.00016801058,0.004525636,0.00004507186],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001921273,0.00007943918,0.079492174,0.004876986,0.00069451216,0.003466501,0.0026785282,0.0037216712,0.008706069,0.00007162695,0.5205762,0.37544417],"study_design_scores_gemma":[0.006323577,0.004036815,0.052659538,0.0052924654,0.0011449835,0.0069130897,0.00014808997,0.6026488,0.00047177327,0.0018107402,0.31693804,0.0016120705],"about_ca_topic_score_codex":0.00025404725,"about_ca_topic_score_gemma":0.000003085669,"teacher_disagreement_score":0.59892714,"about_ca_system_score_codex":0.00025346768,"about_ca_system_score_gemma":0.00031597877,"threshold_uncertainty_score":0.99988115},"labels":[],"label_agreement":null},{"id":"W4386888280","doi":"10.1007/s41666-023-00138-1","title":"Clinical Feature Ranking Based on Ensemble Machine Learning Reveals Top Survival Factors for Glioblastoma Multiforme","year":2023,"lang":"en","type":"article","venue":"Journal of Healthcare Informatics Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Ministero dell'Università e della Ricerca; Università degli Studi di Milano-Bicocca; European Commission; Dipartimenti di Eccellenza","keywords":"Concordance; Random forest; Artificial intelligence; Machine learning; Context (archaeology); Computer science; Glioblastoma; Feature (linguistics); Decision tree; Medicine; Data mining; Internal medicine; Biology","score_opus":0.1123547609147775,"score_gpt":0.4821533126688797,"score_spread":0.36979855175410214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386888280","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95628554,0.00019521445,0.005662601,0.03495619,0.001184247,0.0009697424,0.000022158338,0.000096489835,0.00062779326],"genre_scores_gemma":[0.98813605,0.000383773,0.008882157,0.0010118625,0.00078003056,0.000009812728,0.000060914932,0.000058915768,0.0006764699],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9945208,0.00059822144,0.0016553779,0.00015852448,0.0021578262,0.0009092475],"domain_scores_gemma":[0.9911294,0.0056340867,0.000664536,0.00031004008,0.0015211457,0.0007407727],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.017891632,0.00021614175,0.00085672125,0.001355653,0.0005213504,0.000110559384,0.00035352327,0.0002919007,0.000022687973],"category_scores_gemma":[0.017199416,0.00015335,0.00042428204,0.0009823145,0.00013915844,0.000195216,0.00009387633,0.004903954,0.000027473467],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008903336,0.00055469846,0.53615195,0.00920695,0.00040501766,0.0005766637,0.009100223,0.010872558,0.00069006893,0.0007397595,0.036474194,0.38632458],"study_design_scores_gemma":[0.0077895606,0.009083851,0.02494859,0.0024026798,0.00005859868,0.00018392653,0.005342865,0.8683755,0.00023041171,0.00033405362,0.08095801,0.0002919845],"about_ca_topic_score_codex":0.000039908933,"about_ca_topic_score_gemma":0.000011474239,"teacher_disagreement_score":0.85750294,"about_ca_system_score_codex":0.00029795247,"about_ca_system_score_gemma":0.00089264824,"threshold_uncertainty_score":0.99739176},"labels":[],"label_agreement":null},{"id":"W4386889230","doi":"10.4103/jcrt.jcrt_2298_21","title":"A machine learning approach for prediction of auditory brain stem response in patients after head-and-neck radiation therapy","year":2023,"lang":"en","type":"article","venue":"Journal of Cancer Research and Therapeutics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Head and neck; Medicine; Radiation therapy; Audiology; Head (geology); Radiology; Surgery; Biology","score_opus":0.05413692542853535,"score_gpt":0.39096201216066995,"score_spread":0.3368250867321346,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386889230","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9916375,0.0050590746,0.0003042318,0.0025504315,0.000101138256,0.00031118657,0.000013435954,0.0000067623164,0.000016201004],"genre_scores_gemma":[0.990276,0.008817371,0.00025005653,0.00017064289,0.0002276063,0.000024840203,0.000008379722,0.000020103664,0.00020504266],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9986008,0.00028205756,0.00031791293,0.000111212976,0.00047888455,0.00020915386],"domain_scores_gemma":[0.99901825,0.00041142877,0.0001375912,0.000065943575,0.00026051616,0.00010629016],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002902837,0.00007377322,0.00023315383,0.0004540175,0.000063778185,0.00001996926,0.000051136514,0.00006376028,0.000004611091],"category_scores_gemma":[0.00019141496,0.000054882337,0.000045385255,0.0002848707,0.00010601074,0.00007389694,0.00001912508,0.00062139734,1.240312e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.025511993,0.00021620147,0.7545831,0.00019538152,0.00017764307,0.0000081211,0.0017654798,0.00028746994,0.0039007172,0.000014076991,0.00024939192,0.2130904],"study_design_scores_gemma":[0.008879684,0.0047720354,0.9236078,0.00024239777,0.0000213066,0.00000717662,0.00014477754,0.039528638,0.00024207834,0.00017798967,0.022320308,0.000055777182],"about_ca_topic_score_codex":0.000018659024,"about_ca_topic_score_gemma":0.0000011534314,"teacher_disagreement_score":0.21303463,"about_ca_system_score_codex":0.00008597422,"about_ca_system_score_gemma":0.00015374074,"threshold_uncertainty_score":0.26996967},"labels":[],"label_agreement":null},{"id":"W4386955468","doi":"10.1007/s00330-023-10245-7","title":"The power of the radiologist’s last word: can deep learning models accurately differentiate between high-grade gliomas and metastasis through natural language processing on radiology reports?","year":2023,"lang":"en","type":"letter","venue":"European Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Medicine; Neuroradiology; Radiology; Interventional radiology; Metastasis; Medical physics; Neurology; Cancer; Internal medicine","score_opus":0.03557781134181018,"score_gpt":0.29449900154347475,"score_spread":0.2589211902016646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386955468","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.62987846,0.021483699,0.0008897483,0.33911848,0.0044050575,0.0013702102,0.00006043917,0.000562562,0.002231354],"genre_scores_gemma":[0.9551733,0.000954906,0.0003333537,0.037786443,0.0028447867,0.00002282933,0.00049030967,0.00028323304,0.0021108533],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99282706,0.0033241138,0.0011791646,0.0011223836,0.0004873787,0.0010599219],"domain_scores_gemma":[0.9957625,0.0016499175,0.0013138568,0.0010352007,0.00010634409,0.00013218193],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0017065674,0.0007399604,0.0016476519,0.00025378095,0.00065940927,0.00009409021,0.0007624035,0.00049433735,0.000014823336],"category_scores_gemma":[0.0019382308,0.0004086191,0.0003911595,0.00044308507,0.0016855916,0.000072908675,0.00045899826,0.0066702445,0.000009188056],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007914105,0.00018580804,0.03689972,0.0019111887,0.008274148,0.040815588,0.02401694,0.0043346463,0.003297756,0.0006370978,0.65903234,0.21980338],"study_design_scores_gemma":[0.008748692,0.003168113,0.30714446,0.0029966468,0.005510746,0.03213477,0.0034304021,0.01164117,0.00043684465,0.0032365287,0.61754054,0.0040110564],"about_ca_topic_score_codex":0.00012560184,"about_ca_topic_score_gemma":0.00001209108,"teacher_disagreement_score":0.32529485,"about_ca_system_score_codex":0.00012500233,"about_ca_system_score_gemma":0.00011647251,"threshold_uncertainty_score":0.99983656},"labels":[],"label_agreement":null},{"id":"W4386998495","doi":"10.1101/2023.09.22.23294942","title":"Radiomic-Based Prediction of Lesion-Specific Systemic Treatment Response in Metastatic Disease","year":2023,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; Princess Margaret Cancer Centre; Public Health Ontario; Ontario Institute for Cancer Research; University of Toronto; University Health Network","funders":"National Cancer Institute; National Institutes of Health; Sarcoma Alliance for Research through Collaboration","keywords":"Medicine; Systemic therapy; Disease; Lesion; Oncology; Internal medicine; Radiology; Pathology; Cancer","score_opus":0.06400496934056994,"score_gpt":0.3281873455063746,"score_spread":0.26418237616580464,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386998495","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9887679,0.002445016,0.0034086315,0.0028432196,0.00098465,0.0011887037,0.00015979535,0.00017999667,0.000022063212],"genre_scores_gemma":[0.9963496,0.0010665879,0.0012151122,0.00006833994,0.0001620211,0.00024239779,0.00031736345,0.00009550677,0.0004830801],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9969403,0.0006356077,0.00089182286,0.0006677833,0.00054553646,0.00031893555],"domain_scores_gemma":[0.99769574,0.0006511045,0.00032813303,0.0009005106,0.0000799584,0.00034454],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0017630362,0.00035499307,0.00094982306,0.00083578867,0.00004094411,0.000021903861,0.000196896,0.000113809736,0.00004230888],"category_scores_gemma":[0.0009883451,0.00029064523,0.0003286105,0.00032771932,0.0001397741,0.000023922175,0.00009817876,0.0006606776,0.000032655113],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.017744793,0.001807646,0.8413935,0.0056239413,0.0006959268,0.0064852117,0.001448566,0.07265856,0.037888583,0.00010265154,0.0015915728,0.012559082],"study_design_scores_gemma":[0.0064730356,0.000629078,0.7669571,0.0077032004,0.0006500218,0.00006479886,0.00014437376,0.21389553,0.0007923265,0.00023841973,0.002105132,0.00034700212],"about_ca_topic_score_codex":0.00012714368,"about_ca_topic_score_gemma":0.000002320814,"teacher_disagreement_score":0.14123696,"about_ca_system_score_codex":0.0006042831,"about_ca_system_score_gemma":0.00078458415,"threshold_uncertainty_score":0.9999546},"labels":[],"label_agreement":null},{"id":"W4387157655","doi":"10.1002/jum.16332","title":"Approaches and Limitations of Machine Learning for Synthetic Ultrasound Generation","year":2023,"lang":"en","type":"article","venue":"Journal of Ultrasound in Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Novo Nordisk","keywords":"Medicine; Machine learning; Artificial intelligence; Generative grammar; Ultrasound; Domain (mathematical analysis); Field (mathematics); Training set; Medical physics; Computer science; Radiology","score_opus":0.07982457367280858,"score_gpt":0.31347248089677415,"score_spread":0.23364790722396556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387157655","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9788399,0.0024481697,0.010073502,0.0073398896,0.0003355817,0.00028107016,0.0000023649004,0.000019698351,0.0006598623],"genre_scores_gemma":[0.987783,0.0057447017,0.005387685,0.00018431648,0.00055803265,0.000006579184,0.000049856262,0.000025473264,0.00026032244],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99845856,0.0000955375,0.0007389088,0.00014737732,0.00036444215,0.00019515329],"domain_scores_gemma":[0.99480194,0.004398771,0.00038860584,0.00010482799,0.00016380422,0.00014202805],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0022739428,0.0001288264,0.00054647104,0.0005257949,0.000071750386,0.000011376637,0.00008032371,0.00007080361,0.00002132047],"category_scores_gemma":[0.02265452,0.00009313279,0.0000835922,0.00041674692,0.00024152803,0.00009332606,0.000009945381,0.0005065388,8.474395e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00057026435,0.00043461172,0.16846633,0.0010101412,0.00048424836,0.000105265484,0.011136171,0.010475588,0.6659626,0.0025904155,0.009375049,0.12938935],"study_design_scores_gemma":[0.035205968,0.012451595,0.32888314,0.005749266,0.0025818457,0.011339614,0.01887829,0.4460571,0.009069499,0.008296603,0.12042059,0.0010664552],"about_ca_topic_score_codex":0.000019130635,"about_ca_topic_score_gemma":0.00000679143,"teacher_disagreement_score":0.6568931,"about_ca_system_score_codex":0.00004095398,"about_ca_system_score_gemma":0.00006962578,"threshold_uncertainty_score":0.98557806},"labels":[],"label_agreement":null},{"id":"W4387206833","doi":"10.1016/j.ijrobp.2023.06.1666","title":"Significance of Radiomics in Predicting Local Control for Patients with Malignant Liver Tumors Treated Using Stereotactic Body Radiotherapy","year":2023,"lang":"en","type":"article","venue":"International Journal of Radiation Oncology*Biology*Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Health Services","funders":"","keywords":"Medicine; Interquartile range; Nuclear medicine; Magnetic resonance imaging; Radiology; Receiver operating characteristic; Univariate analysis; Radiation treatment planning; Multivariate analysis; Radiation therapy; Internal medicine","score_opus":0.01349221788449431,"score_gpt":0.3151561161120196,"score_spread":0.3016638982275253,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387206833","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8838148,0.00012160285,0.11440264,0.00056380645,0.000559716,0.00045159363,0.00004605494,0.000023445675,0.000016356216],"genre_scores_gemma":[0.99489087,0.0001816257,0.0037602049,0.00035320126,0.00067834015,0.0000121699795,0.000074456584,0.00003895557,0.000010162033],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982655,0.00018249282,0.0008049151,0.00020791011,0.0002839801,0.00025520683],"domain_scores_gemma":[0.9972835,0.00075998897,0.0011372638,0.000102424834,0.0006085796,0.000108250504],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007384169,0.0001698217,0.0006120075,0.00032245004,0.00004497311,0.000013917878,0.00021412426,0.00013273604,0.0000101734495],"category_scores_gemma":[0.0004424305,0.0001384633,0.0001508182,0.00027340034,0.00025837315,0.00017316359,0.000016302909,0.00039933182,0.0000010082837],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0020316595,0.00042328206,0.9396092,0.000032916916,0.00060620264,0.00007508219,0.00037568237,0.011063059,0.0057695564,0.0005462612,0.00006477885,0.039402295],"study_design_scores_gemma":[0.026454547,0.0029282193,0.27258894,0.00035794693,0.00023104022,0.00014264468,0.00009665117,0.6946898,0.0009126095,0.0004992961,0.00089833257,0.00019995711],"about_ca_topic_score_codex":0.00005141505,"about_ca_topic_score_gemma":0.0000015161756,"teacher_disagreement_score":0.6836268,"about_ca_system_score_codex":0.0007032185,"about_ca_system_score_gemma":0.0004514285,"threshold_uncertainty_score":0.564637},"labels":[],"label_agreement":null},{"id":"W4387207193","doi":"10.1016/j.ijrobp.2023.06.1669","title":"Radiomic-Based Prediction of Lesion-Specific Systemic Treatment Response in Metastatic Disease","year":2023,"lang":"en","type":"article","venue":"International Journal of Radiation Oncology*Biology*Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Princess Margaret Cancer Centre; University Health Network","funders":"","keywords":"Medicine; Receiver operating characteristic; Lesion; Radiology; Lung cancer; Response Evaluation Criteria in Solid Tumors; Mann–Whitney U test; Nuclear medicine; Lung; Doxorubicin; Progressive disease; Oncology; Chemotherapy; Internal medicine; Pathology","score_opus":0.035873623318620276,"score_gpt":0.3574815005031362,"score_spread":0.32160787718451594,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387207193","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97738093,0.0007363233,0.014775906,0.005023487,0.0016383276,0.00027624526,0.00008682868,0.000044394,0.00003755022],"genre_scores_gemma":[0.99601513,0.0012874587,0.0014737289,0.0002645444,0.0007047692,0.000017493636,0.0001674654,0.000026923408,0.000042475556],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9978037,0.0005301647,0.00093234354,0.00020569043,0.00033250757,0.00019562473],"domain_scores_gemma":[0.9975168,0.0009949178,0.00080712995,0.00016276594,0.00033917208,0.00017921753],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013897757,0.00016162872,0.00053522625,0.00058497867,0.000038355738,0.000012802609,0.00020965374,0.00008289324,0.000029821747],"category_scores_gemma":[0.000824437,0.00013550946,0.00024669134,0.00035430293,0.00018943197,0.00011896516,0.000022985989,0.00033630652,0.000019277433],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.011227238,0.0013594673,0.6616543,0.00006319291,0.00077947654,0.0009729787,0.00093673344,0.046378717,0.050945815,0.0028306914,0.0017336336,0.2211178],"study_design_scores_gemma":[0.03795277,0.0057459814,0.56475246,0.0011167346,0.0005298061,0.0007147041,0.00042530903,0.34552222,0.0034546999,0.0051159067,0.034297645,0.00037177096],"about_ca_topic_score_codex":0.000011906097,"about_ca_topic_score_gemma":3.6594452e-7,"teacher_disagreement_score":0.2991435,"about_ca_system_score_codex":0.0011308291,"about_ca_system_score_gemma":0.00093825575,"threshold_uncertainty_score":0.5525915},"labels":[],"label_agreement":null},{"id":"W4387211173","doi":"10.1007/978-3-031-43901-8_65","title":"Learning Reliability of Multi-modality Medical Images for Tumor Segmentation via Evidence-Identified Denoising Diffusion Probabilistic Models","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Modality (human–computer interaction); Computer science; Segmentation; Reliability (semiconductor); Probabilistic logic; Artificial intelligence; Image segmentation; Medical imaging; Task (project management); Noise (video); Pattern recognition (psychology); Image (mathematics); Physics","score_opus":0.035843787594029966,"score_gpt":0.3299367687172087,"score_spread":0.2940929811231787,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387211173","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016713459,0.00017707837,0.97906137,0.0018951498,0.00082053547,0.0011555712,0.0000045796096,0.0001222958,0.000049962593],"genre_scores_gemma":[0.82569194,0.00012471472,0.17252062,0.00048534464,0.00045665543,0.000040316896,0.000044915574,0.00008732463,0.00054813805],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9958432,0.00009474905,0.0008943329,0.0011431574,0.0015628823,0.00046169368],"domain_scores_gemma":[0.9960623,0.0021856478,0.00045381032,0.00054276275,0.0004963202,0.00025916426],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0040794974,0.00036197156,0.0007840846,0.000446597,0.00024022353,0.00009141154,0.0005526687,0.0002598143,0.000029062718],"category_scores_gemma":[0.007925198,0.00030259715,0.00020656324,0.00031111465,0.0011518508,0.00025087115,0.00042671463,0.0013134516,0.0000039532647],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019333862,0.00018046731,0.0020252776,0.0027978348,0.000036560556,0.00012764108,0.0019657277,0.35571545,0.011321761,0.00025875756,0.000021707663,0.6253555],"study_design_scores_gemma":[0.0007603812,0.00024995976,0.00095601036,0.003850572,0.00007478607,0.00005054203,0.0000019656459,0.9574807,0.0010932441,0.03521121,0.000009463709,0.0002611128],"about_ca_topic_score_codex":0.00016203153,"about_ca_topic_score_gemma":0.000020120999,"teacher_disagreement_score":0.8089785,"about_ca_system_score_codex":0.00036331522,"about_ca_system_score_gemma":0.0006662672,"threshold_uncertainty_score":0.9999426},"labels":[],"label_agreement":null},{"id":"W4387211178","doi":"10.1007/978-3-031-43901-8_62","title":"Edge-Aware Multi-task Network for Integrating Quantification Segmentation and Uncertainty Prediction of Liver Tumor on Multi-modality Non-contrast MRI","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Modality (human–computer interaction); Artificial intelligence; Segmentation; Margin (machine learning); Pattern recognition (psychology); Feature (linguistics); Contrast (vision); Enhanced Data Rates for GSM Evolution; Image segmentation; Computer vision; Machine learning","score_opus":0.028352295192021097,"score_gpt":0.30098119613052887,"score_spread":0.2726289009385078,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387211178","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020538974,0.000091036614,0.9950956,0.0006245445,0.00094556826,0.0010525589,0.00004725686,0.000063115134,0.000026389642],"genre_scores_gemma":[0.6828521,0.00010623834,0.31473005,0.00081951724,0.00088893087,0.000048495764,0.00027604096,0.00006386267,0.00021475935],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99801636,0.000031884956,0.000502167,0.00074708695,0.0004043782,0.00029815402],"domain_scores_gemma":[0.9983327,0.00063200085,0.00035367138,0.00031323463,0.00025586228,0.00011254889],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012220971,0.0002746599,0.00046020205,0.00027852505,0.00019292193,0.00006492914,0.00020128579,0.00016045348,0.0000035812761],"category_scores_gemma":[0.0004465416,0.00022889905,0.00008942241,0.00020663634,0.00045716472,0.00009127481,0.00008508313,0.0006542596,0.0000019931545],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019553314,0.00013883559,0.00433513,0.0009056363,0.000074456744,0.000029215746,0.0019614478,0.28888282,0.0067525813,0.00075007684,0.00014289616,0.69583136],"study_design_scores_gemma":[0.0010574501,0.0002766095,0.009524757,0.0016369799,0.00005093368,0.000015537858,0.000003105672,0.9858187,0.00046593693,0.0009257931,0.000060258382,0.00016395135],"about_ca_topic_score_codex":0.00013708997,"about_ca_topic_score_gemma":0.00010416079,"teacher_disagreement_score":0.69693583,"about_ca_system_score_codex":0.00018309172,"about_ca_system_score_gemma":0.00018387746,"threshold_uncertainty_score":0.9334232},"labels":[],"label_agreement":null},{"id":"W4387211376","doi":"10.1007/978-3-031-43990-2","title":"Medical Image Computing and Computer Assisted Intervention – MICCAI 2023","year":2023,"lang":"en","type":"book","venue":"Lecture notes in computer science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":29,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Queen's University","funders":"National Institutes of Health; ShanghaiTech University; Technische Universität München; Nanjing University of Science and Technology; Hong Kong University of Science and Technology; University of Texas at Arlington; Central South University; Chinese Academy of Sciences; Imperial College London; Tencent; University of Pittsburgh; Nanjing University; Baidu; University of Twente; Rensselaer Polytechnic Institute; Massachusetts General Hospital; Beihang University; Nvidia; Arizona State University; Fudan University; Northwestern University; Beijing Institute of Technology; Northwestern Polytechnical University; University of California, Santa Cruz","keywords":"Computer science; Intervention (counseling); Multimedia; Human–computer interaction; Data science; Medicine; Nursing","score_opus":0.01164392047456572,"score_gpt":0.31198643814244326,"score_spread":0.30034251766787756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387211376","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037628538,0.00040468486,0.98825854,0.0035260387,0.002700058,0.00036619403,0.0000038243957,0.00022306023,0.00075477],"genre_scores_gemma":[0.13016644,0.0004759094,0.8224913,0.02004883,0.014571458,0.000025512094,0.0005271959,0.00047789636,0.011215461],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960376,0.000102428705,0.0006847912,0.0011643888,0.0013633107,0.0006474838],"domain_scores_gemma":[0.99777496,0.0008710771,0.00024878155,0.00048672454,0.0001741921,0.0004442728],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002382033,0.00042132114,0.00079794344,0.0008092448,0.00020665085,0.00027234736,0.00064674625,0.0004139859,0.0000648494],"category_scores_gemma":[0.00090347975,0.0003636013,0.00017925526,0.0007377372,0.0013123566,0.00012375372,0.001057074,0.0021754673,0.00005761343],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001627238,0.00006967587,0.00074458326,0.00045159028,0.00004295915,0.00093463075,0.00030432036,0.00052044436,0.00010231812,0.000051293275,0.0023085023,0.99445343],"study_design_scores_gemma":[0.0012587548,0.00024895705,0.0076582567,0.004453863,0.00004756607,0.00088827085,6.352238e-7,0.98126143,0.000033195556,0.0022424122,0.0015200878,0.0003865521],"about_ca_topic_score_codex":0.000058041696,"about_ca_topic_score_gemma":0.000032114327,"teacher_disagreement_score":0.99406683,"about_ca_system_score_codex":0.00032683986,"about_ca_system_score_gemma":0.00069638,"threshold_uncertainty_score":0.99988157},"labels":[],"label_agreement":null},{"id":"W4387211438","doi":"10.1007/978-3-031-43999-5","title":"Medical Image Computing and Computer Assisted Intervention – MICCAI 2023","year":2023,"lang":"en","type":"book","venue":"Lecture notes in computer science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":169,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Queen's University","funders":"National Institutes of Health; ShanghaiTech University; Technische Universität München; Nanjing University of Science and Technology; Hong Kong University of Science and Technology; University of Texas at Arlington; Central South University; Chinese Academy of Sciences; Imperial College London; Tencent; University of Pittsburgh; Nanjing University; Baidu; University of Twente; Rensselaer Polytechnic Institute; Massachusetts General Hospital; Beihang University; Nvidia; Arizona State University; Fudan University; Northwestern University; Beijing Institute of Technology; Northwestern Polytechnical University; University of California, Santa Cruz","keywords":"Computer science; Multimedia; Intervention (counseling); Human–computer interaction; Medical physics; Medicine","score_opus":0.01164392047456572,"score_gpt":0.31198643814244326,"score_spread":0.30034251766787756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387211438","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037628538,0.00040468486,0.98825854,0.0035260387,0.002700058,0.00036619403,0.0000038243957,0.00022306023,0.00075477],"genre_scores_gemma":[0.13016644,0.0004759094,0.8224913,0.02004883,0.014571458,0.000025512094,0.0005271959,0.00047789636,0.011215461],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960376,0.000102428705,0.0006847912,0.0011643888,0.0013633107,0.0006474838],"domain_scores_gemma":[0.99777496,0.0008710771,0.00024878155,0.00048672454,0.0001741921,0.0004442728],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002382033,0.00042132114,0.00079794344,0.0008092448,0.00020665085,0.00027234736,0.00064674625,0.0004139859,0.0000648494],"category_scores_gemma":[0.00090347975,0.0003636013,0.00017925526,0.0007377372,0.0013123566,0.00012375372,0.001057074,0.0021754673,0.00005761343],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001627238,0.00006967587,0.00074458326,0.00045159028,0.00004295915,0.00093463075,0.00030432036,0.00052044436,0.00010231812,0.000051293275,0.0023085023,0.99445343],"study_design_scores_gemma":[0.0012587548,0.00024895705,0.0076582567,0.004453863,0.00004756607,0.00088827085,6.352238e-7,0.98126143,0.000033195556,0.0022424122,0.0015200878,0.0003865521],"about_ca_topic_score_codex":0.000058041696,"about_ca_topic_score_gemma":0.000032114327,"teacher_disagreement_score":0.99406683,"about_ca_system_score_codex":0.00032683986,"about_ca_system_score_gemma":0.00069638,"threshold_uncertainty_score":0.99988157},"labels":[],"label_agreement":null},{"id":"W4387211573","doi":"10.1007/978-3-031-43901-8","title":"Medical Image Computing and Computer Assisted Intervention – MICCAI 2023","year":2023,"lang":"en","type":"book","venue":"Lecture notes in computer science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Queen's University","funders":"National Institutes of Health; ShanghaiTech University; Technische Universität München; Nanjing University of Science and Technology; Hong Kong University of Science and Technology; University of Texas at Arlington; Central South University; Chinese Academy of Sciences; Imperial College London; Tencent; University of Pittsburgh; Nanjing University; Baidu; University of Twente; Rensselaer Polytechnic Institute; Massachusetts General Hospital; Beihang University; Nvidia; Arizona State University; Fudan University; Northwestern University; Beijing Institute of Technology; Northwestern Polytechnical University; University of California, Santa Cruz","keywords":"Computer science; Computer graphics (images); Multimedia; Human–computer interaction","score_opus":0.01164392047456572,"score_gpt":0.31198643814244326,"score_spread":0.30034251766787756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387211573","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037628538,0.00040468486,0.98825854,0.0035260387,0.002700058,0.00036619403,0.0000038243957,0.00022306023,0.00075477],"genre_scores_gemma":[0.13016644,0.0004759094,0.8224913,0.02004883,0.014571458,0.000025512094,0.0005271959,0.00047789636,0.011215461],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960376,0.000102428705,0.0006847912,0.0011643888,0.0013633107,0.0006474838],"domain_scores_gemma":[0.99777496,0.0008710771,0.00024878155,0.00048672454,0.0001741921,0.0004442728],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002382033,0.00042132114,0.00079794344,0.0008092448,0.00020665085,0.00027234736,0.00064674625,0.0004139859,0.0000648494],"category_scores_gemma":[0.00090347975,0.0003636013,0.00017925526,0.0007377372,0.0013123566,0.00012375372,0.001057074,0.0021754673,0.00005761343],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001627238,0.00006967587,0.00074458326,0.00045159028,0.00004295915,0.00093463075,0.00030432036,0.00052044436,0.00010231812,0.000051293275,0.0023085023,0.99445343],"study_design_scores_gemma":[0.0012587548,0.00024895705,0.0076582567,0.004453863,0.00004756607,0.00088827085,6.352238e-7,0.98126143,0.000033195556,0.0022424122,0.0015200878,0.0003865521],"about_ca_topic_score_codex":0.000058041696,"about_ca_topic_score_gemma":0.000032114327,"teacher_disagreement_score":0.99406683,"about_ca_system_score_codex":0.00032683986,"about_ca_system_score_gemma":0.00069638,"threshold_uncertainty_score":0.99988157},"labels":[],"label_agreement":null},{"id":"W4387211861","doi":"10.1007/978-3-031-43907-0","title":"Medical Image Computing and Computer Assisted Intervention – MICCAI 2023","year":2023,"lang":"en","type":"book","venue":"Lecture notes in computer science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Queen's University","funders":"National Institutes of Health; ShanghaiTech University; Technische Universität München; Nanjing University of Science and Technology; Hong Kong University of Science and Technology; University of Texas at Arlington; Central South University; Chinese Academy of Sciences; Imperial College London; Tencent; University of Pittsburgh; Nanjing University; Baidu; University of Twente; Rensselaer Polytechnic Institute; Massachusetts General Hospital; Beihang University; Nvidia; Arizona State University; Fudan University; Northwestern University; Beijing Institute of Technology; Northwestern Polytechnical University; University of California, Santa Cruz","keywords":"Computer science; Multimedia; Human–computer interaction; Data science","score_opus":0.01164392047456572,"score_gpt":0.31198643814244326,"score_spread":0.30034251766787756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387211861","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037628538,0.00040468486,0.98825854,0.0035260387,0.002700058,0.00036619403,0.0000038243957,0.00022306023,0.00075477],"genre_scores_gemma":[0.13016644,0.0004759094,0.8224913,0.02004883,0.014571458,0.000025512094,0.0005271959,0.00047789636,0.011215461],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960376,0.000102428705,0.0006847912,0.0011643888,0.0013633107,0.0006474838],"domain_scores_gemma":[0.99777496,0.0008710771,0.00024878155,0.00048672454,0.0001741921,0.0004442728],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002382033,0.00042132114,0.00079794344,0.0008092448,0.00020665085,0.00027234736,0.00064674625,0.0004139859,0.0000648494],"category_scores_gemma":[0.00090347975,0.0003636013,0.00017925526,0.0007377372,0.0013123566,0.00012375372,0.001057074,0.0021754673,0.00005761343],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001627238,0.00006967587,0.00074458326,0.00045159028,0.00004295915,0.00093463075,0.00030432036,0.00052044436,0.00010231812,0.000051293275,0.0023085023,0.99445343],"study_design_scores_gemma":[0.0012587548,0.00024895705,0.0076582567,0.004453863,0.00004756607,0.00088827085,6.352238e-7,0.98126143,0.000033195556,0.0022424122,0.0015200878,0.0003865521],"about_ca_topic_score_codex":0.000058041696,"about_ca_topic_score_gemma":0.000032114327,"teacher_disagreement_score":0.99406683,"about_ca_system_score_codex":0.00032683986,"about_ca_system_score_gemma":0.00069638,"threshold_uncertainty_score":0.99988157},"labels":[],"label_agreement":null},{"id":"W4387211862","doi":"10.1007/978-3-031-43904-9","title":"Medical Image Computing and Computer Assisted Intervention – MICCAI 2023","year":2023,"lang":"en","type":"book","venue":"Lecture notes in computer science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Queen's University","funders":"National Institutes of Health; ShanghaiTech University; Technische Universität München; Nanjing University of Science and Technology; Hong Kong University of Science and Technology; University of Texas at Arlington; Central South University; Chinese Academy of Sciences; Imperial College London; Tencent; University of Pittsburgh; Nanjing University; Baidu; University of Twente; Rensselaer Polytechnic Institute; Massachusetts General Hospital; Beihang University; Nvidia; Arizona State University; Fudan University; Northwestern University; Beijing Institute of Technology; Northwestern Polytechnical University; University of California, Santa Cruz","keywords":"Computer science; Intervention (counseling); Multimedia; Human–computer interaction; Medicine","score_opus":0.01164392047456572,"score_gpt":0.31198643814244326,"score_spread":0.30034251766787756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387211862","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037628538,0.00040468486,0.98825854,0.0035260387,0.002700058,0.00036619403,0.0000038243957,0.00022306023,0.00075477],"genre_scores_gemma":[0.13016644,0.0004759094,0.8224913,0.02004883,0.014571458,0.000025512094,0.0005271959,0.00047789636,0.011215461],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960376,0.000102428705,0.0006847912,0.0011643888,0.0013633107,0.0006474838],"domain_scores_gemma":[0.99777496,0.0008710771,0.00024878155,0.00048672454,0.0001741921,0.0004442728],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002382033,0.00042132114,0.00079794344,0.0008092448,0.00020665085,0.00027234736,0.00064674625,0.0004139859,0.0000648494],"category_scores_gemma":[0.00090347975,0.0003636013,0.00017925526,0.0007377372,0.0013123566,0.00012375372,0.001057074,0.0021754673,0.00005761343],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001627238,0.00006967587,0.00074458326,0.00045159028,0.00004295915,0.00093463075,0.00030432036,0.00052044436,0.00010231812,0.000051293275,0.0023085023,0.99445343],"study_design_scores_gemma":[0.0012587548,0.00024895705,0.0076582567,0.004453863,0.00004756607,0.00088827085,6.352238e-7,0.98126143,0.000033195556,0.0022424122,0.0015200878,0.0003865521],"about_ca_topic_score_codex":0.000058041696,"about_ca_topic_score_gemma":0.000032114327,"teacher_disagreement_score":0.99406683,"about_ca_system_score_codex":0.00032683986,"about_ca_system_score_gemma":0.00069638,"threshold_uncertainty_score":0.99988157},"labels":[],"label_agreement":null},{"id":"W4387211869","doi":"10.1007/978-3-031-43987-2","title":"Medical Image Computing and Computer Assisted Intervention – MICCAI 2023","year":2023,"lang":"en","type":"book","venue":"Lecture notes in computer science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Queen's University","funders":"National Institutes of Health; ShanghaiTech University; Technische Universität München; Nanjing University of Science and Technology; Hong Kong University of Science and Technology; University of Texas at Arlington; Central South University; Chinese Academy of Sciences; Imperial College London; Tencent; University of Pittsburgh; Nanjing University; Baidu; University of Twente; Rensselaer Polytechnic Institute; Massachusetts General Hospital; Beihang University; Nvidia; Arizona State University; Fudan University; Northwestern University; Beijing Institute of Technology; Northwestern Polytechnical University; University of California, Santa Cruz","keywords":"Computer science; Multimedia; Intervention (counseling); Human–computer interaction; Medical physics; Medicine; Nursing","score_opus":0.01164392047456572,"score_gpt":0.31198643814244326,"score_spread":0.30034251766787756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387211869","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037628538,0.00040468486,0.98825854,0.0035260387,0.002700058,0.00036619403,0.0000038243957,0.00022306023,0.00075477],"genre_scores_gemma":[0.13016644,0.0004759094,0.8224913,0.02004883,0.014571458,0.000025512094,0.0005271959,0.00047789636,0.011215461],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960376,0.000102428705,0.0006847912,0.0011643888,0.0013633107,0.0006474838],"domain_scores_gemma":[0.99777496,0.0008710771,0.00024878155,0.00048672454,0.0001741921,0.0004442728],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002382033,0.00042132114,0.00079794344,0.0008092448,0.00020665085,0.00027234736,0.00064674625,0.0004139859,0.0000648494],"category_scores_gemma":[0.00090347975,0.0003636013,0.00017925526,0.0007377372,0.0013123566,0.00012375372,0.001057074,0.0021754673,0.00005761343],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001627238,0.00006967587,0.00074458326,0.00045159028,0.00004295915,0.00093463075,0.00030432036,0.00052044436,0.00010231812,0.000051293275,0.0023085023,0.99445343],"study_design_scores_gemma":[0.0012587548,0.00024895705,0.0076582567,0.004453863,0.00004756607,0.00088827085,6.352238e-7,0.98126143,0.000033195556,0.0022424122,0.0015200878,0.0003865521],"about_ca_topic_score_codex":0.000058041696,"about_ca_topic_score_gemma":0.000032114327,"teacher_disagreement_score":0.99406683,"about_ca_system_score_codex":0.00032683986,"about_ca_system_score_gemma":0.00069638,"threshold_uncertainty_score":0.99988157},"labels":[],"label_agreement":null},{"id":"W4387218822","doi":"10.1016/j.ijrobp.2023.09.043","title":"A Prospective Study Demonstrating Early Prediction of Skin Toxicity From Radiation Therapy Using Radiomic Features From Optical and Infrared Images","year":2023,"lang":"en","type":"article","venue":"International Journal of Radiation Oncology*Biology*Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Nova Scotia Health Authority; Dalhousie University","funders":"","keywords":"Toxicity; Breast cancer; Radiation therapy; Medicine; Receiver operating characteristic; Nuclear medicine; Radiology; Cancer; Internal medicine","score_opus":0.017318020524608645,"score_gpt":0.33602885351922984,"score_spread":0.3187108329946212,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387218822","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9861208,0.00045359018,0.011128721,0.000687329,0.001005434,0.0003569629,0.00011259105,0.000047956408,0.00008660254],"genre_scores_gemma":[0.99082965,0.0004692541,0.0059745037,0.00015374749,0.0024105627,0.000007434944,0.00011790459,0.000026133803,0.000010812647],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99816245,0.00027634192,0.0007430828,0.00027225455,0.00037179675,0.00017406669],"domain_scores_gemma":[0.9977538,0.0007149407,0.00088742765,0.00011916432,0.00040270574,0.000121968595],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00068089145,0.00017918913,0.00054229656,0.00024024922,0.000101631944,0.000036892056,0.0001897655,0.00019094955,0.000018860112],"category_scores_gemma":[0.000777083,0.00015884185,0.00014031872,0.00022988675,0.0002910921,0.00029398737,0.000053573236,0.00065953983,0.0000020548757],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00048508498,0.00029488932,0.8247482,0.0000030514284,0.00083172123,0.000045347093,0.0024874874,0.00046573626,0.07017607,0.00019440921,0.00013226003,0.10013573],"study_design_scores_gemma":[0.0075796354,0.0013130638,0.95195454,0.00006675601,0.00017684956,0.000080989084,0.00040496644,0.024692414,0.0074570677,0.006065563,0.00009581481,0.00011232947],"about_ca_topic_score_codex":0.00021373152,"about_ca_topic_score_gemma":0.0000018144515,"teacher_disagreement_score":0.12720634,"about_ca_system_score_codex":0.0003317946,"about_ca_system_score_gemma":0.0003295208,"threshold_uncertainty_score":0.6477383},"labels":[],"label_agreement":null},{"id":"W4387225479","doi":"10.1007/978-3-031-43993-3","title":"Medical Image Computing and Computer Assisted Intervention – MICCAI 2023","year":2023,"lang":"en","type":"book","venue":"Lecture notes in computer science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Queen's University","funders":"NIH Clinical Center; National Institutes of Health; ShanghaiTech University; Rheinische Friedrich-Wilhelms-Universität Bonn; Nanjing University; Université de Rouen; University of North Carolina at Chapel Hill; Nanjing University of Science and Technology; Beijing Institute of Technology; Technische Universität München; Ben-Gurion University of the Negev; Fudan University; Chinese Academy of Sciences; University of Twente; Northwestern Polytechnical University; King's College London; Daegu Gyeongbuk Institute of Science and Technology; Washington University in St. Louis; Imperial College London; Northwestern University; York University; Baidu; Technische Universiteit Delft; Tencent; École de technologie supérieure; University of Pittsburgh; National University of Singapore; Rensselaer Polytechnic Institute; Région Normandie; Memorial Sloan-Kettering Cancer Center; Johns Hopkins University; University College London; Peking University; Auris Health; Beihang University; Massachusetts General Hospital; Case Western Reserve University; Hong Kong University of Science and Technology; University of New South Wales; Arizona State University; Sorbonne Université; Concordia University; Nvidia; Central South University; University of Texas at Arlington; Colorado School of Mines; University of California, Santa Cruz","keywords":"Computer science; Intervention (counseling); Multimedia; Human–computer interaction; Artificial intelligence; Medical physics; Medicine","score_opus":0.01164392047456572,"score_gpt":0.31198643814244326,"score_spread":0.30034251766787756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387225479","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037628538,0.00040468486,0.98825854,0.0035260387,0.002700058,0.00036619403,0.0000038243957,0.00022306023,0.00075477],"genre_scores_gemma":[0.13016644,0.0004759094,0.8224913,0.02004883,0.014571458,0.000025512094,0.0005271959,0.00047789636,0.011215461],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960376,0.000102428705,0.0006847912,0.0011643888,0.0013633107,0.0006474838],"domain_scores_gemma":[0.99777496,0.0008710771,0.00024878155,0.00048672454,0.0001741921,0.0004442728],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002382033,0.00042132114,0.00079794344,0.0008092448,0.00020665085,0.00027234736,0.00064674625,0.0004139859,0.0000648494],"category_scores_gemma":[0.00090347975,0.0003636013,0.00017925526,0.0007377372,0.0013123566,0.00012375372,0.001057074,0.0021754673,0.00005761343],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001627238,0.00006967587,0.00074458326,0.00045159028,0.00004295915,0.00093463075,0.00030432036,0.00052044436,0.00010231812,0.000051293275,0.0023085023,0.99445343],"study_design_scores_gemma":[0.0012587548,0.00024895705,0.0076582567,0.004453863,0.00004756607,0.00088827085,6.352238e-7,0.98126143,0.000033195556,0.0022424122,0.0015200878,0.0003865521],"about_ca_topic_score_codex":0.000058041696,"about_ca_topic_score_gemma":0.000032114327,"teacher_disagreement_score":0.99406683,"about_ca_system_score_codex":0.00032683986,"about_ca_system_score_gemma":0.00069638,"threshold_uncertainty_score":0.99988157},"labels":[],"label_agreement":null},{"id":"W4387225571","doi":"10.1007/978-3-031-43898-1","title":"Medical Image Computing and Computer Assisted Intervention – MICCAI 2023","year":2023,"lang":"en","type":"book","venue":"Lecture notes in computer science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Queen's University","funders":"NIH Clinical Center; National Institutes of Health; ShanghaiTech University; Rheinische Friedrich-Wilhelms-Universität Bonn; Nanjing University; Université de Rouen; University of North Carolina at Chapel Hill; Nanjing University of Science and Technology; Beijing Institute of Technology; Technische Universität München; Ben-Gurion University of the Negev; Fudan University; Chinese Academy of Sciences; University of Twente; Northwestern Polytechnical University; King's College London; Daegu Gyeongbuk Institute of Science and Technology; Washington University in St. Louis; Imperial College London; Northwestern University; York University; Baidu; Technische Universiteit Delft; Tencent; École de technologie supérieure; University of Pittsburgh; National University of Singapore; Rensselaer Polytechnic Institute; Région Normandie; Memorial Sloan-Kettering Cancer Center; Johns Hopkins University; University College London; Peking University; Auris Health; Beihang University; Massachusetts General Hospital; Case Western Reserve University; Hong Kong University of Science and Technology; University of New South Wales; Arizona State University; Sorbonne Université; Concordia University; Nvidia; Central South University; University of Texas at Arlington; Colorado School of Mines; University of California, Santa Cruz","keywords":"Computer science; Multimedia; Intervention (counseling); Human–computer interaction; Medicine; Nursing","score_opus":0.01164392047456572,"score_gpt":0.31198643814244326,"score_spread":0.30034251766787756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387225571","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037628538,0.00040468486,0.98825854,0.0035260387,0.002700058,0.00036619403,0.0000038243957,0.00022306023,0.00075477],"genre_scores_gemma":[0.13016644,0.0004759094,0.8224913,0.02004883,0.014571458,0.000025512094,0.0005271959,0.00047789636,0.011215461],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960376,0.000102428705,0.0006847912,0.0011643888,0.0013633107,0.0006474838],"domain_scores_gemma":[0.99777496,0.0008710771,0.00024878155,0.00048672454,0.0001741921,0.0004442728],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002382033,0.00042132114,0.00079794344,0.0008092448,0.00020665085,0.00027234736,0.00064674625,0.0004139859,0.0000648494],"category_scores_gemma":[0.00090347975,0.0003636013,0.00017925526,0.0007377372,0.0013123566,0.00012375372,0.001057074,0.0021754673,0.00005761343],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001627238,0.00006967587,0.00074458326,0.00045159028,0.00004295915,0.00093463075,0.00030432036,0.00052044436,0.00010231812,0.000051293275,0.0023085023,0.99445343],"study_design_scores_gemma":[0.0012587548,0.00024895705,0.0076582567,0.004453863,0.00004756607,0.00088827085,6.352238e-7,0.98126143,0.000033195556,0.0022424122,0.0015200878,0.0003865521],"about_ca_topic_score_codex":0.000058041696,"about_ca_topic_score_gemma":0.000032114327,"teacher_disagreement_score":0.99406683,"about_ca_system_score_codex":0.00032683986,"about_ca_system_score_gemma":0.00069638,"threshold_uncertainty_score":0.99988157},"labels":[],"label_agreement":null},{"id":"W4387225681","doi":"10.1007/978-3-031-43996-4","title":"Medical Image Computing and Computer Assisted Intervention – MICCAI 2023","year":2023,"lang":"en","type":"book","venue":"Lecture notes in computer science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Queen's University","funders":"National Institutes of Health; ShanghaiTech University; Technische Universität München; Nanjing University of Science and Technology; Hong Kong University of Science and Technology; University of Texas at Arlington; Central South University; Chinese Academy of Sciences; Imperial College London; Tencent; University of Pittsburgh; Nanjing University; Baidu; University of Twente; Rensselaer Polytechnic Institute; Massachusetts General Hospital; Beihang University; Nvidia; Arizona State University; Fudan University; Northwestern University; Beijing Institute of Technology; Northwestern Polytechnical University; University of California, Santa Cruz","keywords":"Computer science; Intervention (counseling); Multimedia; Human–computer interaction; Data science; Medicine; Nursing","score_opus":0.01164392047456572,"score_gpt":0.31198643814244326,"score_spread":0.30034251766787756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387225681","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037628538,0.00040468486,0.98825854,0.0035260387,0.002700058,0.00036619403,0.0000038243957,0.00022306023,0.00075477],"genre_scores_gemma":[0.13016644,0.0004759094,0.8224913,0.02004883,0.014571458,0.000025512094,0.0005271959,0.00047789636,0.011215461],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960376,0.000102428705,0.0006847912,0.0011643888,0.0013633107,0.0006474838],"domain_scores_gemma":[0.99777496,0.0008710771,0.00024878155,0.00048672454,0.0001741921,0.0004442728],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002382033,0.00042132114,0.00079794344,0.0008092448,0.00020665085,0.00027234736,0.00064674625,0.0004139859,0.0000648494],"category_scores_gemma":[0.00090347975,0.0003636013,0.00017925526,0.0007377372,0.0013123566,0.00012375372,0.001057074,0.0021754673,0.00005761343],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001627238,0.00006967587,0.00074458326,0.00045159028,0.00004295915,0.00093463075,0.00030432036,0.00052044436,0.00010231812,0.000051293275,0.0023085023,0.99445343],"study_design_scores_gemma":[0.0012587548,0.00024895705,0.0076582567,0.004453863,0.00004756607,0.00088827085,6.352238e-7,0.98126143,0.000033195556,0.0022424122,0.0015200878,0.0003865521],"about_ca_topic_score_codex":0.000058041696,"about_ca_topic_score_gemma":0.000032114327,"teacher_disagreement_score":0.99406683,"about_ca_system_score_codex":0.00032683986,"about_ca_system_score_gemma":0.00069638,"threshold_uncertainty_score":0.99988157},"labels":[],"label_agreement":null},{"id":"W4387225738","doi":"10.1007/978-3-031-43895-0","title":"Medical Image Computing and Computer Assisted Intervention – MICCAI 2023","year":2023,"lang":"en","type":"book","venue":"Lecture notes in computer science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Queen's University","funders":"National Institutes of Health; ShanghaiTech University; Technische Universität München; Nanjing University of Science and Technology; Hong Kong University of Science and Technology; University of Texas at Arlington; Central South University; Chinese Academy of Sciences; Imperial College London; Tencent; University of Pittsburgh; Nanjing University; Baidu; University of Twente; Rensselaer Polytechnic Institute; Massachusetts General Hospital; Beihang University; Nvidia; Arizona State University; Fudan University; Northwestern University; Beijing Institute of Technology; Northwestern Polytechnical University; University of California, Santa Cruz","keywords":"Computer science; Intervention (counseling); Multimedia; Data science; Medical physics; Medicine","score_opus":0.01164392047456572,"score_gpt":0.31198643814244326,"score_spread":0.30034251766787756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387225738","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037628538,0.00040468486,0.98825854,0.0035260387,0.002700058,0.00036619403,0.0000038243957,0.00022306023,0.00075477],"genre_scores_gemma":[0.13016644,0.0004759094,0.8224913,0.02004883,0.014571458,0.000025512094,0.0005271959,0.00047789636,0.011215461],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960376,0.000102428705,0.0006847912,0.0011643888,0.0013633107,0.0006474838],"domain_scores_gemma":[0.99777496,0.0008710771,0.00024878155,0.00048672454,0.0001741921,0.0004442728],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002382033,0.00042132114,0.00079794344,0.0008092448,0.00020665085,0.00027234736,0.00064674625,0.0004139859,0.0000648494],"category_scores_gemma":[0.00090347975,0.0003636013,0.00017925526,0.0007377372,0.0013123566,0.00012375372,0.001057074,0.0021754673,0.00005761343],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001627238,0.00006967587,0.00074458326,0.00045159028,0.00004295915,0.00093463075,0.00030432036,0.00052044436,0.00010231812,0.000051293275,0.0023085023,0.99445343],"study_design_scores_gemma":[0.0012587548,0.00024895705,0.0076582567,0.004453863,0.00004756607,0.00088827085,6.352238e-7,0.98126143,0.000033195556,0.0022424122,0.0015200878,0.0003865521],"about_ca_topic_score_codex":0.000058041696,"about_ca_topic_score_gemma":0.000032114327,"teacher_disagreement_score":0.99406683,"about_ca_system_score_codex":0.00032683986,"about_ca_system_score_gemma":0.00069638,"threshold_uncertainty_score":0.99988157},"labels":[],"label_agreement":null},{"id":"W4387297435","doi":"10.3389/fonc.2023.1258970","title":"Predicting head and neck cancer treatment outcomes with pre-treatment quantitative ultrasound texture features and optimising machine learning classifiers with texture-of-texture features","year":2023,"lang":"en","type":"article","venue":"Frontiers in Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Toronto Metropolitan University; Health Sciences Centre; Sunnybrook Health Science Centre","funders":"Natural Sciences and Engineering Research Council of Canada; Terry Fox Research Institute; University of Toronto; Canadian Institutes of Health Research; Terry Fox Foundation","keywords":"Support vector machine; Artificial intelligence; Medicine; Radiomics; Head and neck cancer; Local binary patterns; Classifier (UML); Pattern recognition (psychology); Computer science; Radiation therapy; Machine learning; Radiology; Histogram; Image (mathematics)","score_opus":0.014177987939988331,"score_gpt":0.3304374398571495,"score_spread":0.3162594519171612,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387297435","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9793373,0.011522744,0.0012499072,0.0056304163,0.00036199408,0.0009421514,0.000033106244,0.00013715937,0.0007852429],"genre_scores_gemma":[0.95261264,0.0069120126,0.036133047,0.00041430804,0.00013758273,0.0001372963,0.00013732415,0.000092156224,0.0034236119],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99798656,0.000197615,0.000331019,0.0006476991,0.0002858289,0.0005513109],"domain_scores_gemma":[0.9986239,0.0005794717,0.00027066952,0.00021056592,0.000066661334,0.00024871214],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002488013,0.0004641815,0.0011397991,0.00039336138,0.00024574267,0.000045527653,0.00008884583,0.00029967332,0.00001052175],"category_scores_gemma":[0.0002845879,0.0002787881,0.00007602132,0.0004254184,0.0005475748,0.000104391525,0.000042115244,0.00087371294,3.2512335e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017170518,0.0001856206,0.904496,0.00012997571,0.00084404845,0.00037255263,0.00890976,0.004403167,0.0002830828,0.000051383966,0.001303175,0.077304155],"study_design_scores_gemma":[0.011090025,0.009462399,0.93709546,0.00078078505,0.0007189603,0.00089725666,0.0070843277,0.023543747,0.000098523786,0.00007840366,0.008736524,0.00041360196],"about_ca_topic_score_codex":0.0018107755,"about_ca_topic_score_gemma":0.0016313446,"teacher_disagreement_score":0.07689055,"about_ca_system_score_codex":0.0005472527,"about_ca_system_score_gemma":0.00029512183,"threshold_uncertainty_score":0.99996644},"labels":[],"label_agreement":null},{"id":"W4387376141","doi":"10.1038/s41598-023-43715-5","title":"Effects of MRI scanner manufacturers in classification tasks with deep learning models","year":2023,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":48,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Women and Children’s Health Research Institute; University of Alberta","funders":"Canadian Institutes of Health Research; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Government of Canada; Natural Sciences and Engineering Research Council of Canada; Fondation Brain Canada; ALS Society of Canada","keywords":"Computer science; Deep learning; Artificial intelligence; Scanner; Machine learning; Harmonization; Neuroimaging; Vendor; Medical imaging; Pattern recognition (psychology); Computer vision; Medicine","score_opus":0.012145899295172694,"score_gpt":0.2665665530994395,"score_spread":0.2544206538042668,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387376141","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98949796,0.0001019734,0.006044103,0.0007307086,0.001054281,0.0003808774,1.0992545e-7,0.00011245639,0.0020775227],"genre_scores_gemma":[0.9962652,0.000018309986,0.0011449299,0.00004014062,0.00003395071,0.0000219322,0.0000584074,0.000022306507,0.0023948655],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982417,0.000053855394,0.00035847005,0.0004997717,0.0005649623,0.00028121323],"domain_scores_gemma":[0.9991308,0.000077752025,0.00022628796,0.0003537419,0.00008361434,0.00012784587],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013803628,0.00011141278,0.00025129569,0.00044444547,0.00010575071,0.0000467058,0.00006378957,0.0000613867,0.000016548764],"category_scores_gemma":[0.000348192,0.000083236926,0.000054771637,0.00085778587,0.00023657922,0.00010783192,0.00003190874,0.00035800287,0.000009344896],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021653506,0.0004243727,0.2787652,0.0018780013,0.00016931388,0.0085205855,0.007710199,0.2889603,0.29091203,0.0005647821,0.012525196,0.10935348],"study_design_scores_gemma":[0.0014889163,0.0001927711,0.2056847,0.0009461793,0.00013188494,0.000543964,0.00073293404,0.744463,0.030368736,0.0052561634,0.009846201,0.0003445078],"about_ca_topic_score_codex":0.000050580533,"about_ca_topic_score_gemma":0.000008055063,"teacher_disagreement_score":0.45550272,"about_ca_system_score_codex":0.000052689153,"about_ca_system_score_gemma":0.00009766716,"threshold_uncertainty_score":0.33943033},"labels":[],"label_agreement":null},{"id":"W4387384038","doi":"10.48083/ryrf4858","title":"Fusion Biopsy, not Cognitive, Is the New Gold Standard","year":2023,"lang":"en","type":"article","venue":"Société Internationale d’Urologie Journal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Generalizability theory; Medicine; Cognition; Medical physics; Learning curve; Biopsy; Gold standard (test); Computer science; Psychology; Pathology; Radiology; Psychiatry","score_opus":0.03911698383520658,"score_gpt":0.3663501008154295,"score_spread":0.32723311698022295,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387384038","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.73610616,0.00027620618,0.0057118325,0.24400543,0.0019753913,0.00021318655,0.000023662415,0.00016495674,0.011523164],"genre_scores_gemma":[0.9423514,0.0014157089,0.0009088262,0.02143892,0.002301472,0.0000076228844,0.0000547136,0.000030208594,0.03149112],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99823785,0.00008205908,0.00035007583,0.00020835878,0.0008047274,0.0003169231],"domain_scores_gemma":[0.9985994,0.0005961753,0.00020455409,0.00013145518,0.0002603642,0.00020802866],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0010440089,0.00014624157,0.00022695019,0.00017907305,0.00023574424,0.00011819031,0.00028960567,0.00009559159,0.0014972049],"category_scores_gemma":[0.002093382,0.000093175455,0.00024518365,0.00024868938,0.0001533101,0.00009787769,0.00014335923,0.0011868011,0.00016615997],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007708558,0.00007619203,0.06612807,0.000019117144,0.00054547645,0.00064049533,0.0012209361,0.00007334465,0.0049724192,0.0009989459,0.6324468,0.2921073],"study_design_scores_gemma":[0.009210586,0.00082255533,0.40582585,0.0004272207,0.0003735549,0.0042546573,0.0023123068,0.022063078,0.001513518,0.01577845,0.5369661,0.00045215775],"about_ca_topic_score_codex":0.000017634511,"about_ca_topic_score_gemma":0.0000010920257,"teacher_disagreement_score":0.33969778,"about_ca_system_score_codex":0.00010615307,"about_ca_system_score_gemma":0.00028744503,"threshold_uncertainty_score":0.9994156},"labels":[],"label_agreement":null},{"id":"W4387414769","doi":"10.1007/978-3-031-44336-7_5","title":"Examining the Effects of Slice Thickness on the Reproducibility of CT Radiomics for Patients with Colorectal Liver Metastases","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Resampling; Reproducibility; Medicine; Radiomics; Proportional hazards model; Colorectal cancer; Artificial intelligence; Robustness (evolution); Radiology; Feature (linguistics); Data set; Computer science; Pattern recognition (psychology); Statistics; Internal medicine; Cancer; Mathematics","score_opus":0.018867077488351553,"score_gpt":0.26122338305349035,"score_spread":0.2423563055651388,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387414769","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.57941383,0.00036174827,0.41237205,0.0016795764,0.0018405521,0.003824292,0.000033947315,0.00006899135,0.00040503673],"genre_scores_gemma":[0.98367167,0.00003613417,0.0149292685,0.0009822801,0.00021331299,0.000025394993,0.000014909483,0.000046433284,0.00008059439],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975943,0.00008006138,0.0003669101,0.0009680209,0.00072915625,0.00026157952],"domain_scores_gemma":[0.990763,0.0072842645,0.00036919344,0.0012514333,0.00027487977,0.000057202742],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003214133,0.00025741762,0.00056470657,0.00019285284,0.0001472142,0.00002891217,0.0006089115,0.00006900623,0.0000035934459],"category_scores_gemma":[0.006266608,0.00012555465,0.000104455416,0.0003125001,0.001392716,0.000042066567,0.00021654027,0.0007261975,7.880643e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011188536,0.000469337,0.019701067,0.0032039536,0.00047971625,0.00011597419,0.0049648695,0.015176277,0.0016246979,0.0068083587,0.00022217662,0.9461147],"study_design_scores_gemma":[0.012966212,0.023915906,0.20625287,0.025941586,0.0022629702,0.00033341916,0.000020766453,0.6285437,0.059486236,0.035573173,0.002066987,0.0026361772],"about_ca_topic_score_codex":0.000036565652,"about_ca_topic_score_gemma":0.000008158471,"teacher_disagreement_score":0.9434785,"about_ca_system_score_codex":0.000072920324,"about_ca_system_score_gemma":0.00024090808,"threshold_uncertainty_score":0.7502168},"labels":[],"label_agreement":null},{"id":"W4387496028","doi":"10.1007/978-3-031-00119-2_16","title":"Correction to: Radiomics in Nuclear Medicine, Robustness, Reproducibility, and Standardization","year":2023,"lang":"en","type":"book-chapter","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University Health Network","funders":"","keywords":"Standardization; Reproducibility; Robustness (evolution); Radiomics; Medical physics; Medicine; Computer science; Artificial intelligence; Statistics; Mathematics; Chemistry","score_opus":0.02024657725718881,"score_gpt":0.29113996174003315,"score_spread":0.27089338448284433,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387496028","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020749315,0.00041157624,0.012223405,0.03148396,0.0058513177,0.0015500345,0.000009988786,0.00063686917,0.9457579],"genre_scores_gemma":[0.00661089,0.0024152026,0.0030614333,0.0028581042,0.0014353555,0.000009549923,0.00017608998,0.00029397625,0.9831394],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976323,0.000025534215,0.0005483867,0.0011410681,0.000434918,0.00021778137],"domain_scores_gemma":[0.99854684,0.00017045518,0.00012462412,0.0007926908,0.00012782056,0.00023754092],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018965619,0.0002754895,0.00069303147,0.0005235289,0.00006622753,0.000026342703,0.00008257765,0.00022629528,0.00038882485],"category_scores_gemma":[0.0032990535,0.0002370443,0.0000628059,0.00014638349,0.00018266242,0.000047616784,0.000109250854,0.0008874326,0.00003605044],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006192716,0.00006673161,0.003331871,0.0008610453,0.00022608959,0.0004626452,0.0013265173,0.005924807,0.00038600093,0.048173573,0.731084,0.20753749],"study_design_scores_gemma":[0.003850267,0.0010443527,0.0071659754,0.007106676,0.0004830681,0.0006119311,0.00025562415,0.14537422,0.000021126169,0.006974232,0.8260536,0.0010588873],"about_ca_topic_score_codex":0.00020299079,"about_ca_topic_score_gemma":0.00008972639,"teacher_disagreement_score":0.2064786,"about_ca_system_score_codex":0.00023171298,"about_ca_system_score_gemma":0.000100498524,"threshold_uncertainty_score":0.96663857},"labels":[],"label_agreement":null},{"id":"W4387500628","doi":"10.3390/cancers15204909","title":"Applying Natural Language Processing to Single-Report Prediction of Metastatic Disease Response Using the OR-RADS Lexicon","year":2023,"lang":"en","type":"article","venue":"Cancers","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"National Cancer Institute; National Institutes of Health","keywords":"Lexicon; Computer science; Artificial intelligence; Natural language processing; Class (philosophy); Machine learning; Encoder; Medicine","score_opus":0.03953127111827726,"score_gpt":0.3598716820690332,"score_spread":0.32034041095075594,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387500628","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9927266,0.0008408978,0.0033534335,0.001936871,0.00039427952,0.0005496888,0.000008939019,0.00012208658,0.000067157926],"genre_scores_gemma":[0.99693435,0.0000071342024,0.001310022,0.0007342163,0.00017024287,0.0000636098,0.000020932763,0.000028808421,0.0007306911],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99889386,0.00007427128,0.0002556964,0.00021023133,0.0003413406,0.00022462252],"domain_scores_gemma":[0.99931526,0.00011362809,0.000117466574,0.00022153874,0.000061408246,0.00017072076],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007398357,0.000105191226,0.00019580613,0.00015496697,0.00012341433,0.000025371088,0.00008409948,0.000015799877,0.000015327343],"category_scores_gemma":[0.0017057769,0.00006779169,0.00006108626,0.0006274088,0.000103704675,0.00006815774,0.000038521157,0.00022516942,0.0000021856565],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.007530539,0.00005803865,0.011686998,0.0015455815,0.0002772375,0.004735313,0.01110462,0.062509,0.64845616,0.000023014458,0.0034205436,0.24865295],"study_design_scores_gemma":[0.0014977703,0.00021299362,0.014771289,0.0017365395,0.000501449,0.00052094983,0.005908889,0.9631015,0.0034909556,0.00002656019,0.008011665,0.0002194186],"about_ca_topic_score_codex":0.000131006,"about_ca_topic_score_gemma":0.00000414216,"teacher_disagreement_score":0.9005925,"about_ca_system_score_codex":0.00046112863,"about_ca_system_score_gemma":0.0009392456,"threshold_uncertainty_score":0.2764465},"labels":[],"label_agreement":null},{"id":"W4387560996","doi":"10.48550/arxiv.2310.06315","title":"Ultra-high dimensional confounder selection algorithms comparison with application to radiomics data","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Cancer Center, University of Colorado; New Brunswick Innovation Foundation","keywords":"Machine learning; Computer science; Artificial intelligence; Causal inference; Feature selection; Lasso (programming language); Inference; Algorithm; Data mining; Mathematics; Statistics","score_opus":0.07863374244323425,"score_gpt":0.2613024635015922,"score_spread":0.18266872105835796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387560996","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2966856,0.000019519872,0.7002669,0.0011571409,0.00041110461,0.00075631135,0.00005369592,0.00032313488,0.00032659416],"genre_scores_gemma":[0.98921376,0.00005809129,0.006416506,0.0005182618,0.00034210627,0.000003521332,0.0017843554,0.00007129123,0.0015920912],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978549,0.000071005714,0.00025864845,0.0012694504,0.000211816,0.00033421905],"domain_scores_gemma":[0.99800986,0.00013028063,0.00021785974,0.0010868431,0.000196831,0.0003582984],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003932727,0.00030770816,0.00053961977,0.0003021777,0.00016520536,0.00005219384,0.00054416887,0.00024544433,0.00002724108],"category_scores_gemma":[0.00010755229,0.0003059077,0.00007208306,0.0005963578,0.00013717999,0.0000990907,0.00047451397,0.0011778502,0.000120839104],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00067318015,0.00033726238,0.063261464,0.00028190564,0.0007342186,0.00026449992,0.00016528877,0.91263455,0.0011042587,0.0068593887,0.008918061,0.0047659427],"study_design_scores_gemma":[0.0013248755,0.00014883633,0.017233582,0.0002176238,0.0004991778,0.000048053593,0.000076673394,0.97620314,0.00009925739,0.00083381083,0.002940387,0.00037456112],"about_ca_topic_score_codex":0.0011159922,"about_ca_topic_score_gemma":0.0000691893,"teacher_disagreement_score":0.6938504,"about_ca_system_score_codex":0.0003192959,"about_ca_system_score_gemma":0.00032212678,"threshold_uncertainty_score":0.9999393},"labels":[],"label_agreement":null},{"id":"W4387563800","doi":"10.1002/jmri.29049","title":"Best Practice for <scp>MRI</scp> Diagnostic Accuracy Research With Lessons and Examples from the <scp>LI‐RADS</scp> Individual Participant Data Group","year":2023,"lang":"en","type":"review","venue":"Journal of Magnetic Resonance Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; Queen Elizabeth II Health Sciences Centre; Juravinski Hospital; McMaster University; University of Toronto; Dalhousie University; Hamilton Health Sciences","funders":"Radiological Society of North America","keywords":"Documentation; Computer science; Data collection; Medical physics; Raw data; Data science; Best practice; Diagnostic accuracy; Data mining; Medicine; Radiology; Statistics","score_opus":0.2645229670947704,"score_gpt":0.4632675049421243,"score_spread":0.1987445378473539,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387563800","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007611665,0.9892247,0.00093495694,0.006351087,0.00045160836,0.001761835,0.00034614292,0.00003943697,0.00012909637],"genre_scores_gemma":[0.00017542511,0.9850434,0.010753545,0.00054466637,0.0024851619,0.00016822503,0.00022992646,0.00023909498,0.00036051983],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99234456,0.001247776,0.0018322504,0.0010462474,0.0021973331,0.0013318604],"domain_scores_gemma":[0.8673,0.12794243,0.0018878465,0.0015099249,0.0007149861,0.00064482173],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.011199538,0.00068305386,0.0023552265,0.00047915374,0.0006128604,0.000870885,0.0020021282,0.00021018337,0.000008542457],"category_scores_gemma":[0.1906543,0.00041344477,0.00030433,0.00093257794,0.00094357395,0.0007057408,0.0010734983,0.0043935,0.00002356663],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001781794,0.00028218323,0.00088732946,0.003125764,0.00046617337,0.0014570503,0.0012073055,0.000004529376,0.000004239216,0.00009284584,0.06816769,0.9242871],"study_design_scores_gemma":[0.0017243754,0.00078649056,0.002123669,0.04451376,0.007723241,0.0028270262,0.0036420873,0.0011648563,4.9240214e-7,0.00025577875,0.93513125,0.00010694528],"about_ca_topic_score_codex":0.00039163203,"about_ca_topic_score_gemma":0.000029712784,"teacher_disagreement_score":0.92418015,"about_ca_system_score_codex":0.000106331325,"about_ca_system_score_gemma":0.0014182224,"threshold_uncertainty_score":0.99983174},"labels":[],"label_agreement":null},{"id":"W4387609774","doi":"10.1101/2023.10.12.23296873","title":"Decoding pan-cancer treatment outcomes using multimodal real-world data and explainable artificial intelligence","year":2023,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Banting and Best Diabetes Centre, University of Toronto; Institute for Information and Communications Technology Promotion; Deutschen Konsortium für Translationale Krebsforschung; Korea University; Ministry of Science and ICT, South Korea; Bundesministerium für Bildung und Forschung; Berlin Center for Machine Learning; Deutsche Forschungsgemeinschaft","keywords":"Artificial intelligence; Computer science; Artificial neural network; Cancer; Cohort; Machine learning; Oncology; Medicine; Internal medicine","score_opus":0.20055222749557286,"score_gpt":0.43944785301660294,"score_spread":0.23889562552103008,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387609774","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.979958,0.0003999859,0.011936343,0.0051400857,0.0014369505,0.0006355835,0.00008367673,0.0002319485,0.0001774175],"genre_scores_gemma":[0.9694355,0.0041439123,0.023322258,0.00022823339,0.0009055019,0.00007954001,0.00024536188,0.00013001106,0.0015096639],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99731785,0.00009990845,0.00061461754,0.0010752544,0.00038466608,0.00050770165],"domain_scores_gemma":[0.99782825,0.00037857585,0.00027706064,0.0011859977,0.000062764855,0.0002673367],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00088903366,0.00042229172,0.00092659006,0.0003604494,0.0001969475,0.00013412234,0.0004029285,0.00013341304,0.00005830789],"category_scores_gemma":[0.0006921341,0.0003370493,0.00012199413,0.00023835429,0.00022540397,0.000081372695,0.0012313221,0.00082209264,0.000020447815],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000064033644,0.00013667581,0.8057523,0.00039490158,0.00037963054,0.00035206697,0.00055525475,0.0016152993,0.0006215701,0.00020166553,0.00008778365,0.18983887],"study_design_scores_gemma":[0.00031577804,0.000069555885,0.12123383,0.0010773896,0.0006163156,0.000018782766,0.00032160192,0.872732,0.00051935384,0.0013189715,0.0013362371,0.00044022163],"about_ca_topic_score_codex":0.010440588,"about_ca_topic_score_gemma":0.0011380347,"teacher_disagreement_score":0.87111664,"about_ca_system_score_codex":0.0003187959,"about_ca_system_score_gemma":0.00027861583,"threshold_uncertainty_score":0.99990815},"labels":[],"label_agreement":null},{"id":"W4387704618","doi":"10.3389/fonc.2023.1198723","title":"Imaging-based adipose biomarkers for predicting clinical outcomes of cancer patients treated with immune checkpoint inhibitors: a systematic review","year":2023,"lang":"en","type":"review","venue":"Frontiers in Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"National Institute of Environmental Health Sciences","keywords":"Medicine; Cancer; Oncology; Internal medicine; Adipose tissue; Biomarker; Lung cancer","score_opus":0.029172831936477128,"score_gpt":0.39993874960539855,"score_spread":0.3707659176689214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387704618","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000082999395,0.98893785,0.00039625887,0.00051826984,0.0015991745,0.008240994,0.0000817061,0.00009455762,0.000048206166],"genre_scores_gemma":[0.00002709102,0.99199015,0.004308489,0.00045031746,0.00013660773,0.002326323,0.00045699012,0.00017116117,0.00013286222],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9937157,0.0008082373,0.0038806899,0.0006830526,0.0003820937,0.0005302059],"domain_scores_gemma":[0.9947598,0.001482957,0.002731692,0.0005563929,0.00025090997,0.00021824203],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0032021431,0.0005673708,0.0087410165,0.000649573,0.000050408125,0.00001027214,0.0003443264,0.00041299252,0.000008726969],"category_scores_gemma":[0.0066453675,0.00036531143,0.0012601607,0.00074759324,0.00036504553,0.000038771042,0.00007674166,0.00096570863,0.000003061689],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011303758,0.00037555883,0.14984022,0.6938103,0.002437543,0.00006542878,0.000021789952,0.0000011641006,4.8331316e-8,4.861185e-7,0.0033921278,0.14994231],"study_design_scores_gemma":[0.005295974,0.0009981975,0.0012528766,0.90840644,0.019475259,0.00001773588,0.00003648234,0.0022165393,3.6655558e-7,0.0000033916258,0.061897907,0.000398825],"about_ca_topic_score_codex":0.00022570479,"about_ca_topic_score_gemma":0.000017046668,"teacher_disagreement_score":0.21459615,"about_ca_system_score_codex":0.0008867753,"about_ca_system_score_gemma":0.0013752523,"threshold_uncertainty_score":0.9998799},"labels":[],"label_agreement":null},{"id":"W4387779946","doi":"10.1007/s11042-023-17210-y","title":"Anterior mediastinal nodular lesion segmentation from chest computed tomography imaging using UNet based neural network with attention mechanisms","year":2023,"lang":"en","type":"article","venue":"Multimedia Tools and Applications","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Computer science; Radiology; Segmentation; Artificial intelligence; Medicine","score_opus":0.022087535745129713,"score_gpt":0.2857535131516202,"score_spread":0.26366597740649045,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387779946","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4175975,0.00012366718,0.5796915,0.001534553,0.000105085324,0.0006766604,0.000035114517,0.00021595812,0.00001991219],"genre_scores_gemma":[0.8121649,0.00003401489,0.18489604,0.00066969864,0.0004978715,0.0001461753,0.0015391256,0.000040881143,0.0000113013375],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998784,0.000042881635,0.0002607575,0.00037470285,0.00026460274,0.00027302094],"domain_scores_gemma":[0.99926114,0.00016276632,0.00012966571,0.0001903978,0.0000672041,0.00018885304],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021093826,0.00017240217,0.00023827402,0.00013739277,0.00028047134,0.00009067646,0.00007234346,0.000047849033,0.000021303822],"category_scores_gemma":[0.000023278066,0.0001465971,0.000059533784,0.0005550439,0.00011294904,0.0001127555,0.0000405739,0.0002234729,0.000008817175],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013776457,0.00016384928,0.12106643,0.00012959959,0.00009849876,0.0000672687,0.00020250939,0.014681167,0.3265803,0.000062964056,0.00038471268,0.53642493],"study_design_scores_gemma":[0.0014576189,0.00003991323,0.16406648,0.00020508845,0.00013256876,0.000019662426,0.0001059041,0.83266723,0.00054199266,0.000087256725,0.0005356464,0.00014064407],"about_ca_topic_score_codex":0.00010361662,"about_ca_topic_score_gemma":0.000004240701,"teacher_disagreement_score":0.8179861,"about_ca_system_score_codex":0.00002650275,"about_ca_system_score_gemma":0.00003379096,"threshold_uncertainty_score":0.5978056},"labels":[],"label_agreement":null},{"id":"W4387807931","doi":"10.1016/j.annonc.2023.09.742","title":"1264MO IMpower010: Exploratory analysis of disease-free survival (DFS) by TGFβ cancer-associated fibroblast (CAF) gene signature expression in patients (pts) with resected NSCLC treated with atezolizumab (atezo) or best supportive care (BSC)","year":2023,"lang":"en","type":"article","venue":"Annals of Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Roche (Canada)","funders":"F. Hoffmann-La Roche","keywords":"Medicine; Oncology; Gene signature; Internal medicine; Distributed File System; Population; Atezolizumab; Breast cancer; Stage (stratigraphy); Adjuvant; Cancer; Database; Immunotherapy; Gene expression; Gene; Nivolumab; Biology","score_opus":0.026648757947546987,"score_gpt":0.3415231081374804,"score_spread":0.31487435018993337,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387807931","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9966796,0.000359963,0.0000142109475,0.0011185925,0.00007200101,0.00054232636,0.00087731495,0.00007378597,0.00026219877],"genre_scores_gemma":[0.9960752,0.0004579846,0.00007728963,0.00020064741,0.000041219497,0.00007683615,0.0027528931,0.00006558293,0.00025234316],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99697745,0.0004171995,0.0006916401,0.00058058044,0.00073297706,0.00060015346],"domain_scores_gemma":[0.9971278,0.00033591202,0.00067620876,0.0005084366,0.00097535184,0.00037631718],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003516025,0.0003403681,0.0013328707,0.0007955613,0.00007946765,0.000009558484,0.00029601963,0.00028979106,0.00014685834],"category_scores_gemma":[0.00067053374,0.00023181285,0.00016200193,0.0028178561,0.00031011118,0.000108544475,0.00013184297,0.00056137634,0.000002346874],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.03240049,0.0024196766,0.8977373,0.00042129704,0.0035003312,0.0009063514,0.003965495,0.0027732449,0.022723017,0.0000033608796,0.023674719,0.009474709],"study_design_scores_gemma":[0.027679762,0.021398453,0.9116403,0.002678185,0.0027112341,0.0000029506011,0.0045756698,0.0031239649,0.024543969,0.000017116117,0.00087019324,0.0007581926],"about_ca_topic_score_codex":0.0010310062,"about_ca_topic_score_gemma":0.0011634969,"teacher_disagreement_score":0.022804525,"about_ca_system_score_codex":0.0002263631,"about_ca_system_score_gemma":0.00073343224,"threshold_uncertainty_score":0.94530535},"labels":[],"label_agreement":null},{"id":"W4387808477","doi":"10.1016/j.annonc.2023.09.528","title":"332P Early prediction of residual cancer burden to neoadjuvant chemotherapy in breast cancer by longitudinal MRI-based multitask learning: A multicenter cohort study","year":2023,"lang":"en","type":"article","venue":"Annals of Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Washington University School of Medicine in St. Louis; Sidney Kimmel Comprehensive Cancer Center; University of California, San Francisco; University of North Carolina at Chapel Hill; University College Cork; University of Alberta; University of Washington; Translational Breast Cancer Research Consortium; Alvin J. Siteman Cancer Center; Johns Hopkins University; Vanderbilt University","keywords":"Medicine; Cohort; Breast cancer; Cancer; Radiomics; Receiver operating characteristic; Oncology; Internal medicine; Radiology","score_opus":0.03568004504754973,"score_gpt":0.39498891432643835,"score_spread":0.3593088692788886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387808477","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9642214,0.00014257716,0.000052514413,0.034287523,0.00021815056,0.00083920953,0.00007761443,0.00005051558,0.000110451816],"genre_scores_gemma":[0.9977005,0.0005104486,0.00013947536,0.0008675143,0.00021353005,0.00017352347,0.00003607444,0.00003548308,0.00032343506],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9981077,0.00018541097,0.0005436386,0.00038383878,0.00040171208,0.00037769924],"domain_scores_gemma":[0.99897486,0.00016590429,0.00022203317,0.00019763332,0.00026605016,0.00017353157],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009805183,0.00016697613,0.0006541533,0.00033507886,0.00004171361,0.000006412187,0.0001388345,0.00012142314,0.00019153653],"category_scores_gemma":[0.00019905827,0.00014860774,0.00008017946,0.00046805936,0.00012422078,0.000048296755,0.00004886136,0.0004728667,0.000007978551],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013958047,0.0007290419,0.939911,0.00006507359,0.0002300494,0.00006525222,0.001920054,0.005887527,0.010075341,9.586075e-7,0.0120181665,0.027701752],"study_design_scores_gemma":[0.0057419916,0.0022838446,0.9685389,0.00024529133,0.00008300298,0.000005559385,0.0004996734,0.01563347,0.00083408994,0.0000023991877,0.0060277428,0.000104077575],"about_ca_topic_score_codex":0.012437331,"about_ca_topic_score_gemma":0.00024064262,"teacher_disagreement_score":0.033479072,"about_ca_system_score_codex":0.000106455744,"about_ca_system_score_gemma":0.00024825992,"threshold_uncertainty_score":0.99413896},"labels":[],"label_agreement":null},{"id":"W4387808479","doi":"10.1016/j.annonc.2023.09.505","title":"309P Machine learning-based characterization of tumor-immune microenvironment at a spatial and multiplexed resolution in early breast cancer: A sub-study of the EORTC 10994/BIG 1-00 randomized phase III trial with long-term follow-up","year":2023,"lang":"en","type":"article","venue":"Annals of Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Princess Margaret Cancer Foundation","keywords":"Medicine; Breast cancer; Oncology; Immune system; Internal medicine; Tumor microenvironment; Tissue microarray; CD8; Multiplex; Hazard ratio; Cancer; Immunology; Confidence interval; Bioinformatics; Biology","score_opus":0.024394042977783827,"score_gpt":0.31563212478390423,"score_spread":0.29123808180612043,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387808479","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9953712,0.00012637813,0.00012793177,0.0021214958,0.00019806206,0.0020004322,0.000029655732,0.000016663895,0.000008180371],"genre_scores_gemma":[0.99913424,0.00031865123,0.0000143311445,0.00012277659,0.000072920775,0.00012559025,0.00010662016,0.000025221738,0.00007966253],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.997664,0.0006913246,0.0008126476,0.00026927557,0.00031817477,0.00024457762],"domain_scores_gemma":[0.9984823,0.00028555683,0.00085617823,0.00021826276,0.00008236492,0.00007537694],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013558011,0.00017328668,0.0011343244,0.0002288518,0.00007155374,0.0000042348224,0.000107532476,0.00008161318,0.000029918212],"category_scores_gemma":[0.0003221145,0.000118667806,0.0001372382,0.00028220945,0.00040278505,0.00003208033,0.00009371737,0.00032958706,5.307105e-7],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.5706409,0.0017956526,0.18387978,0.00012096552,0.00023209056,0.000056810415,0.0015811482,0.0004076977,0.22638923,9.467359e-7,0.000008354533,0.014886424],"study_design_scores_gemma":[0.5518157,0.0040727383,0.42097342,0.00023770037,0.00020598967,0.000020429148,0.000035684985,0.017444296,0.005065891,0.0000011004557,0.000043238186,0.00008384545],"about_ca_topic_score_codex":0.003302952,"about_ca_topic_score_gemma":0.00072270154,"teacher_disagreement_score":0.23709364,"about_ca_system_score_codex":0.00006432694,"about_ca_system_score_gemma":0.00015423395,"threshold_uncertainty_score":0.49930975},"labels":[],"label_agreement":null},{"id":"W4387810829","doi":"10.1016/j.annonc.2023.09.2643","title":"1689O Comprehensive mapping review of real-world evidence publications focusing on targeted therapies in solid tumors: A collaborative work from ESMO real-world data and Digital Health Working Group","year":2023,"lang":"en","type":"article","venue":"Annals of Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Ipsen; Servier; F. Hoffmann-La Roche; Sanofi; AstraZeneca; Daiichi Sankyo Europe; Eli Lilly and Company; Bristol-Myers Squibb","keywords":"Medicine; Real world data; Real world evidence; Work (physics); Working group; Medical physics; Oncology; Data science; Internal medicine","score_opus":0.2003312083554044,"score_gpt":0.460736168542475,"score_spread":0.2604049601870706,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387810829","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6960018,0.037932426,0.00019655477,0.25966078,0.00024243862,0.0016170563,0.00015776377,0.00016151999,0.0040296195],"genre_scores_gemma":[0.8738926,0.1146375,0.0033854856,0.0071897,0.00018523453,0.000037054153,0.00053492124,0.00003488007,0.000102592574],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99749404,0.00039029724,0.00094846246,0.00049260416,0.000301463,0.00037315596],"domain_scores_gemma":[0.9956376,0.0024700414,0.00084730313,0.00058806676,0.0002933689,0.0001636237],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001487549,0.00018698239,0.00116777,0.0006483564,0.000091210815,0.000029828903,0.00029864538,0.000049529706,0.000019766278],"category_scores_gemma":[0.0019363915,0.00016714087,0.000056291232,0.0028876744,0.0003863303,0.00018879383,0.00026583404,0.00047875184,0.0000035177302],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006381949,0.0005702666,0.27816725,0.00295687,0.0005288273,0.0001306178,0.0062980033,0.00006322418,0.00080485607,0.0018217235,0.057229415,0.65079075],"study_design_scores_gemma":[0.001404203,0.0011884165,0.8225064,0.073692754,0.00006203532,0.000008550076,0.00193688,0.0024207805,0.000057924393,0.0011114359,0.09530006,0.0003105274],"about_ca_topic_score_codex":0.0019220121,"about_ca_topic_score_gemma":0.0008618148,"teacher_disagreement_score":0.6504802,"about_ca_system_score_codex":0.00008832328,"about_ca_system_score_gemma":0.00048289687,"threshold_uncertainty_score":0.6815807},"labels":[],"label_agreement":null},{"id":"W4387812143","doi":"10.1016/j.annonc.2023.09.1341","title":"2314P Quality and safety of research biopsies (RB) in oncology clinical trials","year":2023,"lang":"en","type":"article","venue":"Annals of Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Cilag; HORIZON EUROPE Framework Programme; Chugai Pharmaceutical; AstraZeneca; Genentech; INCLIVA Instituto de Investigación Sanitaria; Sun Pharma; EMD Serono; Mersana Therapeutics; Deutschen Konsortium für Translationale Krebsforschung; Incyte; Servier; Sociedad Española de Oncología Médica; Cancer Research UK; Seagen; Grifols; Fundación Científica Asociación Española Contra el Cáncer; MacroGenics; American Society of Clinical Oncology; Oncode Institute; Eisai Canada; BeiGene; Mirati Therapeutics; Amgen; Astellas Pharma; Deciphera Pharmaceuticals; Daiichi Sankyo Europe; Takeda Oncology; European Society for Medical Oncology; Agios Pharmaceuticals; Clovis Oncology; Les Laboratories Pierre Fabre; Novocure; Regeneron Pharmaceuticals; Ipsen; Takeda Pharmaceuticals International; Array BioPharma; Taiho Pharmaceutical; Merck KGaA; Samsung; Eisai; FibroGen; Bristol-Myers Squibb; Eli Lilly and Company; F. Hoffmann-La Roche; Loxo Oncology; European Association for Cancer Research; Pharmacyclics; Exelixis; Sanofi; PharmaMar; Novartis Farmacéutica; OncoMed Pharmaceutical; Pfizer; Celgene","keywords":"Medicine; Clinical trial; Context (archaeology); Internal medicine; Breast cancer; Oncology; Cancer; Surgery","score_opus":0.6642324169962353,"score_gpt":0.6911398944728597,"score_spread":0.026907477476624475,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387812143","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89988756,0.0005341828,0.000018633242,0.08894999,0.00029208564,0.00034705567,0.000009721693,0.00002418252,0.009936552],"genre_scores_gemma":[0.9874765,0.00940734,0.00070869405,0.0017085262,0.00027383392,0.000015471183,0.000019751287,0.0000146510165,0.0003751937],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99154747,0.005377407,0.0020118165,0.00031260558,0.00034472102,0.0004059619],"domain_scores_gemma":[0.9817718,0.01692711,0.0004625744,0.0002720579,0.00035420863,0.00021224872],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07086925,0.00009363179,0.0016569879,0.00053061056,0.000040217314,0.0000030289618,0.00014178536,0.0003724533,0.000083237],"category_scores_gemma":[0.052107643,0.00007463111,0.00016611317,0.0006430802,0.0012672852,0.000031591517,0.00018518767,0.000990204,0.000014666559],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0032766208,0.0008618595,0.18101019,0.0003747195,0.00019154475,0.00025347964,0.0010745451,0.000017548418,0.005367189,0.004708332,0.02605582,0.77680814],"study_design_scores_gemma":[0.0068002706,0.006170174,0.723856,0.00024615103,0.000042678028,0.000040765306,0.0012982632,0.0013591308,0.000692439,0.005509272,0.25387317,0.00011170273],"about_ca_topic_score_codex":0.00039435833,"about_ca_topic_score_gemma":0.00005481867,"teacher_disagreement_score":0.77669644,"about_ca_system_score_codex":0.000036103953,"about_ca_system_score_gemma":0.00063062966,"threshold_uncertainty_score":0.9567356},"labels":[],"label_agreement":null},{"id":"W4387820207","doi":"10.1101/2023.10.16.562593","title":"Functional Tissue Units in the Human Reference Atlas","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of Diabetes and Digestive and Kidney Diseases; Common Fund; National Institutes of Health; NIH Office of the Director; Canadian Institute for Advanced Research","keywords":"Atlas (anatomy); Human body; Computer science; Construct (python library); Function (biology); Information retrieval; Biology; Artificial intelligence; Anatomy; Programming language; Evolutionary biology","score_opus":0.04570732823273298,"score_gpt":0.2873895637135854,"score_spread":0.24168223548085244,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387820207","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9906429,0.00045428204,0.0007636351,0.0053152055,0.0012130608,0.0008087934,0.00004888304,0.0006013536,0.00015188151],"genre_scores_gemma":[0.9967072,0.00014913136,0.00077686494,0.0010060025,0.0009644906,0.00016879807,0.0000042550555,0.00011815738,0.000105074614],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9973016,0.00020995682,0.0005204064,0.00077718357,0.00068536116,0.00050552987],"domain_scores_gemma":[0.99794495,0.00017914249,0.00022779539,0.0011013962,0.00032975627,0.00021698713],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0014147784,0.00040237338,0.0005322695,0.00036599612,0.00019782025,0.00014787765,0.00051709614,0.00041005053,0.000081445985],"category_scores_gemma":[0.0009407851,0.00032453123,0.00007582072,0.0008849175,0.00017770308,0.000058157275,0.00033674185,0.0027239535,0.00023716893],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000104327206,0.00061990024,0.1320782,0.0020243246,0.0004585556,0.0024841405,0.00015459504,0.00068540446,0.7851667,0.014830144,0.061359268,0.000034477056],"study_design_scores_gemma":[0.0011677488,0.00010244717,0.9360956,0.0012685372,0.00018864617,2.48143e-7,0.000015787537,0.0012388547,0.006678565,0.000019498246,0.052624516,0.0005995527],"about_ca_topic_score_codex":0.00031545744,"about_ca_topic_score_gemma":0.000008047656,"teacher_disagreement_score":0.80401736,"about_ca_system_score_codex":0.00019633857,"about_ca_system_score_gemma":0.00059148396,"threshold_uncertainty_score":0.99992067},"labels":[],"label_agreement":null},{"id":"W4387825535","doi":"10.1016/j.annonc.2023.09.2015","title":"869P Utilizing H&amp;E images and digital pathology to predict response to buparlisib in SCCHN","year":2023,"lang":"en","type":"article","venue":"Annals of Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier de l’Université de Montréal","funders":"Deutsche Forschungsgemeinschaft","keywords":"Medicine; Paclitaxel; Placebo; Internal medicine; Oncology; Clinical trial; Stromal cell; Pathology; Chemotherapy","score_opus":0.06425120721555985,"score_gpt":0.4208034776906016,"score_spread":0.3565522704750418,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387825535","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9282902,0.00014893802,0.00016442592,0.06806441,0.00013796204,0.00025320376,0.000016851409,0.000064006585,0.0028600444],"genre_scores_gemma":[0.99192697,0.00019449794,0.0012954028,0.00561615,0.00009356533,0.000023908871,0.000015669484,0.00002253374,0.0008112764],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9986136,0.00014811897,0.00035824423,0.00031597723,0.00016145433,0.00040262853],"domain_scores_gemma":[0.99866325,0.00066679163,0.00006177564,0.00021920289,0.00008909278,0.00029989984],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015576797,0.00011933525,0.00046396026,0.0005867701,0.000033217344,0.000014981662,0.00011292436,0.000118065895,0.000024710376],"category_scores_gemma":[0.005653401,0.0001092142,0.000048588532,0.0005114738,0.00015216786,0.00006553834,0.00020091621,0.00029312083,0.000065920176],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005643289,0.0003699757,0.17020276,0.00012742479,0.00008304511,0.002633141,0.004440931,0.00021156557,0.08375919,0.00020319168,0.092469454,0.63985604],"study_design_scores_gemma":[0.0022220053,0.0043583964,0.5889158,0.00026691656,0.000024494806,0.00046167598,0.0007250154,0.0004801025,0.0013018941,0.0005685171,0.40046206,0.00021309571],"about_ca_topic_score_codex":0.00003934271,"about_ca_topic_score_gemma":0.000011770921,"teacher_disagreement_score":0.63964295,"about_ca_system_score_codex":0.000025873469,"about_ca_system_score_gemma":0.00013149012,"threshold_uncertainty_score":0.67680573},"labels":[],"label_agreement":null},{"id":"W4387903131","doi":"10.1038/s41598-023-45486-5","title":"Image based prognosis in head and neck cancer using convolutional neural networks: a case study in reproducibility and optimization","year":2023,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Alzheimer Nederland; Universiteit Maastricht; ZonMw; Polytechnique Montréal","keywords":"Reproducibility; Computer science; Convolutional neural network; Head and neck; Artificial intelligence; Machine learning; Image processing; Deep learning; Artificial neural network; Image (mathematics); Pattern recognition (psychology); Data mining; Medicine; Statistics; Mathematics; Surgery","score_opus":0.0358956022395503,"score_gpt":0.3524959288033744,"score_spread":0.3166003265638241,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387903131","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9969595,0.00020380072,0.000514847,0.0007274355,0.00079961517,0.00074587204,6.5647237e-7,0.000041024603,0.0000072556873],"genre_scores_gemma":[0.9964489,0.0000050085373,0.0033470902,0.00004438939,0.000049526447,0.00003831642,0.000019686935,0.000011130336,0.00003597124],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979599,0.00009979683,0.00042205176,0.0010463883,0.00024337682,0.0002284544],"domain_scores_gemma":[0.99926066,0.000047591377,0.00011036768,0.00039523392,0.00007921656,0.0001069338],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0042898827,0.000093396324,0.00020923045,0.00027337018,0.00014314654,0.00010386546,0.00002004986,0.000033588334,0.00001539715],"category_scores_gemma":[0.0010428505,0.00008399057,0.00001986765,0.00092099915,0.00022847281,0.00011846836,0.000058493963,0.00021325078,9.459216e-8],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001746802,0.00012571499,0.82881176,0.000042956206,0.0000041834405,0.011036799,0.00035544042,0.15782891,0.00024831036,1.6687947e-7,0.000088203335,0.0014400644],"study_design_scores_gemma":[0.0005849149,0.000031324416,0.2016517,0.00009114681,0.000017723843,0.0017184315,0.0002447388,0.795563,0.00000808459,0.000016206508,0.0000115780595,0.00006116538],"about_ca_topic_score_codex":0.001996838,"about_ca_topic_score_gemma":0.0003630224,"teacher_disagreement_score":0.63773406,"about_ca_system_score_codex":0.00007709937,"about_ca_system_score_gemma":0.00013730615,"threshold_uncertainty_score":0.3425036},"labels":[],"label_agreement":null},{"id":"W4387934035","doi":"10.32920/24438073","title":"Measurement Variability Following MRI System Upgrade","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; Université de Montréal; Institut Universitaire de Gériatrie de Montréal; Toronto Metropolitan University; Montreal Neurological Institute and Hospital; Douglas Mental Health University Institute; McGill University","funders":"Pfizer Canada; Fonds de Recherche du Québec - Santé; Alzheimer's Society; Consortium canadien en neurodégénérescence associée au vieillissement; Pfizer","keywords":"Fluid-attenuated inversion recovery; Upgrade; Hyperintensity; Context (archaeology); Siemens; Magnetic resonance imaging; Nuclear medicine; Medicine; White matter; Radiology; Computer science; Physics; Biology","score_opus":0.03972259078700409,"score_gpt":0.3118656727692562,"score_spread":0.2721430819822521,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387934035","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10653453,0.0012401149,0.6817736,0.056536686,0.02537906,0.0051717455,0.000020873691,0.007748392,0.11559499],"genre_scores_gemma":[0.9854262,0.000031409156,0.0113149835,0.00044830423,0.00077903934,0.00010678061,0.00004822161,0.00010048243,0.0017446085],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99648917,0.00021141107,0.00064713537,0.00084779394,0.0013622992,0.00044217962],"domain_scores_gemma":[0.99820584,0.00010593671,0.00015688673,0.001020954,0.00015159215,0.00035876027],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00520702,0.0003530091,0.00087323476,0.00017685987,0.00010677417,0.00008130862,0.00027524997,0.00033451788,0.00004337887],"category_scores_gemma":[0.0015815939,0.00028511675,0.0005910251,0.00016086848,0.000049214003,0.00002289584,0.0005787085,0.0017687948,0.0001462263],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047423673,0.0019883192,0.57285625,0.07148065,0.0148905935,0.007298635,0.003007637,0.014026591,0.008746391,0.030937584,0.21502279,0.05927034],"study_design_scores_gemma":[0.007609682,0.00034749278,0.114929914,0.030451627,0.0057364907,0.00033945352,0.0015591624,0.78225476,0.0006706851,0.007808011,0.04534414,0.002948586],"about_ca_topic_score_codex":0.00059086125,"about_ca_topic_score_gemma":0.000005522131,"teacher_disagreement_score":0.87889165,"about_ca_system_score_codex":0.0008661898,"about_ca_system_score_gemma":0.00046949962,"threshold_uncertainty_score":0.9999601},"labels":[],"label_agreement":null},{"id":"W4387938583","doi":"10.1007/978-3-031-47076-9_9","title":"Enhancing Clinical Support for Breast Cancer with Deep Learning Models Using Synthetic Correlated Diffusion Imaging","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Niagara Health System; University of Waterloo","funders":"","keywords":"Breast cancer; Deep learning; Leverage (statistics); Artificial intelligence; Convolutional neural network; Computer science; Modality (human–computer interaction); Magnetic resonance imaging; Machine learning; Modalities; Medical physics; Medicine; Cancer; Radiology; Internal medicine","score_opus":0.023853654937925677,"score_gpt":0.3151720809462578,"score_spread":0.29131842600833213,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387938583","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0036602367,0.00020833396,0.9926757,0.0009213216,0.0014466762,0.0005908966,0.000007034191,0.00019006665,0.00029970068],"genre_scores_gemma":[0.7807737,0.00042491843,0.21182372,0.0027709857,0.0020403462,0.000029438828,0.000048479124,0.00037856816,0.0017098346],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99644226,0.000041114028,0.00073437643,0.0012595129,0.0007876338,0.0007351163],"domain_scores_gemma":[0.99768037,0.00085663673,0.0003903108,0.00044514047,0.00032073987,0.00030680955],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0016419548,0.0004700619,0.00087583094,0.00057745446,0.00036869117,0.00014383161,0.00041631225,0.00026644033,0.000047916983],"category_scores_gemma":[0.00030484397,0.00036928023,0.00019653385,0.00034290683,0.0008154442,0.0001765772,0.0003106028,0.0020952197,0.000005652624],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001243152,0.00003217253,0.0037108315,0.00018819518,0.000047579324,0.00025699224,0.00040884933,0.3303974,0.0006113979,0.00013774932,0.0000036151341,0.6640809],"study_design_scores_gemma":[0.0010168914,0.00017125852,0.00052060414,0.0036208946,0.00017017573,0.0007031611,0.0000016396879,0.99062985,0.00005218709,0.0025738792,0.000108825334,0.00043061588],"about_ca_topic_score_codex":0.00009225066,"about_ca_topic_score_gemma":0.000041354484,"teacher_disagreement_score":0.780852,"about_ca_system_score_codex":0.0003331359,"about_ca_system_score_gemma":0.0007410183,"threshold_uncertainty_score":0.9998759},"labels":[],"label_agreement":null},{"id":"W4387962351","doi":"10.1200/op.2023.19.11_suppl.587","title":"Multi-task machine learning of the electronic medical record to predict future symptoms among patients with cancer.","year":2023,"lang":"en","type":"article","venue":"JCO Oncology Practice","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University Health Network; University of Toronto; Princess Margaret Cancer Centre","funders":"","keywords":"Medicine; Interquartile range; Medical record; Medical diagnosis; Cohort; Psychological intervention; Electronic medical record; Physical therapy; Internal medicine; Emergency medicine; Radiology","score_opus":0.0065162739143822005,"score_gpt":0.31650310279435506,"score_spread":0.30998682887997286,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387962351","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9371054,0.00022362219,0.00067839713,0.058695763,0.0010521818,0.0007335134,0.0000075042417,0.00016739045,0.0013361991],"genre_scores_gemma":[0.9884341,0.0007587449,0.0015344409,0.0064150537,0.0006371131,0.000107905376,0.00005438097,0.00006863409,0.0019896522],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99739265,0.0005093171,0.00038488183,0.000378027,0.0008014622,0.0005336725],"domain_scores_gemma":[0.9978089,0.0009039896,0.00040285804,0.0003233509,0.00023494435,0.00032598677],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0014008672,0.00019252273,0.0004486074,0.00013805117,0.00019996689,0.000011842637,0.00031486066,0.00024157605,0.0002379645],"category_scores_gemma":[0.0064257053,0.00011891537,0.000085449064,0.000810834,0.00021874713,0.00013690449,0.00019884764,0.0023681247,0.000036130918],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008352017,0.00044115522,0.8915771,0.00006091653,0.00034842402,0.00009004765,0.0007380832,0.00037326114,0.00015748035,0.00006182502,0.005432506,0.09988398],"study_design_scores_gemma":[0.003770316,0.001573313,0.48605192,0.0001764412,0.00038393188,0.00006208207,0.00024710727,0.025632467,0.000015433914,0.0000039728366,0.48195025,0.00013274871],"about_ca_topic_score_codex":0.0007980007,"about_ca_topic_score_gemma":0.00033943355,"teacher_disagreement_score":0.47651777,"about_ca_system_score_codex":0.00030271476,"about_ca_system_score_gemma":0.0008347341,"threshold_uncertainty_score":0.9999335},"labels":[],"label_agreement":null},{"id":"W4388024378","doi":"10.1016/j.media.2023.103011","title":"Anatomically-aware uncertainty for semi-supervised image segmentation","year":2023,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":57,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; Fonds de recherche du Québec; Compute Canada","keywords":"Segmentation; Artificial intelligence; Computer science; Inference; Pixel; Representation (politics); Scale-space segmentation; Image segmentation; Pattern recognition (psychology); Segmentation-based object categorization; Machine learning","score_opus":0.011542703190844253,"score_gpt":0.33554928277027957,"score_spread":0.3240065795794353,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388024378","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44183797,0.00011161703,0.50933313,0.045595992,0.00026423158,0.00079260627,0.00006959581,0.0007324626,0.0012623874],"genre_scores_gemma":[0.94727635,0.00057820824,0.029224666,0.011790905,0.001166611,0.00031397978,0.0055624186,0.00014324796,0.003943585],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99699575,0.00011513048,0.00060094596,0.00058525807,0.001122855,0.0005800419],"domain_scores_gemma":[0.9979424,0.000500164,0.000114241215,0.00043721442,0.00027030948,0.0007356853],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0015073187,0.00024509872,0.0007557395,0.00068244693,0.00019012848,0.000081958395,0.00026586422,0.00018291087,0.0028843314],"category_scores_gemma":[0.0030587343,0.00019902285,0.0006833204,0.0024531595,0.00027552983,0.00013722613,0.000100813464,0.0005024083,0.0001945672],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009319692,0.0012302928,0.07069523,0.0016837951,0.013838865,0.0032549913,0.002153828,0.0015070584,0.119757034,0.00031794878,0.3167388,0.46789017],"study_design_scores_gemma":[0.0028025769,0.00009199893,0.0052927705,0.000070158516,0.0026711067,0.000019636562,0.00047492038,0.9818188,0.0009778073,0.00021252515,0.005321827,0.0002458532],"about_ca_topic_score_codex":0.0001756013,"about_ca_topic_score_gemma":0.000022925706,"teacher_disagreement_score":0.98031175,"about_ca_system_score_codex":0.000116538984,"about_ca_system_score_gemma":0.00019329165,"threshold_uncertainty_score":0.99802715},"labels":[],"label_agreement":null},{"id":"W4388042232","doi":"10.1136/jitc-2023-sitc2023.0222-n","title":"222-N Analysis of pathologic features and efficacy outcomes with neoadjuvant nivolumab plus platinum-doublet chemotherapy for resectable non-small cell lung cancer in CheckMate 816","year":2023,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; McGill University Health Centre","funders":"Ono Pharmaceutical; Bristol-Myers Squibb","keywords":"Medicine; Nivolumab; Oncology; Chemotherapy; Neoadjuvant therapy; Internal medicine; Lung cancer; Surrogate endpoint; Cancer; Response Evaluation Criteria in Solid Tumors; Phases of clinical research; Immunotherapy; Breast cancer","score_opus":0.011661630076855029,"score_gpt":0.3104396870666964,"score_spread":0.2987780569898414,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388042232","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99370456,0.00042677912,0.0013260144,0.0025969355,0.000051022707,0.0007260464,0.00001695525,0.00007303848,0.0010786769],"genre_scores_gemma":[0.9890115,0.00046824195,0.0042848727,0.0006510222,0.000037973336,0.00008054289,0.00005760244,0.00003999699,0.005368202],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99863166,0.000028259015,0.00032709073,0.00040302638,0.00021930672,0.00039065155],"domain_scores_gemma":[0.99914116,0.00026862233,0.00013767823,0.00026844646,0.000069402886,0.00011472239],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005461065,0.00020283648,0.0008494803,0.0004898709,0.00006132148,0.00002747643,0.00011484411,0.00009674029,0.00009269094],"category_scores_gemma":[0.00011017466,0.0001301536,0.00012464238,0.0009989337,0.000083596104,0.00004035042,0.00004657133,0.0002901897,7.308007e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00095369306,0.00013982046,0.961593,0.000529387,0.0008219498,0.000119328404,0.0022475764,0.014448011,0.008853411,0.00003846204,0.0022568658,0.007998523],"study_design_scores_gemma":[0.011618003,0.00020250591,0.7356405,0.00017485974,0.0006591704,0.000008769113,0.00030974526,0.24937105,0.001645376,0.000011649366,0.00016944183,0.00018892842],"about_ca_topic_score_codex":0.0014607164,"about_ca_topic_score_gemma":0.00041094338,"teacher_disagreement_score":0.23492303,"about_ca_system_score_codex":0.00006793274,"about_ca_system_score_gemma":0.000107631444,"threshold_uncertainty_score":0.53075093},"labels":[],"label_agreement":null},{"id":"W4388044269","doi":"10.1016/j.jtho.2023.09.442","title":"P1.24-05 The Association of Acinar Pattern with Clinicopathological, Molecular Features, and Prognosis in Lung Adenocarcinoma Patients","year":2023,"lang":"en","type":"article","venue":"Journal of Thoracic Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut universitaire de cardiologie et de pneumologie de Québec","funders":"","keywords":"Medicine; Association (psychology); Adenocarcinoma; Internal medicine; Lung; Oncology; Pathology; Gastroenterology; Cancer","score_opus":0.013412591279382905,"score_gpt":0.37337698946869763,"score_spread":0.35996439818931475,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388044269","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98296726,0.000532901,0.00011320551,0.015812594,0.0002338345,0.00020736884,0.0000017139633,0.000008358043,0.00012277611],"genre_scores_gemma":[0.9978478,0.00027096274,0.00082226587,0.0008536528,0.00009853193,0.0000054480897,0.000004572795,0.000012837174,0.000083916675],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99846697,0.00037753346,0.0004766936,0.0001274578,0.0003535797,0.00019774442],"domain_scores_gemma":[0.99855125,0.00040100716,0.0006970646,0.0000919224,0.0001730069,0.000085740685],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019275997,0.00009560458,0.00046623684,0.00018750141,0.000038602964,0.000011452093,0.00011435235,0.00015063668,0.000007146494],"category_scores_gemma":[0.0010605067,0.000053404325,0.00007479516,0.00029030562,0.00008969088,0.000047892387,0.000057664685,0.0008651576,0.0000010892145],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003606769,0.00020740335,0.918923,0.00008211449,0.000057109824,0.0008688909,0.00045232213,0.000034435423,0.00035624127,0.000004523118,0.0027625116,0.07589074],"study_design_scores_gemma":[0.0014177004,0.0025077553,0.99301916,0.00023281931,0.00023836,0.0005257987,0.00023386827,0.0006236326,0.00015158534,0.000058912556,0.00093480415,0.00005557425],"about_ca_topic_score_codex":0.000008880969,"about_ca_topic_score_gemma":0.000004919873,"teacher_disagreement_score":0.07583517,"about_ca_system_score_codex":0.00014894654,"about_ca_system_score_gemma":0.00011345134,"threshold_uncertainty_score":0.37587273},"labels":[],"label_agreement":null},{"id":"W4388044943","doi":"10.1016/j.jtho.2023.09.837","title":"EP04.01-07 Optimal Predictors for Lung Cancer Using High-Resolution CT","year":2023,"lang":"en","type":"article","venue":"Journal of Thoracic Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute of Aging","funders":"","keywords":"Medicine; Lung cancer; Radiology; Computed tomography; Lung; High-resolution computed tomography; Cancer; Lung cancer screening; High resolution; Oncology; Internal medicine","score_opus":0.02849388548504429,"score_gpt":0.4465862031673295,"score_spread":0.4180923176822852,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388044943","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96010405,0.0007946921,0.02483008,0.011040056,0.0027919754,0.00024795855,0.000009149936,0.00004753814,0.00013452659],"genre_scores_gemma":[0.9475634,0.00042923508,0.047014944,0.00086697825,0.003271334,0.000014628313,0.000018456132,0.000055433025,0.000765553],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998472,0.00012111329,0.00056510686,0.00015916543,0.0003100837,0.00037253654],"domain_scores_gemma":[0.9986474,0.00029757278,0.00050472934,0.00011585182,0.00018739521,0.00024703055],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015323764,0.00013086022,0.00055087387,0.00034582271,0.0001229991,0.000016953889,0.00013933344,0.000105764375,0.00013177666],"category_scores_gemma":[0.0007072168,0.00010344542,0.00020509836,0.0002656292,0.00010385664,0.000113640745,0.000048446942,0.0006326442,0.000004411254],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.006562028,0.0007116138,0.06361335,0.0014148154,0.0020809115,0.0038016252,0.0015402002,0.18870386,0.051723212,0.00033770618,0.21323474,0.46627596],"study_design_scores_gemma":[0.002844582,0.0017084236,0.020154726,0.0007032645,0.0015966035,0.002664453,0.00028986583,0.8640884,0.0008004473,0.00017605103,0.10475318,0.00022001423],"about_ca_topic_score_codex":0.000074935786,"about_ca_topic_score_gemma":0.0000035613878,"teacher_disagreement_score":0.6753845,"about_ca_system_score_codex":0.00053821335,"about_ca_system_score_gemma":0.00058383646,"threshold_uncertainty_score":0.42183816},"labels":[],"label_agreement":null},{"id":"W4388048634","doi":"10.1136/jitc-2023-sitc2023.1511","title":"1511 Pan-tumor harmonization of pathologic response assessment for standardized data collection in neoadjuvant IO trials (PATHdata): Interim analysis of a multi-institutional reproducibility study","year":2023,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Queen's University","funders":"Society for Immunotherapy of Cancer; AstraZeneca; Bristol-Myers Squibb","keywords":"Medicine; Response Evaluation Criteria in Solid Tumors; Concordance; Clinical trial; Clinical endpoint; Interim analysis; Lymph node; Interim; Oncology; Breast cancer; Primary tumor; Neoadjuvant therapy; Cancer; Internal medicine; Radiology; Medical physics; Metastasis; Phases of clinical research","score_opus":0.18078084492324323,"score_gpt":0.4746308263835642,"score_spread":0.29384998146032093,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388048634","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8108779,0.00002888859,0.18617891,0.00066012214,0.00016501738,0.0017202898,0.0003064863,0.000052008112,0.000010386427],"genre_scores_gemma":[0.96726745,0.000032492728,0.031293325,0.00005347864,0.00002638243,0.000089735346,0.0011121635,0.000011331732,0.00011361046],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99576414,0.0012933473,0.0013904268,0.00092809944,0.00045048472,0.0001735116],"domain_scores_gemma":[0.9965535,0.0011785708,0.00045711128,0.0014367998,0.00031409034,0.00005995932],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03931041,0.00014233291,0.0012503171,0.0008901008,0.000074044685,0.000016096801,0.0002048581,0.00004883744,0.000059444024],"category_scores_gemma":[0.04867876,0.000101312566,0.00017545855,0.0021746154,0.00011859791,0.000105688,0.00020735544,0.00018920789,5.015744e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.026634758,0.0065164044,0.7232042,0.0003999767,0.0028503684,0.00024423105,0.0026382376,0.006581922,0.20295149,0.00009819349,0.0022892756,0.025590964],"study_design_scores_gemma":[0.0066645406,0.0007540976,0.5111289,0.00005993672,0.0010701785,0.000004747546,0.0010265851,0.47806373,0.0010222915,0.000018265233,0.00011030794,0.000076416654],"about_ca_topic_score_codex":0.00042050582,"about_ca_topic_score_gemma":0.00011368737,"teacher_disagreement_score":0.4714818,"about_ca_system_score_codex":0.00018724028,"about_ca_system_score_gemma":0.00052828743,"threshold_uncertainty_score":0.9892321},"labels":[],"label_agreement":null},{"id":"W4388076994","doi":"10.1016/j.jocd.2023.101439","title":"Reporting of Full-Length Femur Imaging to Detect Incomplete Atypical Femur Fractures: 2023 Official Positions of the International Society for Clinical Densitometry","year":2023,"lang":"en","type":"review","venue":"Journal of Clinical Densitometry","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Women's College Hospital; University of Toronto","funders":"","keywords":"Medicine; Task force; Femur; Radiography; Densitometry; Dual energy; Radiology; Orthodontics; Physical medicine and rehabilitation; Nuclear medicine; Medical physics; Osteoporosis; Surgery; Pathology; Bone mineral; Internal medicine","score_opus":0.17429397320963985,"score_gpt":0.5416570944545924,"score_spread":0.3673631212449526,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388076994","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16824259,0.739652,0.039408736,0.009824369,0.03804072,0.003957988,0.00036611053,0.000152806,0.0003546696],"genre_scores_gemma":[0.017154517,0.89802223,0.061729193,0.0027953968,0.019579418,0.000020010133,0.000074775955,0.00029530167,0.00032914945],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9808743,0.0005782929,0.015430353,0.0006900137,0.001893593,0.0005334315],"domain_scores_gemma":[0.96454877,0.013617814,0.018294582,0.0008453088,0.0019881555,0.0007053496],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.018263597,0.00054618856,0.0064887307,0.0009565801,0.0001805895,0.00007020413,0.0011840018,0.00083104474,0.00003459745],"category_scores_gemma":[0.11749396,0.0003593597,0.0101039475,0.0018268384,0.0005274829,0.000095513155,0.00071989355,0.0049749035,0.000014207762],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012009551,0.0006698788,0.01890235,0.0072407746,0.0060604317,0.00044492655,0.000061432205,0.000045348115,0.00009112728,0.000025727844,0.06858264,0.8966744],"study_design_scores_gemma":[0.005721559,0.0021162254,0.097905084,0.06570227,0.013815203,0.0067999493,0.0003093399,0.0034793583,0.000025322928,0.00042859727,0.8026456,0.0010514578],"about_ca_topic_score_codex":0.000010570942,"about_ca_topic_score_gemma":0.0000031257964,"teacher_disagreement_score":0.89562297,"about_ca_system_score_codex":0.00020987273,"about_ca_system_score_gemma":0.0021640987,"threshold_uncertainty_score":0.99988586},"labels":[],"label_agreement":null},{"id":"W4388082881","doi":"10.1016/j.jtho.2023.09.103","title":"OA20.06 Quantification of Pathologically Assessed Lymph Node Area in Lung Cancer Resection Using Deep Learning","year":2023,"lang":"en","type":"article","venue":"Journal of Thoracic Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; McGill University Health Centre","funders":"","keywords":"Medicine; Lung cancer; Lymph node; Resection; Radiology; Lung; Pathology; Surgery; Internal medicine","score_opus":0.049478014994205864,"score_gpt":0.4589445164315564,"score_spread":0.4094665014373506,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388082881","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9776119,0.00054209994,0.017727355,0.00311116,0.00053252775,0.00011045076,6.001842e-7,0.000023251405,0.00034064092],"genre_scores_gemma":[0.9925355,0.00074432284,0.006127765,0.00016395473,0.00026636536,0.000004415465,0.000007542285,0.000019580093,0.0001305969],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9980452,0.0004464943,0.0007685436,0.00016723866,0.00032750738,0.0002450247],"domain_scores_gemma":[0.99823993,0.00037311434,0.0008580037,0.00011554825,0.00030630917,0.00010706255],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027914513,0.00010738761,0.00056353846,0.0005898433,0.00006775046,0.000013012278,0.00012288422,0.00019347106,0.000062800216],"category_scores_gemma":[0.0020796824,0.00008641141,0.00012051249,0.0006782521,0.00009259596,0.000106362946,0.000040942487,0.00087359943,0.0000025331967],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009205977,0.00025576563,0.5501186,0.00033593518,0.00008729633,0.0008021734,0.0006124179,0.06995255,0.27870744,0.000022705079,0.00018949033,0.097995006],"study_design_scores_gemma":[0.0011408704,0.00039588704,0.53834325,0.0007753644,0.00022645923,0.0008037788,0.0006523734,0.45517322,0.0013203042,0.0001226772,0.0009390705,0.00010677912],"about_ca_topic_score_codex":0.000076108416,"about_ca_topic_score_gemma":0.000013207104,"teacher_disagreement_score":0.38522068,"about_ca_system_score_codex":0.00045603325,"about_ca_system_score_gemma":0.0003636835,"threshold_uncertainty_score":0.37954032},"labels":[],"label_agreement":null},{"id":"W4388182028","doi":"10.21203/rs.3.rs-3427561/v1","title":"AI-based Strategies in Breast Mass ≤ 2cm classification with Mammography and Tomosynthesis: A Retrospective Evaluation","year":2023,"lang":"en","type":"preprint","venue":"Research Square","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"L'Alliance Boviteq","funders":"","keywords":"Deep learning; Artificial intelligence; Mammography; Digital Breast Tomosynthesis; Breast imaging; Medicine; Receiver operating characteristic; Radiomics; Machine learning; Digital mammography; Breast cancer; Radiology; Nuclear medicine; Computer science; Internal medicine; Cancer","score_opus":0.06699757420698672,"score_gpt":0.42086017671354653,"score_spread":0.3538626025065598,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388182028","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90473527,0.0011609688,0.009915929,0.07460806,0.00021163053,0.0054556127,0.00012205094,0.00037667932,0.0034138036],"genre_scores_gemma":[0.9970045,0.00026767474,0.0014086497,0.00008061215,0.00017909808,0.0006528282,0.00027387973,0.000068442125,0.00006432304],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9954424,0.00088516076,0.00031417594,0.0008218225,0.0020402498,0.0004961858],"domain_scores_gemma":[0.99768806,0.00045135335,0.00011073406,0.00058514084,0.0009432582,0.00022145383],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0061509092,0.00024036129,0.00044722215,0.0013145157,0.00013470328,0.0002726079,0.00017417406,0.00027775342,0.000056674897],"category_scores_gemma":[0.0010559384,0.00019494467,0.000082731014,0.000961716,0.0003952429,0.00009566868,0.00012348253,0.0028088454,0.000010848298],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010387306,0.0003085524,0.95698726,0.0034058674,0.00023072003,0.00026740856,0.0008746729,0.0027318355,0.0019738562,0.0016423629,0.0011152963,0.029423436],"study_design_scores_gemma":[0.0011332505,0.00020082555,0.7244692,0.0035016243,0.00007104911,0.000015548121,0.0018699418,0.26238436,0.0000370508,0.006078468,0.00007016792,0.00016852167],"about_ca_topic_score_codex":0.0007300708,"about_ca_topic_score_gemma":0.0001453304,"teacher_disagreement_score":0.25965253,"about_ca_system_score_codex":0.00053887686,"about_ca_system_score_gemma":0.0014442614,"threshold_uncertainty_score":0.9994917},"labels":[],"label_agreement":null},{"id":"W4388272077","doi":"10.32920/24438073.v1","title":"Measurement Variability Following MRI System Upgrade","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; Université de Montréal; Institut Universitaire de Gériatrie de Montréal; Toronto Metropolitan University; Montreal Neurological Institute and Hospital; Douglas Mental Health University Institute; McGill University","funders":"Pfizer Canada; Fonds de Recherche du Québec - Santé; Alzheimer's Society; Consortium canadien en neurodégénérescence associée au vieillissement; Pfizer","keywords":"Fluid-attenuated inversion recovery; Upgrade; Hyperintensity; Context (archaeology); Siemens; Magnetic resonance imaging; Nuclear medicine; Medicine; White matter; Radiology; Computer science; Physics; Biology","score_opus":0.03972259078700409,"score_gpt":0.3118656727692562,"score_spread":0.2721430819822521,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388272077","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10653453,0.0012401149,0.6817736,0.056536686,0.02537906,0.0051717455,0.000020873691,0.007748392,0.11559499],"genre_scores_gemma":[0.9854262,0.000031409156,0.0113149835,0.00044830423,0.00077903934,0.00010678061,0.00004822161,0.00010048243,0.0017446085],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99648917,0.00021141107,0.00064713537,0.00084779394,0.0013622992,0.00044217962],"domain_scores_gemma":[0.99820584,0.00010593671,0.00015688673,0.001020954,0.00015159215,0.00035876027],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00520702,0.0003530091,0.00087323476,0.00017685987,0.00010677417,0.00008130862,0.00027524997,0.00033451788,0.00004337887],"category_scores_gemma":[0.0015815939,0.00028511675,0.0005910251,0.00016086848,0.000049214003,0.00002289584,0.0005787085,0.0017687948,0.0001462263],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047423673,0.0019883192,0.57285625,0.07148065,0.0148905935,0.007298635,0.003007637,0.014026591,0.008746391,0.030937584,0.21502279,0.05927034],"study_design_scores_gemma":[0.007609682,0.00034749278,0.114929914,0.030451627,0.0057364907,0.00033945352,0.0015591624,0.78225476,0.0006706851,0.007808011,0.04534414,0.002948586],"about_ca_topic_score_codex":0.00059086125,"about_ca_topic_score_gemma":0.000005522131,"teacher_disagreement_score":0.87889165,"about_ca_system_score_codex":0.0008661898,"about_ca_system_score_gemma":0.00046949962,"threshold_uncertainty_score":0.9999601},"labels":[],"label_agreement":null},{"id":"W4388291500","doi":"10.1002/jmri.29069","title":"Fashioning the Future: Could <scp>AI</scp> Enhanced <scp>MRI</scp> Put <scp>PET</scp> Out of Style?","year":2023,"lang":"en","type":"article","venue":"Journal of Magnetic Resonance Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Computer science","score_opus":0.00839490860713366,"score_gpt":0.27708737298268754,"score_spread":0.2686924643755539,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388291500","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91563386,0.045545187,0.006664641,0.015656145,0.0044590053,0.0008193235,0.000020799782,0.000226419,0.010974638],"genre_scores_gemma":[0.94977707,0.012407291,0.008669882,0.005507593,0.00560318,0.000043052267,0.000025184392,0.00030398334,0.017662793],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99331504,0.00040303142,0.0019674147,0.00067940354,0.0022113302,0.0014237745],"domain_scores_gemma":[0.9925157,0.0034478994,0.0016230971,0.0008816202,0.00089279196,0.0006389113],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.003854572,0.0006573385,0.0013912985,0.0007189034,0.00043934432,0.00029144232,0.0011316722,0.00018324905,0.000037940405],"category_scores_gemma":[0.00976837,0.0004854963,0.000668452,0.0013188241,0.0006579704,0.00047913843,0.00032637335,0.0032969804,0.000099666824],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000059520273,0.00056289043,0.07790205,0.00084166275,0.00040299416,0.004712466,0.016854282,0.0017775527,0.10971381,0.00085959065,0.3830662,0.403247],"study_design_scores_gemma":[0.0060643456,0.0008509942,0.17970268,0.0027048027,0.000648115,0.0024474273,0.014359813,0.042948954,0.0075832815,0.00093694526,0.7416013,0.00015136041],"about_ca_topic_score_codex":0.000025899808,"about_ca_topic_score_gemma":0.0000061991204,"teacher_disagreement_score":0.40309563,"about_ca_system_score_codex":0.0001830711,"about_ca_system_score_gemma":0.0005477028,"threshold_uncertainty_score":0.9997597},"labels":[],"label_agreement":null},{"id":"W4388302460","doi":"10.1148/rycan.220153","title":"Current Status of Cancer Genomics and Imaging Phenotypes: What Radiologists Need to Know","year":2023,"lang":"en","type":"review","venue":"Radiology Imaging Cancer","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sinai Health System; Lunenfeld-Tanenbaum Research Institute; Mount Sinai Hospital; University of Toronto; University Health Network","funders":"National Cancer Institute","keywords":"Radiogenomics; Medicine; Genomics; Precision medicine; Epigenomics; Personalized medicine; Medical physics; Bioinformatics; Pathology; Radiomics; Radiology; Genome; Genetics","score_opus":0.032637063234663664,"score_gpt":0.4055997921946947,"score_spread":0.3729627289600311,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388302460","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004860117,0.9908928,0.00033621775,0.0027487811,0.0038811057,0.0012770989,0.00013009545,0.00018962206,0.00005822673],"genre_scores_gemma":[0.00007527534,0.99577993,0.0007720744,0.000942357,0.0014403708,0.0004158608,0.00016676639,0.00023497966,0.00017236243],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9957546,0.00029737357,0.001185115,0.0011635948,0.0002835979,0.00131569],"domain_scores_gemma":[0.99724203,0.0005459324,0.0006784947,0.0006529336,0.00017609244,0.00070450985],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006867353,0.0007873103,0.0034768805,0.00080392725,0.00013539853,0.000090819216,0.00039252487,0.00021230962,0.00009155045],"category_scores_gemma":[0.0006353934,0.0006477601,0.00044507944,0.00066085433,0.0006989555,0.00016232661,0.00032257225,0.0015503878,0.00003067025],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035805093,0.000028276461,0.008337687,0.010807025,0.0004657539,0.000064454965,0.0003549081,0.000058371937,0.000038303322,0.000058047674,0.009835785,0.96991557],"study_design_scores_gemma":[0.00078072824,0.00003809032,0.00056470215,0.028493654,0.0020116651,0.00030697443,0.00011572997,0.0016220172,0.000002324496,0.000041981835,0.9654525,0.00056966126],"about_ca_topic_score_codex":0.0010746951,"about_ca_topic_score_gemma":0.000028852817,"teacher_disagreement_score":0.9693459,"about_ca_system_score_codex":0.0011551838,"about_ca_system_score_gemma":0.0016955812,"threshold_uncertainty_score":0.9995974},"labels":[],"label_agreement":null},{"id":"W4388450714","doi":"10.1109/ius51837.2023.10306899","title":"Predicting Head and Neck Cancer Treatment Outcomes using Textural Feature Level Fusion of Quantitative Ultrasound Spectroscopic and Computed Tomography: A Machine Learning Approach","year":2023,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Sunnybrook Hospital; Toronto Metropolitan University; Health Sciences Centre; Sunnybrook Health Science Centre","funders":"","keywords":"Computed tomography; Ultrasound; Head and neck cancer; Feature (linguistics); Feature extraction; Computer science; Head and neck; Head (geology); Artificial intelligence; Fusion; Radiology; Tomography; Medicine; Radiation therapy; Geology; Surgery","score_opus":0.043183851971212106,"score_gpt":0.3463252836734946,"score_spread":0.30314143170228247,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388450714","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9945202,0.0018175726,0.0018815938,0.00094039994,0.000085115425,0.00035222547,0.000014826156,0.00013177299,0.00025632468],"genre_scores_gemma":[0.9629353,0.0005889287,0.035436474,0.000112610025,0.000058594138,0.000007957251,0.000077639525,0.00002862581,0.0007538454],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9988383,0.00006904534,0.00023413723,0.0003460967,0.00022755664,0.0002848779],"domain_scores_gemma":[0.9993181,0.00025299247,0.000121086334,0.00010927831,0.00004871943,0.00014981657],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019769666,0.00022588432,0.00053432153,0.00024298846,0.00020400537,0.00003461494,0.000041126466,0.000075595664,0.000016648877],"category_scores_gemma":[0.00016257633,0.00015272823,0.00007845992,0.0003991818,0.0001552627,0.00006851993,0.00005622181,0.00037492588,4.077705e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006768886,0.00006681217,0.97773564,0.0002152146,0.00022347405,0.000013596984,0.0015204203,0.0006111026,0.01616641,0.00009596625,0.000029746036,0.0032539184],"study_design_scores_gemma":[0.001991451,0.00040564907,0.60787874,0.00021460607,0.00013763906,0.000077001794,0.0005445021,0.38828632,0.00027189756,0.000020476087,0.000062352265,0.00010933775],"about_ca_topic_score_codex":0.0030918808,"about_ca_topic_score_gemma":0.00007766664,"teacher_disagreement_score":0.38767523,"about_ca_system_score_codex":0.00005636843,"about_ca_system_score_gemma":0.000045835077,"threshold_uncertainty_score":0.6228076},"labels":[],"label_agreement":null},{"id":"W4388460768","doi":"10.1177/08465371231209255","title":"Clinical Impact of Preoperative Magnetic Resonance Imaging in Breast Cancer","year":2023,"lang":"en","type":"letter","venue":"Canadian Association of Radiologists Journal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; University of Toronto; McMaster University","funders":"","keywords":"Medicine; Magnetic resonance imaging; Breast cancer; Radiology; Mammography; Breast MRI; Medical physics; Cancer; Internal medicine","score_opus":0.016794910378540587,"score_gpt":0.34382014894452856,"score_spread":0.327025238565988,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388460768","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.096897386,0.005717008,0.000023319033,0.893205,0.0019300468,0.00045451985,0.0008469519,0.000026498137,0.00089925993],"genre_scores_gemma":[0.56252193,0.021527505,0.0013953805,0.37682134,0.020883996,0.000054960983,0.0006076012,0.00037649792,0.015810754],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9967689,0.0006120988,0.0012019081,0.0003017558,0.00046904502,0.0006463087],"domain_scores_gemma":[0.99715716,0.00059483474,0.0011677574,0.0002095058,0.00050904276,0.00036173058],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.002494677,0.00025173713,0.0011019405,0.0007521563,0.00006565395,0.00003178392,0.00027110966,0.00062319904,0.0003130759],"category_scores_gemma":[0.0027756027,0.00021082473,0.00049390784,0.00038780697,0.00022585841,0.00007045376,0.000020652189,0.004317076,0.000007005023],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016162669,0.000008212703,0.5237927,0.000025270248,0.00006230638,0.0005747878,0.00006439673,0.000056843754,0.000005104455,0.0000011288103,0.46561757,0.009775552],"study_design_scores_gemma":[0.0013470637,0.00013705008,0.9512632,0.00083247887,0.00011038009,0.00054401084,0.000019199042,0.001583904,3.5940178e-7,0.000054695123,0.043939818,0.00016787609],"about_ca_topic_score_codex":0.041474868,"about_ca_topic_score_gemma":0.004974337,"teacher_disagreement_score":0.51638365,"about_ca_system_score_codex":0.0038692227,"about_ca_system_score_gemma":0.004493118,"threshold_uncertainty_score":0.99995476},"labels":[],"label_agreement":null},{"id":"W4388497864","doi":"10.18280/ria.370520","title":"A Systematic Review of Machine Learning Prediction Models for Colorectal Cancer Patient Survival Using Clinical Data and Gene Expression Profiles","year":2023,"lang":"en","type":"review","venue":"Revue d intelligence artificielle","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Colorectal cancer; Oncology; Gene; Medicine; Gene expression; Expression (computer science); Cancer; Bioinformatics; Internal medicine; Computational biology; Computer science; Artificial intelligence; Biology; Genetics","score_opus":0.19895006917977393,"score_gpt":0.43609889298306137,"score_spread":0.23714882380328745,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388497864","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00009520951,0.956315,0.03841802,0.0000495696,0.0005545118,0.0040965336,0.00038774454,0.00006811777,0.000015327545],"genre_scores_gemma":[0.00005984176,0.99488974,0.0032453532,0.000031906384,0.0003071546,0.00032807284,0.0009034224,0.00009865266,0.00013584927],"study_design_codex":"systematic_review","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9955287,0.0005160149,0.0025146152,0.0007864505,0.00035294058,0.00030126297],"domain_scores_gemma":[0.9963511,0.0012483193,0.0013220884,0.0006931217,0.00020631158,0.00017901232],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0030986145,0.00035386224,0.003075239,0.00016469779,0.00013849935,0.000025518588,0.00033992328,0.00023330054,0.00001898194],"category_scores_gemma":[0.004144109,0.00026029264,0.00040174092,0.00036123965,0.00014260391,0.000093857576,0.0003816409,0.000767891,0.000006123515],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002028303,0.000081881786,0.000023869863,0.8995279,0.00025142008,0.000009817884,0.000092235074,0.0011152081,0.000032083284,0.000012881125,0.00010036921,0.09873207],"study_design_scores_gemma":[0.000039869912,0.00012478339,8.034763e-8,0.48364544,0.0019804835,0.00005778845,0.00004346858,0.5089833,0.000033762288,0.000011252028,0.004957901,0.00012189563],"about_ca_topic_score_codex":0.00003970496,"about_ca_topic_score_gemma":0.0000013352844,"teacher_disagreement_score":0.50786805,"about_ca_system_score_codex":0.00008204964,"about_ca_system_score_gemma":0.00028620896,"threshold_uncertainty_score":0.9999849},"labels":[],"label_agreement":null},{"id":"W4388589244","doi":"10.1093/neuonc/noad179.0780","title":"NIMG-85. EVALUATING THE PERFORMANCE OF A DEEP LEARNING GLIOMA SEGMENTATION MODEL USING COMBINED PRE- AND POST-TREATMENT MRI TRAINING DATA","year":2023,"lang":"en","type":"article","venue":"Neuro-Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Health Services","funders":"","keywords":"Computer science; Segmentation; Convolutional neural network; Workflow; Magnetic resonance imaging; Artificial intelligence; Glioma; Dice; Deep learning; Pattern recognition (psychology); Machine learning; Medicine; Radiology","score_opus":0.07624121402978769,"score_gpt":0.3977261482719263,"score_spread":0.32148493424213864,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388589244","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9945354,0.000096314885,0.0012455108,0.0032363916,0.00016711552,0.0004536889,0.000004216596,0.00007658382,0.00018477745],"genre_scores_gemma":[0.9893397,0.00019815064,0.009603454,0.00053894846,0.00010628234,0.000017639104,0.000116626536,0.000034454304,0.000044716537],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984472,0.00026354147,0.00036113092,0.00035619264,0.00027644774,0.0002954943],"domain_scores_gemma":[0.9986556,0.00061913294,0.00022697344,0.00032522733,0.000077834695,0.000095242714],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010697446,0.00015002428,0.0003535167,0.00014490944,0.00023969289,0.00001914885,0.00016211423,0.00007570697,0.000010742927],"category_scores_gemma":[0.00075914804,0.00010901919,0.000038579747,0.0002609416,0.00019106276,0.0001181705,0.00020678174,0.00040669908,0.0000031059446],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031707555,0.000057087764,0.0073913676,0.000068475645,0.000062439736,0.00004224843,0.0064752074,0.09111899,0.68724626,0.000018585906,0.000017690265,0.20718455],"study_design_scores_gemma":[0.0023121152,0.003203947,0.004240988,0.00004963995,0.00023139028,0.00029888717,0.0012456109,0.9865189,0.0015697634,0.00002344538,0.00022247406,0.00008283044],"about_ca_topic_score_codex":0.0000634602,"about_ca_topic_score_gemma":0.0000071587788,"teacher_disagreement_score":0.8953999,"about_ca_system_score_codex":0.00010352774,"about_ca_system_score_gemma":0.00025122997,"threshold_uncertainty_score":0.44456732},"labels":[],"label_agreement":null},{"id":"W4388598428","doi":"10.1016/j.rpth.2023.100591","title":"OC 36.2 Machine-Learning Based Risk Prediction of Cancer Associated Thrombosis: Internal, External, and Pre-Clinical Validation Studies","year":2023,"lang":"en","type":"article","venue":"Research and Practice in Thrombosis and Haemostasis","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Ottawa Hospital","funders":"","keywords":"Medicine; Thrombosis; Computer science; Internal medicine","score_opus":0.25691676878617004,"score_gpt":0.5351246871004672,"score_spread":0.2782079183142972,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388598428","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98060364,0.00926845,0.000088415145,0.009256531,0.00011771737,0.00038883233,0.00004602822,0.00005242855,0.00017799033],"genre_scores_gemma":[0.7595348,0.23956491,0.0005274298,0.00013431432,0.00008060805,0.000038737333,0.00002817426,0.000022132988,0.00006888708],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99633735,0.0015615586,0.00059485954,0.00046380734,0.00066593604,0.00037648727],"domain_scores_gemma":[0.9915359,0.0073640165,0.00031421747,0.00016596571,0.00039925656,0.00022063284],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009481481,0.00016552414,0.000569245,0.00039583605,0.00031258544,0.00012683289,0.000076611126,0.00014472965,0.000043226846],"category_scores_gemma":[0.023469098,0.00013651409,0.000054860346,0.00062732346,0.0005491194,0.00038288423,0.0001856818,0.0014535245,0.0000021845526],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00069436553,0.00032284192,0.92160213,0.00036318714,0.00067710073,0.000019439363,0.0022779668,0.00008148462,0.0010272608,0.000022553584,0.001666695,0.07124499],"study_design_scores_gemma":[0.0033819522,0.0013816161,0.92522925,0.0017895593,0.0004231296,0.000012736482,0.0036852865,0.06007608,0.0004455415,0.00039120106,0.003036036,0.00014759954],"about_ca_topic_score_codex":0.003591643,"about_ca_topic_score_gemma":0.000113438124,"teacher_disagreement_score":0.23029646,"about_ca_system_score_codex":0.00006964858,"about_ca_system_score_gemma":0.00010511942,"threshold_uncertainty_score":0.98475665},"labels":[],"label_agreement":null},{"id":"W4388798703","doi":"10.1016/j.jtocrr.2023.100602","title":"Imaging-Based Biomarkers Predict Programmed Death-Ligand 1 and Survival Outcomes in Advanced NSCLC Treated With Nivolumab and Pembrolizumab: A Multi-Institutional Study","year":2023,"lang":"en","type":"article","venue":"JTO Clinical and Research Reports","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre hospitalier de l'Université Laval; Université Laval; Centre Hospitalier de l’Université de Montréal; Centre hospitalier universitaire de Québec; Université du Québec à Trois-Rivières","funders":"Fonds de Recherche du Québec - Santé; Institut universitaire de cardiologie et de pneumologie de Québec, Université Laval","keywords":"Pembrolizumab; Nivolumab; Radiomics; Concordance; Medicine; Oncology; Internal medicine; Cohort; Imaging biomarker; Biomarker; Radiology; Immunotherapy; Cancer; Magnetic resonance imaging","score_opus":0.07396518050724483,"score_gpt":0.44678724647584117,"score_spread":0.37282206596859635,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388798703","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9947504,0.00034337986,0.000060288556,0.0029773698,0.00009846879,0.0014546455,0.0000036773606,0.00012580943,0.00018599075],"genre_scores_gemma":[0.9984725,0.00017116335,0.00067108794,0.00007490708,0.000058348593,0.0001283142,0.000030630858,0.000029275767,0.00036377553],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99644244,0.00037813996,0.00074844697,0.00083614513,0.0010216442,0.000573213],"domain_scores_gemma":[0.99779177,0.0009424226,0.000112264504,0.0003035784,0.00025090808,0.00059907226],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005958839,0.00022715388,0.0006995673,0.00040190516,0.0002726597,0.00009761551,0.00006127124,0.000103022074,0.0000047177377],"category_scores_gemma":[0.0051229787,0.00013879039,0.000066288754,0.0005570812,0.0012931199,0.000095423595,0.0001529236,0.000908062,0.0000011736837],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012005654,0.0008614472,0.9495331,0.000103619015,0.00013957029,0.0086069,0.00009208655,0.000008917201,0.00006287565,0.0000056274525,0.000072909635,0.03931235],"study_design_scores_gemma":[0.013014603,0.00111612,0.9590725,0.00026327113,0.000060346607,0.00033335856,0.0003691392,0.02494339,0.000008050064,0.000038306753,0.0006271721,0.00015377965],"about_ca_topic_score_codex":0.0008931589,"about_ca_topic_score_gemma":0.00021378884,"teacher_disagreement_score":0.03915857,"about_ca_system_score_codex":0.000040439463,"about_ca_system_score_gemma":0.00042194838,"threshold_uncertainty_score":0.6133054},"labels":[],"label_agreement":null},{"id":"W4388934273","doi":"10.1088/2057-1976/ad0f3e","title":"Multimodality radiomics prediction of radiotherapy-induced the early proctitis and cystitis in rectal cancer patients: a machine learning study","year":2023,"lang":"en","type":"article","venue":"Biomedical Physics & Engineering Express","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Tehran University of Medical Sciences and Health Services","keywords":"Artificial intelligence; Random forest; Receiver operating characteristic; Feature selection; Medicine; Naive Bayes classifier; Wilcoxon signed-rank test; Linear discriminant analysis; Magnetic resonance imaging; Mathematics; Support vector machine; Radiology; Nuclear medicine; Pattern recognition (psychology); Computer science; Machine learning; Internal medicine","score_opus":0.010943365618443389,"score_gpt":0.262024390435943,"score_spread":0.2510810248174996,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388934273","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9912128,0.00019097209,0.007079321,0.00029695517,0.00037677604,0.0006395551,0.00003500559,0.00016343992,0.0000051848942],"genre_scores_gemma":[0.9979601,0.00018619123,0.0012443006,0.000031259206,0.00032967655,0.000116042014,0.000057834597,0.0000491349,0.000025473168],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9984098,0.00008019372,0.0003885135,0.00032100466,0.00049028447,0.0003102051],"domain_scores_gemma":[0.99930763,0.00018553413,0.000098770455,0.00019273271,0.000058307793,0.00015700993],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046584048,0.00019425219,0.00039702843,0.00016239072,0.00007135416,0.000023313374,0.00013121363,0.000089390735,0.000007020616],"category_scores_gemma":[0.00036853942,0.00015035605,0.0000635941,0.0006444408,0.00011019759,0.00009094871,0.000078501784,0.0006957638,8.923112e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019220254,0.0011682665,0.6702194,0.0005254062,0.00035764568,0.000066747176,0.008193791,0.0045004645,0.25919527,0.00005494694,0.00022495032,0.055300925],"study_design_scores_gemma":[0.0038341444,0.00062712276,0.60410553,0.00034366295,0.000064814085,0.000006431583,0.00010048807,0.38743895,0.0002060023,0.00001714868,0.003090624,0.00016508992],"about_ca_topic_score_codex":0.0013607943,"about_ca_topic_score_gemma":0.0000015638221,"teacher_disagreement_score":0.38293847,"about_ca_system_score_codex":0.000099013225,"about_ca_system_score_gemma":0.000046569934,"threshold_uncertainty_score":0.61313415},"labels":[],"label_agreement":null},{"id":"W4388967127","doi":"10.1148/rg.230180","title":"National Cancer Institute Imaging Data Commons: Toward Transparency, Reproducibility, and Scalability in Imaging Artificial Intelligence","year":2023,"lang":"en","type":"article","venue":"Radiographics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"National Cancer Institute","keywords":"Data science; Transparency (behavior); Medicine; Computer science; Scalability; Data curation; Data quality; Artificial intelligence; Database","score_opus":0.11315220813134057,"score_gpt":0.3961528615510551,"score_spread":0.28300065341971453,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388967127","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8994163,0.0041034883,0.010760746,0.08247089,0.0012669985,0.0007670708,0.0001425914,0.00042104165,0.00065086456],"genre_scores_gemma":[0.9954226,0.0017088306,0.0016190892,0.00063218136,0.00030532357,0.000027866148,0.0002494444,0.000026081327,0.0000085598695],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99706125,0.00010681307,0.0006011422,0.0012889942,0.0005442877,0.0003975245],"domain_scores_gemma":[0.99826527,0.00021969852,0.00008120626,0.0011241725,0.00012370182,0.00018595542],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0047164913,0.00019395366,0.00036116058,0.00063465687,0.00014261354,0.00007273634,0.00035469313,0.00005462597,0.000019380635],"category_scores_gemma":[0.0023686364,0.00018797259,0.00007467217,0.0018611755,0.0007626227,0.000365093,0.0002183007,0.00073945965,0.0000035348999],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004280016,0.00010813044,0.8353611,0.00019584633,0.000030944015,0.00008983115,0.00055903237,0.0003624979,0.0002850821,0.0016768628,0.00071373046,0.16057411],"study_design_scores_gemma":[0.0003563364,0.000016723667,0.4566222,0.00033363796,0.00007441762,0.000097391836,0.00025024693,0.51996976,0.00006339258,0.018410387,0.003536613,0.00026888712],"about_ca_topic_score_codex":0.0012688027,"about_ca_topic_score_gemma":0.0004726156,"teacher_disagreement_score":0.51960725,"about_ca_system_score_codex":0.00008204191,"about_ca_system_score_gemma":0.0002664891,"threshold_uncertainty_score":0.76653},"labels":[],"label_agreement":null},{"id":"W4388998108","doi":"10.1007/978-1-0716-3499-8_23","title":"Quantitation of Oncologic Image Features for Radiomic Analyses in PET","year":2023,"lang":"en","type":"article","venue":"Methods in molecular biology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Radiomics; Positron emission tomography; Voxel; Artificial intelligence; Computer science; Medical imaging; Field (mathematics); Computer vision; Medical physics; Nuclear medicine; Pattern recognition (psychology); Medicine; Mathematics","score_opus":0.06431353896398899,"score_gpt":0.5417673059431451,"score_spread":0.47745376697915615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388998108","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33577296,0.00058263406,0.661278,0.001544024,0.00015922994,0.00030077237,0.000003337645,0.000028661492,0.00033033127],"genre_scores_gemma":[0.09354392,0.000111308065,0.9057545,0.00037069595,0.000026213795,0.000045698456,0.00007339578,0.000015302245,0.000058975653],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9985198,0.00064229214,0.00031733591,0.00024011021,0.000055156863,0.00022532507],"domain_scores_gemma":[0.9989013,0.00077504193,0.00009150541,0.0001572517,0.000039040977,0.000035857312],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020335373,0.000094980904,0.00044088202,0.0005743741,0.0000141956325,0.0000036413203,0.00009779029,0.00009304184,0.00001061835],"category_scores_gemma":[0.0046722856,0.00007818399,0.000107996806,0.00058841496,0.00013563278,0.000012850475,0.00003502221,0.00024284727,0.0000016207914],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000086296044,0.00004136952,0.005409846,0.00008016615,0.00003050377,0.0001029148,0.00010787496,0.00031064454,0.96981937,0.0020757413,0.00012509622,0.021810155],"study_design_scores_gemma":[0.010913902,0.0023238596,0.20749591,0.00035758063,0.00031078124,0.00027053876,0.0011302648,0.17052455,0.5199016,0.08184507,0.0042928313,0.00063314295],"about_ca_topic_score_codex":0.000102157006,"about_ca_topic_score_gemma":0.000008285193,"teacher_disagreement_score":0.44991782,"about_ca_system_score_codex":0.000041648767,"about_ca_system_score_gemma":0.000053090847,"threshold_uncertainty_score":0.55934995},"labels":[],"label_agreement":null},{"id":"W4389057806","doi":"10.26481/dis.20231205sp","title":"Artificial intelligence in medical imaging","year":2023,"lang":"en","type":"dissertation","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"L'Alliance Boviteq","funders":"","keywords":"Medical imaging; Artificial intelligence; Computer science; Data science; Cognitive science; Psychology","score_opus":0.016707496417361828,"score_gpt":0.36592886847989864,"score_spread":0.3492213720625368,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389057806","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5474455,0.0022479042,0.011549952,0.04844247,0.014455629,0.0018342524,0.000005422181,0.0018541816,0.37216473],"genre_scores_gemma":[0.9158445,0.0014456034,0.0027133147,0.0048185512,0.0024537917,0.00010685294,0.0025062906,0.00035010435,0.06976099],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978947,0.00003424477,0.00057506334,0.0003861602,0.00077810924,0.00033171294],"domain_scores_gemma":[0.9992572,0.00016123967,0.000078673926,0.00020073711,0.00005352007,0.00024859307],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007350804,0.00019957809,0.00042784907,0.0004647832,0.000037298072,0.000029787889,0.00017043608,0.00023565823,0.0017691761],"category_scores_gemma":[0.0020234447,0.0001720143,0.00011377823,0.00042781467,0.000051916824,0.000029183215,0.000027213395,0.00146829,0.00045176086],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000078961995,0.00008278288,0.0023016115,0.00025419923,0.00002379588,0.0016380117,0.00053307967,0.000008000264,0.00014459457,0.0023095803,0.0028322365,0.9897931],"study_design_scores_gemma":[0.0007266505,0.00013478732,0.06844553,0.008871308,0.00030710205,0.000493817,0.013683799,0.8655323,0.001806568,0.026576517,0.0119204195,0.0015012413],"about_ca_topic_score_codex":0.00047423615,"about_ca_topic_score_gemma":0.00048041984,"teacher_disagreement_score":0.9882919,"about_ca_system_score_codex":0.000071521485,"about_ca_system_score_gemma":0.00038978996,"threshold_uncertainty_score":0.99914336},"labels":[],"label_agreement":null},{"id":"W4389062634","doi":"10.21468/scipost.report.6933","title":"Report on scipost_202212_00014v1","year":2023,"lang":"en","type":"peer-review","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Business","score_opus":0.035178815241963333,"score_gpt":0.3849910840147989,"score_spread":0.3498122687728356,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389062634","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000024443636,0.0065304637,0.000076399636,0.5649319,0.006999776,0.0006824927,0.000028806304,0.0005979008,0.42012778],"genre_scores_gemma":[0.000011295634,0.009057111,0.0005640025,0.054183256,0.0018423941,0.000051242063,0.002881756,0.0001441568,0.93126476],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9971288,0.000047665533,0.00061935233,0.00070125534,0.0011142719,0.00038864493],"domain_scores_gemma":[0.99810857,0.00018529006,0.00022917698,0.0009759802,0.0001771552,0.0003238611],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001262623,0.00034410643,0.0010256357,0.00026075222,0.000075205426,0.000026986181,0.00020548842,0.00023882856,0.0039977035],"category_scores_gemma":[0.0038092947,0.00025152034,0.0003773632,0.0003857987,0.00008337697,0.00001533553,0.00012506194,0.0018532253,0.002976772],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008281335,0.00004584407,0.000047235415,0.0030861816,0.00011390886,0.005657999,0.0000035595006,0.0000015068745,0.000003137697,0.000101130674,0.96744716,0.02348408],"study_design_scores_gemma":[0.00031075263,0.0001348106,0.00020472312,0.01222279,0.00039277403,0.0015136248,0.0000022736883,0.00022463888,0.000004026048,0.00005874378,0.984692,0.00023885586],"about_ca_topic_score_codex":0.00020697084,"about_ca_topic_score_gemma":0.0000059580843,"teacher_disagreement_score":0.511137,"about_ca_system_score_codex":0.00012370743,"about_ca_system_score_gemma":0.00042391883,"threshold_uncertainty_score":0.9999937},"labels":[],"label_agreement":null},{"id":"W4389084939","doi":"10.1038/s41598-023-47702-8","title":"Predicting stereotactic radiosurgery outcomes with multi-observer qualitative appearance labelling versus MRI radiomics","year":2023,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"London Health Sciences Centre; Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Western University; London Health Sciences Foundation; Government of Ontario","keywords":"Radiomics; Radiogenomics; Medicine; Radiosurgery; Magnetic resonance imaging; Risk stratification; Radiology; Medical physics; Internal medicine; Radiation therapy","score_opus":0.04992698681118757,"score_gpt":0.3548771689447402,"score_spread":0.3049501821335526,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389084939","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9862323,0.00026479652,0.0021949424,0.0015946005,0.008459341,0.00045979,0.0000022950392,0.0004496735,0.00034228954],"genre_scores_gemma":[0.9871677,0.000031522613,0.006265779,0.00013776335,0.00016399623,0.000031372143,0.000087155146,0.00007266486,0.006042054],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99652493,0.00014863699,0.0007187471,0.0009696832,0.0009805808,0.00065742084],"domain_scores_gemma":[0.99770534,0.00043375924,0.0004538951,0.0008553505,0.0002127107,0.00033897167],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004511735,0.0002702279,0.0005658246,0.00038301418,0.0004835239,0.00023663997,0.00012924589,0.000085857646,0.000031108026],"category_scores_gemma":[0.001902806,0.00020663899,0.00017614284,0.0012862275,0.00045055483,0.00026615857,0.00007479861,0.0005478325,0.0000595792],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044890586,0.0002811202,0.9504922,0.000523968,0.00075731333,0.008763804,0.017557453,0.004252161,0.004799725,0.00007623247,0.006974669,0.0050724642],"study_design_scores_gemma":[0.023107957,0.0009765734,0.31090927,0.0050281784,0.0015975018,0.0053366167,0.023220675,0.5536125,0.0055101514,0.0012255101,0.06624164,0.0032334796],"about_ca_topic_score_codex":0.00007519076,"about_ca_topic_score_gemma":0.0000126597,"teacher_disagreement_score":0.63958293,"about_ca_system_score_codex":0.00012280497,"about_ca_system_score_gemma":0.00027481004,"threshold_uncertainty_score":0.84264934},"labels":[],"label_agreement":null},{"id":"W4389151000","doi":"10.20944/preprints202311.1644.v1","title":"Radiomics and Artificial Intelligence in Radiotheranostics: A Review of Applications for Radioligands Targeting SSTR and PSMA","year":2023,"lang":"en","type":"review","venue":"Preprints.org","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Iran National Science Foundation; Iran University of Medical Sciences; National Science Foundation","keywords":"Radiomics; Workflow; Neuroendocrine tumors; Molecular imaging; Medicine; Computer science; Artificial intelligence; Pathology","score_opus":0.14467847913308893,"score_gpt":0.44436579244819163,"score_spread":0.2996873133151027,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389151000","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00017818711,0.9903946,0.0059938664,0.0003656707,0.00008792682,0.0027983212,0.000022951639,0.00004541869,0.00011308565],"genre_scores_gemma":[0.000104903964,0.9956648,0.003059433,0.00014781879,0.0002637165,0.0005132618,0.00009417327,0.000074328134,0.000077587014],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977166,0.000098250755,0.0011599092,0.00059516216,0.00016458299,0.0002654972],"domain_scores_gemma":[0.99818766,0.0007474631,0.00042874942,0.00040625615,0.00007222121,0.00015765116],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0018834365,0.00028573818,0.0017953502,0.00025529886,0.000056274337,0.000009329726,0.0001861756,0.00018624205,0.000026559093],"category_scores_gemma":[0.002532279,0.00025114822,0.00021503122,0.00039522408,0.00020132137,0.000029190744,0.00013581497,0.00060086726,0.000015109206],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012774005,0.000046230798,0.0009825543,0.18929884,0.00013647368,0.0000073310625,0.00012134965,0.0000018671719,0.000044521857,0.0010168919,0.000034170946,0.808297],"study_design_scores_gemma":[0.00032769924,0.000056237463,0.0001713296,0.15580574,0.0013522053,0.00018832143,0.000048480586,0.002279457,0.00005752465,0.0012451055,0.8380246,0.00044329022],"about_ca_topic_score_codex":0.000018913928,"about_ca_topic_score_gemma":8.1173613e-7,"teacher_disagreement_score":0.83799046,"about_ca_system_score_codex":0.00007587721,"about_ca_system_score_gemma":0.00019983371,"threshold_uncertainty_score":0.9999941},"labels":[],"label_agreement":null},{"id":"W4389196995","doi":"10.1007/978-3-031-47401-9","title":"Medical Image Computing and Computer Assisted Intervention – MICCAI 2023 Workshops","year":2023,"lang":"en","type":"book","venue":"Lecture notes in computer science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Multimedia; Medical physics; Human–computer interaction; Medicine","score_opus":0.01215078078573951,"score_gpt":0.3109308536036566,"score_spread":0.2987800728179171,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389196995","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003264453,0.0005082396,0.98812795,0.0039424836,0.0028930723,0.00038671837,0.0000033323865,0.00023625583,0.00063748733],"genre_scores_gemma":[0.11514208,0.00048511158,0.8426738,0.017366337,0.013527069,0.000025532034,0.0004781285,0.0004430286,0.009858913],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99578077,0.00011381786,0.00073409063,0.0012443921,0.0014185978,0.00070832216],"domain_scores_gemma":[0.99747103,0.0010705063,0.00026827317,0.00052877585,0.00018150748,0.00047987374],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0025308616,0.00045859104,0.000852654,0.00084565714,0.00022502535,0.00032253243,0.00070609164,0.0004823319,0.000068750065],"category_scores_gemma":[0.0010124844,0.00039735116,0.00019506057,0.0008930719,0.0013769771,0.00013567517,0.0011439933,0.0025503386,0.000053099946],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018051236,0.00006735066,0.00066232774,0.00036879984,0.00004326991,0.0008794101,0.00030211895,0.00077812927,0.00005892906,0.000049184106,0.0023685235,0.9944039],"study_design_scores_gemma":[0.001256899,0.00020427389,0.008885969,0.005807078,0.000052011634,0.0008235857,9.0580386e-7,0.9789853,0.000021700751,0.0022077188,0.0013353884,0.00041914496],"about_ca_topic_score_codex":0.000044764733,"about_ca_topic_score_gemma":0.000035214856,"teacher_disagreement_score":0.99398476,"about_ca_system_score_codex":0.00035081917,"about_ca_system_score_gemma":0.00068664516,"threshold_uncertainty_score":0.9998478},"labels":[],"label_agreement":null},{"id":"W4389213238","doi":"10.1007/978-3-031-47401-9_12","title":"Cross-Task Attention Network: Improving Multi-task Learning for Medical Imaging Applications","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; Princess Margaret Cancer Centre; University Health Network; University of Toronto","funders":"","keywords":"Computer science; Leverage (statistics); Multi-task learning; Artificial intelligence; Task (project management); Medical imaging; Machine learning; Deep learning; Segmentation","score_opus":0.013188025284169506,"score_gpt":0.31213184252784076,"score_spread":0.29894381724367125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389213238","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00013040227,0.0005600005,0.993774,0.0024985203,0.0013208211,0.0009515616,0.000003874983,0.00030674433,0.0004540929],"genre_scores_gemma":[0.31484747,0.00047774543,0.64449507,0.009661228,0.015112411,0.00048780476,0.0006125849,0.00064766983,0.01365801],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99614865,0.000027734723,0.00066587125,0.0012604754,0.0010528952,0.00084436743],"domain_scores_gemma":[0.99765813,0.00082790933,0.00032606692,0.00052883325,0.00028652546,0.00037254614],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0024224084,0.0004105286,0.00059037737,0.00048050698,0.0006138397,0.0002872037,0.00069926045,0.00032607082,0.00003495494],"category_scores_gemma":[0.0012430296,0.0003768586,0.00023681315,0.00040344492,0.00094414206,0.00014732766,0.0004919524,0.0021272365,0.000038307215],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001547221,0.000025183295,0.0044349944,0.0002305939,0.0000234561,0.00007512211,0.00009549021,0.034234654,0.00037595248,0.0006489622,0.000048219634,0.9597919],"study_design_scores_gemma":[0.0010181572,0.00006422727,0.0019127041,0.00094398303,0.000054888882,0.00014182126,4.903545e-7,0.98162013,0.000013396886,0.0038450805,0.010010925,0.0003741906],"about_ca_topic_score_codex":0.00003892143,"about_ca_topic_score_gemma":0.000018367538,"teacher_disagreement_score":0.9594177,"about_ca_system_score_codex":0.00025215943,"about_ca_system_score_gemma":0.0005878276,"threshold_uncertainty_score":0.99986833},"labels":[],"label_agreement":null},{"id":"W4389213272","doi":"10.1007/978-3-031-47401-9_10","title":"Cellular Features Based Interpretable Network for Classifying Cell-Of-Origin from Whole Slide Images for Diffuse Large B-cell Lymphoma Patients","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Convolutional neural network; Computer science; Diffuse large B-cell lymphoma; Artificial intelligence; Pattern recognition (psychology); Feature (linguistics); Lymphoma; Image (mathematics); Deep learning; Germinal center; Contextual image classification; Artificial neural network; Machine learning; Pathology; B cell; Medicine","score_opus":0.011577374087686498,"score_gpt":0.25899881969495986,"score_spread":0.24742144560727336,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389213272","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004536336,0.00068931485,0.9900912,0.00048774952,0.002356012,0.0011033681,0.00020157151,0.00009750714,0.00043691194],"genre_scores_gemma":[0.42850518,0.00005163427,0.5611722,0.003739403,0.002081355,0.00008221548,0.0009079352,0.00025551594,0.003204561],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969505,0.000028245086,0.00056850206,0.0010395473,0.00062879804,0.0007844287],"domain_scores_gemma":[0.9967909,0.001717614,0.0003992838,0.0006423611,0.0002337669,0.00021607941],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00075976836,0.00047973488,0.0008591502,0.000385573,0.00023748052,0.00013811549,0.00071141165,0.00033233874,0.000010069009],"category_scores_gemma":[0.00038488102,0.0004118525,0.00032459438,0.000246493,0.00032569168,0.00010189234,0.00027250187,0.00060319,0.0000058274804],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015441885,0.0036224632,0.024260709,0.0059380927,0.00033897246,0.00029248194,0.0025294868,0.084914535,0.024619201,0.0011303879,0.026234748,0.8245747],"study_design_scores_gemma":[0.011993999,0.000638939,0.00088812556,0.0028088752,0.00021825712,0.0000023047144,0.0000013533626,0.93553317,0.009385783,0.012488436,0.025273632,0.0007671188],"about_ca_topic_score_codex":0.00004690506,"about_ca_topic_score_gemma":0.000010202201,"teacher_disagreement_score":0.85061866,"about_ca_system_score_codex":0.00019315863,"about_ca_system_score_gemma":0.0003519324,"threshold_uncertainty_score":0.99983335},"labels":[],"label_agreement":null},{"id":"W4389238089","doi":"10.3389/fmed.2023.1271687","title":"Comparison of MRI radiomics-based machine learning survival models in predicting prognosis of glioblastoma multiforme","year":2023,"lang":"en","type":"article","venue":"Frontiers in Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Montreal Neurological Institute and Hospital","funders":"National Natural Science Foundation of China","keywords":"Lasso (programming language); Radiomics; Glioblastoma; Proportional hazards model; Medicine; Random forest; Artificial intelligence; Machine learning; Test set; Internal medicine; Oncology; Overall survival; Radiology; Computer science","score_opus":0.025208638713158905,"score_gpt":0.32363992375829226,"score_spread":0.29843128504513333,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389238089","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95514476,0.0016130272,0.03754519,0.003118722,0.000997427,0.0006975503,0.00000842847,0.0001440227,0.0007308876],"genre_scores_gemma":[0.9851809,0.00029280235,0.014021596,0.000082178136,0.0001389529,0.000028981252,0.00010158809,0.000058368114,0.00009462892],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967307,0.00020737418,0.0013231708,0.00041530424,0.00079639733,0.0005270977],"domain_scores_gemma":[0.9985982,0.00037426254,0.00044433255,0.00028300815,0.00011049459,0.00018971165],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024595105,0.00026981533,0.0016492878,0.0015998499,0.00004979314,0.0000043698847,0.00024593735,0.00017084487,0.00002766963],"category_scores_gemma":[0.0017402415,0.00023292024,0.000118771335,0.0017660536,0.00044290937,0.000092191694,0.00006924816,0.0011295147,0.0000013171151],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006362091,0.00023110173,0.8945501,0.00066031486,0.00007016157,0.000059343434,0.002693187,0.084752806,0.0020322506,0.00003280069,0.0013984664,0.012883259],"study_design_scores_gemma":[0.0064037074,0.00082430936,0.05684593,0.001912084,0.000090316775,0.000005906623,0.0024854254,0.9295271,0.0012141982,0.0001474366,0.00038974013,0.00015384566],"about_ca_topic_score_codex":0.0006219957,"about_ca_topic_score_gemma":0.00005523082,"teacher_disagreement_score":0.8447743,"about_ca_system_score_codex":0.00014972134,"about_ca_system_score_gemma":0.00013055932,"threshold_uncertainty_score":0.9498212},"labels":[],"label_agreement":null},{"id":"W4389279747","doi":"10.1016/j.annonc.2023.10.294","title":"159P Classical computer vision and modern deep-learning of pancreatic stroma histology features to diagnose cancer","year":2023,"lang":"en","type":"article","venue":"Annals of Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Centre Hospitalier de l’Université de Montréal","funders":"","keywords":"Medicine; Pancreatic cancer; Stroma; Histology; Pathology; Cancer; Artificial intelligence; Internal medicine; Immunohistochemistry","score_opus":0.029870291817855686,"score_gpt":0.40001903912378195,"score_spread":0.3701487473059263,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389279747","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9525671,0.0009774826,0.0016628444,0.043835312,0.00019377605,0.00015286819,0.0000023831624,0.00004078821,0.0005674606],"genre_scores_gemma":[0.99243224,0.0014078865,0.0026038506,0.0029484672,0.00017811063,0.000016230622,0.000013127205,0.000019133393,0.00038094187],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99889714,0.0001462001,0.00028728205,0.00024145095,0.00016184285,0.00026609926],"domain_scores_gemma":[0.9988409,0.00060606404,0.00013291487,0.00013126268,0.00010191944,0.00018690739],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037045262,0.0001115364,0.0006074595,0.00020655793,0.00004232208,0.0000037706602,0.00008164546,0.00013897923,0.00004351051],"category_scores_gemma":[0.0005276543,0.0000905023,0.00007066145,0.00017985735,0.00020985771,0.0000324422,0.00011737375,0.00035082555,0.0000051234456],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040225103,0.00019735268,0.038051214,0.00019765337,0.00015451299,0.00024371425,0.0013521027,0.0014949208,0.015050543,0.00079973886,0.028624354,0.91343164],"study_design_scores_gemma":[0.0026517266,0.009897532,0.68703914,0.0004587492,0.00019742048,0.00022957256,0.00016592394,0.17708108,0.001018977,0.00075217977,0.12027926,0.00022845378],"about_ca_topic_score_codex":0.00016524029,"about_ca_topic_score_gemma":0.000023881195,"teacher_disagreement_score":0.9132032,"about_ca_system_score_codex":0.000025073983,"about_ca_system_score_gemma":0.000076654025,"threshold_uncertainty_score":0.36905766},"labels":[],"label_agreement":null},{"id":"W4389366188","doi":"10.1212/wnl.98.18_supplement.1767","title":"Head-to-head comparison of tau and amyloid PET visual reads for differential diagnosis: An international, multi-center study (S20.003)","year":2022,"lang":"en","type":"article","venue":"Neurology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier de l’Université de Montréal","funders":"","keywords":"Head (geology); Center (category theory); Amyloid (mycology); Differential (mechanical device); Medicine; Pathology; Physics; Chemistry; Biology","score_opus":0.037460824729785805,"score_gpt":0.4076328006394495,"score_spread":0.3701719759096637,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389366188","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99269396,0.000026682153,0.0010556113,0.004539282,0.0009605004,0.0006463615,0.000025716365,0.000033849527,0.000018040773],"genre_scores_gemma":[0.9963047,0.000011809947,0.00045726568,0.0026691712,0.000188581,0.00023241555,0.000079025165,0.00002883741,0.00002822667],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9986536,0.00019952956,0.00032221185,0.0003753155,0.000236807,0.00021255406],"domain_scores_gemma":[0.9993815,0.00015006245,0.000101821024,0.00017726209,0.00004340089,0.00014599552],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020813843,0.00012592143,0.00039058982,0.00017127681,0.000112851434,0.000012608678,0.00016747884,0.000025942807,0.00012745772],"category_scores_gemma":[0.00022089458,0.000118128264,0.00005278464,0.00007254812,0.00007059966,0.000033621265,0.0002061123,0.00044275724,0.00000125487],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015534449,0.0055263666,0.97804636,0.000024713187,0.0000819887,0.00006885297,0.0011074587,0.000142385,0.0046845158,0.000024505807,0.0006610783,0.008078327],"study_design_scores_gemma":[0.010237889,0.014755105,0.8491919,0.0000095411815,0.00012147707,0.00017922951,0.00021510644,0.11138871,0.00008410878,0.000008367444,0.013673884,0.00013466472],"about_ca_topic_score_codex":0.00017424276,"about_ca_topic_score_gemma":0.000077349796,"teacher_disagreement_score":0.12885444,"about_ca_system_score_codex":0.000016398528,"about_ca_system_score_gemma":0.000018969944,"threshold_uncertainty_score":0.4817131},"labels":[],"label_agreement":null},{"id":"W4389367847","doi":"10.1212/wnl.98.18_supplement.1687","title":"Machine Learning-Based Prediction of New Multiple Sclerosis Lesion Formation Using Radiomic Features from Pre-Lesion Normal Appearing White Matter (S26.009)","year":2022,"lang":"en","type":"article","venue":"Neurology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; NeuroRx Research (Canada)","funders":"","keywords":"Lesion; Multiple sclerosis; White matter; Medicine; Artificial intelligence; Pathology; Radiology; Computer science; Magnetic resonance imaging","score_opus":0.0278630576898284,"score_gpt":0.25280566121386533,"score_spread":0.22494260352403694,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389367847","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97406065,0.0002655074,0.022363165,0.0023006666,0.0004748595,0.0003165646,0.000028580529,0.00010668011,0.00008330773],"genre_scores_gemma":[0.9952901,0.000024523644,0.0018548827,0.0020187697,0.00019942512,0.000011796911,0.00039438208,0.00005221204,0.00015388103],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998148,0.00032984203,0.00043771137,0.0003685108,0.00040915192,0.00030678487],"domain_scores_gemma":[0.99912417,0.00012910253,0.0003033758,0.00026290515,0.000037289672,0.00014317245],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034069017,0.00019268431,0.00037635147,0.00030534112,0.0003637825,0.000014381433,0.00015121081,0.00012319807,0.00049088453],"category_scores_gemma":[0.00013728287,0.00019072,0.00012843564,0.0002098418,0.000077677236,0.00013292652,0.00016811104,0.0012549879,0.0000072971447],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0024486836,0.00011633842,0.7020273,0.00006401347,0.000029664923,0.000029703504,0.0006148642,0.13970388,0.15046862,0.0000018767225,0.0011100168,0.0033850062],"study_design_scores_gemma":[0.0024417625,0.0007248999,0.4651793,0.000036487985,0.00007987576,0.00014673367,0.000011404039,0.5289546,0.001089871,0.000010630233,0.0012442798,0.000080145306],"about_ca_topic_score_codex":0.00189187,"about_ca_topic_score_gemma":0.000015476067,"teacher_disagreement_score":0.38925073,"about_ca_system_score_codex":0.000075962605,"about_ca_system_score_gemma":0.000086770575,"threshold_uncertainty_score":0.7777336},"labels":[],"label_agreement":null},{"id":"W4389368173","doi":"10.1212/wnl.98.18_supplement.1597","title":"Examining Regional Brain Volume Differences in Radiologically Isolated Syndrome (P15-4.010)","year":2022,"lang":"en","type":"article","venue":"Neurology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hôpital Notre-Dame; University of British Columbia","funders":"","keywords":"Volume (thermodynamics); Brain size; Medicine; Nuclear medicine; Physical medicine and rehabilitation; Neuroscience; Psychology; Radiology; Magnetic resonance imaging; Physics","score_opus":0.027881841648198045,"score_gpt":0.2595205583807838,"score_spread":0.23163871673258576,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389368173","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95551246,0.00022974418,0.00023425782,0.04283102,0.0003320037,0.00016080873,0.0000017959222,0.0000952402,0.00060266],"genre_scores_gemma":[0.97207713,0.000041848372,0.00017165464,0.026936457,0.00007376831,0.00004336111,0.000026921109,0.00002161824,0.00060725765],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99815196,0.00047333926,0.00030749984,0.00043678746,0.00024139673,0.0003889961],"domain_scores_gemma":[0.99917096,0.00039793874,0.00008993158,0.00020259123,0.000015115958,0.00012347069],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00053265743,0.00014186862,0.00042515591,0.00021736445,0.00013165885,0.0000090366575,0.00021867419,0.00009765722,0.001001603],"category_scores_gemma":[0.00040890058,0.00012624025,0.000055126988,0.00027752042,0.00017763728,0.000027201928,0.00016957465,0.0015340124,0.000016845217],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009886996,0.00022858189,0.974283,0.000019312372,0.000040844894,0.0068564266,0.00032984113,0.00028868177,0.0028940076,0.00037040623,0.007869493,0.005830739],"study_design_scores_gemma":[0.0015275944,0.005279522,0.90704423,0.0000083502855,0.000015451373,0.008744477,0.000027899003,0.045461684,3.509837e-7,0.00033940724,0.031417612,0.00013340122],"about_ca_topic_score_codex":0.000098794146,"about_ca_topic_score_gemma":0.0000037839034,"teacher_disagreement_score":0.06723872,"about_ca_system_score_codex":0.00003190057,"about_ca_system_score_gemma":0.000066756504,"threshold_uncertainty_score":0.9999116},"labels":[],"label_agreement":null},{"id":"W4389409310","doi":"10.1101/2023.12.04.569986","title":"Three-dimensional assessments are necessary to determine the true, spatially-resolved composition of tissues","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Cancer Institute; Rolfe Pancreatic Cancer Foundation","keywords":"Composition (language); Computer science; Art","score_opus":0.025805356762771698,"score_gpt":0.2925519639216907,"score_spread":0.266746607158919,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389409310","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97674066,0.0004681524,0.014131775,0.0055095917,0.0014882265,0.0011923655,0.00013278592,0.00032835113,0.000008082148],"genre_scores_gemma":[0.97979385,0.000058861864,0.01807568,0.0010559146,0.0007094867,0.00013362938,0.000003688516,0.0001557229,0.000013161289],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9970741,0.00012568715,0.00070946646,0.00077751715,0.0008628119,0.00045040945],"domain_scores_gemma":[0.99721223,0.00022863397,0.0005588918,0.0011627228,0.00048572384,0.00035179622],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008868299,0.00045884642,0.0008621673,0.0003127623,0.00017095504,0.000093089366,0.0005040832,0.00031143083,0.000057896727],"category_scores_gemma":[0.00042584594,0.00037057995,0.00020007075,0.00044987793,0.00017410888,0.00006239035,0.00067363295,0.0011642256,0.000052326348],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035158792,0.0005294575,0.09913219,0.0015616056,0.0007944258,0.00060788123,0.000026030513,0.0024887687,0.8882602,0.00016112629,0.005965868,0.00012086928],"study_design_scores_gemma":[0.0016483859,0.00030042237,0.86478,0.004682574,0.0006311301,2.652744e-7,0.000004515483,0.055679016,0.06883364,0.000013302488,0.0026666194,0.0007601096],"about_ca_topic_score_codex":0.0003486507,"about_ca_topic_score_gemma":0.000013667391,"teacher_disagreement_score":0.81942654,"about_ca_system_score_codex":0.0001641238,"about_ca_system_score_gemma":0.0004076275,"threshold_uncertainty_score":0.9998746},"labels":[],"label_agreement":null},{"id":"W4389446261","doi":"10.1212/wnl.96.15_supplement.4537","title":"Axonal and myelin volume fractions and imaging g-ratio in pediatric MS and MOG-associated disorders. (4537)","year":2021,"lang":"en","type":"article","venue":"Neurology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba; Montreal Neurological Institute and Hospital; Hospital for Sick Children","funders":"","keywords":"Multiple sclerosis; Myelin; Medicine; Myelin sheath; Neuroscience; Pathology; Internal medicine; Psychology; Central nervous system; Psychiatry","score_opus":0.0047076834518992,"score_gpt":0.24803207984063055,"score_spread":0.24332439638873135,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389446261","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95656353,0.001702126,0.0004038742,0.040629085,0.00014966447,0.00007596963,0.0000022564502,0.000026540147,0.0004469762],"genre_scores_gemma":[0.9931716,0.00194491,0.0002043955,0.004315436,0.0001388643,0.0000059467093,0.000016761043,0.000015013141,0.00018712152],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9991522,0.00010202749,0.00016731466,0.00029232254,0.00008658128,0.00019955926],"domain_scores_gemma":[0.999554,0.000181805,0.000046406207,0.00008090747,0.00002846272,0.00010842282],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016983155,0.00009309334,0.00020562898,0.000115955,0.000079163416,0.000030750132,0.000021081496,0.00007464634,0.000039899205],"category_scores_gemma":[0.00067171635,0.000094248455,0.000017398166,0.00014762682,0.00010931954,0.000077595614,0.000061292914,0.000598034,0.0000018111834],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029185949,0.000056737386,0.9903495,0.000022025954,0.000008678896,0.00016645399,0.00010717542,0.000014269479,0.00045930172,0.000092409144,0.0004213444,0.008272936],"study_design_scores_gemma":[0.0013274668,0.00010880562,0.9364633,0.000005583678,0.000053004722,0.0003446258,0.000015480126,0.055706725,0.0000021463302,0.00043529237,0.005465642,0.0000719572],"about_ca_topic_score_codex":0.00019001961,"about_ca_topic_score_gemma":0.00018582348,"teacher_disagreement_score":0.055692457,"about_ca_system_score_codex":0.000007650811,"about_ca_system_score_gemma":0.000050354123,"threshold_uncertainty_score":0.38433406},"labels":[],"label_agreement":null},{"id":"W4389460945","doi":"10.1212/wnl.94.15_supplement.876","title":"New/Enlarging T2 Lesion Identification: Semi-automated vs. Human (876)","year":2020,"lang":"en","type":"article","venue":"Neurology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Montreal Neurological Institute and Hospital","funders":"","keywords":"Identification (biology); Lesion; Medicine; Artificial intelligence; Pathology; Computer science; Biology; Botany","score_opus":0.021258233876146282,"score_gpt":0.31477039904648024,"score_spread":0.29351216517033396,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389460945","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8766022,0.00013419002,0.0038569085,0.11652559,0.00036196757,0.0001779056,8.219243e-7,0.0007671073,0.0015733412],"genre_scores_gemma":[0.9684365,0.00002595138,0.00040257993,0.030142562,0.0006532511,0.000003976065,0.000038517577,0.00003373429,0.00026295168],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988049,0.00008637373,0.0002914793,0.0003723141,0.00019355064,0.00025137892],"domain_scores_gemma":[0.99928594,0.000054300628,0.00009729993,0.00022492003,0.00003639358,0.00030116737],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014636248,0.0001246138,0.00026437818,0.000074097276,0.0001201096,0.000025326874,0.00014599532,0.0001111176,0.0003147036],"category_scores_gemma":[0.00029087014,0.00011771491,0.000065878245,0.00018986908,0.00006258365,0.000048780155,0.000068948095,0.00061645603,0.00019231293],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00080350594,0.00014958813,0.0857026,0.0002489116,0.00011688351,0.0015448343,0.0014356286,0.0010200557,0.63778204,0.002710732,0.23198165,0.03650359],"study_design_scores_gemma":[0.0046570436,0.0019359757,0.28670672,0.000047760237,0.00020192766,0.00078576116,0.00001887649,0.37752452,0.004751271,0.0004297512,0.3225677,0.00037268826],"about_ca_topic_score_codex":0.00005688038,"about_ca_topic_score_gemma":0.0000013337466,"teacher_disagreement_score":0.6330308,"about_ca_system_score_codex":0.000010121732,"about_ca_system_score_gemma":0.000052681047,"threshold_uncertainty_score":0.48002747},"labels":[],"label_agreement":null},{"id":"W4389466413","doi":"10.1212/wnl.90.15_supplement.p3.181","title":"MRI-derived markers of disease progression in early versus late PSP and CBS (P3.181)","year":2018,"lang":"en","type":"article","venue":"Neurology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Western Hospital; University of Toronto","funders":"","keywords":"Fagan inspection; Miller; Art; Medicine; Philosophy; Biology; Computer science","score_opus":0.009374327138503167,"score_gpt":0.29639948464882604,"score_spread":0.28702515751032287,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389466413","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9910413,0.00011438001,0.000041675037,0.0073613855,0.000329979,0.00015221306,9.364467e-7,0.000023347415,0.00093478983],"genre_scores_gemma":[0.99820095,0.000073853895,0.00047219804,0.0010815823,0.00011312412,0.000005601895,0.0000034660034,0.000014620639,0.000034580466],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99923384,0.000088744804,0.00015715456,0.00021713426,0.00011060883,0.0001925293],"domain_scores_gemma":[0.9995023,0.00009808465,0.000058927755,0.00015291016,0.000028231454,0.00015953362],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015603972,0.00008143401,0.00018909345,0.00009630319,0.00002755528,0.000004473829,0.000055407294,0.000062466344,0.000043142598],"category_scores_gemma":[0.00025817755,0.00006745089,0.000026117175,0.0000858239,0.00036602397,0.000027628845,0.000057015553,0.00028770312,0.000006795475],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.051141266,0.00020390927,0.865955,0.00014003858,0.000050832015,0.00058163673,0.00052620354,0.000012566318,0.015556975,0.00012700864,0.0007051771,0.06499937],"study_design_scores_gemma":[0.005078455,0.006133716,0.96957266,0.000063765365,0.000052344774,0.000017612718,0.0000042356664,0.014332455,0.00012251096,0.00014530045,0.0043943096,0.00008261286],"about_ca_topic_score_codex":0.000065908374,"about_ca_topic_score_gemma":0.00000850171,"teacher_disagreement_score":0.10361766,"about_ca_system_score_codex":0.000005107692,"about_ca_system_score_gemma":0.00003564082,"threshold_uncertainty_score":0.27505675},"labels":[],"label_agreement":null},{"id":"W4389633038","doi":"10.5114/pjr.2023.133330","title":"Correspondence to “Will ChatGPT pass the Polish specialty exam in radiology and diagnostic imaging?”","year":2023,"lang":"en","type":"article","venue":"Polish Journal of Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Specialty; Medicine; Radiology; Medical imaging; Medical physics; Pathology","score_opus":0.010231753350570737,"score_gpt":0.3013738248586221,"score_spread":0.2911420715080513,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389633038","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9266222,0.0027817078,0.0004483407,0.06741226,0.0018592005,0.0002421813,0.000006038403,0.00003051327,0.00059754564],"genre_scores_gemma":[0.9847399,0.002850939,0.00035010546,0.009136239,0.0025194979,0.000009306589,0.0000059870476,0.000033105654,0.00035492214],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99780285,0.000434807,0.0006383393,0.000261124,0.00024894404,0.00061396044],"domain_scores_gemma":[0.99642056,0.0025537533,0.00026059404,0.00024496156,0.00012208537,0.0003980405],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0021420573,0.00018982703,0.0006899525,0.0006654901,0.000094877054,0.000033205335,0.00035581508,0.00010709683,0.000099928504],"category_scores_gemma":[0.011530904,0.0001299847,0.00010408876,0.0005787539,0.00044316027,0.00012618396,0.00012740924,0.0010539095,0.000033561722],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044985773,0.000073897245,0.73723227,0.000044854994,0.0001033264,0.0038640779,0.0033164301,0.00044902586,0.0018903471,0.0018433082,0.21359059,0.03714203],"study_design_scores_gemma":[0.0020411324,0.00044480967,0.88823926,0.00018688045,0.00007788956,0.026469493,0.00046167176,0.0018188492,0.000027964432,0.0018483754,0.07821371,0.00016993185],"about_ca_topic_score_codex":0.00017059405,"about_ca_topic_score_gemma":0.000026234577,"teacher_disagreement_score":0.15100704,"about_ca_system_score_codex":0.00011681531,"about_ca_system_score_gemma":0.00019184376,"threshold_uncertainty_score":0.9967954},"labels":[],"label_agreement":null},{"id":"W4389666223","doi":"10.1109/nssmicrtsd49126.2023.10338394","title":"Region-of-Interest and Handcrafted vs. Deep Radiomics Feature Comparisons for Survival Outcome Prediction: Application to Lung PET/CT Imaging","year":2023,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Ottawa Regional Cancer Foundation; Canadian Centre for Applied Research in Cancer Control; BC Cancer Agency; Spinal Cord Injury BC; University of British Columbia; Virtual Materials Group (Canada)","funders":"","keywords":"Artificial intelligence; Deep learning; Radiomics; Computer science; Minimum bounding box; Regression; Lung cancer; Pattern recognition (psychology); Medicine; Statistics; Mathematics; Image (mathematics); Oncology","score_opus":0.03091323614844307,"score_gpt":0.33015785722080543,"score_spread":0.2992446210723624,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389666223","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30105287,0.00019265791,0.64836854,0.04721951,0.00066491804,0.0013658352,0.000022618227,0.0004267664,0.00068629644],"genre_scores_gemma":[0.98578745,0.000049703718,0.01133575,0.0009224955,0.00026481165,0.00008269319,0.00017386807,0.000042846306,0.0013403672],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988408,0.000027862228,0.0003439871,0.0003527897,0.00016003352,0.00027449362],"domain_scores_gemma":[0.99903405,0.00022828508,0.00009029213,0.00028153014,0.00011102492,0.0002548309],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043714483,0.00016171901,0.00042029197,0.00023353971,0.00012917198,0.00003682405,0.00010935876,0.000018089857,0.000007792185],"category_scores_gemma":[0.00036622974,0.00013929441,0.00009721424,0.00037011164,0.00008367745,0.00006108531,0.000070887116,0.00027517346,0.000005965521],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003197226,0.00007237358,0.88934714,0.00046453622,0.00012504257,0.0001205051,0.00019295355,0.00034401723,0.0020520133,0.0025964773,0.090310045,0.0140551645],"study_design_scores_gemma":[0.0022341632,0.000095287796,0.09909761,0.00012900402,0.00017134975,0.0007628013,0.0003249363,0.8587558,0.00016179556,0.00009617733,0.03799457,0.00017646872],"about_ca_topic_score_codex":0.0000812927,"about_ca_topic_score_gemma":0.000034417164,"teacher_disagreement_score":0.8584118,"about_ca_system_score_codex":0.000058817717,"about_ca_system_score_gemma":0.00003209345,"threshold_uncertainty_score":0.5680261},"labels":[],"label_agreement":null},{"id":"W4389666702","doi":"10.1109/nssmicrtsd49126.2023.10338080","title":"Towards an automated Segment Anything Model (SAM) for lesion segmentation in oncological PET/CT images","year":2023,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Generalizability theory; Lung cancer; Cancer; Artificial intelligence; Test set; Medicine; Melanoma; Segmentation; Convolutional neural network; Computer science; Nuclear medicine; Pattern recognition (psychology); Mathematics; Pathology; Internal medicine; Statistics; Cancer research","score_opus":0.0466330416631866,"score_gpt":0.40047668054719526,"score_spread":0.35384363888400866,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389666702","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.948181,0.000015330965,0.041611224,0.0064505558,0.00013792989,0.00065862254,0.000005236264,0.0010499229,0.001890224],"genre_scores_gemma":[0.8992955,0.00007978793,0.097700216,0.0014945271,0.000079182544,0.000084964435,0.000240551,0.00002793506,0.0009973049],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987564,0.000055827095,0.0002986938,0.00030884502,0.00027159852,0.0003086136],"domain_scores_gemma":[0.99952185,0.000089655325,0.00005301066,0.00013628571,0.000045493904,0.0001536978],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00092598627,0.00013089256,0.00025764626,0.00019698788,0.00009069671,0.00003825886,0.000078942576,0.000019876277,0.00004311359],"category_scores_gemma":[0.00029723914,0.000099418874,0.00006457328,0.00024152282,0.000038660484,0.00013834424,0.000049613103,0.00023038495,0.0000149231155],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006762069,0.001350533,0.014695387,0.0007530345,0.00011237328,0.0028323608,0.0020316942,0.18100925,0.3642806,0.0019054557,0.045158632,0.38519445],"study_design_scores_gemma":[0.0019946068,0.00028953352,0.00864947,0.00007523641,0.000027170005,0.00010154477,0.0005181787,0.9846342,0.0028577228,0.0005317911,0.00020255733,0.00011793845],"about_ca_topic_score_codex":0.00011697567,"about_ca_topic_score_gemma":0.0000069434377,"teacher_disagreement_score":0.803625,"about_ca_system_score_codex":0.00017352034,"about_ca_system_score_gemma":0.00010661481,"threshold_uncertainty_score":0.4054184},"labels":[],"label_agreement":null},{"id":"W4389778094","doi":"10.1002/mp.16893","title":"Predicting the need for a replan in oropharyngeal cancer: A radiomic, clinical, and dosimetric model","year":2023,"lang":"en","type":"article","venue":"Medical Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre for Imaging Technology Commercialization; Western University","funders":"London Health Sciences Foundation","keywords":"Medicine; Radiation treatment planning; Radiology; Cancer; Medical physics; Nuclear medicine; Radiation therapy; Internal medicine","score_opus":0.04179153048862863,"score_gpt":0.3769880672868399,"score_spread":0.33519653679821126,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389778094","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96159226,0.0005997398,0.010634407,0.025531996,0.00047634362,0.0006857353,0.000014749693,0.00014727794,0.0003174643],"genre_scores_gemma":[0.9915948,0.0016619153,0.00031790405,0.0045812414,0.0013947458,0.00011531698,0.000033781434,0.00004298046,0.00025732495],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981752,0.000069554786,0.00048500692,0.00036095103,0.00051645597,0.00039282543],"domain_scores_gemma":[0.9982027,0.0010786053,0.00009347796,0.00024762328,0.000039857274,0.00033773363],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020320127,0.00014193702,0.00047969472,0.00010572726,0.00012801925,0.000021529531,0.00018066139,0.00012966333,0.0000135572045],"category_scores_gemma":[0.0031288015,0.000095783544,0.000117553216,0.00073713437,0.00052977185,0.00004812228,0.00010855141,0.00089663715,0.0000051273496],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003487753,0.00025180777,0.5142898,0.00038241735,0.00016254254,0.00011838621,0.0012087252,0.0005947819,0.00018446193,0.0007189603,0.031055864,0.45068347],"study_design_scores_gemma":[0.0036312276,0.000109150904,0.024447357,0.00022308188,0.00009227516,0.000018058012,0.00007002403,0.9679562,0.000037302907,0.0023467683,0.0009597498,0.00010883315],"about_ca_topic_score_codex":0.00015983234,"about_ca_topic_score_gemma":0.0000064139485,"teacher_disagreement_score":0.9673614,"about_ca_system_score_codex":0.000036431793,"about_ca_system_score_gemma":0.00031095205,"threshold_uncertainty_score":0.39059395},"labels":[],"label_agreement":null},{"id":"W4389883609","doi":"10.32920/24625203","title":"Synthetic Data Generation Through Image Translation for Improving Out-of-domain MRI Lesion Segmentation","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Artificial intelligence; Synthetic data; Segmentation; Translation (biology); Scanner; Pattern recognition (psychology); Noise (video); Image segmentation; Image (mathematics); Computer vision","score_opus":0.14246712150319685,"score_gpt":0.4002906982812482,"score_spread":0.25782357677805134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389883609","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01046081,0.00016726734,0.9788579,0.0065039783,0.0015009665,0.0015960638,0.0001231084,0.00016410596,0.0006258425],"genre_scores_gemma":[0.083667174,0.00041101666,0.90072066,0.000309011,0.0011591148,0.00012330971,0.012848245,0.00012119907,0.00064026815],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99795747,0.00008102458,0.0006189715,0.0007506442,0.00038028488,0.00021163456],"domain_scores_gemma":[0.9984151,0.00018191268,0.00031827786,0.00088614365,0.00013174005,0.00006683119],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012492492,0.00022564281,0.00043126315,0.00012764194,0.000094706906,0.00006750891,0.00024570912,0.00020966915,0.000042450723],"category_scores_gemma":[0.00045555638,0.00019907265,0.00013276328,0.000073562755,0.00007033583,0.00020932652,0.00023582399,0.00044458042,0.000009887866],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016777363,0.00016904934,0.00014934423,0.004229155,0.00020877291,0.000013265894,0.002507702,0.0016266424,0.71745163,0.00043585507,0.011212407,0.2618284],"study_design_scores_gemma":[0.0014409998,0.000108264045,0.00010112133,0.0004121926,0.00045040497,0.000005372595,0.0002859575,0.9801365,0.012682545,0.0025733944,0.0015662395,0.00023701029],"about_ca_topic_score_codex":0.00022720054,"about_ca_topic_score_gemma":0.00003342394,"teacher_disagreement_score":0.97850984,"about_ca_system_score_codex":0.0000786272,"about_ca_system_score_gemma":0.00017582602,"threshold_uncertainty_score":0.8117947},"labels":[],"label_agreement":null},{"id":"W4389933919","doi":"10.1038/s41598-023-49478-3","title":"A priori prediction of breast cancer response to neoadjuvant chemotherapy using quantitative ultrasound, texture derivative and molecular subtype","year":2023,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University; Health Sciences Centre; Sunnybrook Health Science Centre","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto; Canadian Institutes of Health Research; Terry Fox Foundation","keywords":"Breast cancer; Margin (machine learning); Computer science; Texture (cosmology); Neoadjuvant therapy; Support vector machine; Ultrasound; Oncology; Cancer; Pattern recognition (psychology); Medicine; Artificial intelligence; Internal medicine; Radiology; Machine learning","score_opus":0.015626293022279605,"score_gpt":0.32178156430833765,"score_spread":0.3061552712860581,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389933919","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99326193,0.00016688349,0.0022928067,0.0026162614,0.0011489113,0.00039253462,0.000016408085,0.000063249754,0.000040986208],"genre_scores_gemma":[0.996017,0.000023908313,0.0031883314,0.00020955972,0.000042063126,0.000010815034,0.000023633229,0.000024704283,0.0004600131],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9984109,0.000075352815,0.00033715463,0.0004875495,0.00046080237,0.00022828515],"domain_scores_gemma":[0.9989522,0.00008192228,0.00020147786,0.00032552928,0.0002589455,0.00017991269],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016665519,0.00012042538,0.00025501597,0.00030221386,0.00014029777,0.000055363435,0.000044847468,0.00005500798,0.000038872346],"category_scores_gemma":[0.0009927107,0.00009981763,0.00005480307,0.0010254764,0.00026959355,0.00007421762,0.000034985722,0.00016822222,0.0000023397477],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037389525,0.000030744435,0.037438266,0.00004821983,0.000053898966,0.00033448645,0.0026422802,0.0003566934,0.9531019,0.000013677544,0.0013523593,0.004253585],"study_design_scores_gemma":[0.0013408373,0.0003212963,0.8924808,0.0010777167,0.00015906061,0.0030160828,0.0015118507,0.029201848,0.060897157,0.0010128147,0.008668984,0.00031154725],"about_ca_topic_score_codex":0.00017648682,"about_ca_topic_score_gemma":0.0000031389893,"teacher_disagreement_score":0.89220476,"about_ca_system_score_codex":0.000072050665,"about_ca_system_score_gemma":0.00027604366,"threshold_uncertainty_score":0.4070445},"labels":[],"label_agreement":null},{"id":"W4390056134","doi":"10.1177/08465371231217155","title":"A Visual Aid Tool for Detection of Pancreatic Tumour-Vessel Contact on Staging CT: A Retrospective Cohort Study","year":2023,"lang":"en","type":"article","venue":"Canadian Association of Radiologists Journal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"London Health Sciences Centre; St Joseph's Health Care; Western University","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Medicine; Receiver operating characteristic; Radiology; Adenocarcinoma; Pancreas; Superior mesenteric artery; Retrospective cohort study; Pathology; Cancer; Internal medicine","score_opus":0.010055031357781954,"score_gpt":0.29445818639652094,"score_spread":0.284403155038739,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390056134","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99640906,0.000023357003,0.0009786347,0.0011000017,0.0004228763,0.0007210915,0.000030909003,0.000030488192,0.0002835869],"genre_scores_gemma":[0.9989325,0.0000515634,0.00012136299,0.00018560201,0.00026860644,0.000026525604,0.000023227516,0.000023502254,0.00036710405],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9982766,0.0001986984,0.00052231364,0.00020407661,0.000424453,0.00037388914],"domain_scores_gemma":[0.998154,0.00041992,0.00068402546,0.000110732064,0.00037200813,0.00025934156],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031703173,0.00013398443,0.00060026074,0.00053614296,0.00019505284,0.00002844211,0.00009436298,0.00006955303,0.000019193274],"category_scores_gemma":[0.0071268445,0.00012136933,0.00016509573,0.00036350277,0.00003966198,0.00006420926,0.000007687576,0.0005337444,0.0000034089],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009788983,0.00006457828,0.9908705,0.000030816896,0.00042404357,0.00007780128,0.00031149748,0.00015371987,0.0037303057,0.000057024787,0.002311811,0.0018700217],"study_design_scores_gemma":[0.00256991,0.0013761589,0.9893354,0.000110315515,0.00021871337,0.0000782733,0.0004218146,0.004986086,0.0003070188,0.00016803807,0.00032308287,0.00010519109],"about_ca_topic_score_codex":0.0029978408,"about_ca_topic_score_gemma":0.0008711883,"teacher_disagreement_score":0.004832366,"about_ca_system_score_codex":0.0022256982,"about_ca_system_score_gemma":0.00052963814,"threshold_uncertainty_score":0.8532013},"labels":[],"label_agreement":null},{"id":"W4390081927","doi":"10.1055/a-2210-0635","title":"Establishing ground truth of polyp size, morphology, and volume using three-dimensional scanning","year":2023,"lang":"en","type":"article","venue":"Endoscopy","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier de l’Université de Montréal","funders":"Fujifilm Corporation","keywords":"Morphology (biology); Ground truth; Volume (thermodynamics); Cover (algebra); Medicine; Artificial intelligence; Computer science; Geology; Physics; Paleontology","score_opus":0.020343257744971893,"score_gpt":0.30617091200165186,"score_spread":0.28582765425668,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390081927","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9962409,0.00042248185,0.0012291381,0.001023393,0.0004889575,0.000114616254,0.000005177231,0.00010038521,0.00037492518],"genre_scores_gemma":[0.9778648,0.000017401242,0.021171965,0.00034917129,0.00023442511,0.0000029470004,0.000016810736,0.000035347617,0.0003071545],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9988194,0.000041126492,0.0002637553,0.0002747409,0.00027903222,0.00032190606],"domain_scores_gemma":[0.9990267,0.00047789613,0.0001063576,0.00018154622,0.000044632223,0.00016285923],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005522475,0.00013384304,0.00033943335,0.00017364633,0.0001231525,0.000029960227,0.00007939342,0.00007573338,0.00013834026],"category_scores_gemma":[0.0013968974,0.00012147459,0.00005733513,0.000352483,0.00022507303,0.00012177017,0.0001134221,0.00037979684,0.000010414764],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024527594,0.00009097957,0.68787616,0.00028359622,0.00018327375,0.00057071645,0.00064217456,0.001590082,0.29313272,0.0007761902,0.004093276,0.010515536],"study_design_scores_gemma":[0.0040684137,0.00030790918,0.49616107,0.0008043875,0.00023584614,0.00038533882,0.0003268513,0.49125567,0.003307409,0.0014610364,0.0013436687,0.00034240584],"about_ca_topic_score_codex":0.000763428,"about_ca_topic_score_gemma":0.0000026794025,"teacher_disagreement_score":0.48966557,"about_ca_system_score_codex":0.00003432625,"about_ca_system_score_gemma":0.000089452165,"threshold_uncertainty_score":0.495359},"labels":[],"label_agreement":null},{"id":"W4390200428","doi":"10.1002/alz.079258","title":"Amyloid‐Beta PET Synthesis from Structural MRI: A Potential Alternative Method for Alzheimer’s Disease Screening","year":2023,"lang":"en","type":"article","venue":"Alzheimer s & Dementia","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hotchkiss Brain Institute; University of Calgary","funders":"","keywords":"Positron emission tomography; Magnetic resonance imaging; Amyloid (mycology); Neuroimaging; Dementia; Nuclear medicine; BETA (programming language); Artificial intelligence; Amyloid beta; Medicine; Computer science; Pathology; Neuroscience; Psychology; Radiology; Disease","score_opus":0.03182966971460641,"score_gpt":0.3380252614551212,"score_spread":0.3061955917405148,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390200428","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17214796,0.07730848,0.696975,0.040257383,0.0050908155,0.004422347,0.0012183654,0.0016830587,0.0008965724],"genre_scores_gemma":[0.803879,0.000108889995,0.19272575,0.0012133569,0.0010660876,0.00019236696,0.00066933985,0.00011545261,0.00002975631],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971725,0.00018379795,0.0005177329,0.000793849,0.0006236857,0.000708432],"domain_scores_gemma":[0.99801856,0.00054419204,0.0002230606,0.0005124,0.0001300496,0.00057173247],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00062722916,0.00038404317,0.0005670892,0.0002499971,0.00035131292,0.00011556575,0.000360446,0.000068324676,0.00061408087],"category_scores_gemma":[0.00030074464,0.0003437017,0.00041614263,0.0002970937,0.00012907777,0.00019140165,0.00021847796,0.00039355445,0.00008975843],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018799261,0.00019514754,0.019866757,0.000060071954,0.09997546,0.0015997118,0.00091913925,0.006306891,0.0073744915,0.0014105922,0.041165408,0.8192464],"study_design_scores_gemma":[0.002969907,0.00012484597,0.05399827,0.00018257575,0.07983671,0.000050359606,0.00022692828,0.8381811,0.0063203243,0.0022593234,0.015146417,0.0007032607],"about_ca_topic_score_codex":0.0007503702,"about_ca_topic_score_gemma":0.0000075681323,"teacher_disagreement_score":0.8318742,"about_ca_system_score_codex":0.0000093741255,"about_ca_system_score_gemma":0.00009843451,"threshold_uncertainty_score":0.9999015},"labels":[],"label_agreement":null},{"id":"W4390396595","doi":"10.18280/ts.400622","title":"Temporal Stability and Prognostic Power of Radiomic Features for Survival Analysis in Lung Adenocarcinoma","year":2023,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Adenocarcinoma; Oncology; Stability (learning theory); Radiomics; Lung; Medicine; Internal medicine; Computer science; Radiology; Machine learning; Cancer","score_opus":0.01724738959500124,"score_gpt":0.2917574307422238,"score_spread":0.2745100411472226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390396595","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9955756,0.00031570744,0.0022172793,0.0010545859,0.000061409504,0.00062075583,0.000023919572,0.000041856216,0.00008888035],"genre_scores_gemma":[0.998819,0.000012117077,0.000817141,0.000069596805,0.000055640478,0.00003902377,0.000117970754,0.000015945418,0.000053580967],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.998727,0.00007373992,0.00036782946,0.00028913267,0.00028255867,0.0002597368],"domain_scores_gemma":[0.99929273,0.00031794494,0.00008460911,0.00013376285,0.000052238323,0.00011871799],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011198927,0.00012995179,0.0004694799,0.0003820861,0.000047225378,0.000011714228,0.00007116819,0.000052796728,0.00018538108],"category_scores_gemma":[0.00022596096,0.00010961474,0.00014445429,0.0006321283,0.00012906142,0.000041187483,0.000030742725,0.0001785288,6.536784e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024649716,0.00011580995,0.99420667,0.00026854037,0.00032284402,0.000035566307,0.0009969791,0.00009228147,0.0026682084,0.00011165668,0.00044344785,0.00049148983],"study_design_scores_gemma":[0.0020501397,0.00021990611,0.93690836,0.000044543896,0.00045429423,0.0000071230943,0.000294452,0.059553653,0.00025692803,0.00006905613,0.000046523837,0.00009502979],"about_ca_topic_score_codex":0.00013556445,"about_ca_topic_score_gemma":0.000028275497,"teacher_disagreement_score":0.05946137,"about_ca_system_score_codex":0.000044872486,"about_ca_system_score_gemma":0.00006716473,"threshold_uncertainty_score":0.44699594},"labels":[],"label_agreement":null},{"id":"W4390439998","doi":"10.1016/j.acra.2023.11.022","title":"Machine Learning and CT Texture Features in Ex-smokers with no CT Evidence of Emphysema and Mildly Abnormal Diffusing Capacity","year":2023,"lang":"en","type":"article","venue":"Academic Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Western University","funders":"","keywords":"DLCO; Medicine; Spirometry; Diffusing capacity; COPD; Lung volumes; Area under the curve; Radiology; Nuclear medicine; Cardiology; Internal medicine; Lung","score_opus":0.01596340947807221,"score_gpt":0.3004614929452962,"score_spread":0.284498083467224,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390439998","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9886494,0.0074913553,0.00004662797,0.0031932006,0.00009323512,0.00020609719,0.0000017811551,0.000064924,0.00025336436],"genre_scores_gemma":[0.98747694,0.010765769,0.0006114325,0.00063251227,0.00014883514,0.00000674559,0.000011484682,0.000027879238,0.00031839748],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9984569,0.00020782855,0.00032768914,0.0004054864,0.00018928434,0.00041280218],"domain_scores_gemma":[0.9988478,0.0006704889,0.00015483797,0.00013142513,0.00003114034,0.00016435237],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008735469,0.00021016596,0.0005834952,0.00047854884,0.000118617965,0.000006576034,0.0001080518,0.00013261496,0.0000118308435],"category_scores_gemma":[0.0014502698,0.00015610227,0.000036907542,0.00054442603,0.00057018193,0.000110171226,0.000115790695,0.0022143137,0.0000026321106],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025225012,0.000010481007,0.9666086,0.00030604948,0.000058825426,0.00032631966,0.0012153866,0.00019238229,0.021190204,0.00013711696,0.000539928,0.009162443],"study_design_scores_gemma":[0.0026724013,0.00062724267,0.95597446,0.0015142654,0.000117898955,0.0074145836,0.00032115958,0.025907626,0.0003863422,0.00018232652,0.0045789033,0.0003028149],"about_ca_topic_score_codex":0.0006734395,"about_ca_topic_score_gemma":0.000013896675,"teacher_disagreement_score":0.025715243,"about_ca_system_score_codex":0.00003301393,"about_ca_system_score_gemma":0.000042764346,"threshold_uncertainty_score":0.96202147},"labels":[],"label_agreement":null},{"id":"W4390450410","doi":"10.18280/ts.400639","title":"Bottleneck Feature-Based U-Net for Automated Detection and Segmentation of Gastrointestinal Tract Tumors from CT Scans","year":2023,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Bottleneck; Feature (linguistics); Gastrointestinal tract; Segmentation; Computer science; Artificial intelligence; Pattern recognition (psychology); Computer vision; Radiology; Medicine; Internal medicine; Embedded system","score_opus":0.012973057195105806,"score_gpt":0.281459589679546,"score_spread":0.26848653248444015,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390450410","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9371468,0.00002268213,0.060831722,0.0011554299,0.00005953652,0.00044304217,0.000056530123,0.00025286284,0.000031417014],"genre_scores_gemma":[0.98674905,0.0000031362722,0.012451586,0.0002393822,0.0001249717,0.000040464663,0.00033661147,0.000021985465,0.00003278527],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99909675,0.00003587835,0.00023696976,0.00020537128,0.00023533957,0.00018970831],"domain_scores_gemma":[0.9994692,0.00018742708,0.00011611828,0.00006980279,0.000050792383,0.0001066423],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031475266,0.00012013366,0.00021124238,0.00013928075,0.00006892305,0.000019146248,0.000039792074,0.00001888532,0.00006157347],"category_scores_gemma":[0.00010649394,0.000107152795,0.00006124148,0.00017073003,0.00005966479,0.000046331315,0.000007705481,0.00013447781,0.0000023327282],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007233755,0.0002787087,0.07968519,0.0003979573,0.00008190541,0.00009596196,0.00026255168,0.0067257243,0.85791177,0.000022270075,0.004094988,0.049719602],"study_design_scores_gemma":[0.0032958298,0.0006665184,0.23581359,0.00028748583,0.000113601236,0.000059815226,0.00011065251,0.73991287,0.019410158,0.000040548042,0.00020098522,0.00008795381],"about_ca_topic_score_codex":0.00011255233,"about_ca_topic_score_gemma":0.0000060321013,"teacher_disagreement_score":0.83850163,"about_ca_system_score_codex":0.000043181637,"about_ca_system_score_gemma":0.000058042326,"threshold_uncertainty_score":0.43695644},"labels":[],"label_agreement":null},{"id":"W4390484879","doi":"10.7150/thno.90246","title":"Deep learning for automatic organ and tumor segmentation in nanomedicine pharmacokinetics","year":2024,"lang":"en","type":"article","venue":"Theranostics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; Princess Margaret Cancer Centre; University of Toronto; Canada Research Chairs; University Health Network","funders":"Canadian Institutes of Health Research; Canada Research Chairs; Prostate Cancer Canada; Princess Margaret Cancer Foundation","keywords":"Segmentation; Computer science; Artificial intelligence; Deep learning; Nanomedicine; Medical imaging; Pharmacokinetics; Dosimetry; Medical physics; Pattern recognition (psychology); Medicine; Nuclear medicine; Pharmacology; Materials science; Nanoparticle; Nanotechnology","score_opus":0.009163927886860414,"score_gpt":0.3097853133810424,"score_spread":0.300621385494182,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390484879","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91192853,0.0047517824,0.07793489,0.0037134856,0.00045367162,0.0005800549,9.653112e-7,0.00047827864,0.00015832542],"genre_scores_gemma":[0.98762375,0.0004653217,0.010328678,0.0009524543,0.00027496347,0.000019834992,0.000024196146,0.000086479144,0.00022432071],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992552,0.0000313724,0.00022095427,0.00017075845,0.00013958424,0.00018213816],"domain_scores_gemma":[0.9994226,0.0003685224,0.000029323197,0.00006303631,0.000027492113,0.00008900674],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032366134,0.00010960443,0.00019806268,0.0001417035,0.000029744482,0.000033387027,0.000034565994,0.000031253458,0.00003572381],"category_scores_gemma":[0.00040401806,0.00008940778,0.000026110161,0.00016769467,0.000065660715,0.000034577173,0.000014088873,0.00030520547,0.000002724815],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013545244,0.00012803797,0.022652222,0.0027510456,0.00017326415,0.00037476336,0.007623123,0.0017267918,0.20532146,0.00089728786,0.0006956225,0.7575209],"study_design_scores_gemma":[0.0019792803,0.00025853617,0.004584693,0.0005089727,0.00016381903,0.00012584725,0.0002923445,0.9841452,0.0011645206,0.00029996852,0.0063705426,0.00010625665],"about_ca_topic_score_codex":0.00000937784,"about_ca_topic_score_gemma":0.0000011511162,"teacher_disagreement_score":0.9824184,"about_ca_system_score_codex":0.000047542446,"about_ca_system_score_gemma":0.000038206443,"threshold_uncertainty_score":0.36459434},"labels":[],"label_agreement":null},{"id":"W4390590169","doi":"10.1016/j.eswa.2023.123131","title":"APDF: An active preference-based deep forest expert system for overall survival prediction in gastric cancer","year":2024,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Fundamental Research Funds for the Central Universities; National Natural Science Foundation of China","keywords":"Computer science; Machine learning; Artificial intelligence; Estimator; Credibility; Feature selection; Relevance (law); Curse of dimensionality; Data mining; Statistics; Mathematics","score_opus":0.028539155342008283,"score_gpt":0.31223180197785383,"score_spread":0.28369264663584554,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390590169","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04251339,0.004954581,0.9425045,0.0015296586,0.0008791252,0.005166812,0.0001370152,0.0006672807,0.0016475919],"genre_scores_gemma":[0.97867376,0.00006168616,0.0028643422,0.00012369805,0.00120206,0.0163262,0.00035905666,0.000071731105,0.0003174721],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983619,0.00006739152,0.00037228945,0.00054572866,0.0003305544,0.0003221449],"domain_scores_gemma":[0.9990048,0.00016545133,0.00008633992,0.0003809086,0.00013210815,0.00023042805],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025926257,0.00021481472,0.000356478,0.00024906165,0.0001358653,0.00009603219,0.00013610416,0.00011230461,0.000014290841],"category_scores_gemma":[0.000026009493,0.00016236163,0.0000650086,0.0003811546,0.00005898861,0.00015251093,0.000012193231,0.00027722394,0.00000900976],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0066087935,0.0049367878,0.18103872,0.021334363,0.0027733217,0.00029569402,0.031232778,0.16233568,0.100358255,0.09374283,0.031474438,0.36386833],"study_design_scores_gemma":[0.0023228081,0.00035260653,0.004567878,0.0019530766,0.00007351648,0.00008158826,0.0019050437,0.9216507,0.00027223778,0.000022532944,0.06652899,0.00026899288],"about_ca_topic_score_codex":0.001633292,"about_ca_topic_score_gemma":0.00016465416,"teacher_disagreement_score":0.9396402,"about_ca_system_score_codex":0.00055051374,"about_ca_system_score_gemma":0.00031568692,"threshold_uncertainty_score":0.6620915},"labels":[],"label_agreement":null},{"id":"W4390701962","doi":"10.1186/s12967-024-04854-z","title":"Multi-institutional prognostic modeling of survival outcomes in NSCLC patients treated with first-line immunotherapy using radiomics","year":2024,"lang":"en","type":"article","venue":"Journal of Translational Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre hospitalier de l'Université Laval; Centre Hospitalier de l’Université de Montréal; Université du Québec à Trois-Rivières; Université Laval","funders":"Fonds de Recherche du Québec - Santé; Institut universitaire de cardiologie et de pneumologie de Québec, Université Laval","keywords":"Feature selection; Artificial intelligence; Machine learning; Medicine; Oncology; Radiomics; Computer science; Feature (linguistics); Internal medicine","score_opus":0.03400291794991634,"score_gpt":0.3234476935512806,"score_spread":0.2894447756013643,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390701962","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83762324,0.0021117665,0.15578423,0.003829413,0.00034628398,0.0002275427,0.000008394713,0.00001255788,0.00005658849],"genre_scores_gemma":[0.9807641,0.00025744684,0.018549642,0.00009835003,0.00024983406,0.000001706452,0.000033876502,0.000028366569,0.00001667557],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979137,0.000046970505,0.00093600847,0.0001531139,0.0007801962,0.0001699831],"domain_scores_gemma":[0.99889165,0.00039433117,0.00018807994,0.000083931955,0.000323147,0.00011885826],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006535333,0.00018994209,0.0007000373,0.00057193317,0.000048021477,0.000009436894,0.00009219066,0.00006956086,0.000045171313],"category_scores_gemma":[0.00035862334,0.00011162882,0.00013573052,0.00037260476,0.00017600956,0.00016038312,0.000004576911,0.00050337287,4.0754026e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010862835,0.0005711981,0.78262633,0.0003520561,0.0005341067,0.00023647472,0.0008242936,0.20546697,0.0021359457,0.00016015385,0.000008727598,0.005997493],"study_design_scores_gemma":[0.01112672,0.0006740695,0.15734376,0.004083952,0.0002840731,0.0002646781,0.000034282188,0.8258503,0.000024226652,0.00009480446,0.000107165084,0.0001119539],"about_ca_topic_score_codex":0.00008733786,"about_ca_topic_score_gemma":0.000014946783,"teacher_disagreement_score":0.6252825,"about_ca_system_score_codex":0.00010324354,"about_ca_system_score_gemma":0.00039122533,"threshold_uncertainty_score":0.4552091},"labels":[],"label_agreement":null},{"id":"W4390740209","doi":"10.3390/curroncol31010027","title":"An Informative Review of Radiomics Studies on Cancer Imaging: The Main Findings, Challenges and Limitations of the Methodologies","year":2024,"lang":"en","type":"review","venue":"Current Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Cancer Institute","keywords":"Medicine; Radiomics; Medical physics; Workflow; Standardization; Data science; Computer science; Radiology; Database","score_opus":0.5138827474450695,"score_gpt":0.570925307467731,"score_spread":0.057042560022661504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390740209","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00002310414,0.9889429,0.000014829183,0.007894246,0.0016922298,0.0008817523,0.00003084572,0.00001631527,0.0005037718],"genre_scores_gemma":[0.000016598355,0.9987972,0.0004530471,0.00037510323,0.00015899446,0.00013808813,0.000017001632,0.000021855774,0.000022148897],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99770206,0.000904111,0.0007949206,0.00023361976,0.00019976789,0.00016549439],"domain_scores_gemma":[0.9951531,0.0036562704,0.00063396763,0.00036780804,0.00013764751,0.000051158295],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022346997,0.00026298666,0.0018683709,0.00014870665,0.00006041661,0.0000057513685,0.00030056486,0.00009236374,0.0000032378264],"category_scores_gemma":[0.0059646848,0.0001138155,0.0003059034,0.00022041488,0.00080643984,0.00003461684,0.00018459783,0.0011068464,0.0000015732734],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004221052,0.000036978694,0.0000041383,0.11552552,0.000331342,0.0000019140077,0.002602783,0.0000012301633,2.875985e-7,0.002685245,0.0030236733,0.87578267],"study_design_scores_gemma":[0.00013565969,0.00015193062,0.0000319259,0.13683434,0.003396047,0.000059760016,0.0011569011,0.00010065835,9.0151974e-7,0.00034612828,0.857698,0.00008775419],"about_ca_topic_score_codex":0.0000019432025,"about_ca_topic_score_gemma":0.0000034804152,"teacher_disagreement_score":0.87569493,"about_ca_system_score_codex":0.00019272201,"about_ca_system_score_gemma":0.00054444314,"threshold_uncertainty_score":0.7140716},"labels":[],"label_agreement":null},{"id":"W4390745309","doi":"10.3389/frai.2023.1291136","title":"Artificial intelligence in biology and medicine, and radioprotection research: perspectives from Jerusalem","year":2024,"lang":"en","type":"article","venue":"Frontiers in Artificial Intelligence","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Ministère de l'Enseignement supérieur, de la Recherche et de l'Innovation","keywords":"Artificial intelligence; Data science; Engineering ethics; Computer science; Medicine; Engineering","score_opus":0.08498273556094818,"score_gpt":0.4231167017570224,"score_spread":0.33813396619607416,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390745309","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43974707,0.042003334,0.49079144,0.02221871,0.0026990103,0.0009969792,0.0000108315935,0.00016370477,0.0013689327],"genre_scores_gemma":[0.9825343,0.0039340197,0.012515148,0.00011889209,0.0007515163,0.000042194595,0.000010806721,0.000032539654,0.00006059261],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9973794,0.00030479953,0.00066256226,0.0008550126,0.000304267,0.0004939168],"domain_scores_gemma":[0.9988814,0.0005658533,0.00004597862,0.00023252013,0.000078598765,0.00019565964],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002216683,0.00021901348,0.00047493307,0.0012383293,0.00013298276,0.000094662944,0.00015127519,0.00020846703,0.00010741597],"category_scores_gemma":[0.0021438967,0.0001921785,0.00004260603,0.0011222236,0.001635081,0.00014951281,0.00009472468,0.0015704457,0.00001706284],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002750424,0.00009208058,0.0055966824,0.00009114586,0.000038995997,0.0002184186,0.012986642,0.00006659589,0.005491786,0.065045364,0.000469498,0.90962774],"study_design_scores_gemma":[0.000053722724,0.0004302213,0.0018001557,0.0010288085,0.000031470372,0.00005488202,0.02375234,0.3272504,0.003002237,0.63985217,0.0024781972,0.0002654017],"about_ca_topic_score_codex":0.0022217138,"about_ca_topic_score_gemma":0.00026044145,"teacher_disagreement_score":0.9093624,"about_ca_system_score_codex":0.00023725769,"about_ca_system_score_gemma":0.000099570105,"threshold_uncertainty_score":0.78368115},"labels":[],"label_agreement":null},{"id":"W4390866104","doi":"","title":"The Image Biomarker Standardization Initiative: Standardized convolutional filters for quantitative radiomics Authors and affiliations","year":2023,"lang":"en","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Centre For Medical Engineering, King’s College London; Engineering and Physical Sciences Research Council; Natural Sciences and Engineering Research Council of Canada; National Cancer Institute; National Science Foundation; Cancer Research UK; Canadian Institute for Advanced Research; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; King's College London","keywords":"Radiomics; Standardization; Biomarker; Computer science; Medical physics; Artificial intelligence; Medicine; Biology","score_opus":0.03283905751194652,"score_gpt":0.3198527801391205,"score_spread":0.28701372262717395,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390866104","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018311901,0.00095421576,0.90874594,0.067279786,0.0004706184,0.0011435052,0.0007376331,0.00021850367,0.0021379052],"genre_scores_gemma":[0.3099851,0.0066381036,0.66218144,0.000567776,0.00013320937,0.0007143134,0.0073003503,0.0002730595,0.012206612],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9958124,0.0022133158,0.00055924134,0.0005944938,0.0004909187,0.0003296399],"domain_scores_gemma":[0.99017036,0.005701532,0.0004897929,0.0007568508,0.0026667705,0.0002147041],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008539836,0.00027405607,0.0004259601,0.00020697285,0.00090764416,0.00041926847,0.00032881295,0.000206087,0.000023351367],"category_scores_gemma":[0.014884104,0.00023457766,0.00021631763,0.0003035815,0.00076425343,0.00010019626,0.00043984596,0.00067193055,0.0000050882036],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015312489,0.00088305684,0.008272542,0.0021779018,0.0032368528,0.00003736641,0.04025561,0.001103764,0.016715059,0.68549234,0.11456694,0.12572731],"study_design_scores_gemma":[0.0054441406,0.000005816857,0.022705315,0.0035739408,0.0005586503,0.000032615648,0.001509396,0.84646773,0.0040347236,0.027754813,0.087132536,0.00078034954],"about_ca_topic_score_codex":0.00011905245,"about_ca_topic_score_gemma":0.00012775925,"teacher_disagreement_score":0.8453639,"about_ca_system_score_codex":0.00022600267,"about_ca_system_score_gemma":0.0006870424,"threshold_uncertainty_score":0.9934139},"labels":[],"label_agreement":null},{"id":"W4390885336","doi":"10.3390/cancers16020348","title":"The Cross-Scale Association between Pathomics and Radiomics Features in Immunotherapy-Treated NSCLC Patients: A Preliminary Study","year":2024,"lang":"en","type":"article","venue":"Cancers","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier de l’Université de Montréal; Université Laval; Montreal Heart Institute; Université du Québec à Trois-Rivières","funders":"Institut universitaire de cardiologie et de pneumologie de Québec, Université Laval; U.S. Department of Veterans Affairs","keywords":"Radiomics; Medicine; Immunotherapy; Internal medicine; Oncology; Association (psychology); Cancer; Radiology; Psychology","score_opus":0.005775328754237411,"score_gpt":0.2938120156038869,"score_spread":0.2880366868496495,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390885336","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99365807,0.004168291,0.00003177807,0.00085987244,0.00037795547,0.0005143457,0.000012185824,0.00005810458,0.00031943008],"genre_scores_gemma":[0.99779373,0.000766072,0.00006589587,0.0002135375,0.00019864867,0.000038686074,0.000028964274,0.00003157997,0.00086287933],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99899966,0.00007557144,0.00023395952,0.00024270789,0.00021630994,0.00023178784],"domain_scores_gemma":[0.9993607,0.00030752277,0.00006201382,0.00015348136,0.000046233454,0.00007006035],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00058411766,0.00012278045,0.00021173587,0.00007918444,0.00013706312,0.0001530496,0.000081329235,0.00008383845,0.0000043303544],"category_scores_gemma":[0.0002064222,0.00008602056,0.00004765715,0.00021673247,0.000078507655,0.000072371586,0.000029044677,0.00051021227,0.0000019446989],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016502911,0.00002349896,0.9083468,0.000028554121,0.00013682716,0.000017415356,0.0021699925,0.000059518567,0.00006843126,0.000007391668,0.0010865803,0.08789001],"study_design_scores_gemma":[0.0020767218,0.0003747766,0.98761445,0.00015049957,0.00008678318,0.0000038523776,0.00037919337,0.0039363215,0.000031354044,0.000055592456,0.005188912,0.00010152569],"about_ca_topic_score_codex":0.00042117856,"about_ca_topic_score_gemma":0.000036126985,"teacher_disagreement_score":0.08778848,"about_ca_system_score_codex":0.001463373,"about_ca_system_score_gemma":0.00017460088,"threshold_uncertainty_score":0.38266695},"labels":[],"label_agreement":null},{"id":"W4390885406","doi":"10.3390/diagnostics14020181","title":"Radiomics and Artificial Intelligence in Radiotheranostics: A Review of Applications for Radioligands Targeting Somatostatin Receptors and Prostate-Specific Membrane Antigens","year":2024,"lang":"en","type":"review","venue":"Diagnostics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":54,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Iran National Science Foundation; Iran University of Medical Sciences; National Science Foundation","keywords":"Radiomics; Prostate cancer; Glutamate carboxypeptidase II; Somatostatin receptor; Medicine; Neuroendocrine tumors; Radionuclide therapy; Workflow; Artificial intelligence; Computer science; Somatostatin; Cancer; Nuclear medicine; Internal medicine; Database","score_opus":0.027039884717652892,"score_gpt":0.35539047204117774,"score_spread":0.32835058732352485,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390885406","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000027106691,0.9858546,0.009061739,0.00048616598,0.00030439478,0.0039981217,0.00019270593,0.00004333488,0.000031797204],"genre_scores_gemma":[0.000011811423,0.9805672,0.01766564,0.00019171403,0.00036817233,0.00047915094,0.0005612291,0.00012886846,0.000026203574],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99718654,0.000099674806,0.0014954837,0.00062377925,0.00022763108,0.00036686804],"domain_scores_gemma":[0.9965535,0.0023972313,0.00042019453,0.00030307143,0.00011737287,0.00020863663],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010735693,0.0004569606,0.0022425926,0.00038262535,0.000071453214,0.000054356708,0.00014711313,0.00023692929,0.000013020774],"category_scores_gemma":[0.0028132352,0.00037541304,0.00023596235,0.0005758705,0.00032323904,0.000036103433,0.00006953202,0.0007337173,0.0000044897656],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010470143,0.00006745339,0.00003493566,0.22588316,0.00010463295,0.00002700737,0.0002469409,0.0000017004883,0.000008767601,0.0020310055,0.0019370823,0.7696468],"study_design_scores_gemma":[0.00017755941,0.00011004241,0.000001585667,0.14341792,0.0013481699,0.00014846958,0.000065407345,0.0013829559,0.000022043263,0.0004714503,0.8525186,0.0003358005],"about_ca_topic_score_codex":0.000006437977,"about_ca_topic_score_gemma":7.6551987e-7,"teacher_disagreement_score":0.8505815,"about_ca_system_score_codex":0.00009050788,"about_ca_system_score_gemma":0.0002771581,"threshold_uncertainty_score":0.99986976},"labels":[],"label_agreement":null},{"id":"W4390915338","doi":"10.1158/1538-7445.panca2023-b073","title":"Abstract B073: Understanding treatment response in pancreatic cancer: NetraAI provides genetic differentiation in FOLFIRINOX and gemcitabine response","year":2024,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"FOLFIRINOX; Gemcitabine; Pancreatic cancer; Oncology; Internal medicine; Chemotherapy; Cancer; Biology; Medicine; Cancer research; Bioinformatics; Irinotecan","score_opus":0.0855619075787892,"score_gpt":0.4223365486978676,"score_spread":0.3367746411190784,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390915338","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97081727,0.016844155,0.00013451905,0.0112074055,0.00013307398,0.0007268313,0.000008724836,0.000043141452,0.000084899526],"genre_scores_gemma":[0.9925249,0.006083083,0.00008274302,0.00007283835,0.00013873493,0.0003620971,0.0000058061646,0.0000437825,0.0006860095],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9976955,0.00048756468,0.000323995,0.00048184674,0.00046970023,0.00054138154],"domain_scores_gemma":[0.9981716,0.001349642,0.000027230848,0.0002103627,0.000040156832,0.00020095852],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020872878,0.00016743346,0.000312835,0.0009192661,0.00009169788,0.00013579486,0.00008188485,0.00008969498,0.0001595021],"category_scores_gemma":[0.00062460086,0.00013469516,0.000044124332,0.00070727436,0.00018140207,0.00009566197,0.000045845143,0.00069923996,0.000005944931],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.037395444,0.00036178177,0.5127358,0.0018658254,0.00027213243,0.0026517364,0.0069916015,0.0008984637,0.31484073,0.0004754523,0.0007182125,0.12079287],"study_design_scores_gemma":[0.0024658705,0.00070431747,0.97158265,0.0023430423,0.000047055182,0.000022694781,0.00049993343,0.019102037,0.000618412,0.00083045266,0.0016307996,0.00015272108],"about_ca_topic_score_codex":0.0034112476,"about_ca_topic_score_gemma":0.00073802844,"teacher_disagreement_score":0.4588469,"about_ca_system_score_codex":0.0027837998,"about_ca_system_score_gemma":0.00085612986,"threshold_uncertainty_score":0.727954},"labels":[],"label_agreement":null},{"id":"W4390928581","doi":"10.1186/s13244-023-01572-w","title":"METhodological RadiomICs Score (METRICS): a quality scoring tool for radiomics research endorsed by EuSoMII","year":2024,"lang":"en","type":"article","venue":"Insights into Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":269,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier Universitaire de Sherbrooke; Université de Sherbrooke; University of Toronto; University Health Network","funders":"National Cancer Institute; National Institutes of Health","keywords":"Radiomics; Medicine; Neuroradiology; Medical physics; Quality Score; Quality (philosophy); Interventional radiology; Radiology; Neurology; Operations management; Engineering; Metric (unit)","score_opus":0.20445325374953044,"score_gpt":0.4761892435788327,"score_spread":0.27173598982930225,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390928581","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.51143944,0.02354412,0.44679618,0.010651785,0.0024424102,0.0016649527,0.000018554141,0.0007354398,0.0027070919],"genre_scores_gemma":[0.87371653,0.00097147614,0.12016577,0.0017797732,0.0016950283,0.00018862275,0.00012665107,0.00017715424,0.0011789579],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9947859,0.0008363351,0.0010228208,0.001240433,0.0010605655,0.0010539263],"domain_scores_gemma":[0.99196666,0.006336384,0.00012943507,0.00070290646,0.0004022237,0.00046240282],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.008619542,0.0004328747,0.0009479658,0.001246203,0.0005768002,0.0005651902,0.0005079747,0.00021538776,0.000059950657],"category_scores_gemma":[0.011815546,0.00034796257,0.00042886278,0.0016076626,0.00063681975,0.00040696753,0.00026454873,0.0021808434,0.000041990523],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007037583,0.0003415963,0.011196206,0.0022940792,0.0004813357,0.00080970535,0.004351325,0.00009292826,0.31940296,0.034623142,0.04868111,0.57702184],"study_design_scores_gemma":[0.0046082456,0.00037765058,0.0013063969,0.0015703404,0.0003081421,0.00057869626,0.00068225426,0.3729048,0.028585583,0.03238804,0.55558443,0.0011053786],"about_ca_topic_score_codex":0.00030136076,"about_ca_topic_score_gemma":0.000002637358,"teacher_disagreement_score":0.57591647,"about_ca_system_score_codex":0.0008029742,"about_ca_system_score_gemma":0.0004506043,"threshold_uncertainty_score":0.99989724},"labels":[],"label_agreement":null},{"id":"W4390977337","doi":"10.1136/bmjonc-2023-000134","title":"Artificial intelligence across oncology specialties: current applications and emerging tools","year":2024,"lang":"en","type":"review","venue":"BMJ Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Cancer Institute; Innovate UK; Cancer Institute NSW; National Institute for Health and Care Research; NIHR Leicester Biomedical Research Centre; Kuni Foundation; Association of Breast Surgery","keywords":"Current (fluid); Medical physics; Medicine; Data science; Computer science; Engineering; Electrical engineering","score_opus":0.15782026867385004,"score_gpt":0.545501874537262,"score_spread":0.38768160586341194,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390977337","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000050546964,0.9814973,0.0060644606,0.002728269,0.0022520078,0.0023905837,0.00004235293,0.00012696376,0.004893042],"genre_scores_gemma":[0.000009083115,0.9907133,0.002073785,0.00029634096,0.0049408698,0.0012143523,0.00016694749,0.00007884916,0.00050644844],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99689233,0.00025339864,0.0012830774,0.00077329343,0.00023413515,0.000563751],"domain_scores_gemma":[0.99792504,0.0008407054,0.00042360902,0.00041664398,0.00007807378,0.00031590456],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0013239724,0.00042661527,0.002334919,0.00025212317,0.00017831649,0.00008290672,0.0002599073,0.00054722175,0.000157622],"category_scores_gemma":[0.00070410746,0.00033309983,0.00037337808,0.00041309773,0.000512735,0.00003590399,0.00037152262,0.0023136323,0.00052570546],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013733665,0.0001429953,0.0000017544198,0.010638197,0.00014674563,0.00022864202,0.00039956608,7.4339766e-7,5.635458e-7,0.004610319,0.0044951816,0.97932154],"study_design_scores_gemma":[0.0000713572,0.00027681646,0.0000013684943,0.0044294423,0.0014969059,0.001536033,0.00022751739,0.000295691,2.948904e-7,0.0013014721,0.9900818,0.00028133826],"about_ca_topic_score_codex":0.000016062279,"about_ca_topic_score_gemma":0.000023784743,"teacher_disagreement_score":0.9855866,"about_ca_system_score_codex":0.00067883614,"about_ca_system_score_gemma":0.0016170655,"threshold_uncertainty_score":0.9999881},"labels":[],"label_agreement":null},{"id":"W4391065113","doi":"10.1016/b978-0-12-822000-9.00009-4","title":"Radiomics: “unlocking the potential of medical images for precision radiation oncology”","year":2024,"lang":"en","type":"book-chapter","venue":"Elsevier eBooks","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Radiomics; Medical physics; Standardization; Medical imaging; Precision medicine; Pipeline (software); Radiation oncology; Medicine; Computer science; Data science; Artificial intelligence; Radiation therapy; Radiology; Pathology","score_opus":0.011943615614127365,"score_gpt":0.3176675471720686,"score_spread":0.3057239315579412,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391065113","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00020191721,0.012159355,0.0015157983,0.011952777,0.0025284537,0.0017127568,0.000050462724,0.000101838086,0.96977663],"genre_scores_gemma":[0.004733007,0.0024708614,0.002008071,0.0014211833,0.0035249114,0.000073752104,0.00013609689,0.00019370596,0.9854384],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99736065,0.000042575375,0.0008045703,0.00047551453,0.0010277064,0.00028896204],"domain_scores_gemma":[0.9983087,0.0004946156,0.00037653153,0.00045933298,0.00014213035,0.00021865439],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019425653,0.00033927357,0.00084223057,0.00024363441,0.00012217849,0.000045879227,0.00039042678,0.0006521426,0.00024354218],"category_scores_gemma":[0.00050185056,0.0002242504,0.00056609564,0.000021230242,0.000410337,0.000023965591,0.00017463537,0.0015025876,0.000030923755],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000110685054,0.000015442198,0.0000029784997,0.0004622057,0.0003408739,0.00010332778,0.00019661813,0.0000071047025,0.0002923732,0.005914906,0.004008329,0.9885452],"study_design_scores_gemma":[0.0012033557,0.0002724744,0.00001553805,0.001957081,0.0010091142,0.00034522652,0.000022055723,0.007976213,0.00012226519,0.015322175,0.9715521,0.00020242686],"about_ca_topic_score_codex":0.00000190937,"about_ca_topic_score_gemma":0.0000012341096,"teacher_disagreement_score":0.9883427,"about_ca_system_score_codex":0.00018504442,"about_ca_system_score_gemma":0.0005908418,"threshold_uncertainty_score":0.91446656},"labels":[],"label_agreement":null},{"id":"W4391095388","doi":"10.1200/jco.2024.42.3_suppl.162","title":"Development of an improved risk stratification scheme for stage II and III colorectal cancers through incorporation of the digital pathology biomarker QuantCRC.","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mount Sinai Hospital; University of Toronto","funders":"","keywords":"Medicine; Hazard ratio; Internal medicine; Risk stratification; Oncology; Stage (stratigraphy); Biomarker; Cohort; Colorectal cancer; Log-rank test; Proportional hazards model; Cancer; Confidence interval","score_opus":0.07902622233437456,"score_gpt":0.44862327910188066,"score_spread":0.3695970567675061,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391095388","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9877205,0.00023546131,0.009058827,0.0017368371,0.0007828632,0.00025896463,0.000013640862,0.000005597918,0.00018730719],"genre_scores_gemma":[0.95410556,0.0001465244,0.045374155,0.00012354294,0.00018347244,0.0000050428403,0.000009816003,0.000010348005,0.000041530922],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9977396,0.00015048865,0.0016711712,0.00015419045,0.00017803215,0.00010649672],"domain_scores_gemma":[0.99722517,0.00083238655,0.0015093754,0.0001012723,0.00023241999,0.00009938368],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029424173,0.00008437419,0.0006174089,0.000058427442,0.00006501065,0.000010700623,0.00009889154,0.00019297255,0.000008893656],"category_scores_gemma":[0.0027600052,0.000050870563,0.00016125596,0.00010630145,0.0003693747,0.0001701138,0.000042968633,0.0005379883,1.2879497e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0039031564,0.0007939622,0.026261674,0.00025236214,0.00059944915,0.00003877207,0.0021790778,0.000037971633,0.076863274,0.0016227219,0.00029848036,0.8871491],"study_design_scores_gemma":[0.020631084,0.029724,0.5699579,0.00090982026,0.0012026813,0.0006537394,0.003007133,0.28484654,0.010181961,0.0046159476,0.07386302,0.00040617157],"about_ca_topic_score_codex":0.000019292154,"about_ca_topic_score_gemma":0.000040888186,"teacher_disagreement_score":0.88674295,"about_ca_system_score_codex":0.00009192429,"about_ca_system_score_gemma":0.002243952,"threshold_uncertainty_score":0.3980674},"labels":[],"label_agreement":null},{"id":"W4391111407","doi":"10.1186/s13014-024-02409-6","title":"Development and validation of survival prognostic models for head and neck cancer patients using machine learning and dosiomics and CT radiomics features: a multicentric study","year":2024,"lang":"en","type":"article","venue":"Radiation Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Óbudai Egyetem; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Medicine; Radiomics; Head and neck cancer; Radiation therapy; Head and neck; Overall survival; Radiology; Oncology; Medical physics; Surgery","score_opus":0.025137581873333904,"score_gpt":0.3559575987771724,"score_spread":0.3308200169038385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391111407","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99215484,0.00452611,0.0019017578,0.00026629816,0.000179741,0.0009270106,0.000007129425,0.00002377914,0.00001334038],"genre_scores_gemma":[0.988454,0.0012978753,0.009992879,0.00005485977,0.00006658957,0.000033505377,0.000051793275,0.000023370236,0.000025131763],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99906474,0.00008632752,0.0002870478,0.0002833183,0.00012388041,0.0001546553],"domain_scores_gemma":[0.99927455,0.00039609053,0.00011428554,0.000039904822,0.00006131441,0.00011384264],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043809318,0.00012677684,0.0003261686,0.00019757675,0.00012286869,0.000039953688,0.000019467525,0.00005877528,0.0000016063432],"category_scores_gemma":[0.00035491402,0.000112314374,0.000015229435,0.0001197971,0.00006122651,0.00009509856,0.000040719468,0.00021202768,5.4516633e-8],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022884946,0.0002306226,0.765574,0.0005790994,0.00017175885,0.000012301951,0.0060988204,0.0012289154,0.0006093051,0.00009755223,0.000015265146,0.22515355],"study_design_scores_gemma":[0.005551465,0.000625794,0.11771105,0.00016511025,0.00033097286,0.000055008913,0.0002755113,0.87238413,0.00011507612,0.000041015093,0.0026108115,0.00013404358],"about_ca_topic_score_codex":0.00017856024,"about_ca_topic_score_gemma":0.000027361622,"teacher_disagreement_score":0.8711552,"about_ca_system_score_codex":0.00014613103,"about_ca_system_score_gemma":0.00016097058,"threshold_uncertainty_score":0.4580047},"labels":[],"label_agreement":null},{"id":"W4391212953","doi":"10.1016/j.labinv.2024.100341","title":"Reliability and Variability of Ki-67 Digital Image Analysis Methods for Clinical Diagnostics in Breast Cancer","year":2024,"lang":"en","type":"article","venue":"Laboratory Investigation","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Michael's Hospital; Ontario Institute for Cancer Research; University Health Network; Toronto Metropolitan University; University of Toronto; Princess Margaret Cancer Centre","funders":"Canadian Institutes of Health Research; Canadian Cancer Society; Ontario Ministry of Health and Long-Term Care","keywords":"Digital image analysis; Breast cancer; Reliability (semiconductor); Digital image; Medicine; Cancer; Pathology; Internal medicine; Computer science; Image processing; Oncology; Image (mathematics); Artificial intelligence; Computer vision; Physics","score_opus":0.020257782496347753,"score_gpt":0.41640344112362704,"score_spread":0.3961456586272793,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391212953","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9596129,0.00088481134,0.03337632,0.0052340487,0.00024421897,0.00031697773,0.00024008923,0.000049306396,0.00004129835],"genre_scores_gemma":[0.93941534,0.0006794078,0.059081778,0.0004945889,0.00016611691,0.000048061218,0.000083963045,0.000017779597,0.000012949142],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9985824,0.00027351137,0.000544423,0.00035261747,0.0001231054,0.00012393261],"domain_scores_gemma":[0.99742645,0.0018500487,0.00008832879,0.00021903901,0.000251213,0.00016489324],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0033123104,0.00010145878,0.000381533,0.00014448426,0.00002323811,0.000047347057,0.000045810597,0.00010824387,0.000020259455],"category_scores_gemma":[0.007468017,0.000085686785,0.00009244638,0.0008682682,0.0005166287,0.00019859373,0.000026667998,0.00032225793,5.4295566e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035454843,0.00006395418,0.97342306,0.00052925845,0.00014682852,0.0000034355667,0.00021086633,0.000041518742,0.0018941709,0.00065334,0.0005469857,0.022451133],"study_design_scores_gemma":[0.00042319082,0.000046438287,0.8481721,0.0001687427,0.00064552197,0.0000019302868,0.00002974251,0.1429804,0.0002523159,0.005160707,0.0020250776,0.000093790935],"about_ca_topic_score_codex":0.000061800856,"about_ca_topic_score_gemma":0.0000037069167,"teacher_disagreement_score":0.14293888,"about_ca_system_score_codex":0.00007118688,"about_ca_system_score_gemma":0.00031284965,"threshold_uncertainty_score":0.8940453},"labels":[],"label_agreement":null},{"id":"W4391215608","doi":"10.1088/2057-1976/ad229c","title":"PSMA PET/CT as a predictive tool for subregional importance estimates in the parotid gland","year":2024,"lang":"en","type":"article","venue":"Biomedical Physics & Engineering Express","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Surrey Memorial Hospital; BC Cancer Agency; University of British Columbia","funders":"Canadian Institutes of Health Research","keywords":"Parotid gland; Nuclear medicine; Medicine; Radiology; Pathology","score_opus":0.008220484469837535,"score_gpt":0.2745024866614886,"score_spread":0.26628200219165105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391215608","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.52930653,0.001244686,0.46162504,0.0054001524,0.00090631115,0.00097068585,0.000059481485,0.00037378934,0.000113334914],"genre_scores_gemma":[0.97677064,0.00004080885,0.020842584,0.00046344745,0.0012769867,0.00029951142,0.00017796714,0.000056729616,0.00007131074],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984471,0.000017018165,0.0002893749,0.00036212054,0.0004920509,0.00039231265],"domain_scores_gemma":[0.9988675,0.00067664456,0.000032599462,0.0002430305,0.00003048627,0.00014971575],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043526842,0.00021938302,0.0003004872,0.0000895466,0.000049936352,0.00007597107,0.00021689392,0.000024976645,0.000017595372],"category_scores_gemma":[0.00048665036,0.00015046101,0.00014555064,0.00030787272,0.00013816937,0.00009953666,0.000041138217,0.0005551894,0.000010127868],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021206373,0.0050455146,0.0732466,0.019716563,0.0033615748,0.033755787,0.009019011,0.020226512,0.34792683,0.16224967,0.25469235,0.068638936],"study_design_scores_gemma":[0.001615639,0.00036709107,0.006105474,0.0013418901,0.00015278415,0.0013369874,0.000064289714,0.75404745,0.00020984934,0.004180677,0.23022076,0.00035711096],"about_ca_topic_score_codex":0.000022311438,"about_ca_topic_score_gemma":5.3704305e-8,"teacher_disagreement_score":0.7338209,"about_ca_system_score_codex":0.000065658336,"about_ca_system_score_gemma":0.00011901127,"threshold_uncertainty_score":0.61356217},"labels":[],"label_agreement":null},{"id":"W4391288548","doi":"10.1016/j.acra.2024.01.024","title":"Imaging Genomics and Multiomics: A Guide for Beginners Starting Radiomics-Based Research","year":2024,"lang":"en","type":"review","venue":"Academic Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Radiogenomics; Radiomics; Workflow; Medical imaging; Genomics; Computer science; Precision medicine; Medical physics; Medicine; Data science; Computational biology; Artificial intelligence; Bioinformatics; Pathology; Genome; Gene; Biology","score_opus":0.1272120937636347,"score_gpt":0.4792639904936971,"score_spread":0.35205189673006243,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391288548","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005204654,0.98953277,0.0015721921,0.004456415,0.0009363251,0.0023389484,0.00008705446,0.00019151175,0.00036429055],"genre_scores_gemma":[0.00005227372,0.98335415,0.0112546375,0.0012262554,0.002233569,0.00045265947,0.0003395264,0.00030171403,0.00078519556],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9948244,0.00049260573,0.0015883929,0.0014280968,0.0003148329,0.0013516624],"domain_scores_gemma":[0.99553317,0.0027984022,0.000415301,0.00059598254,0.00015431423,0.0005028078],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0057167523,0.00069174473,0.0027910725,0.0029471535,0.00028916117,0.00007300812,0.0005503025,0.0010785442,0.000011184979],"category_scores_gemma":[0.003395173,0.0005653605,0.00061560347,0.000726302,0.0010322465,0.000067878,0.0002605536,0.006202653,0.000030044974],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005991129,0.000016411039,0.00012402226,0.015752887,0.0004686908,0.00017195879,0.00026187318,0.000013385291,0.00013543235,0.0015568602,0.06786799,0.9135706],"study_design_scores_gemma":[0.0011109672,0.00012416039,0.000002965387,0.008235177,0.0020041487,0.0012854859,0.00006623707,0.025841478,0.0000033058411,0.0008793182,0.959988,0.00045876988],"about_ca_topic_score_codex":0.00010408126,"about_ca_topic_score_gemma":0.0000013616144,"teacher_disagreement_score":0.9131118,"about_ca_system_score_codex":0.0008268427,"about_ca_system_score_gemma":0.0013559021,"threshold_uncertainty_score":0.9996798},"labels":[],"label_agreement":null},{"id":"W4391303212","doi":"10.1200/jco.2024.42.4_suppl.262","title":"Stockholm3 validation in a multi-ethnic cohort for prostate cancer (SEPTA) detection: A multicentered, prospective trial.","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto; University Health Network","funders":"Vetenskapsrådet","keywords":"Medicine; Prostate cancer; Prospective cohort study; Cohort; Cancer; Prostate; Oncology; Gynecology; Internal medicine","score_opus":0.14412154296887295,"score_gpt":0.5400226121622324,"score_spread":0.39590106919335943,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391303212","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96313244,0.002021215,0.016277289,0.010328283,0.005879224,0.0021324423,0.00000492349,0.0000313612,0.00019280399],"genre_scores_gemma":[0.98776615,0.0012549568,0.0073412,0.00080742524,0.0018950626,0.00016512405,0.0000028922866,0.000031096642,0.00073608826],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.996965,0.0003237412,0.0019232419,0.00027340013,0.00028219447,0.00023243648],"domain_scores_gemma":[0.9968005,0.0018134005,0.0006959715,0.00010569344,0.00034722546,0.00023725515],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0060571404,0.00012702103,0.0010334909,0.00022263377,0.000033892335,0.000023750785,0.000094779636,0.00025827732,0.000051010327],"category_scores_gemma":[0.008359657,0.00009093943,0.0004541777,0.00023985992,0.0001288045,0.0001345546,0.000025303718,0.0016482386,0.000005458541],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.057516314,0.0020082507,0.07567103,0.0002314669,0.00072044076,0.00052371685,0.0006640804,0.00030442845,0.0009228045,0.000034103934,0.0010039329,0.8603994],"study_design_scores_gemma":[0.26577166,0.029113384,0.40601796,0.0016233898,0.0017052626,0.00056562544,0.00034374287,0.18790646,0.0004918142,0.0006715308,0.10546156,0.00032762074],"about_ca_topic_score_codex":0.00005823754,"about_ca_topic_score_gemma":0.00009491189,"teacher_disagreement_score":0.86007184,"about_ca_system_score_codex":0.0004273967,"about_ca_system_score_gemma":0.0012565299,"threshold_uncertainty_score":0.9999933},"labels":[],"label_agreement":null},{"id":"W4391345880","doi":"10.1038/s41598-023-50382-z","title":"Edge roughness quantifies impact of physician variation on training and performance of deep learning auto-segmentation models for the esophagus","year":2024,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"National Cancer Institute; National Institutes of Health","keywords":"Segmentation; Esophagus; Artificial intelligence; Computer science; Deep learning; Variation (astronomy); Surface roughness; Medicine; Computer vision; Pattern recognition (psychology); Anatomy; Materials science; Composite material","score_opus":0.024351721727445843,"score_gpt":0.3212167419278237,"score_spread":0.29686502020037786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391345880","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9555057,0.0017386453,0.040515553,0.00015013243,0.0015405631,0.0003469981,0.0000012504378,0.000035512934,0.0001656443],"genre_scores_gemma":[0.99868405,0.000024098446,0.0008347435,0.000013143057,0.00008571653,0.000011514058,0.000029979614,0.000014798522,0.00030193248],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988957,0.000025911651,0.00034276163,0.0002887694,0.0003038798,0.00014297153],"domain_scores_gemma":[0.99925977,0.0001919131,0.00021080389,0.00019252404,0.000104118866,0.000040888885],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015813214,0.00009015392,0.00019822952,0.00013861466,0.00016975074,0.00008840156,0.00003934376,0.00003101184,0.000009238599],"category_scores_gemma":[0.00020820167,0.000057539506,0.00010520681,0.00025940276,0.00016982734,0.00017536197,0.000014843758,0.00016272315,3.6784343e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016175547,0.00011701361,0.009680097,0.0011791055,0.00030894755,0.000037184527,0.028771413,0.19837241,0.07852384,0.0011687522,0.00032546202,0.681354],"study_design_scores_gemma":[0.00016766357,0.00024818553,0.013837502,0.0003001075,0.00009958822,0.00004847741,0.00038561382,0.97944474,0.004174478,0.001176663,0.00006109464,0.000055910095],"about_ca_topic_score_codex":0.00002920621,"about_ca_topic_score_gemma":5.436387e-7,"teacher_disagreement_score":0.7810723,"about_ca_system_score_codex":0.00003672338,"about_ca_system_score_gemma":0.00010912552,"threshold_uncertainty_score":0.23463929},"labels":[],"label_agreement":null},{"id":"W4391447087","doi":"10.1002/ima.23028","title":"Differentiation of COVID‐19 pneumonia from other lung diseases using CT radiomic features and machine learning: A large multicentric cohort study","year":2024,"lang":"en","type":"article","venue":"International Journal of Imaging Systems and Technology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung","keywords":"Coronavirus disease 2019 (COVID-19); Pneumonia; 2019-20 coronavirus outbreak; Cohort; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Medicine; Lung; Betacoronavirus; Radiomics; Cohort study; Artificial intelligence; Machine learning; Computer science; Medical physics; Radiology; Pathology; Internal medicine; Infectious disease (medical specialty)","score_opus":0.006899129293915221,"score_gpt":0.3003786153671597,"score_spread":0.2934794860732445,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391447087","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9527588,0.03541026,0.008325853,0.0023643333,0.0008421799,0.00021235566,0.00002751129,0.00004989875,0.000008840461],"genre_scores_gemma":[0.998994,0.0004188984,0.00019767472,0.000050619226,0.00024701632,0.0000029090254,0.000010318721,0.000022012264,0.00005657466],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987926,0.0000833331,0.00044890126,0.00019862448,0.00035062025,0.0001259542],"domain_scores_gemma":[0.99917513,0.0001519467,0.00031220124,0.0000826197,0.0001636025,0.00011451735],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038864688,0.00012838571,0.00038971964,0.0007944535,0.00006492742,0.000080127946,0.00012042928,0.000036203794,0.000014081504],"category_scores_gemma":[0.00047488918,0.000097427524,0.000058257803,0.00014780312,0.00013699342,0.000101339916,0.00007400151,0.000464806,2.6665407e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000053252974,0.0001342808,0.99009824,0.000106937,0.0007625741,0.00092523673,0.0002735337,0.000060441074,0.0049047666,0.00027293613,0.0000816389,0.0023261583],"study_design_scores_gemma":[0.0049266294,0.00018701365,0.3946074,0.001301416,0.0012037962,0.013123155,0.0016042391,0.57838506,0.00012343282,0.00032908955,0.0039852257,0.00022353894],"about_ca_topic_score_codex":0.0009049073,"about_ca_topic_score_gemma":0.0000047142967,"teacher_disagreement_score":0.5954909,"about_ca_system_score_codex":0.00011877451,"about_ca_system_score_gemma":0.00009641126,"threshold_uncertainty_score":0.3972979},"labels":[],"label_agreement":null},{"id":"W4391465176","doi":"10.1007/978-3-031-47425-5","title":"Medical Image Computing and Computer Assisted Intervention – MICCAI 2023 Workshops","year":2023,"lang":"en","type":"book","venue":"Lecture notes in computer science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Eberhard Karls Universität Tübingen; University of Bern","keywords":"Computer science; Computer graphics (images); Multimedia; Human–computer interaction","score_opus":0.01215078078573951,"score_gpt":0.3109308536036566,"score_spread":0.2987800728179171,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391465176","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003264453,0.0005082396,0.98812795,0.0039424836,0.0028930723,0.00038671837,0.0000033323865,0.00023625583,0.00063748733],"genre_scores_gemma":[0.11514208,0.00048511158,0.8426738,0.017366337,0.013527069,0.000025532034,0.0004781285,0.0004430286,0.009858913],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99578077,0.00011381786,0.00073409063,0.0012443921,0.0014185978,0.00070832216],"domain_scores_gemma":[0.99747103,0.0010705063,0.00026827317,0.00052877585,0.00018150748,0.00047987374],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0025308616,0.00045859104,0.000852654,0.00084565714,0.00022502535,0.00032253243,0.00070609164,0.0004823319,0.000068750065],"category_scores_gemma":[0.0010124844,0.00039735116,0.00019506057,0.0008930719,0.0013769771,0.00013567517,0.0011439933,0.0025503386,0.000053099946],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018051236,0.00006735066,0.00066232774,0.00036879984,0.00004326991,0.0008794101,0.00030211895,0.00077812927,0.00005892906,0.000049184106,0.0023685235,0.9944039],"study_design_scores_gemma":[0.001256899,0.00020427389,0.008885969,0.005807078,0.000052011634,0.0008235857,9.0580386e-7,0.9789853,0.000021700751,0.0022077188,0.0013353884,0.00041914496],"about_ca_topic_score_codex":0.000044764733,"about_ca_topic_score_gemma":0.000035214856,"teacher_disagreement_score":0.99398476,"about_ca_system_score_codex":0.00035081917,"about_ca_system_score_gemma":0.00068664516,"threshold_uncertainty_score":0.9998478},"labels":[],"label_agreement":null},{"id":"W4391553138","doi":"10.26226/morressier.5c8f90a0b5d368000a26b6df","title":"1892 - Automatic Extraction of Pelvic Coordinate System and Bony Landmarks from CT Imaging Data for Endoprosthetic Pelvic Reconstruction of Sarcoma Patients","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Medicine; Radiology; Sarcoma; Pathology","score_opus":0.014092761249508805,"score_gpt":0.2879547228837197,"score_spread":0.2738619616342109,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391553138","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98538166,0.0007387465,0.009136869,0.00030408855,0.001422481,0.0015699232,0.00036055775,0.000091046524,0.0009946284],"genre_scores_gemma":[0.98578,0.000085798834,0.012108594,0.00003434246,0.00011330856,0.000025006113,0.0016868269,0.00005279712,0.00011334832],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977591,0.00010872093,0.00088451384,0.0006682113,0.0003467037,0.00023272337],"domain_scores_gemma":[0.9973202,0.00037011658,0.0009279002,0.001056719,0.0002096638,0.00011542348],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006988659,0.00028771893,0.0009769453,0.00025311884,0.000049291146,0.000039136812,0.00026150595,0.00011610146,0.000053240303],"category_scores_gemma":[0.00044862356,0.00024432002,0.0001287317,0.00006782828,0.00013600414,0.00014038899,0.00041896067,0.00060437433,0.0000027991232],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002619683,0.00026126052,0.6051718,0.013061211,0.0004763352,0.000017130997,0.00025142127,0.00006989873,0.002992822,0.000081024846,0.0011103431,0.37624478],"study_design_scores_gemma":[0.004631294,0.00014039295,0.11069755,0.0057737343,0.0009733245,0.00031459058,0.0004008006,0.8756232,0.00054994406,0.00032040206,0.0002815492,0.00029319883],"about_ca_topic_score_codex":0.0016807105,"about_ca_topic_score_gemma":0.0000075380635,"teacher_disagreement_score":0.8755533,"about_ca_system_score_codex":0.00011200105,"about_ca_system_score_gemma":0.00014870615,"threshold_uncertainty_score":0.9963081},"labels":[],"label_agreement":null},{"id":"W4391554807","doi":"10.1016/j.ejrad.2024.111349","title":"Impact of different reconstruction algorithms and setting parameters on radiomics features of PSMA PET images: A preliminary study","year":2024,"lang":"en","type":"article","venue":"European Journal of Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Tehran University of Medical Sciences and Health Services","keywords":"Imaging phantom; Medicine; Iterative reconstruction; Radiomics; Robustness (evolution); Nuclear medicine; Reproducibility; Artificial intelligence; Reconstruction algorithm; Positron emission tomography; Algorithm; Pattern recognition (psychology); Mathematics; Radiology; Computer science; Statistics","score_opus":0.011319432608382361,"score_gpt":0.29672786999273054,"score_spread":0.2854084373843482,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391554807","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99560785,0.0014420885,0.0015131233,0.0004623374,0.0005423299,0.0001476213,0.0000052958158,0.000012618616,0.0002667053],"genre_scores_gemma":[0.9910727,0.0003525541,0.0082197925,0.000036347832,0.00026082425,3.986029e-7,0.0000025683346,0.000031144926,0.000023681303],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9982119,0.00067432923,0.00061037147,0.00017867434,0.00016347565,0.00016124068],"domain_scores_gemma":[0.99885476,0.00040272658,0.00039125397,0.00014265244,0.00007108955,0.00013753836],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012413041,0.00016273686,0.0005830126,0.0003674484,0.000029685349,0.000016409622,0.00010764171,0.000023208855,0.000011570701],"category_scores_gemma":[0.00053826696,0.00010383398,0.00022510155,0.00009919018,0.00022662866,0.000053125834,0.000033633245,0.0007425437,6.098792e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0027923544,0.0006232484,0.15990454,0.0004060597,0.002466435,0.0064590443,0.004329037,0.00083295035,0.022464216,0.00008341942,0.003650343,0.7959883],"study_design_scores_gemma":[0.0032884139,0.022684932,0.8921375,0.0011712478,0.00054766616,0.072830185,0.0009535269,0.0056324936,0.000443148,0.00012759356,0.000033672542,0.00014960018],"about_ca_topic_score_codex":0.0000064896417,"about_ca_topic_score_gemma":6.699331e-8,"teacher_disagreement_score":0.7958388,"about_ca_system_score_codex":0.000057979727,"about_ca_system_score_gemma":0.000060390794,"threshold_uncertainty_score":0.4234227},"labels":[],"label_agreement":null},{"id":"W4391577343","doi":"10.1148/radiol.231319","title":"The Image Biomarker Standardization Initiative: Standardized Convolutional Filters for Reproducible Radiomics and Enhanced Clinical Insights","year":2024,"lang":"en","type":"review","venue":"Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":216,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Cancer Institute; Centre For Medical Engineering, King’s College London; UK Research and Innovation; Engineering and Physical Sciences Research Council; Natural Sciences and Engineering Research Council of Canada; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; Wellcome Trust; Cancer Research UK; Canadian Institute for Advanced Research; National Science Foundation; Wellcome; King's College London","keywords":"Reproducibility; Intraclass correlation; Medicine; Artificial intelligence; Feature (linguistics); Filter (signal processing); Pattern recognition (psychology); Standardization; Computer science; Nuclear medicine; Computer vision; Mathematics; Statistics","score_opus":0.06928972278475067,"score_gpt":0.43989186909350586,"score_spread":0.3706021463087552,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391577343","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000552565,0.93901926,0.055084895,0.001319207,0.002130736,0.001657644,0.00018408176,0.000092334485,0.0004565958],"genre_scores_gemma":[0.00005606059,0.99182594,0.005217696,0.00029838036,0.0011443413,0.00022398734,0.0007048654,0.00009662148,0.00043212637],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9964172,0.00067465723,0.0012357964,0.001028194,0.0002307646,0.00041334762],"domain_scores_gemma":[0.99596906,0.0025899105,0.00043575524,0.0005752043,0.0002214265,0.0002086466],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002998249,0.00042232356,0.0021737434,0.00021776208,0.00031212243,0.00009216955,0.00018807806,0.0004693138,0.000017568269],"category_scores_gemma":[0.0052268473,0.0002488997,0.00063402567,0.00027365636,0.0011279905,0.000058837195,0.00010913506,0.0010165514,0.000012698455],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034119334,0.000030465879,0.0000056851977,0.005228534,0.0015172866,0.00004547655,0.000098348035,8.013175e-7,0.00002841021,0.002356406,0.05685754,0.93348986],"study_design_scores_gemma":[0.001588227,0.00028636662,0.000015818317,0.0024993375,0.0022247068,0.00055288506,0.000021865659,0.0013395968,0.0000033663687,0.0011827784,0.9900302,0.000254804],"about_ca_topic_score_codex":0.000001651938,"about_ca_topic_score_gemma":8.7854573e-7,"teacher_disagreement_score":0.93323505,"about_ca_system_score_codex":0.00025138183,"about_ca_system_score_gemma":0.0011281568,"threshold_uncertainty_score":0.9999963},"labels":[],"label_agreement":null},{"id":"W4391615040","doi":"10.1053/j.semnuclmed.2024.01.002","title":"Application of Artificial Intelligence in Oncologic Molecular PET-Imaging: A Narrative Review on Beyond [18F]F-FDG Tracers Part II. [F]F-FLT, [F]F-FET, [C]C-MET and Other Less-Commonly Used Radiotracers","year":2024,"lang":"en","type":"review","venue":"Seminars in Nuclear Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Women's College Hospital; University of Toronto; University Health Network","funders":"","keywords":"Medicine; Positron emission tomography; Glioma; Nuclear medicine; Cancer research","score_opus":0.03295989430763512,"score_gpt":0.37984505574897104,"score_spread":0.3468851614413359,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391615040","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011021902,0.98601764,0.00006485161,0.006899794,0.00039694205,0.0024624667,0.000019476021,0.00008005432,0.002956583],"genre_scores_gemma":[0.0020511202,0.9930163,0.0010543901,0.0030540705,0.00027282367,0.00014595472,0.00010089181,0.0001917407,0.000112712165],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9950416,0.00048247364,0.002001051,0.001138094,0.00077879115,0.00055797317],"domain_scores_gemma":[0.9976457,0.00049567537,0.0007473631,0.0007479225,0.00006740611,0.00029594052],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.002808074,0.0008010805,0.0036972277,0.0010305485,0.00008268605,0.000019106868,0.0004349405,0.0002647627,0.00017467554],"category_scores_gemma":[0.0012224321,0.000594099,0.0003413593,0.0015016042,0.0010194965,0.00006353659,0.00015543977,0.0026388483,0.00002303025],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007738427,0.0002674352,0.000034019435,0.02836394,0.00013997938,0.0009785347,0.0024757453,0.000012653723,0.00004275178,0.0024418463,0.0052278796,0.9599378],"study_design_scores_gemma":[0.0005092172,0.0009732312,0.0000053679546,0.2211433,0.0016266824,0.00072380726,0.0019966178,0.0033596097,0.0000034921356,0.0006411098,0.76852274,0.0004948056],"about_ca_topic_score_codex":0.00014289677,"about_ca_topic_score_gemma":0.000019442698,"teacher_disagreement_score":0.95944303,"about_ca_system_score_codex":0.0005529168,"about_ca_system_score_gemma":0.0002788187,"threshold_uncertainty_score":0.9996621},"labels":[],"label_agreement":null},{"id":"W4391636325","doi":"10.1055/s-0043-1776428","title":"Radiomics in Musculoskeletal Tumors","year":2024,"lang":"en","type":"article","venue":"Seminars in Musculoskeletal Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sinai Health System; Women's College Hospital; University of Toronto; University Health Network; Mount Sinai Hospital","funders":"","keywords":"Radiomics; Medicine; Sarcoma; Radiogenomics; Medical imaging; Viewpoints; Medical physics; Radiology; Pathology","score_opus":0.006774629798402162,"score_gpt":0.30647949875698965,"score_spread":0.2997048689585875,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391636325","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9744871,0.010322288,0.0006037974,0.0043590968,0.0013118063,0.00053167366,0.000005496161,0.00022682383,0.008151878],"genre_scores_gemma":[0.9924873,0.001986897,0.0031473055,0.0005461033,0.0006241129,0.00007889959,0.00010046426,0.00010774334,0.0009211361],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99655294,0.00029469052,0.0008552286,0.0009497773,0.00034534518,0.0010020055],"domain_scores_gemma":[0.99859136,0.000510251,0.000070920556,0.0004941863,0.00003058349,0.00030267236],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0015753339,0.00043874062,0.0009420016,0.0011872591,0.000055392287,0.000039807852,0.00031332634,0.00038500893,0.00026321836],"category_scores_gemma":[0.00093965506,0.0003969048,0.00041326397,0.0011803147,0.0005295669,0.00017729354,0.00012228031,0.0020712223,0.00013576986],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004601645,0.00077815645,0.22052129,0.0035041093,0.00034547574,0.02162852,0.002621595,0.0015801969,0.02282181,0.021277748,0.012154463,0.69230646],"study_design_scores_gemma":[0.014028075,0.004515532,0.39336738,0.011261344,0.00060220953,0.024105119,0.002148562,0.34389755,0.0004948197,0.015632993,0.18615976,0.0037866386],"about_ca_topic_score_codex":0.00015215795,"about_ca_topic_score_gemma":0.000035876477,"teacher_disagreement_score":0.68851984,"about_ca_system_score_codex":0.0004994657,"about_ca_system_score_gemma":0.0003002777,"threshold_uncertainty_score":0.9998483},"labels":[],"label_agreement":null},{"id":"W4391810690","doi":"10.1038/s41598-024-52828-4","title":"Distinguishing recurrence from radiation-induced lung injury at the time of RECIST progressive disease on post-SABR CT scans using radiomics","year":2024,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Victoria Hospital; London Health Sciences Centre; Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Ontario Institute for Cancer Research; London Health Sciences Foundation; Government of Ontario","keywords":"Radiomics; SABR volatility model; Medicine; Radiology; Radiosurgery; Radiation therapy; Disease; Nuclear medicine; Pathology","score_opus":0.012484952296491044,"score_gpt":0.3139795119362478,"score_spread":0.30149455963975674,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391810690","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98695165,0.0023675412,0.00013177026,0.0018234228,0.0075231763,0.0005427256,0.000055814868,0.00009073816,0.0005131598],"genre_scores_gemma":[0.9968914,0.000011117517,0.0005280088,0.0001663254,0.00040113556,0.000013735573,0.0003960672,0.000039540304,0.0015526926],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972816,0.00010670973,0.00062549615,0.0008298537,0.00084517465,0.00031112524],"domain_scores_gemma":[0.99794626,0.00030332428,0.00039019456,0.00087878,0.00019052485,0.00029088923],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017323116,0.00019488166,0.0003033853,0.00019604132,0.0004669606,0.00036797588,0.00016712617,0.000033882443,0.0002114116],"category_scores_gemma":[0.004384388,0.00013518444,0.00016367559,0.0006496918,0.00042227865,0.00013707242,0.000115922194,0.00044899192,0.00001639523],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000682912,0.0006021309,0.0853378,0.0011091124,0.0006977285,0.023054611,0.0065990943,0.0025402503,0.30944005,0.00028678335,0.100623034,0.4690265],"study_design_scores_gemma":[0.0006730337,0.00018529917,0.015605694,0.008205619,0.0011493644,0.0016774848,0.00021398177,0.9000139,0.02399235,0.0023905758,0.0450533,0.0008393926],"about_ca_topic_score_codex":0.00020541721,"about_ca_topic_score_gemma":0.000002507559,"teacher_disagreement_score":0.89747363,"about_ca_system_score_codex":0.00030759058,"about_ca_system_score_gemma":0.0007140995,"threshold_uncertainty_score":0.55126613},"labels":[],"label_agreement":null},{"id":"W4391871413","doi":"10.48550/arxiv.2402.09359","title":"Pruning Sparse Tensor Neural Networks Enables Deep Learning for 3D Ultrasound Localization Microscopy","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Montreal Heart Institute; Minnow Environmental (Canada); Polytechnique Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Alliance de recherche numérique du Canada; Institut de Valorisation des Données; Canada First Research Excellence Fund","keywords":"Pruning; Artificial neural network; Deep neural networks; Artificial intelligence; Microscopy; Deep learning; Computer science; Tensor (intrinsic definition); Pattern recognition (psychology); Mathematics; Physics; Biology; Optics; Geometry","score_opus":0.030636248203635873,"score_gpt":0.22716344365591962,"score_spread":0.19652719545228375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391871413","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24505466,0.0011535052,0.750313,0.00023400491,0.0011452688,0.00077125925,0.0000066228995,0.0003885678,0.0009331093],"genre_scores_gemma":[0.9897051,0.0005908931,0.0031649265,0.00038128305,0.0006791463,0.0000044661874,0.00040098972,0.00012315987,0.004950063],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978433,0.00012448942,0.00032007808,0.001034566,0.00011227721,0.00056524435],"domain_scores_gemma":[0.99850106,0.00034098976,0.00024205398,0.00043233085,0.00019829844,0.00028528215],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00043064854,0.00042246934,0.0005862369,0.0003137489,0.00030960605,0.00015780395,0.00028385702,0.0004304058,0.00007862012],"category_scores_gemma":[0.00053046446,0.0004422809,0.00031866992,0.000401634,0.00021707609,0.00007891614,0.0004304392,0.0021594465,0.000018677016],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019020031,0.00005704679,0.016916841,0.00077969895,0.00024413154,0.00034713687,0.00023685936,0.97666186,0.00027925728,0.0012613676,0.0006686777,0.0023569136],"study_design_scores_gemma":[0.00096112385,0.00012401823,0.00038207398,0.00070965855,0.0008620392,0.000058562553,0.00023616916,0.98822147,0.00004006748,0.0019538014,0.006045135,0.00040590268],"about_ca_topic_score_codex":0.00012362155,"about_ca_topic_score_gemma":0.000014612514,"teacher_disagreement_score":0.7471481,"about_ca_system_score_codex":0.00026359624,"about_ca_system_score_gemma":0.00012801426,"threshold_uncertainty_score":0.9998029},"labels":[],"label_agreement":null},{"id":"W4391873649","doi":"10.1093/jcag/gwad061.096","title":"A96 A QUALITY ASSESSMENT STUDY TO DETERMINE IF TISSUE ACQUISTION AND SPECIMEN HANDLING IMPACT THE DIAGNOSTIC YIELD OF ENDOSCOPIC ULTRASOUND-GUIDED FINE NEEDLE ASPIRATION OF SOLID MASS","year":2024,"lang":"en","type":"article","venue":"Journal of the Canadian Association of Gastroenterology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Endoscopic ultrasound; Yield (engineering); Ultrasound; Fine-needle aspiration; Medicine; Quality (philosophy); Radiology; Materials science; Biopsy; Physics; Composite material","score_opus":0.021158749594035162,"score_gpt":0.34514910885024974,"score_spread":0.32399035925621456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391873649","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9882381,0.00004700521,0.0013721216,0.009548398,0.00041709762,0.00031065464,0.000028400094,0.0000023890882,0.000035859466],"genre_scores_gemma":[0.9989659,0.00001376703,0.00038475302,0.00035527677,0.00018156614,0.0000026668083,0.0000031368143,0.000009442738,0.00008345162],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99828,0.0003530198,0.00073012186,0.00009598052,0.0003549965,0.00018590325],"domain_scores_gemma":[0.9978002,0.000890929,0.0007593504,0.00013919121,0.00025972005,0.00015062517],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023461014,0.00009481384,0.00043827132,0.0002190153,0.000059567818,0.00002101049,0.0001331649,0.000047980306,0.000043896365],"category_scores_gemma":[0.0044188243,0.00005994447,0.000109248474,0.00013464928,0.00005072665,0.000050679282,0.000021828862,0.00033691333,2.9466065e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007397757,0.00008002149,0.9712356,0.000059029917,0.0003460167,0.0000115867815,0.00087207777,0.0010208805,0.024465978,0.000014450413,0.0012188858,0.00060151704],"study_design_scores_gemma":[0.0010453993,0.0028351836,0.99348706,0.00028629755,0.00030593073,0.0000808429,0.00020418373,0.0009630875,0.0006167189,0.00006645453,0.0000788902,0.000029936975],"about_ca_topic_score_codex":0.006088019,"about_ca_topic_score_gemma":0.021302145,"teacher_disagreement_score":0.023849258,"about_ca_system_score_codex":0.0005280364,"about_ca_system_score_gemma":0.00032731448,"threshold_uncertainty_score":0.9965565},"labels":[],"label_agreement":null},{"id":"W4391908317","doi":"10.1117/12.3003897","title":"Using attention-based convolutional auto-encoders for catheter path reconstruction in ultrasound images","year":2024,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University; University of Alberta","funders":"","keywords":"Computer science; Path (computing); Encoder; Artificial intelligence; Computer vision; Iterative reconstruction; Autoencoder; Speech recognition; Deep learning; Computer network","score_opus":0.020988333059879512,"score_gpt":0.31928199464510193,"score_spread":0.2982936615852224,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391908317","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43344545,0.000363756,0.55976,0.0034916312,0.00093628163,0.00037440774,0.000014513273,0.00015462075,0.0014593577],"genre_scores_gemma":[0.93226117,0.000012613537,0.06613878,0.0005136939,0.0002093735,0.000019615592,0.000054186465,0.000022250008,0.00076829386],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992133,0.000023958353,0.00021032541,0.00023445496,0.00013605776,0.00018191118],"domain_scores_gemma":[0.9995319,0.00024845093,0.000024862476,0.00008270361,0.000044686618,0.00006735898],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035476562,0.00009246467,0.00014267901,0.00017735442,0.00005756914,0.000048687638,0.000030903957,0.00005558626,0.00020208847],"category_scores_gemma":[0.00022726021,0.00007632958,0.000113709364,0.0001295961,0.000103892206,0.00008889577,0.0000049155115,0.00021957686,0.0000079557],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032078047,0.00073354115,0.37195393,0.0020934988,0.00037456542,0.00018177279,0.0004982116,0.006706413,0.50999486,0.0083077615,0.012121461,0.086713225],"study_design_scores_gemma":[0.0011471817,0.0000929292,0.008511408,0.0005305169,0.00007850509,0.00030232046,0.00012439185,0.98572475,0.00050145725,0.0010335386,0.0018184916,0.00013452026],"about_ca_topic_score_codex":0.00014156934,"about_ca_topic_score_gemma":0.0000041629924,"teacher_disagreement_score":0.97901833,"about_ca_system_score_codex":0.00014771617,"about_ca_system_score_gemma":0.00020074948,"threshold_uncertainty_score":0.311263},"labels":[],"label_agreement":null},{"id":"W4391934577","doi":"10.1016/j.jcct.2024.02.003","title":"Prediction of the development of new coronary atherosclerotic plaques with radiomics","year":2024,"lang":"en","type":"article","venue":"Journal of cardiovascular computed tomography","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Ministry of Health and Welfare; Ministry of Science, ICT and Future Planning; Ministry of Trade, Industry and Energy; Korea Medical Device Development Fund; National Research Foundation; Ministry of Science and ICT, South Korea; Ministry of Food and Drug Safety; National Research Foundation of Korea; Dalio Foundation","keywords":"Medicine; Radiomics; Confidence interval; Internal medicine; Cardiology; Coronary angiography; Radiology; Coronary atherosclerosis; Coronary anatomy; Proportional hazards model; Predictive value of tests; Coronary artery disease; Myocardial infarction","score_opus":0.015233459809437624,"score_gpt":0.2264268020825,"score_spread":0.21119334227306236,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391934577","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.782467,0.019642614,0.1965616,0.00023259154,0.0006995266,0.00021449871,0.0000023942127,0.000026769194,0.00015301509],"genre_scores_gemma":[0.9613144,0.00024685345,0.038063463,0.000032505424,0.00029777098,6.7070323e-7,0.0000026147434,0.000026408543,0.000015326093],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99819785,0.00008519828,0.00061030703,0.00013211234,0.0008433253,0.00013123009],"domain_scores_gemma":[0.9991185,0.00005752465,0.00021669459,0.00027135116,0.00020655773,0.00012936731],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008090328,0.00013536753,0.0005743973,0.00035158472,0.00003893111,0.00001759737,0.0001808629,0.00006169181,0.0000051756933],"category_scores_gemma":[0.00003454543,0.00007903166,0.0010941052,0.0006679658,0.00013492838,0.00007663661,0.000037011945,0.0004613864,2.8717446e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009567075,0.0005689384,0.16239233,0.0028411676,0.06576815,0.0004932107,0.0077970554,0.06813627,0.009036602,0.0003790593,0.0056340103,0.6759965],"study_design_scores_gemma":[0.008727008,0.0014878775,0.83788913,0.011272259,0.0066876775,0.0066396673,0.00030653068,0.03007326,0.011897606,0.00032953435,0.08433833,0.00035109167],"about_ca_topic_score_codex":0.000006673243,"about_ca_topic_score_gemma":2.7901032e-7,"teacher_disagreement_score":0.6756454,"about_ca_system_score_codex":0.000043060332,"about_ca_system_score_gemma":0.0005143295,"threshold_uncertainty_score":0.32228178},"labels":[],"label_agreement":null},{"id":"W4392058465","doi":"10.32920/25262749","title":"Impact of Image Pre-processing Methods on Computed Tomography Radiomics Features in Chronic Obstructive Pulmonary Disease","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Toronto Metropolitan University","funders":"","keywords":"Thresholding; Image processing; Resampling; COPD; Artificial intelligence; Preprocessor; Medicine; Pattern recognition (psychology); Computer science; Image segmentation; Radiomics; Feature extraction; Feature (linguistics); Segmentation; Radiology; Image (mathematics); Internal medicine","score_opus":0.011330062945140593,"score_gpt":0.37208044242646976,"score_spread":0.36075037948132915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392058465","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9346939,0.027071007,0.02169241,0.002440994,0.0012304849,0.0017695652,0.00010624296,0.00043892697,0.010556468],"genre_scores_gemma":[0.9241802,0.00017438292,0.07435687,0.000140951,0.00051474746,0.00003982169,0.00021135267,0.000118155105,0.0002635113],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99728507,0.00025968582,0.0006501422,0.0009207727,0.00042702607,0.0004572762],"domain_scores_gemma":[0.99829286,0.00021282177,0.00027361276,0.00066538114,0.00012614568,0.00042916214],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.000667126,0.0005567053,0.0010976334,0.0011267563,0.00004487571,0.00009524972,0.0003298488,0.00031498758,0.00006346811],"category_scores_gemma":[0.0003345178,0.0004159748,0.00082058785,0.000637662,0.00027383433,0.000052977844,0.00061344483,0.0034691175,0.000002489908],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002527607,0.0010058585,0.03560933,0.015657522,0.0015846167,0.0022370182,0.00158506,0.03495347,0.03366137,0.00072123966,0.0020960788,0.8683608],"study_design_scores_gemma":[0.0007473804,0.00019571153,0.5704384,0.0042268983,0.00046628783,0.00008781257,0.000036003108,0.41379082,0.00054577657,0.008973815,0.00006726469,0.00042381888],"about_ca_topic_score_codex":0.00048347015,"about_ca_topic_score_gemma":0.0000028541763,"teacher_disagreement_score":0.867937,"about_ca_system_score_codex":0.00085860805,"about_ca_system_score_gemma":0.0013670471,"threshold_uncertainty_score":0.99982923},"labels":[],"label_agreement":null},{"id":"W4392058486","doi":"10.32920/25262749.v1","title":"Impact of Image Pre-processing Methods on Computed Tomography Radiomics Features in Chronic Obstructive Pulmonary Disease","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Toronto Metropolitan University","funders":"","keywords":"Thresholding; Image processing; Resampling; COPD; Artificial intelligence; Preprocessor; Medicine; Radiomics; Image segmentation; Pattern recognition (psychology); Computer science; Feature extraction; Feature (linguistics); Segmentation; Radiology; Image (mathematics); Internal medicine","score_opus":0.011330062945140593,"score_gpt":0.37208044242646976,"score_spread":0.36075037948132915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392058486","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9346939,0.027071007,0.02169241,0.002440994,0.0012304849,0.0017695652,0.00010624296,0.00043892697,0.010556468],"genre_scores_gemma":[0.9241802,0.00017438292,0.07435687,0.000140951,0.00051474746,0.00003982169,0.00021135267,0.000118155105,0.0002635113],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99728507,0.00025968582,0.0006501422,0.0009207727,0.00042702607,0.0004572762],"domain_scores_gemma":[0.99829286,0.00021282177,0.00027361276,0.00066538114,0.00012614568,0.00042916214],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.000667126,0.0005567053,0.0010976334,0.0011267563,0.00004487571,0.00009524972,0.0003298488,0.00031498758,0.00006346811],"category_scores_gemma":[0.0003345178,0.0004159748,0.00082058785,0.000637662,0.00027383433,0.000052977844,0.00061344483,0.0034691175,0.000002489908],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002527607,0.0010058585,0.03560933,0.015657522,0.0015846167,0.0022370182,0.00158506,0.03495347,0.03366137,0.00072123966,0.0020960788,0.8683608],"study_design_scores_gemma":[0.0007473804,0.00019571153,0.5704384,0.0042268983,0.00046628783,0.00008781257,0.000036003108,0.41379082,0.00054577657,0.008973815,0.00006726469,0.00042381888],"about_ca_topic_score_codex":0.00048347015,"about_ca_topic_score_gemma":0.0000028541763,"teacher_disagreement_score":0.867937,"about_ca_system_score_codex":0.00085860805,"about_ca_system_score_gemma":0.0013670471,"threshold_uncertainty_score":0.99982923},"labels":[],"label_agreement":null},{"id":"W4392100000","doi":"10.1148/rycan.230029","title":"Quantitative US Delta Radiomics to Predict Radiation Response in Individuals with Head and Neck Squamous Cell Carcinoma","year":2024,"lang":"en","type":"article","venue":"Radiology Imaging Cancer","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Sunnybrook Hospital; Health Sciences Centre; Institute for Clinical Evaluative Sciences; Sunnybrook Health Science Centre","funders":"Natural Sciences and Engineering Research Council of Canada; Terry Fox Foundation","keywords":"Radiomics; Medicine; Head and neck squamous-cell carcinoma; Radiation therapy; Basal cell; Head and neck; Nuclear medicine; Lymph node; Head and neck cancer; Internal medicine; Oncology; Radiology; Surgery","score_opus":0.010329222134360414,"score_gpt":0.31318321300837715,"score_spread":0.3028539908740167,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392100000","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9655019,0.017610427,0.00226125,0.013325544,0.0004052295,0.0005255255,0.000041766794,0.00011083192,0.00021752855],"genre_scores_gemma":[0.990779,0.0002578725,0.0055323043,0.002861588,0.00021153202,0.000096121345,0.00003556094,0.00006345447,0.0001626102],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.998117,0.00025676095,0.00033527176,0.0006096668,0.00020057852,0.00048070346],"domain_scores_gemma":[0.9988107,0.000579425,0.00006430558,0.0002287244,0.000047433536,0.00026938002],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008805016,0.00025200547,0.00046316825,0.0005907842,0.00008034228,0.00006456595,0.00011032794,0.00009183204,0.000034167504],"category_scores_gemma":[0.0003908992,0.00021005754,0.000047487683,0.00049222156,0.00023617891,0.000142688,0.00004592235,0.00066327915,0.000009265907],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015776339,0.00004223012,0.9735657,0.00017319148,0.00004829441,0.00051091897,0.0028762831,0.0016923305,0.0039256667,0.00013095675,0.00433987,0.011116913],"study_design_scores_gemma":[0.004043792,0.001059398,0.8490721,0.00038190486,0.00017188347,0.0011131559,0.00021864846,0.12678762,0.00036225197,0.000068149195,0.016394427,0.00032670095],"about_ca_topic_score_codex":0.0008261956,"about_ca_topic_score_gemma":0.000038461672,"teacher_disagreement_score":0.12509528,"about_ca_system_score_codex":0.00038593847,"about_ca_system_score_gemma":0.00047636047,"threshold_uncertainty_score":0.85658973},"labels":[],"label_agreement":null},{"id":"W4392156102","doi":"10.32739/uha.id.44352","title":"Brain imaging data collected for a quarter of a century is in artificial intelligence!","year":2024,"lang":"en","type":"article","venue":"üha","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Quarter (Canadian coin); Artificial intelligence; Computer science; History; Archaeology","score_opus":0.032854621874176294,"score_gpt":0.36043091428375723,"score_spread":0.3275762924095809,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392156102","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35483634,0.0100617455,0.30226204,0.31797794,0.0034333465,0.0028807027,0.0004942948,0.00044020513,0.007613391],"genre_scores_gemma":[0.99193585,0.000045171382,0.005390472,0.0019009697,0.00027295435,0.0000146710245,0.00015117535,0.000025106006,0.00026363053],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991052,0.000022842318,0.0002884899,0.00026633227,0.00013596832,0.00018117933],"domain_scores_gemma":[0.9993657,0.00024009318,0.000028089058,0.00027803716,0.00003000838,0.0000580717],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004756977,0.00007720861,0.00019219905,0.00018057658,0.000021020742,0.000030322453,0.00013679577,0.000031774212,0.00016952306],"category_scores_gemma":[0.0005607243,0.00006573843,0.000047943588,0.000332903,0.000059807637,0.000061785824,0.000050658953,0.00022633727,0.000009653957],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030574895,0.00026385396,0.0035707727,0.0010193301,0.00012616135,0.00022349441,0.0067146798,0.000018169878,0.01487269,0.0060594436,0.23078825,0.73603743],"study_design_scores_gemma":[0.00029304705,0.000084036656,0.0005393194,0.0005938687,0.000055889464,0.000042896136,0.0006144994,0.8840627,0.00089160504,0.0036367571,0.10907751,0.00010787261],"about_ca_topic_score_codex":0.000087848275,"about_ca_topic_score_gemma":0.000012578504,"teacher_disagreement_score":0.8840445,"about_ca_system_score_codex":0.000030631356,"about_ca_system_score_gemma":0.00012878829,"threshold_uncertainty_score":0.26807353},"labels":[],"label_agreement":null},{"id":"W4392193166","doi":"","title":"A Synthesis of Papers on Embolization","year":2011,"lang":"fr","type":"dissertation","venue":"theses.fr (ABES)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Embolization; Computer science; Engineering; Medicine; Radiology","score_opus":0.013766243367295991,"score_gpt":0.2836848451498416,"score_spread":0.2699186017825456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392193166","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34976265,0.0013613792,0.00017749834,0.00036596335,0.003557147,0.0006612568,0.00003420513,0.00010565935,0.64397424],"genre_scores_gemma":[0.99188495,0.0023450311,0.0006584847,0.00043118646,0.0010431019,0.00006794847,0.00030494996,0.00017664926,0.0030876847],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9967777,0.00031206262,0.0008685767,0.0006202888,0.00078405224,0.0006373289],"domain_scores_gemma":[0.99707603,0.0009968007,0.0006667375,0.00068444514,0.00021248554,0.00036346787],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00080878945,0.0005785845,0.0011747704,0.00042605886,0.00016016145,0.000029056797,0.00042193162,0.00055548316,0.004053326],"category_scores_gemma":[0.004246666,0.0005106594,0.00037929192,0.00036978553,0.00028741438,0.00008307211,0.000040623832,0.0010314434,0.00049816415],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012625043,0.0019090762,0.019083468,0.0059486977,0.0016528927,0.00021406813,0.035675302,0.0005291002,0.042435594,0.21756934,0.0005297475,0.67319024],"study_design_scores_gemma":[0.008807518,0.0038706297,0.23367168,0.085130855,0.01453256,0.000269744,0.07640833,0.04182658,0.30819198,0.0054080724,0.21644178,0.005440285],"about_ca_topic_score_codex":0.0035066055,"about_ca_topic_score_gemma":0.00008092867,"teacher_disagreement_score":0.66774994,"about_ca_system_score_codex":0.00014974861,"about_ca_system_score_gemma":0.0002560636,"threshold_uncertainty_score":0.9997345},"labels":[],"label_agreement":null},{"id":"W4392241449","doi":"10.3390/radiation4010005","title":"Deep Texture Analysis—Enhancing CT Radiomics Features for Prediction of Head and Neck Cancer Treatment Outcomes: A Machine Learning Approach","year":2024,"lang":"en","type":"article","venue":"Radiation","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Health Sciences Centre; Toronto Metropolitan University; Sunnybrook Health Science Centre","funders":"Natural Sciences and Engineering Research Council of Canada; Terry Fox Research Institute; University of Toronto; Canadian Institutes of Health Research; Terry Fox Foundation","keywords":"Radiomics; Receiver operating characteristic; Artificial intelligence; Support vector machine; Head and neck cancer; Medicine; Computer science; Classifier (UML); Radiation treatment planning; Pattern recognition (psychology); Head and neck; Machine learning; Cancer; Radiology; Radiation therapy; Internal medicine; Surgery","score_opus":0.011111413740578752,"score_gpt":0.302917550051129,"score_spread":0.2918061363105503,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392241449","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.80437964,0.022057367,0.16985418,0.0019304467,0.00036717963,0.00086054223,0.00008479673,0.00017941602,0.00028642628],"genre_scores_gemma":[0.992043,0.0014745231,0.0046358746,0.0001092269,0.0002781221,0.00007959589,0.0006414654,0.00003087041,0.00070730137],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99904424,0.0000396086,0.00027223548,0.0003025401,0.00017134224,0.00017003405],"domain_scores_gemma":[0.9995211,0.00013442473,0.00009374066,0.00011801056,0.00003468682,0.00009804982],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025420266,0.00015861538,0.00042158083,0.0003341341,0.000090908296,0.000043230815,0.000031956257,0.00006356701,0.000013216287],"category_scores_gemma":[0.00015804825,0.0001179997,0.00019555441,0.00038104405,0.00003112691,0.000081759485,0.000008500725,0.00023275825,4.1532832e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000152785,0.0001751446,0.55451167,0.0009277441,0.0033508271,0.000013072339,0.0032476077,0.06333085,0.0029940028,0.000467469,0.00025903858,0.37056983],"study_design_scores_gemma":[0.0012416866,0.00021551522,0.16305448,0.00008159834,0.0017047898,0.000030385532,0.00006197043,0.8291768,0.00018172085,0.000025723675,0.0041477634,0.00007761201],"about_ca_topic_score_codex":0.00043037665,"about_ca_topic_score_gemma":0.00005850783,"teacher_disagreement_score":0.7658459,"about_ca_system_score_codex":0.0002251396,"about_ca_system_score_gemma":0.00007099539,"threshold_uncertainty_score":0.4811888},"labels":[],"label_agreement":null},{"id":"W4392376600","doi":"10.3991/ijoe.v20i04.45429","title":"The Role of Artificial Intelligence in the Diagnosis of Neoplastic Diseases: A Systematic and Bibliometric Review","year":2024,"lang":"en","type":"article","venue":"International Journal of Online and Biomedical Engineering (iJOE)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Artificial intelligence; Computer science; Management science; Medicine; Engineering","score_opus":0.009949731993055919,"score_gpt":0.3148784795199555,"score_spread":0.3049287475268996,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392376600","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4737523,0.48580483,0.014910753,0.023944754,0.0011317579,0.0003874792,0.000038872793,0.0000150238475,0.0000142451845],"genre_scores_gemma":[0.94735396,0.0516337,0.0005865752,0.0001415895,0.00026563214,0.0000047480453,0.0000044924773,0.0000069085395,0.0000024143117],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984558,0.00003788163,0.000721567,0.00007403679,0.00062298524,0.00008770162],"domain_scores_gemma":[0.9980559,0.0015150371,0.00014715121,0.000063852145,0.00012880642,0.0000892793],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009733726,0.00007859717,0.0003070712,0.0021613354,0.000012262955,0.000035459936,0.00020303916,0.000029685802,0.000007665515],"category_scores_gemma":[0.003638008,0.000038078964,0.000086967564,0.0024814038,0.000119140495,0.00004953112,0.000040368723,0.00031131416,2.7863453e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012126727,0.0007955546,0.006410812,0.038879745,0.00097597414,0.000752431,0.00071115827,0.00022988307,0.0016137252,0.004684797,0.0005130527,0.9443116],"study_design_scores_gemma":[0.0007777719,0.0012242772,0.02876086,0.1879953,0.0015130808,0.0046835924,0.0011759034,0.75443906,0.00019160802,0.0022487857,0.016710788,0.0002790006],"about_ca_topic_score_codex":0.0000103654365,"about_ca_topic_score_gemma":5.6832715e-7,"teacher_disagreement_score":0.9440326,"about_ca_system_score_codex":0.00001781842,"about_ca_system_score_gemma":0.000080954036,"threshold_uncertainty_score":0.4355298},"labels":[],"label_agreement":null},{"id":"W4392391571","doi":"10.5194/gmd-2023-151-rc3","title":"Comment on gmd-2023-151","year":2024,"lang":"en","type":"peer-review","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Royal Military College of Canada; Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Environmental science; Statistics; Mathematics","score_opus":0.027310287240598655,"score_gpt":0.3640448576970724,"score_spread":0.33673457045647376,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392391571","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000001622159,0.035524867,0.00011195812,0.6717981,0.0045363707,0.00043735065,0.000035905174,0.00015673354,0.2873971],"genre_scores_gemma":[0.000012993046,0.00986391,0.000594538,0.3706252,0.0013056911,0.00003301341,0.0010074364,0.00006692443,0.6164903],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978033,0.000056658788,0.00045429898,0.0005504337,0.00079178566,0.00034353035],"domain_scores_gemma":[0.9987418,0.00015822114,0.00008917169,0.0006234848,0.00008003191,0.00030726462],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00071009685,0.00037729027,0.0009431336,0.00019196044,0.000047597176,0.00004582103,0.00020414156,0.00021436249,0.0077226115],"category_scores_gemma":[0.0005152812,0.00025357906,0.00037651142,0.00019811273,0.000067157074,0.0000111771315,0.00013574673,0.002375191,0.0033011017],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000072639223,0.00007263083,0.0000032150867,0.0075184,0.0001735525,0.0002673419,0.000009460538,6.4003854e-7,0.000001806343,0.0010392108,0.93869615,0.052210335],"study_design_scores_gemma":[0.00032852346,0.00019958906,0.000007974767,0.024569154,0.0007188796,0.000097563854,0.000004795221,0.0007044599,0.000004139682,0.00015935325,0.9729682,0.00023731857],"about_ca_topic_score_codex":0.00022391003,"about_ca_topic_score_gemma":0.0000043997593,"teacher_disagreement_score":0.3290932,"about_ca_system_score_codex":0.00017587912,"about_ca_system_score_gemma":0.00019553855,"threshold_uncertainty_score":0.99999166},"labels":[],"label_agreement":null},{"id":"W4392402197","doi":"10.1186/s12967-024-05018-9","title":"Conditional generative adversarial network driven radiomic prediction of mutation status based on magnetic resonance imaging of breast cancer","year":2024,"lang":"en","type":"article","venue":"Journal of Translational Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lawson Health Research Institute; Children’s Health Research Institute; University of Winnipeg; Western University","funders":"Canadian Institutes of Health Research; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Breast Cancer Society of Canada","keywords":"Radiogenomics; Artificial intelligence; Computer science; Deep learning; Receiver operating characteristic; Computational biology; Magnetic resonance imaging; Breast cancer; Pattern recognition (psychology); Machine learning; Bioinformatics; Medicine; Genetics; Biology; Cancer; Radiomics; Radiology","score_opus":0.009024295515271267,"score_gpt":0.28578550857655666,"score_spread":0.27676121306128537,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392402197","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30790725,0.08517729,0.4618813,0.12888195,0.010873694,0.0014668629,0.0015357274,0.00010427985,0.002171649],"genre_scores_gemma":[0.9914843,0.00033064603,0.004975438,0.00044110217,0.002565784,0.0000042478164,0.0001407924,0.000022184706,0.000035539597],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978061,0.000098044235,0.000832631,0.0001583545,0.000934775,0.00017010607],"domain_scores_gemma":[0.99860334,0.00045381451,0.00031555936,0.00007921952,0.0004018808,0.00014616872],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006002522,0.00014104784,0.00043483873,0.00037290851,0.00004463523,0.000006405274,0.00006624724,0.00005358605,0.00059646514],"category_scores_gemma":[0.00013995402,0.00010659658,0.0001482141,0.00033019995,0.00028498986,0.00013204126,0.0000033925037,0.00045093353,6.3950006e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.006385541,0.00045840122,0.19606188,0.0009181427,0.0005583247,0.00046516035,0.0025097667,0.52956843,0.048880298,0.0050781947,0.01949812,0.18961775],"study_design_scores_gemma":[0.005363503,0.0007432173,0.37069544,0.0035199455,0.0004644979,0.00036304852,0.000047098456,0.6154984,0.00019588922,0.0008132733,0.0022219922,0.00007365337],"about_ca_topic_score_codex":0.000038859052,"about_ca_topic_score_gemma":0.0000017763568,"teacher_disagreement_score":0.683577,"about_ca_system_score_codex":0.00010809946,"about_ca_system_score_gemma":0.0006029794,"threshold_uncertainty_score":0.6530875},"labels":[],"label_agreement":null},{"id":"W4392450902","doi":"10.1007/978-981-97-1335-6","title":"Proceedings of 2023 International Conference on Medical Imaging and Computer-Aided Diagnosis (MICAD 2023)","year":2024,"lang":"en","type":"book","venue":"Lecture notes in electrical engineering","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Rheinische Friedrich-Wilhelms-Universität Bonn; Peking University; Khalifa University of Science, Technology and Research; University of New South Wales; Jiangnan University; Beihang University; Universitat Pompeu Fabra; Central South University; King's College London; Vanderbilt University; Kwantlen Polytechnic University; University of Toledo; Zhejiang University","keywords":"Medical physics; Medicine","score_opus":0.006196837697502185,"score_gpt":0.25428390308353105,"score_spread":0.24808706538602887,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392450902","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.047476154,0.07150741,0.40879247,0.13733657,0.016325789,0.0068918183,0.00021266215,0.0029184027,0.3085387],"genre_scores_gemma":[0.9246749,0.014920022,0.023599094,0.006620654,0.01159039,0.00031642988,0.00046358234,0.00084661087,0.016968274],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99757,0.000008571155,0.0005603682,0.0006168877,0.0008283624,0.00041581635],"domain_scores_gemma":[0.99875104,0.0006378606,0.00011009111,0.00012048033,0.0001101953,0.00027033078],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.00034269973,0.00041771875,0.0007906719,0.0007816563,0.000020692814,0.000065457214,0.0002709999,0.00043462892,0.00017555192],"category_scores_gemma":[0.0017769746,0.0003699782,0.00014684601,0.0003546297,0.000102449376,0.00004425835,0.00014859704,0.0032018656,0.000011052163],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031592752,0.0004751034,0.00500957,0.004930053,0.0011722668,0.0022274456,0.000588119,0.0041045207,0.0043593273,0.050591253,0.038378943,0.8878475],"study_design_scores_gemma":[0.00079939136,0.00019654873,0.00041314084,0.005438202,0.00012477276,0.0003171501,0.0000010410849,0.97239894,0.0003027725,0.0025179607,0.017103054,0.00038702152],"about_ca_topic_score_codex":0.00002064248,"about_ca_topic_score_gemma":0.0000014123511,"teacher_disagreement_score":0.96829444,"about_ca_system_score_codex":0.00032490026,"about_ca_system_score_gemma":0.00023080624,"threshold_uncertainty_score":0.9998752},"labels":[],"label_agreement":null},{"id":"W4392499120","doi":"10.3390/cancers16051076","title":"The Convergence of Radiology and Genomics: Advancing Breast Cancer Diagnosis with Radiogenomics","year":2024,"lang":"en","type":"article","venue":"Cancers","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network","funders":"Medical Research Council; South African Medical Research Council; National Research Foundation","keywords":"Radiogenomics; Medicine; Precision medicine; Context (archaeology); Disease; Intensive care medicine; Breast cancer; Bioinformatics; Cancer; Pathology; Internal medicine; Radiomics; Biology; Radiology","score_opus":0.005569263858952556,"score_gpt":0.26598512806763946,"score_spread":0.2604158642086869,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392499120","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94884884,0.04207787,0.001009029,0.0068187374,0.0006943495,0.00021262134,0.00003409526,0.000039164872,0.00026529253],"genre_scores_gemma":[0.95932764,0.038940784,0.0006469557,0.0005522934,0.00027488533,0.00008427859,0.0000029738098,0.00002817388,0.00014204648],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992969,0.000021637465,0.00016093501,0.00021100507,0.00008886565,0.00022063445],"domain_scores_gemma":[0.999444,0.00020659938,0.000048305228,0.00014220053,0.00003747247,0.00012143104],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022089834,0.000101252066,0.00021065155,0.000045288834,0.00008574329,0.000019073945,0.00007602629,0.000035121557,0.000060522845],"category_scores_gemma":[0.000039662187,0.000062125095,0.00003799677,0.00012439956,0.0004112144,0.00003835392,0.00002277668,0.00022711043,0.0000012730928],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00080666464,0.000015017971,0.41896415,0.00115783,0.0013026566,0.0002713977,0.0031242527,0.008673589,0.018421583,0.0036250115,0.027674513,0.5159633],"study_design_scores_gemma":[0.0037361674,0.000712787,0.086816825,0.0026234088,0.0011740116,0.005534379,0.001954341,0.31324044,0.0050704177,0.00055167463,0.57778996,0.00079558184],"about_ca_topic_score_codex":0.0005773788,"about_ca_topic_score_gemma":0.000050556824,"teacher_disagreement_score":0.55011547,"about_ca_system_score_codex":0.00053727144,"about_ca_system_score_gemma":0.00070224545,"threshold_uncertainty_score":0.25333878},"labels":[],"label_agreement":null},{"id":"W4392509442","doi":"10.1007/978-3-031-54806-2_13","title":"3d U-Net with ROI Segmentation of Kidneys and Masses in CT Scans","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Segmentation; Artificial intelligence; Computer vision; Computer graphics (images)","score_opus":0.008007707190731995,"score_gpt":0.2659208682364771,"score_spread":0.2579131610457451,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392509442","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016303837,0.0015234735,0.9704554,0.00306956,0.0005869141,0.00049288257,0.000007288638,0.00004830245,0.007512342],"genre_scores_gemma":[0.7621843,0.00027025884,0.23458107,0.0018462877,0.00031204487,0.0000059674485,0.00002298002,0.000051705552,0.0007253897],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99863964,0.000009386603,0.00024501383,0.00048430127,0.00042364022,0.00019803685],"domain_scores_gemma":[0.9994083,0.00015033584,0.00008718886,0.00020673485,0.0000466906,0.000100717494],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037948886,0.00019144795,0.0003476457,0.0005021463,0.000029487735,0.00005679202,0.0001559225,0.000060291684,0.00002337909],"category_scores_gemma":[0.000075050615,0.00014004072,0.000023908213,0.0002581973,0.00055345014,0.00007062223,0.000110699315,0.0006427921,0.0000018353198],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000054550143,0.00004829913,0.016471146,0.0010399284,0.000050198054,0.0009017124,0.0014151168,0.017915573,0.0015056658,0.0021813181,0.00007003091,0.9583465],"study_design_scores_gemma":[0.001966871,0.00094027485,0.0045699165,0.009807078,0.00014946125,0.0010434592,0.0000039318265,0.9512139,0.002035515,0.024388492,0.0031981529,0.00068294385],"about_ca_topic_score_codex":0.00008553342,"about_ca_topic_score_gemma":0.000043080705,"teacher_disagreement_score":0.95766354,"about_ca_system_score_codex":0.000096311865,"about_ca_system_score_gemma":0.00028399302,"threshold_uncertainty_score":0.5710695},"labels":[],"label_agreement":null},{"id":"W4392544796","doi":"10.1093/ibd/izae030","title":"AI-luminating Artificial Intelligence in Inflammatory Bowel Diseases: A Narrative Review on the Role of AI in Endoscopy, Histology, and Imaging for IBD","year":2024,"lang":"en","type":"review","venue":"Inflammatory Bowel Diseases","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Inflammatory bowel disease; Medicine; Context (archaeology); Narrative review; Endoscopy; Crohn's disease; Artificial intelligence; Disease; Pathology; Intensive care medicine; Radiology; Computer science","score_opus":0.016361296361270775,"score_gpt":0.3448715988778479,"score_spread":0.32851030251657715,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392544796","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010089773,0.9926083,0.000044718814,0.0023408714,0.00032615714,0.003327937,0.00013080509,0.00008115875,0.00013106462],"genre_scores_gemma":[0.0052819443,0.9904726,0.00008254799,0.0018826341,0.00035458987,0.0015914452,0.00014625587,0.00014379321,0.000044169203],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.99555254,0.0005722114,0.001921466,0.00089483685,0.00047279822,0.0005861443],"domain_scores_gemma":[0.9969434,0.0013298081,0.0006474766,0.00062230404,0.00013460098,0.0003223883],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010297066,0.0007459438,0.0020483779,0.0007194881,0.00013783271,0.000083674844,0.00043474723,0.00019205015,0.000045656834],"category_scores_gemma":[0.0038366313,0.0005265018,0.00065388833,0.0004017558,0.00077003875,0.00016812123,0.00022447864,0.001643553,0.000016274815],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019558758,0.00030364707,0.004919812,0.16785343,0.00025792536,0.00078811176,0.0014516051,0.000011549378,0.000008045884,0.008582856,0.0025333022,0.81309414],"study_design_scores_gemma":[0.00075257185,0.00023439311,0.001749749,0.54419136,0.005756961,0.00015643795,0.002810872,0.014003553,0.0000072520043,0.013466943,0.41541794,0.0014519749],"about_ca_topic_score_codex":0.000032600045,"about_ca_topic_score_gemma":0.000019089885,"teacher_disagreement_score":0.81164217,"about_ca_system_score_codex":0.00036758045,"about_ca_system_score_gemma":0.0012318254,"threshold_uncertainty_score":0.99971867},"labels":[],"label_agreement":null},{"id":"W4392588478","doi":"10.1016/j.gimo.2024.101614","title":"P710: Phenome-wide association study (PheWAS) for the Canadian HostSeq Biobank","year":2024,"lang":"en","type":"article","venue":"Genetics in Medicine Open","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Hospital for Sick Children; Ontario Institute for Cancer Research; Women's College Hospital; University Health Network; University of Toronto; McGill University; Baycrest Hospital; William Osler Health System; Lunenfeld-Tanenbaum Research Institute","funders":"","keywords":"Phenome; Biobank; Association (psychology); Biorepository; Biology; Computational biology; Medicine; Bioinformatics; Genetics; Psychology; Genome; Gene","score_opus":0.03751210535942534,"score_gpt":0.3778744752006622,"score_spread":0.34036236984123686,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392588478","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29937524,0.015176961,0.00418138,0.6321038,0.0068309368,0.01157483,0.00003549731,0.00014058514,0.030580759],"genre_scores_gemma":[0.98254555,0.00045247652,0.00094550784,0.008684291,0.0011168015,0.00022653249,0.00004431576,0.00005901852,0.005925511],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99819684,0.000093686605,0.00038278414,0.00039554542,0.00047373347,0.00045741972],"domain_scores_gemma":[0.99793434,0.001202451,0.00007041415,0.00040806748,0.00011389458,0.00027083882],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0035017228,0.0001785948,0.0003954437,0.00025496667,0.0002309829,0.00018296612,0.00053347467,0.000099951365,0.00023360545],"category_scores_gemma":[0.0024249654,0.000115994255,0.000052942287,0.00048850273,0.00009333861,0.000045653247,0.000120913435,0.0006298663,0.000032248598],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000079258265,0.00015845601,0.6413273,0.00019091122,0.00047966346,0.0002722558,0.005957723,0.0003245411,0.00013526288,0.0006744333,0.26411343,0.08628675],"study_design_scores_gemma":[0.003970224,0.0009460619,0.23916824,0.00054758845,0.0005235194,0.000015168173,0.002504452,0.047479045,0.000019128509,0.0012516952,0.7033227,0.00025216307],"about_ca_topic_score_codex":0.056852758,"about_ca_topic_score_gemma":0.088015415,"teacher_disagreement_score":0.6831703,"about_ca_system_score_codex":0.00069239916,"about_ca_system_score_gemma":0.0006551865,"threshold_uncertainty_score":0.9494277},"labels":[],"label_agreement":null},{"id":"W4392631937","doi":"10.1136/ijgc-2024-esgo.368","title":"680 Is there a way to optimize the performance of preoperative diagnosis of patients with endometrial cancer on imaging? The artificial intelligence response","year":2024,"lang":"en","type":"article","venue":"International Journal of Gynecological Cancer","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre","funders":"","keywords":"Endometrial cancer; Sørensen–Dice coefficient; Segmentation; Artificial intelligence; Computer science; Pipeline (software); Cervical cancer; Stage (stratigraphy); Medicine; Radiology; Cancer; Image segmentation; Internal medicine","score_opus":0.02113890227282735,"score_gpt":0.3416441317647595,"score_spread":0.32050522949193216,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392631937","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96554935,0.00096573454,0.000696501,0.031300794,0.0010754116,0.00027650272,0.000038715905,0.0000050650133,0.00009190528],"genre_scores_gemma":[0.99624515,0.00073009165,0.00035229526,0.0021403125,0.00039583657,0.000054794175,9.734376e-7,0.000011479831,0.000069060545],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99825853,0.00014197605,0.00049899734,0.00014835323,0.0008175592,0.0001345914],"domain_scores_gemma":[0.996743,0.0020815816,0.00026069113,0.0001048462,0.00073509576,0.00007477597],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008503003,0.000120228106,0.00027310284,0.00016480742,0.00004982451,0.000043033044,0.00039415748,0.000035064237,0.0013758152],"category_scores_gemma":[0.001741386,0.0000497874,0.00013761081,0.00028084387,0.00023825139,0.00007925888,0.00006225476,0.0005186207,0.000003216732],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.029250082,0.00071373954,0.5184125,0.00005703553,0.0012524733,0.00012179185,0.0038219828,0.03186228,0.000575809,0.0006234134,0.002869905,0.410439],"study_design_scores_gemma":[0.0017166731,0.0050750254,0.930163,0.0018239109,0.00034031278,0.000035666573,0.0004566191,0.03239944,0.015803866,0.0002311238,0.011745643,0.00020867321],"about_ca_topic_score_codex":0.000047204507,"about_ca_topic_score_gemma":0.000006442188,"teacher_disagreement_score":0.41175058,"about_ca_system_score_codex":0.00021150452,"about_ca_system_score_gemma":0.00021447266,"threshold_uncertainty_score":0.99953705},"labels":[],"label_agreement":null},{"id":"W4392654434","doi":"10.1136/heartjnl-2024-bscmr.9","title":"11 Visual quality control of assessment of AI-assisted high-volume CMR segmentation in the UK Biobank","year":2024,"lang":"en","type":"article","venue":"Abstracts","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Circle Cardiovascular Imaging","funders":"","keywords":"Computer science; Visual inspection; Outlier; Artificial intelligence; Image quality; Quality assurance; Segmentation; Biobank; Reliability (semiconductor); Visualization; Image processing; Computer vision; Data mining; Medicine; Image (mathematics); Pathology","score_opus":0.016620108930489305,"score_gpt":0.3900369164801031,"score_spread":0.37341680754961376,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392654434","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98929477,0.00016008559,0.0032073301,0.0060079526,0.00025528102,0.00025304744,0.000009583835,0.000020199373,0.00079175463],"genre_scores_gemma":[0.9982415,0.000014438814,0.00081669615,0.0007128322,0.000081620936,0.000010123044,0.000046529025,0.000010124138,0.000066122426],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9986747,0.0001241605,0.0005128597,0.00015309041,0.0003978181,0.00013740019],"domain_scores_gemma":[0.9992734,0.0003465698,0.00013182938,0.00014734689,0.00005279537,0.00004802494],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013602348,0.00008742548,0.00026572318,0.00010067854,0.000018996085,0.000021663982,0.000077148325,0.00005501486,0.00009381755],"category_scores_gemma":[0.00023425494,0.000059383307,0.00007276726,0.0001855537,0.00008436181,0.00005486045,0.00001062459,0.00036102452,0.0000042947627],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014404971,0.001147492,0.6284885,0.0015241662,0.00030323066,0.0002710002,0.0015246866,0.0012504804,0.27829435,0.008155308,0.0030048112,0.07589195],"study_design_scores_gemma":[0.0012197203,0.00014659231,0.98662454,0.00024254168,0.0000882072,0.000016247646,0.00023873182,0.0094249835,0.0013436329,0.00014475278,0.00045343308,0.00005661143],"about_ca_topic_score_codex":0.0015961285,"about_ca_topic_score_gemma":0.000042923868,"teacher_disagreement_score":0.3581361,"about_ca_system_score_codex":0.000052431424,"about_ca_system_score_gemma":0.00014719045,"threshold_uncertainty_score":0.2421581},"labels":[],"label_agreement":null},{"id":"W4392785829","doi":"10.1016/j.acra.2024.01.031","title":"Contrast Enhanced CT Radiogenomics in a Retrospective NSCLC Cohort: Models, Attempted Validation of a Published Model and the Relevance of the Clinical Context","year":2024,"lang":"en","type":"article","venue":"Academic Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Princess Margaret Cancer Centre; University Health Network","funders":"","keywords":"Radiogenomics; Context (archaeology); Contrast (vision); Relevance (law); Retrospective cohort study; Clinical significance; Medicine; Medical physics; Radiomics; Radiology; Cohort; Computer science; Internal medicine; Artificial intelligence; Geography; Political science","score_opus":0.018377985539890423,"score_gpt":0.31985634796144397,"score_spread":0.30147836242155357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392785829","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97298926,0.005939033,0.0078315595,0.011083592,0.00037472005,0.00081559183,0.0000115168705,0.00002646649,0.000928284],"genre_scores_gemma":[0.9917912,0.0065768175,0.00032704204,0.0009669348,0.00014057431,0.00003534609,0.000010188203,0.000023681765,0.00012821837],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99762005,0.0004943564,0.0010131982,0.00042945766,0.00020289009,0.00024003616],"domain_scores_gemma":[0.9976387,0.0015476157,0.0003128945,0.00034579774,0.00008398422,0.000070999515],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034506528,0.000155654,0.0008811549,0.00019362188,0.000039547376,0.000009064739,0.00027283153,0.00022554705,0.0000068528875],"category_scores_gemma":[0.003919946,0.00008989329,0.00016925758,0.0004868321,0.0013702541,0.000119329416,0.000080981685,0.0018927961,6.510583e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0052297334,0.0002288657,0.4327083,0.0006734967,0.0021560965,0.000053864707,0.0117822485,0.029208764,0.09111077,0.36175135,0.011872289,0.05322425],"study_design_scores_gemma":[0.005847645,0.000107302214,0.030817332,0.00046446596,0.0002711061,0.00028877883,0.00013654679,0.9355452,0.0014106678,0.024626493,0.00035260816,0.00013187354],"about_ca_topic_score_codex":0.00013543104,"about_ca_topic_score_gemma":0.000006421518,"teacher_disagreement_score":0.9063364,"about_ca_system_score_codex":0.00008807557,"about_ca_system_score_gemma":0.0002326016,"threshold_uncertainty_score":0.82233626},"labels":[],"label_agreement":null},{"id":"W4392826795","doi":"10.1016/j.ijrobp.2024.01.103","title":"Developing Machine Learning Algorithms Incorporating Patient Reported Outcomes to Predict Disease Progression in Head and Neck Cancers","year":2024,"lang":"en","type":"article","venue":"International Journal of Radiation Oncology*Biology*Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; Princess Margaret Cancer Centre; University of Toronto","funders":"","keywords":"Medicine; Head and neck; Head and neck cancer; Disease; Machine learning; Oncology; Algorithm; Artificial intelligence; Internal medicine; Surgery; Cancer","score_opus":0.02007327497365244,"score_gpt":0.3680006166736511,"score_spread":0.3479273416999986,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392826795","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94931877,0.0014205037,0.030570893,0.016210558,0.0020112258,0.00028349852,0.000012840161,0.00006373227,0.00010797383],"genre_scores_gemma":[0.9751998,0.00037479264,0.022152819,0.0013594104,0.0007682086,0.000016677284,0.000071521245,0.000030205932,0.00002653928],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99821,0.00015713953,0.0008243566,0.00027462127,0.000332843,0.00020104588],"domain_scores_gemma":[0.9986029,0.0002800241,0.00052567467,0.000078371006,0.00026417256,0.0002488496],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000699241,0.00017248154,0.00040504299,0.00031345803,0.00006883386,0.000054933622,0.00013212973,0.000100720754,0.000009307122],"category_scores_gemma":[0.0014347801,0.00013899922,0.00010146757,0.00024320587,0.00011081899,0.00020067008,0.000089098656,0.00084274996,0.000002786179],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014954446,0.000053851247,0.60076183,0.000021240076,0.00016326197,0.00039550653,0.00042547678,0.001999814,0.00026937798,0.00101538,0.00007637871,0.3946683],"study_design_scores_gemma":[0.006452449,0.002073088,0.47550786,0.0026094206,0.00021183511,0.0007692474,0.00018256511,0.45781824,0.00029678253,0.007921815,0.045716997,0.00043969796],"about_ca_topic_score_codex":0.00007054152,"about_ca_topic_score_gemma":0.0000066145076,"teacher_disagreement_score":0.4558184,"about_ca_system_score_codex":0.0010571259,"about_ca_system_score_gemma":0.0009848785,"threshold_uncertainty_score":0.5668224},"labels":[],"label_agreement":null},{"id":"W4392850630","doi":"10.1038/s42256-024-00807-9","title":"Foundation model for cancer imaging biomarkers","year":2024,"lang":"en","type":"article","venue":"Nature Machine Intelligence","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":171,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"National Cancer Institute; National Institutes of Health; Deutsche Forschungsgemeinschaft; European Commission","keywords":"Foundation (evidence); Medicine; Cancer; Medical physics; Oncology; Internal medicine; History; Archaeology","score_opus":0.013216732216401123,"score_gpt":0.36509031867862723,"score_spread":0.3518735864622261,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392850630","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0027542573,0.018224467,0.95126194,0.023524525,0.0014665482,0.00044669185,0.00002142237,0.0002918938,0.0020082558],"genre_scores_gemma":[0.97324216,0.0005538741,0.020550499,0.0031480622,0.0005044164,0.0000711152,0.00009424946,0.000057834593,0.0017777899],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987597,0.000015202433,0.00025477115,0.00042259827,0.00026574914,0.00028197703],"domain_scores_gemma":[0.99933314,0.00018022786,0.00003966397,0.00019809623,0.000114465096,0.00013441792],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043670536,0.00018259294,0.00020297586,0.00021128384,0.00009865106,0.00010506723,0.00014491442,0.0001258717,0.00015932007],"category_scores_gemma":[0.00045844537,0.00014387371,0.00015784372,0.00029624338,0.00008673746,0.00012689069,0.00003652235,0.0009705693,0.000022940198],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010384817,0.000035004134,0.0017679312,0.00044081928,0.00013958738,0.00003952796,0.00028327483,0.0032309187,0.0037673886,0.010791252,0.0065861293,0.9728143],"study_design_scores_gemma":[0.00012118971,0.000022812797,0.0001268386,0.00034756714,0.00011300865,0.00007100685,0.000017377195,0.9449968,0.001534327,0.005383329,0.047117915,0.00014785948],"about_ca_topic_score_codex":0.000092223694,"about_ca_topic_score_gemma":0.000013931515,"teacher_disagreement_score":0.97266644,"about_ca_system_score_codex":0.00013570425,"about_ca_system_score_gemma":0.00018386201,"threshold_uncertainty_score":0.58669996},"labels":[],"label_agreement":null},{"id":"W4392905914","doi":"10.32920/25413817","title":"Improving Interactive Segmentation Techniques in Medical Imaging","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Segmentation; Computer science; Feature (linguistics); Function (biology); Artificial intelligence; Net (polyhedron); Image segmentation; Computer vision; Pattern recognition (psychology); Mathematics","score_opus":0.007026015954259444,"score_gpt":0.34316200385759815,"score_spread":0.3361359879033387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392905914","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3843734,0.0062479973,0.2206877,0.14705256,0.007709067,0.004591962,0.000019344388,0.0037424727,0.2255755],"genre_scores_gemma":[0.96270496,0.00025129708,0.030243523,0.004397915,0.0008769764,0.00015782176,0.00013259378,0.00009534336,0.0011395569],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980344,0.000066062974,0.0004955206,0.0005731902,0.0005660023,0.000264788],"domain_scores_gemma":[0.99927145,0.000113170754,0.000107814696,0.00025611516,0.00005663562,0.00019482015],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.00087287073,0.0002507965,0.00042941998,0.00051574816,0.000022078706,0.000100893194,0.00016360066,0.00022381579,0.0005140421],"category_scores_gemma":[0.0007379136,0.00020515261,0.00013902079,0.0001434818,0.00008647702,0.000050122853,0.0009972107,0.0037525531,0.00003406856],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043420376,0.000095669864,0.0052135107,0.0011525075,0.00006711259,0.001445698,0.0006528465,0.0000076301185,0.003867063,0.0002931828,0.0027742449,0.9843871],"study_design_scores_gemma":[0.0011343465,0.000066720895,0.0018368578,0.010417252,0.00026236105,0.0007730298,0.0010411242,0.9619283,0.010100422,0.008752354,0.0030516197,0.0006356061],"about_ca_topic_score_codex":0.0012667615,"about_ca_topic_score_gemma":0.000023827975,"teacher_disagreement_score":0.98375154,"about_ca_system_score_codex":0.00039098278,"about_ca_system_score_gemma":0.00046063398,"threshold_uncertainty_score":0.9985458},"labels":[],"label_agreement":null},{"id":"W4392905953","doi":"10.32920/25413817.v1","title":"Improving Interactive Segmentation Techniques in Medical Imaging","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Segmentation; Computer science; Feature (linguistics); Function (biology); Artificial intelligence; Net (polyhedron); Image segmentation; Computer vision; Pattern recognition (psychology); Mathematics","score_opus":0.007026015954259444,"score_gpt":0.34316200385759815,"score_spread":0.3361359879033387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392905953","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3843734,0.0062479973,0.2206877,0.14705256,0.007709067,0.004591962,0.000019344388,0.0037424727,0.2255755],"genre_scores_gemma":[0.96270496,0.00025129708,0.030243523,0.004397915,0.0008769764,0.00015782176,0.00013259378,0.00009534336,0.0011395569],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980344,0.000066062974,0.0004955206,0.0005731902,0.0005660023,0.000264788],"domain_scores_gemma":[0.99927145,0.000113170754,0.000107814696,0.00025611516,0.00005663562,0.00019482015],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.00087287073,0.0002507965,0.00042941998,0.00051574816,0.000022078706,0.000100893194,0.00016360066,0.00022381579,0.0005140421],"category_scores_gemma":[0.0007379136,0.00020515261,0.00013902079,0.0001434818,0.00008647702,0.000050122853,0.0009972107,0.0037525531,0.00003406856],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043420376,0.000095669864,0.0052135107,0.0011525075,0.00006711259,0.001445698,0.0006528465,0.0000076301185,0.003867063,0.0002931828,0.0027742449,0.9843871],"study_design_scores_gemma":[0.0011343465,0.000066720895,0.0018368578,0.010417252,0.00026236105,0.0007730298,0.0010411242,0.9619283,0.010100422,0.008752354,0.0030516197,0.0006356061],"about_ca_topic_score_codex":0.0012667615,"about_ca_topic_score_gemma":0.000023827975,"teacher_disagreement_score":0.98375154,"about_ca_system_score_codex":0.00039098278,"about_ca_system_score_gemma":0.00046063398,"threshold_uncertainty_score":0.9985458},"labels":[],"label_agreement":null},{"id":"W4392954266","doi":"10.1177/08465371241241235","title":"Interventional Radiology is Now at the Confluence of Expertise, Innovation, and Artificial Intelligence","year":2024,"lang":"en","type":"editorial","venue":"Canadian Association of Radiologists Journal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Medicine; Confluence; Radiology; Interventional radiology","score_opus":0.01742399015609348,"score_gpt":0.3188149211980925,"score_spread":0.30139093104199904,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392954266","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.048963044,0.020410892,0.004513556,0.07619998,0.84634864,0.0007632761,0.0011746375,0.000041676452,0.0015842827],"genre_scores_gemma":[0.36299673,0.0071048536,0.0015273063,0.0032941147,0.601467,0.00004035891,0.0011366786,0.00016039524,0.022272542],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974579,0.00022016332,0.0011378702,0.00027647254,0.0005827395,0.0003248294],"domain_scores_gemma":[0.99635905,0.0008807458,0.0012474043,0.00018320524,0.0011087757,0.00022084481],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0026306217,0.00020466259,0.00063615124,0.0005514067,0.00016930551,0.000053531032,0.00025146492,0.0006511439,0.00033131836],"category_scores_gemma":[0.010845556,0.00015216548,0.00019249941,0.00036481905,0.00052710867,0.00004895584,0.00005116764,0.0017855479,0.00001273817],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004232863,0.000014080823,0.0027882673,0.00011843598,0.00042385986,0.000044561784,0.00034193436,0.000017737557,0.00015556067,0.0014007676,0.98664254,0.00800991],"study_design_scores_gemma":[0.00033914633,0.00036086896,0.0021905713,0.0007100605,0.00033406692,0.000555313,0.000092290924,0.001231092,0.0001484844,0.004813485,0.9890103,0.00021436048],"about_ca_topic_score_codex":0.0014064809,"about_ca_topic_score_gemma":0.002374675,"teacher_disagreement_score":0.3140337,"about_ca_system_score_codex":0.0016914201,"about_ca_system_score_gemma":0.0019586284,"threshold_uncertainty_score":0.99748653},"labels":[],"label_agreement":null},{"id":"W4392966801","doi":"10.1101/2024.03.15.24303032","title":"New implementation of data standards for AI in oncology. Experience from the EuCanImage project","year":2024,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Agencia Estatal de Investigación; Ministerio de Ciencia e Innovación; Euskal Herriko Unibertsitatea; Eusko Jaurlaritza; Generalitat de Catalunya; European Commission; Centres de Recerca de Catalunya","keywords":"Precision oncology; Medical physics; Computer science; Data science; Oncology; Medicine; Internal medicine; Cancer","score_opus":0.06891323366201042,"score_gpt":0.483450062649563,"score_spread":0.41453682898755256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392966801","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9331284,0.0024835092,0.024812303,0.033928305,0.0013338464,0.0022439363,0.0014188112,0.00006123322,0.00058964704],"genre_scores_gemma":[0.96154165,0.00044102932,0.033449695,0.0018072458,0.00094009674,0.0002007988,0.0013182381,0.00006512494,0.00023613815],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982816,0.000091290705,0.00047855638,0.000535837,0.00041468412,0.00019802676],"domain_scores_gemma":[0.9985948,0.0003063098,0.00016538196,0.00078440894,0.00008433061,0.00006472322],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015293575,0.00016230324,0.00042557745,0.00009747162,0.000028238308,0.00003990677,0.0005832978,0.000113751856,0.0001317674],"category_scores_gemma":[0.00075344875,0.000108454864,0.000076563156,0.00014192538,0.00009161478,0.00004550206,0.0010208999,0.0009797174,0.000001441227],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004107805,0.000112766,0.116907254,0.0012174915,0.00036345396,0.00013495104,0.027173497,0.000018508674,0.010597148,0.00043068358,0.19900516,0.6436283],"study_design_scores_gemma":[0.0051983986,0.0005871847,0.10066117,0.0029012982,0.0008872258,0.00002732756,0.008564022,0.038967997,0.0031039678,0.00835955,0.83022785,0.00051398994],"about_ca_topic_score_codex":0.008260649,"about_ca_topic_score_gemma":0.0007423119,"teacher_disagreement_score":0.6431143,"about_ca_system_score_codex":0.00018218218,"about_ca_system_score_gemma":0.0030530996,"threshold_uncertainty_score":0.9983434},"labels":[],"label_agreement":null},{"id":"W4393032454","doi":"10.1183/23120541.00968-2023","title":"Enhancing COPD classification using combined quantitative computed tomography and texture-based radiomics: a CanCOLD cohort study","year":2024,"lang":"en","type":"article","venue":"ERJ Open Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Royal Victoria Hospital; McGill University Health Centre; University of British Columbia; Toronto Metropolitan University","funders":"University of Toronto; Dalhousie University; University of Ottawa; Natural Sciences and Engineering Research Council of Canada; Queen's University; Johns Hopkins University; McGill University; American Thoracic Society","keywords":"Medicine; Radiomics; Cohort; COPD; Texture (cosmology); Radiology; Medical physics; Artificial intelligence; Internal medicine","score_opus":0.10523573684120527,"score_gpt":0.45864639700017706,"score_spread":0.3534106601589718,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393032454","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97622454,0.0011862986,0.011526215,0.004178303,0.00031130319,0.0044884575,0.000007682408,0.00010821282,0.0019690099],"genre_scores_gemma":[0.9884788,0.000025927147,0.010519872,0.00023690626,0.00013364152,0.00014583542,0.000044705015,0.000053344527,0.0003609912],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969982,0.0006322506,0.00039152702,0.00069530203,0.00082716224,0.00045554707],"domain_scores_gemma":[0.99801373,0.00090874097,0.00005580867,0.00039569044,0.0003242853,0.0003017642],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005487918,0.00018146295,0.00047089672,0.00071088265,0.00040805739,0.00069525297,0.0003262403,0.00008655732,0.000075405645],"category_scores_gemma":[0.00061219954,0.00015358628,0.000062713116,0.0013622503,0.00032595725,0.00017582183,0.00023627937,0.0012418231,0.000017178707],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017651384,0.0016615742,0.8564548,0.0012449797,0.0013544888,0.0014451027,0.005256779,0.00028690856,0.08733249,0.012610256,0.0106349215,0.0199526],"study_design_scores_gemma":[0.003054715,0.0011346525,0.20344996,0.0010123029,0.00013541896,0.000045761797,0.0020048385,0.7854656,0.0006945299,0.0002377762,0.002531298,0.00023315214],"about_ca_topic_score_codex":0.0028256387,"about_ca_topic_score_gemma":0.00018641051,"teacher_disagreement_score":0.78517866,"about_ca_system_score_codex":0.00026282112,"about_ca_system_score_gemma":0.0007610076,"threshold_uncertainty_score":0.67043406},"labels":[],"label_agreement":null},{"id":"W4393039554","doi":"10.1007/s13246-024-01408-x","title":"Semi-supervised learning towards automated segmentation of PET images with limited annotations: application to lymphoma patients","year":2024,"lang":"en","type":"article","venue":"Physical and Engineering Sciences in Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Spinal Cord Injury BC; University of British Columbia; BC Cancer Agency","funders":"Canadian Institutes of Health Research; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Dice; Artificial intelligence; Segmentation; Computer science; Cluster analysis; Machine learning; Supervised learning; Pattern recognition (psychology); Convolutional neural network; Sørensen–Dice coefficient; Image segmentation; Artificial neural network; Mathematics; Statistics","score_opus":0.006451226901158923,"score_gpt":0.2862585839268453,"score_spread":0.2798073570256864,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393039554","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98440945,0.00014780131,0.012927527,0.0018546324,0.00006796448,0.00020882499,0.0000013023524,0.00018349776,0.0001990026],"genre_scores_gemma":[0.9945994,0.000035442656,0.005064198,0.00012809366,0.00009044202,0.000028493365,0.00002427446,0.000011627322,0.000018000796],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99906194,0.00001601756,0.00018070276,0.00024630286,0.00033884938,0.00015617584],"domain_scores_gemma":[0.9996454,0.00012486093,0.000025736214,0.000062880696,0.000051260842,0.00008982631],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002711946,0.000111111665,0.00023104809,0.0002660613,0.000041903637,0.000018417046,0.00006026841,0.000014614585,0.000003119136],"category_scores_gemma":[0.00027880134,0.000073305426,0.000016773274,0.0009426013,0.00015650596,0.00010791883,0.000020434942,0.00013108582,0.0000016267871],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014640523,0.0004934811,0.064909026,0.002239774,0.00011751311,0.00007124314,0.014086009,0.18779711,0.26887617,0.0013402139,0.0006434504,0.4592796],"study_design_scores_gemma":[0.0006722528,0.0005525595,0.104452245,0.0007935308,0.000033090753,0.0000130669205,0.0002102138,0.8922732,0.00070010754,0.000027257423,0.00019238607,0.000080096775],"about_ca_topic_score_codex":0.0000960225,"about_ca_topic_score_gemma":5.4166935e-7,"teacher_disagreement_score":0.70447606,"about_ca_system_score_codex":0.000035651734,"about_ca_system_score_gemma":0.00003322582,"threshold_uncertainty_score":0.29893085},"labels":[],"label_agreement":null},{"id":"W4393071888","doi":"10.1158/1538-7445.am2024-2914","title":"Abstract 2914: AI/ML-driven discovery of CTHRC1, collagen triple helix repeat-containing 1, a novel proteoglycan for stroma + tumor targeting and delivery of 4-1BB costimulation","year":2024,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario","funders":"","keywords":"Stroma; Triple helix; Medicine; Proteoglycan; Cancer research; Chemistry; Immunology; Anatomy; Cartilage; Stereochemistry; Immunohistochemistry","score_opus":0.05112483774378429,"score_gpt":0.4076410583531972,"score_spread":0.3565162206094129,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393071888","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99014324,0.0028542306,0.0034805145,0.0017118672,0.00014053682,0.0013555371,0.00011119023,0.000029814611,0.000173052],"genre_scores_gemma":[0.996236,0.00017519547,0.0025598768,0.00006794307,0.0003224151,0.00017891036,0.000057879734,0.000045277335,0.00035646601],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99817634,0.000054254982,0.00044932222,0.00038666802,0.0005555549,0.00037789127],"domain_scores_gemma":[0.9986497,0.0005259612,0.000105918116,0.00018438752,0.0003963749,0.00013765387],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001552406,0.00012883973,0.00038373633,0.00029171788,0.000119570475,0.00007486997,0.00011292962,0.000065160144,0.000039922063],"category_scores_gemma":[0.0011470699,0.0001105558,0.000096145915,0.00033548195,0.00025161039,0.00019540163,0.00008376864,0.00043927252,7.656033e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014701557,0.00008921727,0.012903988,0.0031868976,0.00018539798,0.000052181404,0.001076638,0.00076871,0.9635923,0.00036515493,0.001819603,0.014489756],"study_design_scores_gemma":[0.01625495,0.00457585,0.08530343,0.015123097,0.00046124335,0.00010994813,0.004142951,0.6426183,0.20668943,0.0007675496,0.023076842,0.0008763831],"about_ca_topic_score_codex":0.0011582137,"about_ca_topic_score_gemma":0.000025175437,"teacher_disagreement_score":0.7569029,"about_ca_system_score_codex":0.00019551256,"about_ca_system_score_gemma":0.00075842417,"threshold_uncertainty_score":0.45083347},"labels":[],"label_agreement":null},{"id":"W4393084988","doi":"10.1158/1538-7445.am2024-3510","title":"Abstract 3510: A radiogenomic approach for triple-negative breast cancer risk stratification","year":2024,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Medicine; Breast cancer; Risk stratification; Cancer; Internal medicine; Oncology","score_opus":0.062313688167205714,"score_gpt":0.4315073901216721,"score_spread":0.3691937019544664,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393084988","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9265557,0.020868355,0.018344408,0.021247417,0.0011594945,0.004384293,0.0010681666,0.0003142277,0.0060579353],"genre_scores_gemma":[0.98911154,0.0029452355,0.0020386733,0.000101214195,0.001607384,0.001320037,0.000081245074,0.00006925992,0.0027254291],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980043,0.00010477582,0.00027005075,0.00056397624,0.00053348194,0.0005233827],"domain_scores_gemma":[0.9987417,0.00039548744,0.000050861865,0.0002889718,0.00025675684,0.0002662536],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017948084,0.00015118373,0.00026394997,0.00030152636,0.0002522849,0.00016263437,0.00018772243,0.000099880126,0.0004742913],"category_scores_gemma":[0.00034022832,0.00012040883,0.00013501967,0.0005345889,0.00026537542,0.0001125579,0.000030730513,0.0012287031,0.000023716877],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012278067,0.00024131208,0.004323848,0.0025513314,0.00077145506,0.000047562673,0.0037458965,0.0013555358,0.16496062,0.0015777928,0.06921538,0.74998146],"study_design_scores_gemma":[0.009413315,0.0005818023,0.16070522,0.002664377,0.00072174217,0.00026537562,0.0034505604,0.7374551,0.024764646,0.004008897,0.054818723,0.0011502119],"about_ca_topic_score_codex":0.003081556,"about_ca_topic_score_gemma":0.000028602823,"teacher_disagreement_score":0.7488313,"about_ca_system_score_codex":0.0006348699,"about_ca_system_score_gemma":0.0010638487,"threshold_uncertainty_score":0.5338172},"labels":[],"label_agreement":null},{"id":"W4393088906","doi":"10.1158/1538-7445.am2024-2311","title":"Abstract 2311: Precise assessment of cancer cell growth and survival by artificial intelligence","year":2024,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BGC Engineering (Canada)","funders":"","keywords":"Cancer; Cancer survival; Medicine; Oncology; Internal medicine","score_opus":0.07129761671495684,"score_gpt":0.48214353162600854,"score_spread":0.4108459149110517,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393088906","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95341396,0.025818042,0.001408885,0.006386017,0.00064399967,0.00041320664,0.000055270946,0.000048962585,0.011811646],"genre_scores_gemma":[0.9879087,0.010754494,0.00024189547,0.000047064048,0.0003366173,0.00007393834,0.000009018294,0.000029081419,0.0005991566],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9982647,0.00007139212,0.0002576565,0.00034302718,0.0007198467,0.00034339],"domain_scores_gemma":[0.999104,0.00034138488,0.000028800643,0.00015726578,0.00015098874,0.00021754326],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011102482,0.000102645565,0.00022746158,0.00011428272,0.00007340869,0.00007277183,0.00012850555,0.000064379296,0.00080829667],"category_scores_gemma":[0.00014044679,0.000082586346,0.00004651269,0.00030043747,0.00030212692,0.000075957796,0.00008175964,0.0008816769,0.000005145311],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013254085,0.00020191706,0.0114984,0.0027719014,0.0001312909,0.000097332246,0.0006267789,0.000056507102,0.53163713,0.003382596,0.0091192415,0.44034433],"study_design_scores_gemma":[0.0016368532,0.0012745191,0.061684556,0.0067960965,0.00036371985,0.000029439272,0.0025341485,0.10479498,0.73407716,0.008554133,0.07716279,0.001091642],"about_ca_topic_score_codex":0.00540708,"about_ca_topic_score_gemma":0.00008929429,"teacher_disagreement_score":0.4392527,"about_ca_system_score_codex":0.00018188794,"about_ca_system_score_gemma":0.00057674834,"threshold_uncertainty_score":0.8850282},"labels":[],"label_agreement":null},{"id":"W4393089534","doi":"10.1158/1538-7445.am2024-3650","title":"Abstract 3650: Deep learning-based image cytometry and co-localization index in tumor immune microenvironment","year":2024,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Immune system; Tumor microenvironment; Flow cytometry; Cancer research; Cytometry; Index (typography); Medicine; Pathology; Immunology; Computer science; World Wide Web","score_opus":0.01977205213123029,"score_gpt":0.3898936218034814,"score_spread":0.3701215696722511,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393089534","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9757111,0.012734852,0.0062293075,0.0038278066,0.000112914226,0.00041807262,0.000003960789,0.00007050595,0.0008914581],"genre_scores_gemma":[0.9977621,0.0011525882,0.00014266891,0.00024197788,0.00014772938,0.00006808028,0.000032257,0.000046165067,0.00040645272],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99829096,0.000116620475,0.00024243063,0.00037001164,0.00055968715,0.00042029307],"domain_scores_gemma":[0.9993694,0.0002170798,0.000025503408,0.00016303388,0.00004238525,0.00018260376],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001451369,0.00011838943,0.00021254555,0.00057764753,0.00011235724,0.000114251394,0.00009277293,0.000063684754,0.0007234545],"category_scores_gemma":[0.0003611161,0.00010437241,0.000041807947,0.0005366979,0.00034125123,0.0000753245,0.000054155716,0.0015560242,0.000058606747],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005312215,0.0002836046,0.3201656,0.0029670945,0.00010735998,0.0024134028,0.0010629237,0.0064879823,0.5366229,0.00005920909,0.0018178062,0.12748088],"study_design_scores_gemma":[0.002570679,0.00024968738,0.51103616,0.0019871895,0.000027424701,0.000062525505,0.0004224214,0.40117392,0.019191701,0.00008876034,0.06290869,0.00028084303],"about_ca_topic_score_codex":0.0006547543,"about_ca_topic_score_gemma":0.000016240048,"teacher_disagreement_score":0.5174312,"about_ca_system_score_codex":0.00040967876,"about_ca_system_score_gemma":0.00019149653,"threshold_uncertainty_score":0.792132},"labels":[],"label_agreement":null},{"id":"W4393093059","doi":"10.1158/1538-7445.am2024-2427","title":"Abstract 2427: The development of a tissue-agnostic genome-wide methylome enrichment MRD assay for applications across the cancer care continuum for head and neck malignancies","year":2024,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Association of Canadian Map Libraries and Archives; University Health Network","funders":"","keywords":"Head and neck; Head and neck cancer; DNA methylation; Cancer; Oncology; Biology; Medicine; Computational biology; Internal medicine; Genetics; Surgery; Gene","score_opus":0.05720385399069514,"score_gpt":0.4574640619463747,"score_spread":0.4002602079556795,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393093059","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86523426,0.08064044,0.019808432,0.028074404,0.00028262523,0.005473083,0.00022931356,0.000043091986,0.00021433794],"genre_scores_gemma":[0.98416454,0.0013746453,0.0024014998,0.00031686277,0.0004229882,0.009681263,0.000040272866,0.00004228444,0.0015556564],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983777,0.000049636907,0.0003177141,0.0003449436,0.0004287042,0.0004813369],"domain_scores_gemma":[0.997006,0.00212281,0.000050983603,0.00027696835,0.0004252056,0.00011804464],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022872135,0.00012395755,0.00024065572,0.00006893612,0.0005071961,0.000107657004,0.00026261373,0.00005383786,0.000038236336],"category_scores_gemma":[0.00057988334,0.00006967482,0.0000633583,0.00027233645,0.00033699846,0.000032309857,0.0001146447,0.0004280247,0.0000029657324],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030347856,0.000102314116,0.0089510735,0.0078405,0.0006993234,0.00001029193,0.042356372,0.00020306112,0.2210144,0.0009205133,0.01335528,0.70424336],"study_design_scores_gemma":[0.00085573125,0.00011838601,0.048032694,0.0006853432,0.00008354408,0.0000036887716,0.0030911895,0.00034227714,0.01842385,0.00032038515,0.9279162,0.00012671069],"about_ca_topic_score_codex":0.00030808206,"about_ca_topic_score_gemma":0.00041265538,"teacher_disagreement_score":0.9145609,"about_ca_system_score_codex":0.0002756552,"about_ca_system_score_gemma":0.00079479575,"threshold_uncertainty_score":0.3900994},"labels":[],"label_agreement":null},{"id":"W4393093106","doi":"10.1158/1538-7445.am2024-6176","title":"Abstract 6176: Identifying poor prognosis stage I lung adenocarcinoma patients through novel morphological biomarker based on computational pathology","year":2024,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; Institut universitaire de cardiologie et de pneumologie de Québec","funders":"","keywords":"Stage (stratigraphy); Medicine; Biomarker; Adenocarcinoma; Pathology; Lung cancer; Lung; Oncology; Internal medicine; Cancer; Biology","score_opus":0.11966133644897951,"score_gpt":0.4505551289426281,"score_spread":0.3308937924936486,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393093106","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9808486,0.0014060409,0.0062653837,0.0085581895,0.00054198183,0.0007032981,0.00008896467,0.00013262055,0.0014548954],"genre_scores_gemma":[0.99504614,0.000057934893,0.0024859286,0.0013407252,0.00024756385,0.00019309913,0.00018494843,0.000053906097,0.00038977334],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9970986,0.00013790802,0.0003260824,0.0006652624,0.0011659635,0.00060613756],"domain_scores_gemma":[0.99866205,0.00061038183,0.00004333009,0.00019743702,0.00027160018,0.00021517735],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0011691788,0.00018022126,0.0002705438,0.0003507422,0.00021959477,0.00015180398,0.00020131173,0.00014552775,0.0012356223],"category_scores_gemma":[0.00056702207,0.00014063198,0.0001241867,0.0005679311,0.00037043373,0.000110520334,0.00010594153,0.0013823399,0.00009162396],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017839213,0.002688218,0.74748206,0.004411994,0.00053606735,0.009014527,0.0013711157,0.005884001,0.0767186,0.0025925862,0.08234045,0.06517647],"study_design_scores_gemma":[0.0026588493,0.0003760804,0.7534104,0.00119196,0.000052119984,0.0000454109,0.000081854625,0.23530632,0.0008104631,0.00023069177,0.0055846474,0.00025120281],"about_ca_topic_score_codex":0.0001902324,"about_ca_topic_score_gemma":0.0000017150624,"teacher_disagreement_score":0.22942233,"about_ca_system_score_codex":0.00039524466,"about_ca_system_score_gemma":0.00040330397,"threshold_uncertainty_score":0.99967736},"labels":[],"label_agreement":null},{"id":"W4393093726","doi":"10.1158/1538-7445.am2024-67","title":"Abstract 67: Predicting colorectal patient prognoses by functional characterisation of heterogeneous cell types and their spatial interaction using a new technique: Whole slide imaging mass cytometry","year":2024,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Integrity Testing Laboratory (Canada)","funders":"","keywords":"Mass cytometry; Colorectal cancer; Medicine; Pathology; Internal medicine; Biology; Cancer; Genetics","score_opus":0.03101204730136115,"score_gpt":0.3591058842236604,"score_spread":0.32809383692229926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393093726","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98200923,0.002508693,0.013843079,0.0006322191,0.00032147052,0.00046875214,0.000029860761,0.00006286014,0.00012381085],"genre_scores_gemma":[0.99878794,0.00013447333,0.00042405986,0.000035533914,0.00040953953,0.000057850073,0.000052596162,0.000035225927,0.00006276683],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987322,0.000065275846,0.00025521612,0.000299888,0.00039103898,0.0002563727],"domain_scores_gemma":[0.99937195,0.0001844852,0.00007363959,0.000090346555,0.00014188245,0.00013770156],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004949925,0.00011828032,0.0001746407,0.00031320867,0.00010630459,0.000096003154,0.000050313673,0.0000585634,0.00013447345],"category_scores_gemma":[0.00016103132,0.00009626031,0.00005052968,0.00025959653,0.00011396751,0.00015233166,0.00005768469,0.0006949862,0.0000026223904],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017518822,0.000037872822,0.015194535,0.00034117544,0.000041350442,0.000023092096,0.00048387735,0.00006020973,0.88140655,7.312135e-7,0.0004790879,0.10175634],"study_design_scores_gemma":[0.0006506804,0.0004039143,0.009826519,0.0019458963,0.000055295346,0.00023080614,0.00061590585,0.14541496,0.8342258,0.00007739307,0.0063531706,0.00019966628],"about_ca_topic_score_codex":0.0011160623,"about_ca_topic_score_gemma":0.000004939858,"teacher_disagreement_score":0.14535475,"about_ca_system_score_codex":0.00027840317,"about_ca_system_score_gemma":0.00032765002,"threshold_uncertainty_score":0.39253816},"labels":[],"label_agreement":null},{"id":"W4393095315","doi":"10.30564/jeis.v6i1.6174","title":"Evaluating Maximum Diameters of Tumor Sub-regions for Survival Prediction in Glioblastoma Patients via Machine Learning, Considering Resection Status","year":2024,"lang":"en","type":"article","venue":"Journal of Electronic & Information Systems","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Glioblastoma; Correlation; Medicine; Glioma; Magnetic resonance imaging; Univariate; Cancer; Resection; Univariate analysis; Brain tumor; Artificial intelligence; Machine learning; Radiology; Computer science; Surgery; Internal medicine; Mathematics; Pathology; Multivariate analysis; Multivariate statistics","score_opus":0.014731407127079764,"score_gpt":0.30034052694938357,"score_spread":0.2856091198223038,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393095315","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91692984,0.0011033458,0.07978386,0.00013334963,0.0012769491,0.00058426894,0.000009793973,0.000037148857,0.0001414591],"genre_scores_gemma":[0.9993469,0.00010066952,0.00024825567,0.000027510081,0.0001784664,0.00001905932,0.000033969558,0.000020243682,0.000024913295],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974623,0.00015397626,0.0013046506,0.000097459786,0.0006270289,0.0003546274],"domain_scores_gemma":[0.9983192,0.00029321466,0.00072102505,0.00008934649,0.00046636793,0.00011085647],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025514825,0.00013424642,0.00039942117,0.0007956385,0.00007082906,0.00007261626,0.000062744635,0.00006516252,0.0000073990705],"category_scores_gemma":[0.0012908538,0.000113032016,0.00015439458,0.00037073274,0.00003455159,0.00071817666,0.000015212687,0.00079897174,0.0000028504558],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.011053422,0.00080460816,0.31528524,0.016276145,0.0026552856,0.00007046268,0.01754295,0.3471937,0.06230953,0.005137576,0.0038904848,0.2177806],"study_design_scores_gemma":[0.0046103657,0.005572244,0.0037647982,0.0019508263,0.0001701331,0.00049274205,0.00071228266,0.9700419,0.0012172797,0.00023563115,0.011086111,0.00014573222],"about_ca_topic_score_codex":0.00010593071,"about_ca_topic_score_gemma":0.000014175452,"teacher_disagreement_score":0.62284815,"about_ca_system_score_codex":0.0006148377,"about_ca_system_score_gemma":0.00043609916,"threshold_uncertainty_score":0.46093118},"labels":[],"label_agreement":null},{"id":"W4393096100","doi":"10.1158/1538-7445.am2024-926","title":"Abstract 926: Adaptive universal platform for real-world observational studies (AUPROS): An emerging model for clinical, epidemiologic, and precision oncology research","year":2024,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Princess Margaret Cancer Centre; University Health Network","funders":"","keywords":"Precision oncology; Observational study; Medicine; Clinical Oncology; Medical physics; Oncology; Internal medicine; Cancer","score_opus":0.7609573847194339,"score_gpt":0.6698915856855782,"score_spread":0.0910657990338557,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393096100","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9231914,0.012830354,0.0137323765,0.043428373,0.00082975195,0.0037672096,0.00013926857,0.00015444605,0.0019268144],"genre_scores_gemma":[0.92059153,0.03579911,0.03159872,0.0005699266,0.0023918026,0.0012963341,0.00013357546,0.00009373454,0.0075252648],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996883,0.00030788162,0.0005811629,0.000796811,0.0006544245,0.00077671575],"domain_scores_gemma":[0.98302674,0.014977554,0.000066869325,0.00026530377,0.0013052588,0.00035826006],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.021382036,0.00015409039,0.00056624314,0.00051533506,0.0005884825,0.00006367592,0.00022590415,0.00018366476,0.00003628509],"category_scores_gemma":[0.007298886,0.00011661073,0.00012672703,0.00047275418,0.0009701651,0.0002633493,0.00020846199,0.0018127252,0.000003775179],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.006694278,0.00033021302,0.007641925,0.0017198827,0.00071415526,0.00009906499,0.0036435875,0.0029930957,0.0036266006,0.070942,0.23480515,0.66679007],"study_design_scores_gemma":[0.0016823012,0.001811727,0.006747962,0.0008301786,0.00005360058,0.000004898633,0.0018798786,0.86339486,0.000059948743,0.04064927,0.08273134,0.00015402613],"about_ca_topic_score_codex":0.00039555796,"about_ca_topic_score_gemma":0.00028299494,"teacher_disagreement_score":0.8604018,"about_ca_system_score_codex":0.0008373115,"about_ca_system_score_gemma":0.0016116011,"threshold_uncertainty_score":0.87379754},"labels":[],"label_agreement":null},{"id":"W4393169231","doi":"10.1016/j.imu.2024.101481","title":"Predictive biomarker discovery in cancer using a unique AI model based on set theory","year":2024,"lang":"en","type":"article","venue":"Informatics in Medicine Unlocked","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; McGill University Health Centre","funders":"MEDTEQ+","keywords":"Biomarker discovery; Computational biology; Set (abstract data type); Computer science; Biomarker; Cancer; Artificial intelligence; Machine learning; Biology; Proteomics; Genetics","score_opus":0.02898435212249525,"score_gpt":0.36985996685662087,"score_spread":0.34087561473412564,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393169231","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5500003,0.0006611254,0.42759228,0.009896154,0.0008221868,0.0010159216,0.000039435316,0.00018997298,0.009782619],"genre_scores_gemma":[0.985267,0.00015464603,0.0033093647,0.010604831,0.00016939164,0.000057258065,0.00006951682,0.00005064777,0.00031736854],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976533,0.00011785335,0.0009152747,0.00023820104,0.00063533534,0.0004400071],"domain_scores_gemma":[0.998749,0.00054756785,0.00010722364,0.0003549035,0.000064685155,0.00017657435],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020142167,0.0002985371,0.0005761381,0.0012049995,0.00005041543,0.00004644375,0.00017372677,0.00017253034,0.00008192672],"category_scores_gemma":[0.00091971783,0.00021371174,0.000080864455,0.0009053248,0.00032807156,0.00035020473,0.000055300825,0.0013756796,0.000005321476],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021719425,0.0004320819,0.02278817,0.004141419,0.00029700046,0.0009397201,0.04277524,0.85555166,0.0019066072,0.012661545,0.010505068,0.04582956],"study_design_scores_gemma":[0.0025661008,0.00019769593,0.0009926584,0.008275392,0.00010017596,0.000034729946,0.0013181063,0.9826426,0.00006924592,0.0027203264,0.0008837225,0.00019926231],"about_ca_topic_score_codex":0.00027339786,"about_ca_topic_score_gemma":0.000017802275,"teacher_disagreement_score":0.43526667,"about_ca_system_score_codex":0.00058714795,"about_ca_system_score_gemma":0.00072894443,"threshold_uncertainty_score":0.8714912},"labels":[],"label_agreement":null},{"id":"W4393182279","doi":"10.7554/elife.92819.2.sa1","title":"Reviewer #2 (Public Review): Endogenous tagging using split mNeonGreen in human iPSCs for live imaging studies","year":2024,"lang":"en","type":"peer-review","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; Concordia University","keywords":"Endogeny; Induced pluripotent stem cell; Neuroscience; Computational biology; Biology; Genetics; Biochemistry; Gene","score_opus":0.13432986358832105,"score_gpt":0.42643893558643164,"score_spread":0.2921090719981106,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393182279","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000028897852,0.8144107,0.00042746612,0.17262298,0.004006928,0.0044893357,0.000067378736,0.0002143903,0.0037319139],"genre_scores_gemma":[0.000059887585,0.7808701,0.007961819,0.0941263,0.003704749,0.000617929,0.0017222237,0.00035866973,0.11057832],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9939184,0.00027805948,0.0022054457,0.0014466072,0.0009975658,0.0011538733],"domain_scores_gemma":[0.99546933,0.00053163635,0.0006879485,0.0011105858,0.001814776,0.00038569712],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0055416888,0.0009997842,0.0041098422,0.00067325274,0.0002614292,0.000108583125,0.00053474307,0.00021253551,0.00065124733],"category_scores_gemma":[0.012873716,0.0007734479,0.0010635324,0.0007705145,0.0002611218,0.00014884658,0.0005007487,0.0024707655,0.00008690013],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000033373535,0.000054759348,0.00006736306,0.19282511,0.00040353247,0.00036155392,0.00010714755,0.0000012014361,0.000039981504,0.00010895756,0.74500287,0.061024196],"study_design_scores_gemma":[0.00046471227,0.00005689474,0.0000046833684,0.2769886,0.0027493616,0.00044344,0.00005207254,0.0014582545,0.0000019881404,0.00013474136,0.71711,0.0005352839],"about_ca_topic_score_codex":0.00045174797,"about_ca_topic_score_gemma":0.000061032497,"teacher_disagreement_score":0.10684641,"about_ca_system_score_codex":0.00086690095,"about_ca_system_score_gemma":0.0006284313,"threshold_uncertainty_score":0.9998306},"labels":[],"label_agreement":null},{"id":"W4393227005","doi":"10.1007/s11517-024-03071-6","title":"Impact of harmonization on the reproducibility of MRI radiomic features when using different scanners, acquisition parameters, and image pre-processing techniques: a phantom study","year":2024,"lang":"en","type":"article","venue":"Medical & Biological Engineering & Computing","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; McGill University; Douglas Mental Health University Institute","funders":"Université de Genève; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung","keywords":"Reproducibility; Imaging phantom; Biomedical engineering; Image processing; Human physiology; Medical physics; Artificial intelligence; Computer vision; Computer science; Nuclear medicine; Pattern recognition (psychology); Medicine; Image (mathematics); Mathematics; Statistics","score_opus":0.018604160096241537,"score_gpt":0.3242742442032294,"score_spread":0.30567008410698787,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393227005","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90316975,0.0008524997,0.09480418,0.00043247218,0.0000969021,0.00047626853,0.0000029559817,0.00015110466,0.000013885475],"genre_scores_gemma":[0.9920509,0.000036333397,0.0076227915,0.00006454511,0.00018160329,0.000005322785,0.000012319086,0.00002325578,0.0000029666867],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99792504,0.00016696485,0.00052976684,0.0006848168,0.00042924512,0.0002641442],"domain_scores_gemma":[0.9987135,0.00055011694,0.00012334484,0.00038488788,0.00006674419,0.00016141497],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023389012,0.0002319362,0.0005405488,0.00014882034,0.00008484778,0.000038421145,0.0001631303,0.00014136649,0.000039019535],"category_scores_gemma":[0.0024935694,0.00012552353,0.00015092881,0.00027333578,0.0002680119,0.00004297719,0.00014265957,0.00072282436,2.7858133e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00069106865,0.0019373465,0.45668885,0.0023267933,0.00096204196,0.00031955467,0.0065935375,0.010328463,0.3036984,0.00021410831,0.00033894466,0.2159009],"study_design_scores_gemma":[0.0003759249,0.00087329035,0.29753318,0.0018168745,0.00009463567,0.0001512243,0.000067166126,0.69643646,0.002443525,0.0000604813,0.000004361471,0.00014286843],"about_ca_topic_score_codex":0.0001252464,"about_ca_topic_score_gemma":1.3922742e-7,"teacher_disagreement_score":0.686108,"about_ca_system_score_codex":0.00011294142,"about_ca_system_score_gemma":0.000073899064,"threshold_uncertainty_score":0.51187},"labels":[],"label_agreement":null},{"id":"W4393227855","doi":"10.54254/2755-2721/53/20241290","title":"Application of machine learning in lung cancer prediction","year":2024,"lang":"en","type":"article","venue":"Applied and Computational Engineering","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Machine learning; Artificial intelligence; Computer science; Lung cancer; Medicine; Pathology","score_opus":0.0030012133303715443,"score_gpt":0.24007181952708387,"score_spread":0.23707060619671233,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393227855","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35930353,0.0038923935,0.6351649,0.00065076345,0.00010154597,0.00020940797,0.0000049375735,0.0001702756,0.00050224416],"genre_scores_gemma":[0.99610955,0.00008465345,0.003587862,0.00003501161,0.00007420559,0.000031451982,0.00004455619,0.000012865451,0.000019856992],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99955964,0.0000027458382,0.00013877713,0.00012267054,0.00010548827,0.00007068851],"domain_scores_gemma":[0.9998468,0.000065714354,0.000014849928,0.000025779611,0.000011935444,0.000034878893],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000105549174,0.000058267986,0.000103395825,0.00012811551,0.000014303131,0.00000947343,0.00001597279,0.000026349751,0.000006234037],"category_scores_gemma":[0.000012326552,0.00005576127,0.000016111528,0.00016010166,0.0000126515015,0.000024730429,0.000011301731,0.00021777509,5.7425126e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010672517,0.000012580836,0.01481823,0.0005098033,0.00003281497,0.0000036192325,0.00018388165,0.90407485,0.0070018624,0.0153116,0.000013656291,0.058026403],"study_design_scores_gemma":[0.0002572765,0.000009592994,0.03608084,0.00013748421,0.000019310106,0.000012964242,0.000006843142,0.96216667,0.00005990828,0.00019711262,0.001011405,0.000040625033],"about_ca_topic_score_codex":0.000036683574,"about_ca_topic_score_gemma":3.4190998e-7,"teacher_disagreement_score":0.636806,"about_ca_system_score_codex":0.000028997487,"about_ca_system_score_gemma":0.000024569583,"threshold_uncertainty_score":0.22738785},"labels":[],"label_agreement":null},{"id":"W4393250388","doi":"10.1055/a-2248-1385","title":"Establishing ground truth of polyp size, morphology, and volume using three-dimensional scanning","year":2024,"lang":"en","type":"article","venue":"Endoscopy","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier de l’Université de Montréal","funders":"Fujifilm Corporation","keywords":"Morphology (biology); Ground truth; Volume (thermodynamics); Cover (algebra); Medicine; Artificial intelligence; Computer science; Geology; Paleontology; Physics","score_opus":0.015577359744334999,"score_gpt":0.30277037616855385,"score_spread":0.28719301642421885,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393250388","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98808247,0.004149531,0.005064312,0.0010973546,0.0008236654,0.000106961874,0.0000056057215,0.00008503949,0.0005850673],"genre_scores_gemma":[0.96366197,0.000019653668,0.03534886,0.0003177907,0.0003318115,0.0000023147265,0.000008563441,0.0000373353,0.0002717188],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99889106,0.00003531441,0.00025749154,0.00030477194,0.00024986183,0.00026149314],"domain_scores_gemma":[0.99913496,0.00046995227,0.00005643254,0.0001546493,0.00003410478,0.00014992434],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000450484,0.0001398003,0.00030909668,0.00014537381,0.000085187996,0.000066964785,0.00006713618,0.00007596679,0.00022254475],"category_scores_gemma":[0.0007565081,0.00012038374,0.00006565684,0.00021415896,0.00022501883,0.00016366508,0.000079639874,0.00048858643,0.0000056684066],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003947799,0.0001939857,0.34577465,0.0014604859,0.00059827016,0.0019860568,0.0015080702,0.0012575284,0.58929604,0.0054780114,0.0061182487,0.045933884],"study_design_scores_gemma":[0.0026531108,0.00040408675,0.09166238,0.0027421326,0.00050257606,0.0012666258,0.00022121293,0.88866335,0.0044844206,0.0023782656,0.0045945263,0.0004273054],"about_ca_topic_score_codex":0.0007123144,"about_ca_topic_score_gemma":0.0000021814728,"teacher_disagreement_score":0.8874058,"about_ca_system_score_codex":0.000047894035,"about_ca_system_score_gemma":0.0001304722,"threshold_uncertainty_score":0.49091065},"labels":[],"label_agreement":null},{"id":"W4393306525","doi":"10.1117/12.3004837","title":"Modular 3D-printed liver tumour phantom for modelling embolization procedures","year":2024,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Robarts Clinical Trials; Western University","funders":"","keywords":"Imaging phantom; 3d printed; Modular design; Computer science; Biomedical engineering; Radiology; Medicine; Programming language","score_opus":0.018707375698405318,"score_gpt":0.30325840195418374,"score_spread":0.28455102625577844,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393306525","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06025388,0.0012245594,0.93255216,0.002103681,0.0002237443,0.0003888327,0.0000016427114,0.00032182975,0.0029296558],"genre_scores_gemma":[0.9437419,0.0002162628,0.04954634,0.0007443571,0.00044837364,0.000033097844,0.000040842046,0.000044973065,0.005183839],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991891,0.000010117937,0.00017429821,0.00026115277,0.00017025348,0.00019509142],"domain_scores_gemma":[0.9996392,0.000057439025,0.00001847014,0.000098259,0.000082180864,0.000104434956],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020682593,0.00010786059,0.00016217811,0.00012360494,0.000057902696,0.000062728526,0.00005480658,0.000051938634,0.000117137344],"category_scores_gemma":[0.00020399642,0.00008228688,0.00007789231,0.00013992091,0.000026688722,0.00008176416,0.000018719495,0.00018269903,0.000026841479],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005537495,0.0006470246,0.001746836,0.012852068,0.0009742677,0.00058733084,0.00489393,0.35819831,0.22039917,0.14756905,0.0358183,0.21575995],"study_design_scores_gemma":[0.0003870759,0.000052690128,0.000094688534,0.00036138177,0.00009481793,0.00006690308,0.0000339592,0.9818208,0.0018987937,0.00093688734,0.014155211,0.00009678955],"about_ca_topic_score_codex":0.000037542148,"about_ca_topic_score_gemma":0.0000015422129,"teacher_disagreement_score":0.88348806,"about_ca_system_score_codex":0.000035617606,"about_ca_system_score_gemma":0.00010001467,"threshold_uncertainty_score":0.33555618},"labels":[],"label_agreement":null},{"id":"W4393336171","doi":"10.48550/arxiv.2403.19508","title":"Fairness-Aware Data Augmentation for Cardiac MRI using Text-Conditioned Diffusion Models","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"HORIZON EUROPE Framework Programme; Circle Cardiovascular Imaging; Barts Health NHS Trust; National Institute for Health and Care Research; Medical Research Council; Barts Charity; Queen Mary University of London","keywords":"Debiasing; Diffusion; Computer science; Psychology; Cognitive science; Physics; Thermodynamics","score_opus":0.1310471993832416,"score_gpt":0.2765588862868102,"score_spread":0.14551168690356858,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393336171","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36061382,0.00024008944,0.6350365,0.0005896349,0.0012622499,0.00092670845,0.0005012976,0.00020032114,0.00062931725],"genre_scores_gemma":[0.9910755,0.00036354703,0.002538373,0.00016856023,0.00048145378,0.0000031864408,0.0036983702,0.00007460251,0.0015963882],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99804324,0.00007618182,0.0002596692,0.0011673935,0.00014872101,0.0003048234],"domain_scores_gemma":[0.9983049,0.00011356159,0.00018270186,0.0010414692,0.00014410366,0.00021325398],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003800952,0.00031005143,0.0005142164,0.00031072937,0.00019387271,0.0000847625,0.00044361045,0.00028662986,0.000049306513],"category_scores_gemma":[0.00007027876,0.0003275577,0.00025985498,0.00025297847,0.00011897412,0.00020506718,0.0014472988,0.0008731547,0.000019485902],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007006346,0.00040868312,0.004081605,0.0050765937,0.0017644442,0.0008209724,0.00086941494,0.9204734,0.003173737,0.0418847,0.013810112,0.0069356994],"study_design_scores_gemma":[0.0010412531,0.0000376782,0.00015700945,0.00073768926,0.0014423343,0.000008823799,0.00029552716,0.95527107,0.000046048655,0.03988586,0.00077360927,0.00030308028],"about_ca_topic_score_codex":0.00031147877,"about_ca_topic_score_gemma":0.000005718146,"teacher_disagreement_score":0.6324982,"about_ca_system_score_codex":0.00035380514,"about_ca_system_score_gemma":0.0003280234,"threshold_uncertainty_score":0.9999176},"labels":[],"label_agreement":null},{"id":"W4393399813","doi":"10.48550/arxiv.2403.20253","title":"MedCLIP-SAM: Bridging Text and Image Towards Universal Medical Image Segmentation","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Bridging (networking); Image (mathematics); Computer science; Segmentation; Computer vision; Image segmentation; Artificial intelligence; Computer security","score_opus":0.027660124688799897,"score_gpt":0.23806376477806043,"score_spread":0.21040364008926055,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393399813","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89902496,0.0005022268,0.07531526,0.0069424394,0.001031707,0.00053394015,0.00003559946,0.00044497068,0.016168889],"genre_scores_gemma":[0.9910832,0.0013963707,0.002561724,0.00061487796,0.0004982922,0.000001154472,0.00014027143,0.000078865516,0.0036252222],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997677,0.00013795673,0.00030412024,0.001102464,0.0003423661,0.00043606703],"domain_scores_gemma":[0.99845314,0.00011367167,0.00015970446,0.00047968148,0.00013536985,0.0006584584],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0006402906,0.00041124478,0.00058824744,0.00044209324,0.0001416348,0.00013408692,0.00034029796,0.00040514328,0.00055971486],"category_scores_gemma":[0.00038232206,0.00042459942,0.00024465393,0.00036742855,0.00056438433,0.00015649624,0.0014561036,0.0023780828,0.0001246429],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0031920036,0.0022958848,0.04448061,0.025086606,0.009091868,0.18797,0.01155352,0.008019392,0.04716148,0.115498744,0.0994278,0.4462221],"study_design_scores_gemma":[0.004079933,0.0001953323,0.0046110563,0.0024315445,0.0019447084,0.0005074526,0.001223791,0.9696554,0.0008109877,0.010498883,0.0030182262,0.0010226893],"about_ca_topic_score_codex":0.0006003322,"about_ca_topic_score_gemma":0.000015704392,"teacher_disagreement_score":0.961636,"about_ca_system_score_codex":0.00037341498,"about_ca_system_score_gemma":0.00063857477,"threshold_uncertainty_score":0.99992347},"labels":[],"label_agreement":null},{"id":"W4393431433","doi":"10.5281/zenodo.4590293","title":"Virtual cohort of adult healthy four-chamber heart meshes from CT images","year":2021,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Thomas Hospital","funders":"European Commission; Research Councils UK; Wellcome","keywords":"Polygon mesh; Cohort; Medicine; Computer science; Computer graphics (images); Internal medicine","score_opus":0.020878134899622588,"score_gpt":0.28210911182394016,"score_spread":0.26123097692431757,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393431433","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007519268,0.00046884833,0.0004478188,0.005229822,0.00045751914,0.00076299574,0.9799618,0.0003697575,0.0047821715],"genre_scores_gemma":[0.0034761527,0.0014617977,0.0004906223,0.0017121112,0.0005950299,9.429401e-8,0.99055487,0.0011777938,0.0005315551],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9968333,0.0005243713,0.0005838127,0.000704469,0.00090628065,0.00044776875],"domain_scores_gemma":[0.99734986,0.000108818436,0.00027438937,0.0009606475,0.0008859799,0.00042027837],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0007349837,0.0002960985,0.0007016751,0.00029434453,0.0007415975,0.0002880316,0.0005562218,0.00013823873,0.020038633],"category_scores_gemma":[0.0035940874,0.0002909981,0.00017319297,0.00041631795,0.00034752546,0.00010221439,0.001071435,0.0013103433,0.0023822084],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012712057,0.00020593124,0.0000262664,0.0002623403,0.00022594379,0.0002712367,0.00006438839,0.000009588897,0.00060199347,0.000030350255,0.9887675,0.009407307],"study_design_scores_gemma":[0.0009494442,0.00041269528,0.0011129229,0.00039089762,0.0001759864,0.0006865406,0.00011911117,0.00016767488,0.00014991472,0.000014840255,0.9955858,0.00023414812],"about_ca_topic_score_codex":0.0006238264,"about_ca_topic_score_gemma":0.0000011623434,"teacher_disagreement_score":0.017656425,"about_ca_system_score_codex":0.00015649319,"about_ca_system_score_gemma":0.000036119523,"threshold_uncertainty_score":0.9999542},"labels":[],"label_agreement":null},{"id":"W4393444729","doi":"10.5281/zenodo.3234172","title":"Coexpression and purification of HTT and HTT-HAP40 with NEDD4L and HAP1 2019/05/02","year":2019,"lang":"en","type":"dataset","venue":"Figshare","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science","score_opus":0.0192251444758786,"score_gpt":0.2917441667186074,"score_spread":0.27251902224272884,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393444729","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00097649137,0.0029201596,0.0000016134486,0.00045889846,0.000045623216,0.000415955,0.9950756,0.000014952636,0.00009071825],"genre_scores_gemma":[0.0006772379,0.0005976665,0.00030402027,0.0003326092,0.00013729525,0.000026542475,0.99751157,0.000026515925,0.00038657282],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989158,0.000037629034,0.00022017589,0.0003916745,0.0002671359,0.00016759183],"domain_scores_gemma":[0.99892426,0.00017362015,0.00025831812,0.00037630115,0.00008548337,0.00018202675],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00009561991,0.00022324205,0.00045831312,0.00012295075,0.00005776647,0.00004540617,0.000093644565,0.00022659134,0.0049799476],"category_scores_gemma":[0.0008327754,0.00016256474,0.000024569299,0.00006679336,0.00005185352,0.000074905845,0.00012801227,0.00056058366,0.00004722167],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000061029783,0.000024799474,0.00013387339,0.0021562213,0.00003517716,0.000024892763,0.000038038663,9.845269e-7,0.00013633995,7.592385e-7,0.99389154,0.0034963393],"study_design_scores_gemma":[0.0011269925,0.00026217528,0.0048555667,0.008991788,0.00012742096,0.0001822694,0.000021702877,0.0006208788,0.000054766486,0.000005097308,0.98356193,0.00018942545],"about_ca_topic_score_codex":0.000058397563,"about_ca_topic_score_gemma":0.0000027431893,"teacher_disagreement_score":0.010329628,"about_ca_system_score_codex":0.000012503337,"about_ca_system_score_gemma":0.00007253828,"threshold_uncertainty_score":0.99592966},"labels":[],"label_agreement":null},{"id":"W4393469418","doi":"10.5281/zenodo.3555321","title":"Large-scale purification of Q23 HTT-HAP40 from Sf9 expression system with contaminating nucleic acid material 2019/09/16","year":2019,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Structural Genomics Consortium; Princess Margaret Cancer Centre; University of Toronto","funders":"","keywords":"Nucleic acid; Sf9; Scale (ratio); Chemistry; Molecular biology; Chromatography; Biology; Biochemistry; Physics; Recombinant DNA; Gene","score_opus":0.0140232221909292,"score_gpt":0.24981592360348237,"score_spread":0.23579270141255318,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393469418","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02964862,0.00015298805,0.0051511773,0.0004876195,0.0005391725,0.0014888437,0.9562662,0.0005168121,0.0057485607],"genre_scores_gemma":[0.045953322,0.000104146704,0.00061019044,0.000099305726,0.00046206662,2.1636912e-7,0.95124537,0.001133082,0.00039228887],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9969953,0.00046182176,0.00058387936,0.0006895642,0.0008330288,0.00043641592],"domain_scores_gemma":[0.9974844,0.00005729076,0.0006083636,0.0010128318,0.00058906066,0.0002480622],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0009823006,0.0003150364,0.0006162793,0.00032514028,0.0007288098,0.00035117386,0.00085359585,0.00025097225,0.010555554],"category_scores_gemma":[0.0006703521,0.0002708917,0.000088484936,0.0003091867,0.00017171491,0.00016447186,0.00076662144,0.0008295564,0.0032027457],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033714753,0.00018585096,0.0000058147607,0.00095312577,0.00009627909,0.00003220218,0.00030509834,0.0000072390612,0.037891697,0.00006893189,0.9574419,0.0026746665],"study_design_scores_gemma":[0.0016010093,0.00041216024,0.00019393234,0.0019110689,0.0001463281,0.000118807635,0.00076790026,0.0008658121,0.0038180898,0.0000039592715,0.9898796,0.00028130008],"about_ca_topic_score_codex":0.00012755377,"about_ca_topic_score_gemma":5.39938e-7,"teacher_disagreement_score":0.03407361,"about_ca_system_score_codex":0.00029413885,"about_ca_system_score_gemma":0.00001904838,"threshold_uncertainty_score":0.9999743},"labels":[],"label_agreement":null},{"id":"W4393545758","doi":"10.5281/zenodo.4585356","title":"Confocal surface texture analysis included in the paper Paixao et al. 2021 - JASr. (supplemental to SOM3)","year":2021,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Trent University","funders":"","keywords":"Texture (cosmology); Surface (topology); Computer science; Artificial intelligence; Mathematics; Geometry; Image (mathematics)","score_opus":0.019736393018086284,"score_gpt":0.31027391436426704,"score_spread":0.29053752134618077,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393545758","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021000898,0.0003836894,0.00096751336,0.102640234,0.00023359168,0.0013931317,0.88520557,0.00017718885,0.006898992],"genre_scores_gemma":[0.0046928595,0.00051438616,0.00025418805,0.023640292,0.00017562741,1.421399e-7,0.96977687,0.0005771673,0.0003684987],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9961472,0.001129513,0.000484916,0.00072113716,0.0010166138,0.0005005962],"domain_scores_gemma":[0.99810445,0.00010606354,0.00014314825,0.0010186362,0.00032383547,0.00030386093],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0024116754,0.00029394584,0.00054151984,0.00043360394,0.00083439995,0.00077404216,0.0011577549,0.00014552768,0.057772364],"category_scores_gemma":[0.0019723135,0.00023768382,0.00018713088,0.0017977615,0.00015108543,0.0001078442,0.001569154,0.001757419,0.0021942987],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006272064,0.00025483928,0.000011318968,0.000070060894,0.00035715295,0.00032564523,0.0005131446,0.000168495,0.0005127954,0.00006064158,0.99256295,0.0051002237],"study_design_scores_gemma":[0.0008671488,0.0001830747,0.00047624664,0.000107914944,0.00032270036,0.00017481424,0.00074571115,0.0005907763,0.00001045436,0.0000055097607,0.9962784,0.00023725368],"about_ca_topic_score_codex":0.0004362878,"about_ca_topic_score_gemma":0.000021571357,"teacher_disagreement_score":0.08457127,"about_ca_system_score_codex":0.00026918238,"about_ca_system_score_gemma":0.000027675887,"threshold_uncertainty_score":0.9985826},"labels":[],"label_agreement":null},{"id":"W4393546796","doi":"10.5281/zenodo.1233638","title":"Ruthwell Cross 3D Model High Resolution (112M poly count)","year":2018,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Lethbridge","funders":"","keywords":"Resolution (logic); High resolution; Mathematics; Statistics; Computer science; Geography; Artificial intelligence; Remote sensing","score_opus":0.024892737719227932,"score_gpt":0.2920421882229112,"score_spread":0.2671494505036833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393546796","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00079631945,0.0003285697,0.0058367685,0.0014148758,0.00055066845,0.0007617726,0.9768576,0.0008567728,0.012596679],"genre_scores_gemma":[0.0013247941,0.0005024223,0.0011517691,0.000965662,0.0011464363,7.9619824e-8,0.9909973,0.0016532213,0.0022583231],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.996816,0.00027414077,0.0005065344,0.0007998169,0.00094118173,0.00066233444],"domain_scores_gemma":[0.9972841,0.00003312009,0.00027776917,0.0011038848,0.0008454657,0.0004556349],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0012612747,0.00034758577,0.00044664674,0.00041623387,0.0020836873,0.0008740191,0.0011375915,0.00032285572,0.012478796],"category_scores_gemma":[0.001903614,0.00034269603,0.000117638454,0.00043905218,0.00061388663,0.00017818177,0.0012542525,0.0013912306,0.009440002],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001940988,0.0001692116,8.9701e-7,0.00028441966,0.00008578812,0.00006279671,0.00008362317,0.0001709959,0.00015798853,0.00012052431,0.99070156,0.007968072],"study_design_scores_gemma":[0.0011361399,0.00037338337,0.000082899984,0.00022234386,0.00012628506,0.00033704037,0.0000135686805,0.020319894,0.000018618482,0.000080444166,0.9769745,0.0003148734],"about_ca_topic_score_codex":0.00020191769,"about_ca_topic_score_gemma":6.8805167e-7,"teacher_disagreement_score":0.020148898,"about_ca_system_score_codex":0.00041867877,"about_ca_system_score_gemma":0.00003164233,"threshold_uncertainty_score":0.9999025},"labels":[],"label_agreement":null},{"id":"W4393583519","doi":"10.5281/zenodo.5808389","title":"Head-Neck-PET-CT combined GTVs 2D images","year":2021,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Head and neck; Head (geology); Computer science; Nuclear medicine; Computer graphics (images); Geology; Medicine; Paleontology; Surgery","score_opus":0.022436888563803867,"score_gpt":0.2956641792817873,"score_spread":0.2732272907179834,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393583519","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001377087,0.00072836026,0.0003433481,0.006746402,0.0007515461,0.0010123951,0.95712256,0.001135376,0.030782916],"genre_scores_gemma":[0.0010201759,0.0010581011,0.00040377997,0.001271185,0.0005516907,8.435728e-8,0.9915004,0.0017361549,0.0024584339],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9968052,0.00045853856,0.00049469195,0.000798488,0.00083055964,0.000612512],"domain_scores_gemma":[0.9974222,0.00005828217,0.0002229047,0.0011559295,0.0006230215,0.00051764154],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00085770787,0.00036404398,0.00060521194,0.0004072627,0.0015094078,0.00087276095,0.0010626385,0.000072742296,0.031954944],"category_scores_gemma":[0.0032808718,0.00036225497,0.00018349991,0.00062208803,0.0003215662,0.0001228544,0.0015587213,0.0017460198,0.008649897],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000082359926,0.0003008158,0.0000016830747,0.0005293317,0.00015881284,0.0021141027,0.00003311526,0.0000069623497,0.00033739628,0.000048604157,0.9778509,0.01853589],"study_design_scores_gemma":[0.0015188238,0.00038162599,0.00012478254,0.0004453908,0.00015964107,0.0036242441,0.00007530714,0.00021827154,0.000071001195,0.000025188743,0.9930252,0.00033052402],"about_ca_topic_score_codex":0.00010198176,"about_ca_topic_score_gemma":4.3618743e-7,"teacher_disagreement_score":0.034377825,"about_ca_system_score_codex":0.00024337086,"about_ca_system_score_gemma":0.000029351895,"threshold_uncertainty_score":0.99988294},"labels":[],"label_agreement":null},{"id":"W4393587908","doi":"10.5281/zenodo.4593738","title":"Virtual cohort of extreme and average four-chamber heart meshes from statistical shape model","year":2021,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Thomas Hospital","funders":"European Commission; Research Councils UK; Wellcome","keywords":"Polygon mesh; Cohort; Computer science; Mathematics; Statistics; Computer graphics (images)","score_opus":0.03884697281809946,"score_gpt":0.2766191471307145,"score_spread":0.23777217431261505,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393587908","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0078337,0.00028209097,0.0090942085,0.0010211586,0.00013165323,0.0004905358,0.9785967,0.00018408438,0.0023658786],"genre_scores_gemma":[0.010301708,0.0007385623,0.001720603,0.0005571174,0.00023780021,6.1446556e-8,0.9852716,0.00082404976,0.00034852608],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976886,0.00029754516,0.0004150018,0.0005958508,0.0006861725,0.00031684307],"domain_scores_gemma":[0.99845165,0.000112745256,0.0001390794,0.0005677107,0.00037204815,0.00035674783],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006444283,0.00023459956,0.0005386263,0.00018515353,0.0004989978,0.00025775775,0.00030026704,0.0001713864,0.01915208],"category_scores_gemma":[0.0021988826,0.0002315245,0.000071015646,0.00018732852,0.0003496411,0.00007867488,0.001038843,0.00094542623,0.000561879],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000085827945,0.00012608916,0.000013534308,0.0001656639,0.0001598306,0.00017543497,0.00008778922,0.00010406464,0.00073862495,0.00013085036,0.9870278,0.011184464],"study_design_scores_gemma":[0.0007201036,0.00019478107,0.0010032667,0.00021634206,0.00016795786,0.00033199656,0.000042013093,0.041314043,0.000017916671,0.00006653627,0.95572627,0.00019879146],"about_ca_topic_score_codex":0.00013862738,"about_ca_topic_score_gemma":4.9584435e-7,"teacher_disagreement_score":0.041209977,"about_ca_system_score_codex":0.000080356156,"about_ca_system_score_gemma":0.000022768449,"threshold_uncertainty_score":0.9817445},"labels":[],"label_agreement":null},{"id":"W4393596048","doi":"10.5281/zenodo.4604060","title":"bartfqa-data","year":2021,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science","score_opus":0.04909374261105927,"score_gpt":0.3098200590253715,"score_spread":0.26072631641431226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393596048","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000046264024,0.0005353807,0.0005494195,0.0030769845,0.00033724535,0.0003761933,0.979971,0.00044586617,0.014661628],"genre_scores_gemma":[0.00007265342,0.0011050011,0.0003999272,0.0010724255,0.00078679767,1.68568e-8,0.9942697,0.0013215453,0.0009719242],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974287,0.00032902628,0.00035080742,0.0007971987,0.0006644319,0.00042984553],"domain_scores_gemma":[0.99688584,0.000038875776,0.00014737294,0.0020717573,0.00046533445,0.00039081828],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001019143,0.00023666737,0.0003935692,0.00027296704,0.0012302152,0.00072498625,0.0017972214,0.00018500238,0.039558783],"category_scores_gemma":[0.004004363,0.00023530601,0.00008405023,0.00045355913,0.00020952773,0.00012787961,0.0037547762,0.0013771399,0.00975246],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029636669,0.00016397709,3.0719906e-7,0.00029826784,0.00013560611,0.00044159632,0.000027716014,0.0000029849234,0.000114511706,0.000021728263,0.9565119,0.04225177],"study_design_scores_gemma":[0.0006825275,0.00013255893,0.000029841942,0.00023873587,0.0001740746,0.0015381189,0.000048676848,0.00049256516,0.000007736343,0.000012035584,0.99642676,0.00021634503],"about_ca_topic_score_codex":0.000046339428,"about_ca_topic_score_gemma":2.7995785e-7,"teacher_disagreement_score":0.042035427,"about_ca_system_score_codex":0.00013428455,"about_ca_system_score_gemma":0.00002176266,"threshold_uncertainty_score":0.99101853},"labels":[],"label_agreement":null},{"id":"W4393611621","doi":"10.5281/zenodo.3555322","title":"Large-scale purification of Q23 HTT-HAP40 from Sf9 expression system with contaminating nucleic acid material 2019/09/16","year":2019,"lang":"en","type":"dataset","venue":"Figshare","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Structural Genomics Consortium; Princess Margaret Cancer Centre; University of Toronto","funders":"","keywords":"Nucleic acid; Sf9; Scale (ratio); Chemistry; Expression (computer science); Molecular biology; Chromatography; Computational biology; Biology; Biochemistry; Computer science; Geography; Gene; Recombinant DNA; Cartography","score_opus":0.012824595505464519,"score_gpt":0.262656469747813,"score_spread":0.24983187424234846,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393611621","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024017994,0.00024134849,0.000030599767,0.00008076771,0.000359942,0.00074285665,0.995822,0.00007488827,0.00024580123],"genre_scores_gemma":[0.0069361296,0.00001195955,0.00038706692,0.00013215332,0.00074175553,0.00011562352,0.9913821,0.00007512055,0.00021808303],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977489,0.00012333502,0.0005548674,0.0005801972,0.0006391017,0.00035356174],"domain_scores_gemma":[0.9977336,0.00016961267,0.0008168449,0.0008934867,0.00020836343,0.00017807861],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00019061747,0.00037249248,0.0008542342,0.00015437449,0.000091510905,0.0000702188,0.00038396433,0.00043487235,0.061887164],"category_scores_gemma":[0.0007717731,0.00028597456,0.000117313815,0.0001207405,0.000019529363,0.00010492801,0.00018430647,0.00077175244,0.0014387284],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012469813,0.00007507278,0.00002629835,0.0032381425,0.000063120504,0.00004739769,0.000073090174,0.0000024863793,0.0062471693,0.000001010382,0.9898679,0.0002335991],"study_design_scores_gemma":[0.001789525,0.00019882827,0.00053518283,0.051160265,0.00018921132,0.000043013104,0.00033822312,0.0012032589,0.008040605,9.550987e-7,0.936098,0.00040297263],"about_ca_topic_score_codex":0.0001402669,"about_ca_topic_score_gemma":0.000006946496,"teacher_disagreement_score":0.060448434,"about_ca_system_score_codex":0.00015466374,"about_ca_system_score_gemma":0.00015340613,"threshold_uncertainty_score":0.99995923},"labels":[],"label_agreement":null},{"id":"W4393660674","doi":"10.5281/zenodo.7779321","title":"Dataset for the CHCHD10 antibody screening study","year":2023,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Montreal Neurological Institute and Hospital","funders":"","keywords":"Computer science","score_opus":0.05504061868672248,"score_gpt":0.3542337299391608,"score_spread":0.2991931112524383,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393660674","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000064904234,0.00010596603,0.0033781254,0.0032525193,0.00033997121,0.0020238028,0.9901897,0.0003713588,0.00027369318],"genre_scores_gemma":[0.000152375,0.00030570608,0.00016253816,0.0008211032,0.0008324591,3.4657546e-7,0.9955968,0.0016007335,0.0005279319],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973684,0.00030447368,0.00041377646,0.0006725224,0.0007200342,0.00052079465],"domain_scores_gemma":[0.99762255,0.00022488092,0.00020628318,0.0012307196,0.00046355533,0.00025202747],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0023135082,0.00027772147,0.00039748233,0.00034041735,0.0029314125,0.0007864766,0.0015440824,0.0001226722,0.0023855495],"category_scores_gemma":[0.005099623,0.00021514182,0.00011417046,0.0005816838,0.00022470928,0.00009290791,0.0017161537,0.0011883018,0.007237597],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000120918005,0.00023325217,0.0000019297718,0.00021830953,0.00029194544,0.00008513018,0.00010381512,0.000030216146,0.00006316921,0.000010068613,0.9746449,0.024196366],"study_design_scores_gemma":[0.0014348489,0.00060993555,0.00038255824,0.0001310307,0.00034408478,0.00016211135,0.0004565093,0.0016144599,0.0000020360758,0.0000077497725,0.99464005,0.00021461013],"about_ca_topic_score_codex":0.00023167918,"about_ca_topic_score_gemma":0.0000013129536,"teacher_disagreement_score":0.023981756,"about_ca_system_score_codex":0.00008271191,"about_ca_system_score_gemma":0.000010899565,"threshold_uncertainty_score":0.9985264},"labels":[],"label_agreement":null},{"id":"W4393678398","doi":"10.5281/zenodo.4584121","title":"pourmalek/covir2: 2.2 public release","year":2021,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Business","score_opus":0.03255734349033316,"score_gpt":0.2815169288183154,"score_spread":0.24895958532798226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393678398","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000405549,0.00079992163,0.0008832644,0.011093739,0.00050646,0.00068741955,0.9561293,0.00094027206,0.028554047],"genre_scores_gemma":[0.00068932265,0.0010823595,0.00027068748,0.0017399894,0.00080094114,5.4474647e-8,0.99221236,0.0015820629,0.0016222404],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99693775,0.0004975482,0.00043029737,0.0007282951,0.00080151955,0.000604565],"domain_scores_gemma":[0.9971818,0.000047550686,0.0002091851,0.00112162,0.0007720136,0.0006678808],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0009779497,0.00029948042,0.0004588773,0.00048663488,0.0016096977,0.0010855936,0.0010272206,0.0002410008,0.04469779],"category_scores_gemma":[0.0056934883,0.00030308505,0.00017026896,0.00068760273,0.00026442093,0.00014713072,0.0015235009,0.0017865308,0.011036507],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039846025,0.00024228726,0.000001302658,0.00037338334,0.00012241406,0.0005091628,0.000037855847,0.0000042945157,0.00020622276,0.00009075526,0.95095617,0.0474163],"study_design_scores_gemma":[0.0008763595,0.00017172506,0.00006513662,0.0002219581,0.00012436927,0.0014475511,0.00007219817,0.00024185015,0.00001609796,0.000016157488,0.99646926,0.0002773552],"about_ca_topic_score_codex":0.00004475596,"about_ca_topic_score_gemma":2.5989925e-7,"teacher_disagreement_score":0.047138944,"about_ca_system_score_codex":0.00025690423,"about_ca_system_score_gemma":0.000039182218,"threshold_uncertainty_score":0.99995136},"labels":[],"label_agreement":null},{"id":"W4393686370","doi":"10.5281/zenodo.3234178","title":"Purification of HTT mutant samples 2019/05/17","year":2019,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Structural Genomics Consortium; University of Toronto","funders":"","keywords":"Mutant; Computational biology; Biology; Genetics; Gene","score_opus":0.037099135205810006,"score_gpt":0.2924935005451949,"score_spread":0.2553943653393849,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393686370","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00056531583,0.00034798676,0.0012851537,0.0026702932,0.00039648058,0.0010316256,0.9844684,0.00030588466,0.008928877],"genre_scores_gemma":[0.0012425191,0.00083050964,0.00035317993,0.00032870486,0.0003142395,4.211318e-8,0.9947553,0.00092878036,0.0012466686],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977309,0.00024878647,0.00048504918,0.00051801105,0.000665134,0.00035213004],"domain_scores_gemma":[0.99777454,0.000055942994,0.0003627329,0.0010068635,0.0005698902,0.00023001106],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00091736903,0.00022941991,0.00045473274,0.00042639414,0.0005481618,0.00022365843,0.0009129837,0.00019144524,0.0121582905],"category_scores_gemma":[0.0019726562,0.00021792526,0.00012009303,0.0003914438,0.00024719382,0.00009211044,0.00066730153,0.00089291506,0.0053336634],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008227073,0.00017243729,0.000001141954,0.00048561333,0.00009807205,0.000022485148,0.00007707997,0.000025368576,0.0020151474,0.00011996057,0.97774625,0.01915419],"study_design_scores_gemma":[0.00072554755,0.00034703547,0.00017642736,0.0002708803,0.00012751395,0.00027338066,0.00004910495,0.00037922425,0.00013695324,0.000023258162,0.9972993,0.00019138979],"about_ca_topic_score_codex":0.00006305813,"about_ca_topic_score_gemma":1.495435e-7,"teacher_disagreement_score":0.01955305,"about_ca_system_score_codex":0.00014030618,"about_ca_system_score_gemma":0.000018824794,"threshold_uncertainty_score":0.9954408},"labels":[],"label_agreement":null},{"id":"W4393691466","doi":"10.5281/zenodo.4708697","title":"Confocal surface texture analysis included in the paper Paixao et al. 2021 - JASr. (supplemental to SOM3)","year":2021,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Trent University","funders":"","keywords":"Texture (cosmology); Surface (topology); Computer science; Artificial intelligence; Mathematics; Geometry; Image (mathematics)","score_opus":0.019736393018086284,"score_gpt":0.31027391436426704,"score_spread":0.29053752134618077,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393691466","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021000898,0.0003836894,0.00096751336,0.102640234,0.00023359168,0.0013931317,0.88520557,0.00017718885,0.006898992],"genre_scores_gemma":[0.0046928595,0.00051438616,0.00025418805,0.023640292,0.00017562741,1.421399e-7,0.96977687,0.0005771673,0.0003684987],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9961472,0.001129513,0.000484916,0.00072113716,0.0010166138,0.0005005962],"domain_scores_gemma":[0.99810445,0.00010606354,0.00014314825,0.0010186362,0.00032383547,0.00030386093],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0024116754,0.00029394584,0.00054151984,0.00043360394,0.00083439995,0.00077404216,0.0011577549,0.00014552768,0.057772364],"category_scores_gemma":[0.0019723135,0.00023768382,0.00018713088,0.0017977615,0.00015108543,0.0001078442,0.001569154,0.001757419,0.0021942987],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006272064,0.00025483928,0.000011318968,0.000070060894,0.00035715295,0.00032564523,0.0005131446,0.000168495,0.0005127954,0.00006064158,0.99256295,0.0051002237],"study_design_scores_gemma":[0.0008671488,0.0001830747,0.00047624664,0.000107914944,0.00032270036,0.00017481424,0.00074571115,0.0005907763,0.00001045436,0.0000055097607,0.9962784,0.00023725368],"about_ca_topic_score_codex":0.0004362878,"about_ca_topic_score_gemma":0.000021571357,"teacher_disagreement_score":0.08457127,"about_ca_system_score_codex":0.00026918238,"about_ca_system_score_gemma":0.000027675887,"threshold_uncertainty_score":0.9985826},"labels":[],"label_agreement":null},{"id":"W4393694735","doi":"10.5281/zenodo.5951194","title":"Wallops SuperDARN data in netCDF format (2020-Jun)","year":2022,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"NetCDF; Geology; Computer science; Operating system","score_opus":0.03363024756416159,"score_gpt":0.29504509239164967,"score_spread":0.26141484482748806,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393694735","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00035606307,0.0005751609,0.00012659913,0.0039122663,0.00045077674,0.00088223553,0.98275626,0.00048373314,0.010456906],"genre_scores_gemma":[0.0003193104,0.0018955572,0.0001598507,0.0010436465,0.00034971666,1.02672985e-7,0.994261,0.0012903692,0.00068044645],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9966151,0.00047314793,0.0005381348,0.00084206776,0.0009197642,0.00061176583],"domain_scores_gemma":[0.99727964,0.000054273092,0.00017290689,0.0019600044,0.00018501005,0.00034815696],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0019313608,0.00029245153,0.0004717353,0.0005174737,0.0012950519,0.00050630164,0.0027718474,0.00015680357,0.20266375],"category_scores_gemma":[0.0027701799,0.00029994643,0.00007471567,0.0007939072,0.00019174763,0.00026898418,0.006343744,0.002313192,0.0034176374],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009577264,0.00021203503,0.000004331491,0.00034105076,0.00006456317,0.00039679476,0.00013707689,0.000018225071,0.00003440933,0.000027265196,0.9660114,0.032657042],"study_design_scores_gemma":[0.0011842364,0.00025648833,0.00012336114,0.00012057106,0.0000766674,0.00088707113,0.0001468678,0.0016320761,0.0000014249421,0.000019826031,0.99527586,0.0002755314],"about_ca_topic_score_codex":0.00020659938,"about_ca_topic_score_gemma":0.0000023728196,"teacher_disagreement_score":0.19924612,"about_ca_system_score_codex":0.0003677168,"about_ca_system_score_gemma":0.000028018132,"threshold_uncertainty_score":0.9999885},"labels":[],"label_agreement":null},{"id":"W4393699231","doi":"10.5281/zenodo.6463434","title":"An interactive meta-analysis of MRI biomarkers of myelin","year":2022,"lang":"en","type":"dataset","venue":"PolyPublie (École Polytechnique de Montréal)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Montreal Heart Institute; Polytechnique Montréal","funders":"","keywords":"Myelin; Computer science; Computational biology; Neuroscience; Psychology; Biology","score_opus":0.017253144951763916,"score_gpt":0.30545586463522184,"score_spread":0.2882027196834579,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393699231","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012262199,0.0035898006,0.025799068,0.0033587366,0.00018281987,0.0010790556,0.96451813,0.00015851184,0.00008768059],"genre_scores_gemma":[0.0076790354,0.0010271956,0.021627827,0.0031247288,0.000096004675,0.00048248717,0.9656643,0.00010905054,0.00018933926],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.995663,0.0005703259,0.0013748346,0.0007894927,0.0010637116,0.0005386403],"domain_scores_gemma":[0.99514174,0.00044827154,0.0014750141,0.00221931,0.00025930852,0.00045636162],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0019965256,0.0005830948,0.003333054,0.0031451345,0.00011334565,0.00004155326,0.0009283593,0.00043530337,0.01216947],"category_scores_gemma":[0.00078982866,0.0005116372,0.0024681643,0.0020498808,0.00028305384,0.00014678432,0.00035129045,0.0017181472,0.0000022850643],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00049594126,0.0010217109,0.0008751335,0.0003067628,0.15947446,0.0001972277,0.0001285846,0.0036678917,0.0015376372,0.000084234656,0.83067465,0.0015357896],"study_design_scores_gemma":[0.0010296556,0.0011464441,0.0029950463,0.00006625721,0.43826216,0.00014096384,0.0003370537,0.094858445,0.0012522584,0.000102241844,0.45900342,0.00080604595],"about_ca_topic_score_codex":0.036150265,"about_ca_topic_score_gemma":0.0014044733,"teacher_disagreement_score":0.3716712,"about_ca_system_score_codex":0.00038739963,"about_ca_system_score_gemma":0.00048899173,"threshold_uncertainty_score":0.9997335},"labels":[],"label_agreement":null},{"id":"W4393740670","doi":"10.5281/zenodo.1490878","title":"Ruthwell Cross 3D Model High Resolution (112M poly count)","year":2018,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Lethbridge","funders":"","keywords":"Resolution (logic); Computer science; Artificial intelligence","score_opus":0.024892737719227932,"score_gpt":0.2920421882229112,"score_spread":0.2671494505036833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393740670","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00079631945,0.0003285697,0.0058367685,0.0014148758,0.00055066845,0.0007617726,0.9768576,0.0008567728,0.012596679],"genre_scores_gemma":[0.0013247941,0.0005024223,0.0011517691,0.000965662,0.0011464363,7.9619824e-8,0.9909973,0.0016532213,0.0022583231],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.996816,0.00027414077,0.0005065344,0.0007998169,0.00094118173,0.00066233444],"domain_scores_gemma":[0.9972841,0.00003312009,0.00027776917,0.0011038848,0.0008454657,0.0004556349],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0012612747,0.00034758577,0.00044664674,0.00041623387,0.0020836873,0.0008740191,0.0011375915,0.00032285572,0.012478796],"category_scores_gemma":[0.001903614,0.00034269603,0.000117638454,0.00043905218,0.00061388663,0.00017818177,0.0012542525,0.0013912306,0.009440002],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001940988,0.0001692116,8.9701e-7,0.00028441966,0.00008578812,0.00006279671,0.00008362317,0.0001709959,0.00015798853,0.00012052431,0.99070156,0.007968072],"study_design_scores_gemma":[0.0011361399,0.00037338337,0.000082899984,0.00022234386,0.00012628506,0.00033704037,0.0000135686805,0.020319894,0.000018618482,0.000080444166,0.9769745,0.0003148734],"about_ca_topic_score_codex":0.00020191769,"about_ca_topic_score_gemma":6.8805167e-7,"teacher_disagreement_score":0.020148898,"about_ca_system_score_codex":0.00041867877,"about_ca_system_score_gemma":0.00003164233,"threshold_uncertainty_score":0.9999025},"labels":[],"label_agreement":null},{"id":"W4393746456","doi":"10.5281/zenodo.7806382","title":"Test_MD_traj_for_MD2NMR","year":2023,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Test (biology); Computational biology; Computer science; Biology; Ecology","score_opus":0.03173908848096394,"score_gpt":0.2936810808340033,"score_spread":0.26194199235303933,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393746456","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00012995834,0.00012117733,0.0001928712,0.002784856,0.00048238825,0.00063038856,0.9775621,0.0017023386,0.016393887],"genre_scores_gemma":[0.00012754169,0.0004974687,0.00013444103,0.00057983096,0.0006298177,4.799425e-8,0.9936991,0.0022182257,0.0021135537],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99770105,0.00018199673,0.0003571511,0.0005864274,0.00066243915,0.00051095424],"domain_scores_gemma":[0.9982105,0.000052079056,0.00015271876,0.0008174577,0.0003682647,0.0003989672],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00083440304,0.00025915017,0.00038030976,0.0005076549,0.0014390748,0.00051662535,0.00094429986,0.0002041701,0.00869416],"category_scores_gemma":[0.0027088034,0.00025348456,0.00013999439,0.0006705822,0.00024067675,0.00007670801,0.0010729809,0.0013650793,0.0815483],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003794602,0.00012373326,4.2898876e-7,0.00034367485,0.00010568305,0.00021406688,0.000041252544,0.000008119777,0.000092384056,0.00006902648,0.97063,0.028333716],"study_design_scores_gemma":[0.00069508416,0.00028676633,0.00016098916,0.00022774204,0.00012185515,0.00061143056,0.000034427296,0.00020071531,0.000006817259,0.00005548631,0.9973666,0.00023210605],"about_ca_topic_score_codex":0.00009428291,"about_ca_topic_score_gemma":2.722485e-7,"teacher_disagreement_score":0.07285415,"about_ca_system_score_codex":0.00017664742,"about_ca_system_score_gemma":0.000011139119,"threshold_uncertainty_score":0.9999917},"labels":[],"label_agreement":null},{"id":"W4393761517","doi":"10.5281/zenodo.3234179","title":"Purification of HTT mutant samples 2019/05/17","year":2019,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Structural Genomics Consortium; University of Toronto","funders":"","keywords":"Mutant; Chemistry; Computational biology; Molecular biology; Biology; Genetics; Gene","score_opus":0.037099135205810006,"score_gpt":0.2924935005451949,"score_spread":0.2553943653393849,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393761517","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00056531583,0.00034798676,0.0012851537,0.0026702932,0.00039648058,0.0010316256,0.9844684,0.00030588466,0.008928877],"genre_scores_gemma":[0.0012425191,0.00083050964,0.00035317993,0.00032870486,0.0003142395,4.211318e-8,0.9947553,0.00092878036,0.0012466686],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977309,0.00024878647,0.00048504918,0.00051801105,0.000665134,0.00035213004],"domain_scores_gemma":[0.99777454,0.000055942994,0.0003627329,0.0010068635,0.0005698902,0.00023001106],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00091736903,0.00022941991,0.00045473274,0.00042639414,0.0005481618,0.00022365843,0.0009129837,0.00019144524,0.0121582905],"category_scores_gemma":[0.0019726562,0.00021792526,0.00012009303,0.0003914438,0.00024719382,0.00009211044,0.00066730153,0.00089291506,0.0053336634],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008227073,0.00017243729,0.000001141954,0.00048561333,0.00009807205,0.000022485148,0.00007707997,0.000025368576,0.0020151474,0.00011996057,0.97774625,0.01915419],"study_design_scores_gemma":[0.00072554755,0.00034703547,0.00017642736,0.0002708803,0.00012751395,0.00027338066,0.00004910495,0.00037922425,0.00013695324,0.000023258162,0.9972993,0.00019138979],"about_ca_topic_score_codex":0.00006305813,"about_ca_topic_score_gemma":1.495435e-7,"teacher_disagreement_score":0.01955305,"about_ca_system_score_codex":0.00014030618,"about_ca_system_score_gemma":0.000018824794,"threshold_uncertainty_score":0.9954408},"labels":[],"label_agreement":null},{"id":"W4393781477","doi":"10.5281/zenodo.6463435","title":"An interactive meta-analysis of MRI biomarkers of myelin","year":2022,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Montreal Heart Institute; Polytechnique Montréal","funders":"","keywords":"Myelin; Computational biology; Meta-analysis; Computer science; Chemistry; Neuroscience; Biology; Medicine; Pathology","score_opus":0.04701107296060253,"score_gpt":0.32992606352412374,"score_spread":0.2829149905635212,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393781477","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003278813,0.00031129824,0.00081940833,0.000876901,0.000097216485,0.00047006417,0.993998,0.00013009421,0.0029691271],"genre_scores_gemma":[0.0031021973,0.00023767774,0.00029512017,0.00023492087,0.000047619145,7.889159e-8,0.99535847,0.0005969873,0.00012691095],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9971441,0.0007757503,0.0005810791,0.00049812754,0.0007659703,0.00023499942],"domain_scores_gemma":[0.99761057,0.00008699713,0.00054346526,0.000982102,0.0005637329,0.00021311616],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0015220098,0.00020545658,0.001054278,0.0013330102,0.00044778493,0.000098893724,0.0010149918,0.00009310514,0.30653438],"category_scores_gemma":[0.0012749023,0.0001869141,0.0006000647,0.0014525849,0.00026725628,0.00009628607,0.00084911566,0.0007884983,0.00014489346],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018615302,0.00034561852,9.045029e-7,0.00019253057,0.05005378,0.00003132077,0.0002391555,0.0002675966,0.0005884798,0.00002372081,0.9442451,0.0038256163],"study_design_scores_gemma":[0.00034689845,0.00048656826,0.00006789737,0.000012820798,0.04987039,0.000040678002,0.00025467726,0.0014728071,0.000052687286,0.0000066862876,0.94725335,0.0001345228],"about_ca_topic_score_codex":0.00022212396,"about_ca_topic_score_gemma":7.439113e-7,"teacher_disagreement_score":0.30638948,"about_ca_system_score_codex":0.00011952038,"about_ca_system_score_gemma":0.000012823927,"threshold_uncertainty_score":0.7622136},"labels":[],"label_agreement":null},{"id":"W4393805907","doi":"10.5281/zenodo.3234171","title":"Coexpression and purification of HTT and HTT-HAP40 with NEDD4L and HAP1 2019/05/02","year":2019,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Statistics; Mathematics","score_opus":0.019748828238745592,"score_gpt":0.2687576251596283,"score_spread":0.2490087969208827,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393805907","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0893871,0.005599657,0.0022174614,0.010339746,0.00048463285,0.0045994483,0.8753007,0.0006877112,0.01138354],"genre_scores_gemma":[0.016225662,0.0056791487,0.0010703591,0.0004091849,0.00022504601,1.1079145e-7,0.9740513,0.0010392996,0.0012998793],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984779,0.00017613545,0.00026222097,0.00047581285,0.0003850798,0.00022287446],"domain_scores_gemma":[0.9987544,0.00005466867,0.00022316232,0.00045894444,0.0002689604,0.00023990778],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005646573,0.00019397763,0.00034928357,0.00025900415,0.0004923929,0.00024502247,0.00024966357,0.00013534786,0.0010606251],"category_scores_gemma":[0.00071015937,0.00016004064,0.000021603997,0.00017759482,0.00038896396,0.000120223754,0.0005867828,0.0005968637,0.00017862991],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017577635,0.00006717665,0.000021323305,0.0006944809,0.000055803583,0.000017794717,0.00018187064,0.000002909476,0.00184716,0.00006237459,0.97126997,0.025603393],"study_design_scores_gemma":[0.0012079579,0.0005889011,0.0014501365,0.00047963212,0.00011401581,0.00047497725,0.000090650356,0.000576962,0.00006440349,0.00001693727,0.99477226,0.00016314545],"about_ca_topic_score_codex":0.00005868431,"about_ca_topic_score_gemma":2.0078319e-7,"teacher_disagreement_score":0.098750606,"about_ca_system_score_codex":0.000033992546,"about_ca_system_score_gemma":0.000008892521,"threshold_uncertainty_score":0.99985254},"labels":[],"label_agreement":null},{"id":"W4393807014","doi":"10.5281/zenodo.10526884","title":"Dataset related to article \"Diagnostic accuracy of multiparametric MRI- and microultrasound-targeted biopsy in biopsy-naïve patients with a PI-RADS 5 lesion: a single-institutional study \"","year":2024,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University and Génome Québec Innovation Centre","funders":"","keywords":"Biopsy; Medicine; Radiology; Diagnostic accuracy; Multiparametric MRI; Lesion; Nuclear medicine; Pathology; Internal medicine; Cancer","score_opus":0.021109954814767556,"score_gpt":0.28895139822084365,"score_spread":0.2678414434060761,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393807014","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38543624,0.00020479881,0.00010574075,0.0004604119,0.00012212715,0.0016133265,0.6118634,0.00012097284,0.00007300552],"genre_scores_gemma":[0.2311667,0.00006268443,0.0004276125,0.00010127389,0.000040851468,3.1902547e-7,0.767792,0.000393549,0.000014984343],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974691,0.0002861993,0.00054875825,0.0007001175,0.0006403732,0.0003554053],"domain_scores_gemma":[0.9983555,0.00022917193,0.00018295897,0.00057617365,0.00034221148,0.00031399043],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0006992,0.00026654475,0.0004194136,0.0010429106,0.00042223782,0.00031103354,0.0004754207,0.00012073408,0.0009566256],"category_scores_gemma":[0.008994803,0.0002291863,0.00003735077,0.0018958024,0.00027179858,0.00013757702,0.0007910896,0.00088448473,0.0016029442],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039627677,0.00236454,0.0013214597,0.00052951934,0.00021981115,0.00049593643,0.0005980973,0.000115165654,0.0008718047,0.000010700689,0.98531425,0.0077624237],"study_design_scores_gemma":[0.0038384995,0.0017307558,0.03633487,0.00095286337,0.0002741382,0.00055451575,0.0002643915,0.00042152472,0.000027298038,0.00001121717,0.9552417,0.00034823615],"about_ca_topic_score_codex":0.00017124134,"about_ca_topic_score_gemma":0.0000015970256,"teacher_disagreement_score":0.15592864,"about_ca_system_score_codex":0.00020604246,"about_ca_system_score_gemma":0.000023560673,"threshold_uncertainty_score":0.9999566},"labels":[],"label_agreement":null},{"id":"W4393826639","doi":"10.5281/zenodo.2651349","title":"Gold standard for tractogram io testing","year":2019,"lang":"en","type":"dataset","venue":"Figshare","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Computer science","score_opus":0.07003059468852822,"score_gpt":0.3568816584200188,"score_spread":0.28685106373149055,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393826639","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000022970185,0.00033526262,0.000005531869,0.0002952663,0.0002742982,0.00096008484,0.9974855,0.00007683077,0.000564925],"genre_scores_gemma":[0.000007556264,0.000008608747,0.0012711483,0.0013733358,0.0011691429,0.00022923632,0.9950196,0.00006410446,0.0008572729],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984313,0.000020432084,0.00031265628,0.0004361391,0.00038946114,0.00040997492],"domain_scores_gemma":[0.9980493,0.00072096556,0.0002415748,0.00053693075,0.00022927872,0.00022191313],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00014037646,0.00029889809,0.00061340246,0.00013245299,0.00005896837,0.000088183886,0.0002695339,0.00034237682,0.04626952],"category_scores_gemma":[0.01473135,0.00025662823,0.00021278323,0.0001489036,0.000009959229,0.000041595606,0.000091731104,0.0011206651,0.0013505971],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004063417,0.000032713993,0.0000074275226,0.0029854188,0.000056876608,0.00005920584,0.0000043929085,0.000008581512,0.000005878787,1.6340387e-7,0.98207635,0.014722379],"study_design_scores_gemma":[0.0010271375,0.00035551068,0.00007460626,0.008245015,0.00014745675,0.000077542914,0.000004728258,0.0008937989,0.0000061577725,0.000005674958,0.98889405,0.00026833906],"about_ca_topic_score_codex":0.000018023986,"about_ca_topic_score_gemma":0.0000022664194,"teacher_disagreement_score":0.044918925,"about_ca_system_score_codex":0.00008737516,"about_ca_system_score_gemma":0.00035675123,"threshold_uncertainty_score":0.9999886},"labels":[],"label_agreement":null},{"id":"W4393833275","doi":"10.5281/zenodo.7779320","title":"Dataset for the CHCHD10 antibody screening study","year":2023,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Montreal Neurological Institute and Hospital","funders":"","keywords":"Computer science","score_opus":0.05504061868672248,"score_gpt":0.3542337299391608,"score_spread":0.2991931112524383,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393833275","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000064904234,0.00010596603,0.0033781254,0.0032525193,0.00033997121,0.0020238028,0.9901897,0.0003713588,0.00027369318],"genre_scores_gemma":[0.000152375,0.00030570608,0.00016253816,0.0008211032,0.0008324591,3.4657546e-7,0.9955968,0.0016007335,0.0005279319],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973684,0.00030447368,0.00041377646,0.0006725224,0.0007200342,0.00052079465],"domain_scores_gemma":[0.99762255,0.00022488092,0.00020628318,0.0012307196,0.00046355533,0.00025202747],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0023135082,0.00027772147,0.00039748233,0.00034041735,0.0029314125,0.0007864766,0.0015440824,0.0001226722,0.0023855495],"category_scores_gemma":[0.005099623,0.00021514182,0.00011417046,0.0005816838,0.00022470928,0.00009290791,0.0017161537,0.0011883018,0.007237597],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000120918005,0.00023325217,0.0000019297718,0.00021830953,0.00029194544,0.00008513018,0.00010381512,0.000030216146,0.00006316921,0.000010068613,0.9746449,0.024196366],"study_design_scores_gemma":[0.0014348489,0.00060993555,0.00038255824,0.0001310307,0.00034408478,0.00016211135,0.0004565093,0.0016144599,0.0000020360758,0.0000077497725,0.99464005,0.00021461013],"about_ca_topic_score_codex":0.00023167918,"about_ca_topic_score_gemma":0.0000013129536,"teacher_disagreement_score":0.023981756,"about_ca_system_score_codex":0.00008271191,"about_ca_system_score_gemma":0.000010899565,"threshold_uncertainty_score":0.9985264},"labels":[],"label_agreement":null},{"id":"W4393840607","doi":"10.5281/zenodo.5951193","title":"Wallops SuperDARN data in netCDF format (2020-Jun)","year":2022,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"NetCDF; Geology; Computer science; Meteorology; Computer graphics (images); Geography; Operating system","score_opus":0.03363024756416159,"score_gpt":0.29504509239164967,"score_spread":0.26141484482748806,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393840607","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00035606307,0.0005751609,0.00012659913,0.0039122663,0.00045077674,0.00088223553,0.98275626,0.00048373314,0.010456906],"genre_scores_gemma":[0.0003193104,0.0018955572,0.0001598507,0.0010436465,0.00034971666,1.02672985e-7,0.994261,0.0012903692,0.00068044645],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9966151,0.00047314793,0.0005381348,0.00084206776,0.0009197642,0.00061176583],"domain_scores_gemma":[0.99727964,0.000054273092,0.00017290689,0.0019600044,0.00018501005,0.00034815696],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0019313608,0.00029245153,0.0004717353,0.0005174737,0.0012950519,0.00050630164,0.0027718474,0.00015680357,0.20266375],"category_scores_gemma":[0.0027701799,0.00029994643,0.00007471567,0.0007939072,0.00019174763,0.00026898418,0.006343744,0.002313192,0.0034176374],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009577264,0.00021203503,0.000004331491,0.00034105076,0.00006456317,0.00039679476,0.00013707689,0.000018225071,0.00003440933,0.000027265196,0.9660114,0.032657042],"study_design_scores_gemma":[0.0011842364,0.00025648833,0.00012336114,0.00012057106,0.0000766674,0.00088707113,0.0001468678,0.0016320761,0.0000014249421,0.000019826031,0.99527586,0.0002755314],"about_ca_topic_score_codex":0.00020659938,"about_ca_topic_score_gemma":0.0000023728196,"teacher_disagreement_score":0.19924612,"about_ca_system_score_codex":0.0003677168,"about_ca_system_score_gemma":0.000028018132,"threshold_uncertainty_score":0.9999885},"labels":[],"label_agreement":null},{"id":"W4393869721","doi":"10.5194/gmd-2023-239-rc2","title":"Comment on gmd-2023-239","year":2024,"lang":"en","type":"peer-review","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"GDG Environnement","funders":"National Science Foundation","keywords":"Statistics; Mathematics; Environmental science","score_opus":0.02735177512190369,"score_gpt":0.36408859146278744,"score_spread":0.33673681634088376,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393869721","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000001745801,0.035318,0.00010113306,0.6696573,0.004501617,0.00043554493,0.000035757654,0.000155968,0.28979293],"genre_scores_gemma":[0.00001147837,0.009585427,0.0005822908,0.37050864,0.0012883607,0.000030944877,0.000988814,0.00006582899,0.6169382],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978064,0.00005631189,0.00045381513,0.0005493959,0.00079125585,0.00034285447],"domain_scores_gemma":[0.99874014,0.0001619302,0.000089155146,0.0006223824,0.0000796544,0.0003067405],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00070912467,0.0003767894,0.000939538,0.0001959483,0.000047397512,0.000045761884,0.00020099164,0.00021203328,0.007855078],"category_scores_gemma":[0.00052322453,0.00025312437,0.0003757126,0.00019732457,0.000067464876,0.000011100278,0.00013548245,0.0023717454,0.003400815],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000074158434,0.00007248642,0.0000033389508,0.0075471257,0.0001539542,0.00027466283,0.0000094519755,6.7678735e-7,0.0000022887505,0.0010501905,0.9555952,0.035283234],"study_design_scores_gemma":[0.00032714524,0.00019546783,0.000005354785,0.024863342,0.0007186289,0.000097115015,0.0000046620685,0.00064346154,0.0000050684944,0.00016334753,0.9727395,0.00023688679],"about_ca_topic_score_codex":0.00019167966,"about_ca_topic_score_gemma":0.0000045194106,"teacher_disagreement_score":0.32714528,"about_ca_system_score_codex":0.0001759533,"about_ca_system_score_gemma":0.00019498268,"threshold_uncertainty_score":0.9999921},"labels":[],"label_agreement":null},{"id":"W4393895664","doi":"10.5281/zenodo.4028817","title":"AbdulAli/replication-kit-emse-2020-benchmark: Second Release","year":2020,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Replication (statistics); Benchmark (surveying); Computer science; Environmental science; Biology; Geology; Virology; Geodesy","score_opus":0.02168605006693855,"score_gpt":0.2792266635721622,"score_spread":0.2575406135052236,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393895664","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00024149062,0.00041304049,0.0005861634,0.008454107,0.00036509914,0.0011868231,0.9518248,0.0009816942,0.03594679],"genre_scores_gemma":[0.001001888,0.0007759586,0.00030182282,0.0028359669,0.001022283,1.73324e-7,0.9915595,0.0012846414,0.0012177365],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9967013,0.0003538661,0.0005681668,0.0010836001,0.00076075614,0.000532323],"domain_scores_gemma":[0.99679285,0.00005932014,0.00031314645,0.0015340096,0.0005369009,0.00076379324],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0008500639,0.00036056852,0.0005185024,0.00029868406,0.0014300174,0.0006488229,0.00129097,0.00024519593,0.049594335],"category_scores_gemma":[0.0042739282,0.00036905924,0.00017174611,0.0006909028,0.00027846752,0.00013478295,0.0009850546,0.0017861538,0.01915847],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009371774,0.00014962064,0.000001016994,0.00068180874,0.00013202723,0.00020125366,0.00010588768,0.000007020774,0.00046950992,0.000093413815,0.9521971,0.045867678],"study_design_scores_gemma":[0.00092511484,0.0002909537,0.00020131723,0.00020831799,0.00014476839,0.0006355711,0.000059663667,0.00066460675,0.00003786719,0.00004181863,0.99645376,0.000336258],"about_ca_topic_score_codex":0.00003150926,"about_ca_topic_score_gemma":3.576915e-7,"teacher_disagreement_score":0.04553142,"about_ca_system_score_codex":0.0002439281,"about_ca_system_score_gemma":0.00002964959,"threshold_uncertainty_score":0.99987614},"labels":[],"label_agreement":null},{"id":"W4393908736","doi":"10.55124/jaim.v1i1.33","title":"Machine learning-based survival prediction in glioma using large scale registry data–the importance of chemotherapy and radiation therapy management as predictive features","year":2021,"lang":"en","type":"article","venue":"Journal of Artificial intelligence and Machine Learning","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Radiation therapy; Scale (ratio); Glioma; Machine learning; Artificial intelligence; Medicine; Computer science; Oncology; Medical physics; Internal medicine; Cartography; Geography; Cancer research","score_opus":0.029189613611148302,"score_gpt":0.3252552431161357,"score_spread":0.2960656295049874,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393908736","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9488031,0.008473056,0.039377693,0.0027274468,0.000231748,0.00021460142,0.000011453659,0.000018037155,0.00014284038],"genre_scores_gemma":[0.9920738,0.005179699,0.0019396252,0.0003372535,0.0002764763,0.0000017229169,0.000060116883,0.000028766142,0.00010258279],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99798554,0.0002967137,0.00071409263,0.00030779425,0.00045936203,0.00023650825],"domain_scores_gemma":[0.9986565,0.00021323087,0.0006067226,0.0002385994,0.00016660802,0.00011832364],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020048018,0.0001843292,0.00043642154,0.00022884354,0.00020247034,0.00006728706,0.00016296933,0.0000952805,0.00006431978],"category_scores_gemma":[0.0006453454,0.00013887002,0.00008087601,0.0004031818,0.0001628534,0.00019471187,0.000084607535,0.0012051164,4.439931e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0030672965,0.00064370787,0.66292727,0.00027791012,0.0004106452,0.0006046501,0.0028198287,0.047788482,0.01809462,0.0005134423,0.00006213728,0.26279002],"study_design_scores_gemma":[0.0014673824,0.001032052,0.053953912,0.00051254535,0.00018139325,0.0007924792,0.0031701208,0.92442536,0.009487667,0.0007558102,0.004027398,0.00019385543],"about_ca_topic_score_codex":0.00013350787,"about_ca_topic_score_gemma":0.000052285683,"teacher_disagreement_score":0.8766369,"about_ca_system_score_codex":0.000049562248,"about_ca_system_score_gemma":0.00012600058,"threshold_uncertainty_score":0.5662955},"labels":[],"label_agreement":null},{"id":"W4393930088","doi":"10.1007/s12149-024-01923-7","title":"The effect of harmonization on the variability of PET radiomic features extracted using various segmentation methods","year":2024,"lang":"en","type":"article","venue":"Annals of Nuclear Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Douglas Mental Health University Institute","funders":"Université de Genève; Tehran University of Medical Sciences and Health Services; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Medicine; Harmonization; Segmentation; Medical physics; Nuclear medicine; Artificial intelligence; Radiology","score_opus":0.03503470101941309,"score_gpt":0.40985376273014107,"score_spread":0.374819061710728,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393930088","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9690295,0.0015537424,0.0046254224,0.022829711,0.0004573961,0.00051103334,0.0000042767374,0.000039871436,0.0009490703],"genre_scores_gemma":[0.99608314,0.00039336717,0.0026424676,0.00061472994,0.00016287052,0.0000027003941,0.000011195976,0.000031087555,0.00005843576],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99803025,0.0007404902,0.0004765556,0.00018405195,0.0004203423,0.00014833045],"domain_scores_gemma":[0.9960682,0.003149666,0.00023636762,0.00033383927,0.00014780289,0.00006411525],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0051837214,0.00013527792,0.00042866782,0.00012193863,0.000104250605,0.000008356048,0.00014285585,0.00005257924,0.00012206078],"category_scores_gemma":[0.00436196,0.0000643452,0.00011611823,0.0003802813,0.0005274946,0.000042242093,0.000028206265,0.00041696543,0.0000010857577],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012463697,0.00012205843,0.0024635328,0.0014988302,0.00075144554,0.000046831236,0.0031200212,0.00041692617,0.84249145,0.005466899,0.01486069,0.12751497],"study_design_scores_gemma":[0.00593372,0.011618273,0.15132008,0.009224795,0.0031827185,0.0009961192,0.0013645387,0.5547571,0.23464018,0.0040953914,0.022320198,0.0005468449],"about_ca_topic_score_codex":0.00014615186,"about_ca_topic_score_gemma":2.753105e-7,"teacher_disagreement_score":0.60785127,"about_ca_system_score_codex":0.000023191453,"about_ca_system_score_gemma":0.000051441348,"threshold_uncertainty_score":0.5221989},"labels":[],"label_agreement":null},{"id":"W4393985262","doi":"10.1158/1538-7445.am2024-lb396","title":"Abstract LB396: The power of NetraAI: Precision medicine in oncology through sub-insight learning from small data sets","year":2024,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Medicine; Precision oncology; Clinical Oncology; Oncology; Internal medicine; Medical physics; Cancer","score_opus":0.19733868170692995,"score_gpt":0.48915427810643963,"score_spread":0.2918155963995097,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393985262","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91520363,0.031803474,0.00034708958,0.038565017,0.0007287221,0.00048589226,0.000018456696,0.000049791266,0.012797952],"genre_scores_gemma":[0.9912315,0.0069396948,0.00026008624,0.00038867467,0.0005599938,0.000029291072,0.00012458152,0.000043411143,0.0004227792],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.997253,0.0003819352,0.0004587874,0.00057768944,0.0008617802,0.00046681528],"domain_scores_gemma":[0.9960923,0.0028048337,0.000061055005,0.0007484895,0.00015355836,0.00013974571],"candidate_categories":["research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0038329866,0.0001421094,0.00041680562,0.0002471627,0.00010551456,0.00003771558,0.00064892694,0.00015148381,0.0012646843],"category_scores_gemma":[0.0026257879,0.000084907464,0.00004606473,0.00075411965,0.0006007673,0.00012913776,0.00039189777,0.003052774,0.00003956451],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009002676,0.00026179076,0.01506196,0.0006423097,0.00034277886,0.001660773,0.020361729,0.000631118,0.19423723,0.0006423466,0.08805206,0.6772056],"study_design_scores_gemma":[0.0027149,0.0008719329,0.07536609,0.005439188,0.000099267774,0.000056663946,0.0022250062,0.027944487,0.0040406585,0.0023494663,0.8786532,0.00023911966],"about_ca_topic_score_codex":0.008495421,"about_ca_topic_score_gemma":0.00041747652,"teacher_disagreement_score":0.79060113,"about_ca_system_score_codex":0.00026848537,"about_ca_system_score_gemma":0.0007281797,"threshold_uncertainty_score":0.9996483},"labels":[],"label_agreement":null},{"id":"W4394037768","doi":"10.5281/zenodo.5808388","title":"Head-Neck-PET-CT combined GTVs 2D images","year":2021,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Head and neck; Head (geology); Nuclear medicine; Medicine; Geology; Surgery","score_opus":0.022436888563803867,"score_gpt":0.2956641792817873,"score_spread":0.2732272907179834,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394037768","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001377087,0.00072836026,0.0003433481,0.006746402,0.0007515461,0.0010123951,0.95712256,0.001135376,0.030782916],"genre_scores_gemma":[0.0010201759,0.0010581011,0.00040377997,0.001271185,0.0005516907,8.435728e-8,0.9915004,0.0017361549,0.0024584339],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9968052,0.00045853856,0.00049469195,0.000798488,0.00083055964,0.000612512],"domain_scores_gemma":[0.9974222,0.00005828217,0.0002229047,0.0011559295,0.0006230215,0.00051764154],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00085770787,0.00036404398,0.00060521194,0.0004072627,0.0015094078,0.00087276095,0.0010626385,0.000072742296,0.031954944],"category_scores_gemma":[0.0032808718,0.00036225497,0.00018349991,0.00062208803,0.0003215662,0.0001228544,0.0015587213,0.0017460198,0.008649897],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000082359926,0.0003008158,0.0000016830747,0.0005293317,0.00015881284,0.0021141027,0.00003311526,0.0000069623497,0.00033739628,0.000048604157,0.9778509,0.01853589],"study_design_scores_gemma":[0.0015188238,0.00038162599,0.00012478254,0.0004453908,0.00015964107,0.0036242441,0.00007530714,0.00021827154,0.000071001195,0.000025188743,0.9930252,0.00033052402],"about_ca_topic_score_codex":0.00010198176,"about_ca_topic_score_gemma":4.3618743e-7,"teacher_disagreement_score":0.034377825,"about_ca_system_score_codex":0.00024337086,"about_ca_system_score_gemma":0.000029351895,"threshold_uncertainty_score":0.99988294},"labels":[],"label_agreement":null},{"id":"W4394049318","doi":"10.5281/zenodo.7027914","title":"Diffusion MRI quality control reports for the BTC datasets","year":2022,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Diffusion; Quality (philosophy); Computer science; Control (management); Diffusion MRI; Data mining; Medicine; Artificial intelligence; Physics; Radiology; Magnetic resonance imaging","score_opus":0.02952938042458884,"score_gpt":0.3165052443214618,"score_spread":0.28697586389687296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394049318","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000040546875,0.0003711192,0.0047398787,0.0063530994,0.00062125426,0.0017597097,0.98468804,0.00032055605,0.0011058043],"genre_scores_gemma":[0.0005178235,0.0005045772,0.00010206353,0.0018531592,0.0005110001,6.4033935e-7,0.99504274,0.0009700897,0.00049789646],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9967308,0.00059064344,0.0006132082,0.0007096823,0.00089293293,0.00046270402],"domain_scores_gemma":[0.9971085,0.00030640158,0.0004505551,0.0015408832,0.00031474003,0.00027889528],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0031220317,0.00026254982,0.0004460838,0.00020798323,0.0035536187,0.00048888143,0.0010645967,0.00012702406,0.078443274],"category_scores_gemma":[0.0066854707,0.00020542437,0.00017459283,0.0003168443,0.00025300853,0.000082382656,0.0014765823,0.0013351112,0.00041854836],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021839236,0.00019484878,9.5182855e-7,0.00024890402,0.00014163845,0.00013424939,0.00006811537,0.000030300751,0.00019444757,0.00006570432,0.97167706,0.027025385],"study_design_scores_gemma":[0.0013525237,0.0002985002,0.00014403914,0.00006792418,0.000250884,0.00076910807,0.000104977815,0.0007746142,0.0000046355412,0.00004052747,0.99597555,0.00021669289],"about_ca_topic_score_codex":0.0001658541,"about_ca_topic_score_gemma":6.118144e-7,"teacher_disagreement_score":0.07802472,"about_ca_system_score_codex":0.00021609633,"about_ca_system_score_gemma":0.000018062523,"threshold_uncertainty_score":0.9977436},"labels":[],"label_agreement":null},{"id":"W4394056469","doi":"10.5281/zenodo.6799604","title":"Perron_et_al_2022_Supplementary_Datasets","year":2022,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science","score_opus":0.025521871234380877,"score_gpt":0.2916849995552838,"score_spread":0.26616312832090294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394056469","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00005114913,0.00013811706,0.00006364087,0.0028174145,0.00029287091,0.00051758916,0.99134046,0.0003469148,0.0044318167],"genre_scores_gemma":[0.000060977873,0.00046187968,0.000115060044,0.0014698354,0.0003138884,1.0202581e-7,0.9958646,0.0011678861,0.00054572296],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99741584,0.00035915466,0.00035427205,0.0006097173,0.00081067235,0.00045031754],"domain_scores_gemma":[0.99840796,0.000029700526,0.00015689773,0.0009030111,0.00015693091,0.000345489],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0008542887,0.0002451911,0.00033954025,0.00039894297,0.0023483154,0.00038409012,0.001176012,0.00009147507,0.7390674],"category_scores_gemma":[0.0008264174,0.00025652154,0.000120100754,0.00040643598,0.00017361616,0.00009940267,0.0025833326,0.0015717158,0.004981725],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007181062,0.0002122706,3.7879516e-7,0.00022804216,0.00011207987,0.00023118847,0.00006153676,0.000010004813,0.000051748397,0.00003222596,0.97510064,0.023888059],"study_design_scores_gemma":[0.00082136685,0.0004454016,0.000024139932,0.00004448232,0.00014517808,0.0009380497,0.00013906865,0.00009337521,0.0000037831583,0.000013649543,0.99709636,0.00023512218],"about_ca_topic_score_codex":0.00013357072,"about_ca_topic_score_gemma":3.720743e-7,"teacher_disagreement_score":0.7340856,"about_ca_system_score_codex":0.0003351273,"about_ca_system_score_gemma":0.000012389777,"threshold_uncertainty_score":0.9999887},"labels":[],"label_agreement":null},{"id":"W4394074439","doi":"10.6084/m9.figshare.19619655","title":"Images Meta Data","year":2022,"lang":"en","type":"dataset","venue":"Figshare","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Computer science","score_opus":0.10811987772625513,"score_gpt":0.3703712815465138,"score_spread":0.26225140382025863,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394074439","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.6551682e-8,0.003779631,2.2433046e-7,0.0011019266,0.00017225054,0.00025360467,0.99398196,0.00006923948,0.0006411208],"genre_scores_gemma":[1.9423707e-7,0.00012665067,0.000116039264,0.0030311092,0.0005277577,0.00016562584,0.99467856,0.000042360094,0.0013117143],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982351,0.000072058385,0.00024636005,0.0006088029,0.00056313875,0.00027451786],"domain_scores_gemma":[0.9971852,0.00019694799,0.00017672975,0.0022008228,0.000042906584,0.00019741432],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00017614289,0.000269203,0.00064318086,0.00013573238,0.000119559896,0.000062964275,0.0011824172,0.00013322778,0.98265165],"category_scores_gemma":[0.005731259,0.00021774667,0.0001839403,0.00015615924,0.000011773866,0.000075044016,0.0019052539,0.0017278497,0.0018680412],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000062860877,0.000047728827,3.3127054e-7,0.00071760983,0.0007082767,0.0006554647,0.0000015275294,0.000001634041,7.3420375e-7,7.547805e-8,0.99663067,0.001229691],"study_design_scores_gemma":[0.00025808346,0.000043816362,0.00001660655,0.00041257904,0.0018036463,0.00020502403,0.0000036307367,0.000109109955,0.0000013580741,0.0000021813185,0.9969395,0.00020445806],"about_ca_topic_score_codex":0.00008463439,"about_ca_topic_score_gemma":0.0000022390982,"teacher_disagreement_score":0.9807836,"about_ca_system_score_codex":0.000044056345,"about_ca_system_score_gemma":0.00025191845,"threshold_uncertainty_score":0.9989091},"labels":[],"label_agreement":null},{"id":"W4394088186","doi":"10.6084/m9.figshare.20318241","title":"2022-v2-9classes-AsturApple-SIZE224-train-dev-test.hdf5","year":2022,"lang":"en","type":"dataset","venue":"Figshare","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Test (biology); Computer science; Geology; Paleontology","score_opus":0.022110307116025293,"score_gpt":0.30877700648391554,"score_spread":0.28666669936789024,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394088186","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000004302623,0.0013880751,6.2915245e-7,0.0016525381,0.0006040892,0.0007379948,0.9937221,0.0001950551,0.0016952222],"genre_scores_gemma":[0.000014795858,0.00018147512,0.0000976443,0.005145059,0.0014999309,0.0005883578,0.98864025,0.00012589309,0.0037065805],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99640363,0.00012925333,0.0005989908,0.000921727,0.0011819188,0.0007644663],"domain_scores_gemma":[0.99676645,0.0008937168,0.0004089102,0.0012606774,0.00013071999,0.0005395307],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0002634602,0.00064492837,0.0009857072,0.00036130063,0.00032933606,0.00012889145,0.0008734482,0.00042742293,0.9412098],"category_scores_gemma":[0.009492651,0.0005985899,0.00043701133,0.00052256277,0.000037236256,0.00008039008,0.00072574225,0.004252693,0.0036545882],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024165185,0.00018929856,0.000016909456,0.0013315952,0.00013792468,0.0013346127,0.000020252899,0.000005858132,0.000016970895,9.25879e-7,0.9932396,0.003681883],"study_design_scores_gemma":[0.0011020845,0.0002625547,0.000391609,0.002099966,0.00017416633,0.00043460523,0.0000386907,0.00020595845,0.0000052618557,0.000011640196,0.9946965,0.0005769846],"about_ca_topic_score_codex":0.00008500788,"about_ca_topic_score_gemma":0.000015919419,"teacher_disagreement_score":0.9375552,"about_ca_system_score_codex":0.00028000938,"about_ca_system_score_gemma":0.0006713563,"threshold_uncertainty_score":0.99964654},"labels":[],"label_agreement":null},{"id":"W4394115072","doi":"10.6084/m9.figshare.23658339","title":"Additional file 1 of Dynamic profiling of medulloblastoma surfaceome","year":2023,"lang":"en","type":"dataset","venue":"Figshare","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; University of Toronto; McMaster University","funders":"","keywords":"Profiling (computer programming); Medulloblastoma; Computer science; Computational biology; Biology; Operating system; Cancer research","score_opus":0.015643979667860693,"score_gpt":0.29045233431459366,"score_spread":0.274808354646733,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394115072","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000010978732,0.000045991885,7.061807e-8,0.000046315727,0.000064608575,0.00023079824,0.9994143,0.0000443703,0.00015241296],"genre_scores_gemma":[5.874614e-7,0.000007016073,0.00077829463,0.00007240503,0.00013305234,0.00030443782,0.9976862,0.000041958672,0.0009760665],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99851936,0.000030752228,0.0004213531,0.00027832895,0.00053153565,0.00021867873],"domain_scores_gemma":[0.9970505,0.001805282,0.00044469436,0.00037885254,0.00019695656,0.00012371966],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00005109572,0.00020261091,0.0005726533,0.00022661588,0.000028249162,0.00000666475,0.00023775523,0.00023793051,0.9894201],"category_scores_gemma":[0.01736778,0.00018628029,0.00019905105,0.00028026372,0.00003313528,0.000024889214,0.00015501218,0.000686565,0.0060958783],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013270588,0.00004645645,1.6121403e-7,0.0028302295,0.00009093761,0.00007331549,0.0000023724251,0.000007726641,0.000011620847,6.313676e-8,0.99647,0.00045389062],"study_design_scores_gemma":[0.00019931693,0.00009683254,0.00023568468,0.021553488,0.000044895227,0.000037579266,0.000009325716,0.0013846321,0.000014082269,0.0000043166306,0.97628397,0.00013588328],"about_ca_topic_score_codex":0.000020500098,"about_ca_topic_score_gemma":0.0000075173202,"teacher_disagreement_score":0.9833242,"about_ca_system_score_codex":0.00004665541,"about_ca_system_score_gemma":0.00043155206,"threshold_uncertainty_score":0.99467796},"labels":[],"label_agreement":null},{"id":"W4394124773","doi":"10.6084/m9.figshare.23300555","title":"Is it necessary for all patients with suspicious lesions undergo systematic biopsy in the era of MRI-TRUS fusion targeted biopsy?","year":2023,"lang":"en","type":"dataset","venue":"Figshare","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Biopsy; Medicine; Radiology","score_opus":0.031166730341239825,"score_gpt":0.31273480292393296,"score_spread":0.2815680725826931,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394124773","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00051460153,0.0003290377,0.000004222147,0.0020973652,0.00014762605,0.0023631447,0.994489,0.000035056182,0.000019921685],"genre_scores_gemma":[0.001014499,0.000040369632,0.00014116171,0.0017403876,0.00012312274,0.0005376873,0.99624807,0.0000624704,0.00009220575],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976722,0.00013990191,0.0006568522,0.00043495838,0.0007123423,0.00038375764],"domain_scores_gemma":[0.9974517,0.0009075163,0.00053685094,0.00077046733,0.0002079132,0.00012550414],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00027201616,0.00035548036,0.0008504821,0.0002677156,0.00010365803,0.000042787262,0.00053473044,0.0003003057,0.0034422076],"category_scores_gemma":[0.003039745,0.00021106923,0.00017551275,0.00048821513,0.000027096816,0.000047250756,0.00014035849,0.0009882747,0.00037999134],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000058966067,0.0001684724,0.00007538276,0.03509844,0.00012998543,0.00011247702,0.00019114031,0.0000127411595,0.0000028805605,5.0543986e-7,0.96410537,0.000043667267],"study_design_scores_gemma":[0.008607426,0.0014764476,0.012639746,0.39520335,0.0016816726,0.00020873536,0.001480507,0.0042469082,0.000014754369,0.00005250881,0.5731303,0.0012576055],"about_ca_topic_score_codex":0.0002999947,"about_ca_topic_score_gemma":0.00004953554,"teacher_disagreement_score":0.390975,"about_ca_system_score_codex":0.00007607318,"about_ca_system_score_gemma":0.00020240853,"threshold_uncertainty_score":0.99746877},"labels":[],"label_agreement":null},{"id":"W4394169567","doi":"10.6084/m9.figshare.19703874","title":"Additional file 5 of Prostate cancer multiparametric magnetic resonance imaging visibility is a tumor-intrinsic phenomena","year":2022,"lang":"en","type":"dataset","venue":"Open MIND","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; University of Toronto; University Health Network","funders":"","keywords":"Magnetic resonance imaging; Prostate cancer; Visibility; Medicine; Nuclear magnetic resonance; Prostate; Cancer; Radiology; Physics; Optics; Internal medicine","score_opus":0.014695498426505296,"score_gpt":0.3089899889900935,"score_spread":0.2942944905635882,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394169567","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00013885077,0.0020719834,2.5967992e-7,0.00035369612,0.00016947732,0.0010890515,0.9951952,0.000003087937,0.0009783617],"genre_scores_gemma":[0.0000064841065,0.00014711828,0.0034092632,0.0009295396,0.00021789779,0.0009015782,0.98915344,0.00003854129,0.005196127],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9971371,0.0001288358,0.00066570204,0.00089737633,0.0007432717,0.00042765873],"domain_scores_gemma":[0.9971883,0.0010919569,0.00052193337,0.0008153707,0.00015036388,0.00023204001],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004191194,0.00034191998,0.000818544,0.00035148006,0.00015386795,0.000092269365,0.00070280157,0.00006670175,0.9942296],"category_scores_gemma":[0.0026783997,0.00032347706,0.00015728334,0.0007589209,0.00026962627,0.000105056824,0.00075848884,0.0012667135,0.00024127131],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012322991,0.00019796967,0.00006674461,0.000113614326,0.000024822997,0.00015947393,0.00005121189,0.000002393217,0.0000016425063,5.08891e-8,0.74237895,0.25687993],"study_design_scores_gemma":[0.0011516418,0.0001698229,0.0020025626,0.00083883374,0.00014284941,0.00008099493,0.000058720896,0.00086939737,0.0000049202204,0.000009683889,0.9943673,0.0003032492],"about_ca_topic_score_codex":0.0013225236,"about_ca_topic_score_gemma":0.000030171,"teacher_disagreement_score":0.99398834,"about_ca_system_score_codex":0.00029037904,"about_ca_system_score_gemma":0.0010726028,"threshold_uncertainty_score":0.99992174},"labels":[],"label_agreement":null},{"id":"W4394176629","doi":"10.6084/m9.figshare.15075195","title":"MICCAI 2018 – Computational Precision Medicine Challenge: 18F-FDG PET Radiomics Risk Stratifiers in Head and Neck Cancer","year":2022,"lang":"en","type":"dataset","venue":"Figshare","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"National Institute of Biomedical Imaging and Bioengineering","keywords":"Radiomics; Head and neck cancer; Medicine; Head and neck; Cancer; Medical physics; Nuclear medicine; Radiology; Internal medicine; Surgery","score_opus":0.032567806225436174,"score_gpt":0.34437955443991275,"score_spread":0.31181174821447655,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394176629","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005035158,0.0065717413,0.0000014554058,0.002605773,0.0004091346,0.00062503334,0.98909956,0.00003629984,0.00014749978],"genre_scores_gemma":[0.000118803,0.0035093762,0.0002228624,0.0010423771,0.0006464996,0.00022479407,0.99403346,0.00005199557,0.00014981584],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973778,0.00017129464,0.0005896115,0.0007125929,0.0007612529,0.00038742594],"domain_scores_gemma":[0.9982401,0.00052692444,0.00040022246,0.00042479634,0.00008768388,0.0003202583],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00032286326,0.00040773686,0.00080938794,0.00040138292,0.00018556743,0.000041183932,0.0003074149,0.0001711554,0.3719497],"category_scores_gemma":[0.002334109,0.00036468828,0.000091362475,0.00027515469,0.00006728603,0.000077221135,0.0002389606,0.0023541977,0.00006363933],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009648922,0.00009031949,0.000081730956,0.00081249635,0.00008539643,0.0005319261,0.00011525329,0.0012833464,7.8614056e-7,0.0000010247467,0.989314,0.0075872256],"study_design_scores_gemma":[0.0027289349,0.00035181947,0.002669538,0.0053698346,0.00012216643,0.00026823362,0.00006237546,0.011848818,1.8772617e-7,0.00008556152,0.9761728,0.00031970194],"about_ca_topic_score_codex":0.0011901297,"about_ca_topic_score_gemma":0.00029237798,"teacher_disagreement_score":0.37188604,"about_ca_system_score_codex":0.00030060648,"about_ca_system_score_gemma":0.00043518053,"threshold_uncertainty_score":0.9999474},"labels":[],"label_agreement":null},{"id":"W4394229679","doi":"10.6084/m9.figshare.21508062.v1","title":"TamburelloLitt_DataTrackingTable_20210217_analysis.xlsx","year":2022,"lang":"en","type":"dataset","venue":"Figshare","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Geology","score_opus":0.023973647219099847,"score_gpt":0.31432379035286273,"score_spread":0.2903501431337629,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394229679","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[4.833763e-7,0.0013657694,3.860637e-7,0.00042304661,0.00019521236,0.0002487705,0.9969111,0.00008253159,0.00077271456],"genre_scores_gemma":[0.0000013709006,0.00014441856,0.00005227194,0.0031786636,0.00065441366,0.0002178698,0.9941088,0.000055596236,0.0015865797],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99765176,0.00008637777,0.00039772503,0.0006197482,0.0008011904,0.00044323216],"domain_scores_gemma":[0.99808896,0.00016399489,0.00026469736,0.00107531,0.00009148772,0.00031554888],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00015244489,0.00035515215,0.0007127469,0.00029943135,0.00020507535,0.00009828612,0.0005264285,0.00023407322,0.9839415],"category_scores_gemma":[0.0033849375,0.00033405228,0.00038662448,0.00047277586,0.000014090039,0.000059566966,0.00053267844,0.0023489688,0.0036510834],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011494277,0.00008729579,0.0000028563343,0.000923224,0.00021079082,0.0010998619,0.0000042553356,0.00002316197,0.000001613575,4.4593142e-7,0.99624175,0.0013932694],"study_design_scores_gemma":[0.0003596593,0.00007169936,0.000032499192,0.001095651,0.00043576714,0.0002483912,0.000012703928,0.00023346537,0.0000023038147,0.00000501879,0.9971911,0.00031177388],"about_ca_topic_score_codex":0.00013008279,"about_ca_topic_score_gemma":0.0000057050875,"teacher_disagreement_score":0.9802904,"about_ca_system_score_codex":0.00015594605,"about_ca_system_score_gemma":0.00037526144,"threshold_uncertainty_score":0.9999527},"labels":[],"label_agreement":null},{"id":"W4394277182","doi":"10.6084/m9.figshare.19703871","title":"Additional file 4 of Prostate cancer multiparametric magnetic resonance imaging visibility is a tumor-intrinsic phenomena","year":2022,"lang":"en","type":"dataset","venue":"Figshare","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; University of Toronto; University Health Network","funders":"","keywords":"Prostate cancer; Visibility; Magnetic resonance imaging; Medicine; Cancer; Nuclear magnetic resonance; Physics; Radiology; Optics; Internal medicine","score_opus":0.013666224627759401,"score_gpt":0.2794907635611044,"score_spread":0.265824538933345,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394277182","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000020750567,0.0052441205,1.4810042e-8,0.00016041764,0.000089849585,0.0006845673,0.99356693,0.000047273366,0.00020474638],"genre_scores_gemma":[0.0000017454203,0.000056416815,0.00020621868,0.0021198401,0.00037583237,0.003393031,0.9926422,0.000053707434,0.0011510131],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99724174,0.00009309843,0.0005715856,0.00076933217,0.00086187664,0.00046239127],"domain_scores_gemma":[0.99665415,0.0016122689,0.0005118267,0.0007468396,0.0002384537,0.0002364667],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00009596397,0.00037340287,0.0007007318,0.00040774076,0.00013815716,0.00003834278,0.00040418256,0.00008390937,0.9996662],"category_scores_gemma":[0.012601183,0.00036325783,0.0002357779,0.00082323205,0.00005997786,0.000067246816,0.00041365164,0.0015177091,0.0006846891],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000055355315,0.00014170895,0.000014381407,0.0012525404,0.000023103457,0.00021511115,0.000023337738,0.000003184076,3.4933996e-7,3.5516525e-8,0.9581682,0.040102705],"study_design_scores_gemma":[0.0006620883,0.00011826661,0.002913593,0.0058192397,0.0000633985,0.00007250527,0.000015851916,0.0010767169,0.0000013929625,0.000006256953,0.988934,0.00031668934],"about_ca_topic_score_codex":0.0002474591,"about_ca_topic_score_gemma":0.0000070219958,"teacher_disagreement_score":0.99898154,"about_ca_system_score_codex":0.0003083022,"about_ca_system_score_gemma":0.00084320555,"threshold_uncertainty_score":0.9998819},"labels":[],"label_agreement":null},{"id":"W4394321151","doi":"10.6084/m9.figshare.23744002","title":"Construction of lung cancer serum markers based on ReliefF feature selection","year":2023,"lang":"en","type":"dataset","venue":"Figshare","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Health Services","funders":"","keywords":"Feature selection; Selection (genetic algorithm); Lung cancer; Feature (linguistics); Computer science; Computational biology; Cancer; Pattern recognition (psychology); Artificial intelligence; Internal medicine; Biology; Medicine","score_opus":0.010991150470512013,"score_gpt":0.3067001875597479,"score_spread":0.2957090370892359,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394321151","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000011345149,0.00013504292,9.5033494e-7,0.001320909,0.0003876613,0.00036379922,0.9975234,0.000091733615,0.00016514602],"genre_scores_gemma":[0.00001667207,0.000068469264,0.00013602359,0.0008461494,0.0005864659,0.0001211549,0.99751014,0.000047476067,0.0006674754],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986952,0.000055660308,0.0002162711,0.00035383887,0.0004484538,0.0002305863],"domain_scores_gemma":[0.99899393,0.0001707851,0.00027111123,0.0002948633,0.00014298016,0.00012630041],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00009378568,0.00023591521,0.00040438116,0.000292393,0.000068891735,0.000019884983,0.00012470427,0.0004039504,0.038815532],"category_scores_gemma":[0.0019620564,0.00021120305,0.00015218019,0.000394236,0.000017638733,0.000025658992,0.00003651813,0.0013137357,0.00034848868],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009583459,0.000024526751,0.00012843074,0.0028834164,0.00008731173,0.000035260375,0.0000022977183,0.00028491876,0.0000062915738,1.5702766e-7,0.9945581,0.0018934691],"study_design_scores_gemma":[0.0006621358,0.00012385195,0.0028563682,0.01563977,0.00017848033,0.000025552677,0.000004311029,0.02287396,0.000031822026,9.616774e-7,0.9574272,0.00017560805],"about_ca_topic_score_codex":0.00018314221,"about_ca_topic_score_gemma":0.000024370791,"teacher_disagreement_score":0.038467042,"about_ca_system_score_codex":0.00018022163,"about_ca_system_score_gemma":0.00037636253,"threshold_uncertainty_score":0.96206313},"labels":[],"label_agreement":null},{"id":"W4394337445","doi":"10.6084/m9.figshare.15075195.v1","title":"MICCAI 2018 – Computational Precision Medicine Challenge: 18F-FDG PET Radiomics Risk Stratifiers in Head and Neck Cancer","year":2021,"lang":"en","type":"dataset","venue":"Figshare","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"National Institute of Biomedical Imaging and Bioengineering","keywords":"Radiomics; Head and neck cancer; Medicine; Precision medicine; Head and neck; Medical physics; Cancer; Nuclear medicine; Internal medicine; Radiology; Pathology; Surgery","score_opus":0.03306970358172672,"score_gpt":0.3463552591522771,"score_spread":0.3132855555705504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394337445","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005924545,0.011089268,0.0000029719379,0.0027692425,0.00037288654,0.0004711301,0.9845363,0.000029018172,0.0001367621],"genre_scores_gemma":[0.00013250788,0.0051924405,0.0004939798,0.0010070992,0.0009711096,0.00010896596,0.9919069,0.000047403715,0.00013961665],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99749607,0.00014828163,0.0005984928,0.0007367654,0.0006363275,0.00038408674],"domain_scores_gemma":[0.9981797,0.000502737,0.00035506344,0.00044718978,0.000162875,0.00035247247],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002481497,0.00041786197,0.0008931696,0.00030897805,0.000115706054,0.00005758628,0.00023531346,0.00024763538,0.052475244],"category_scores_gemma":[0.003248206,0.00036504283,0.00009660003,0.00026699336,0.000069987735,0.00007882013,0.00016702322,0.0019226155,0.000098023585],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000056873454,0.00008582211,0.00008490972,0.0010928771,0.00009669091,0.0008177329,0.00008130208,0.00056088297,0.0000017156069,7.026736e-7,0.988819,0.008301463],"study_design_scores_gemma":[0.0026909867,0.00020160917,0.0035249507,0.017174466,0.00013835181,0.00032897855,0.000055346045,0.012954803,7.206282e-7,0.000063801825,0.9625366,0.00032940315],"about_ca_topic_score_codex":0.00083725306,"about_ca_topic_score_gemma":0.0004436528,"teacher_disagreement_score":0.05237722,"about_ca_system_score_codex":0.0002047984,"about_ca_system_score_gemma":0.00054289395,"threshold_uncertainty_score":0.99988014},"labels":[],"label_agreement":null},{"id":"W4394360790","doi":"10.6084/m9.figshare.23751836","title":"Additional file 1 of Integration of single-cell regulon atlas and multi-omics data for prognostic stratification and personalized treatment prediction in human lung adenocarcinoma","year":2023,"lang":"en","type":"dataset","venue":"Open MIND","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Regulon; Atlas (anatomy); Omics; Adenocarcinoma; Computational biology; Stratification (seeds); Risk stratification; Computer science; Internal medicine; Oncology; Data mining; Biology; Bioinformatics; Medicine; Cancer; Genetics; Dormancy","score_opus":0.08061342085937294,"score_gpt":0.35069146920885025,"score_spread":0.2700780483494773,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394360790","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031984742,0.000091064234,0.000057641824,0.000066628054,0.00003129148,0.001411346,0.99511284,0.0000015005398,0.00002918774],"genre_scores_gemma":[0.00026977563,0.000047844576,0.015327882,0.0000047405033,0.000067613815,0.00024038854,0.9831093,0.000016704387,0.00091576716],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99884963,0.0000508164,0.00042312994,0.00042282123,0.00015049605,0.00010307686],"domain_scores_gemma":[0.9984569,0.0007230026,0.00035924235,0.00033071375,0.000069710004,0.000060458224],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00022294375,0.00015454265,0.00038742548,0.00015824083,0.000049864633,0.000041130083,0.00015371782,0.00014110084,0.009358126],"category_scores_gemma":[0.0010568465,0.0001361493,0.000028420789,0.000087998684,0.00013797489,0.0001021773,0.000098606935,0.00016097898,0.0000041028015],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000110455905,0.0003438438,0.00009880731,0.00030034053,0.000051390827,0.000004594826,0.00011139164,0.0000016159333,0.0017656276,6.3062754e-7,0.988811,0.008400273],"study_design_scores_gemma":[0.0077531165,0.0021591992,0.011246752,0.004859193,0.0011093317,0.00005392509,0.0007475717,0.08269191,0.00073515,0.000024533674,0.8882782,0.00034111133],"about_ca_topic_score_codex":0.00031694095,"about_ca_topic_score_gemma":0.00028045246,"teacher_disagreement_score":0.10053282,"about_ca_system_score_codex":0.00007764998,"about_ca_system_score_gemma":0.00017173798,"threshold_uncertainty_score":0.99154747},"labels":[],"label_agreement":null},{"id":"W4394403014","doi":"10.6084/m9.figshare.19389866","title":"Supplementary Material for: Assessing Mild Cognitive Impairment in Parkinson’s Disease by Magnetic Resonance Quantitative Susceptibility Mapping Combined Voxel-Wise and Radiomic Analysis","year":2022,"lang":"en","type":"dataset","venue":"Figshare","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Cognitive impairment; Voxel; Magnetic resonance imaging; Parkinson's disease; Medicine; Disease; Quantitative susceptibility mapping; Psychology; Pathology; Radiology","score_opus":0.023267892788026826,"score_gpt":0.32139435868846306,"score_spread":0.29812646590043623,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394403014","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01547705,0.0021463076,0.0000043252367,0.00048760304,0.00013342313,0.0018655608,0.97985715,0.000025865304,0.00000271064],"genre_scores_gemma":[0.004349232,0.00021781812,0.00030173865,0.0007040866,0.000102549224,0.0011757676,0.9930653,0.000047782163,0.000035714034],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9968874,0.00034428397,0.00069024845,0.0010224172,0.0004999913,0.0005556841],"domain_scores_gemma":[0.99811345,0.00066206726,0.00033706863,0.00042593144,0.00008908484,0.0003724069],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00046046963,0.00047049767,0.0010137197,0.0006028188,0.00023079835,0.00015373327,0.00023892305,0.00013725775,0.3194756],"category_scores_gemma":[0.0014053523,0.00048495442,0.00026220543,0.0005774756,0.00006629019,0.00010121295,0.00032460009,0.0007893334,0.0000061273067],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009503644,0.000321112,0.005345923,0.0018881175,0.00024471234,0.00021603667,0.00011229241,0.00000584676,0.000010910632,1.7316661e-7,0.9901241,0.00078039605],"study_design_scores_gemma":[0.0044116997,0.00047327566,0.06275621,0.0024985443,0.0012253157,0.0000066067205,0.00039414808,0.004283857,0.000005115033,0.000010071222,0.9234384,0.00049679476],"about_ca_topic_score_codex":0.00073603773,"about_ca_topic_score_gemma":0.00018960774,"teacher_disagreement_score":0.31946948,"about_ca_system_score_codex":0.00043327006,"about_ca_system_score_gemma":0.0002862604,"threshold_uncertainty_score":0.9997602},"labels":[],"label_agreement":null},{"id":"W4394436875","doi":"10.6084/m9.figshare.20176117","title":"Additional file 1 of Improve individual treatment by comparing treatment benefits: cancer artificial intelligence survival analysis system for cervical carcinoma","year":2022,"lang":"en","type":"dataset","venue":"Figshare","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Cervical carcinoma; Oncology; Cervical cancer; Medicine; Carcinoma; Internal medicine; Cancer","score_opus":0.06485687028744158,"score_gpt":0.31805577591564,"score_spread":0.2531989056281984,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394436875","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000011383337,0.0004091216,0.0000026713417,0.000057576257,0.00015074902,0.00074652117,0.99855465,0.00003488045,0.000032445907],"genre_scores_gemma":[0.00012733915,0.000015477635,0.00014768336,0.00004812412,0.0005554078,0.008250176,0.9906716,0.00003777989,0.00014641265],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976433,0.00007570315,0.0006417253,0.000641684,0.0006146853,0.00038292687],"domain_scores_gemma":[0.9969671,0.0016704185,0.00051824393,0.00045299955,0.00014516889,0.0002460689],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000057042376,0.00042576305,0.0012320065,0.00030183102,0.00018570437,0.000047636426,0.00029446627,0.0002009757,0.9853058],"category_scores_gemma":[0.0007137571,0.00036105234,0.0006243467,0.00039837934,0.000024413826,0.000029644294,0.00014167957,0.00035150972,0.00006726146],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010144469,0.00035837307,0.00001239037,0.000688514,0.0021793966,0.000028963883,0.000027192738,0.00032055622,7.7938347e-7,0.0000011587364,0.98520005,0.011081193],"study_design_scores_gemma":[0.00035845573,0.00073672546,0.00022227553,0.0010937089,0.002553397,0.000009218423,0.00012252292,0.006808612,0.000033012922,9.968737e-7,0.9877864,0.00027468905],"about_ca_topic_score_codex":0.0012381225,"about_ca_topic_score_gemma":0.00029822713,"teacher_disagreement_score":0.98523855,"about_ca_system_score_codex":0.0010138074,"about_ca_system_score_gemma":0.00055291696,"threshold_uncertainty_score":0.9998841},"labels":[],"label_agreement":null},{"id":"W4394444711","doi":"10.6084/m9.figshare.22151537","title":"Tissue specificity - tau values","year":2023,"lang":"en","type":"dataset","venue":"Figshare","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Ministry of Colleges and Universities","keywords":"Computational biology; Biology","score_opus":0.04138342033023817,"score_gpt":0.34451377170593267,"score_spread":0.3031303513756945,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394444711","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000014060386,0.0003344576,5.4503994e-7,0.0006393873,0.0004464798,0.00031623017,0.9973457,0.00021757622,0.00069822837],"genre_scores_gemma":[0.0000010658082,0.00008664133,0.00006937619,0.00094139634,0.0023052902,0.00007853936,0.9917394,0.000065700595,0.0047125923],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99834687,0.000042784173,0.00028387352,0.00045463422,0.00051021244,0.00036161148],"domain_scores_gemma":[0.99863154,0.00021046308,0.00014883293,0.00065415667,0.00008590839,0.00026908686],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00010824372,0.00028914548,0.0005237384,0.00018621486,0.000092181006,0.00006835202,0.00032603575,0.0003322106,0.20412126],"category_scores_gemma":[0.0050723,0.00025285222,0.00013834542,0.00023815584,0.000017824295,0.000032716365,0.00022727688,0.0013232898,0.094453864],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000069520206,0.000034776785,0.0000012857953,0.0010547303,0.00005075129,0.0008453413,0.0000068542845,0.0000026869022,0.0000044913136,2.6553923e-7,0.9947698,0.0032220564],"study_design_scores_gemma":[0.0002747002,0.00007380766,0.0003551331,0.0047409595,0.000077885474,0.000082824445,0.0000067425817,0.00008352023,0.000026462698,0.000018228784,0.99401957,0.00024018767],"about_ca_topic_score_codex":0.00013894783,"about_ca_topic_score_gemma":0.00000816994,"teacher_disagreement_score":0.1096674,"about_ca_system_score_codex":0.00007791931,"about_ca_system_score_gemma":0.00015870796,"threshold_uncertainty_score":0.9999924},"labels":[],"label_agreement":null},{"id":"W4394471698","doi":"10.6084/m9.figshare.19703868","title":"Additional file 3 of Prostate cancer multiparametric magnetic resonance imaging visibility is a tumor-intrinsic phenomena","year":2022,"lang":"en","type":"dataset","venue":"Figshare","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; University of Toronto; University Health Network","funders":"","keywords":"Prostate cancer; Visibility; Magnetic resonance imaging; Medicine; Cancer; Nuclear magnetic resonance; Physics; Radiology; Optics; Internal medicine","score_opus":0.013562438225973002,"score_gpt":0.27908951498005824,"score_spread":0.2655270767540852,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394471698","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000020849502,0.005224867,1.4715557e-8,0.00016071925,0.00009067561,0.0006839827,0.99358517,0.00004720944,0.0002052935],"genre_scores_gemma":[0.0000017009552,0.000056400695,0.00020593354,0.0021168962,0.00037959404,0.0033918028,0.9926014,0.000053705604,0.0011925861],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.997242,0.00009311082,0.0005713774,0.0007692537,0.0008619316,0.0004623378],"domain_scores_gemma":[0.9966531,0.0016091847,0.00051175995,0.00074646925,0.00024305689,0.00023646394],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0000958856,0.00037337642,0.00070056354,0.00040754784,0.00013808721,0.00003832202,0.00040388023,0.000083902145,0.99967194],"category_scores_gemma":[0.012780743,0.00036318763,0.00023575932,0.00082333904,0.000059966893,0.00006723681,0.0004134912,0.001517757,0.00069920655],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000054729964,0.0001415189,0.00001433688,0.0012615516,0.000023083892,0.00021417487,0.00002329446,0.000003227247,3.5458052e-7,3.421784e-8,0.9581624,0.040101252],"study_design_scores_gemma":[0.00066487864,0.00011626916,0.0029000044,0.0058061876,0.00006292716,0.00007175919,0.00001580569,0.0010731128,0.0000014229602,0.000006193996,0.98896474,0.00031667267],"about_ca_topic_score_codex":0.00024971503,"about_ca_topic_score_gemma":0.000006992794,"teacher_disagreement_score":0.9989727,"about_ca_system_score_codex":0.00030951406,"about_ca_system_score_gemma":0.00084643177,"threshold_uncertainty_score":0.999882},"labels":[],"label_agreement":null},{"id":"W4394493786","doi":"10.6084/m9.figshare.20126087","title":"Hamilton_allData.csv","year":2022,"lang":"en","type":"dataset","venue":"Figshare","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Mathematics","score_opus":0.028153032642276074,"score_gpt":0.31717407079494114,"score_spread":0.28902103815266506,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394493786","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[3.831639e-7,0.0006173006,1.1402582e-7,0.00048589404,0.00027434202,0.00027744236,0.9969673,0.00008858742,0.0012886192],"genre_scores_gemma":[5.0816266e-7,0.000053446576,0.00004383393,0.0053392984,0.00054793525,0.0002141893,0.9919591,0.00004545636,0.0017962529],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983736,0.000051765834,0.00025525666,0.0004296098,0.00057465665,0.00031506942],"domain_scores_gemma":[0.9986181,0.0001227889,0.00015990526,0.0007970647,0.000046324505,0.0002558033],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00009058292,0.0002604385,0.00044032812,0.00017610453,0.0001320204,0.000049310845,0.00043127034,0.00018358686,0.98738414],"category_scores_gemma":[0.0031092227,0.00024058881,0.00017823926,0.00018116449,0.00001082108,0.00003427831,0.0004872605,0.001979242,0.0049185124],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011067571,0.00005734137,0.0000012657388,0.00071038766,0.000059895614,0.0007547071,0.0000038335334,0.0000029161797,0.0000010850492,3.5257034e-7,0.9966267,0.0017704641],"study_design_scores_gemma":[0.000426669,0.000085558946,0.000067467896,0.0012002483,0.00008303308,0.000252323,0.000005088019,0.00008575636,0.0000013033601,0.0000027624035,0.99755716,0.00023261005],"about_ca_topic_score_codex":0.00004960035,"about_ca_topic_score_gemma":0.0000038895646,"teacher_disagreement_score":0.9824656,"about_ca_system_score_codex":0.0001078253,"about_ca_system_score_gemma":0.00027967402,"threshold_uncertainty_score":0.9958563},"labels":[],"label_agreement":null},{"id":"W4394499756","doi":"10.6084/m9.figshare.23676918","title":"IG_dataset_2023.dta","year":2023,"lang":"en","type":"dataset","venue":"Figshare","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Business; Environmental science; Chemistry","score_opus":0.045793999885364214,"score_gpt":0.34552973745533744,"score_spread":0.29973573756997324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394499756","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.0058667e-7,0.0002180112,1.1368363e-7,0.0007270467,0.00034112568,0.0002795476,0.99802643,0.00020471672,0.00020283474],"genre_scores_gemma":[1.15290966e-7,0.00008009923,0.00003531651,0.0020782643,0.0011829457,0.00013534189,0.9950128,0.00006571136,0.001409358],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.998372,0.000031903586,0.0002800691,0.00046297561,0.0004779197,0.00037509558],"domain_scores_gemma":[0.9984164,0.00020521162,0.00013865929,0.0008783366,0.000064525026,0.00029685692],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00009570188,0.00028559007,0.00047474238,0.00022061125,0.00007730797,0.00006858331,0.00039114634,0.00032227856,0.19681214],"category_scores_gemma":[0.006732581,0.00025006582,0.00017166062,0.00030286852,0.000012923579,0.000038265178,0.00036973818,0.0013754449,0.19091482],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000075308612,0.000029460462,6.8603543e-7,0.001248159,0.00007347643,0.0011944466,0.0000017492433,0.0000014354889,8.717216e-7,1.7425685e-7,0.9961335,0.0013085245],"study_design_scores_gemma":[0.00036148334,0.000051049523,0.00010737616,0.005480125,0.00010746097,0.00011214238,0.000003209441,0.00014317839,0.0000017733856,0.000005409021,0.9933896,0.00023720809],"about_ca_topic_score_codex":0.00013140606,"about_ca_topic_score_gemma":0.000013059174,"teacher_disagreement_score":0.006636879,"about_ca_system_score_codex":0.00006232488,"about_ca_system_score_gemma":0.00023091462,"threshold_uncertainty_score":0.9999952},"labels":[],"label_agreement":null},{"id":"W4394530213","doi":"10.6084/m9.figshare.22604836","title":"Additional file 1 of Identification of biomarkers predictive of metastasis development in early-stage colorectal cancer using network-based regularization","year":2023,"lang":"en","type":"dataset","venue":"Figshare","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Agency of Canada","funders":"","keywords":"Colorectal cancer; Regularization (linguistics); Stage (stratigraphy); Identification (biology); Oncology; Computer science; Internal medicine; Computational biology; Medicine; Cancer; Artificial intelligence; Biology; Ecology; Paleontology","score_opus":0.027639909384532257,"score_gpt":0.2978834351191721,"score_spread":0.27024352573463983,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394530213","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00009661108,0.00004216479,0.000013653202,0.000009440502,0.000055069173,0.00038606426,0.9993773,0.000011799685,0.0000078660105],"genre_scores_gemma":[0.00006649304,0.000004539878,0.0012116084,0.000014584582,0.00006821466,0.00045825331,0.9980948,0.000024745912,0.00005675915],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983359,0.00007720817,0.00068856886,0.00025068212,0.00048685656,0.0001608098],"domain_scores_gemma":[0.99777806,0.0006898393,0.0010007622,0.00017569652,0.00029906214,0.00005657215],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00015054854,0.0001554852,0.00044859046,0.00035495957,0.000030026773,0.000006310699,0.00013686287,0.00017680717,0.56093115],"category_scores_gemma":[0.0043231132,0.00015909219,0.000094979805,0.00063204736,0.00004054532,0.000042331434,0.00006441684,0.00025493282,0.000031069707],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008605634,0.00006390305,0.000036177145,0.0015373358,0.00022131276,0.000009519821,0.000019765512,0.0036244658,0.000066092165,8.025286e-8,0.9938527,0.0004825902],"study_design_scores_gemma":[0.00065562245,0.000084388106,0.027357064,0.029551767,0.00016841404,0.0000020541543,0.00001866981,0.03712617,0.0012765789,0.0000026459645,0.90355146,0.00020519008],"about_ca_topic_score_codex":0.00021072493,"about_ca_topic_score_gemma":0.00005443511,"teacher_disagreement_score":0.5609001,"about_ca_system_score_codex":0.0001529648,"about_ca_system_score_gemma":0.00097737,"threshold_uncertainty_score":0.6487591},"labels":[],"label_agreement":null},{"id":"W4394553080","doi":"10.6084/m9.figshare.16685041.v1","title":"TVC_Array_09.2021.zip","year":2021,"lang":"en","type":"dataset","venue":"Figshare","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computational biology; Computer science; Biology","score_opus":0.02443760595126802,"score_gpt":0.3133131596970647,"score_spread":0.28887555374579665,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394553080","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[7.861417e-7,0.0016467472,7.930327e-7,0.0009674933,0.00033122138,0.00019677817,0.9952474,0.000044707198,0.0015640667],"genre_scores_gemma":[0.0000021937828,0.000089898014,0.00015078818,0.0031255053,0.0018937496,0.000084506464,0.99289036,0.000043550837,0.0017194367],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99835247,0.00004881425,0.00027532136,0.0004907361,0.0004781905,0.0003544485],"domain_scores_gemma":[0.99846745,0.00013386876,0.00014585849,0.0007857643,0.00014191285,0.0003251447],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00007241987,0.00029481653,0.0005569259,0.00012971809,0.000086837834,0.00008172525,0.00027327734,0.00035564217,0.67764586],"category_scores_gemma":[0.0057779965,0.00026277863,0.0002388224,0.00021435082,0.000013540021,0.000034387023,0.0002334346,0.001556397,0.009945547],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000056266563,0.000051594612,0.000002329354,0.0010041881,0.000073000374,0.0014420495,0.00000517567,0.0000017744019,0.0000074045615,1.8318758e-7,0.9941667,0.0032400233],"study_design_scores_gemma":[0.00038863008,0.000040117535,0.000063179716,0.0071589192,0.00010616818,0.000250456,0.000008174549,0.00010406068,0.000018162895,0.0000027603314,0.99160767,0.00025167828],"about_ca_topic_score_codex":0.000027450706,"about_ca_topic_score_gemma":0.0000033313365,"teacher_disagreement_score":0.66770035,"about_ca_system_score_codex":0.00007328002,"about_ca_system_score_gemma":0.00045307112,"threshold_uncertainty_score":0.9999824},"labels":[],"label_agreement":null},{"id":"W4394618526","doi":"10.3389/fneur.2024.1377538","title":"Machine learning techniques based on 18F-FDG PET radiomics features of temporal regions for the classification of temporal lobe epilepsy patients from healthy controls","year":2024,"lang":"en","type":"article","venue":"Frontiers in Neurology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Jinan University; National Natural Science Foundation of China","keywords":"Temporal lobe; Artificial intelligence; Machine learning; Epilepsy; Radiomics; Logistic regression; Lasso (programming language); Computer science; Test set; Set (abstract data type); Medicine","score_opus":0.012121265533083687,"score_gpt":0.28446292002847007,"score_spread":0.2723416544953864,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394618526","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.50410247,0.0058630835,0.38482535,0.09446473,0.00492999,0.0043592183,0.00036070505,0.00035672955,0.0007377361],"genre_scores_gemma":[0.98298264,0.00022666874,0.013403328,0.002639204,0.0001640081,0.00008471543,0.00039192563,0.000047496782,0.00006003297],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99827474,0.00028823828,0.0005571455,0.00038434315,0.0002329534,0.00026255785],"domain_scores_gemma":[0.99838287,0.0008680875,0.0002692068,0.000325362,0.00007459874,0.00007989232],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006366324,0.0001838269,0.00056660693,0.0003617289,0.000075418684,0.000013194675,0.00020553135,0.00012111704,0.000007660845],"category_scores_gemma":[0.0008706258,0.00013489835,0.00016628654,0.00023390981,0.00030083585,0.00003952284,0.00002609961,0.0010271196,4.0013842e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0061204415,0.00047265392,0.918332,0.00033149333,0.00014612223,0.00006592383,0.00026459122,0.0006911513,0.0011869876,0.0016989139,0.032198407,0.038491357],"study_design_scores_gemma":[0.004232981,0.00396025,0.16718383,0.00024008375,0.0001904697,0.000023195784,0.00006377831,0.7508332,0.00023911925,0.0020875987,0.0707592,0.00018627685],"about_ca_topic_score_codex":0.00036652494,"about_ca_topic_score_gemma":0.00001620035,"teacher_disagreement_score":0.7511481,"about_ca_system_score_codex":0.000051359824,"about_ca_system_score_gemma":0.0001442044,"threshold_uncertainty_score":0.5500995},"labels":[],"label_agreement":null},{"id":"W4394714140","doi":"10.3174/ajnr.a8199","title":"Identification of Multiclass Pediatric Low-Grade Neuroepithelial Tumor Molecular Subtype with ADC MR Imaging and Machine Learning","year":2024,"lang":"en","type":"article","venue":"American Journal of Neuroradiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"SickKids Foundation; Vector Institute; Hospital for Sick Children; University of Toronto","funders":"Canadian Cancer Society Research Institute; Canadian Institutes of Health Research","keywords":"Medicine; Receiver operating characteristic; Biopsy; Random forest; Magnetic resonance imaging; Oncology; Pathology; Artificial intelligence; Internal medicine; Radiology; Computer science","score_opus":0.0051063303177758534,"score_gpt":0.25548791713608665,"score_spread":0.2503815868183108,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394714140","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98888,0.0019629376,0.005010559,0.0037117472,0.00029364732,0.00009261931,0.000002471253,0.00003031586,0.000015725276],"genre_scores_gemma":[0.99756795,0.00063159695,0.00093715434,0.00052944996,0.0002661713,0.0000014295656,0.0000026642956,0.000047240737,0.00001632519],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99840975,0.00027964835,0.0005710599,0.00025458678,0.00025145535,0.00023348235],"domain_scores_gemma":[0.99870294,0.00030916193,0.0005352244,0.00013812573,0.00012521812,0.00018933328],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004560221,0.00016463843,0.00053401187,0.00042539506,0.00004379435,0.000029082377,0.00012499127,0.000019049266,0.0000074972254],"category_scores_gemma":[0.00058328395,0.00012257457,0.0001018602,0.0004244511,0.00045505905,0.00008980111,0.000031443014,0.0009394743,0.0000020720095],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006139005,0.00014319354,0.42518443,0.00035289087,0.00019734047,0.006123796,0.0005728699,0.0020637393,0.5127888,0.00014711742,0.00010506148,0.05170687],"study_design_scores_gemma":[0.006551358,0.012547318,0.3569949,0.0007376026,0.0025859915,0.09949275,0.00081444357,0.502031,0.01240488,0.00030381174,0.00466221,0.00087368046],"about_ca_topic_score_codex":0.000028548373,"about_ca_topic_score_gemma":3.0340667e-7,"teacher_disagreement_score":0.5003839,"about_ca_system_score_codex":0.000023572537,"about_ca_system_score_gemma":0.00013782724,"threshold_uncertainty_score":0.4998446},"labels":[],"label_agreement":null},{"id":"W4394741143","doi":"10.2174/0115734056261997231217085501","title":"Application Exploration of Medical Image-aided Diagnosis of Breast TumourBased on Deep Learning","year":2024,"lang":"en","type":"article","venue":"Current Medical Imaging Formerly Current Medical Imaging Reviews","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Artificial intelligence; Region of interest; Computer science; Medical imaging; Breast cancer; Magnetic resonance imaging; Feature extraction; Feature (linguistics); Breast imaging; Medicine; Pattern recognition (psychology); Mammography; Computer vision; Radiology; Cancer; Internal medicine","score_opus":0.026541880744828907,"score_gpt":0.3741750889269588,"score_spread":0.3476332081821299,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394741143","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010945954,0.31216088,0.5928816,0.07127518,0.0078119487,0.0028734226,0.000041106272,0.0009008463,0.001109055],"genre_scores_gemma":[0.76929,0.2188365,0.0017425454,0.002296644,0.004642836,0.0012572296,0.0014762131,0.00039173543,0.000066333225],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9852123,0.00080339285,0.0035645429,0.0014457117,0.0078023546,0.0011716569],"domain_scores_gemma":[0.9935381,0.0015360648,0.0009504387,0.00089891034,0.00049216964,0.002584329],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008939356,0.00090287946,0.0021954468,0.0009797661,0.00021968281,0.00014267716,0.0012544536,0.0002934936,0.002862584],"category_scores_gemma":[0.018745217,0.0006922219,0.001045352,0.0015933367,0.0016305104,0.00090848096,0.00038439585,0.0052084764,0.00030823657],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006730195,0.0011894781,0.017707746,0.0066824416,0.000082104656,0.00016447931,0.00044561896,0.0000033785943,0.00019884398,0.0013598951,0.015234728,0.956864],"study_design_scores_gemma":[0.0028640032,0.00015507732,0.0016120197,0.046649255,0.00062281464,0.000819023,0.00014402346,0.53095704,0.0002570684,0.00054877246,0.41464242,0.00072850357],"about_ca_topic_score_codex":0.00008306859,"about_ca_topic_score_gemma":0.0000037673822,"teacher_disagreement_score":0.95613545,"about_ca_system_score_codex":0.00029473554,"about_ca_system_score_gemma":0.0014065176,"threshold_uncertainty_score":0.9995529},"labels":[],"label_agreement":null},{"id":"W4394750638","doi":"10.1177/08465371241234545","title":"Radiomics Studies on Ischemic Stroke and Carotid Atherosclerotic Disease: A Reporting Quality Assessment","year":2024,"lang":"en","type":"review","venue":"Canadian Association of Radiologists Journal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"Florey Institute of Neuroscience and Mental Health","keywords":"Medicine; Stroke (engine); Radiomics; Ischemic stroke; Quality assessment; Disease; Internal medicine; Cardiology; Radiology; Pathology; Ischemia","score_opus":0.09679976496386196,"score_gpt":0.4305006389687585,"score_spread":0.33370087400489656,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394750638","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024821998,0.9923433,0.000032808763,0.0021621261,0.0013953026,0.00051811634,0.00013381631,0.000032372434,0.0008999221],"genre_scores_gemma":[0.0024955454,0.9924783,0.0007070629,0.00029735063,0.0008140688,0.000022268829,0.00007276964,0.00006336439,0.003049259],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9956244,0.00053523557,0.0023973477,0.0004333424,0.00052815943,0.00048147663],"domain_scores_gemma":[0.9930067,0.00062189426,0.0048789424,0.00028292785,0.00024719903,0.0009623579],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.00635771,0.00040151202,0.0025291669,0.00055295904,0.0002035558,0.000102856786,0.00016283551,0.00032963188,0.000017848402],"category_scores_gemma":[0.017191648,0.0002982211,0.0006910614,0.0002147647,0.00016299183,0.00004777835,0.000037770238,0.002397522,0.000006927414],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034750716,0.00012823248,0.06251266,0.048827194,0.012621795,0.0020145774,0.00082589965,0.00012592858,0.000022899972,0.0013850995,0.19149533,0.68000567],"study_design_scores_gemma":[0.00080262055,0.00021026643,0.0061685983,0.028103724,0.0055630254,0.0010913822,0.00019851308,0.00029442244,4.3505233e-7,0.00009468365,0.956937,0.00053531723],"about_ca_topic_score_codex":0.00036421098,"about_ca_topic_score_gemma":0.00024190122,"teacher_disagreement_score":0.76544166,"about_ca_system_score_codex":0.0056538484,"about_ca_system_score_gemma":0.0039658276,"threshold_uncertainty_score":0.999947},"labels":[],"label_agreement":null},{"id":"W4394761328","doi":"10.1186/s12880-024-01253-0","title":"A survey of the impact of self-supervised pretraining for diagnostic tasks in medical X-ray, CT, MRI, and ultrasound","year":2024,"lang":"en","type":"review","venue":"BMC Medical Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Artificial intelligence; Machine learning; Generalization; Transfer of learning; Feature (linguistics); Supervised learning; Segmentation; Task (project management); Ultrasound; Pattern recognition (psychology); Medicine; Artificial neural network; Radiology","score_opus":0.0366002777191312,"score_gpt":0.3929904576735468,"score_spread":0.3563901799544156,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394761328","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0034727247,0.9911273,0.0024967685,0.0003292411,0.0005443153,0.0016697411,0.00011309026,0.00006304018,0.00018374919],"genre_scores_gemma":[0.016637815,0.9801178,0.0022025788,0.00017348015,0.00036235133,0.00013468764,0.00018309084,0.0001542457,0.00003394527],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9942854,0.0009173732,0.0018295229,0.0007264674,0.0015932452,0.00064800336],"domain_scores_gemma":[0.977143,0.02083389,0.0004919795,0.0006146312,0.00014336032,0.00077312015],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0071962876,0.0005916638,0.0030021504,0.00041743714,0.000060907685,0.00004289517,0.0006857708,0.0003155879,0.0002096304],"category_scores_gemma":[0.088643014,0.0003345038,0.00093803945,0.000914077,0.0007880829,0.00005993268,0.00033188378,0.0023244603,0.000002873456],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002556068,0.00029200225,0.070333175,0.05908451,0.0005963966,0.00027131132,0.00040377575,0.000004429562,0.0000015139142,0.000040384923,0.0029970652,0.86594987],"study_design_scores_gemma":[0.008190042,0.00041971143,0.052403115,0.42361903,0.007362184,0.005795558,0.00021343528,0.45687827,0.0000013609297,0.00021811912,0.043420117,0.0014790447],"about_ca_topic_score_codex":0.001226043,"about_ca_topic_score_gemma":0.000094909534,"teacher_disagreement_score":0.86447084,"about_ca_system_score_codex":0.0001856077,"about_ca_system_score_gemma":0.0055041253,"threshold_uncertainty_score":0.99997723},"labels":[],"label_agreement":null},{"id":"W4394768787","doi":"10.3233/xst-230255","title":"A user-friendly deep learning application for accurate lung cancer diagnosis","year":2024,"lang":"en","type":"article","venue":"Journal of X-Ray Science and Technology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto; University Health Network","funders":"","keywords":"Deep learning; Artificial intelligence; Computer science; Segmentation; Medical diagnosis; Lung cancer; Machine learning; Python (programming language); Radiation treatment planning; Image processing; Lung cancer screening; Medicine; Radiology; Pathology; Image (mathematics); Radiation therapy","score_opus":0.0063836881396800715,"score_gpt":0.33033288187432597,"score_spread":0.3239491937346459,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394768787","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8444569,0.0109521495,0.09749208,0.04617109,0.00046751497,0.0002707871,0.0000010024958,0.000081353115,0.00010711045],"genre_scores_gemma":[0.99260825,0.0017688355,0.005101585,0.00021118045,0.00017400949,0.000041322113,3.5769477e-7,0.00000959197,0.00008488511],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991248,0.000007416096,0.00022901455,0.00018189134,0.00025060755,0.00020626548],"domain_scores_gemma":[0.999259,0.00010955091,0.00012448919,0.00008256624,0.0003262899,0.00009813258],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010008983,0.00007089017,0.00018939072,0.0005897618,0.00016484267,0.00006304198,0.00016807865,0.000067824956,0.0000110788205],"category_scores_gemma":[0.0012033278,0.00005034787,0.000038960297,0.00090901693,0.00039927414,0.00021057084,0.000040651703,0.0005076367,9.971072e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033877197,0.00004699945,0.08312586,0.00022095545,0.00007474859,0.000069193185,0.00026114655,0.00032448507,0.045876034,0.0058593336,0.002337998,0.8617694],"study_design_scores_gemma":[0.0013161581,0.0011144382,0.0076896166,0.0008539066,0.00035633153,0.0008731678,0.00069814234,0.49400628,0.005960459,0.0016435811,0.4852756,0.00021234498],"about_ca_topic_score_codex":0.000009101185,"about_ca_topic_score_gemma":0.0000014704681,"teacher_disagreement_score":0.861557,"about_ca_system_score_codex":0.00008283588,"about_ca_system_score_gemma":0.0002911306,"threshold_uncertainty_score":0.22054571},"labels":[],"label_agreement":null},{"id":"W4394769784","doi":"10.1016/j.acra.2024.02.028","title":"Use of Response Permutation to Measure an Imaging Dataset’s Susceptibility to Overfitting by Selected Standard Analysis Pipelines","year":2024,"lang":"en","type":"article","venue":"Academic Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; University Health Network","funders":"National Cancer Institute; National Institutes of Health; Queen's University","keywords":"Overfitting; Artificial intelligence; Random forest; Computer science; Support vector machine; Pattern recognition (psychology); Linear discriminant analysis; Machine learning; Logistic regression; Sample size determination; Cross-validation; Bootstrapping (finance); Receiver operating characteristic; Statistics; Data mining; Mathematics; Artificial neural network; Econometrics","score_opus":0.026664217587847757,"score_gpt":0.3603955308308786,"score_spread":0.33373131324303085,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394769784","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94851017,0.0007490004,0.03464673,0.014848664,0.00019714206,0.00034467262,0.0005580974,0.00013781953,0.000007703889],"genre_scores_gemma":[0.98920757,0.00009034861,0.0059770388,0.0029282696,0.00022236965,0.000014250853,0.0014178096,0.00003675615,0.00010559754],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972075,0.00068008277,0.0006565737,0.00070442865,0.0003508676,0.0004005226],"domain_scores_gemma":[0.9979086,0.00094095914,0.00009508053,0.0004324357,0.00022807243,0.00039487213],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0030497815,0.0002047907,0.00063112366,0.0012369753,0.00007194446,0.00003201102,0.00019652446,0.0001799737,0.0000693204],"category_scores_gemma":[0.009885011,0.00017905339,0.00009682563,0.0029382426,0.00012107725,0.00022002221,0.000066462795,0.00095972145,0.000010736016],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022949965,0.000026478223,0.13629217,0.00007692617,0.00042277988,0.000060201965,0.001752492,0.002264696,0.7003811,0.000040787698,0.1322318,0.024155539],"study_design_scores_gemma":[0.0020450633,0.0017542777,0.2680613,0.00064190006,0.0040143915,0.0007881951,0.00089655555,0.3768276,0.015773954,0.0001566943,0.32798868,0.0010513896],"about_ca_topic_score_codex":0.00036811846,"about_ca_topic_score_gemma":0.000017155422,"teacher_disagreement_score":0.68460715,"about_ca_system_score_codex":0.00017548776,"about_ca_system_score_gemma":0.00021811854,"threshold_uncertainty_score":0.99845517},"labels":[],"label_agreement":null},{"id":"W4394786842","doi":"10.5194/essd-2024-19-rc2","title":"Comment on essd-2024-19","year":2024,"lang":"en","type":"peer-review","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Museum of Nature; Université du Québec à Rimouski","funders":"Natural Sciences and Engineering Research Council of Canada; ArcticNet; Fisheries and Oceans Canada; Université du Québec à Rimouski","keywords":"Computer science","score_opus":0.028428650746575333,"score_gpt":0.373399324539043,"score_spread":0.34497067379246765,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394786842","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[9.960182e-7,0.038593646,0.00017167052,0.6600242,0.006221765,0.000440321,0.00003249497,0.00016136645,0.29435351],"genre_scores_gemma":[0.000009118468,0.009507869,0.0005651305,0.39098123,0.0011458161,0.00003561977,0.0006877211,0.000063282605,0.5970042],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.997788,0.00005937793,0.00045079872,0.00056825404,0.0007970116,0.00033655288],"domain_scores_gemma":[0.9986342,0.00018340575,0.000088874585,0.00062919455,0.00006965885,0.00039466124],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00074239756,0.0003812026,0.00094394205,0.00020553022,0.000050685478,0.000049467275,0.00020543755,0.00021490717,0.010867795],"category_scores_gemma":[0.0006467801,0.00025524534,0.0003713676,0.00020292842,0.000071195194,0.000011117456,0.00014046277,0.002492206,0.002116915],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008206119,0.00007458549,0.000004886227,0.010501281,0.00018260474,0.00033154205,0.000013753199,0.0000012366623,0.000001107723,0.0013960415,0.95459676,0.032888025],"study_design_scores_gemma":[0.00035669073,0.00017600438,0.0000038187363,0.02187051,0.00076964154,0.000117377334,0.000005994546,0.00086692034,0.0000026687453,0.00022635383,0.975363,0.00024101703],"about_ca_topic_score_codex":0.00026145697,"about_ca_topic_score_gemma":0.0000039707734,"teacher_disagreement_score":0.3026507,"about_ca_system_score_codex":0.00021468887,"about_ca_system_score_gemma":0.00026568322,"threshold_uncertainty_score":0.99999},"labels":[],"label_agreement":null},{"id":"W4394855486","doi":"10.3390/curroncol31040165","title":"Survival Outcome Prediction in Glioblastoma: Insights from MRI Radiomics","year":2024,"lang":"en","type":"article","venue":"Current Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Isocitrate dehydrogenase; Medicine; Radiomics; Proportional hazards model; Glioblastoma; Lasso (programming language); Magnetic resonance imaging; Feature selection; IDH1; Effective diffusion coefficient; Perfusion; Nuclear medicine; Oncology; Radiology; Pathology; Internal medicine; Artificial intelligence; Computer science; Cancer research; Biology","score_opus":0.0483235910964295,"score_gpt":0.3905166699949984,"score_spread":0.34219307889856887,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394855486","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96516305,0.0079976665,0.0060260063,0.0039728386,0.01323626,0.000292097,0.000018787796,0.00025411483,0.0030391843],"genre_scores_gemma":[0.9967518,0.0005315879,0.0004952511,0.00020337336,0.0016407238,0.000026769412,0.00008527697,0.00003505527,0.00023018687],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985348,0.00012450885,0.000460057,0.0004002508,0.00022233087,0.00025804917],"domain_scores_gemma":[0.9992554,0.0002990442,0.000045005065,0.00019161712,0.000032224405,0.00017667183],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028950197,0.00016082023,0.0004400662,0.0003245941,0.00003720585,0.000028317252,0.000104858,0.00015939008,0.00015748324],"category_scores_gemma":[0.0002548746,0.00013446635,0.00010415488,0.00031496157,0.000113761605,0.00008264279,0.00006041773,0.0010941715,0.00015450694],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046355528,0.0010517568,0.49027434,0.00046821343,0.00019711567,0.0015436304,0.0027725513,0.00024771405,0.0030416555,0.005167285,0.023866381,0.4709058],"study_design_scores_gemma":[0.0026705167,0.00045272964,0.056125473,0.00036449317,0.0001413121,0.00010251711,0.00013813165,0.19223782,0.000069997004,0.0014229086,0.74609745,0.00017665699],"about_ca_topic_score_codex":0.0000552351,"about_ca_topic_score_gemma":0.000047260215,"teacher_disagreement_score":0.72223103,"about_ca_system_score_codex":0.0004558527,"about_ca_system_score_gemma":0.00020174701,"threshold_uncertainty_score":0.5483378},"labels":[],"label_agreement":null},{"id":"W4394866831","doi":"10.1186/s13058-024-01786-w","title":"Meeting Abstracts from the British Society of Breast Radiology annual scientific meeting 2023","year":2024,"lang":"en","type":"article","venue":"Breast Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Dalhousie University; Ottawa Hospital","funders":"","keywords":"Surgical oncology; Medicine; Breast cancer; Medical physics; Radiology; Oncology; Internal medicine; Cancer","score_opus":0.028449231285511887,"score_gpt":0.371402188977522,"score_spread":0.34295295769201006,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394866831","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9413923,0.013675633,0.000047752666,0.038182292,0.0009661804,0.0003809771,0.00079270185,0.000100098114,0.0044620447],"genre_scores_gemma":[0.99395514,0.0006707977,0.00045799633,0.00027931188,0.0019996893,0.000040495794,0.00007111817,0.000049778533,0.002475666],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.99697363,0.00025410118,0.00040239573,0.0005920315,0.0010864156,0.00069143367],"domain_scores_gemma":[0.9979701,0.00092300033,0.000065102264,0.0003423923,0.00047405742,0.00022531862],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004830362,0.0001330702,0.00030430063,0.00008876311,0.0007533286,0.0005415882,0.0003733765,0.000117109645,0.00042138566],"category_scores_gemma":[0.00035695016,0.00010400787,0.00019369563,0.0008572262,0.0012175982,0.00011662765,0.0002371669,0.0015404724,0.000038748232],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017764783,0.00017134756,0.03963286,0.0007294084,0.0005597315,0.0003341621,0.0030388029,0.00048416297,0.05911811,0.000099629055,0.52683455,0.36881956],"study_design_scores_gemma":[0.0021770583,0.00011308503,0.73856354,0.01230671,0.0002168319,0.006224182,0.0055628475,0.05114987,0.0011742036,0.0008238734,0.18118872,0.00049906794],"about_ca_topic_score_codex":0.052098937,"about_ca_topic_score_gemma":0.0005508792,"teacher_disagreement_score":0.6989307,"about_ca_system_score_codex":0.00018559923,"about_ca_system_score_gemma":0.0008568829,"threshold_uncertainty_score":0.9542132},"labels":[],"label_agreement":null},{"id":"W4394873431","doi":"10.1007/s11547-024-01783-1","title":"Ultrasound-based radiomics for early predicting response to neoadjuvant chemotherapy in patients with breast cancer: a systematic review with meta-analysis","year":2024,"lang":"en","type":"review","venue":"La radiologia medica","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":17,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Impact","funders":"Natural Science Foundation of Gansu Province","keywords":"Medicine; Diagnostic odds ratio; Breast cancer; Meta-analysis; Internal medicine; Oncology; Odds ratio; Cochrane Library; Subgroup analysis; Prospective cohort study; Likelihood ratios in diagnostic testing; Receiver operating characteristic; Cancer","score_opus":0.019965296232879362,"score_gpt":0.3307857774371623,"score_spread":0.31082048120428296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394873431","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00032724213,0.9845373,0.0016100293,0.0034119622,0.0001181417,0.009343519,0.0004668668,0.00017034412,0.000014601373],"genre_scores_gemma":[0.0005239955,0.9855114,0.0041116197,0.0034003202,0.00016760315,0.0052961023,0.0004862223,0.00026466892,0.00023803144],"study_design_codex":"systematic_review","study_design_gemma":"meta_analysis","domain_scores_codex":[0.9936077,0.0014392994,0.0018486026,0.0012922385,0.0010420865,0.0007700455],"domain_scores_gemma":[0.99362564,0.003422434,0.00096355664,0.0011593989,0.00022716034,0.00060183427],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.005351956,0.0010562771,0.011970405,0.0010765333,0.000088729335,0.00008558589,0.0006246476,0.00044062332,0.0000926943],"category_scores_gemma":[0.00244772,0.00051711884,0.0021427441,0.002601553,0.00025503588,0.000055470104,0.00004094675,0.0015955676,0.000008926085],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001388307,0.00024298279,0.0017208853,0.84027183,0.14287166,0.00031287855,0.00020152387,0.00007816628,2.921471e-7,0.0000063886646,0.0016380702,0.01126699],"study_design_scores_gemma":[0.0022749437,0.00085474906,0.0004907834,0.3239659,0.64707905,0.0004911002,0.000010267786,0.00046471512,7.608678e-8,0.0000011149639,0.023741014,0.000626264],"about_ca_topic_score_codex":0.00009662192,"about_ca_topic_score_gemma":0.000013229441,"teacher_disagreement_score":0.5163059,"about_ca_system_score_codex":0.0006232891,"about_ca_system_score_gemma":0.0013525963,"threshold_uncertainty_score":0.999728},"labels":[],"label_agreement":null},{"id":"W4394908620","doi":"10.1200/po.23.00687","title":"Tumor Size Is Not Everything: Advancing Radiomics as a Precision Medicine Biomarker in Oncology Drug Development and Clinical Care. A Report of a Multidisciplinary Workshop Coordinated by the RECIST Working Group","year":2024,"lang":"en","type":"article","venue":"JCO Precision Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Ottawa Hospital; Queen's University","funders":"","keywords":"Radiomics; Multidisciplinary approach; Precision oncology; Drug development; Medicine; Medical physics; Clinical trial; Oncology; Precision medicine; Patient care; Internal medicine; Drug; Pathology; Pharmacology; Radiology","score_opus":0.030831788705128912,"score_gpt":0.4029483198222747,"score_spread":0.37211653111714577,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394908620","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95062184,0.00887627,0.0030237213,0.030512616,0.0026726918,0.0013248066,0.0000037953835,0.00011940263,0.0028448445],"genre_scores_gemma":[0.96730715,0.0016664915,0.02623677,0.0022982417,0.00029873024,0.0000934312,0.00005898195,0.00009101566,0.0019492011],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99394685,0.0009210961,0.0026017928,0.0012189535,0.00070346287,0.00060781714],"domain_scores_gemma":[0.9829143,0.015198691,0.00066356355,0.00062669837,0.00020344932,0.0003932571],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.010115843,0.0004170237,0.0015391019,0.00045919186,0.00022476038,0.000037230126,0.00038307044,0.00048143495,0.0001336819],"category_scores_gemma":[0.012568718,0.00027694265,0.00020363297,0.00091891707,0.0008916817,0.00012527652,0.0006417726,0.0020185497,0.000010598652],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0027198428,0.00043048378,0.008690827,0.00017851502,0.00019981203,0.0049081678,0.013904188,0.000015017437,0.0041750777,0.000031347252,0.024724528,0.9400222],"study_design_scores_gemma":[0.009535665,0.0020121897,0.027194967,0.006516064,0.0004150651,0.009312927,0.008725965,0.0392699,0.0004998551,0.0005196112,0.8954502,0.0005475926],"about_ca_topic_score_codex":0.00026408202,"about_ca_topic_score_gemma":0.00015346154,"teacher_disagreement_score":0.9394746,"about_ca_system_score_codex":0.0011168739,"about_ca_system_score_gemma":0.0011348786,"threshold_uncertainty_score":0.9999683},"labels":[],"label_agreement":null},{"id":"W4394913459","doi":"10.3390/biomedicines12040896","title":"Integrating Demographics and Imaging Features for Various Stages of Dementia Classification: Feed Forward Neural Network Multi-Class Approach","year":2024,"lang":"en","type":"article","venue":"Biomedicines","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of Mental Health; National Institute on Aging; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Eisai; Northern California Institute for Research and Education; Pfizer; Biogen; BioClinica; Avid Radiopharmaceuticals; National Center for Research Resources; F. Hoffmann-La Roche; Wellcome Trust; University of Southern California; Novartis Pharmaceuticals Corporation; U.S. Department of Defense; Eli Lilly and Company; Bristol-Myers Squibb; James S. McDonnell Foundation; Alzheimer's Disease Neuroimaging Initiative; National Center for Advancing Translational Sciences; Meso Scale Diagnostics; Alzheimer's Association; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; Tung Wah College","keywords":"Demographics; Class (philosophy); Artificial neural network; Dementia; Artificial intelligence; Computer science; Pattern recognition (psychology); Medicine; Pathology; Demography; Sociology","score_opus":0.018894808543210094,"score_gpt":0.3081722049262466,"score_spread":0.2892773963830365,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394913459","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22770917,0.112000965,0.6147797,0.03728802,0.003489066,0.0025681367,0.000051620045,0.0007431232,0.0013702061],"genre_scores_gemma":[0.9371973,0.0003428534,0.06054272,0.0006230493,0.0008611744,0.000049044145,0.00013162378,0.000046063044,0.00020616919],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985933,0.000041083833,0.00040635778,0.00038723994,0.00025575171,0.00031627066],"domain_scores_gemma":[0.9990787,0.0003372893,0.00011308535,0.00018998454,0.00012236225,0.00015857756],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006656434,0.00021025725,0.0003974487,0.00028403974,0.00013581847,0.0000644609,0.00010606829,0.0000833952,0.000005932105],"category_scores_gemma":[0.00034475172,0.00014823962,0.0001202157,0.00042544777,0.00038849373,0.0000788606,0.000045928457,0.000347202,3.4338703e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026215182,0.00031380882,0.43813366,0.0062487167,0.001429156,0.00008142629,0.0027202112,0.00016386659,0.04879391,0.010721908,0.047510583,0.44362062],"study_design_scores_gemma":[0.0020082616,0.00022867134,0.08015764,0.0008601647,0.0008627874,0.00026564766,0.0012566089,0.89473885,0.00009253291,0.00029583744,0.018994378,0.0002385997],"about_ca_topic_score_codex":0.000045947978,"about_ca_topic_score_gemma":0.0000042661654,"teacher_disagreement_score":0.894575,"about_ca_system_score_codex":0.000019959292,"about_ca_system_score_gemma":0.00006481728,"threshold_uncertainty_score":0.6045036},"labels":[],"label_agreement":null},{"id":"W4394959049","doi":"10.3389/fonc.2024.1273437","title":"Quantitative ultrasound radiomics guided adaptive neoadjuvant chemotherapy in breast cancer: early results from a randomized feasibility study","year":2024,"lang":"en","type":"article","venue":"Frontiers in Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University; Health Sciences Centre; York University; University of Toronto; Sunnybrook Health Science Centre","funders":"Canadian Institutes of Health Research; Terry Fox Foundation","keywords":"Medicine; Breast cancer; Taxane; Chemotherapy; Anthracycline; Regimen; Randomized controlled trial; Internal medicine; Neoadjuvant therapy; Oncology; Radiology; Cancer","score_opus":0.025459208068525536,"score_gpt":0.3629605852494369,"score_spread":0.3375013771809114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394959049","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9703238,0.0032838145,0.007966042,0.012024583,0.0027375922,0.0024572397,0.0001440741,0.00008749297,0.00097538193],"genre_scores_gemma":[0.97158843,0.0016031555,0.025116907,0.000889121,0.0002879232,0.00018861514,0.000053020274,0.00005646999,0.00021634008],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.99619746,0.001077267,0.0010678426,0.0008745551,0.00031145316,0.00047144562],"domain_scores_gemma":[0.997172,0.0020112186,0.00018539968,0.00036529644,0.00008536639,0.0001807224],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0031342115,0.0003086981,0.0018038442,0.00049126963,0.000047806774,0.00004433532,0.00022549977,0.00023659688,0.000059741767],"category_scores_gemma":[0.0014792542,0.00025321989,0.00020101973,0.0006276187,0.00050403626,0.000123087,0.000043750268,0.0012474058,0.00000720373],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.4373217,0.0028696663,0.3924716,0.00006857769,0.0017257096,0.0027667766,0.05420558,0.0008134414,0.0013323083,0.00035773343,0.034507066,0.07155982],"study_design_scores_gemma":[0.47128543,0.001800506,0.2924481,0.00077179755,0.00045570196,0.00016308426,0.008862187,0.21554461,0.000043960565,0.005523072,0.0025280293,0.0005735265],"about_ca_topic_score_codex":0.011432103,"about_ca_topic_score_gemma":0.00045447098,"teacher_disagreement_score":0.21473117,"about_ca_system_score_codex":0.0016742488,"about_ca_system_score_gemma":0.00071083,"threshold_uncertainty_score":0.999992},"labels":[],"label_agreement":null},{"id":"W4394961497","doi":"10.3389/fimag.2024.1373420","title":"ChestBioX-Gen: contextual biomedical report generation from chest X-ray images using BioGPT and co-attention mechanism","year":2024,"lang":"en","type":"article","venue":"Frontiers in Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"Alliance de recherche numérique du Canada; New Brunswick Innovation Foundation; Fondation de la recherche en santé du Nouveau-Brunswick","keywords":"Mechanism (biology); Medicine; Psychology; Philosophy; Epistemology","score_opus":0.014768357407791897,"score_gpt":0.2975488164979846,"score_spread":0.28278045909019267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394961497","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42741305,0.005881126,0.5574515,0.005464496,0.0030149077,0.00027910143,0.000019906362,0.00017410178,0.000301803],"genre_scores_gemma":[0.8678993,0.00024424717,0.12933409,0.0005534431,0.00116335,0.00001271674,0.0004405454,0.00006266075,0.0002896119],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980044,0.00007990333,0.00051921763,0.0006448528,0.0003919908,0.00035967163],"domain_scores_gemma":[0.99936324,0.000047831392,0.000093844916,0.00023442617,0.00004289855,0.00021775792],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008681338,0.00023528592,0.00040617507,0.0004609521,0.000119066855,0.00019992919,0.00008492014,0.00010906686,0.000047733567],"category_scores_gemma":[0.00029407113,0.00021867246,0.00009253689,0.0002805856,0.0002972618,0.00028497743,0.00005608166,0.00058516674,0.000006515075],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005170147,0.00014238215,0.12995216,0.00023246348,0.0002539439,0.0068110707,0.0010308648,0.000017821878,0.66720676,0.00043848078,0.047400434,0.14646192],"study_design_scores_gemma":[0.0017760878,0.00005411612,0.018088268,0.0009002002,0.00030195477,0.0013111988,0.0011252047,0.9462961,0.0038649652,0.0015432372,0.02428496,0.00045372712],"about_ca_topic_score_codex":0.00034122437,"about_ca_topic_score_gemma":0.000001269857,"teacher_disagreement_score":0.9462783,"about_ca_system_score_codex":0.00017483628,"about_ca_system_score_gemma":0.00013951608,"threshold_uncertainty_score":0.8917204},"labels":[],"label_agreement":null},{"id":"W4394962110","doi":"","title":"[A review on the application of image fusion technology in prostate cancer radiotherapy based on gold fiducial biomarker].","year":2023,"lang":"en","type":"article","venue":"PubMed","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Northern College","funders":"","keywords":"Fiducial marker; Prostate cancer; Gold standard (test); Radiation therapy; Medicine; Image fusion; Image-guided radiation therapy; Biomarker; Prostate; Medical physics; Cancer; Radiology; Oncology; Nuclear medicine; Internal medicine; Computer science; Artificial intelligence; Image (mathematics); Chemistry","score_opus":0.01579097833457517,"score_gpt":0.30676871506647624,"score_spread":0.2909777367319011,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394962110","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44529867,0.008519245,0.00049713586,0.53543717,0.00035256677,0.006953139,0.000018225162,0.00030255353,0.0026212821],"genre_scores_gemma":[0.964004,0.016970066,0.0002260555,0.012785064,0.00012370085,0.005458223,0.0000374026,0.000042810083,0.00035269838],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9990796,0.00006282103,0.0002271718,0.0002097755,0.0001933361,0.00022731793],"domain_scores_gemma":[0.99939,0.00012597856,0.00010489889,0.00030075177,0.00003290419,0.000045476198],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010058839,0.000093518465,0.00023362602,0.00026469163,0.000026675785,0.0000046911855,0.00011762883,0.000045690515,0.000019563873],"category_scores_gemma":[0.0005479726,0.00005882963,0.000049491937,0.0009837011,0.00010159933,0.00001388366,0.000016409513,0.0002704641,0.000005651442],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015749277,0.00008671622,0.0060869474,0.00048492913,0.000014583711,0.00001048395,0.00002634042,0.000052533807,0.004778459,0.00019437348,0.012581476,0.9755257],"study_design_scores_gemma":[0.0054305145,0.00026083784,0.59160674,0.0048821224,0.00011002614,0.000012471543,0.000046532412,0.19303596,0.0046772105,0.0006253686,0.19893001,0.00038218926],"about_ca_topic_score_codex":0.00007456317,"about_ca_topic_score_gemma":0.0000036306603,"teacher_disagreement_score":0.9751435,"about_ca_system_score_codex":0.00008356636,"about_ca_system_score_gemma":0.00003783511,"threshold_uncertainty_score":0.23990028},"labels":[],"label_agreement":null},{"id":"W4394988492","doi":"10.1016/j.urology.2024.04.009","title":"Advancing Precision Oncology With Artificial Intelligence: Ushering in the ArteraAI Prostate Test","year":2024,"lang":"en","type":"letter","venue":"Urology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Medicine; Test (biology); Prostate; Medical physics; Prostate cancer; Oncology; Internal medicine; Cancer","score_opus":0.013073617345333665,"score_gpt":0.31193223473180015,"score_spread":0.29885861738646646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394988492","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0059042587,0.0005484046,0.004453809,0.9838288,0.00092756475,0.000705458,0.000004676997,0.00008335979,0.0035437078],"genre_scores_gemma":[0.06755262,0.00016002907,0.0017311632,0.92400354,0.0051119006,0.00015391712,0.00015920872,0.00012686726,0.0010007551],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.997706,0.00022312887,0.0005116776,0.0005927619,0.00034374118,0.0006226709],"domain_scores_gemma":[0.9980097,0.0013545506,0.00013290814,0.00039510423,0.000047590882,0.00006017937],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0009252454,0.00029962082,0.00057933177,0.0003363315,0.00006517734,0.00005691177,0.0002699588,0.0005671406,0.000108980785],"category_scores_gemma":[0.00069261057,0.00017736397,0.00008380588,0.0003121302,0.00025927965,0.00003915405,0.0000810269,0.0063555394,0.00012777597],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041128485,0.00022516516,0.0016450868,0.0006006982,0.00012560432,0.03814488,0.004526132,0.0012936768,0.00040942323,0.00016115145,0.590881,0.36157593],"study_design_scores_gemma":[0.0001912355,0.0019437239,0.000107143554,0.00023590821,0.00017537417,0.0028753194,0.00014343143,0.019105326,0.000013025991,0.002738216,0.9722794,0.0001918912],"about_ca_topic_score_codex":0.000041879677,"about_ca_topic_score_gemma":0.000038854607,"teacher_disagreement_score":0.38139844,"about_ca_system_score_codex":0.00013283844,"about_ca_system_score_gemma":0.00026938206,"threshold_uncertainty_score":0.9959368},"labels":[],"label_agreement":null},{"id":"W4395026787","doi":"10.5435/jaaos-d-23-00831","title":"Deep Learning and Multimodal Artificial Intelligence in Orthopaedic Surgery","year":2024,"lang":"en","type":"review","venue":"Journal of the American Academy of Orthopaedic Surgeons","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"National Cancer Institute; Fondation du cancer des Cèdres; University of Toronto","keywords":"Deep learning; Artificial intelligence; Medicine; Convolutional neural network; Machine learning; Artificial neural network; Computer science","score_opus":0.03478081678079281,"score_gpt":0.36437706973177064,"score_spread":0.32959625295097783,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4395026787","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006540503,0.98937416,0.00030994805,0.0026230058,0.0007327567,0.0003329778,0.0000044210033,0.000023804125,0.000058425496],"genre_scores_gemma":[0.017070243,0.98128605,0.00060128665,0.00025892843,0.0005729519,0.000008579846,0.0000033660422,0.00009944149,0.00009915985],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9944823,0.0008550424,0.0027541579,0.00041424859,0.00096436613,0.0005299136],"domain_scores_gemma":[0.99341863,0.002622865,0.003299895,0.0001804146,0.00007898363,0.00039922685],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.004445282,0.0005173575,0.00388626,0.0015444929,0.000089545865,0.00003640703,0.00038802403,0.00025317393,0.000044311186],"category_scores_gemma":[0.004874214,0.00031523296,0.00236736,0.0019468734,0.0012148408,0.00008561822,0.00026312418,0.0062450357,0.000007899294],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006793921,0.00007759424,0.010823443,0.004101006,0.0003896759,0.0002494673,0.00008846442,0.000031161697,0.0000033201873,0.000043797,0.00028544953,0.9838387],"study_design_scores_gemma":[0.00026592257,0.0002828395,0.005592203,0.06786441,0.00621135,0.0072789756,0.00046332803,0.004481153,0.000003486566,0.0003592742,0.9064813,0.00071569986],"about_ca_topic_score_codex":0.00006961353,"about_ca_topic_score_gemma":0.0000039726724,"teacher_disagreement_score":0.983123,"about_ca_system_score_codex":0.00015639885,"about_ca_system_score_gemma":0.0007458001,"threshold_uncertainty_score":0.99992996},"labels":[],"label_agreement":null},{"id":"W4395034382","doi":"10.1055/s-0044-1782888","title":"Artificial Intelligence and colorectal neoplasia detection performances in FIT+patients: a meta-analysis and systematic review","year":2024,"lang":"en","type":"article","venue":"Endoscopy","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Michael's Hospital","funders":"","keywords":"Medicine; Meta-analysis; MEDLINE; Colonoscopy; Colorectal cancer; Artificial intelligence; Internal medicine; Computer science; Cancer","score_opus":0.02908867110665957,"score_gpt":0.3268310205569749,"score_spread":0.2977423494503153,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4395034382","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83311796,0.15547168,0.007656354,0.0016996927,0.00023126355,0.0015493816,0.0000047562335,0.00008401786,0.00018487696],"genre_scores_gemma":[0.99467856,0.004182089,0.00068054756,0.00026958864,0.000026275919,0.000108386,0.0000054982497,0.000008721782,0.0000403123],"study_design_codex":"systematic_review","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999034,0.00008215845,0.00036677325,0.0002251346,0.00017130862,0.00012066165],"domain_scores_gemma":[0.9995835,0.00017998167,0.000052006297,0.000091992304,0.000021973432,0.00007058422],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005729078,0.000109191074,0.0007322292,0.00024819505,0.000039617687,0.000050940507,0.000033064327,0.000031056494,0.00007099826],"category_scores_gemma":[0.00045225368,0.0000726487,0.00014464752,0.0005533008,0.00005594741,0.00008409102,0.000020405454,0.00024447724,0.00000928494],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002830808,0.00041349666,0.04696212,0.7988696,0.072387904,0.0003384641,0.0050615794,0.0001970559,0.0015334828,0.0009079148,0.00016858077,0.072876684],"study_design_scores_gemma":[0.0003313542,0.0010342724,0.007509109,0.030973831,0.3794259,0.00014016575,0.00036998722,0.5747686,0.0040802024,0.0005454593,0.0002731646,0.0005479252],"about_ca_topic_score_codex":0.000053682732,"about_ca_topic_score_gemma":0.00004060679,"teacher_disagreement_score":0.7678958,"about_ca_system_score_codex":0.000026818003,"about_ca_system_score_gemma":0.00001684289,"threshold_uncertainty_score":0.2962528},"labels":[],"label_agreement":null},{"id":"W4395073625","doi":"10.18280/ria.380205","title":"Deep Learning-Based Medical Image Reconstruction: Overview, Analysis, and Challenges","year":2024,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Artificial intelligence; Deep learning; Computer science; Image (mathematics); Computer vision; Data science","score_opus":0.032435264312782444,"score_gpt":0.3163047142954529,"score_spread":0.2838694499826705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4395073625","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.046105556,0.12774077,0.74299175,0.07102099,0.0011873575,0.00040587023,0.000002234516,0.0006800897,0.009865379],"genre_scores_gemma":[0.95603687,0.035022065,0.006461884,0.0005340172,0.0006298199,0.000021689284,0.000025950583,0.000044422508,0.001223286],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983702,0.00009587717,0.00040233086,0.00051470916,0.0003378868,0.00027904776],"domain_scores_gemma":[0.998941,0.00034924076,0.000051295425,0.00026899864,0.00007211203,0.00031736863],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009330662,0.00017120645,0.0003819953,0.000358343,0.00012171695,0.00009124005,0.00011178694,0.00013236138,0.0018595348],"category_scores_gemma":[0.0007744354,0.00014709863,0.00020794904,0.0007212361,0.00028992334,0.00008621748,0.000046701945,0.00076611515,0.0002167873],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024585544,0.00007657079,0.0023085445,0.0009295344,0.00033902374,0.0004274601,0.00058688194,0.0043057045,0.00047554448,0.002643274,0.0001045788,0.9877783],"study_design_scores_gemma":[0.000062167,0.00011351652,0.00068964827,0.00051588967,0.00036634965,0.00046516667,0.00040623036,0.96594065,0.00104564,0.0003871824,0.029856058,0.00015149874],"about_ca_topic_score_codex":0.000025573205,"about_ca_topic_score_gemma":0.000017698858,"teacher_disagreement_score":0.9876268,"about_ca_system_score_codex":0.000041611052,"about_ca_system_score_gemma":0.00010791806,"threshold_uncertainty_score":0.9990529},"labels":[],"label_agreement":null},{"id":"W4395080969","doi":"10.5194/essd-2024-96-rc1","title":"Comment on essd-2024-96","year":2024,"lang":"en","type":"peer-review","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science","score_opus":0.026047797199725733,"score_gpt":0.3654806963533679,"score_spread":0.33943289915364216,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4395080969","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000014649318,0.033068296,0.00013096104,0.6562389,0.00656203,0.00041678167,0.000029837905,0.00015165962,0.30340004],"genre_scores_gemma":[0.000011998068,0.009156006,0.00059194147,0.35062528,0.0012967912,0.00003652127,0.0006749297,0.00007050638,0.63753605],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977912,0.00005555303,0.00045477707,0.0005616818,0.0007957665,0.00034103967],"domain_scores_gemma":[0.99873966,0.00015815222,0.00008783256,0.00062818674,0.00008057407,0.00030556697],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0006871437,0.00038624147,0.00095907814,0.00019683153,0.000047148158,0.00005014038,0.0002044862,0.00021512918,0.0107381055],"category_scores_gemma":[0.000464015,0.00025768986,0.00037378556,0.00019784321,0.00006983697,0.000011728889,0.000139562,0.0025438054,0.0023785643],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007489084,0.00007649662,0.0000064554556,0.008784414,0.00018408333,0.0002891381,0.000011371234,7.191913e-7,0.0000013785095,0.0011827262,0.94550294,0.04395282],"study_design_scores_gemma":[0.00032732222,0.00018531784,0.0000052693254,0.027036732,0.0007882929,0.00009797708,0.000005190573,0.0007774993,0.0000053243584,0.00018306547,0.9703466,0.00024139027],"about_ca_topic_score_codex":0.00016758605,"about_ca_topic_score_gemma":0.0000032577677,"teacher_disagreement_score":0.334136,"about_ca_system_score_codex":0.00017435823,"about_ca_system_score_gemma":0.00020131197,"threshold_uncertainty_score":0.99998754},"labels":[],"label_agreement":null},{"id":"W4395955371","doi":"10.5194/essd-2024-96-rc2","title":"Comment on essd-2024-96","year":2024,"lang":"en","type":"peer-review","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Mathematics","score_opus":0.026047797199725733,"score_gpt":0.3654806963533679,"score_spread":0.33943289915364216,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4395955371","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000014649318,0.033068296,0.00013096104,0.6562389,0.00656203,0.00041678167,0.000029837905,0.00015165962,0.30340004],"genre_scores_gemma":[0.000011998068,0.009156006,0.00059194147,0.35062528,0.0012967912,0.00003652127,0.0006749297,0.00007050638,0.63753605],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977912,0.00005555303,0.00045477707,0.0005616818,0.0007957665,0.00034103967],"domain_scores_gemma":[0.99873966,0.00015815222,0.00008783256,0.00062818674,0.00008057407,0.00030556697],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0006871437,0.00038624147,0.00095907814,0.00019683153,0.000047148158,0.00005014038,0.0002044862,0.00021512918,0.0107381055],"category_scores_gemma":[0.000464015,0.00025768986,0.00037378556,0.00019784321,0.00006983697,0.000011728889,0.000139562,0.0025438054,0.0023785643],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007489084,0.00007649662,0.0000064554556,0.008784414,0.00018408333,0.0002891381,0.000011371234,7.191913e-7,0.0000013785095,0.0011827262,0.94550294,0.04395282],"study_design_scores_gemma":[0.00032732222,0.00018531784,0.0000052693254,0.027036732,0.0007882929,0.00009797708,0.000005190573,0.0007774993,0.0000053243584,0.00018306547,0.9703466,0.00024139027],"about_ca_topic_score_codex":0.00016758605,"about_ca_topic_score_gemma":0.0000032577677,"teacher_disagreement_score":0.334136,"about_ca_system_score_codex":0.00017435823,"about_ca_system_score_gemma":0.00020131197,"threshold_uncertainty_score":0.99998754},"labels":[],"label_agreement":null},{"id":"W4395959600","doi":"10.1016/j.biopsych.2024.02.794","title":"295. Rare Variant Genetic Architecture of the Human Cortical MRI Phenotypes in General Population","year":2024,"lang":"en","type":"article","venue":"Biological Psychiatry","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Centre Hospitalier Universitaire Sainte-Justine","funders":"","keywords":"Genetic architecture; Phenotype; Architecture; Population; Biology; Genetics; Neuroscience; Medicine; Gene; Geography","score_opus":0.012772636671505543,"score_gpt":0.296745267547273,"score_spread":0.28397263087576746,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4395959600","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9878481,0.0016644162,0.0013583016,0.007247045,0.00089744735,0.00020957009,0.0000034665486,0.000052043542,0.0007195862],"genre_scores_gemma":[0.9915611,0.000027312997,0.0067917076,0.0008763855,0.00060394563,0.0000060080865,0.000022263737,0.000011988783,0.000099293306],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99895996,0.0001281356,0.00031189894,0.0002607814,0.0001522638,0.0001869732],"domain_scores_gemma":[0.9996317,0.000053660093,0.000039236384,0.0001923956,0.00001136751,0.000071647],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019549072,0.000114044466,0.00022071014,0.00006292479,0.00005664533,0.000013847106,0.00012405621,0.00013612589,0.00013880679],"category_scores_gemma":[0.00012696917,0.000058808815,0.00012922216,0.0002093208,0.00012556034,0.000010249328,0.00005018529,0.00063331006,0.000005368984],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000054815697,0.00017147412,0.9550491,0.00015788316,0.000043012937,0.000043474018,0.00009819321,0.00043109106,0.008017649,0.024438769,0.0010660217,0.010428518],"study_design_scores_gemma":[0.00034582024,0.0001364847,0.9802495,0.00020488983,0.0000334541,0.00008824815,0.00001304473,0.005033057,0.000013165956,0.012452127,0.0013485075,0.000081670376],"about_ca_topic_score_codex":0.00009012264,"about_ca_topic_score_gemma":0.000014378875,"teacher_disagreement_score":0.025200432,"about_ca_system_score_codex":0.000024485944,"about_ca_system_score_gemma":0.000046640547,"threshold_uncertainty_score":0.27514523},"labels":[],"label_agreement":null},{"id":"W4395959855","doi":"10.1016/j.biopsych.2024.02.057","title":"Nilearn and Big Data Facilitates Transdiagnostic Brain Biomarkers","year":2024,"lang":"en","type":"article","venue":"Biological Psychiatry","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Institut Universitaire de Gériatrie de Montréal","funders":"","keywords":"Big data; Psychology; Data science; Neuroscience; Computer science; Medicine; Data mining","score_opus":0.057386006896343496,"score_gpt":0.33046807204370515,"score_spread":0.27308206514736166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4395959855","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81306857,0.036462925,0.0041023614,0.139612,0.0032995092,0.00037348905,0.00014544721,0.00047064375,0.002465059],"genre_scores_gemma":[0.9879035,0.0012383187,0.0048539466,0.004402326,0.0009232286,0.0000085845595,0.0003169232,0.000021800251,0.00033141839],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99873745,0.0000770738,0.00022682744,0.00057240226,0.00012676638,0.000259491],"domain_scores_gemma":[0.99885154,0.00055398274,0.000017459786,0.00034527102,0.000010550918,0.00022121253],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005458101,0.00015816977,0.00023534684,0.00008719822,0.00006920762,0.00005526366,0.00017616682,0.00013697513,0.00014120516],"category_scores_gemma":[0.0009372421,0.000099957935,0.00006668253,0.00018994682,0.00029515184,0.000044902063,0.000090664405,0.0004294542,0.000053176147],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018278343,0.0002070725,0.21537343,0.000608261,0.00036929004,0.00019439029,0.00017955611,0.0000015526093,0.0035509286,0.0026048017,0.15206425,0.6246637],"study_design_scores_gemma":[0.0014790073,0.0009144677,0.28608155,0.0007012591,0.00018395256,0.0005375208,0.0003640399,0.013250147,0.000009888783,0.006616252,0.6894113,0.00045062794],"about_ca_topic_score_codex":0.000028540502,"about_ca_topic_score_gemma":0.0000030113342,"teacher_disagreement_score":0.62421304,"about_ca_system_score_codex":0.000011123033,"about_ca_system_score_gemma":0.000081858576,"threshold_uncertainty_score":0.40761665},"labels":[],"label_agreement":null},{"id":"W4396515772","doi":"10.1164/ajrccm-conference.2024.209.1_meetingabstracts.a2732","title":"Prevalence and Prognosis of Subclinical Lung Pathology on Computed Tomography (CT) Scan Among Adults Meeting Lung Function Reference Population Eligibility Criteria","year":2024,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Dalhousie University; Hamilton Health Sciences","funders":"","keywords":"Subclinical infection; Computed tomography; Lung function; Medicine; Lung; Radiology; Population; Pathology; Internal medicine; Environmental health","score_opus":0.014457963102094386,"score_gpt":0.3429596129213144,"score_spread":0.32850164981922,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396515772","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99535966,0.000652,0.0016226397,0.0005265171,0.00032971826,0.00043817243,0.000004694049,0.00018686724,0.00087971013],"genre_scores_gemma":[0.9975579,0.00012613987,0.0018950833,0.00017768893,0.00011094845,0.0000169806,0.000052519703,0.00001778738,0.000044946417],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9983003,0.00017528876,0.00052162784,0.0005434448,0.00025782772,0.00020150049],"domain_scores_gemma":[0.9991093,0.00034652711,0.00010270831,0.00020890741,0.00009549067,0.00013701426],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009876931,0.00015182108,0.00032304687,0.0001941147,0.000066193534,0.000039015504,0.0000623585,0.00008593012,0.00005415909],"category_scores_gemma":[0.00056356395,0.0001201907,0.000085348365,0.00027320694,0.00017165243,0.00010483012,0.000053946835,0.00045636774,0.0000010588244],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020164561,0.000091895185,0.9771316,0.0019378242,0.000042436288,0.000028347364,0.00010288165,0.000013357463,0.0006490569,0.0004828863,0.00023620817,0.019081842],"study_design_scores_gemma":[0.0003889337,0.00030100986,0.7578779,0.001972508,0.00013533492,0.000028627508,0.000018511872,0.23893197,0.00011854685,0.00012762628,0.000012990104,0.00008603917],"about_ca_topic_score_codex":0.00031035076,"about_ca_topic_score_gemma":0.000013903519,"teacher_disagreement_score":0.23891862,"about_ca_system_score_codex":0.000033678778,"about_ca_system_score_gemma":0.000026003047,"threshold_uncertainty_score":0.49012345},"labels":[],"label_agreement":null},{"id":"W4396519860","doi":"10.18280/ts.410248","title":"Machine Learning-Based Lung Cancer Classification and Enhanced Accuracy on CT Images","year":2024,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Lung cancer; Artificial intelligence; Computer science; Computed tomography; Pattern recognition (psychology); Computer vision; Machine learning; Radiology; Medicine; Pathology","score_opus":0.015028101508926122,"score_gpt":0.32086640210037554,"score_spread":0.3058383005914494,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396519860","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89418036,0.007144114,0.05477113,0.037845746,0.0005192401,0.00091788126,0.00003138067,0.0005863936,0.004003737],"genre_scores_gemma":[0.9965828,0.00037127122,0.00036887743,0.001328827,0.00031725448,0.00007088504,0.00008159627,0.000035639187,0.00084284926],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998814,0.00006302952,0.00023275217,0.0003536015,0.00031526526,0.0002213688],"domain_scores_gemma":[0.99944645,0.00021254447,0.000056249064,0.000103503306,0.000034638135,0.00014662309],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003452497,0.00017091031,0.00020052775,0.00014729434,0.000111907706,0.00009312338,0.000060536957,0.000029445258,0.0009766072],"category_scores_gemma":[0.00013184566,0.00013399016,0.00006957545,0.00014447272,0.000079165206,0.00007735666,0.000014357785,0.00053009915,0.000016050162],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00049867586,0.00037429505,0.023886004,0.0015121904,0.00038010473,0.0003005127,0.0007134871,0.006239071,0.2827776,0.0014775272,0.011369047,0.6704715],"study_design_scores_gemma":[0.0015618901,0.00028616277,0.024087518,0.00073534815,0.00019880378,0.0000201789,0.00003487053,0.9326196,0.008586636,0.000033990058,0.031640742,0.00019430916],"about_ca_topic_score_codex":0.000069176946,"about_ca_topic_score_gemma":0.0000019178217,"teacher_disagreement_score":0.92638046,"about_ca_system_score_codex":0.00009418404,"about_ca_system_score_gemma":0.000095976786,"threshold_uncertainty_score":0.99993664},"labels":[],"label_agreement":null},{"id":"W4396531001","doi":"10.1164/ajrccm-conference.2024.209.1_meetingabstracts.a6814","title":"Association of Pre-pandemic High Attenuation Areas on Lung CT and COVID-19 Hospitalization and Death: The C4R Study","year":2024,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Pandemic; Coronavirus disease 2019 (COVID-19); 2019-20 coronavirus outbreak; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Attenuation; Medicine; Pneumonia; Betacoronavirus; Association (psychology); Virology; Internal medicine; Physics; Psychology; Outbreak; Disease; Optics","score_opus":0.012341895473958168,"score_gpt":0.3274320236769593,"score_spread":0.31509012820300114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396531001","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98351234,0.0003741836,0.00563713,0.009413132,0.0001188979,0.00047162865,0.000002020501,0.00006971726,0.00040093],"genre_scores_gemma":[0.9973773,0.00016267499,0.00005983491,0.0008743148,0.00008313509,0.000012424699,0.000020787613,0.000011220889,0.0013983347],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9992245,0.00008330489,0.00016844418,0.00017832089,0.00026199428,0.00008345322],"domain_scores_gemma":[0.9993456,0.00038933402,0.0000625987,0.0000939405,0.000034851255,0.00007368379],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008454712,0.000074731375,0.0001344786,0.0000720033,0.00007386526,0.000043895972,0.000027600941,0.000024775445,0.000029819768],"category_scores_gemma":[0.0011286455,0.00004601257,0.000018991437,0.000114825634,0.000022958526,0.000053940657,0.000021031145,0.00016960257,0.0000010704699],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002665276,0.000059263526,0.9864852,0.00012295328,0.00012060313,0.000009477074,0.0013382739,0.00012291652,0.00012126295,0.001495394,0.0024768913,0.00762113],"study_design_scores_gemma":[0.0010622664,0.00035370048,0.88021016,0.00010937946,0.00033432213,0.00002844108,0.00037466089,0.115577176,0.000025517022,0.00061128906,0.0012410515,0.000072040195],"about_ca_topic_score_codex":0.0003883852,"about_ca_topic_score_gemma":0.000017378557,"teacher_disagreement_score":0.11545426,"about_ca_system_score_codex":0.00012592718,"about_ca_system_score_gemma":0.000053700947,"threshold_uncertainty_score":0.18763381},"labels":[],"label_agreement":null},{"id":"W4396559668","doi":"10.18280/ts.410243","title":"Classification of Lung Adenocarcinoma Using Convolutional Neural Networks: A Bioinformatics Approach","year":2024,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Convolutional neural network; Computer science; Adenocarcinoma; Artificial intelligence; Computational biology; Bioinformatics; Machine learning; Biology; Medicine; Internal medicine; Cancer","score_opus":0.028346184123631383,"score_gpt":0.289869088207222,"score_spread":0.26152290408359063,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396559668","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40328574,0.0017249744,0.59268165,0.0006279135,0.0002413182,0.00034220336,0.000007538454,0.0000925407,0.0009960872],"genre_scores_gemma":[0.986753,0.000014435087,0.012451445,0.00020855792,0.00039182304,0.0000094510115,0.00011203387,0.000018900753,0.000040393967],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99881524,0.000034255325,0.00042591777,0.00016729745,0.00035061786,0.00020667847],"domain_scores_gemma":[0.9995789,0.0000649739,0.00008256223,0.000107825465,0.00005688565,0.00010887577],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003910956,0.0001234147,0.00020854991,0.00015134837,0.000060869344,0.000039625393,0.00007725361,0.000057633068,0.00013710016],"category_scores_gemma":[0.000024537752,0.00010244934,0.00010971831,0.00023079696,0.00012467211,0.00012000771,0.00002401272,0.00029214608,0.0000023506634],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008663375,0.0016552875,0.41031274,0.009738712,0.0022878358,0.00023405974,0.0071453033,0.2971583,0.04744049,0.06822385,0.021888241,0.13304883],"study_design_scores_gemma":[0.0005455166,0.000072731935,0.035802014,0.00016170081,0.00017948715,0.00014769835,0.00012625866,0.9625265,0.000020248002,0.00002470931,0.00030391436,0.00008923997],"about_ca_topic_score_codex":0.000012538777,"about_ca_topic_score_gemma":9.036459e-8,"teacher_disagreement_score":0.6653682,"about_ca_system_score_codex":0.000095614254,"about_ca_system_score_gemma":0.000095133866,"threshold_uncertainty_score":0.4177763},"labels":[],"label_agreement":null},{"id":"W4396571304","doi":"10.1088/2057-1976/ad4651","title":"Developing and validating multi-omics prediction models for late patient-reported dysphagia in head and neck radiotherapy","year":2024,"lang":"en","type":"article","venue":"Biomedical Physics & Engineering Express","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Baker Hughes (Canada); University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Innovates; Killam Trusts","keywords":"Dysphagia; Medicine; Omics; Head and neck cancer; Radiation therapy; Feature (linguistics); Head and neck; Radiology; Bioinformatics; Surgery","score_opus":0.021658679519089216,"score_gpt":0.291710717689301,"score_spread":0.2700520381702118,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396571304","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4077593,0.0011414149,0.59008723,0.00033139688,0.00027297655,0.00025930416,0.000009950635,0.00013599619,0.000002432816],"genre_scores_gemma":[0.5548359,0.00033967878,0.4440372,0.00016903438,0.00035198627,0.00007586443,0.00008923338,0.00007741247,0.000023653834],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987211,0.000013199532,0.00037146205,0.00037819386,0.00021060674,0.00030543836],"domain_scores_gemma":[0.9994467,0.0001607099,0.000042985088,0.0001243064,0.000029873663,0.0001954222],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002400438,0.00019467132,0.00030996202,0.00013664909,0.00004761393,0.000069664566,0.000049336944,0.00011211404,0.0000010297433],"category_scores_gemma":[0.00013969737,0.00017891066,0.00004629282,0.0002034308,0.0000694267,0.00016363378,0.000044709228,0.00036254158,2.220625e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015609468,0.0002817485,0.0033944058,0.0038171299,0.0005890608,0.0002346321,0.0047955834,0.031849507,0.6997345,0.00462793,0.0004096927,0.2501097],"study_design_scores_gemma":[0.0016199618,0.00009512209,0.0010269993,0.0010877872,0.00004277527,0.000043594508,0.00001734871,0.9784553,0.00033753176,0.0004193222,0.016681455,0.00017276983],"about_ca_topic_score_codex":0.000030454052,"about_ca_topic_score_gemma":5.53413e-8,"teacher_disagreement_score":0.9466058,"about_ca_system_score_codex":0.00010223343,"about_ca_system_score_gemma":0.0000692382,"threshold_uncertainty_score":0.72957647},"labels":[],"label_agreement":null},{"id":"W4396587423","doi":"10.1158/1538-7445.sabcs23-po3-19-03","title":"Abstract PO3-19-03: Addressing USPSTF 2023 Identified Key Gaps in Knowledge in Breast Cancer Screening through TMIST (ECOG-ACRIN EA1151) or its Ancillary Studies","year":2024,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; Sunnybrook Health Science Centre","funders":"","keywords":"Medicine; Breast cancer; Cancer; Internal medicine; Oncology; Environmental health","score_opus":0.2402534428005667,"score_gpt":0.5307182232119402,"score_spread":0.29046478041137347,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396587423","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.79383504,0.1785926,0.000047301393,0.019179484,0.0013157213,0.0008049152,0.00009460982,0.00013819637,0.0059921327],"genre_scores_gemma":[0.95943487,0.029927572,0.00021864935,0.00043628094,0.0015197342,0.00040891912,0.000022613014,0.00011730547,0.007914058],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9959123,0.00028523596,0.0006826906,0.0009138993,0.0010042104,0.0012016486],"domain_scores_gemma":[0.99802434,0.00081351906,0.00006694286,0.00037370864,0.00038820345,0.00033326406],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0031361035,0.00031733088,0.00069545256,0.0007521882,0.00027067703,0.0002524148,0.0003565451,0.00017432247,0.0018071643],"category_scores_gemma":[0.001150003,0.000254813,0.00011554085,0.002094404,0.00044960016,0.00040686116,0.00035292003,0.0027901153,0.00014624183],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0038729964,0.00084920693,0.077024676,0.025099544,0.0014608144,0.024608592,0.03353271,0.0028153027,0.10253561,0.00057745783,0.35340208,0.374221],"study_design_scores_gemma":[0.013379075,0.00036965188,0.46892676,0.110891536,0.00027718232,0.0010434629,0.021545123,0.045929506,0.0063565285,0.000822884,0.32812822,0.0023300692],"about_ca_topic_score_codex":0.006162117,"about_ca_topic_score_gemma":0.0040365783,"teacher_disagreement_score":0.3919021,"about_ca_system_score_codex":0.0013551785,"about_ca_system_score_gemma":0.0017735871,"threshold_uncertainty_score":0.9999904},"labels":[],"label_agreement":null},{"id":"W4396597578","doi":"10.3389/fonc.2024.1359148","title":"Apriori prediction of chemotherapy response in locally advanced breast cancer patients using CT imaging and deep learning: transformer versus transfer learning","year":2024,"lang":"en","type":"article","venue":"Frontiers in Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University; Health Sciences Centre; University of Toronto; Sunnybrook Health Science Centre","funders":"Natural Sciences and Engineering Research Council of Canada; Terry Fox Research Institute","keywords":"Breast cancer; Transfer of learning; Deep learning; Artificial intelligence; Medicine; Computer science; Machine learning; Pattern recognition (psychology); Cancer; Internal medicine","score_opus":0.006958700580095246,"score_gpt":0.29602640652476614,"score_spread":0.2890677059446709,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396597578","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9749806,0.0029572288,0.018522654,0.001594804,0.0013732268,0.00032780715,0.000007145782,0.000048246533,0.00018827873],"genre_scores_gemma":[0.99513304,0.0019148864,0.0025861824,0.00013440418,0.00007907222,0.000019795789,0.000012942573,0.00004783732,0.00007182118],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99840695,0.0002570328,0.00042919975,0.0003648473,0.00020041033,0.00034158412],"domain_scores_gemma":[0.9995493,0.00018117194,0.000044551743,0.00007343957,0.000048261456,0.00010323073],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006813691,0.00017625804,0.00047583733,0.0004968097,0.000051106705,0.000013376771,0.00006345669,0.00009800752,0.000037738224],"category_scores_gemma":[0.0001566628,0.00016979537,0.00006895777,0.0003795415,0.00020636662,0.00015072711,0.000009978646,0.00104374,4.1222586e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.009268204,0.00011758139,0.44008744,0.00015464405,0.000067584944,0.00011124587,0.0028681792,0.006739686,0.0063300226,0.0000052909954,0.000047163776,0.53420293],"study_design_scores_gemma":[0.017217057,0.0012723565,0.2844318,0.0009471523,0.00013674994,0.00010315926,0.0018050148,0.67268103,0.00023532638,0.000033387016,0.020902894,0.00023406663],"about_ca_topic_score_codex":0.00016750014,"about_ca_topic_score_gemma":0.0000185403,"teacher_disagreement_score":0.66594136,"about_ca_system_score_codex":0.0006340507,"about_ca_system_score_gemma":0.00025403948,"threshold_uncertainty_score":0.6924054},"labels":[],"label_agreement":null},{"id":"W4396623700","doi":"10.1097/01.ju.0001015816.87470.c9.05","title":"P2-05 THE NEXT GENERATION TRIAL – ASSESSING <sup>18</sup> F-PSMA-1007 POSITRON EMISSION TOMOGRAPHY AND MAGNETIC RESONANCE IMAGING IN THE PRIMARY STAGING OF PROSTATE CANCER PATIENTS","year":2024,"lang":"en","type":"article","venue":"The Journal of Urology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Prostate cancer; Positron emission tomography; Magnetic resonance imaging; Medicine; Nuclear medicine; Brain positron emission tomography; Radiology; Cancer; Preclinical imaging; Internal medicine","score_opus":0.015188820273075485,"score_gpt":0.2971873342622999,"score_spread":0.2819985139892244,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396623700","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94999975,0.03193411,0.00019406795,0.017067488,0.00035256805,0.00032491644,0.0000014251084,0.000006078358,0.000119587676],"genre_scores_gemma":[0.99545807,0.001636189,0.00017775525,0.002173266,0.0004981865,0.0000051997686,0.000003047649,0.000017042948,0.00003123837],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99825317,0.0005793548,0.00048630754,0.00012407138,0.0003484287,0.00020870019],"domain_scores_gemma":[0.99903613,0.00046486728,0.00022415112,0.00014286893,0.00008543439,0.000046564594],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024121539,0.000116247844,0.00024372041,0.00017492607,0.00013216914,0.00007448922,0.00017811985,0.000040210245,0.000015747513],"category_scores_gemma":[0.00020205141,0.0000537907,0.00007046548,0.00024250428,0.00022074024,0.00016741024,0.000051402003,0.0008450197,1.7303093e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.007209485,0.0002639268,0.16616613,0.00020727831,0.00007579797,0.00018387225,0.0158448,0.0017651594,0.048019573,0.000067855086,0.005920236,0.7542759],"study_design_scores_gemma":[0.033877403,0.004025633,0.44946164,0.0015946324,0.0015182919,0.0016426162,0.0019525804,0.4743979,0.0005724046,0.0011903703,0.029382586,0.00038393066],"about_ca_topic_score_codex":0.00006221544,"about_ca_topic_score_gemma":0.0000014515231,"teacher_disagreement_score":0.75389194,"about_ca_system_score_codex":0.00004035334,"about_ca_system_score_gemma":0.00014329686,"threshold_uncertainty_score":0.3671237},"labels":[],"label_agreement":null},{"id":"W4396665374","doi":"10.32920/25758126.v1","title":"Predicting Head &amp; Neck Cancer Treatment Outcomes with Quantitative Ultrasound Texture Features &amp; Optimizing Machine Learning Classifiers with Novel Texture-of-Texture Features","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University; University of Manitoba; Thunder Bay Regional Research Institute; University of Toronto; Toronto Metropolitan University; Health Sciences Centre; Sunnybrook Health Science Centre","funders":"Natural Sciences and Engineering Research Council of Canada; Terry Fox Research Institute; University of Toronto; Canadian Institutes of Health Research; Terry Fox Foundation","keywords":"Medicine; Radiomics; Head and neck cancer; Cancer; Head and neck; Artificial intelligence; Texture (cosmology); Lymph node; Nuclear medicine; Internal medicine; Radiology; Computer science; Surgery; Image (mathematics)","score_opus":0.03021776226692748,"score_gpt":0.34186555324474505,"score_spread":0.3116477909778176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396665374","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81188476,0.05705411,0.06001209,0.033266477,0.0031586234,0.006894093,0.0013779532,0.0024918837,0.023860028],"genre_scores_gemma":[0.7552437,0.0026126634,0.1766842,0.0016316521,0.0010157956,0.0004509314,0.0023428972,0.00068674784,0.05933141],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99404263,0.00020614915,0.0009980361,0.002085131,0.0015023476,0.0011656833],"domain_scores_gemma":[0.9957458,0.0010274232,0.00095405965,0.0011426867,0.00045990563,0.0006701188],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.0005577801,0.0018180958,0.0027253856,0.0007158533,0.00046630073,0.00041933908,0.00051393267,0.0010411765,0.00027535614],"category_scores_gemma":[0.00083680934,0.0010401161,0.00070413714,0.0006726682,0.00066798314,0.00013612157,0.00045136746,0.008344829,0.000010974124],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005267588,0.0016684389,0.65416276,0.0074240505,0.0201331,0.00062122423,0.029047396,0.23542324,0.008732585,0.0024931796,0.011724929,0.023301534],"study_design_scores_gemma":[0.05541653,0.014765842,0.42523873,0.09209804,0.03978775,0.014389942,0.020435378,0.12575458,0.002055083,0.0016559964,0.19332144,0.015080696],"about_ca_topic_score_codex":0.010224801,"about_ca_topic_score_gemma":0.00958874,"teacher_disagreement_score":0.22892402,"about_ca_system_score_codex":0.0007912036,"about_ca_system_score_gemma":0.0011840834,"threshold_uncertainty_score":0.9994564},"labels":[],"label_agreement":null},{"id":"W4396665421","doi":"10.32920/25758126","title":"Predicting Head &amp; Neck Cancer Treatment Outcomes with Quantitative Ultrasound Texture Features &amp; Optimizing Machine Learning Classifiers with Novel Texture-of-Texture Features","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University; University of Manitoba; Thunder Bay Regional Research Institute; University of Toronto; Toronto Metropolitan University; Health Sciences Centre; Sunnybrook Health Science Centre","funders":"","keywords":"Medicine; Radiomics; Head and neck cancer; Cancer; Artificial intelligence; Texture (cosmology); Head and neck; Lymph node; Nuclear medicine; Internal medicine; Radiology; Computer science; Surgery; Image (mathematics)","score_opus":0.03021776226692748,"score_gpt":0.34186555324474505,"score_spread":0.3116477909778176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396665421","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81188476,0.05705411,0.06001209,0.033266477,0.0031586234,0.006894093,0.0013779532,0.0024918837,0.023860028],"genre_scores_gemma":[0.7552437,0.0026126634,0.1766842,0.0016316521,0.0010157956,0.0004509314,0.0023428972,0.00068674784,0.05933141],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99404263,0.00020614915,0.0009980361,0.002085131,0.0015023476,0.0011656833],"domain_scores_gemma":[0.9957458,0.0010274232,0.00095405965,0.0011426867,0.00045990563,0.0006701188],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.0005577801,0.0018180958,0.0027253856,0.0007158533,0.00046630073,0.00041933908,0.00051393267,0.0010411765,0.00027535614],"category_scores_gemma":[0.00083680934,0.0010401161,0.00070413714,0.0006726682,0.00066798314,0.00013612157,0.00045136746,0.008344829,0.000010974124],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005267588,0.0016684389,0.65416276,0.0074240505,0.0201331,0.00062122423,0.029047396,0.23542324,0.008732585,0.0024931796,0.011724929,0.023301534],"study_design_scores_gemma":[0.05541653,0.014765842,0.42523873,0.09209804,0.03978775,0.014389942,0.020435378,0.12575458,0.002055083,0.0016559964,0.19332144,0.015080696],"about_ca_topic_score_codex":0.010224801,"about_ca_topic_score_gemma":0.00958874,"teacher_disagreement_score":0.22892402,"about_ca_system_score_codex":0.0007912036,"about_ca_system_score_gemma":0.0011840834,"threshold_uncertainty_score":0.9994564},"labels":[],"label_agreement":null},{"id":"W4396665435","doi":"10.32920/25758135","title":"Enhancing CT Radiomics Features for Prediction of Head and Neck Cancer Treatment Outcomes: A Machine Learning Approach","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Health Sciences Centre; Toronto Metropolitan University; Sunnybrook Health Science Centre","funders":"","keywords":"Radiomics; Receiver operating characteristic; Artificial intelligence; Support vector machine; Head and neck cancer; Medicine; Head and neck; Lymph node; Classifier (UML); Computer science; Machine learning; Pattern recognition (psychology); Cancer; Nuclear medicine; Internal medicine; Surgery","score_opus":0.02180670522659431,"score_gpt":0.3239558583759631,"score_spread":0.30214915314936874,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396665435","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94711447,0.021104585,0.018837525,0.0045894524,0.0014933785,0.0027851886,0.00042630555,0.00041363313,0.0032354365],"genre_scores_gemma":[0.9095578,0.006399694,0.064120844,0.00046526437,0.00093498355,0.0007394901,0.0012712644,0.00021599,0.016294658],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980306,0.000052051935,0.0005716661,0.0007318375,0.00028449218,0.0003293391],"domain_scores_gemma":[0.9990124,0.00016471795,0.00022130323,0.0003161913,0.000077973586,0.0002073792],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004140525,0.00045382098,0.0011325956,0.00029271015,0.000096323056,0.00006509568,0.00009658071,0.00019979222,0.00002560506],"category_scores_gemma":[0.00026120202,0.0003152162,0.00036951297,0.000102926635,0.00009842032,0.000024947913,0.00024408357,0.0012842815,7.5400243e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014914296,0.0018632162,0.5320147,0.04083908,0.011632373,0.00016762421,0.010216066,0.0335428,0.014717513,0.0028796347,0.0046467017,0.34598884],"study_design_scores_gemma":[0.009005736,0.0016389705,0.03728677,0.004442623,0.0042897374,0.00048799816,0.00043421704,0.92042196,0.003315193,0.0013836061,0.016518451,0.0007747669],"about_ca_topic_score_codex":0.0025179158,"about_ca_topic_score_gemma":0.00007597066,"teacher_disagreement_score":0.88687915,"about_ca_system_score_codex":0.00033271397,"about_ca_system_score_gemma":0.0003020347,"threshold_uncertainty_score":0.99992996},"labels":[],"label_agreement":null},{"id":"W4396665436","doi":"10.32920/25758135.v1","title":"Enhancing CT Radiomics Features for Prediction of Head and Neck Cancer Treatment Outcomes: A Machine Learning Approach","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Health Sciences Centre; Toronto Metropolitan University; Sunnybrook Health Science Centre","funders":"Natural Sciences and Engineering Research Council of Canada; Terry Fox Research Institute; University of Toronto; Canadian Institutes of Health Research; Terry Fox Foundation","keywords":"Radiomics; Receiver operating characteristic; Artificial intelligence; Support vector machine; Medicine; Head and neck cancer; Head and neck; Classifier (UML); Computer science; Machine learning; Pattern recognition (psychology); Nuclear medicine; Radiology; Radiation therapy; Surgery","score_opus":0.02180670522659431,"score_gpt":0.3239558583759631,"score_spread":0.30214915314936874,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396665436","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94711447,0.021104585,0.018837525,0.0045894524,0.0014933785,0.0027851886,0.00042630555,0.00041363313,0.0032354365],"genre_scores_gemma":[0.9095578,0.006399694,0.064120844,0.00046526437,0.00093498355,0.0007394901,0.0012712644,0.00021599,0.016294658],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980306,0.000052051935,0.0005716661,0.0007318375,0.00028449218,0.0003293391],"domain_scores_gemma":[0.9990124,0.00016471795,0.00022130323,0.0003161913,0.000077973586,0.0002073792],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004140525,0.00045382098,0.0011325956,0.00029271015,0.000096323056,0.00006509568,0.00009658071,0.00019979222,0.00002560506],"category_scores_gemma":[0.00026120202,0.0003152162,0.00036951297,0.000102926635,0.00009842032,0.000024947913,0.00024408357,0.0012842815,7.5400243e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014914296,0.0018632162,0.5320147,0.04083908,0.011632373,0.00016762421,0.010216066,0.0335428,0.014717513,0.0028796347,0.0046467017,0.34598884],"study_design_scores_gemma":[0.009005736,0.0016389705,0.03728677,0.004442623,0.0042897374,0.00048799816,0.00043421704,0.92042196,0.003315193,0.0013836061,0.016518451,0.0007747669],"about_ca_topic_score_codex":0.0025179158,"about_ca_topic_score_gemma":0.00007597066,"teacher_disagreement_score":0.88687915,"about_ca_system_score_codex":0.00033271397,"about_ca_system_score_gemma":0.0003020347,"threshold_uncertainty_score":0.99992996},"labels":[],"label_agreement":null},{"id":"W4396768109","doi":"10.1016/j.htct.2024.04.067","title":"PROGNOSTIC EVALUATION OF THE NUTRITIONAL PROGNOSTIC INDEX IN PATIENTS WITH NON-METASTATIC RECTAL CANCER","year":2024,"lang":"en","type":"article","venue":"Hematology Transfusion and Cell Therapy","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Medicine; Colorectal cancer; Oncology; Internal medicine; Cancer; Index (typography); Computer science","score_opus":0.011291425136674459,"score_gpt":0.28615576815424787,"score_spread":0.2748643430175734,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396768109","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9944855,0.002675362,0.00033484056,0.0012510765,0.00012631305,0.00093313353,0.0000031114134,0.000012775095,0.00017786483],"genre_scores_gemma":[0.99890226,0.0006294375,0.00011642095,0.00018992434,0.000013674771,0.000102625934,0.000011504218,0.000013663038,0.000020469517],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9990891,0.00010351333,0.00018052208,0.00018007873,0.00032954273,0.000117200456],"domain_scores_gemma":[0.99965745,0.00011713913,0.000030510975,0.0000750124,0.00007978722,0.000040127823],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003031007,0.00009253067,0.00019627565,0.000092460126,0.00003877991,0.000007667864,0.00003700303,0.0000450891,0.00015888616],"category_scores_gemma":[0.000029379407,0.00005222312,0.000036512924,0.00021790515,0.00011884271,0.000027975533,0.0000049097202,0.0002538032,7.1586965e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000271824,0.0004119611,0.96087015,0.00033279098,0.00004235257,0.00000839156,0.000594293,0.000034738696,0.0008220035,0.00007317437,0.000043860076,0.03649446],"study_design_scores_gemma":[0.0068658325,0.00031634246,0.95746964,0.0011397612,0.00015054157,0.000047905032,0.00007507753,0.032557633,0.0007908163,0.00036734596,0.00013372315,0.000085402105],"about_ca_topic_score_codex":0.000036614867,"about_ca_topic_score_gemma":0.000019656598,"teacher_disagreement_score":0.036409058,"about_ca_system_score_codex":0.000018898507,"about_ca_system_score_gemma":0.00016218753,"threshold_uncertainty_score":0.2129597},"labels":[],"label_agreement":null},{"id":"W4396778312","doi":"10.3390/cancers16142538","title":"Segmentation-Free Outcome Prediction from Head and Neck Cancer PET/CT Images: Deep Learning-Based Feature Extraction from Multi-Angle Maximum Intensity Projections (MA-MIPs)","year":2024,"lang":"en","type":"preprint","venue":"Cancers","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Artificial intelligence; Deep learning; Computer science; Segmentation; Convolutional neural network; Feature (linguistics); Feature extraction; Projection (relational algebra); Pattern recognition (psychology); Positron emission tomography; Head and neck; Nuclear medicine; Medicine","score_opus":0.022909375498782313,"score_gpt":0.33508934943504015,"score_spread":0.31217997393625785,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396778312","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9399827,0.009948016,0.028227348,0.009101768,0.008709195,0.0016088849,0.0013472262,0.00079583685,0.0002790058],"genre_scores_gemma":[0.94910336,0.0027722395,0.032130383,0.0023883258,0.0030234633,0.0008261954,0.005826082,0.00027470806,0.0036552758],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99736696,0.000115694806,0.0005021388,0.0011429394,0.000497938,0.0003742967],"domain_scores_gemma":[0.99840075,0.00014683996,0.00032819086,0.0005828157,0.00022879812,0.00031261408],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.00024342655,0.000505936,0.00073358417,0.00027980114,0.00027447642,0.00020092813,0.00019015007,0.0001531505,0.0002717581],"category_scores_gemma":[0.0005696715,0.00047665965,0.00026117696,0.00022115195,0.00021142149,0.000111536,0.00029300846,0.004189708,0.000017841827],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013975349,0.00027727685,0.6735323,0.00268026,0.0028927661,0.0021047608,0.0032633964,0.18683687,0.012494738,0.000005196438,0.04330143,0.07121347],"study_design_scores_gemma":[0.005521612,0.00020705425,0.13721748,0.0032360184,0.0024741862,0.00017481654,0.0015976973,0.82950246,0.0010026966,0.0006104948,0.01765501,0.0008004448],"about_ca_topic_score_codex":0.041987825,"about_ca_topic_score_gemma":0.0019330777,"teacher_disagreement_score":0.6426656,"about_ca_system_score_codex":0.0030198144,"about_ca_system_score_gemma":0.00092568714,"threshold_uncertainty_score":0.9997685},"labels":[],"label_agreement":null},{"id":"W4396779536","doi":"10.1016/j.jconrel.2024.05.004","title":"Image-based predictive modelling frameworks for personalised drug delivery in cancer therapy","year":2024,"lang":"en","type":"article","venue":"Journal of Controlled Release","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"Science and Engineering Research Board","keywords":"Drug delivery; Computer science; Modalities; Risk analysis (engineering); Medical physics; Medicine; Nanotechnology","score_opus":0.01155936443263939,"score_gpt":0.3067027712411702,"score_spread":0.2951434068085308,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396779536","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5975838,0.040177546,0.3358587,0.024356656,0.0008862715,0.00090666144,0.000012250725,0.000037864356,0.00018025853],"genre_scores_gemma":[0.9831066,0.002570739,0.010321956,0.002524091,0.0011386146,0.0000598252,0.000003777964,0.000047434467,0.00022695308],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99843717,0.000102511556,0.0006056205,0.00018050529,0.00039595045,0.00027825605],"domain_scores_gemma":[0.99814135,0.00094870635,0.0002130046,0.00010033179,0.00035289372,0.00024374333],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011497629,0.00017113451,0.0007140436,0.00037780407,0.000051832016,0.00007439699,0.00010508808,0.00014191386,0.00009265217],"category_scores_gemma":[0.00044867347,0.00011533466,0.00054493826,0.00018183181,0.00006780757,0.00013904314,0.000005867315,0.001592334,0.0000012586388],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.15420046,0.0017988628,0.0037247154,0.0013336207,0.003850089,0.004291382,0.005069199,0.5717121,0.020541433,0.00035036582,0.032075543,0.20105226],"study_design_scores_gemma":[0.029583031,0.00035347874,0.00009078718,0.0016158202,0.00029079284,0.00003807293,0.00012247256,0.96314615,0.00011924992,0.0005343516,0.0040008747,0.00010490375],"about_ca_topic_score_codex":0.000058908925,"about_ca_topic_score_gemma":0.0000016270428,"teacher_disagreement_score":0.3914341,"about_ca_system_score_codex":0.00019470709,"about_ca_system_score_gemma":0.0008784983,"threshold_uncertainty_score":0.69179875},"labels":[],"label_agreement":null},{"id":"W4396842991","doi":"","title":"Evidence-based treatment planning in mCRC- The key to maximising outcomes","year":2013,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency","funders":"","keywords":"Key (lock); Process management; Computer science; Business; Computer security","score_opus":0.33867417653328546,"score_gpt":0.5741126788181888,"score_spread":0.23543850228490337,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396842991","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96933997,0.010526729,0.0009314778,0.015808232,0.00036438124,0.001050852,0.0000023366167,0.000034339377,0.0019417038],"genre_scores_gemma":[0.9909751,0.0015949858,0.0013231875,0.005237199,0.00016585797,0.000103111306,0.000003988878,0.000049723512,0.00054687023],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99741304,0.00026366298,0.00077866775,0.0003863151,0.00069436344,0.00046394896],"domain_scores_gemma":[0.99742293,0.0011091834,0.0003780717,0.00051836326,0.00015995413,0.00041148785],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0014677347,0.00030660123,0.0008514699,0.00071686035,0.00021121427,0.0008936015,0.0011952692,0.00007416527,0.0040810113],"category_scores_gemma":[0.001785925,0.0001865979,0.0002010016,0.00071742095,0.0001099977,0.0009509433,0.00029991433,0.0005663369,0.00004023588],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012328864,0.00017954786,0.90615714,0.000047393165,0.0001098549,0.00010550472,0.000542902,0.0025968067,0.015284825,0.000009878343,0.0093785515,0.0654643],"study_design_scores_gemma":[0.0011000943,0.000040769934,0.9831407,0.0027006438,0.00009358484,0.00002263467,0.00014599883,0.0033075898,0.0024223314,0.0004337936,0.0063648177,0.00022703821],"about_ca_topic_score_codex":0.0041742413,"about_ca_topic_score_gemma":0.000028120428,"teacher_disagreement_score":0.076983556,"about_ca_system_score_codex":0.00027749196,"about_ca_system_score_gemma":0.00021720328,"threshold_uncertainty_score":0.9968294},"labels":[],"label_agreement":null},{"id":"W4396890326","doi":"10.1038/s41597-024-03295-z","title":"ReMIND: The Brain Resection Multimodal Imaging Database","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"National Institutes of Health; Brigham and Women's Hospital; National Institute of Biomedical Imaging and Bioengineering; U.S. Department of Health and Human Services","keywords":"Neuronavigation; Magnetic resonance imaging; Interventional magnetic resonance imaging; Medicine; Intraoperative MRI; Workflow; Database; Radiology; Brain tumor; Computer science; Pathology","score_opus":0.03263658663287678,"score_gpt":0.35931578249153895,"score_spread":0.3266791958586622,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396890326","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18159033,0.018693164,0.11250758,0.5893998,0.05235756,0.0025731537,0.0055191484,0.00200914,0.035350118],"genre_scores_gemma":[0.927093,0.00005723917,0.009525623,0.0035532995,0.0022978678,0.000018181136,0.015565097,0.00008344003,0.041806232],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982493,0.00006500511,0.00018627883,0.00074735505,0.00048458626,0.00026748076],"domain_scores_gemma":[0.997581,0.0002297834,0.000026527287,0.0019972578,0.000039644703,0.00012578175],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0040005473,0.00009594407,0.00010204784,0.00015880517,0.00036756392,0.0006483699,0.00065835315,0.000021361826,0.00026904984],"category_scores_gemma":[0.0019243796,0.000059807146,0.00003834254,0.00053041603,0.0004008165,0.00040352653,0.0005990312,0.0005618252,0.000259868],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014263493,0.000023084318,0.00036063086,0.000080189224,0.000019682486,0.00013872547,0.00020763134,0.000004535399,0.023811724,0.0003046001,0.83917564,0.1358593],"study_design_scores_gemma":[0.00016014611,0.000006362093,0.00041781575,0.00019622655,0.00003692649,0.0001827434,0.0001054131,0.40033993,0.00028211193,0.000111705274,0.59810567,0.000054934804],"about_ca_topic_score_codex":0.0001343323,"about_ca_topic_score_gemma":0.000019401015,"teacher_disagreement_score":0.7455027,"about_ca_system_score_codex":0.000039646107,"about_ca_system_score_gemma":0.0001800691,"threshold_uncertainty_score":0.6252246},"labels":[],"label_agreement":null},{"id":"W4396931828","doi":"10.3390/cancers16101873","title":"The [18F]F-FDG PET/CT Radiomics Classifier of Histologic Subtypes and Anatomical Disease Origins across Various Malignancies: A Proof-of-Principle Study","year":2024,"lang":"en","type":"article","venue":"Cancers","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario; Princess Margaret Cancer Centre; Sinai Health System; Women's College Hospital; Toronto General Hospital; University of Toronto; University Health Network","funders":"","keywords":"Histology; Medicine; Radiomics; Adenocarcinoma; Recursive partitioning; Radiology; Nuclear medicine; Pathology; Cancer; Internal medicine","score_opus":0.016429672701352458,"score_gpt":0.3310591902557479,"score_spread":0.31462951755439544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396931828","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98876464,0.008656362,0.00026603622,0.0009776856,0.00058637775,0.00047723038,0.000022684952,0.000045639343,0.0002033606],"genre_scores_gemma":[0.9985694,0.0004048462,0.00017952648,0.00013574399,0.00009028938,0.00003746371,0.000005203839,0.00002608888,0.0005513947],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99872977,0.000060020953,0.00033003165,0.00032726384,0.00026312695,0.0002897667],"domain_scores_gemma":[0.9990858,0.00023265585,0.00009213507,0.00031777064,0.000057837053,0.0002138146],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005060939,0.00015224767,0.0003538455,0.000057879915,0.0001281587,0.00003872291,0.00016004534,0.000012875736,0.000016989878],"category_scores_gemma":[0.00042084823,0.000098162964,0.00009756657,0.0002352072,0.00061802455,0.00004573782,0.000074854215,0.0003658159,0.000001321184],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0031064271,0.00076865545,0.80060846,0.0047866357,0.0022970045,0.014603088,0.01137111,0.0030954706,0.0039719897,0.031229237,0.010540126,0.11362177],"study_design_scores_gemma":[0.0065272935,0.0018129215,0.0980206,0.0015548964,0.0015938731,0.0018002897,0.0065452834,0.42561352,0.0014017114,0.0019424806,0.4522635,0.0009236303],"about_ca_topic_score_codex":0.0003213233,"about_ca_topic_score_gemma":0.00003566169,"teacher_disagreement_score":0.7025879,"about_ca_system_score_codex":0.0006506049,"about_ca_system_score_gemma":0.0009957856,"threshold_uncertainty_score":0.40029696},"labels":[],"label_agreement":null},{"id":"W4396960342","doi":"10.1016/j.hpb.2024.03.600","title":"Is it resectable? a survey regarding tumour classification and vascular involvement","year":2024,"lang":"en","type":"article","venue":"HPB","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto General Hospital","funders":"","keywords":"Medicine; General surgery; Oncology","score_opus":0.056132675063210166,"score_gpt":0.33733466047351734,"score_spread":0.28120198541030716,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396960342","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96174896,0.0046434035,0.015392991,0.012186526,0.00047613267,0.00032269096,0.000006599315,0.00015300997,0.0050696633],"genre_scores_gemma":[0.9919042,0.0007708606,0.0021187174,0.0018709849,0.0002361917,0.000013888921,0.0000468238,0.000027991167,0.0030103454],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9990998,0.000069253976,0.00015799027,0.00026785288,0.00024285022,0.00016226433],"domain_scores_gemma":[0.99954,0.00010448834,0.000020756128,0.0001711299,0.000044719636,0.00011892156],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012171444,0.00008432404,0.00015091004,0.00010206024,0.00006429583,0.00008559788,0.00004433913,0.00004428586,0.00014024353],"category_scores_gemma":[0.0003801706,0.000068145615,0.000048338505,0.00018207784,0.00004396535,0.000059115286,0.000035544886,0.000297237,0.000043032025],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000090500886,0.0001384067,0.40586475,0.0018396005,0.00059004204,0.0002238055,0.0044079614,0.000015923213,0.06252951,0.0018868559,0.39816156,0.124251075],"study_design_scores_gemma":[0.00075925526,0.00008709001,0.42021817,0.0007470732,0.00012125816,0.00004553632,0.00031522982,0.37418333,0.00022100458,0.00009068899,0.20305161,0.0001597749],"about_ca_topic_score_codex":0.00026395515,"about_ca_topic_score_gemma":0.000013674509,"teacher_disagreement_score":0.37416738,"about_ca_system_score_codex":0.000054950036,"about_ca_system_score_gemma":0.000060679282,"threshold_uncertainty_score":0.27788976},"labels":[],"label_agreement":null},{"id":"W4396979276","doi":"10.1016/j.hpb.2024.05.006","title":"Impact of an artificial intelligence based model to predict non-transplantable recurrence among patients with hepatocellular carcinoma","year":2024,"lang":"en","type":"article","venue":"HPB","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":19,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Hepatocellular carcinoma; Medicine; Resection; Internal medicine; Oncology; Gastroenterology; Surgery","score_opus":0.017057067321706434,"score_gpt":0.28611804371412575,"score_spread":0.2690609763924193,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396979276","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7380897,0.000028443588,0.26130652,0.000028805756,0.000075419324,0.00027952273,0.000037411795,0.000039579132,0.00011464937],"genre_scores_gemma":[0.99106854,0.0000032903056,0.0086240005,0.000059395017,0.00006407344,0.000013859289,0.00010468359,0.000029948102,0.00003219459],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998808,0.000023430559,0.0002482282,0.0003139522,0.00034715433,0.0002591922],"domain_scores_gemma":[0.99927664,0.000039267146,0.000035997844,0.0002596001,0.00008673013,0.00030176484],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021754319,0.00015232374,0.00024398896,0.00015809441,0.00003925501,0.000032123113,0.00011957346,0.00005234951,0.00006183423],"category_scores_gemma":[0.00005008975,0.00010839361,0.000080809965,0.0002924414,0.0000852974,0.00011160705,0.000014194939,0.00030542773,0.0000093317],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039413263,0.00026508354,0.9341795,0.0002904056,0.00004615743,0.00010855842,0.00067944126,0.034792148,0.0019040774,0.000023861425,0.0001494912,0.027167162],"study_design_scores_gemma":[0.00017024919,0.0008537226,0.11856625,0.0005476676,0.00007579733,0.0000047083868,0.000009021503,0.87855846,0.0010728588,0.000025247735,0.000008910474,0.00010712387],"about_ca_topic_score_codex":0.00042609195,"about_ca_topic_score_gemma":0.0000093896,"teacher_disagreement_score":0.8437663,"about_ca_system_score_codex":0.00006122795,"about_ca_system_score_gemma":0.0002572586,"threshold_uncertainty_score":0.4420163},"labels":[],"label_agreement":null},{"id":"W4396993831","doi":"10.1681/asn.20213210s1595a","title":"Pathology Core Scoring Parameters and Reproducibility in the CureGN Study","year":2021,"lang":"en","type":"article","venue":"Journal of the American Society of Nephrology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Université de Montréal","funders":"","keywords":"Reproducibility; Core (optical fiber); Medicine; Pathology; Medical physics; Computer science; Statistics; Mathematics","score_opus":0.03320852098337266,"score_gpt":0.33703040443381854,"score_spread":0.30382188345044586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396993831","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96275914,0.00042549634,0.0000840208,0.036454495,0.00012753712,0.0001265562,3.6722528e-7,0.0000022972279,0.000020119222],"genre_scores_gemma":[0.98074704,0.0002838754,0.0039273393,0.01489691,0.0001182168,0.0000014368647,1.938042e-7,0.000006773535,0.000018186838],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9984821,0.0004772648,0.00041088773,0.0002537721,0.00022044312,0.00015550226],"domain_scores_gemma":[0.9982637,0.00039768234,0.0005573718,0.0006317678,0.00010570644,0.000043771077],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032056328,0.00007984869,0.00049658486,0.000025639485,0.00005403242,0.0000060691823,0.00020159075,0.00002931993,0.000003824038],"category_scores_gemma":[0.0012337578,0.000043522967,0.00021223578,0.00030253732,0.0008869523,0.000024510726,0.00010718692,0.00082302676,1.2212699e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019025552,0.0005172846,0.9358283,0.00003571218,0.00022674774,0.00024325399,0.009668593,0.00010710116,0.033260297,0.000016983158,0.004187479,0.015717987],"study_design_scores_gemma":[0.0010068454,0.0008517065,0.9800074,0.00003349246,0.00014244167,0.0029411651,0.012633673,0.0004319279,0.000092243085,0.00037729516,0.0014413599,0.00004045122],"about_ca_topic_score_codex":0.0000811783,"about_ca_topic_score_gemma":0.000006627848,"teacher_disagreement_score":0.044179097,"about_ca_system_score_codex":0.000028574794,"about_ca_system_score_gemma":0.000113579255,"threshold_uncertainty_score":0.35756874},"labels":[],"label_agreement":null},{"id":"W4398138487","doi":"10.3892/mi.2024.164","title":"Uses of artificial intelligence in glioma: A systematic review","year":2024,"lang":"en","type":"review","venue":"Medicine International","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Montreal Neurological Institute and Hospital","funders":"","keywords":"Glioma; Grading (engineering); Scopus; Glioblastoma; Medicine; Oncology; Computer science; MEDLINE; Cancer research; Biology","score_opus":0.060597467288102995,"score_gpt":0.4365255769587914,"score_spread":0.3759281096706884,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398138487","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000012066757,0.9921622,0.00066005165,0.0028969378,0.0013524974,0.0012751485,0.000010912981,0.00003868031,0.0016023478],"genre_scores_gemma":[0.000033193846,0.99778235,0.00026615523,0.00041886469,0.00067957246,0.00015227048,0.00014453454,0.000050499562,0.00047254175],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.99621016,0.00015876655,0.0022240398,0.0003922629,0.0008246949,0.00019007163],"domain_scores_gemma":[0.99843305,0.00041325853,0.00054525986,0.0003537044,0.00014313257,0.00011158614],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001489888,0.00034571954,0.0034003875,0.000986505,0.000010941331,0.0000117924665,0.00042365553,0.00013719576,0.00046553198],"category_scores_gemma":[0.0049769343,0.00020717738,0.00043399096,0.0007433046,0.00020441931,0.000034828034,0.00010390434,0.0009215312,0.00013112603],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000035241221,0.000059889768,0.0000013153794,0.83665,0.00030378217,0.0004415123,0.000056393907,2.1719516e-7,8.638794e-7,0.0020434293,0.001961936,0.15847713],"study_design_scores_gemma":[0.00006235361,0.000068593814,3.4368168e-7,0.87935954,0.0043114,0.0010620835,0.000025504043,0.00072012417,3.7941666e-7,0.0003077232,0.11395613,0.00012580804],"about_ca_topic_score_codex":0.000054386666,"about_ca_topic_score_gemma":0.0000029386763,"teacher_disagreement_score":0.15835133,"about_ca_system_score_codex":0.00020078369,"about_ca_system_score_gemma":0.00026010172,"threshold_uncertainty_score":0.8448448},"labels":[],"label_agreement":null},{"id":"W4398153731","doi":"10.2196/51347","title":"Research Trends and Evolution in Radiogenomics (2005-2023): Bibliometric Analysis","year":2024,"lang":"en","type":"article","venue":"Interactive Journal of Medical Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Radiogenomics; Bibliometrics; Data science; Computational biology; Biology; Computer science; Library science; Radiomics; Artificial intelligence","score_opus":0.05894001489551383,"score_gpt":0.5003711779207107,"score_spread":0.4414311630251969,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398153731","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9106056,0.023703076,0.003718759,0.05716524,0.00048751358,0.00012511501,0.000003730316,0.000012903478,0.0041780607],"genre_scores_gemma":[0.98918533,0.008456225,0.0003451276,0.00008127555,0.00079996104,0.0000055228857,0.000004287118,0.000023274806,0.0010990145],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99143195,0.0012679797,0.0007728948,0.00035330586,0.0054399525,0.0007339141],"domain_scores_gemma":[0.99169016,0.0059969323,0.00008631068,0.0002084504,0.00096362183,0.0010545088],"candidate_categories":["metaresearch","bibliometrics","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","bibliometrics"],"category_scores_codex":[0.036232274,0.00012696929,0.0005827694,0.22164726,0.00010395524,0.00023941584,0.00041438758,0.00022551928,0.0014159516],"category_scores_gemma":[0.01614802,0.00009245549,0.00023621866,0.13873011,0.00061875326,0.0002877463,0.00024156408,0.0073470264,0.00003090952],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00098002,0.0005245144,0.0545957,0.00023877544,0.0017833103,0.008593911,0.0009273243,0.00006254336,0.0019118554,0.0011295126,0.029646756,0.89960575],"study_design_scores_gemma":[0.0025672645,0.001529972,0.6694214,0.0026470886,0.000354524,0.002777832,0.0018602777,0.21305965,0.00012728728,0.0016126976,0.10385102,0.00019104089],"about_ca_topic_score_codex":0.00062983285,"about_ca_topic_score_gemma":0.0000646746,"teacher_disagreement_score":0.8994147,"about_ca_system_score_codex":0.0011559161,"about_ca_system_score_gemma":0.0012871897,"threshold_uncertainty_score":0.9994969},"labels":[],"label_agreement":null},{"id":"W4398221719","doi":"10.3389/fradi.2024.1357341","title":"Standardized evaluation of the extent of resection in glioblastoma with automated early post-operative segmentation","year":2024,"lang":"en","type":"article","venue":"Frontiers in Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Sunnybrook Health Science Centre","funders":"Helse Sør-Øst RHF; Norges Forskningsråd; Universitetet i Oslo; European Commission","keywords":"Medicine; Glioblastoma; Resection; Segmentation; Radiology; Magnetic resonance imaging; Overall survival; Surgery; Artificial intelligence; Computer science","score_opus":0.008266627573678516,"score_gpt":0.31779303761862143,"score_spread":0.3095264100449429,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398221719","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99107444,0.0015304416,0.0052456353,0.0007750619,0.0006473608,0.00054547534,0.0000049789037,0.000028706938,0.00014789098],"genre_scores_gemma":[0.9962635,0.000061810606,0.003527306,0.00004137107,0.000027373771,0.00003100809,0.000008696812,0.000010858921,0.000028066299],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99869305,0.00043305836,0.00028551507,0.0001683144,0.00030417944,0.00011585914],"domain_scores_gemma":[0.9995886,0.000052853306,0.000075917545,0.00011784469,0.00014262294,0.000022163895],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012077905,0.00007503007,0.00026732922,0.00030218755,0.000017107044,0.0000039117836,0.00005320613,0.00006764344,0.000016588732],"category_scores_gemma":[0.00032037747,0.000047309095,0.000038186314,0.0004266765,0.00017719879,0.000056588287,0.000012423544,0.0002646989,2.885146e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.007753273,0.0002794419,0.6648588,0.00058787636,0.0006342945,0.00007725225,0.020110652,0.042244002,0.13547632,0.00036536597,0.00646137,0.121151365],"study_design_scores_gemma":[0.0043800883,0.0013789599,0.30715948,0.00069466175,0.00014949142,0.00009649806,0.0012769564,0.6762676,0.008084194,0.00035397208,0.00008052083,0.000077552635],"about_ca_topic_score_codex":0.000114555914,"about_ca_topic_score_gemma":0.00004429701,"teacher_disagreement_score":0.6340236,"about_ca_system_score_codex":0.000273602,"about_ca_system_score_gemma":0.00024784578,"threshold_uncertainty_score":0.19292088},"labels":[],"label_agreement":null},{"id":"W4398239580","doi":"10.20944/preprints202405.1505.v1","title":"Differentiating Gliosarcoma from Glioblastoma: A Novel Approach Using PEACE and XGBoost","year":2024,"lang":"en","type":"preprint","venue":"Preprints.org","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton; Université du Québec à Trois-Rivières","funders":"","keywords":"Gliosarcoma; Glioblastoma; Computer science; Medicine; Cancer research","score_opus":0.08632113721708837,"score_gpt":0.3553845283820572,"score_spread":0.2690633911649688,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398239580","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98300904,0.0020984989,0.007962225,0.00093669683,0.00088282273,0.0007140615,0.000047785827,0.00037476252,0.003974119],"genre_scores_gemma":[0.9844924,0.00013374725,0.013254597,0.0002744398,0.0009961389,0.000052061707,0.00011155774,0.00016128623,0.0005237716],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963261,0.00013172043,0.00070565863,0.0016855971,0.00061089837,0.00054006453],"domain_scores_gemma":[0.9978848,0.00018274723,0.00031393077,0.0010924394,0.00009972338,0.000426374],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.00084465195,0.0006099035,0.0009969331,0.0003366091,0.00016221942,0.0001193444,0.0003783845,0.00046280702,0.00019590503],"category_scores_gemma":[0.0008597419,0.000566599,0.000304121,0.00020248852,0.00023528481,0.000052759664,0.0046144007,0.0038412835,0.000111367925],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032670176,0.0009048534,0.70697796,0.004469419,0.0018214238,0.00036372416,0.0058786753,0.0010693268,0.2709627,0.00053848827,0.0001496453,0.006537125],"study_design_scores_gemma":[0.0025806942,0.000057013076,0.2715868,0.0046119345,0.0018635971,0.0005780027,0.00051202916,0.70636195,0.006877766,0.002418703,0.0013830417,0.0011684707],"about_ca_topic_score_codex":0.0010656347,"about_ca_topic_score_gemma":0.000005232328,"teacher_disagreement_score":0.70529264,"about_ca_system_score_codex":0.00023595965,"about_ca_system_score_gemma":0.00024335111,"threshold_uncertainty_score":0.99967855},"labels":[],"label_agreement":null},{"id":"W4398255805","doi":"10.1017/cjn.2024.199","title":"P.094 Incidence of pathologically confirmed primary malignant brain tumours in Newfoundland and Labrador: an eight-year review spanning 2015-2022","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Neurological Sciences / Journal Canadien des Sciences Neurologiques","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Incidence (geometry); Medicine; Oligodendroglioma; Population; Glioblastoma; Demography; Internal medicine; Astrocytoma; Environmental health","score_opus":0.019798436442853094,"score_gpt":0.30287599952354083,"score_spread":0.2830775630806877,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398255805","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94876796,0.025913125,0.000037822367,0.023767188,0.00045550303,0.00019720834,0.000006843597,0.000015446778,0.00083892257],"genre_scores_gemma":[0.97900367,0.007871017,0.0024755676,0.010431164,0.00017764675,0.0000021876103,8.9005397e-7,0.00001276252,0.000025072577],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99559104,0.0010216744,0.0010551473,0.0005825614,0.00081560196,0.00093395176],"domain_scores_gemma":[0.99659866,0.0008296331,0.0004828838,0.00014420022,0.00024554654,0.0016990952],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.009195791,0.0002822831,0.00079634314,0.0009882079,0.0006075617,0.00037640607,0.00096248166,0.0001502246,0.00014845967],"category_scores_gemma":[0.004322836,0.00017630903,0.00016336243,0.0013184879,0.0051374915,0.0007851313,0.000077304794,0.001845456,0.0000011060127],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000074902666,0.00003423705,0.9616824,0.00019572642,0.000010643724,0.023411961,0.0004082308,0.00023114699,0.00046072048,0.0009681663,0.0008786051,0.011643287],"study_design_scores_gemma":[0.00055478286,0.0454089,0.8527311,0.002425108,0.0001026394,0.082858816,0.00020704593,0.004644557,0.00001925515,0.00662866,0.0040469933,0.00037213202],"about_ca_topic_score_codex":0.002679311,"about_ca_topic_score_gemma":0.019898301,"teacher_disagreement_score":0.10895126,"about_ca_system_score_codex":0.00022418462,"about_ca_system_score_gemma":0.0033550507,"threshold_uncertainty_score":0.997986},"labels":[],"label_agreement":null},{"id":"W4398280695","doi":"10.7910/dvn/28075/vdi1l8","title":"events.2017.20180122111453.tab","year":2018,"lang":"en","type":"dataset","venue":"Harvard Dataverse","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lockheed Martin (Canada)","funders":"","keywords":"Event (particle physics); Computer science; Event data; Database; Physics; Data modeling","score_opus":0.01619207186779557,"score_gpt":0.2966626893548206,"score_spread":0.280470617487025,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398280695","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00009930128,0.000005831788,0.00010975571,0.00010920702,0.0023615486,0.00042913732,0.9958672,0.00011055302,0.00090747006],"genre_scores_gemma":[0.000016841728,0.000835869,0.0014421749,0.003138799,0.0037565888,0.000023752185,0.9885878,0.0000644069,0.0021337643],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99712515,0.00010872466,0.0005333459,0.00080304086,0.0007968757,0.00063289254],"domain_scores_gemma":[0.9966694,0.000096296666,0.00030972325,0.0022154523,0.00013946982,0.0005696629],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0006898671,0.00050385285,0.00081648084,0.00031581311,0.00018131085,0.00006204955,0.0007026306,0.000449492,0.034577146],"category_scores_gemma":[0.0013363066,0.00043781806,0.00026163243,0.0001962068,0.00029635112,0.00015927925,0.00053338584,0.0014111561,0.16017155],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011263155,0.00018710068,0.000070374575,0.00033404582,0.00022251392,0.00055534486,0.000012566126,4.4721892e-7,0.000020659147,0.000008056403,0.99779814,0.0006781245],"study_design_scores_gemma":[0.0015608978,0.00020354787,0.00023187645,0.00056449237,0.00066504907,0.00035842464,0.000013691761,0.00011813763,0.00000887827,0.000033431912,0.9958208,0.00042076418],"about_ca_topic_score_codex":0.00044402902,"about_ca_topic_score_gemma":0.000020678615,"teacher_disagreement_score":0.1255944,"about_ca_system_score_codex":0.00014718637,"about_ca_system_score_gemma":0.0003382077,"threshold_uncertainty_score":0.99980736},"labels":[],"label_agreement":null},{"id":"W4398287077","doi":"10.7910/dvn/28075/ss1wjc","title":"events.2015.20170206133646.tab","year":2017,"lang":"en","type":"dataset","venue":"Harvard Dataverse","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lockheed Martin (Canada)","funders":"","keywords":"Event data; Event (particle physics); Computer science; Data science; Physics","score_opus":0.016750189544812576,"score_gpt":0.32435851138943633,"score_spread":0.3076083218446238,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398287077","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000050473795,0.000010032205,0.00007541156,0.00027162457,0.0022969185,0.00044103857,0.9958054,0.000088797795,0.0009603125],"genre_scores_gemma":[0.00003657604,0.0011226911,0.0007640813,0.0017091222,0.0022913953,0.000025970636,0.989382,0.00006508202,0.0046030553],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99727446,0.000088833345,0.00047383903,0.00077230803,0.0007885073,0.0006020508],"domain_scores_gemma":[0.99525255,0.000087205066,0.00048903225,0.003480562,0.00010561085,0.00058503146],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0006911126,0.00050622434,0.0009160885,0.00026250418,0.00033956708,0.00012986366,0.0010982205,0.00045974483,0.020151839],"category_scores_gemma":[0.0022063022,0.00044354226,0.00029597082,0.00006787414,0.00025395665,0.00023056185,0.00066224206,0.0018021242,0.17295371],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009297136,0.00015628799,0.00015688872,0.00037485195,0.00023243614,0.0009658824,0.000008738164,0.0000010209028,0.00001787768,0.000006123407,0.9961,0.001886898],"study_design_scores_gemma":[0.0017799311,0.00010758419,0.0006088993,0.00068073865,0.0007415172,0.0002838586,0.000010419851,0.00010698472,0.000005094716,0.000029647272,0.99521893,0.00042637283],"about_ca_topic_score_codex":0.0006631284,"about_ca_topic_score_gemma":0.000027453581,"teacher_disagreement_score":0.15280187,"about_ca_system_score_codex":0.00013638326,"about_ca_system_score_gemma":0.0004288869,"threshold_uncertainty_score":0.99980164},"labels":[],"label_agreement":null},{"id":"W4398428220","doi":"10.7910/dvn/8yvinu/viaoii","title":"MedRed_test.txt","year":2020,"lang":"en","type":"dataset","venue":"Harvard Dataverse","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bell (Canada)","funders":"","keywords":"Test (biology); Computer science; Geology; Paleontology","score_opus":0.01577265526808443,"score_gpt":0.27750829806244826,"score_spread":0.26173564279436384,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398428220","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000011805933,0.0000023309642,0.000092089525,0.00028779436,0.00076134724,0.0003007594,0.99772984,0.00013458364,0.0006794416],"genre_scores_gemma":[0.000011803227,0.00062653807,0.0015370625,0.0080875065,0.0012337508,0.000015122363,0.98806363,0.000048691218,0.00037591357],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99797046,0.000065348126,0.0003897794,0.00060084794,0.000589856,0.0003837255],"domain_scores_gemma":[0.9979418,0.0001057912,0.00018346588,0.0011081845,0.000057331934,0.00060344744],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00024647507,0.00035929578,0.0006854191,0.00016662892,0.000088198845,0.000068523346,0.0004595928,0.00028507333,0.0367945],"category_scores_gemma":[0.0019746681,0.00032054292,0.00019785263,0.00019966306,0.00015908956,0.00008810007,0.00037084517,0.0016544554,0.30900717],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006367131,0.00008061029,0.000028679386,0.0003865204,0.00016510072,0.0017221941,0.000013085671,0.0000013924663,0.000037173544,0.000014613785,0.9959797,0.001507239],"study_design_scores_gemma":[0.0010735197,0.00012523032,0.00008510994,0.0002791391,0.00057112705,0.0002058035,0.00001656624,0.00024861054,0.000008433898,0.00001497239,0.9970791,0.0002924254],"about_ca_topic_score_codex":0.00024526817,"about_ca_topic_score_gemma":0.0000063375965,"teacher_disagreement_score":0.27221265,"about_ca_system_score_codex":0.0000834053,"about_ca_system_score_gemma":0.00029240947,"threshold_uncertainty_score":0.99992466},"labels":[],"label_agreement":null},{"id":"W4398449374","doi":"10.7910/dvn/8yvinu/4qqkt8","title":"MedRed_train.txt","year":2020,"lang":"en","type":"dataset","venue":"Harvard Dataverse","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bell (Canada)","funders":"","keywords":"Computer science","score_opus":0.015997329023421887,"score_gpt":0.2780904244601892,"score_spread":0.26209309543676734,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398449374","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000007931549,0.0000020391328,0.00012017751,0.00032294862,0.0007553549,0.00030929272,0.9975776,0.00011980378,0.0007848539],"genre_scores_gemma":[0.00001545779,0.0005945189,0.0014909223,0.008488845,0.001218822,0.000015229042,0.98778313,0.000048595248,0.00034445792],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99795145,0.00006568628,0.0003893303,0.0006045277,0.0005951075,0.00039389965],"domain_scores_gemma":[0.9980357,0.00008657953,0.00016844236,0.0010456685,0.00005266252,0.00061089644],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00025699416,0.00036136352,0.00068596844,0.00016670677,0.000089616384,0.00006693623,0.00044804678,0.0002874853,0.034654055],"category_scores_gemma":[0.0013344306,0.00032263965,0.00021221169,0.00019029625,0.00017612091,0.00008477175,0.00030433157,0.0016749601,0.27540138],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000075634714,0.00007985492,0.000011934056,0.0004217264,0.00020387057,0.0017921227,0.00001873636,0.0000016106532,0.000036836864,0.00002048378,0.99552524,0.0018119424],"study_design_scores_gemma":[0.0012454973,0.00011775748,0.00006751642,0.0002618624,0.0005959819,0.00020087375,0.000023615568,0.0002037373,0.0000084939975,0.000015138384,0.9969676,0.00029189672],"about_ca_topic_score_codex":0.00015214458,"about_ca_topic_score_gemma":0.000005391466,"teacher_disagreement_score":0.24074732,"about_ca_system_score_codex":0.0000770412,"about_ca_system_score_gemma":0.0002911108,"threshold_uncertainty_score":0.9999226},"labels":[],"label_agreement":null},{"id":"W4398661188","doi":"10.7910/dvn/itvlik/cbzbr5","title":"all data for CH EUvotes _big.tab","year":2020,"lang":"en","type":"dataset","venue":"Harvard Dataverse","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Big data; Computer science; Data mining","score_opus":0.04616482979426597,"score_gpt":0.328658993437961,"score_spread":0.28249416364369506,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398661188","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000003340539,0.000008688264,0.0010926552,0.00097285287,0.0010381094,0.0007312821,0.99593836,0.00010391349,0.00011077941],"genre_scores_gemma":[0.0000036260521,0.0008798239,0.0073612486,0.009602266,0.0029409267,0.00003505501,0.9787954,0.000072475734,0.00030919016],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972871,0.000062882296,0.0004975206,0.0010906117,0.0005448581,0.00051701494],"domain_scores_gemma":[0.9956391,0.00027420375,0.00025079143,0.0032159034,0.00008095068,0.00053905474],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00063908973,0.00043364544,0.00083991647,0.00014554715,0.000110082336,0.00014623904,0.0015365512,0.00031626268,0.00337999],"category_scores_gemma":[0.0045520365,0.0003848339,0.00016378082,0.00013609849,0.00015572603,0.00020616989,0.0013095281,0.0012192283,0.026262643],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017800108,0.000107823806,0.000013686971,0.000937447,0.00035334716,0.00031061177,0.000012009829,0.0000014813364,0.00004179921,0.000018848179,0.9955658,0.0024591805],"study_design_scores_gemma":[0.0019572768,0.00014425401,0.000023301249,0.00029096726,0.001237748,0.000083194,0.000024055176,0.0034196659,0.000006133839,0.0000168033,0.9924207,0.00037590225],"about_ca_topic_score_codex":0.00029576238,"about_ca_topic_score_gemma":0.000014623757,"teacher_disagreement_score":0.022882653,"about_ca_system_score_codex":0.000066166205,"about_ca_system_score_gemma":0.0003431915,"threshold_uncertainty_score":0.99986035},"labels":[],"label_agreement":null},{"id":"W4398699980","doi":"10.7910/dvn/jzyacj/rb3lkp","title":"LAD_2_Summary_Statistics_Unionized.do","year":2017,"lang":"en","type":"dataset","venue":"Harvard Dataverse","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Statistics Canada; Memorial University of Newfoundland","funders":"","keywords":"Statistics; Mathematics","score_opus":0.01452291500544443,"score_gpt":0.306287242446001,"score_spread":0.2917643274405565,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398699980","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000053784443,0.0000070125507,0.0002942356,0.00006985853,0.0012963832,0.00028220026,0.9948426,0.00005789634,0.0031444326],"genre_scores_gemma":[0.000010751796,0.0013782157,0.0030395708,0.001244628,0.00087293726,0.000013556364,0.99047244,0.000044873905,0.0029230362],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99802613,0.000067253866,0.00036023348,0.0005715111,0.00056430924,0.00041058005],"domain_scores_gemma":[0.9965577,0.00012907083,0.00033809093,0.0024526492,0.000103272105,0.0004192094],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00043503082,0.00036973043,0.00069724245,0.00023247795,0.0002957771,0.0002252825,0.0006933338,0.0003032152,0.024687069],"category_scores_gemma":[0.0027027752,0.00033152825,0.00016765989,0.000059487742,0.0002975443,0.00012605585,0.00041174478,0.0013798055,0.08128447],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007473456,0.00009524063,0.00005188381,0.0003281801,0.00016611344,0.001898874,0.0000064027727,9.929072e-7,0.000005366457,0.000051911673,0.99203825,0.005282064],"study_design_scores_gemma":[0.0012481391,0.000089922105,0.00019564465,0.0005394666,0.00054783194,0.0002014155,0.000007446102,0.000143907,0.0000013430814,0.0000568557,0.99665165,0.0003163998],"about_ca_topic_score_codex":0.0003442162,"about_ca_topic_score_gemma":0.000013080176,"teacher_disagreement_score":0.056597404,"about_ca_system_score_codex":0.000086854285,"about_ca_system_score_gemma":0.00032951473,"threshold_uncertainty_score":0.9999137},"labels":[],"label_agreement":null},{"id":"W4398750483","doi":"10.7910/dvn/g6qbd2","title":"Reconstructed Cropped CT Scans","year":2021,"lang":"en","type":"dataset","venue":"Harvard Dataverse","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Light Source (Canada)","funders":"","keywords":"Nuclear medicine; Geology; Medicine","score_opus":0.012755643797134127,"score_gpt":0.27406747819535393,"score_spread":0.2613118343982198,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398750483","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002543738,0.000009065344,0.000064402164,0.00011094258,0.0014977922,0.00026342116,0.9968773,0.000088685614,0.00083400327],"genre_scores_gemma":[0.000015082842,0.0010115335,0.0019539963,0.002470559,0.0007519315,0.000013934004,0.9926079,0.000048943068,0.0011261418],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.997695,0.00012392178,0.0004888357,0.000703789,0.00052056514,0.0004678659],"domain_scores_gemma":[0.99740934,0.00010578655,0.0002230645,0.0016801199,0.00013071514,0.00045098687],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00033258743,0.0003908857,0.0008095367,0.00024727828,0.00013084213,0.00011630358,0.00038785962,0.00019177554,0.058426686],"category_scores_gemma":[0.0017726077,0.00036270055,0.00020563754,0.00031395076,0.00024914107,0.00010135654,0.00033278964,0.0016093968,0.02458159],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004259872,0.00009443336,0.000102337624,0.00035849755,0.00023849755,0.00426536,0.000005099304,0.000002094503,0.00006461255,0.000005509062,0.9910679,0.0037530859],"study_design_scores_gemma":[0.0014040992,0.000048580478,0.0001243175,0.0006840873,0.00061289134,0.0017595382,0.000047203484,0.00021465721,0.000025712547,0.0000057861407,0.9947276,0.00034549856],"about_ca_topic_score_codex":0.0007000047,"about_ca_topic_score_gemma":0.000045988985,"teacher_disagreement_score":0.033845093,"about_ca_system_score_codex":0.00013145155,"about_ca_system_score_gemma":0.00075799075,"threshold_uncertainty_score":0.9998825},"labels":[],"label_agreement":null},{"id":"W4398778192","doi":"10.31083/j.rcm2505184","title":"UltraAIGenomics: Artificial Intelligence-Based Cardiovascular Disease Risk Assessment by Fusion of Ultrasound-Based Radiomics and Genomics Features for Preventive, Personalized and Precision Medicine: A Narrative Review","year":2024,"lang":"en","type":"review","venue":"Reviews in Cardiovascular Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Queen's University","funders":"","keywords":"Medicine; Radiomics; Precision medicine; Personalized medicine; Genomics; Disease; Narrative review; Medical physics; Artificial intelligence; Bioinformatics; Intensive care medicine; Internal medicine; Pathology; Radiology; Genome; Gene; Genetics","score_opus":0.033821482791050725,"score_gpt":0.36926829928248533,"score_spread":0.3354468164914346,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398778192","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000024084538,0.96133316,0.025174424,0.00081058603,0.0005723313,0.011750773,0.00023752134,0.00004787205,0.00004925948],"genre_scores_gemma":[0.000040097177,0.989701,0.0059204567,0.0003771756,0.0007947377,0.0011754616,0.0017179932,0.0002141738,0.0000589512],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98987484,0.0026556128,0.0033117554,0.0020515772,0.0014639883,0.00064223877],"domain_scores_gemma":[0.9940608,0.001917843,0.0011440885,0.0018521505,0.00030728464,0.00071779493],"candidate_categories":["metaepi_narrow"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.015354919,0.0014040341,0.012264324,0.00079667766,0.00020019026,0.0000413197,0.00044353836,0.00048563862,0.00005104452],"category_scores_gemma":[0.007311469,0.00091493555,0.0047897273,0.0010537553,0.0013479268,0.000077801655,0.00011359533,0.0019511523,0.000003319372],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008555067,0.00009479181,0.000009819913,0.19076851,0.00405545,0.00007259797,0.0003527138,0.000035072087,0.000009319065,0.000055265165,0.0044057793,0.80005515],"study_design_scores_gemma":[0.0013318352,0.00036371587,0.0000071953455,0.24096844,0.052592043,0.00018815992,0.00012727125,0.0011945638,0.0000019150336,0.00016166954,0.70251936,0.00054383464],"about_ca_topic_score_codex":0.00013024661,"about_ca_topic_score_gemma":0.0000022127847,"teacher_disagreement_score":0.7995113,"about_ca_system_score_codex":0.000685155,"about_ca_system_score_gemma":0.00096359913,"threshold_uncertainty_score":0.999871},"labels":[],"label_agreement":null},{"id":"W4398781270","doi":"10.1017/cjn.2024.180","title":"P.074 Assessing the emergence and evolution of artificial intelligence and machine learning research in neuroradiology","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Neurological Sciences / Journal Canadien des Sciences Neurologiques","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Toronto Public Health","funders":"","keywords":"Neuroradiology; Artificial intelligence; Machine learning; Medicine; Computer science; Medical physics; Psychology; Neurology; Psychiatry","score_opus":0.0954847100205579,"score_gpt":0.38133582895275575,"score_spread":0.28585111893219783,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398781270","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9741478,0.009466711,0.00032416824,0.015119704,0.0004641231,0.00009993832,0.0000010585212,0.0000075902635,0.00036892458],"genre_scores_gemma":[0.99689317,0.0015855774,0.00094351574,0.00039729552,0.0001663888,0.0000010325377,8.5313275e-8,0.0000069648604,0.000005970443],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9961828,0.0014570693,0.00068561063,0.00038355673,0.0005496998,0.00074126583],"domain_scores_gemma":[0.9972483,0.0015276853,0.00022049995,0.000074159245,0.00021818855,0.0007111619],"candidate_categories":["sts","research_integrity"],"consensus_categories":["sts"],"category_scores_codex":[0.011349522,0.00015413843,0.0003457616,0.0012546885,0.0013482464,0.00045654605,0.000575391,0.00010656463,0.000030309408],"category_scores_gemma":[0.0046725865,0.00008852178,0.00007379317,0.001710324,0.009568841,0.00046653743,0.000075734875,0.0027601772,4.2406478e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003211329,0.000014460774,0.9316464,0.000033704153,0.000008289693,0.003360667,0.000650575,0.003256188,0.00030408602,0.0060838074,0.000037297843,0.05457242],"study_design_scores_gemma":[0.00013146205,0.032201193,0.53791404,0.00036024125,0.000050814986,0.0643687,0.0016536713,0.28440335,0.00007243667,0.07729936,0.0013191059,0.00022564801],"about_ca_topic_score_codex":0.002419698,"about_ca_topic_score_gemma":0.0083853975,"teacher_disagreement_score":0.39373237,"about_ca_system_score_codex":0.00010711851,"about_ca_system_score_gemma":0.0018677239,"threshold_uncertainty_score":0.99995184},"labels":[],"label_agreement":null},{"id":"W4398781422","doi":"10.1017/cjn.2024.99","title":"E.2 Proof of concept for liquid biopsy: positive correlation between extracellular vesicles shed by high grade gliomas and volume of hypervascular tumour tissue on MRI","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Neurological Sciences / Journal Canadien des Sciences Neurologiques","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Moncton Hospital","funders":"","keywords":"Biomarker; RNA; Brain tissue; Extracellular vesicle; Cerebral blood volume; Intensity (physics); Pathology; Chemistry; Corpus callosum; Magnetic resonance imaging; Extracellular fluid; Medicine; Nuclear medicine; Extracellular; Radiology; Biomedical engineering; Gene; Microvesicles; Biochemistry","score_opus":0.01753298329514864,"score_gpt":0.27242101429616267,"score_spread":0.25488803100101404,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398781422","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98066807,0.0059806355,0.0021196958,0.010416388,0.00041712247,0.00026030556,0.00004411531,0.000010348118,0.000083305764],"genre_scores_gemma":[0.9967586,0.0001318623,0.0024133713,0.00043730435,0.00021571253,0.0000019642566,0.0000022583627,0.000013268962,0.00002567227],"study_design_codex":"observational","study_design_gemma":"nonrandomized_trial","domain_scores_codex":[0.99711084,0.00042705637,0.000817973,0.00041429707,0.0006178407,0.00061196106],"domain_scores_gemma":[0.9973392,0.0007384605,0.0005241534,0.00009035122,0.00029043743,0.0010174126],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0029994478,0.00022793621,0.00061107223,0.0006981021,0.0006098518,0.00018036214,0.00049290096,0.00015314657,0.000034274555],"category_scores_gemma":[0.0016560203,0.00015236845,0.00018386716,0.00074404123,0.004645177,0.0003610372,0.000028347542,0.0008661995,2.4959755e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001384987,0.0003678674,0.8006534,0.0004922906,0.0004545912,0.017638782,0.003976427,0.02305214,0.04383429,0.010054702,0.0050935145,0.09299701],"study_design_scores_gemma":[0.003005621,0.49826324,0.25188687,0.0017119604,0.0010748069,0.052186087,0.000675734,0.09838632,0.05901354,0.023361875,0.009221195,0.0012127415],"about_ca_topic_score_codex":0.0009051886,"about_ca_topic_score_gemma":0.00032499016,"teacher_disagreement_score":0.5487665,"about_ca_system_score_codex":0.00009002453,"about_ca_system_score_gemma":0.001154774,"threshold_uncertainty_score":0.9980636},"labels":[],"label_agreement":null},{"id":"W4398822678","doi":"10.7910/dvn/rj7vuq/ygpi9t","title":"JD_Sweden_4digit.tab","year":2018,"lang":"en","type":"dataset","venue":"Harvard Dataverse","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Geology; Geography","score_opus":0.01374480942265064,"score_gpt":0.2876350569651714,"score_spread":0.2738902475425207,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398822678","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000054857323,0.0000031862014,0.0000666576,0.000081529426,0.0014729769,0.00029677115,0.9963921,0.00010161185,0.0015303672],"genre_scores_gemma":[0.000010307857,0.0005032316,0.0010844915,0.003557203,0.0030893728,0.00001460605,0.9899618,0.000049422786,0.001729553],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99778366,0.000060631395,0.00041420208,0.0006337895,0.0006228855,0.00048485096],"domain_scores_gemma":[0.9974596,0.000081765014,0.00020339336,0.0016861119,0.00011138361,0.0004577782],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00042614577,0.0003873828,0.00065513176,0.00024713326,0.00012740995,0.000112126785,0.0005085958,0.00035140975,0.03288613],"category_scores_gemma":[0.0011526134,0.0003331906,0.0002013303,0.00017092384,0.00031307436,0.00012993123,0.00039072373,0.0011201329,0.13563138],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007267109,0.0001117399,0.000029700439,0.0002547319,0.00016004723,0.00066562096,0.000008759386,3.7632765e-7,0.000017217531,0.0000068529525,0.99773264,0.00093966746],"study_design_scores_gemma":[0.0010406134,0.0001556396,0.000071012895,0.0003852702,0.00045895937,0.00029138985,0.000011884142,0.000107162596,0.00001237762,0.000017141143,0.99712485,0.0003236843],"about_ca_topic_score_codex":0.00035758805,"about_ca_topic_score_gemma":0.000017394033,"teacher_disagreement_score":0.10274526,"about_ca_system_score_codex":0.00012697908,"about_ca_system_score_gemma":0.000293691,"threshold_uncertainty_score":0.999912},"labels":[],"label_agreement":null},{"id":"W4398840568","doi":"10.7910/dvn/udgofr/06l2d7","title":"Data_R_PSLE.tab","year":2020,"lang":"kn","type":"dataset","venue":"Harvard Dataverse","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science","score_opus":0.01662999133641903,"score_gpt":0.2775897916260731,"score_spread":0.2609598002896541,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398840568","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00003593192,0.000022855784,0.0009880579,0.00064030226,0.004473725,0.00082514423,0.9913109,0.00019657536,0.0015065032],"genre_scores_gemma":[0.00012835077,0.004710376,0.002314893,0.0122399675,0.007375996,0.000029417743,0.9715188,0.00017399939,0.0015081782],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99370646,0.0003702727,0.0012559298,0.0019065024,0.001483832,0.0012770185],"domain_scores_gemma":[0.99343544,0.0004044718,0.0006478363,0.0035752084,0.0001368617,0.0018001612],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0010368725,0.0011079563,0.0017815079,0.00037041528,0.00037017453,0.00036410472,0.0020614944,0.0006953139,0.08131807],"category_scores_gemma":[0.0052969707,0.0010630155,0.0004236867,0.0005792889,0.00061039516,0.00048371308,0.0020179378,0.0044079134,0.74232906],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003129968,0.00033312972,0.000117328425,0.001395015,0.0006867009,0.0044740485,0.00011410878,0.000010126507,0.00015878219,0.000102658734,0.9866159,0.0056792037],"study_design_scores_gemma":[0.0033958098,0.00035191965,0.00014132618,0.0011862541,0.0020096395,0.00024643017,0.00024392463,0.0035792973,0.000019964204,0.000016413385,0.98783195,0.0009770469],"about_ca_topic_score_codex":0.0006613707,"about_ca_topic_score_gemma":0.000016417378,"teacher_disagreement_score":0.661011,"about_ca_system_score_codex":0.00026046907,"about_ca_system_score_gemma":0.00083274714,"threshold_uncertainty_score":0.999182},"labels":[],"label_agreement":null},{"id":"W4398879717","doi":"10.7910/dvn/vmr7ms/3iormu","title":"biomarker_data.csv","year":2019,"lang":"en","type":"dataset","venue":"Harvard Dataverse","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; University of Toronto","funders":"","keywords":"Biomarker; Computer science; Computational biology; Chemistry; Biology; Biochemistry","score_opus":0.016787844014165915,"score_gpt":0.28852109987047664,"score_spread":0.2717332558563107,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398879717","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000026456652,0.000006286885,0.00009171441,0.00012876297,0.0015942205,0.0004572806,0.99680996,0.000071173,0.0008141534],"genre_scores_gemma":[0.0000070308456,0.00083893875,0.00088693266,0.0033047977,0.00071389193,0.000013750803,0.99203277,0.00005349088,0.0021483798],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99761236,0.00007957817,0.0004416342,0.00073354976,0.0006414129,0.00049149344],"domain_scores_gemma":[0.99671155,0.00011917759,0.00022555374,0.002489572,0.00007078803,0.0003833547],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00050714385,0.00042161354,0.00075559353,0.00033487089,0.00008188821,0.00009441009,0.00063849246,0.0003746497,0.04209806],"category_scores_gemma":[0.00088642363,0.00036617662,0.00022151848,0.00020971888,0.00016766245,0.0001561594,0.0005589324,0.0012866985,0.25555584],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010391853,0.00012260872,0.00007647577,0.00061142206,0.00023777845,0.0006331846,0.0000045566244,0.0000012095763,0.000046046433,0.0000058486894,0.99695945,0.0011974802],"study_design_scores_gemma":[0.0014348655,0.00008290494,0.00017556702,0.00046680402,0.00060096866,0.00025718886,0.000013649675,0.00027157503,0.0000063301954,0.0000057372986,0.99631727,0.0003671257],"about_ca_topic_score_codex":0.00029286582,"about_ca_topic_score_gemma":0.000006590762,"teacher_disagreement_score":0.21345776,"about_ca_system_score_codex":0.00011123925,"about_ca_system_score_gemma":0.00031321886,"threshold_uncertainty_score":0.999879},"labels":[],"label_agreement":null},{"id":"W4398902670","doi":"10.7910/dvn/rnl8ka/uz7rhe","title":"Experiment_2_63.csv","year":2020,"lang":"en","type":"dataset","venue":"Harvard Dataverse","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Computer science; Mathematics","score_opus":0.01664039658121278,"score_gpt":0.2911401342262805,"score_spread":0.2744997376450677,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398902670","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000012558304,0.0000051097286,0.00009086736,0.0002962678,0.0007857618,0.0003105097,0.9976691,0.00010957066,0.0007202568],"genre_scores_gemma":[0.000013352696,0.0005671684,0.0011678968,0.007700182,0.0011657653,0.000021120739,0.98871464,0.00004417016,0.0006057326],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981128,0.00005769258,0.0003571291,0.0005780889,0.0005427832,0.00035150134],"domain_scores_gemma":[0.9981839,0.000056096767,0.00015907879,0.001047492,0.00004015971,0.0005132448],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00018336484,0.00034679647,0.0006232772,0.0001430328,0.00008418138,0.0000708549,0.00040512995,0.0002390637,0.028804816],"category_scores_gemma":[0.0007485182,0.00030946365,0.00018882735,0.00014865794,0.000134518,0.00009004606,0.00036102638,0.0012198342,0.1864705],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008722449,0.000102145226,0.0000134846105,0.00027758584,0.00014634087,0.0011350452,0.000022924103,9.408876e-7,0.00012586126,0.00001370774,0.9975076,0.0005671806],"study_design_scores_gemma":[0.0011487696,0.00010781222,0.000021059092,0.00022783045,0.00036272273,0.00010179723,0.00003742803,0.00017697923,0.0000455052,0.000005174755,0.9974795,0.00028539944],"about_ca_topic_score_codex":0.00013163111,"about_ca_topic_score_gemma":0.0000017952785,"teacher_disagreement_score":0.15766567,"about_ca_system_score_codex":0.000082924555,"about_ca_system_score_gemma":0.00020533876,"threshold_uncertainty_score":0.99993575},"labels":[],"label_agreement":null},{"id":"W4398905266","doi":"10.7910/dvn/rnl8ka/wagexc","title":"Experiment_2_38.csv","year":2020,"lang":"en","type":"dataset","venue":"Harvard Dataverse","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Mathematics","score_opus":0.01664039658121278,"score_gpt":0.2911401342262805,"score_spread":0.2744997376450677,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398905266","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00001234766,0.000005165867,0.00009201224,0.0002974169,0.00078416173,0.000309628,0.99765956,0.00010949954,0.00073019206],"genre_scores_gemma":[0.000012674563,0.0005558254,0.0012079404,0.0077857235,0.0011593507,0.000020560972,0.98860323,0.000044153017,0.0006105252],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981147,0.000057627913,0.00035681733,0.00057751854,0.0005421303,0.0003512092],"domain_scores_gemma":[0.99818575,0.000055955563,0.00015897962,0.0010464576,0.000040069615,0.00051278854],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00018289525,0.00034659228,0.0006228228,0.0001426737,0.000084038824,0.00007046449,0.0004047619,0.00023883069,0.028877733],"category_scores_gemma":[0.0007451912,0.00030930492,0.00018873185,0.00014820315,0.0001333131,0.00008997851,0.0003608049,0.0012183927,0.18584123],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008642513,0.000102099286,0.000013389327,0.00027741725,0.0001462823,0.0011488352,0.000022785676,8.8762806e-7,0.00012404202,0.000013759435,0.9975058,0.0005582642],"study_design_scores_gemma":[0.0011430782,0.00010774759,0.00002072637,0.00022745843,0.00035926583,0.00010302875,0.000036946272,0.00017259471,0.000046022324,0.000005170194,0.99749273,0.0002852226],"about_ca_topic_score_codex":0.00012954258,"about_ca_topic_score_gemma":0.000001776743,"teacher_disagreement_score":0.1569635,"about_ca_system_score_codex":0.00008269553,"about_ca_system_score_gemma":0.00020540645,"threshold_uncertainty_score":0.9999359},"labels":[],"label_agreement":null},{"id":"W4399041927","doi":"10.1136/heartjnl-2024-bcs.175","title":"178 Fully automated coronary artery calcium score and risk categorization from non-ECG gated chest CT using deep learning and multiorgan segmentation: a validation study from national lung screening trial (NLST)","year":2024,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"National Lung Screening Trial; Medicine; Convolutional neural network; Coronary artery disease; Segmentation; Internal medicine; Deep learning; Artificial intelligence; Categorization; Lung cancer screening; Gold standard (test); Radiology; Cardiology; Lung cancer; Computer science","score_opus":0.02310169998468323,"score_gpt":0.3310220866272437,"score_spread":0.30792038664256044,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399041927","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.833647,0.00027543353,0.16420655,0.00015305159,0.00034273334,0.0008545198,0.000017064773,0.00045206907,0.000051532126],"genre_scores_gemma":[0.98005754,0.0000672492,0.01774017,0.00007303683,0.0005259385,0.000018902538,0.0013835953,0.000057287318,0.000076285505],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978715,0.00024038581,0.00050755724,0.00060589286,0.00055195275,0.00022271265],"domain_scores_gemma":[0.9990278,0.00037802814,0.00016757725,0.000101672325,0.00014115966,0.00018380236],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006113668,0.00025899636,0.00034934946,0.0002580637,0.00036461596,0.000323624,0.000051575043,0.00008670827,0.00017300129],"category_scores_gemma":[0.00037271605,0.00023702535,0.000047859947,0.0003332144,0.00008037763,0.00038232518,0.00007134693,0.0005858116,0.000005167597],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019718385,0.00027529083,0.907497,0.00010478388,0.001042955,0.00034653913,0.0040179933,0.006404671,0.03601315,0.000008748918,0.00014925093,0.04216779],"study_design_scores_gemma":[0.013997241,0.00022422182,0.15180531,0.00017857517,0.00057550945,0.000067375164,0.0014913304,0.8309686,0.00042638314,0.000030605817,0.000032588352,0.00020221788],"about_ca_topic_score_codex":0.0027792098,"about_ca_topic_score_gemma":0.00003514648,"teacher_disagreement_score":0.824564,"about_ca_system_score_codex":0.00016152307,"about_ca_system_score_gemma":0.00013404853,"threshold_uncertainty_score":0.9665614},"labels":[],"label_agreement":null},{"id":"W4399071479","doi":"10.1200/jco.23.02475","title":"Surveillance Imaging After Curative-Intent Treatment for Cancer: Benefits, Harms, and Evidence","year":2024,"lang":"en","type":"review","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":21,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Medicine; Cancer; Intensive care medicine; Internal medicine","score_opus":0.265175740569886,"score_gpt":0.5760310266439186,"score_spread":0.31085528607403257,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399071479","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002061054,0.98002696,0.00020766474,0.015565057,0.003287321,0.0006158328,0.000024798488,0.000013096211,0.00005318672],"genre_scores_gemma":[0.0003635334,0.9920383,0.0023509657,0.0012993992,0.0033293841,0.00009615602,0.000005410641,0.00005884201,0.00045798134],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99547005,0.0004575719,0.0030415084,0.00043585204,0.00028482015,0.0003102295],"domain_scores_gemma":[0.9914031,0.0054214452,0.0020910318,0.0001987378,0.00037027945,0.00051540905],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037790544,0.00037601168,0.0052371556,0.00019662912,0.00004070905,0.0000439306,0.00017298984,0.00034308375,0.00004363867],"category_scores_gemma":[0.006000979,0.00020524104,0.0015973086,0.00012274053,0.00026313993,0.000091717004,0.0000821924,0.001735152,0.000008453656],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045818067,0.00018920374,0.0017201,0.005397188,0.00094627205,0.0006886242,0.000047054717,0.000001133201,1.2808646e-7,0.000029151128,0.003706376,0.9868166],"study_design_scores_gemma":[0.0015330196,0.0030238037,0.00051560055,0.04014501,0.0049926597,0.001402744,0.00001638076,0.00045198144,7.790515e-8,0.000041550327,0.9477104,0.0001667637],"about_ca_topic_score_codex":0.00003849718,"about_ca_topic_score_gemma":0.000023306291,"teacher_disagreement_score":0.9866498,"about_ca_system_score_codex":0.0005269662,"about_ca_system_score_gemma":0.0032977345,"threshold_uncertainty_score":0.8369487},"labels":[],"label_agreement":null},{"id":"W4399122128","doi":"10.1200/jco.2024.42.16_suppl.103","title":"Telisotuzumab vedotin monotherapy in patients with previously treated c-Met–overexpressing non-squamous <i>EGFR</i> wildtype advanced NSCLC: Primary analysis of the LUMINOSITY trial.","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto; Hôpital Charles-Le Moyne","funders":"","keywords":"Medicine; Internal medicine; Clinical endpoint; Oncology; Population; Phases of clinical research; Chemotherapy; Clinical trial","score_opus":0.022615103615234937,"score_gpt":0.3832729628268702,"score_spread":0.36065785921163523,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399122128","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9950096,0.0007675715,0.00039430876,0.0015251166,0.00075568113,0.00049254013,0.000002923105,0.00001215889,0.001040123],"genre_scores_gemma":[0.99503684,0.00029528246,0.002750767,0.0014730864,0.00029629088,0.0000039864763,0.000007372486,0.000027760158,0.00010858922],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99605364,0.00058670173,0.0022441351,0.0002807179,0.0005793225,0.00025549962],"domain_scores_gemma":[0.9956409,0.0021513612,0.0014368147,0.00031000155,0.0002512121,0.0002097112],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002838181,0.00018377462,0.0020144873,0.0003550992,0.000041481686,0.000020239257,0.0002722427,0.00025456035,0.000035342913],"category_scores_gemma":[0.0020352781,0.00009997947,0.00073233433,0.0009397771,0.00023818022,0.00013668578,0.0000522459,0.0016560052,0.0000011706799],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.060521517,0.0024816021,0.60364413,0.00009251513,0.0017584855,0.00018678886,0.00024928592,0.0011259781,0.00035917122,0.000008148673,0.00053755596,0.3290348],"study_design_scores_gemma":[0.08331026,0.012600813,0.88744926,0.0009227265,0.0032855072,0.000019296296,0.000027809703,0.0048944536,0.00006317291,0.000028207947,0.007252738,0.00014574223],"about_ca_topic_score_codex":0.000060750284,"about_ca_topic_score_gemma":0.000018213334,"teacher_disagreement_score":0.32888904,"about_ca_system_score_codex":0.00029016292,"about_ca_system_score_gemma":0.0012753075,"threshold_uncertainty_score":0.7194611},"labels":[],"label_agreement":null},{"id":"W4399150161","doi":"10.1200/jco.2024.42.16_suppl.e13639","title":"Auto-machine learning for opportunistic thyroid nodule detection in lung cancer screening chest CT.","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Medicine; Lung cancer screening; Radiology; Lung cancer; Context (archaeology); Thyroid nodules; Thyroid cancer; Artificial intelligence; National Lung Screening Trial; Colorectal cancer; Machine learning; Thyroid; Nuclear medicine; Cancer; Computed tomography; Computer science; Pathology; Internal medicine","score_opus":0.08138901625536003,"score_gpt":0.4727752139493028,"score_spread":0.39138619769394273,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399150161","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6506469,0.010007836,0.276495,0.051894497,0.00797194,0.0006354276,0.000006868078,0.00011774778,0.0022237715],"genre_scores_gemma":[0.98619586,0.0016931248,0.0072766696,0.0014214135,0.0024984344,0.000012344054,0.0000067891206,0.00004131222,0.00085405033],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971186,0.00027872878,0.0017840869,0.00024235451,0.00028456614,0.00029164273],"domain_scores_gemma":[0.99575627,0.0029677495,0.00065892783,0.00009354037,0.00016819892,0.00035532765],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0061776815,0.00014194126,0.0010577852,0.00028208707,0.00006871195,0.000029975414,0.0001254954,0.0001802682,0.00010520758],"category_scores_gemma":[0.010443067,0.00010650702,0.00042957283,0.00021419495,0.00012419836,0.00012045519,0.00003915722,0.0029256071,0.0000028973445],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00090683985,0.00025670158,0.042854197,0.00029371353,0.00030746486,0.0017131865,0.0001042628,0.0010939898,0.0017927069,0.00012432998,0.0013858518,0.9491668],"study_design_scores_gemma":[0.0037597562,0.0027050048,0.033171706,0.00067654584,0.00041659226,0.0007339177,0.00004680096,0.7042116,0.000036075704,0.00012653615,0.25400794,0.00010754169],"about_ca_topic_score_codex":0.000121434976,"about_ca_topic_score_gemma":0.00006389216,"teacher_disagreement_score":0.9490592,"about_ca_system_score_codex":0.00022675427,"about_ca_system_score_gemma":0.0010794891,"threshold_uncertainty_score":0.9993747},"labels":[],"label_agreement":null},{"id":"W4399318666","doi":"10.5194/essd-2024-84-rc2","title":"Comment on essd-2024-84","year":2024,"lang":"en","type":"peer-review","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université de Montréal; McGill University","funders":"","keywords":"Computer science; Mathematics","score_opus":0.02612666667166775,"score_gpt":0.366663759454192,"score_spread":0.34053709278252425,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399318666","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000001158141,0.033022024,0.00014724428,0.64895374,0.006566962,0.0004171976,0.00002966753,0.0001507238,0.31071126],"genre_scores_gemma":[0.000012684232,0.009393231,0.000588711,0.3507931,0.0013068169,0.00003679165,0.0006788142,0.000070600574,0.63711923],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977885,0.000055802906,0.0004552095,0.00056219986,0.0007968393,0.0003414743],"domain_scores_gemma":[0.99873936,0.00015850512,0.000088252644,0.0006277224,0.000080595426,0.0003055506],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00069062156,0.00038635702,0.0009598149,0.00019288319,0.00004728571,0.000049903494,0.00020574304,0.00021495039,0.011293405],"category_scores_gemma":[0.0004621496,0.0002576115,0.0003739501,0.00019748305,0.000071550465,0.000011711796,0.00014013502,0.0025348417,0.0024871465],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000074945547,0.000076680175,0.0000045322536,0.008704413,0.00018212959,0.00028894405,0.000011667879,7.358889e-7,0.0000015467367,0.0011925885,0.9459319,0.043597333],"study_design_scores_gemma":[0.00032772348,0.00018520847,0.0000057196326,0.026937308,0.0007884383,0.000097180826,0.0000051328275,0.0007807528,0.0000042493316,0.00019256282,0.9704342,0.00024154679],"about_ca_topic_score_codex":0.0001719514,"about_ca_topic_score_gemma":0.000003480233,"teacher_disagreement_score":0.326408,"about_ca_system_score_codex":0.00017437903,"about_ca_system_score_gemma":0.00020206696,"threshold_uncertainty_score":0.9999876},"labels":[],"label_agreement":null},{"id":"W4399324701","doi":"10.1200/jco.2024.42.16_suppl.2008","title":"Results from METIS (EF-25), an international, multicenter phase III randomized study evaluating the efficacy and safety of tumor treating fields (TTFields) therapy in NSCLC patients with brain metastases.","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Jewish General Hospital; McGill University; Centre Hospitalier de l’Université de Montréal","funders":"","keywords":"Medicine; Oncology; Internal medicine; Metis","score_opus":0.07240373420940606,"score_gpt":0.5012010046874324,"score_spread":0.4287972704780264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399324701","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9878973,0.00031449716,0.00074088766,0.00930674,0.00067333947,0.00079239474,0.000010596241,0.0000071794066,0.00025708164],"genre_scores_gemma":[0.9935013,0.00025611953,0.0041514025,0.0015720677,0.00045536974,0.0000070780616,0.00001562683,0.000015040987,0.000025975074],"study_design_codex":"design_other","study_design_gemma":"randomized_trial","domain_scores_codex":[0.9943414,0.0021416869,0.0026256265,0.00025429256,0.00049841346,0.000138592],"domain_scores_gemma":[0.9750279,0.02314705,0.0012198071,0.00018895057,0.00025890354,0.00015737569],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.013745597,0.00013931036,0.0014597458,0.0001441398,0.00003973963,0.00003081662,0.00018710551,0.000096654876,0.00007378008],"category_scores_gemma":[0.024506269,0.00006846521,0.00020993309,0.000120157325,0.00022017583,0.00014304696,0.000048607166,0.0012978924,4.2265364e-7],"study_design_candidate":"randomized_trial","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.37209103,0.0037265792,0.019060425,0.00000791474,0.0011611332,0.00025958335,0.0026669952,0.000108056636,0.00006107663,0.00001345944,0.00011999989,0.60072374],"study_design_scores_gemma":[0.81723887,0.033463877,0.092165366,0.0005726587,0.0008014301,0.000028739652,0.0008367938,0.05350147,0.000012682847,0.00006787494,0.001206701,0.00010351527],"about_ca_topic_score_codex":0.0003229633,"about_ca_topic_score_gemma":0.00004192555,"teacher_disagreement_score":0.6006202,"about_ca_system_score_codex":0.00004184322,"about_ca_system_score_gemma":0.00030563716,"threshold_uncertainty_score":0.9837107},"labels":[],"label_agreement":null},{"id":"W4399343148","doi":"10.2139/ssrn.4851908","title":"Integrating Plasma Transcriptomics and Brain Radiomics to Identify Biomarkers for Diabetic Peripheral Neuropathy","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Radiomics; Peripheral neuropathy; Peripheral; Medicine; Biomarker; Transcriptome; Diabetes mellitus; Internal medicine; Diabetic neuropathy; Biology; Endocrinology; Radiology; Gene expression; Gene","score_opus":0.009084940666718841,"score_gpt":0.3016388095342956,"score_spread":0.2925538688675768,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399343148","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8942293,0.0072156074,0.06620624,0.028894544,0.0022566065,0.00092485826,0.000024846364,0.00010590781,0.00014212313],"genre_scores_gemma":[0.9836418,0.0036232758,0.0074609187,0.0021653143,0.0016835431,0.00006793984,0.00005723618,0.0002485946,0.0010513726],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9958088,0.00014493261,0.00073104457,0.00073152286,0.00037453702,0.0022091628],"domain_scores_gemma":[0.9987372,0.00019926617,0.00017749408,0.00029194631,0.00012151178,0.00047256544],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0032873047,0.0005054758,0.0007877989,0.0004909428,0.0002257497,0.0004406675,0.00034669595,0.00029728835,0.000008655356],"category_scores_gemma":[0.0010697438,0.00044395626,0.0004732995,0.0002006476,0.0001276685,0.000055728637,0.00024345683,0.008776267,0.000004709041],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00184668,0.00024581017,0.0024560143,0.0029814022,0.0047874725,0.00032703992,0.0058856225,0.0013280358,0.080444284,0.03535834,0.0060243127,0.858315],"study_design_scores_gemma":[0.009221883,0.003590924,0.0013634888,0.004827236,0.0033109032,0.014705111,0.0051548276,0.59012413,0.00056146376,0.34462157,0.020334587,0.002183865],"about_ca_topic_score_codex":0.00006352993,"about_ca_topic_score_gemma":0.00008645738,"teacher_disagreement_score":0.85613114,"about_ca_system_score_codex":0.0013733675,"about_ca_system_score_gemma":0.002900534,"threshold_uncertainty_score":0.9998012},"labels":[],"label_agreement":null},{"id":"W4399353240","doi":"10.21203/rs.3.rs-4397157/v1","title":"Validation of new, circulating biomarkers for glioma","year":2024,"lang":"en","type":"preprint","venue":"Research Square","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; University of Toronto","funders":"","keywords":"Glioma; Medicine; Computer science; Cancer research","score_opus":0.07751273803696927,"score_gpt":0.4547729837209573,"score_spread":0.377260245683988,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399353240","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97509295,0.0027241048,0.005599548,0.009322976,0.0006902855,0.0022487747,0.000056536603,0.00013308656,0.0041317395],"genre_scores_gemma":[0.9888394,0.0000656586,0.008624241,0.000025728072,0.000949396,0.00009864091,0.0003567465,0.00008253069,0.00095765555],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974268,0.00014016696,0.0004350139,0.00052250695,0.0010398262,0.00043570073],"domain_scores_gemma":[0.9980858,0.0005220348,0.000107892694,0.00049147574,0.0005086067,0.00028418397],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027805883,0.00017326127,0.00042754962,0.00081348367,0.00008728928,0.000091802736,0.00020287411,0.0002669679,0.00009500763],"category_scores_gemma":[0.0037912296,0.00015270476,0.00030951772,0.00048648898,0.0001433797,0.000021340804,0.00061549427,0.0016416236,0.000019501938],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011185657,0.0005003858,0.016839406,0.0932454,0.0028079406,0.00074063387,0.00546952,0.002820144,0.26037458,0.0066052554,0.145866,0.46361217],"study_design_scores_gemma":[0.007575933,0.0021417346,0.013639063,0.050575692,0.0011888855,0.00038194985,0.0027586897,0.59890807,0.098952964,0.18644083,0.03603167,0.0014044967],"about_ca_topic_score_codex":0.00044864512,"about_ca_topic_score_gemma":0.0000011369641,"teacher_disagreement_score":0.59608793,"about_ca_system_score_codex":0.00020946709,"about_ca_system_score_gemma":0.0010483353,"threshold_uncertainty_score":0.71321285},"labels":[],"label_agreement":null},{"id":"W4399359135","doi":"10.5489/cuaj.8832","title":"Poster Session 7: Oncology – Prostate (Part 2)","year":2024,"lang":"en","type":"article","venue":"Canadian Urological Association Journal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"Research Nova Scotia; Dalhousie University; Dalhousie Medical Research Foundation","keywords":"Medicine; Prostate cancer; Nomogram; Biochemical recurrence; Receiver operating characteristic; Concordance; Stage (stratigraphy); Androgen deprivation therapy; Prostate; Cohort; Lymph node; Oncology; Internal medicine; Cancer; Prostatectomy","score_opus":0.010831654902655818,"score_gpt":0.2815225316366104,"score_spread":0.2706908767339546,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399359135","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45040646,0.0014577565,0.0002388654,0.5056519,0.003432155,0.00023849763,0.000017878985,0.00013610745,0.038420416],"genre_scores_gemma":[0.972988,0.00019091196,0.00029109177,0.019419359,0.0015274979,0.0000045982324,0.000025606247,0.000017770091,0.0055351304],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99869335,0.0001539651,0.00027821513,0.00017432691,0.0002747232,0.00042541305],"domain_scores_gemma":[0.9987414,0.00016764493,0.00008342826,0.00006108522,0.00011616973,0.0008302722],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0011365663,0.00009836711,0.00020737345,0.00019619161,0.00018913897,0.00015779558,0.00006963052,0.00021551661,0.0012843487],"category_scores_gemma":[0.00096024666,0.00006922535,0.00011421218,0.00017527009,0.00003228077,0.00008854874,0.000013369209,0.00135155,0.00022743392],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000072081486,0.00006343607,0.36324576,0.000032822154,0.00023906126,0.0038928122,0.00050314626,0.000037043603,0.00064483413,0.0007470659,0.45200258,0.17851935],"study_design_scores_gemma":[0.00039993718,0.00028367533,0.06074424,0.000057764784,0.0000615612,0.001507171,0.000022719261,0.0018493793,0.000007837097,0.0007003736,0.93428516,0.00008018681],"about_ca_topic_score_codex":0.00022311987,"about_ca_topic_score_gemma":0.000055118522,"teacher_disagreement_score":0.5225816,"about_ca_system_score_codex":0.0012910616,"about_ca_system_score_gemma":0.0009782382,"threshold_uncertainty_score":0.9996286},"labels":[],"label_agreement":null},{"id":"W4399380900","doi":"10.1200/jco.2024.42.16_suppl.e17105","title":"Addition of MRI or DRE to clinical data and risk prediction for clinically significant prostate cancer.","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; McGill University; University of Calgary; University of Toronto; University Health Network; Mount Sinai Hospital","funders":"","keywords":"Medicine; Prostate cancer; Cancer; Prostate; Oncology; Magnetic resonance imaging; Internal medicine; Radiology","score_opus":0.14141515787709968,"score_gpt":0.5425953067782464,"score_spread":0.4011801489011467,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399380900","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.894004,0.0014269353,0.03507828,0.05789197,0.009257224,0.0012007431,0.00082864705,0.000050170518,0.00026205656],"genre_scores_gemma":[0.81631476,0.06123965,0.10337422,0.0046727443,0.013357471,0.00003435163,0.00012070693,0.0000800115,0.0008060777],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9936696,0.0005808009,0.004695106,0.0004510299,0.00037286463,0.00023059767],"domain_scores_gemma":[0.9855377,0.011252657,0.0016903296,0.0003477203,0.0004935089,0.00067806774],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.017874615,0.00014203406,0.0015657203,0.0001458599,0.00004852943,0.00002414733,0.00028328347,0.00038538326,0.00010237344],"category_scores_gemma":[0.04209702,0.000088772285,0.0003634383,0.0001783249,0.0003894064,0.00015650396,0.00014735507,0.0018932885,0.000004128073],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008921135,0.0005888046,0.16127662,0.00020430006,0.00065232767,0.00018383384,0.00009992965,0.000050999523,0.00004885879,0.00003236589,0.09969413,0.7282467],"study_design_scores_gemma":[0.007862085,0.03623561,0.21389045,0.0013246661,0.0021814813,0.00021931894,0.00016247183,0.06315228,0.000009114066,0.00059508445,0.67422986,0.00013755697],"about_ca_topic_score_codex":0.000032524782,"about_ca_topic_score_gemma":0.000020991989,"teacher_disagreement_score":0.7281091,"about_ca_system_score_codex":0.000058235142,"about_ca_system_score_gemma":0.002588393,"threshold_uncertainty_score":0.9659718},"labels":[],"label_agreement":null},{"id":"W4399388943","doi":"10.3390/diagnostics14111205","title":"Gastro-Esophageal Cancer: Can Radiomic Parameters from Baseline 18F-FDG-PET/CT Predict the Development of Distant Metastatic Disease?","year":2024,"lang":"en","type":"article","venue":"Diagnostics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; Sinai Health System; Women's College Hospital; Toronto General Hospital; University of Toronto; University Health Network","funders":"","keywords":"Medicine; Radiomics; Sarcopenia; Stage (stratigraphy); PET-CT; Radiology; Disease; Esophageal cancer; Proportional hazards model; Cancer; Internal medicine; Oncology; Nuclear medicine; Positron emission tomography","score_opus":0.014368936092058292,"score_gpt":0.29155699304672755,"score_spread":0.27718805695466925,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399388943","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96850586,0.0100129675,0.013623085,0.005371454,0.0011805804,0.00052430056,0.00062033377,0.00011484374,0.00004657333],"genre_scores_gemma":[0.982743,0.0012473968,0.0142686665,0.00073405175,0.00023576056,0.00009641215,0.0004992414,0.000059387963,0.00011606438],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99796444,0.00012250552,0.0005970452,0.00039177042,0.00054889306,0.00037534907],"domain_scores_gemma":[0.9969478,0.0021035392,0.0001087975,0.00038706438,0.00006021297,0.00039256964],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005738764,0.00025728298,0.0004356172,0.00010711617,0.00011464379,0.00006130517,0.00022365754,0.000006747234,0.00014207113],"category_scores_gemma":[0.0017479721,0.00017112662,0.00014822013,0.00024933307,0.0002446159,0.000039625913,0.00007293844,0.00049072684,0.0000135868995],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00087630696,0.0019102086,0.5324359,0.0041822637,0.006482172,0.044278584,0.008044127,0.012632816,0.002602862,0.0024043988,0.076992124,0.30715823],"study_design_scores_gemma":[0.00460226,0.00036394596,0.16616367,0.007038906,0.006538485,0.00049866765,0.0013379597,0.73969406,0.004895843,0.0017182039,0.06607697,0.0010710083],"about_ca_topic_score_codex":0.00044156818,"about_ca_topic_score_gemma":0.00005495487,"teacher_disagreement_score":0.7270613,"about_ca_system_score_codex":0.00018190121,"about_ca_system_score_gemma":0.0008032615,"threshold_uncertainty_score":0.6978341},"labels":[],"label_agreement":null},{"id":"W4399482662","doi":"10.1136/annrheumdis-2024-eular.4358","title":"POS0038 ANATOMICAL DISTRIBUTION OF MRI LESIONS IN axSpA AND DIFFERENCES BETWEEN PATIENTS WITH AND WITHOUT PERIPHERAL INVOLVEMENT: RESULTS FROM THE ASAS CLASSIFICATION COHORT","year":2024,"lang":"en","type":"article","venue":"Annals of the Rheumatic Diseases","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Cohort; Peripheral; Medicine; Artificial intelligence; Computer science; Internal medicine","score_opus":0.030293040885788432,"score_gpt":0.306093030869206,"score_spread":0.27579998998341754,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399482662","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99145806,0.0009315033,0.0001309817,0.006754214,0.00003085764,0.00029466263,0.00036805234,0.000010162709,0.000021481692],"genre_scores_gemma":[0.99914676,0.00043810534,0.00004287883,0.000066724024,0.00001594978,0.000008122619,0.00026018813,0.0000069072908,0.000014344483],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9990685,0.00010109223,0.0003010082,0.00016599197,0.00026792032,0.00009550402],"domain_scores_gemma":[0.9992137,0.0003566146,0.00011218278,0.00019224157,0.000050624945,0.000074647636],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022381924,0.00008926568,0.00023933181,0.000026584687,0.00005552379,0.0000289858,0.00008833434,0.000026745485,0.0000046972823],"category_scores_gemma":[0.00057480717,0.000042787306,0.0000373876,0.00012103,0.00031316394,0.00005860071,0.000050596565,0.00012645501,1.854306e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000110112385,0.00008216024,0.98195934,0.00013119461,0.00012097769,2.3554449e-7,0.00036235814,0.0000032941027,0.0000063555844,0.0002456747,0.00046744783,0.016510833],"study_design_scores_gemma":[0.00066584186,0.00007208659,0.98540014,0.0019465388,0.00017865017,2.976821e-7,0.00018318224,0.010585568,0.000012924826,0.0008589059,0.000047736103,0.000048102665],"about_ca_topic_score_codex":0.00047421004,"about_ca_topic_score_gemma":0.000013197276,"teacher_disagreement_score":0.01646273,"about_ca_system_score_codex":0.000011393946,"about_ca_system_score_gemma":0.00005275784,"threshold_uncertainty_score":0.17448157},"labels":[],"label_agreement":null},{"id":"W4399519890","doi":"10.1200/jco.2024.42.16_suppl.e20083","title":"Multimodal risk stratification of non-metastatic lung adenocarcinoma using AI on histology and immunohistochemistry slides.","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre; Jewish General Hospital; McGill University","funders":"","keywords":"Medicine; Immunohistochemistry; Histology; Risk stratification; Adenocarcinoma; Pathology; Lung; Lung cancer; Oncology; Internal medicine; Cancer","score_opus":0.05037953881576407,"score_gpt":0.47601615692893307,"score_spread":0.425636618113169,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399519890","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97973675,0.0038240866,0.010146294,0.0045103217,0.0011329256,0.000115459065,0.0000028745426,0.000008233867,0.0005230805],"genre_scores_gemma":[0.9812759,0.00046345475,0.017102968,0.00056817004,0.00049028837,0.0000010912057,0.0000028228376,0.000017844317,0.000077434794],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973149,0.00025998498,0.0018153572,0.00020650076,0.00024782828,0.00015545748],"domain_scores_gemma":[0.99620575,0.0021222362,0.0010840769,0.00016225815,0.00019803032,0.00022765757],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028718677,0.00012169506,0.0010470811,0.00016179713,0.0000408159,0.000011174966,0.00010557557,0.00022170154,0.000058141955],"category_scores_gemma":[0.004529864,0.00009121337,0.00027349452,0.00010238577,0.00039691228,0.0000676698,0.00002700781,0.0019426782,0.0000023445466],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0041875136,0.0020319966,0.19229542,0.00142069,0.0019473874,0.00332516,0.0009711094,0.0010976546,0.100022644,0.0006772908,0.00685074,0.6851724],"study_design_scores_gemma":[0.008652906,0.009255333,0.29680422,0.0013704286,0.0029578176,0.004593602,0.00024932643,0.66858727,0.000984199,0.0014908331,0.0047847256,0.00026932947],"about_ca_topic_score_codex":0.000051287665,"about_ca_topic_score_gemma":6.764881e-7,"teacher_disagreement_score":0.6849031,"about_ca_system_score_codex":0.00017503893,"about_ca_system_score_gemma":0.001163595,"threshold_uncertainty_score":0.8440078},"labels":[],"label_agreement":null},{"id":"W4399548242","doi":"10.1186/s42492-024-00161-y","title":"Simulated deep CT characterization of liver metastases with high-resolution filtered back projection reconstruction","year":2024,"lang":"en","type":"article","venue":"Visual Computing for Industry Biomedicine and Art","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"National Science Foundation Graduate Research Fellowship Program; National Institute of Biomedical Imaging and Bioengineering; National Cancer Institute; National Institutes of Health; National Science Foundation","keywords":"Artificial intelligence; Computer science; Kernel (algebra); Artificial neural network; Pipeline (software); Projection (relational algebra); Fractal dimension; Pattern recognition (psychology); Fractal; Algorithm; Mathematics","score_opus":0.018135174615359215,"score_gpt":0.30201182961077516,"score_spread":0.2838766549954159,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399548242","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9625403,0.00014544098,0.035658475,0.0007310176,0.00034309295,0.0004223844,0.000012705198,0.00009244622,0.000054115928],"genre_scores_gemma":[0.99576795,0.000031472697,0.0026836644,0.00013966074,0.0005523222,0.0000028854522,0.0004938191,0.000023987768,0.00030421567],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990247,0.0000390932,0.00031593067,0.0002770454,0.00016666863,0.00017655334],"domain_scores_gemma":[0.9995243,0.0000939913,0.000116045405,0.00007540362,0.00009587657,0.0000943882],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032725872,0.00014357555,0.00028068852,0.00028303333,0.000090331705,0.00003159443,0.00002677573,0.00009537492,0.000049930728],"category_scores_gemma":[0.00007638336,0.00010460624,0.000040847714,0.00040625254,0.00016476646,0.00010478218,0.000019684565,0.00036815266,0.0000032318576],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006887578,0.0002810734,0.012483975,0.0027019407,0.000624159,0.00009735768,0.0005029311,0.00040105538,0.2697939,0.0002411856,0.0012590524,0.7109246],"study_design_scores_gemma":[0.0019893593,0.0018733422,0.015159892,0.002386658,0.00040265985,0.0009291111,0.00012248225,0.96130544,0.006992407,0.000016466063,0.008648036,0.00017415505],"about_ca_topic_score_codex":0.000053991484,"about_ca_topic_score_gemma":7.7998834e-7,"teacher_disagreement_score":0.96090436,"about_ca_system_score_codex":0.000029574823,"about_ca_system_score_gemma":0.00005923548,"threshold_uncertainty_score":0.42657185},"labels":[],"label_agreement":null},{"id":"W4399556881","doi":"10.1016/j.hpb.2024.04.066","title":"Comparing resection and stereotactic body radiation therapy for HCC with macrovascular invasion","year":2024,"lang":"en","type":"article","venue":"HPB","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network","funders":"","keywords":"Medicine; Stereotactic radiation therapy; Resection; Radiation therapy; Radiology; Oncology; Internal medicine; Radiosurgery; Surgery","score_opus":0.01941913233142881,"score_gpt":0.300518758486036,"score_spread":0.28109962615460715,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399556881","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97569203,0.0027862855,0.01973944,0.0009016956,0.0001880112,0.00034451674,3.7487683e-7,0.00007977252,0.00026788792],"genre_scores_gemma":[0.9969392,0.0005797456,0.0016181482,0.00027038017,0.0002550002,0.000022802393,0.000022469474,0.000022724917,0.00026952368],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999487,0.000020550013,0.00008842933,0.00017390141,0.00012279904,0.000107339554],"domain_scores_gemma":[0.9997325,0.00007296172,0.000018767054,0.00009296782,0.000022157932,0.00006067047],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027438567,0.00006778533,0.00012932855,0.00008071477,0.000068848305,0.000066292276,0.000019393226,0.000029734121,0.000013223958],"category_scores_gemma":[0.000056366327,0.000047555866,0.00003246167,0.0000860901,0.000026513986,0.00007784703,0.0000075796097,0.00016974693,0.0000032171588],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013138792,0.0001202571,0.17048673,0.0013121504,0.0005548579,0.00011520476,0.0015108086,0.00007802956,0.031020561,0.0007701362,0.004141522,0.7885759],"study_design_scores_gemma":[0.0044024414,0.0010711695,0.13775489,0.00070651004,0.00016762002,0.00042213273,0.00006733941,0.75172454,0.0015729835,0.00013260014,0.1017983,0.00017947181],"about_ca_topic_score_codex":0.000046163917,"about_ca_topic_score_gemma":0.0000030785727,"teacher_disagreement_score":0.7883964,"about_ca_system_score_codex":0.000033508008,"about_ca_system_score_gemma":0.00002971388,"threshold_uncertainty_score":0.1939272},"labels":[],"label_agreement":null},{"id":"W4399594865","doi":"10.3389/fbioe.2024.1368188","title":"Radiomics analysis using magnetic resonance imaging of bone marrow edema for diagnosing knee osteoarthritis","year":2024,"lang":"en","type":"article","venue":"Frontiers in Bioengineering and Biotechnology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Nomogram; Medicine; Magnetic resonance imaging; Osteoarthritis; Receiver operating characteristic; Area under the curve; Radiology; Radiomics; Radiography; Logistic regression; Bone marrow; Grading (engineering); Nuclear medicine; Internal medicine; Pathology","score_opus":0.004873287240449561,"score_gpt":0.2343827238841605,"score_spread":0.22950943664371096,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399594865","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5070956,0.17778352,0.3115465,0.0022867366,0.000788336,0.00028362908,0.000019186105,0.00018232671,0.000014217734],"genre_scores_gemma":[0.83039564,0.0017222004,0.16764559,0.000055693767,0.000081308484,0.000016486843,0.000013018477,0.00003485321,0.000035213936],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99883395,0.000012587095,0.00035928417,0.0003643366,0.00009580883,0.00033403686],"domain_scores_gemma":[0.9996018,0.000074118354,0.00004165544,0.00019501685,0.000021947133,0.00006547279],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031041648,0.00016850604,0.00055668486,0.0014200878,0.00003940668,0.00002718455,0.00006650068,0.00019283383,0.000003118318],"category_scores_gemma":[0.00022143169,0.0001674622,0.00013084678,0.0010211307,0.00023871384,0.00005046224,0.00004577922,0.0003569728,1.4618898e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006719235,0.000034696954,0.071248256,0.0006749546,0.00015336179,0.00023141663,0.0001610434,0.0012785251,0.03594335,0.00063151686,0.00040464097,0.88917106],"study_design_scores_gemma":[0.0009592669,0.00020977584,0.0028730442,0.00071464264,0.0004443183,0.00024458714,0.00015323635,0.98193896,0.0030638205,0.00021511687,0.008979678,0.0002035423],"about_ca_topic_score_codex":0.00003404855,"about_ca_topic_score_gemma":0.0000018437335,"teacher_disagreement_score":0.98066044,"about_ca_system_score_codex":0.00007833271,"about_ca_system_score_gemma":0.000032029835,"threshold_uncertainty_score":0.6828911},"labels":[],"label_agreement":null},{"id":"W4399603768","doi":"10.3390/cancers16122215","title":"Relating Macroscopic PET Radiomics Features to Microscopic Tumor Phenotypes Using a Stochastic Mathematical Model of Cellular Metabolism and Proliferation","year":2024,"lang":"en","type":"article","venue":"Cancers","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Canadian Institutes of Health Research","keywords":"Phenotype; Positron emission tomography; Cellular metabolism; Tumor microenvironment; In vivo; Computational biology; Pathology; Biology; Computer science; Tumor cells; Cancer research; Metabolism; Medicine; Gene; Genetics; Neuroscience","score_opus":0.013926192578764667,"score_gpt":0.296932975312569,"score_spread":0.28300678273380436,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399603768","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8095022,0.002466409,0.18701597,0.00036183753,0.00017482042,0.0003070218,0.0000072465655,0.000041696985,0.00012278737],"genre_scores_gemma":[0.95356244,0.000014613746,0.045586046,0.00035903617,0.00017186011,0.000013620214,0.000005238969,0.000036012938,0.00025112482],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991107,0.00001950199,0.0002442825,0.0002508278,0.00017621626,0.00019849591],"domain_scores_gemma":[0.9995799,0.000057226636,0.00004682456,0.00013041613,0.000037253383,0.00014839324],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019812018,0.00013365499,0.00032003914,0.0001252708,0.00006650234,0.00005242638,0.00005018564,0.00003471986,0.000011275784],"category_scores_gemma":[0.00023644224,0.00011375944,0.000046493325,0.00015097087,0.00009427957,0.000060430466,0.00003278307,0.00029518723,0.0000020945356],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006390985,0.000011583519,0.00010381392,0.0013638923,0.00009848693,0.000040138893,0.003243376,0.13229941,0.85561603,0.005155922,0.0002485393,0.0017549129],"study_design_scores_gemma":[0.00037929797,0.000038554994,0.00004860744,0.00092950655,0.00021197293,0.000101147554,0.00010125335,0.9882429,0.008551587,0.0012541321,0.000037918544,0.00010310484],"about_ca_topic_score_codex":0.00004450829,"about_ca_topic_score_gemma":0.0000011455759,"teacher_disagreement_score":0.8559435,"about_ca_system_score_codex":0.00023691617,"about_ca_system_score_gemma":0.00041830452,"threshold_uncertainty_score":0.46389753},"labels":[],"label_agreement":null},{"id":"W4399668294","doi":"10.3390/radiation4020015","title":"Deep Texture Analysis Enhanced MRI Radiomics for Predicting Head and Neck Cancer Treatment Outcomes with Machine Learning Classifiers","year":2024,"lang":"en","type":"article","venue":"Radiation","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Toronto Metropolitan University; Sunnybrook Health Science Centre","funders":"","keywords":"Artificial intelligence; Radiomics; Support vector machine; Computer science; Classifier (UML); Pattern recognition (psychology); Head and neck cancer; Boosting (machine learning); Feature selection; Feature (linguistics); Magnetic resonance imaging; Machine learning; Medicine; Radiology; Radiation therapy","score_opus":0.009199259163806069,"score_gpt":0.3044280582926168,"score_spread":0.2952287991288107,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399668294","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7874992,0.005454535,0.20006707,0.00581113,0.00022248806,0.00055138447,0.000015718882,0.00019227232,0.00018620945],"genre_scores_gemma":[0.9920268,0.0015237944,0.0045256163,0.0002644238,0.00028129396,0.00010155697,0.0002387945,0.000040449402,0.0009972901],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998988,0.00003316201,0.00021409473,0.0003591597,0.00017355105,0.00023203617],"domain_scores_gemma":[0.99941266,0.00020428872,0.000081846105,0.000117180505,0.000035488734,0.00014851578],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017919227,0.00018413168,0.00039093677,0.00027017095,0.00013488892,0.000085515974,0.000032641805,0.00008157554,0.000028761304],"category_scores_gemma":[0.00012165745,0.0001268013,0.00013527647,0.00039601038,0.000041583127,0.00009898156,0.000007508588,0.00026477955,0.0000011364392],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016905459,0.000046349753,0.64803416,0.00018601958,0.0024572772,0.000016664635,0.0026747012,0.038928483,0.0007275079,0.00012682183,0.00007733816,0.30655563],"study_design_scores_gemma":[0.0017624277,0.00036629726,0.08121008,0.000097680066,0.0019891714,0.000015781054,0.0001049533,0.90609556,0.00014021175,0.000016428627,0.008073237,0.000128146],"about_ca_topic_score_codex":0.00031610005,"about_ca_topic_score_gemma":0.00017217407,"teacher_disagreement_score":0.8671671,"about_ca_system_score_codex":0.0002985068,"about_ca_system_score_gemma":0.0000908195,"threshold_uncertainty_score":0.5170807},"labels":[],"label_agreement":null},{"id":"W4399737887","doi":"10.1200/jco.2024.42.16_suppl.2515","title":"Pan-tumor harmonization of pathologic response assessment for standardized data collection in neoadjuvant IO trials (PATHdata): Final analysis of a multi-institutional reproducibility study.","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Queen's University","funders":"Society for Immunotherapy of Cancer","keywords":"Medicine; Reproducibility; Harmonization; Medical physics; Oncology; Internal medicine; Nuclear medicine; Statistics","score_opus":0.38368616817211587,"score_gpt":0.5908749837485884,"score_spread":0.2071888155764725,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399737887","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8638016,0.00046882062,0.12992015,0.0038671424,0.0010453924,0.00075687544,0.00012014184,0.000008516807,0.0000113776405],"genre_scores_gemma":[0.93244815,0.00023308181,0.066785,0.00015028495,0.0002536946,0.000011481013,0.00007333757,0.000009221355,0.00003576036],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98932326,0.0041164868,0.0052010487,0.0006326056,0.0005706923,0.00015588489],"domain_scores_gemma":[0.9838703,0.011853237,0.0025828525,0.000781798,0.00077276805,0.00013901693],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.12893851,0.00013075708,0.0030327747,0.00071037695,0.0000443724,0.000014413794,0.00025606318,0.00016167863,0.000047473182],"category_scores_gemma":[0.19267814,0.000084323874,0.00062225113,0.0009684815,0.00026103237,0.00014216117,0.0001170086,0.0009045223,2.3057466e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.113618344,0.01823754,0.5043597,0.00043453235,0.007505776,0.0029689255,0.00085500703,0.0051814304,0.011796338,0.00013300241,0.0036077672,0.33130163],"study_design_scores_gemma":[0.0154951215,0.010231009,0.70556587,0.00021938892,0.005095201,0.00011648279,0.00025430715,0.25924525,0.0000674273,0.0001053581,0.003527028,0.0000775385],"about_ca_topic_score_codex":0.00005791283,"about_ca_topic_score_gemma":0.000049233786,"teacher_disagreement_score":0.3312241,"about_ca_system_score_codex":0.00031018766,"about_ca_system_score_gemma":0.005009826,"threshold_uncertainty_score":0.8969411},"labels":[],"label_agreement":null},{"id":"W4399762448","doi":"10.2463/mrms.rev.2023-0174","title":"Reproducible Research Practices in Magnetic Resonance Neuroimaging: A Review Informed by Advanced Language Models","year":2024,"lang":"en","type":"review","venue":"Magnetic Resonance in Medical Sciences","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal; Montreal Heart Institute","funders":"","keywords":"Medicine; Neuroimaging; Magnetic resonance imaging; Medical physics; Radiology; Psychiatry","score_opus":0.12202217168265103,"score_gpt":0.4878586616619054,"score_spread":0.36583648997925433,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399762448","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00020817899,0.9705201,0.0000025468546,0.014535934,0.00047915636,0.0025324493,0.000013496764,0.00010411628,0.011604015],"genre_scores_gemma":[0.00003826777,0.99071944,0.001230345,0.0020310946,0.00028718458,0.0007653772,0.000040639705,0.000090306334,0.0047973497],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9871801,0.0013786164,0.002310169,0.0027061151,0.004637373,0.0017876166],"domain_scores_gemma":[0.99488884,0.0023792197,0.0005455154,0.001374935,0.0001141849,0.00069730205],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.017702173,0.0007371954,0.002796359,0.0011513788,0.00018777263,0.00024186641,0.0020814918,0.00046834597,0.00071161846],"category_scores_gemma":[0.036578495,0.0005135786,0.00032174564,0.0071228594,0.0023446947,0.0004376779,0.00072504114,0.0061724395,0.00017362762],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015815223,0.00015590861,0.0000864337,0.029948922,0.0000030710855,0.001849405,0.00021993734,9.766862e-7,9.253196e-7,0.00022959802,0.032332137,0.9351569],"study_design_scores_gemma":[0.0005322141,0.0005013188,0.00004867828,0.1802756,0.00013054634,0.0005438896,0.000098703444,0.0059844707,2.5250662e-7,0.00040059345,0.8110817,0.0004020248],"about_ca_topic_score_codex":0.00096272596,"about_ca_topic_score_gemma":0.00015709098,"teacher_disagreement_score":0.93475485,"about_ca_system_score_codex":0.00040617224,"about_ca_system_score_gemma":0.0039958083,"threshold_uncertainty_score":0.9997316},"labels":[],"label_agreement":null},{"id":"W4399765528","doi":"10.32920/26052826.v1","title":"Quantitative Computed Tomography Imaging and Machine Learning for Evaluating Chronic Obstructive Pulmonary Disease","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Pulmonary disease; Computed tomography; Medicine; Quantitative computed tomography; Tomography; Radiology; Computer science; Internal medicine","score_opus":0.02679421758697185,"score_gpt":0.3480444189983911,"score_spread":0.32125020141141925,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399765528","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5606238,0.19127412,0.2057094,0.023324141,0.003975911,0.0066003986,0.00024765788,0.002009494,0.0062350803],"genre_scores_gemma":[0.94420713,0.0002575385,0.05251765,0.0004159605,0.00058577495,0.00020527215,0.00080809224,0.00016015307,0.00084241864],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99722236,0.00016127828,0.000536565,0.0011392604,0.0004491023,0.00049141847],"domain_scores_gemma":[0.99812645,0.0006001732,0.00023415615,0.00032723887,0.00024836833,0.0004636347],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0008614362,0.00051844184,0.00075279333,0.0005170072,0.0002577566,0.00019551665,0.00016016322,0.0001290453,0.000056606877],"category_scores_gemma":[0.0009649718,0.00044527583,0.00039240794,0.00023971446,0.00024628834,0.000058201593,0.0009592146,0.0025735705,0.000006586955],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022995383,0.00042167658,0.15066606,0.032817315,0.002889389,0.0015519349,0.002725311,0.026304372,0.00859566,0.020267334,0.0014642447,0.7499972],"study_design_scores_gemma":[0.0008105637,0.0001940767,0.019613877,0.0021610474,0.001032817,0.000091666225,0.00021444909,0.95809716,0.000031292435,0.016423916,0.00089288264,0.00043624852],"about_ca_topic_score_codex":0.00015338906,"about_ca_topic_score_gemma":0.0000031296881,"teacher_disagreement_score":0.9317928,"about_ca_system_score_codex":0.0002032427,"about_ca_system_score_gemma":0.00045198677,"threshold_uncertainty_score":0.9997999},"labels":[],"label_agreement":null},{"id":"W4399765579","doi":"10.32920/26052826","title":"Quantitative Computed Tomography Imaging and Machine Learning for Evaluating Chronic Obstructive Pulmonary Disease","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Pulmonary disease; Computed tomography; Medicine; Quantitative computed tomography; Tomography; Radiology; Computer science; Internal medicine","score_opus":0.02679421758697185,"score_gpt":0.3480444189983911,"score_spread":0.32125020141141925,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399765579","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5606238,0.19127412,0.2057094,0.023324141,0.003975911,0.0066003986,0.00024765788,0.002009494,0.0062350803],"genre_scores_gemma":[0.94420713,0.0002575385,0.05251765,0.0004159605,0.00058577495,0.00020527215,0.00080809224,0.00016015307,0.00084241864],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99722236,0.00016127828,0.000536565,0.0011392604,0.0004491023,0.00049141847],"domain_scores_gemma":[0.99812645,0.0006001732,0.00023415615,0.00032723887,0.00024836833,0.0004636347],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0008614362,0.00051844184,0.00075279333,0.0005170072,0.0002577566,0.00019551665,0.00016016322,0.0001290453,0.000056606877],"category_scores_gemma":[0.0009649718,0.00044527583,0.00039240794,0.00023971446,0.00024628834,0.000058201593,0.0009592146,0.0025735705,0.000006586955],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022995383,0.00042167658,0.15066606,0.032817315,0.002889389,0.0015519349,0.002725311,0.026304372,0.00859566,0.020267334,0.0014642447,0.7499972],"study_design_scores_gemma":[0.0008105637,0.0001940767,0.019613877,0.0021610474,0.001032817,0.000091666225,0.00021444909,0.95809716,0.000031292435,0.016423916,0.00089288264,0.00043624852],"about_ca_topic_score_codex":0.00015338906,"about_ca_topic_score_gemma":0.0000031296881,"teacher_disagreement_score":0.9317928,"about_ca_system_score_codex":0.0002032427,"about_ca_system_score_gemma":0.00045198677,"threshold_uncertainty_score":0.9997999},"labels":[],"label_agreement":null},{"id":"W4399826484","doi":"10.1177/10732748241264704","title":"Adaptive Cancer Therapy in the Age of Generative Artificial Intelligence","year":2024,"lang":"en","type":"article","venue":"Cancer Control","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"Toronto Metropolitan University","keywords":"Medicine; Artificial intelligence; Context (archaeology); Generative grammar; Disease; Machine learning; Computer science; Internal medicine","score_opus":0.04148395327002339,"score_gpt":0.3592394429347402,"score_spread":0.3177554896647168,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399826484","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.51446474,0.13628098,0.21012631,0.12828195,0.0030257716,0.0026003614,0.000094951465,0.0001349264,0.0049900315],"genre_scores_gemma":[0.99326944,0.001679442,0.00012795223,0.0039585396,0.0006391478,0.00018335797,0.0000029470136,0.000013725029,0.00012545177],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991711,0.000083247105,0.00021448202,0.00018036635,0.00019093149,0.00015992408],"domain_scores_gemma":[0.99958,0.0001850805,0.000033762743,0.000121495075,0.000045898596,0.000033741664],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033150509,0.00009671697,0.00023228381,0.000071166265,0.000027668573,0.000024225017,0.00010566594,0.000038320646,0.0001967761],"category_scores_gemma":[0.000059932514,0.000056759745,0.0000756449,0.00022871603,0.00014352152,0.00003435349,0.000006462279,0.00038563582,0.0000037451057],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003671172,0.000077843666,0.0026996504,0.000057014957,0.00023163825,0.0002604991,0.0069379406,0.002525289,0.025756555,0.011771612,0.001427653,0.9478872],"study_design_scores_gemma":[0.0024195649,0.0010854538,0.016371565,0.0017466706,0.0003461879,0.000041686646,0.002340038,0.8924396,0.010823743,0.0127750905,0.059121907,0.0004884746],"about_ca_topic_score_codex":0.00069860707,"about_ca_topic_score_gemma":0.000118980824,"teacher_disagreement_score":0.9473987,"about_ca_system_score_codex":0.00007112955,"about_ca_system_score_gemma":0.00020777763,"threshold_uncertainty_score":0.23145953},"labels":[],"label_agreement":null},{"id":"W4399843980","doi":"10.1515/9782760623347","title":"Radioscopie de l’information télévisée au Canada","year":2000,"lang":"fr","type":"book","venue":"Les Presses de l'Université de Montréal eBooks","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Geography; Political science","score_opus":0.003791062679914785,"score_gpt":0.18384626612977595,"score_spread":0.18005520344986117,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399843980","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028157093,0.008679766,0.004810275,0.0025455668,0.0012037475,0.0006975928,0.00019446656,0.00017984737,0.9535316],"genre_scores_gemma":[0.31936786,0.009454789,0.007065704,0.010595885,0.005513267,0.000049519145,0.001855607,0.00039558986,0.6457018],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9964512,0.00025698898,0.0005911886,0.0004502172,0.0007111803,0.0015392385],"domain_scores_gemma":[0.9972778,0.00042874244,0.00040353896,0.00061341794,0.000112780384,0.0011637347],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004169386,0.00068224734,0.0008359472,0.00023889083,0.00085396104,0.0000950162,0.00071182137,0.00076291664,0.0022542868],"category_scores_gemma":[0.00026243977,0.0007658124,0.0002854737,0.00006677022,0.00041414288,0.00018250098,0.0002892896,0.0020666055,0.000105620515],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00064711244,0.000052340125,0.008021852,0.0016819146,0.0007878033,0.00438056,0.004527214,0.0075702635,0.00037509482,0.0023344401,0.4243517,0.5452697],"study_design_scores_gemma":[0.0022303995,0.00014842088,0.009454863,0.0017221625,0.0010574189,0.0011796217,0.00041070202,0.027027594,0.000245464,0.00021631173,0.9556718,0.00063527946],"about_ca_topic_score_codex":0.90225834,"about_ca_topic_score_gemma":0.5257399,"teacher_disagreement_score":0.54463446,"about_ca_system_score_codex":0.01638638,"about_ca_system_score_gemma":0.009235837,"threshold_uncertainty_score":0.9994793},"labels":[],"label_agreement":null},{"id":"W4399852062","doi":"10.1101/2024.06.19.24308396","title":"Multi-task Bayesian Model Combining FDG-PET/CT Imaging and Clinical Data for Interpretable High-Grade Prostate Cancer Prognosis","year":2024,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke; Université Laval","funders":"","keywords":"Prostate cancer; Bayesian probability; Medicine; Artificial intelligence; Cancer; Medical physics; Computer science; Internal medicine","score_opus":0.04486002714107295,"score_gpt":0.38776520174740553,"score_spread":0.3429051746063326,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399852062","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8908863,0.011566758,0.056320954,0.031531695,0.0042618373,0.003610846,0.0010780309,0.00061174884,0.00013181963],"genre_scores_gemma":[0.9069333,0.0030193874,0.08587208,0.0013257709,0.000545796,0.00045234876,0.0008152298,0.00022527279,0.0008108026],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9957423,0.00014462482,0.0011056386,0.0018910486,0.00041692366,0.0006994715],"domain_scores_gemma":[0.99731225,0.00036081235,0.00035023657,0.0013432034,0.00013110289,0.00050242594],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0024002886,0.00057337916,0.0012513741,0.00024615094,0.00015730191,0.0002975016,0.0007391153,0.00007651352,0.000019679148],"category_scores_gemma":[0.0010766506,0.00048316998,0.00025785374,0.00014504176,0.00036855976,0.0001257626,0.0023997535,0.003074366,0.000006224854],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004429006,0.001077637,0.83514845,0.010967997,0.0026354059,0.0022836423,0.0013180836,0.005651208,0.0017136851,0.0001848521,0.024045613,0.114530526],"study_design_scores_gemma":[0.0022725572,0.00006334648,0.0029396706,0.003968458,0.0014549107,0.00019511342,0.00006134458,0.98320115,0.000038780927,0.0013265745,0.0040036105,0.00047449805],"about_ca_topic_score_codex":0.00054232206,"about_ca_topic_score_gemma":0.00003931549,"teacher_disagreement_score":0.9775499,"about_ca_system_score_codex":0.00011319802,"about_ca_system_score_gemma":0.0005598443,"threshold_uncertainty_score":0.999762},"labels":[],"label_agreement":null},{"id":"W4399855219","doi":"10.18280/isi.290324","title":"Hybrid Clustering-Based Technique to Isolate Tumors in PET/CT Images","year":2024,"lang":"fr","type":"article","venue":"Ingénierie des systèmes d information","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Cluster analysis; Artificial intelligence; Nuclear medicine; Computer science; Pattern recognition (psychology); Computer vision; Medicine","score_opus":0.007589828885319399,"score_gpt":0.265349048404181,"score_spread":0.2577592195188616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399855219","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09793765,0.0054578558,0.8644873,0.008359473,0.0048593865,0.002145182,0.000111799076,0.0007337268,0.015907627],"genre_scores_gemma":[0.9850319,0.00016255377,0.010661959,0.0023046308,0.00041001826,0.00022921356,0.00015654963,0.000064340325,0.0009788276],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972261,0.0001462204,0.0011240742,0.00030166868,0.00041407484,0.00078786473],"domain_scores_gemma":[0.9988175,0.0002038405,0.00015513829,0.0003407159,0.00013036528,0.00035243088],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0018068028,0.000384002,0.00050519546,0.0011401455,0.00014699563,0.0005591137,0.00024212278,0.000039697225,0.00024176796],"category_scores_gemma":[0.0009895478,0.00038809545,0.00015902429,0.0008126517,0.00025343677,0.0021298858,0.00011963556,0.0009788481,0.0007553556],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030848736,0.00018311145,0.0027898045,0.029478777,0.00019002907,0.010330626,0.0054975315,0.0804023,0.003845778,0.0031550976,0.01819607,0.84562236],"study_design_scores_gemma":[0.00082732027,0.0003949834,0.0016626368,0.02024693,0.0000896683,0.0053829383,0.0004032574,0.8287326,0.003118968,0.0013118843,0.13724321,0.0005855994],"about_ca_topic_score_codex":0.00077945367,"about_ca_topic_score_gemma":0.000018531955,"teacher_disagreement_score":0.88709426,"about_ca_system_score_codex":0.0012469647,"about_ca_system_score_gemma":0.000489759,"threshold_uncertainty_score":0.99985707},"labels":[],"label_agreement":null},{"id":"W4399867579","doi":"10.1007/s00261-024-04434-1","title":"The importance and future of prostate MRI report templates: improving oncological care","year":2024,"lang":"en","type":"review","venue":"Abdominal Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vancouver General Hospital; University of British Columbia","funders":"","keywords":"CLARITY; Medicine; Prostate cancer; Medical physics; Modalities; Cancer; Internal medicine","score_opus":0.015088108345972918,"score_gpt":0.3537356212375009,"score_spread":0.338647512891528,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399867579","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004738453,0.99509466,0.000022239214,0.0014532497,0.0010365675,0.0008824019,0.000011111434,0.00004670465,0.0009792232],"genre_scores_gemma":[0.00015983233,0.99626255,0.0011442661,0.00012695498,0.0015088378,0.00010001157,0.000102762184,0.00005721267,0.00053759944],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99749804,0.0001932404,0.0010668995,0.00063804846,0.00019562349,0.0004081731],"domain_scores_gemma":[0.9980573,0.0005666372,0.00062915526,0.00048133067,0.00009097102,0.00017457215],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010125443,0.0003995866,0.0020824696,0.00011402382,0.0001450806,0.000028671713,0.00021443966,0.00047789296,0.000015688156],"category_scores_gemma":[0.00054860354,0.0001984803,0.00040703567,0.0001912988,0.00064059906,0.000021876,0.00015678762,0.001674926,0.0000072567277],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000054487016,0.000010965486,0.00026466057,0.014081324,0.0002500429,0.003993015,0.0002058711,1.3315493e-7,0.00000284035,0.00038877304,0.0023493117,0.97839856],"study_design_scores_gemma":[0.00026906253,0.00042449796,0.000049170405,0.0026853725,0.0020098682,0.036232505,0.00035935792,0.000077692275,3.4829986e-7,0.000092661365,0.9576213,0.00017820127],"about_ca_topic_score_codex":0.000018811294,"about_ca_topic_score_gemma":0.0000043116324,"teacher_disagreement_score":0.9782204,"about_ca_system_score_codex":0.00014634959,"about_ca_system_score_gemma":0.000620866,"threshold_uncertainty_score":0.80937916},"labels":[],"label_agreement":null},{"id":"W4399880496","doi":"10.5194/essd-2024-218-rc1","title":"Comment on essd-2024-218","year":2024,"lang":"en","type":"peer-review","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science","score_opus":0.02632453653124437,"score_gpt":0.36785592370710507,"score_spread":0.3415313871758607,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399880496","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000001309098,0.03256899,0.00014695361,0.64721894,0.006611448,0.00042707732,0.000030003572,0.00015375776,0.31284153],"genre_scores_gemma":[0.00000863765,0.008991727,0.00080558687,0.3497887,0.0012980287,0.000037883852,0.0006443341,0.000071744784,0.63835335],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977704,0.00005624279,0.0004599236,0.00057127356,0.0007963633,0.00034576142],"domain_scores_gemma":[0.998734,0.00015831401,0.00008967256,0.000625991,0.00008296676,0.00030907217],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00069123274,0.00039223998,0.000965204,0.00019714054,0.000047998965,0.000050861323,0.00020694685,0.00021832774,0.010614178],"category_scores_gemma":[0.00046101602,0.00026220857,0.00030281127,0.00020076393,0.0000726052,0.000011902662,0.00014107469,0.0025300018,0.0024601072],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008356563,0.000099086086,0.0000036713843,0.008642792,0.00018606582,0.00028990608,0.000010848168,4.387108e-7,0.0000015421731,0.0012161381,0.9329998,0.05654134],"study_design_scores_gemma":[0.00042230426,0.00022310184,0.0000035271787,0.02702335,0.00080248836,0.00009981781,0.0000046593373,0.0012296776,0.000003945884,0.00020450704,0.9697371,0.00024548834],"about_ca_topic_score_codex":0.00015215322,"about_ca_topic_score_gemma":0.000003188312,"teacher_disagreement_score":0.3255118,"about_ca_system_score_codex":0.00017692447,"about_ca_system_score_gemma":0.00020261527,"threshold_uncertainty_score":0.999983},"labels":[],"label_agreement":null},{"id":"W4399973757","doi":"10.1016/j.radi.2024.06.010","title":"Nuclear medicine technologists practice impacted by AI denoising applications in PET/CT images","year":2024,"lang":"en","type":"article","venue":"Radiography","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Nuclear medicine; Medical physics; Medicine; Noise reduction; Artificial intelligence; Computer science","score_opus":0.00487728207846319,"score_gpt":0.313966926189471,"score_spread":0.3090896441110078,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399973757","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40498385,0.10113435,0.03279135,0.42092362,0.000996293,0.0030519913,0.00006244367,0.0046229525,0.031433173],"genre_scores_gemma":[0.9907487,0.002106853,0.00375795,0.002877592,0.00019545242,0.000038223276,0.00007985441,0.000070783215,0.00012460609],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99842256,0.00006286493,0.0003661138,0.00044645206,0.0003354058,0.00036662648],"domain_scores_gemma":[0.99896324,0.0003318014,0.00007154555,0.0003757568,0.000059710914,0.00019795308],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00059025385,0.00021445063,0.00036990322,0.0010898729,0.00010796991,0.00008222472,0.00018247233,0.000032455937,0.00009459383],"category_scores_gemma":[0.0006409045,0.00016773662,0.00014642415,0.0023191238,0.0004301749,0.00022410393,0.00003608398,0.0011305942,0.000025310306],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001772013,0.0009855839,0.06849195,0.0012357938,0.0011003304,0.009216679,0.0010631913,0.0000449235,0.12405834,0.012461946,0.6540691,0.12709492],"study_design_scores_gemma":[0.0013260888,0.00028065476,0.005711209,0.00095579383,0.00042948252,0.0049309507,0.0008908429,0.0057110093,0.0005219854,0.0010798689,0.97779924,0.0003628736],"about_ca_topic_score_codex":0.00038085034,"about_ca_topic_score_gemma":0.0000016572347,"teacher_disagreement_score":0.5857648,"about_ca_system_score_codex":0.000088159686,"about_ca_system_score_gemma":0.0000492911,"threshold_uncertainty_score":0.6840101},"labels":[],"label_agreement":null},{"id":"W4399998587","doi":"10.1016/j.compmedimag.2024.102413","title":"Radiomic-based prediction of lesion-specific systemic treatment response in metastatic disease","year":2024,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; Princess Margaret Cancer Centre; Public Health Ontario; Ontario Institute for Cancer Research; University of Toronto; University Health Network","funders":"Center for Scientific Review; National Cancer Institute; National Institutes of Health","keywords":"Medicine; Radiomics; Lesion; Radiology; Pathology","score_opus":0.02187002177830999,"score_gpt":0.3037242018003519,"score_spread":0.28185418002204193,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399998587","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87107486,0.022114737,0.09447064,0.010887695,0.0007800949,0.0004186515,0.000028344632,0.00020510146,0.000019867677],"genre_scores_gemma":[0.9938666,0.003001413,0.0022806276,0.00055197824,0.00014422437,0.00002716469,0.000061030256,0.000034032557,0.000032892323],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99794775,0.00029677083,0.0005476489,0.0004303075,0.0005132185,0.00026431878],"domain_scores_gemma":[0.9983074,0.00076981774,0.00006017869,0.0002653637,0.00004508899,0.0005521231],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012447275,0.00021438021,0.00050784135,0.00062872143,0.000055583492,0.000051043095,0.000093875824,0.000047986163,0.000023172224],"category_scores_gemma":[0.00033183343,0.00016315094,0.00015930817,0.00046620175,0.00037887503,0.00006413356,0.000035684756,0.00041078494,0.0000021801054],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008213736,0.0015002561,0.05722298,0.0045263837,0.00047596882,0.015972735,0.0016510481,0.00038868893,0.021392273,0.0035984279,0.0031340823,0.88192344],"study_design_scores_gemma":[0.0045992862,0.0002367176,0.021507295,0.0047489568,0.00016143924,0.0005956717,0.000048310358,0.95602435,0.000060453844,0.00022247618,0.011652186,0.00014285403],"about_ca_topic_score_codex":0.000035737572,"about_ca_topic_score_gemma":3.2167452e-7,"teacher_disagreement_score":0.95563567,"about_ca_system_score_codex":0.00009504947,"about_ca_system_score_gemma":0.0004654192,"threshold_uncertainty_score":0.6653102},"labels":[],"label_agreement":null},{"id":"W4400049373","doi":"10.1038/s41467-024-49017-2","title":"AI-based histopathology image analysis reveals a distinct subset of endometrial cancers","year":2024,"lang":"en","type":"article","venue":"Nature Communications","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":35,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia Hospital; Canada's Michael Smith Genome Sciences Centre; Vancouver General Hospital; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Terry Fox Research Institute; Michael Smith Health Research BC","keywords":"Histopathology; Endometrial cancer; Oncology; Biology; Internal medicine; Cancer; Pathology; Computational biology; Medicine; Bioinformatics","score_opus":0.015256048394701585,"score_gpt":0.3673189074628091,"score_spread":0.3520628590681075,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400049373","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33450964,0.18169154,0.08825975,0.3482948,0.003286503,0.0021611326,0.0009836884,0.0011315213,0.039681427],"genre_scores_gemma":[0.98011196,0.0002507556,0.017514093,0.0013286588,0.00009048409,0.000026116833,0.00045523138,0.000018112094,0.00020459737],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989176,0.00018900099,0.00032878717,0.00020295283,0.00021166496,0.00015002536],"domain_scores_gemma":[0.9975293,0.0008693438,0.000090294234,0.0012573269,0.00015653671,0.000097167],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00067510095,0.000105990744,0.00039860292,0.0006885258,0.000092379516,0.000022356473,0.00043337903,0.00016470949,0.00011664979],"category_scores_gemma":[0.001955838,0.00008962801,0.00028352792,0.0018987769,0.00035234398,0.0000395441,0.000091358685,0.0015388122,0.000007191055],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00078270375,0.0013191974,0.52304626,0.0015556642,0.0051556807,0.00051787397,0.002273982,0.00067919417,0.13353384,0.06294947,0.20597114,0.062215023],"study_design_scores_gemma":[0.0031667994,0.0003149761,0.20586875,0.00054484094,0.0082204705,0.000100217985,0.000085230124,0.2664085,0.0007741902,0.000899749,0.51313233,0.00048393753],"about_ca_topic_score_codex":0.00015680984,"about_ca_topic_score_gemma":0.00013392969,"teacher_disagreement_score":0.6456023,"about_ca_system_score_codex":0.00019441229,"about_ca_system_score_gemma":0.0002836649,"threshold_uncertainty_score":0.6685459},"labels":[],"label_agreement":null},{"id":"W4400058505","doi":"10.5194/essd-2024-218-rc2","title":"Comment on essd-2024-218","year":2024,"lang":"en","type":"peer-review","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science","score_opus":0.02632453653124437,"score_gpt":0.36785592370710507,"score_spread":0.3415313871758607,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400058505","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000001309098,0.03256899,0.00014695361,0.64721894,0.006611448,0.00042707732,0.000030003572,0.00015375776,0.31284153],"genre_scores_gemma":[0.00000863765,0.008991727,0.00080558687,0.3497887,0.0012980287,0.000037883852,0.0006443341,0.000071744784,0.63835335],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977704,0.00005624279,0.0004599236,0.00057127356,0.0007963633,0.00034576142],"domain_scores_gemma":[0.998734,0.00015831401,0.00008967256,0.000625991,0.00008296676,0.00030907217],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00069123274,0.00039223998,0.000965204,0.00019714054,0.000047998965,0.000050861323,0.00020694685,0.00021832774,0.010614178],"category_scores_gemma":[0.00046101602,0.00026220857,0.00030281127,0.00020076393,0.0000726052,0.000011902662,0.00014107469,0.0025300018,0.0024601072],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008356563,0.000099086086,0.0000036713843,0.008642792,0.00018606582,0.00028990608,0.000010848168,4.387108e-7,0.0000015421731,0.0012161381,0.9329998,0.05654134],"study_design_scores_gemma":[0.00042230426,0.00022310184,0.0000035271787,0.02702335,0.00080248836,0.00009981781,0.0000046593373,0.0012296776,0.000003945884,0.00020450704,0.9697371,0.00024548834],"about_ca_topic_score_codex":0.00015215322,"about_ca_topic_score_gemma":0.000003188312,"teacher_disagreement_score":0.3255118,"about_ca_system_score_codex":0.00017692447,"about_ca_system_score_gemma":0.00020261527,"threshold_uncertainty_score":0.999983},"labels":[],"label_agreement":null},{"id":"W4400073437","doi":"10.1007/s10278-024-01114-w","title":"Automated Segmentation of Lymph Nodes on Neck CT Scans Using Deep Learning","year":2024,"lang":"en","type":"article","venue":"Journal of Imaging Informatics in Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre","funders":"Fonds de Recherche du Québec - Santé; Fondation de l'Association des radiologistes du Québec; Réseau de cancérologie Rossy","keywords":"Lymph; Cervical lymph nodes; Segmentation; Lymph node; Context (archaeology); Computer science; Head and neck cancer; Medicine; Radiology; Artificial intelligence; Metastasis; Cancer; Pathology; Radiation therapy; Internal medicine","score_opus":0.013615294188680674,"score_gpt":0.34054315141602104,"score_spread":0.32692785722734036,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400073437","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95299625,0.0017703277,0.03886406,0.0022692946,0.001002835,0.000155123,0.0000010242621,0.000109734276,0.0028313748],"genre_scores_gemma":[0.9708655,0.00042431604,0.027485246,0.0008212696,0.00032235874,8.9930234e-7,0.000010042473,0.00003262084,0.00003774945],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99723357,0.0000676311,0.0015538837,0.000084655374,0.0008068364,0.0002534252],"domain_scores_gemma":[0.99855494,0.00031439163,0.0006268361,0.0001326852,0.00021598086,0.0001551688],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019512802,0.00018590568,0.00061219046,0.001159881,0.000054760567,0.0000384102,0.00014195264,0.000033759974,0.00005474705],"category_scores_gemma":[0.0014126333,0.00013233627,0.00010028541,0.00063428364,0.00020814277,0.00036658937,0.000029724866,0.00094980415,0.0000034313505],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004517266,0.00034314318,0.24797517,0.006714152,0.00066508964,0.002598655,0.0328858,0.24316716,0.030942956,0.0007427115,0.0043702954,0.42914313],"study_design_scores_gemma":[0.002435813,0.00021609016,0.005922785,0.009695734,0.00020327706,0.0025896986,0.004040656,0.9733852,0.0004979199,0.000094316834,0.00081031566,0.00010819299],"about_ca_topic_score_codex":0.000047887697,"about_ca_topic_score_gemma":2.6676227e-7,"teacher_disagreement_score":0.73021805,"about_ca_system_score_codex":0.0003039953,"about_ca_system_score_gemma":0.00021859743,"threshold_uncertainty_score":0.53965163},"labels":[],"label_agreement":null},{"id":"W4400122148","doi":"10.3390/jmp5030018","title":"Reply to Torlakovic, E.; Normanno, N. Comment on “Bisson et al. Novel Approach to Proficiency Testing Highlights Key Practice Variations in Cancer Biomarker Delivery. J. Mol. Pathol. 2024, 5, 1–10”","year":2024,"lang":"en","type":"article","venue":"Journal of Molecular Pathology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Queen Elizabeth II Health Sciences Centre; William Osler Health System","funders":"Pfizer Canada; Amgen Canada; AstraZeneca; Pfizer; Amgen","keywords":"Key (lock); Biomarker; Cancer; Medicine; Computer science; Internal medicine; Biology; Computer security; Genetics","score_opus":0.027510669323649317,"score_gpt":0.34280574428422866,"score_spread":0.31529507496057935,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400122148","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19864286,0.0016806049,0.16988207,0.61486983,0.0017750254,0.0009830047,0.000018981707,0.00006141317,0.012086199],"genre_scores_gemma":[0.4470968,0.00022329211,0.2148797,0.33663034,0.00031452667,0.000115787734,0.000020240699,0.00010712414,0.00061218377],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99756455,0.00030258676,0.000726273,0.00043303275,0.00059305807,0.00038050115],"domain_scores_gemma":[0.99837554,0.00034353833,0.00024712767,0.00028660148,0.0004338842,0.0003133013],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025194457,0.00022439196,0.000435999,0.0007275373,0.00007000042,0.000071798946,0.00020783827,0.00009171785,0.000029013592],"category_scores_gemma":[0.0032779896,0.00017978466,0.00011726621,0.0008186963,0.00003728617,0.00014197578,0.000105206804,0.0009710229,0.000025589485],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011607413,0.0039904797,0.0015340257,0.00032639745,0.00041826296,0.021526055,0.006346759,0.028117798,0.62700653,0.007449505,0.2656123,0.03651113],"study_design_scores_gemma":[0.0021957937,0.002384942,0.009842689,0.0014719475,0.00033407754,0.006871388,0.00023276574,0.04434112,0.0016964506,0.0000639588,0.9301391,0.0004257531],"about_ca_topic_score_codex":0.00014133287,"about_ca_topic_score_gemma":0.000001948111,"teacher_disagreement_score":0.6645268,"about_ca_system_score_codex":0.00031043732,"about_ca_system_score_gemma":0.00042602592,"threshold_uncertainty_score":0.7331406},"labels":[],"label_agreement":null},{"id":"W4400136483","doi":"10.1016/j.diii.2024.06.004","title":"Canadian radiology: 2024 update","year":2024,"lang":"en","type":"review","venue":"Diagnostic and Interventional Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Ottawa Hospital; Vancouver General Hospital; University of Ottawa; University of Toronto; University Health Network; McGill University Health Centre; University of British Columbia; Hospital for Sick Children; McMaster University","funders":"","keywords":"Medicine; Multidisciplinary approach; Radiology; Sustainability; Medical physics; Medical education","score_opus":0.01732918184754995,"score_gpt":0.35339372384570134,"score_spread":0.3360645419981514,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400136483","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000054120956,0.99127835,0.00022944958,0.003254773,0.0015622358,0.00034526337,0.000087167195,0.00005851133,0.0031788647],"genre_scores_gemma":[0.0001149873,0.9924959,0.00030978155,0.0009358521,0.0006583496,0.00007161821,0.0006680142,0.00007829582,0.0046672113],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99827045,0.00008045909,0.0005630577,0.00052050047,0.00016648971,0.00039901203],"domain_scores_gemma":[0.99876595,0.00039908066,0.00010104791,0.0001942399,0.00004567183,0.0004940269],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00039841692,0.00036682517,0.0010498993,0.00059793005,0.00009783104,0.00014201946,0.00013408929,0.00012970492,0.00091307244],"category_scores_gemma":[0.001102859,0.00027842415,0.0006434068,0.00019295957,0.00016227538,0.000065432934,0.000113232454,0.0011381862,0.00061810197],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001044388,0.000023921919,0.00032517625,0.010362574,0.00033496914,0.0010990188,0.000011258179,1.07211854e-7,2.56534e-8,0.002187928,0.12040533,0.8652486],"study_design_scores_gemma":[0.00015769756,0.000028800854,0.00006748379,0.042027596,0.002609742,0.003765286,0.000009740437,0.0005445393,1.7093004e-8,0.0006477586,0.9499074,0.00023391598],"about_ca_topic_score_codex":0.0031146358,"about_ca_topic_score_gemma":0.00022795422,"teacher_disagreement_score":0.86501473,"about_ca_system_score_codex":0.00026686586,"about_ca_system_score_gemma":0.00052880833,"threshold_uncertainty_score":0.9999668},"labels":[],"label_agreement":null},{"id":"W4400143742","doi":"10.1016/j.annonc.2024.05.055","title":"44P BOLD-100-001: A phase II study of BOLD-100 in combination with FOLFOX in advanced mCRC patients that have failed at least two prior lines of therapy","year":2024,"lang":"en","type":"article","venue":"Annals of Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Translational Research in Oncology; iCo Therapeutics (Canada); Innovative Targeting Solutions (Canada); McGill University; Princess Margaret Cancer Centre; University Health Network; Jewish General Hospital; McMaster University; Ottawa Regional Cancer Foundation; Ontario Clinical Oncology Group","funders":"","keywords":"Medicine; FOLFOX; Internal medicine; Oncology; Phases of clinical research; Oxaliplatin; Colorectal cancer; Chemotherapy; Cancer","score_opus":0.051525430029275766,"score_gpt":0.42209046439000353,"score_spread":0.37056503436072774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400143742","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99496526,0.0007514267,0.000026476084,0.002605815,0.00015993175,0.0010061106,0.000008266609,0.000018109922,0.00045860317],"genre_scores_gemma":[0.9987083,0.00035427723,0.00023241637,0.00036877743,0.00003293546,0.000051720766,0.000042714273,0.00002858563,0.00018025261],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9982634,0.00018307142,0.00064099516,0.00030946342,0.00035330091,0.00024977847],"domain_scores_gemma":[0.99891585,0.00024574788,0.00031565945,0.00021940228,0.00022603708,0.000077314275],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006415649,0.00017357664,0.0007882059,0.00045476068,0.000030097302,0.000004290585,0.00012982338,0.00009152344,0.00005024812],"category_scores_gemma":[0.00020220492,0.00013169079,0.000066656656,0.0003372271,0.0001543157,0.00010631472,0.00007290696,0.0003399725,0.0000010711203],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005509324,0.030948145,0.40127283,0.00030324105,0.00024347538,0.00020110386,0.010205099,0.00032469135,0.009157815,0.00009249267,0.00061550207,0.54112625],"study_design_scores_gemma":[0.18767841,0.21728076,0.5251937,0.0026721691,0.0002376852,0.000040488685,0.0050806203,0.023364171,0.01963377,0.00048003395,0.017715085,0.0006231062],"about_ca_topic_score_codex":0.0005133716,"about_ca_topic_score_gemma":0.00047689737,"teacher_disagreement_score":0.54050314,"about_ca_system_score_codex":0.00007163882,"about_ca_system_score_gemma":0.00015417548,"threshold_uncertainty_score":0.5370195},"labels":[],"label_agreement":null},{"id":"W4400151721","doi":"10.1016/j.annonc.2024.05.269","title":"263P PET-CT and MRI correlation of tumour regression grading in rectal carcinoma post neoadjuvant treatment","year":2024,"lang":"en","type":"article","venue":"Annals of Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Key Research and Development Program of China; Basic Research Program of Jiangsu Province; Government of Jiangsu Province","keywords":"Medicine; Rectal carcinoma; Grading (engineering); Neoadjuvant therapy; Radiology; Correlation; Colorectal cancer; Nuclear medicine; Oncology; Internal medicine; Cancer","score_opus":0.03306485543786184,"score_gpt":0.375535373696433,"score_spread":0.3424705182585711,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400151721","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98267126,0.002902707,0.000051468403,0.011506363,0.00025852307,0.00014897552,0.0000037583318,0.000015268766,0.0024416621],"genre_scores_gemma":[0.99804693,0.0009464924,0.00050825474,0.00019951256,0.00006847547,0.0000044844123,0.000021631118,0.000012249177,0.00019195877],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9991792,0.000086399676,0.00030056632,0.00018084742,0.000105422754,0.00014755073],"domain_scores_gemma":[0.99944896,0.0002507039,0.00009135816,0.000083812956,0.00004838831,0.000076757584],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003691554,0.0000939589,0.0003708596,0.00023027665,0.000019979863,0.000004384738,0.000032305765,0.000027334598,0.000025478876],"category_scores_gemma":[0.00021953105,0.00006785293,0.00006505205,0.00012809192,0.000094900024,0.000044751363,0.000023358743,0.00022309177,0.0000022505924],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006905882,0.00057561736,0.1982972,0.00050694816,0.00013785264,0.0074779377,0.0028483102,0.0001449731,0.07057148,0.0016258243,0.0032720612,0.7138512],"study_design_scores_gemma":[0.00674113,0.018664619,0.67214835,0.0036738385,0.00033033095,0.009109375,0.001499327,0.23222843,0.020330142,0.0014318537,0.033461776,0.0003808431],"about_ca_topic_score_codex":0.00049184385,"about_ca_topic_score_gemma":0.000020473011,"teacher_disagreement_score":0.71347034,"about_ca_system_score_codex":0.00006017178,"about_ca_system_score_gemma":0.00015887758,"threshold_uncertainty_score":0.2766962},"labels":[],"label_agreement":null},{"id":"W4400179266","doi":"10.1038/s41591-024-03126-z","title":"Author Correction: Prediction of recurrence risk in endometrial cancer with multimodal deep learning","year":2024,"lang":"en","type":"erratum","venue":"Nature Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Health Science Centre","funders":"","keywords":"Endometrial cancer; Medicine; Oncology; Deep learning; Internal medicine; Artificial intelligence; Cancer; Computer science","score_opus":0.00887847246085655,"score_gpt":0.3169642090176916,"score_spread":0.3080857365568351,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400179266","genre_codex":"editorial","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022171395,0.32050973,0.0053221905,0.024405971,0.5615769,0.0039686225,0.00024514346,0.00092921156,0.060870845],"genre_scores_gemma":[0.4864621,0.03925984,0.002488646,0.00097543333,0.063405566,0.00034743827,0.0033843562,0.00054976455,0.40312687],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99606174,0.0002481731,0.0008801039,0.00086721353,0.0014776648,0.0004651251],"domain_scores_gemma":[0.9977876,0.0005364053,0.0006407668,0.00038857877,0.0003647349,0.00028192578],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.001620513,0.00053109135,0.0014977047,0.0015529526,0.00009328886,0.000017253438,0.00021852588,0.0015044106,0.00046383627],"category_scores_gemma":[0.008777507,0.00035548708,0.00016403792,0.0020114153,0.00043480683,0.00006705164,0.00006659729,0.020323003,0.0000073876163],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013262032,0.00014102056,0.032092012,0.0018159016,0.00051768665,0.00045260886,0.0015890275,0.0005198242,0.00017259174,0.000022266915,0.7739293,0.18742153],"study_design_scores_gemma":[0.006946875,0.0023786207,0.02663142,0.023228066,0.0019364613,0.00034387913,0.00037372962,0.12523498,0.000052971543,0.00004685844,0.81244415,0.00038199523],"about_ca_topic_score_codex":0.0014657932,"about_ca_topic_score_gemma":0.00021849788,"teacher_disagreement_score":0.49817133,"about_ca_system_score_codex":0.0004182057,"about_ca_system_score_gemma":0.00059997424,"threshold_uncertainty_score":0.99988973},"labels":[],"label_agreement":null},{"id":"W4400230716","doi":"10.1109/iscas58744.2024.10558364","title":"MAGNet: A Convolutional Neural Network with Multi-Scale and Global Attention Modules for Medical Image Segmentation","year":2024,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Convolutional neural network; Computer science; Segmentation; Artificial intelligence; Image segmentation; Scale (ratio); Computer vision; Pattern recognition (psychology); Cartography","score_opus":0.008648454823366377,"score_gpt":0.3046119428632009,"score_spread":0.2959634880398345,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400230716","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37530467,0.0009888487,0.61009103,0.012187127,0.000301599,0.0004105073,0.000012989969,0.00015599266,0.00054720807],"genre_scores_gemma":[0.75339687,0.00007423133,0.24238415,0.0017904828,0.00080190506,0.00006333553,0.00023335125,0.000027037608,0.0012286273],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990725,0.000021947897,0.00016302627,0.00024894203,0.00029213825,0.00020144669],"domain_scores_gemma":[0.99961907,0.000067616085,0.00002026897,0.00006090888,0.00004544532,0.00018669254],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027415677,0.00010277571,0.0001431784,0.000026140518,0.000077480465,0.00006107957,0.000032647502,0.000056339963,0.00018523043],"category_scores_gemma":[0.000058011192,0.00007102947,0.00004754819,0.00010311302,0.00015980467,0.000097425254,0.000022218452,0.00015904124,0.0000060755983],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013554362,0.0005391584,0.34650797,0.002236512,0.00067000487,0.0005462423,0.0003477853,0.0011104642,0.01372327,0.019073995,0.0826612,0.53122795],"study_design_scores_gemma":[0.0020000474,0.00021175294,0.07198448,0.00017840939,0.000104570034,0.00046369902,0.00007203107,0.9232764,0.0000113621545,0.00024814866,0.0013605233,0.00008852865],"about_ca_topic_score_codex":0.00005783343,"about_ca_topic_score_gemma":0.000035862977,"teacher_disagreement_score":0.922166,"about_ca_system_score_codex":0.000046364723,"about_ca_system_score_gemma":0.00006235615,"threshold_uncertainty_score":0.28964975},"labels":[],"label_agreement":null},{"id":"W4400258896","doi":"10.5194/gmd-2024-15-rc1","title":"Comment on gmd-2024-15","year":2024,"lang":"en","type":"peer-review","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Mathematics; Statistics","score_opus":0.0267705886544134,"score_gpt":0.36479354036167155,"score_spread":0.33802295170725816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400258896","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000012861244,0.037266247,0.000106922525,0.6486517,0.0064253234,0.0004233492,0.000029946432,0.00015038942,0.30694482],"genre_scores_gemma":[0.000012351922,0.008463814,0.000580052,0.3654726,0.0013083433,0.000030933512,0.000667684,0.00006772411,0.6233965],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99780273,0.000055043914,0.0004527573,0.0005540832,0.0007963907,0.00033898896],"domain_scores_gemma":[0.99874854,0.00015371421,0.00008561059,0.0006198953,0.000078991965,0.00031324418],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0006914507,0.00038177095,0.00094132207,0.00019669425,0.000045283414,0.000047751215,0.00019840388,0.00021146193,0.0104867695],"category_scores_gemma":[0.00048431449,0.00025451754,0.00037715674,0.00019667306,0.00006764762,0.0000111788095,0.00013632516,0.002517928,0.0028098994],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007675661,0.00007351266,0.000005543738,0.008115863,0.00018186723,0.00029079453,0.000010924316,6.4191977e-7,0.0000014950342,0.00091267336,0.950814,0.039585017],"study_design_scores_gemma":[0.00032707828,0.00020274668,0.000004496987,0.025494147,0.0007700351,0.00010628564,0.000007192695,0.00070434733,0.0000040726095,0.00017423378,0.97196746,0.00023788214],"about_ca_topic_score_codex":0.00015317317,"about_ca_topic_score_gemma":0.00000351855,"teacher_disagreement_score":0.31645167,"about_ca_system_score_codex":0.00017362517,"about_ca_system_score_gemma":0.0002023321,"threshold_uncertainty_score":0.9999907},"labels":[],"label_agreement":null},{"id":"W4400261369","doi":"10.3389/fonc.2024.1444543","title":"Editorial: Machine learning in radiation therapy for lung cancer","year":2024,"lang":"en","type":"editorial","venue":"Frontiers in Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto; University Health Network","funders":"","keywords":"Lung cancer; Radiation therapy; Medicine; Medical physics; Cancer; Oncology; Radiology; Internal medicine","score_opus":0.0061666477678333515,"score_gpt":0.3439718252924609,"score_spread":0.3378051775246275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400261369","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00013168955,0.040756498,0.0012928696,0.0036343727,0.9525045,0.0010347884,0.00005139426,0.000099733836,0.0004941197],"genre_scores_gemma":[0.00008031798,0.019211236,0.0031488587,0.00027532887,0.9725874,0.0006167768,0.00097577606,0.00014704964,0.002957246],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.997394,0.00022775069,0.0006429463,0.0006760308,0.000505589,0.0005536491],"domain_scores_gemma":[0.99841523,0.00089302426,0.00024234323,0.00019447491,0.0001224183,0.00013250754],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.0016544812,0.00035128836,0.0012004435,0.00082312984,0.000055750737,0.00003810975,0.00022334613,0.0016517589,0.000039712744],"category_scores_gemma":[0.0031743855,0.000323215,0.00018577928,0.00035594657,0.000102233076,0.000057826,0.000050540923,0.004466622,0.0000024911526],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008110617,0.00009719618,0.008012978,0.0004124115,0.00012614144,0.00006211614,0.00043850325,0.0004502044,0.000017457325,0.000005739327,0.8709234,0.11864277],"study_design_scores_gemma":[0.0057952516,0.000516065,0.00007243159,0.00036336816,0.0001304161,0.0000020811729,0.00003005506,0.085077606,0.0000029038665,0.00018807789,0.9075728,0.00024891624],"about_ca_topic_score_codex":0.0008900956,"about_ca_topic_score_gemma":0.00011488143,"teacher_disagreement_score":0.11839385,"about_ca_system_score_codex":0.0023060923,"about_ca_system_score_gemma":0.002000807,"threshold_uncertainty_score":0.999922},"labels":[],"label_agreement":null},{"id":"W4400315292","doi":"10.1109/isivc61350.2024.10577878","title":"Automatic Lung Segmentation in Chest X-Ray Images using Dilated Dense-ResUNet","year":2024,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan; Toronto Metropolitan University","funders":"","keywords":"Computer science; Lung; Segmentation; Image segmentation; Artificial intelligence; Computer vision; Radiology; Medicine; Internal medicine","score_opus":0.012757746577063448,"score_gpt":0.32810406208406107,"score_spread":0.3153463155069976,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400315292","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9781709,0.0008611601,0.014980546,0.0025366468,0.0003049482,0.00025223484,9.853939e-7,0.00028153264,0.0026110949],"genre_scores_gemma":[0.97533095,0.000037783087,0.023017403,0.0004696563,0.00011256352,0.000006237318,0.000025640886,0.000028385952,0.00097135245],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99909836,0.000040149724,0.00025968612,0.0002077455,0.00019569421,0.0001983785],"domain_scores_gemma":[0.9996677,0.000092571136,0.000024475952,0.00011083734,0.000018149849,0.00008626968],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034926407,0.00010814005,0.00018117676,0.00021383572,0.00003442161,0.00007656252,0.000042542502,0.000049132534,0.00059696287],"category_scores_gemma":[0.00014564265,0.00008471836,0.000045442466,0.0003172638,0.000044257627,0.000115924464,0.000021283915,0.0003117497,0.000032410462],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000052941494,0.00027793538,0.11958727,0.0032658118,0.0003370216,0.00268005,0.0035431792,0.004125041,0.6278687,0.0006521184,0.021586673,0.21602327],"study_design_scores_gemma":[0.00053388154,0.000023465682,0.030424153,0.000597469,0.00008162646,0.00009223926,0.00012660776,0.9660723,0.0014077298,0.00006270127,0.00047940173,0.00009837881],"about_ca_topic_score_codex":0.000247358,"about_ca_topic_score_gemma":0.0000041336625,"teacher_disagreement_score":0.9619473,"about_ca_system_score_codex":0.000112157824,"about_ca_system_score_gemma":0.00008119586,"threshold_uncertainty_score":0.65363246},"labels":[],"label_agreement":null},{"id":"W4400353080","doi":"10.1101/2024.07.04.24309964","title":"Radiomic-Based Approaches in the Multi-metastatic Setting: A Quantitative Review","year":2024,"lang":"en","type":"review","venue":"medRxiv","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto; Queen's University; University Health Network","funders":"","keywords":"Computer science; Medicine; Medical physics","score_opus":0.173241489952689,"score_gpt":0.4266973014503644,"score_spread":0.2534558114976754,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400353080","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000009892786,0.9906738,0.0008341576,0.0053824983,0.00025332771,0.0023372057,0.000015921183,0.00007616446,0.0004170689],"genre_scores_gemma":[0.000014027872,0.98417646,0.012096745,0.0025007955,0.00012665066,0.0004775399,0.0002054019,0.00011938823,0.00028296886],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.996087,0.0011855433,0.0010884939,0.00068790244,0.00051807624,0.0004329517],"domain_scores_gemma":[0.9976521,0.0011189701,0.00034297223,0.00071162963,0.00003066999,0.00014363245],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.004612932,0.0005703136,0.0025311022,0.0004154113,0.0000613145,0.0000655981,0.0005195408,0.00012775653,0.00004285392],"category_scores_gemma":[0.00278301,0.00029472285,0.00085649785,0.0011507361,0.00020307658,0.000034206485,0.000059812148,0.002356157,0.00025081713],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005173874,0.0002063251,0.00006906994,0.30484957,0.00029632275,0.0009832657,0.00029283072,0.0000027455935,2.9823275e-7,0.00042160737,0.0054657925,0.687407],"study_design_scores_gemma":[0.000378446,0.000063212,0.000013030323,0.16952032,0.004135491,0.00034044002,0.000051685132,0.006618851,6.790437e-8,0.000016292222,0.818614,0.00024813492],"about_ca_topic_score_codex":0.000016452277,"about_ca_topic_score_gemma":0.0000030243289,"teacher_disagreement_score":0.81314826,"about_ca_system_score_codex":0.00012207738,"about_ca_system_score_gemma":0.000586666,"threshold_uncertainty_score":0.99995047},"labels":[],"label_agreement":null},{"id":"W4400427682","doi":"10.1038/s44303-024-00026-2","title":"Author Correction: Artificial intelligence unravels interpretable malignancy grades of prostate cancer on histology images","year":2024,"lang":"en","type":"article","venue":"npj Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Centre Hospitalier de l’Université de Montréal","funders":"","keywords":"Prostate cancer; Malignancy; Artificial intelligence; Prostate; Medicine; Computer science; Cancer; Pathology; Internal medicine","score_opus":0.019517738820647706,"score_gpt":0.3431405216929636,"score_spread":0.3236227828723159,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400427682","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29728422,0.04851703,0.41932002,0.1513137,0.04052329,0.0021101302,0.00006720486,0.001449602,0.03941481],"genre_scores_gemma":[0.99289244,0.00017671507,0.0015781192,0.00060684554,0.00032324938,0.00003383687,0.000007887818,0.000043171316,0.0043377117],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985742,0.000054999993,0.00041229595,0.00039802914,0.00024078837,0.00031966154],"domain_scores_gemma":[0.9993517,0.0001613836,0.0000864955,0.00020895504,0.00008012324,0.000111375535],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035221977,0.00017893956,0.00033423014,0.0002799932,0.00007832846,0.000060679427,0.00010907461,0.000044911376,0.00037747237],"category_scores_gemma":[0.00030383345,0.00015125092,0.000113171154,0.00031391197,0.00025453581,0.00009012642,0.000045096356,0.0005950819,0.00003665464],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012851531,0.000095572876,0.008912397,0.0004558265,0.00008586544,0.0003529492,0.002188255,0.00043130276,0.032620788,0.0033973912,0.008924854,0.9424063],"study_design_scores_gemma":[0.0003387016,0.00041984406,0.0041575003,0.0068005873,0.0004351998,0.0009611545,0.0013289074,0.78496236,0.13488404,0.0089434795,0.056143664,0.0006245827],"about_ca_topic_score_codex":0.00026298448,"about_ca_topic_score_gemma":0.000004161815,"teacher_disagreement_score":0.9417817,"about_ca_system_score_codex":0.00013858982,"about_ca_system_score_gemma":0.00015000229,"threshold_uncertainty_score":0.6167833},"labels":[],"label_agreement":null},{"id":"W4400433113","doi":"10.1093/mam/ozae057","title":"Bridging Histopathology and Radiomics Toward Prognosis of Metastasis in Early Breast Cancer","year":2024,"lang":"en","type":"article","venue":"Microscopy and Microanalysis","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Radiomics; Histopathology; Feature selection; Breast cancer; Medicine; Artificial intelligence; Oncology; Radiology; Cancer; Internal medicine; Pathology; Computer science","score_opus":0.01025818093090576,"score_gpt":0.2999705673691017,"score_spread":0.28971238643819597,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400433113","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96583664,0.027398735,0.0021267666,0.0043013524,0.00009206155,0.00012630069,0.000047925067,0.000028725779,0.00004146374],"genre_scores_gemma":[0.9914874,0.004247661,0.0036957806,0.00027875553,0.00005961779,0.000014284729,0.000012290666,0.000025313982,0.0001789359],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9988341,0.000057047848,0.00035662725,0.0004058012,0.00009956517,0.00024688398],"domain_scores_gemma":[0.9996039,0.00005220503,0.000063500804,0.00012649292,0.000039602168,0.000114245224],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004321355,0.00016658926,0.0005731542,0.0004974312,0.000043627802,0.00005170094,0.00005904091,0.00007921909,0.000043563115],"category_scores_gemma":[0.000034831002,0.00014332788,0.00012010545,0.00047307595,0.0002578928,0.00007685168,0.00005824807,0.00032334914,0.0000013437416],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009228515,0.0000670083,0.38741922,0.00071905775,0.00033232386,0.00017227665,0.002052982,0.000008350739,0.45186412,0.000069267866,0.00030201307,0.15690108],"study_design_scores_gemma":[0.004047891,0.00032255767,0.83480287,0.002908164,0.0074519967,0.003442805,0.0006748202,0.0457614,0.09017021,0.00022033336,0.0091954535,0.0010014945],"about_ca_topic_score_codex":0.0016760667,"about_ca_topic_score_gemma":0.00003376402,"teacher_disagreement_score":0.44738364,"about_ca_system_score_codex":0.00007035875,"about_ca_system_score_gemma":0.00007357869,"threshold_uncertainty_score":0.58447415},"labels":[],"label_agreement":null},{"id":"W4400452630","doi":"10.1016/j.jtho.2024.05.355","title":"PP01.132 Auto-Segmentation of Lung Tumors Using Deep Learning Engines","year":2024,"lang":"en","type":"article","venue":"Journal of Thoracic Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Science North","funders":"","keywords":"Medicine; Segmentation; Artificial intelligence; Lung; Deep learning; Radiology; Internal medicine; Computer science","score_opus":0.01693927514831196,"score_gpt":0.42149560159889343,"score_spread":0.4045563264505815,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400452630","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93572396,0.004140643,0.05527769,0.0025661858,0.0013216999,0.000100438185,4.5591523e-7,0.000032984866,0.00083597173],"genre_scores_gemma":[0.96696603,0.00020098253,0.031629696,0.00016731033,0.00072901626,9.119741e-7,0.0000030524618,0.000028125427,0.0002748652],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985374,0.00018291434,0.0006585174,0.00012359276,0.00030589695,0.00019166918],"domain_scores_gemma":[0.9989148,0.0002953086,0.00040523373,0.00007524948,0.00016785582,0.0001416006],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013169231,0.000114504495,0.00050051673,0.0004295522,0.00005200921,0.000023222445,0.00009562582,0.00009913787,0.00014474092],"category_scores_gemma":[0.0006293481,0.00008932651,0.0001812546,0.00027208196,0.0000901216,0.00014865803,0.000032250024,0.0009644405,0.000003812432],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047438,0.00018812207,0.015189402,0.0011999388,0.00047172373,0.002291031,0.0027391117,0.012394091,0.18082815,0.00016711983,0.00072362216,0.7833333],"study_design_scores_gemma":[0.0009555129,0.0017249399,0.008164391,0.0022467847,0.0012793541,0.010127689,0.001292999,0.9437196,0.006191318,0.0003028211,0.023791406,0.00020314503],"about_ca_topic_score_codex":0.000013285351,"about_ca_topic_score_gemma":5.949709e-7,"teacher_disagreement_score":0.93132555,"about_ca_system_score_codex":0.00028992846,"about_ca_system_score_gemma":0.00035740592,"threshold_uncertainty_score":0.4190068},"labels":[],"label_agreement":null},{"id":"W4400452750","doi":"10.1016/j.jtho.2024.05.257","title":"PP01.10 Real-World Outcomes of Patients with Advanced EGFR-Mutated NSCLC in Canada Using AI-Extracted Data","year":2024,"lang":"en","type":"article","venue":"Journal of Thoracic Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University Health Network; Princess Margaret Cancer Centre; Centre for Social Innovation","funders":"","keywords":"Medicine; Oncology; Internal medicine; Real world data; Data science","score_opus":0.022406640428778324,"score_gpt":0.42191355811423026,"score_spread":0.39950691768545193,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400452750","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9937044,0.0002810096,0.00032965816,0.004129551,0.0007672002,0.00015592677,0.000023650122,0.00001019554,0.0005984335],"genre_scores_gemma":[0.9910449,0.000055017637,0.007994464,0.0005414618,0.000100395926,6.8960435e-7,0.000050876402,0.00003007784,0.00018212787],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99807376,0.00015424233,0.0008340826,0.00020599883,0.00046941979,0.00026248235],"domain_scores_gemma":[0.99839115,0.00038961112,0.00047992176,0.00028858,0.0002624492,0.00018830934],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007188837,0.00015133541,0.0007925555,0.0004192581,0.000026103711,0.000013084012,0.0002699609,0.00006403175,0.00014747308],"category_scores_gemma":[0.0005601395,0.00010271846,0.000053034957,0.00050911406,0.00007889971,0.00023435085,0.00007863283,0.0010100938,0.0000010680164],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0026164285,0.00036170942,0.69204456,0.00033790283,0.0005126564,0.0036180639,0.00021342754,0.0021007813,0.0013073889,0.00001435766,0.0033675265,0.2935052],"study_design_scores_gemma":[0.0031518561,0.0011019987,0.9155604,0.0016996049,0.0007453573,0.00039084835,0.00026804683,0.048910264,0.00015751312,0.000052507374,0.027724044,0.00023752228],"about_ca_topic_score_codex":0.084661126,"about_ca_topic_score_gemma":0.13946193,"teacher_disagreement_score":0.29326767,"about_ca_system_score_codex":0.0013632374,"about_ca_system_score_gemma":0.0050048064,"threshold_uncertainty_score":0.9214342},"labels":[],"label_agreement":null},{"id":"W4400452878","doi":"10.1016/j.jtho.2024.05.265","title":"PP01.19 Comparison of A.I. Models in Lung Cancer Staging and Subtyping","year":2024,"lang":"en","type":"article","venue":"Journal of Thoracic Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Milton District Hospital","funders":"","keywords":"Subtyping; Medicine; Lung cancer; Lung; Oncology; Internal medicine; Programming language","score_opus":0.0329563464470569,"score_gpt":0.4839581926622077,"score_spread":0.45100184621515077,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400452878","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94759643,0.026009843,0.013908354,0.01068102,0.0006474991,0.00008441452,8.832777e-7,0.00000996156,0.0010616127],"genre_scores_gemma":[0.99416137,0.0010345145,0.004120379,0.00030687056,0.00024842663,0.0000015340092,5.606904e-7,0.000014389669,0.00011197492],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99885005,0.00010367616,0.0005760795,0.000113022,0.00019258639,0.00016456994],"domain_scores_gemma":[0.99923617,0.00025512007,0.0002327363,0.00006473201,0.00007635204,0.00013490919],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011189111,0.00008311984,0.0005625186,0.0003781315,0.000021922704,0.000015070325,0.00007142166,0.00008414436,0.000039164363],"category_scores_gemma":[0.00017708445,0.00006489355,0.00006976,0.00018992656,0.00008617294,0.00012288378,0.000036954796,0.00090113725,2.9701684e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00073504733,0.00020944283,0.257001,0.001914691,0.00025782303,0.0010486662,0.006633578,0.015161109,0.0062762955,0.0004399988,0.0029332496,0.7073891],"study_design_scores_gemma":[0.00068024057,0.00035686765,0.012350803,0.002226143,0.00028127735,0.00059980695,0.0008105654,0.97346914,0.0002991746,0.00095750886,0.007879368,0.00008913577],"about_ca_topic_score_codex":0.000102496895,"about_ca_topic_score_gemma":0.000012394565,"teacher_disagreement_score":0.958308,"about_ca_system_score_codex":0.0002417442,"about_ca_system_score_gemma":0.00038537357,"threshold_uncertainty_score":0.39150432},"labels":[],"label_agreement":null},{"id":"W4400494807","doi":"10.1007/978-981-97-3545-7_11","title":"Computational Designing in Nanomedicine","year":2024,"lang":"en","type":"book-chapter","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Laurentian University","funders":"","keywords":"Nanomedicine; Computer science; Nanotechnology; Materials science; Nanoparticle","score_opus":0.01526212939708944,"score_gpt":0.28871445318165967,"score_spread":0.27345232378457024,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400494807","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000058913563,0.0019855327,0.004125689,0.006547111,0.0003418581,0.00022073957,0.0000021111127,0.000120963596,0.98659706],"genre_scores_gemma":[0.008301859,0.00013252329,0.009999914,0.0027300266,0.0004942778,0.000004401146,0.00013847389,0.00008835386,0.9781102],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99876124,0.0000045466613,0.00036513578,0.00033065208,0.00036333877,0.00017507054],"domain_scores_gemma":[0.9995114,0.00012283587,0.00005141332,0.0001324103,0.000039862673,0.00014207784],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00028556742,0.00021739643,0.00045603522,0.0004348669,0.000020251611,0.000018333323,0.00006267224,0.00017706495,0.001856265],"category_scores_gemma":[0.000055775046,0.00017230496,0.000105537896,0.00004343247,0.0001068528,0.00002029493,0.000045099816,0.0011100947,0.0004404772],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006928182,0.00004797782,0.00053890917,0.0010176618,0.00033813043,0.004607682,0.00030130814,0.0011084735,0.000137907,0.8878128,0.04289537,0.061124507],"study_design_scores_gemma":[0.0018040269,0.00024387223,0.000329423,0.005838234,0.0003072829,0.00078378845,0.000027164708,0.07053258,0.0000065572212,0.17252347,0.74713755,0.0004660486],"about_ca_topic_score_codex":0.000017098144,"about_ca_topic_score_gemma":0.0000020684308,"teacher_disagreement_score":0.7152893,"about_ca_system_score_codex":0.00012504151,"about_ca_system_score_gemma":0.00015208001,"threshold_uncertainty_score":0.99905616},"labels":[],"label_agreement":null},{"id":"W4400572999","doi":"10.1093/oncolo/oyae172","title":"It is time to rethink randomized clinical trial approaches","year":2024,"lang":"en","type":"letter","venue":"The Oncologist","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"BATES; Randomized controlled trial; Clinical trial; Psychology; Medical physics; Medicine; Engineering; Internal medicine","score_opus":0.1228221381364503,"score_gpt":0.4079856865953792,"score_spread":0.2851635484589289,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400572999","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00008148799,0.00043226505,0.00028763324,0.89018583,0.0025257193,0.002841309,0.000017981578,0.00021090626,0.103416845],"genre_scores_gemma":[0.000040085342,0.00011696915,0.0016066085,0.7939653,0.022821976,0.00022594367,0.00018225747,0.0000939022,0.18094698],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.994833,0.0018115212,0.0012802039,0.00080795994,0.00074023823,0.0005271068],"domain_scores_gemma":[0.99253935,0.005884126,0.0003329966,0.0009808319,0.00006166697,0.00020102542],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.012549695,0.00044322736,0.0023895456,0.00014380811,0.00013703275,0.0001504406,0.00068156223,0.0012858934,0.0019478492],"category_scores_gemma":[0.010041318,0.00023106173,0.0012004825,0.0002285171,0.0013353347,0.000019651732,0.00032637682,0.008687273,0.006535191],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.09040975,0.00006630756,7.8238486e-7,0.00012016585,0.0005435286,0.00089356524,0.00031529812,0.0000017732904,0.0000011173196,0.000017452043,0.8972538,0.01037647],"study_design_scores_gemma":[0.17633694,0.00057086407,7.6071115e-7,0.00025019675,0.0014521573,0.00013225847,0.00001154501,0.0038522452,6.943472e-7,0.00063157984,0.8165426,0.00021810981],"about_ca_topic_score_codex":0.0000425075,"about_ca_topic_score_gemma":7.8614295e-7,"teacher_disagreement_score":0.096220575,"about_ca_system_score_codex":0.00018573986,"about_ca_system_score_gemma":0.00052012585,"threshold_uncertainty_score":0.9989645},"labels":[],"label_agreement":null},{"id":"W4400592592","doi":"10.1002/msd2.12119","title":"Letter of thanks for <i>IJMSD</i>'s JCR debut in 2024","year":2024,"lang":"en","type":"article","venue":"International journal of mechanical system dynamics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Art","score_opus":0.008480385225177722,"score_gpt":0.3040621743192465,"score_spread":0.29558178909406874,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400592592","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20607741,0.0012211581,0.7379236,0.03681411,0.015025264,0.00048395075,0.00007181893,0.00005214372,0.0023305032],"genre_scores_gemma":[0.9920199,0.00004343152,0.0058046407,0.00063710316,0.0010684436,0.00000517921,0.0000114788245,0.000026028669,0.00038377428],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99824315,0.000043863514,0.00081422547,0.00014096969,0.00060968637,0.00014810091],"domain_scores_gemma":[0.998986,0.00031265288,0.00021089663,0.0000894487,0.00029741458,0.000103599705],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011069794,0.00010737683,0.0003745337,0.00031965098,0.000010555371,0.000042033993,0.00027312763,0.00009999901,0.000028500248],"category_scores_gemma":[0.00037947934,0.00008099198,0.00028322556,0.00011633983,0.00002750647,0.000088381894,0.00004559014,0.0005022109,0.0000042309734],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0034250868,0.0011130897,0.009981704,0.005648092,0.004091192,0.008285035,0.00082688726,0.0038637607,0.04274691,0.6425304,0.036237374,0.24125046],"study_design_scores_gemma":[0.0020036795,0.00036746103,0.0002876979,0.0047425977,0.00015183109,0.0024953783,0.00014379235,0.96804255,0.00057660457,0.0022806309,0.018783815,0.00012398475],"about_ca_topic_score_codex":0.000027641789,"about_ca_topic_score_gemma":0.00001005397,"teacher_disagreement_score":0.96417874,"about_ca_system_score_codex":0.00041249598,"about_ca_system_score_gemma":0.00013799834,"threshold_uncertainty_score":0.3302757},"labels":[],"label_agreement":null},{"id":"W4400613309","doi":"10.1016/j.acra.2024.06.038","title":"Predictive [18F]-FDG PET/CT-Based Radiogenomics Modelling of Driver Gene Mutations in Non-small Cell Lung Cancer","year":2024,"lang":"en","type":"article","venue":"Academic Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; Sinai Health System; Women's College Hospital; Toronto General Hospital; University of Toronto; University Health Network","funders":"","keywords":"Radiogenomics; Lung cancer; Medicine; Positron emission tomography; Cancer research; Pathology; Radiology; Radiomics","score_opus":0.014510483744309641,"score_gpt":0.2926061619679461,"score_spread":0.27809567822363646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400613309","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90448034,0.010625279,0.08115046,0.0019623889,0.00058205286,0.00047778993,0.000033889544,0.0000726158,0.0006151611],"genre_scores_gemma":[0.98540246,0.0050406917,0.007948423,0.00070966897,0.00039023726,0.00008519285,0.000091236325,0.00006153384,0.00027052435],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981341,0.000113742724,0.00062330137,0.00051197497,0.00016299383,0.0004538919],"domain_scores_gemma":[0.9989585,0.0004547755,0.00013237957,0.00022295641,0.000053920634,0.00017743613],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005555721,0.00023109984,0.0005746671,0.0008634489,0.00005035338,0.0000072274147,0.00022239065,0.00009664903,0.00005839526],"category_scores_gemma":[0.000095598945,0.00021484241,0.0001485201,0.000639702,0.00026924012,0.000065313885,0.000039895844,0.0017365641,0.000007664706],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013769575,0.00006840447,0.07711293,0.0006467239,0.00024699143,0.0014472224,0.0017105475,0.8628533,0.050891332,0.00038107377,0.0027746377,0.001729143],"study_design_scores_gemma":[0.0013886697,0.00009504227,0.0023767655,0.00037869607,0.00029886328,0.0007314101,0.000086369546,0.9887885,0.0038021812,0.00022573236,0.0016451138,0.00018265565],"about_ca_topic_score_codex":0.000456081,"about_ca_topic_score_gemma":0.000004472542,"teacher_disagreement_score":0.1259352,"about_ca_system_score_codex":0.00027934008,"about_ca_system_score_gemma":0.00049495517,"threshold_uncertainty_score":0.8761019},"labels":[],"label_agreement":null},{"id":"W4400682601","doi":"10.3390/life14070882","title":"Differentiating Gliosarcoma from Glioblastoma: A Novel Approach Using PEACE and XGBoost to Deal with Datasets with Ultra-High Dimensional Confounders","year":2024,"lang":"en","type":"article","venue":"Life","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton; Université du Québec à Trois-Rivières","funders":"","keywords":"GSM; Probabilistic logic; Metric (unit); Confounding; Computer science; Glioblastoma; Gradient boosting; Statistics; Artificial intelligence; Mathematics; Machine learning; Random forest; Medicine","score_opus":0.014103629560524144,"score_gpt":0.26570873865057537,"score_spread":0.25160510909005124,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400682601","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8981149,0.0003207806,0.09934871,0.0015157714,0.00007603031,0.00025860305,0.00011706676,0.00009968537,0.00014843236],"genre_scores_gemma":[0.9197086,0.0000034789252,0.07797144,0.0016027967,0.00029481773,0.000008089843,0.00032309926,0.00005174493,0.000035905465],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985182,0.000033872293,0.00019750919,0.0005079034,0.00043631802,0.0003061923],"domain_scores_gemma":[0.99907315,0.00020431593,0.00004755288,0.00019966057,0.000030749823,0.0004445837],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017066587,0.0002257888,0.00032690863,0.00012747776,0.000137701,0.00014636644,0.00007851931,0.000054343906,0.000027436492],"category_scores_gemma":[0.000074479176,0.000152051,0.000027125014,0.00022566828,0.00014020597,0.00010416191,0.00005852794,0.00046116157,0.000005011891],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.013409552,0.003377015,0.18830605,0.005137716,0.009038956,0.0060983133,0.019614821,0.021141306,0.6320758,0.012543389,0.028524185,0.060732912],"study_design_scores_gemma":[0.010414445,0.0016178412,0.04183778,0.004000424,0.0014354367,0.0032289529,0.0015184866,0.9239452,0.0016634127,0.000071382645,0.009005617,0.0012610197],"about_ca_topic_score_codex":0.00087643863,"about_ca_topic_score_gemma":0.00002883478,"teacher_disagreement_score":0.9028039,"about_ca_system_score_codex":0.00004853329,"about_ca_system_score_gemma":0.00016522415,"threshold_uncertainty_score":0.62004596},"labels":[],"label_agreement":null},{"id":"W4400724407","doi":"10.1162/imag_a_00251","title":"Translating phenotypic prediction models from big to small anatomical MRI data using meta-matching","year":2024,"lang":"en","type":"article","venue":"Imaging Neuroscience","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute; Montreal Neurological Institute and Hospital","funders":"Medical Research Council; McDonnell Center for Systems Neuroscience; National Supercomputing Centre Singapore; National Institutes of Health; National Medical Research Council; Temasek Foundation","keywords":"Matching (statistics); Computer science; Meta-analysis; Artificial intelligence; Big data; Pattern recognition (psychology); Data mining; Statistics; Mathematics; Medicine; Internal medicine","score_opus":0.127420788564673,"score_gpt":0.35091318928618703,"score_spread":0.22349240072151402,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400724407","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21719895,0.0012304618,0.7700912,0.008667409,0.0017076769,0.00024475149,0.00008480553,0.00039978165,0.0003749813],"genre_scores_gemma":[0.94901025,0.000025314539,0.046687543,0.0037017402,0.00043090305,0.000006273759,0.00003329636,0.000057178808,0.000047478738],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973468,0.000087882996,0.00040036012,0.001157974,0.00053292327,0.000474046],"domain_scores_gemma":[0.99866444,0.00017598087,0.000049431394,0.0007299385,0.000036271427,0.000343927],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008393093,0.00023784334,0.00037338032,0.0002722202,0.00024196948,0.0004069925,0.000574859,0.000037045582,0.000015853217],"category_scores_gemma":[0.00037904578,0.0001989874,0.00011705772,0.00067111774,0.00015939365,0.0005969627,0.0002880824,0.000716324,0.00000866951],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044430763,0.000101120204,0.0027765464,0.00016733466,0.00013729342,0.00069785636,0.0022248467,0.05788089,0.6963948,0.00052443455,0.00044723233,0.23860323],"study_design_scores_gemma":[0.00020846142,0.000018229097,0.00081637554,0.00023506803,0.00061895465,0.00018967954,0.000041752395,0.99343365,0.00035217553,0.0013880517,0.0025292984,0.00016829724],"about_ca_topic_score_codex":0.0007939145,"about_ca_topic_score_gemma":0.000008501513,"teacher_disagreement_score":0.9355528,"about_ca_system_score_codex":0.00007266651,"about_ca_system_score_gemma":0.00021849977,"threshold_uncertainty_score":0.8114471},"labels":[],"label_agreement":null},{"id":"W4400839365","doi":"10.1016/j.yasa.2024.06.005","title":"Artificial Intelligence in Diagnostic Imaging","year":2024,"lang":"en","type":"article","venue":"Advances in Small Animal Care","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Workflow; Medical imaging; Computer science; Applications of artificial intelligence; Artificial intelligence; Data science; Medical physics; Medicine","score_opus":0.012765562018144461,"score_gpt":0.32762915170630913,"score_spread":0.3148635896881647,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400839365","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8109846,0.16198443,0.009804536,0.0037512437,0.0011339515,0.0004497432,0.000006467437,0.00022722494,0.011657784],"genre_scores_gemma":[0.9944202,0.0016789869,0.0031716027,0.00036760134,0.0002747331,0.00002611887,0.000013401337,0.000026375352,0.000021015745],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99882066,0.000031636366,0.00034528394,0.0003598362,0.00013776172,0.00030482298],"domain_scores_gemma":[0.99921733,0.0005215817,0.00002297835,0.00012425879,0.00003134601,0.000082474835],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021895942,0.00013663677,0.00022173312,0.00023190663,0.000026640453,0.000044950935,0.00010706985,0.000038386777,0.000058439597],"category_scores_gemma":[0.0012410375,0.00012290466,0.000058383466,0.00042465643,0.000100851874,0.00016971752,0.00005149023,0.0006081023,0.00003786003],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006541608,0.000038187864,0.122383334,0.0004773787,0.000004052563,0.0025929029,0.0016697726,0.0006834824,0.00064083765,0.007077818,0.000016379126,0.86435044],"study_design_scores_gemma":[0.0011397947,0.0014931154,0.16228798,0.016649632,0.00023768996,0.0012071151,0.026379036,0.55420965,0.005576867,0.051174946,0.17749414,0.0021500287],"about_ca_topic_score_codex":0.000089002824,"about_ca_topic_score_gemma":0.00027858006,"teacher_disagreement_score":0.86220044,"about_ca_system_score_codex":0.00014297738,"about_ca_system_score_gemma":0.00007106152,"threshold_uncertainty_score":0.50119066},"labels":[],"label_agreement":null},{"id":"W4400893595","doi":"10.1136/jnis-2024-snis.20","title":"O-020 Recan or rescan? Validation of the halt score and refinement to HALT+","year":2024,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science","score_opus":0.02391218465350076,"score_gpt":0.32416494856736255,"score_spread":0.3002527639138618,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400893595","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9030328,0.00026761676,0.0018410211,0.081946224,0.0003755042,0.00034483505,0.0000024365931,0.00006240807,0.012127178],"genre_scores_gemma":[0.9802701,0.000057885132,0.002811891,0.0022603958,0.00014494883,0.000008609983,0.0000049921928,0.000014640939,0.01442655],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993227,0.000027666127,0.0001742296,0.00016435077,0.00020794144,0.00010309985],"domain_scores_gemma":[0.99960864,0.00005935348,0.000021599306,0.00018120866,0.000031329,0.000097852935],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034600098,0.00006491968,0.00012339171,0.00006244155,0.00003917241,0.000025061285,0.000056681652,0.000024924246,0.00043432452],"category_scores_gemma":[0.00037907183,0.00003272896,0.000031163614,0.00020824863,0.00004448283,0.000020994425,0.00005931002,0.0001677518,0.000009052016],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041093235,0.0001590652,0.042166855,0.0018165538,0.00025067516,0.000115721006,0.004482289,0.0001546146,0.069040924,0.015484758,0.25601605,0.60990155],"study_design_scores_gemma":[0.0021711802,0.0012920432,0.05553768,0.0045336927,0.00043600358,0.00034833126,0.0007188332,0.044610683,0.06202588,0.000818884,0.827115,0.0003918193],"about_ca_topic_score_codex":0.0002588497,"about_ca_topic_score_gemma":0.000024484936,"teacher_disagreement_score":0.60950977,"about_ca_system_score_codex":0.000030313973,"about_ca_system_score_gemma":0.000085774576,"threshold_uncertainty_score":0.47555488},"labels":[],"label_agreement":null},{"id":"W4400904304","doi":"10.1007/978-3-031-66958-3_32","title":"Prediction of Incident Atrial Fibrillation in Population with Ischemic Heart Disease Using Machine Learning with Radiomics and ECG Markers","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Atrial fibrillation; Computer science; Heart disease; Population; Disease; Artificial intelligence; Internal medicine; Cardiology; Machine learning; Radiomics; Medicine","score_opus":0.010977004478984224,"score_gpt":0.25239828534339787,"score_spread":0.24142128086441364,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400904304","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.62109965,0.0019531104,0.37504295,0.00080697145,0.000343814,0.0006076238,0.000008100396,0.000055016822,0.00008275248],"genre_scores_gemma":[0.9537638,0.000076191434,0.045574885,0.00009026604,0.0003538119,7.3840977e-7,0.00005347421,0.000038934788,0.000047893427],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99834013,0.00002187169,0.0003403217,0.0005587598,0.0005352943,0.00020359595],"domain_scores_gemma":[0.9993044,0.00013527775,0.00017674037,0.00019175487,0.00006170579,0.00013013191],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005210028,0.00023553133,0.0003978059,0.00061788515,0.000067883964,0.00006293661,0.0000811339,0.00009677179,0.000004728542],"category_scores_gemma":[0.00012541369,0.00018044641,0.00005011487,0.00028864137,0.0003208645,0.00013932252,0.000092571674,0.00076874904,2.9624624e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005904939,0.000005674737,0.45907232,0.00035402426,0.000027839042,0.00009537934,0.00022931886,0.508156,0.0004994004,0.00005774086,0.0000011680089,0.03091063],"study_design_scores_gemma":[0.00080300577,0.00025830994,0.027575849,0.0025481053,0.000102849284,0.0002578525,4.4377597e-7,0.96735644,0.000027988299,0.0008144092,0.00009443236,0.00016031065],"about_ca_topic_score_codex":0.00025797405,"about_ca_topic_score_gemma":0.00003677542,"teacher_disagreement_score":0.45920044,"about_ca_system_score_codex":0.00027916764,"about_ca_system_score_gemma":0.00024159529,"threshold_uncertainty_score":0.7358391},"labels":[],"label_agreement":null},{"id":"W4401019209","doi":"10.21203/rs.3.rs-4644889/v1","title":"Predicting MGMT Methylation in Glioblastoma for Informed Clinical Decisions: An AI-Driven Approach in Resource-Limited Settings","year":2024,"lang":"en","type":"preprint","venue":"Research Square","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"London Health Sciences Centre","funders":"","keywords":"Artificial intelligence; Feature selection; Computer science; Machine learning; Linear discriminant analysis; Convolutional neural network; DNA methylation; Toolbox; Deep learning; Gene; Biology","score_opus":0.09311859926077962,"score_gpt":0.48400203501969735,"score_spread":0.3908834357589177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401019209","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98189044,0.0009013366,0.0022780655,0.008172491,0.00030950902,0.0045287157,0.000060416034,0.00023103236,0.0016280082],"genre_scores_gemma":[0.9775314,0.00038823774,0.017904434,0.0005777881,0.0012964138,0.0009691865,0.0009251189,0.00017113169,0.0002363045],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9929442,0.0012513772,0.0017073704,0.001338068,0.0016872203,0.0010717597],"domain_scores_gemma":[0.99225384,0.005476486,0.00021911059,0.00093836954,0.0005275031,0.00058471295],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0154415965,0.00037889837,0.0010360219,0.002732684,0.00016040153,0.00027241145,0.0005621863,0.0009805991,0.000018871035],"category_scores_gemma":[0.035110038,0.00033440063,0.00035387234,0.0014540185,0.00030051993,0.00013598608,0.0014619797,0.010340163,0.000016770326],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0056218826,0.0021712137,0.46806914,0.0147107355,0.0004038896,0.0007329585,0.011441398,0.029648447,0.00028637607,0.0011317813,0.018541936,0.44724026],"study_design_scores_gemma":[0.0029832132,0.0010456515,0.039807487,0.009881771,0.00005887565,0.000030076275,0.0022570433,0.92860514,0.000022271652,0.004073794,0.0109244,0.00031030338],"about_ca_topic_score_codex":0.0002276991,"about_ca_topic_score_gemma":0.00016401973,"teacher_disagreement_score":0.89895666,"about_ca_system_score_codex":0.0007374402,"about_ca_system_score_gemma":0.0015038756,"threshold_uncertainty_score":0.99991083},"labels":[],"label_agreement":null},{"id":"W4401103145","doi":"","title":"Generative models of MRI-derived neuroimaging features and associated dataset of 18,000 samples.","year":2024,"lang":"en","type":"preprint","venue":"PubMed","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Northern California Institute for Research and Education; Pfizer; Novartis Pharmaceuticals Corporation; Eisai; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; BioClinica; University of Southern California; Bristol-Myers Squibb; Eli Lilly and Company; Biogen","keywords":"Generative grammar; Generative model; Artificial intelligence; Psychology; Neuroscience; Pattern recognition (psychology); Computer science","score_opus":0.04231343947932548,"score_gpt":0.29631934232019236,"score_spread":0.2540059028408669,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401103145","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9324479,0.020397754,0.005646483,0.0145706255,0.0020837814,0.004085956,0.013977746,0.00028542837,0.006504286],"genre_scores_gemma":[0.9909362,0.0009617308,0.0031138954,0.0005791301,0.00020320457,0.00022611422,0.0036172445,0.0000720473,0.00029042663],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9979327,0.000138021,0.0005689049,0.0005846753,0.00042858403,0.00034716603],"domain_scores_gemma":[0.9986377,0.00017559966,0.00038065,0.00046529842,0.00012544039,0.00021531647],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007846189,0.00029386094,0.00088561804,0.0002650526,0.000036011734,0.000054228112,0.00020418312,0.00019637072,0.00002133392],"category_scores_gemma":[0.00083914853,0.00025091795,0.00013503744,0.00014982173,0.00029189192,0.000044349505,0.00087208167,0.0014890116,4.080255e-7],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00090543495,0.0012847205,0.018540474,0.015390439,0.008412323,0.0009593842,0.0076366826,0.024625208,0.017665235,0.0032190485,0.52760035,0.3737607],"study_design_scores_gemma":[0.0071545565,0.00020386491,0.47483975,0.0035587356,0.004966226,0.0003812931,0.00042504538,0.43139076,0.010822055,0.055891447,0.00848993,0.001876339],"about_ca_topic_score_codex":0.0005066491,"about_ca_topic_score_gemma":0.0000065968984,"teacher_disagreement_score":0.51911044,"about_ca_system_score_codex":0.00006567911,"about_ca_system_score_gemma":0.00011937731,"threshold_uncertainty_score":0.9999943},"labels":[],"label_agreement":null},{"id":"W4401173661","doi":"10.1007/s00405-024-08862-z","title":"Prediction of bone invasion of oral squamous cell carcinoma using a magnetic resonance imaging-based machine learning model","year":2024,"lang":"en","type":"article","venue":"European Archives of Oto-Rhino-Laryngology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Radiomics; Magnetic resonance imaging; Medicine; Support vector machine; Basal cell; Random forest; Bone metastasis; Radiology; Machine learning; Artificial intelligence; Pathology; Metastasis; Computer science; Cancer; Internal medicine","score_opus":0.01921310634209348,"score_gpt":0.24715713681751306,"score_spread":0.22794403047541958,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401173661","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93261266,0.014307863,0.044935632,0.00037750017,0.00019650316,0.00039879608,0.0000753194,0.000119766475,0.006975943],"genre_scores_gemma":[0.96956074,0.00009140365,0.02946898,0.0001729952,0.0000822255,0.000003554397,0.00011113708,0.00010875944,0.00040021574],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972033,0.0006248129,0.00089964963,0.0005388208,0.00034084794,0.00039257237],"domain_scores_gemma":[0.99862075,0.00039246352,0.0003071403,0.00043802845,0.00006512407,0.00017652234],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007407216,0.0002910077,0.0007135038,0.0006461694,0.00007553639,0.000012315012,0.00023831906,0.00005082534,0.000064577165],"category_scores_gemma":[0.0004901777,0.00026677534,0.00027102543,0.00027651075,0.00052969594,0.000082455044,0.00021450115,0.0008651796,0.000006915344],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007634669,0.00041098704,0.13594444,0.002050784,0.000026522235,0.00070139783,0.0018914796,0.021468375,0.8073183,0.00017731573,0.0002103059,0.029036643],"study_design_scores_gemma":[0.002081885,0.0009384978,0.052732576,0.00056250533,0.00022521126,0.00021947095,0.0000357122,0.9321853,0.009645181,0.000091293376,0.0011202638,0.00016213354],"about_ca_topic_score_codex":0.0002870185,"about_ca_topic_score_gemma":0.0000027938313,"teacher_disagreement_score":0.9107169,"about_ca_system_score_codex":0.000029702705,"about_ca_system_score_gemma":0.0001993173,"threshold_uncertainty_score":0.9999784},"labels":[],"label_agreement":null},{"id":"W4401305040","doi":"10.1093/noajnl/vdae090.069","title":"NIRL-08 AUTOMATED LONGITUDINAL TRACKING OF BRAIN METASTASES INTEGRATED IN A USER-ORIENTED SOFTWARE","year":2024,"lang":"en","type":"article","venue":"Neuro-Oncology Advances","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Douglas Mental Health University Institute; Centre Hospitalier de l’Université de Montréal; Hôpital Charles-Le Moyne","funders":"","keywords":"Segmentation; Centroid; Computer science; Artificial intelligence; Pattern recognition (psychology); Matching (statistics); Similarity (geometry); Tracking (education); Sørensen–Dice coefficient; Software; Computer vision; Image segmentation; Image (mathematics); Medicine; Pathology","score_opus":0.015344573080860862,"score_gpt":0.35011944958825675,"score_spread":0.3347748765073959,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401305040","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97315127,0.0068470747,0.009961341,0.006697478,0.0014082382,0.00043246167,0.000031725376,0.0009851102,0.0004853328],"genre_scores_gemma":[0.9846113,0.00030383296,0.013441904,0.0012285747,0.00012534476,0.000035223366,0.00007850997,0.000049691418,0.00012561785],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980969,0.0002570852,0.0005467337,0.00047910758,0.0002536655,0.0003664965],"domain_scores_gemma":[0.997958,0.0014953429,0.00012564416,0.00019323143,0.00009987697,0.00012787845],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00055685727,0.00022065129,0.00062458764,0.0004373286,0.000053038108,0.000019285138,0.00013321555,0.00012073883,0.00012695756],"category_scores_gemma":[0.003843015,0.00017751203,0.00011769986,0.0008665923,0.00031283987,0.00024089987,0.00005398113,0.00089707354,0.000013877392],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001172284,0.0010634214,0.3081592,0.0018650991,0.00034533127,0.011468477,0.0015969846,0.0030703424,0.1666865,0.0017668848,0.014676255,0.4881292],"study_design_scores_gemma":[0.0052794674,0.002530423,0.042228833,0.0018287336,0.0004253548,0.0021784129,0.0007239873,0.10224777,0.012935309,0.00042142806,0.82867247,0.0005278006],"about_ca_topic_score_codex":0.000064778964,"about_ca_topic_score_gemma":0.00006228916,"teacher_disagreement_score":0.81399626,"about_ca_system_score_codex":0.00011318541,"about_ca_system_score_gemma":0.0003054029,"threshold_uncertainty_score":0.723873},"labels":[],"label_agreement":null},{"id":"W4401352381","doi":"10.36227/techrxiv.172297920.01199828/v1","title":"ImageFlowNet: Forecasting Multiscale Image-Level Trajectories of Disease Progression with Irregularly-Sampled Longitudinal Medical Images","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Longitudinal data; Computer science; Artificial intelligence; Computer vision; Geography; Data mining","score_opus":0.03415780051152814,"score_gpt":0.3333530205206379,"score_spread":0.2991952200091098,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401352381","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7473812,0.008636546,0.19519667,0.029721688,0.0026793552,0.004069737,0.0005637959,0.0013814645,0.010369498],"genre_scores_gemma":[0.8510655,0.00013814472,0.14456932,0.00015220407,0.0009901427,0.00015825339,0.00044404366,0.00019340558,0.0022889443],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9950071,0.00012728178,0.0009523041,0.0012006895,0.0020478694,0.0006647829],"domain_scores_gemma":[0.99698013,0.0003311929,0.00035707504,0.00080795743,0.00043889234,0.001084755],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0010460604,0.00070209184,0.0012652974,0.0003615889,0.00012643241,0.0001802649,0.000437124,0.00035803852,0.00078993686],"category_scores_gemma":[0.0022142024,0.00044916998,0.000439116,0.00030691418,0.0011002225,0.00010795712,0.0012544703,0.0029163007,0.0000183384],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0077522253,0.0033971164,0.28874746,0.054711003,0.0040412503,0.020947732,0.002324186,0.000523585,0.009767402,0.0011776822,0.03354259,0.5730678],"study_design_scores_gemma":[0.012809102,0.0018852012,0.22094746,0.068249,0.00682758,0.0021625583,0.0005677389,0.663785,0.009250241,0.007961728,0.0021556176,0.0033987702],"about_ca_topic_score_codex":0.00031181014,"about_ca_topic_score_gemma":0.000026497753,"teacher_disagreement_score":0.6632614,"about_ca_system_score_codex":0.00011791163,"about_ca_system_score_gemma":0.001386711,"threshold_uncertainty_score":0.99979603},"labels":[],"label_agreement":null},{"id":"W4401414830","doi":"10.1109/cec60901.2024.10611971","title":"Pan-Cancer Classification System with Explainable AI Interpretation: A Feasibility Study","year":2024,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Thompson Rivers University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Interpretation (philosophy); Cancer; Artificial intelligence; Information retrieval; Natural language processing; Medicine; Programming language; Internal medicine","score_opus":0.024620636043502245,"score_gpt":0.3545054042264503,"score_spread":0.3298847681829481,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401414830","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.82529527,0.0006833088,0.13229537,0.010955748,0.00051224325,0.0014450672,0.0000018338487,0.0007441037,0.028067056],"genre_scores_gemma":[0.99563205,0.000008180186,0.0005865001,0.00042287505,0.00015614805,0.00014336458,0.0000070371607,0.000021735495,0.003022082],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99897903,0.000060017446,0.00020521988,0.0003407879,0.0002688269,0.00014611617],"domain_scores_gemma":[0.99948287,0.00005903826,0.000027312455,0.0002464483,0.000090967354,0.00009337555],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044224208,0.00010640728,0.00019358851,0.00008417742,0.000063934254,0.00010012275,0.000057778936,0.000031072927,0.00014942959],"category_scores_gemma":[0.000056871937,0.00006638734,0.00003987696,0.00025703854,0.000045070232,0.00012779747,0.000017381695,0.0003134992,0.000042719013],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013998104,0.0016682576,0.70652515,0.0051784874,0.0010655052,0.0007672207,0.012436484,0.00035294585,0.003382046,0.028457433,0.014936562,0.22383007],"study_design_scores_gemma":[0.0016003621,0.00087593007,0.124947004,0.0013816147,0.00034447934,0.0001808418,0.016339688,0.8494987,0.00009509103,0.00004549099,0.004484528,0.00020629639],"about_ca_topic_score_codex":0.00023748793,"about_ca_topic_score_gemma":0.000022885859,"teacher_disagreement_score":0.8491457,"about_ca_system_score_codex":0.00024155795,"about_ca_system_score_gemma":0.00014914344,"threshold_uncertainty_score":0.27071974},"labels":[],"label_agreement":null},{"id":"W4401592835","doi":"10.1007/978-3-031-67285-9_5","title":"CVD_Net: Head and Neck Tumor Segmentation and Generalization in PET/CT Scans Across Data from Multiple Medical Centers","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Generalization; Head and neck; Segmentation; Artificial intelligence; Medical imaging; Computer vision; Medical physics; Medicine; Mathematics; Surgery","score_opus":0.02131529928321184,"score_gpt":0.3211768443246457,"score_spread":0.29986154504143386,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401592835","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4328581,0.0029747197,0.5560777,0.0056059575,0.0015278758,0.0005790103,0.00010294251,0.00007768275,0.00019596968],"genre_scores_gemma":[0.9154791,0.00089658896,0.07455347,0.0071109906,0.00091704144,0.0000066623593,0.0007509489,0.00007381796,0.00021138253],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99774045,0.000020799784,0.00033818814,0.00096780807,0.0006371438,0.00029563298],"domain_scores_gemma":[0.9990315,0.00024249799,0.0000829561,0.00040137372,0.000030659463,0.00021102306],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00059789006,0.00024196098,0.00035739815,0.00023000466,0.00008653435,0.0001809675,0.00036790848,0.000042944837,0.0000268116],"category_scores_gemma":[0.00031166722,0.00020431778,0.000020833597,0.00017773088,0.0005858819,0.00016288362,0.0006573553,0.00078741706,0.0000034061527],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011169794,0.0001086076,0.14387804,0.00066514796,0.000080971084,0.0073977676,0.0029864071,0.0077984976,0.0014519104,0.00032023675,0.00031274278,0.834888],"study_design_scores_gemma":[0.0010873909,0.00006390907,0.005044929,0.0018704883,0.000021612692,0.00067080144,0.0000020099633,0.98821515,0.00006798879,0.0017724965,0.0009768701,0.00020634572],"about_ca_topic_score_codex":0.00068610325,"about_ca_topic_score_gemma":0.0014710273,"teacher_disagreement_score":0.98041666,"about_ca_system_score_codex":0.00011702434,"about_ca_system_score_gemma":0.00018900678,"threshold_uncertainty_score":0.83318377},"labels":[],"label_agreement":null},{"id":"W4401610901","doi":"10.26481/dis.20240909zs","title":"Towards trustworthy artificial intelligence in medical imaging","year":2024,"lang":"en","type":"dissertation","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"L'Alliance Boviteq","funders":"","keywords":"Trustworthiness; Computer science; Artificial intelligence; Medical imaging; Data science; Computer security","score_opus":0.012139739117155008,"score_gpt":0.3518645188657806,"score_spread":0.3397247797486256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401610901","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19705667,0.011678467,0.011941025,0.04976166,0.013363727,0.0012888554,0.000006550923,0.0009164275,0.71398664],"genre_scores_gemma":[0.9628355,0.001377472,0.0032122068,0.004107719,0.0025229016,0.00007928535,0.00132136,0.00023083112,0.02431274],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973003,0.000041722913,0.0007176949,0.0005634177,0.0009808369,0.0003960282],"domain_scores_gemma":[0.99920964,0.00007673217,0.0000735106,0.00024260944,0.000067567285,0.00032993848],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008323134,0.00030250102,0.00057759933,0.00055875926,0.000036520967,0.00007830427,0.00021151977,0.00031989833,0.0036002644],"category_scores_gemma":[0.0010855865,0.0002453989,0.0001994429,0.0004705436,0.00007585853,0.000045318022,0.000042081225,0.0023952238,0.00029942667],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009562609,0.00008990464,0.00039667025,0.0005533371,0.00004394516,0.002231676,0.00083912455,0.000006790633,0.00007136892,0.009681144,0.0025398796,0.98345053],"study_design_scores_gemma":[0.00057431444,0.0001390315,0.0068255845,0.009803444,0.00058286014,0.0008753318,0.0075122886,0.8845438,0.0011956674,0.04145511,0.045199603,0.0012929908],"about_ca_topic_score_codex":0.0005111068,"about_ca_topic_score_gemma":0.0003672726,"teacher_disagreement_score":0.9821575,"about_ca_system_score_codex":0.000126504,"about_ca_system_score_gemma":0.00081768195,"threshold_uncertainty_score":0.9999998},"labels":[],"label_agreement":null},{"id":"W4401615242","doi":"10.1177/2325967124s00240","title":"Poster 273: Three-Dimensional Imaging Compared to Conventional Radiographs for Corrective Osteotomy Planning: An Advanced Imaging Analysis","year":2024,"lang":"en","type":"article","venue":"Orthopaedic Journal of Sports Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Medicine; Radiography; Orthodontics; Surgical planning; Osteotomy; Medical imaging; Radiology","score_opus":0.011459676269475295,"score_gpt":0.31755093760043135,"score_spread":0.30609126133095604,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401615242","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8150806,0.021214573,0.12819357,0.027210837,0.005977265,0.0012515907,0.000029695144,0.00019676278,0.0008451476],"genre_scores_gemma":[0.98835313,0.000055604887,0.006270553,0.0030578303,0.0017748694,0.000017539573,0.00019589155,0.000078960635,0.00019560114],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99601954,0.00005874597,0.0013518207,0.000571894,0.0014454676,0.00055253465],"domain_scores_gemma":[0.9969898,0.00038634136,0.0005054447,0.0003077269,0.0008114996,0.0009992257],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0025347942,0.00039408912,0.0012315958,0.0025494348,0.00017428475,0.00005732881,0.00022135291,0.00006186785,0.000519408],"category_scores_gemma":[0.0004462658,0.00029322674,0.0007666602,0.0015077256,0.00032421108,0.00033428374,0.00004683404,0.0008720716,0.0000028536401],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022223552,0.00021213427,0.74129677,0.0002666507,0.0020274932,0.0060687256,0.0013621796,0.0035392765,0.0018009172,0.00015578391,0.01582314,0.22522455],"study_design_scores_gemma":[0.014025488,0.0015383346,0.68107057,0.012283886,0.011193143,0.012125388,0.001859916,0.21239638,0.00009044684,0.0017557149,0.05074556,0.00091514585],"about_ca_topic_score_codex":0.00003120846,"about_ca_topic_score_gemma":0.0000029724902,"teacher_disagreement_score":0.2243094,"about_ca_system_score_codex":0.00015547631,"about_ca_system_score_gemma":0.00036819093,"threshold_uncertainty_score":0.99995196},"labels":[],"label_agreement":null},{"id":"W4401632081","doi":"10.1117/12.3035725","title":"Swin UNet: a memory-efficient and accurate deep learning model for medical image segmentation","year":2024,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Artificial intelligence; Deep learning; Segmentation; Image segmentation; Convolutional neural network; Segmentation-based object categorization; Probabilistic logic; Scale-space segmentation; Scalability; Encoder; Machine learning; Pattern recognition (psychology); Computer vision; Database","score_opus":0.01184777087732224,"score_gpt":0.3288687207979259,"score_spread":0.31702094992060365,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401632081","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.113008186,0.00077783235,0.87258273,0.010110272,0.00017649913,0.00036141297,0.0000013332607,0.00021790527,0.0027638066],"genre_scores_gemma":[0.94572717,0.00020446084,0.046747014,0.0016942616,0.0002663704,0.000056256617,0.000053555457,0.000051211755,0.0051997034],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99883527,0.000029994962,0.0002392965,0.00030615518,0.0003513645,0.00023791473],"domain_scores_gemma":[0.9993772,0.00021582464,0.000026977983,0.000083787956,0.00004214313,0.00025410406],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00077099825,0.00012432912,0.00019081314,0.00011112694,0.00010197093,0.00009224782,0.00005079674,0.00007509761,0.00023253953],"category_scores_gemma":[0.00066111155,0.0000927283,0.00006704789,0.00011387909,0.00008869359,0.0000634442,0.000042602736,0.0004310028,0.00001706466],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018282326,0.0001621615,0.00034907676,0.0013623246,0.00022469899,0.00026757814,0.0053885123,0.043847695,0.025079293,0.0038614718,0.005635348,0.913639],"study_design_scores_gemma":[0.0010924267,0.000081839615,0.00008346165,0.00015889628,0.00008362278,0.00011257247,0.00032843463,0.99563015,0.00043217867,0.00020802442,0.0016849659,0.000103449565],"about_ca_topic_score_codex":0.000021226855,"about_ca_topic_score_gemma":0.0000030337012,"teacher_disagreement_score":0.9517824,"about_ca_system_score_codex":0.000048185568,"about_ca_system_score_gemma":0.000103668695,"threshold_uncertainty_score":0.37813503},"labels":[],"label_agreement":null},{"id":"W4401665673","doi":"10.1038/s41598-024-69870-x","title":"Beyond hand-crafted features for pretherapeutic molecular status identification of pediatric low-grade gliomas","year":2024,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; Stollery Children's Hospital; Princess Margaret Cancer Centre; Hospital for Sick Children; University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"Convolutional neural network; Radiomics; Random forest; Fluid-attenuated inversion recovery; Computer science; Artificial intelligence; Pattern recognition (psychology); Identification (biology); Feature (linguistics); Variance (accounting); Magnetic resonance imaging; Medicine; Radiology; Biology","score_opus":0.008602710142498943,"score_gpt":0.3038630263580196,"score_spread":0.2952603162155206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401665673","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9637185,0.013939795,0.011612243,0.001236356,0.008069381,0.0009347456,0.000010337885,0.0001437417,0.00033490692],"genre_scores_gemma":[0.994123,0.000046879293,0.0013937098,0.000074037,0.00022971803,0.00004996511,0.00019072772,0.000040336297,0.0038516417],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9976143,0.00003844876,0.00065858243,0.000696066,0.0006433274,0.0003492282],"domain_scores_gemma":[0.9986647,0.00008926211,0.00023168317,0.0006002075,0.00022553155,0.00018864179],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015807179,0.00015122243,0.0002630781,0.0005097472,0.00015933497,0.0003288962,0.00008673588,0.0000898106,0.0000330088],"category_scores_gemma":[0.00058165565,0.00012582874,0.00020813684,0.0009184711,0.00027236892,0.000106664025,0.00002975736,0.00023379298,0.000005283824],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000036955826,0.00015806414,0.0037503801,0.0013233317,0.00014532206,0.0006714606,0.00090088486,0.00017167725,0.95968276,0.00060300255,0.016167978,0.016388154],"study_design_scores_gemma":[0.0016522288,0.0003399811,0.017203579,0.00062799774,0.0019996148,0.0017183537,0.00019346515,0.045074392,0.76374036,0.06435157,0.10233993,0.0007585004],"about_ca_topic_score_codex":0.00001618055,"about_ca_topic_score_gemma":0.0000011357903,"teacher_disagreement_score":0.1959424,"about_ca_system_score_codex":0.00005729196,"about_ca_system_score_gemma":0.00035333328,"threshold_uncertainty_score":0.51311475},"labels":[],"label_agreement":null},{"id":"W4401750001","doi":"10.1109/isbi56570.2024.10635713","title":"Cell-Level GNN-Based Prediction of Tumor Regression Grade in Colorectal Liver Metastases From Histopathology Images","year":2024,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Centre Hospitalier de l’Université de Montréal; Polytechnique Montréal","funders":"","keywords":"Histopathology; Colorectal cancer; Regression; Medicine; Pathology; Internal medicine; Computer science; Mathematics; Cancer; Statistics","score_opus":0.019936560621302654,"score_gpt":0.28278993456801543,"score_spread":0.26285337394671277,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401750001","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9843245,0.0040363283,0.008001595,0.0014336294,0.0004840206,0.00020662138,0.0001179135,0.00012917722,0.001266189],"genre_scores_gemma":[0.986215,0.000087878405,0.012625443,0.00030771355,0.000113242066,0.000013868482,0.00015205258,0.000023359877,0.00046146926],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9988875,0.000110625464,0.00030859196,0.00029908295,0.00022359,0.00017063995],"domain_scores_gemma":[0.999408,0.00028000717,0.000057232155,0.0001339866,0.000031216,0.00008957932],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000324649,0.00013211746,0.00031542566,0.00026015993,0.000024747564,0.00001170956,0.000067399305,0.00006132164,0.00041356534],"category_scores_gemma":[0.000244022,0.000094138486,0.00009428448,0.00018763094,0.00014484876,0.00005768408,0.000029115296,0.00040249398,0.000013859493],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003434456,0.0005969163,0.06314969,0.00050606974,0.000039689337,0.0033645255,0.0005482208,0.00017088225,0.87364656,0.00018334757,0.03273878,0.024711894],"study_design_scores_gemma":[0.0036794741,0.0007696138,0.34905183,0.0015076034,0.00038919653,0.00020831084,0.00023293005,0.3309021,0.30476815,0.00027300595,0.007957678,0.000260097],"about_ca_topic_score_codex":0.0007605233,"about_ca_topic_score_gemma":0.0000074959635,"teacher_disagreement_score":0.56887835,"about_ca_system_score_codex":0.00008091997,"about_ca_system_score_gemma":0.00012653368,"threshold_uncertainty_score":0.45282504},"labels":[],"label_agreement":null},{"id":"W4401750216","doi":"10.5194/gmd-2024-15-cc1","title":"Comment on gmd-2024-15","year":2024,"lang":"en","type":"peer-review","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Statistics; Mathematics","score_opus":0.0267705886544134,"score_gpt":0.36479354036167155,"score_spread":0.33802295170725816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401750216","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000012861244,0.037266247,0.000106922525,0.6486517,0.0064253234,0.0004233492,0.000029946432,0.00015038942,0.30694482],"genre_scores_gemma":[0.000012351922,0.008463814,0.000580052,0.3654726,0.0013083433,0.000030933512,0.000667684,0.00006772411,0.6233965],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99780273,0.000055043914,0.0004527573,0.0005540832,0.0007963907,0.00033898896],"domain_scores_gemma":[0.99874854,0.00015371421,0.00008561059,0.0006198953,0.000078991965,0.00031324418],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0006914507,0.00038177095,0.00094132207,0.00019669425,0.000045283414,0.000047751215,0.00019840388,0.00021146193,0.0104867695],"category_scores_gemma":[0.00048431449,0.00025451754,0.00037715674,0.00019667306,0.00006764762,0.0000111788095,0.00013632516,0.002517928,0.0028098994],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007675661,0.00007351266,0.000005543738,0.008115863,0.00018186723,0.00029079453,0.000010924316,6.4191977e-7,0.0000014950342,0.00091267336,0.950814,0.039585017],"study_design_scores_gemma":[0.00032707828,0.00020274668,0.000004496987,0.025494147,0.0007700351,0.00010628564,0.000007192695,0.00070434733,0.0000040726095,0.00017423378,0.97196746,0.00023788214],"about_ca_topic_score_codex":0.00015317317,"about_ca_topic_score_gemma":0.00000351855,"teacher_disagreement_score":0.31645167,"about_ca_system_score_codex":0.00017362517,"about_ca_system_score_gemma":0.0002023321,"threshold_uncertainty_score":0.9999907},"labels":[],"label_agreement":null},{"id":"W4401751357","doi":"10.1109/isbi56570.2024.10635812","title":"Feature Tokenizer-Transformers with Self-Training for The Prediction of PD-L1 Expression of Non-Small Cell Lung Cancer from CT","year":2024,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier Universitaire de Sherbrooke; Institut universitaire de cardiologie et de pneumologie de Québec; Polytechnique Montréal","funders":"","keywords":"Lung cancer; Transformer; Computer science; Feature (linguistics); Training set; Cancer research; Artificial intelligence; Medicine; Oncology; Engineering; Electrical engineering","score_opus":0.00905804852472802,"score_gpt":0.2725826153711242,"score_spread":0.2635245668463962,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401751357","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7733351,0.004006777,0.21184754,0.0050062365,0.000602454,0.0010894354,0.000099212964,0.00013200063,0.0038812568],"genre_scores_gemma":[0.97985804,0.0004806611,0.018123442,0.00020059418,0.00027639334,0.000061864215,0.000039098864,0.00003493152,0.0009249692],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991768,0.000014144144,0.00018821805,0.00021196199,0.00023305658,0.00017579652],"domain_scores_gemma":[0.99936503,0.0002949397,0.00006360835,0.00013964238,0.00006118835,0.00007559727],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020767465,0.00012793527,0.00025444228,0.00006325252,0.000057136815,0.000014566498,0.00008321361,0.000053575735,0.000078021985],"category_scores_gemma":[0.000023735636,0.00006675346,0.00011151413,0.0001379063,0.00005608703,0.00005927513,0.000012505964,0.00035298278,2.6371455e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012680691,0.00022084672,0.050237708,0.0058115404,0.0012208773,0.000041417323,0.01944387,0.0023551916,0.77671385,0.000109606226,0.047065675,0.095511325],"study_design_scores_gemma":[0.004263093,0.0005096947,0.012843867,0.004208852,0.0018593826,0.000028989256,0.0030087798,0.77254605,0.17104618,0.000029005238,0.029450644,0.00020545788],"about_ca_topic_score_codex":0.00033624147,"about_ca_topic_score_gemma":0.000014185868,"teacher_disagreement_score":0.77019083,"about_ca_system_score_codex":0.000035270725,"about_ca_system_score_gemma":0.00018609992,"threshold_uncertainty_score":0.2722127},"labels":[],"label_agreement":null},{"id":"W4401757767","doi":"10.3390/diagnostics14161835","title":"Enhancing the Clinical Utility of Radiomics: Addressing the Challenges of Repeatability and Reproducibility in CT and MRI","year":2024,"lang":"en","type":"review","venue":"Diagnostics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Health and Medical Research Fund; Health Technology Assessment international","keywords":"Repeatability; Generalizability theory; Reproducibility; Radiomics; Reliability (semiconductor); Computer science; Medical physics; Variation (astronomy); Artificial intelligence; Machine learning; Data mining; Medicine; Statistics; Mathematics","score_opus":0.13803086873517242,"score_gpt":0.4433410324604096,"score_spread":0.3053101637252372,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401757767","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011511627,0.9850377,0.000021801488,0.0017690844,0.00046494612,0.0009860337,0.00002823142,0.000015862164,0.00016472429],"genre_scores_gemma":[0.025661767,0.97365946,0.00031351065,0.000054034823,0.0002394534,0.00002270113,0.000010094277,0.000030330699,0.00000862315],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99575835,0.0009400378,0.0017057061,0.0011186758,0.00026403094,0.0002132115],"domain_scores_gemma":[0.98646307,0.010643119,0.00051134924,0.002199669,0.00008099368,0.00010178025],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.016540503,0.00027659463,0.0019693978,0.00008153371,0.0000543826,0.000020733263,0.00021936852,0.00013805059,0.0000051488796],"category_scores_gemma":[0.054456152,0.00013880023,0.0002850192,0.00021218321,0.0012991226,0.000025871568,0.0003546435,0.0017481785,5.950703e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012665504,0.00012803757,0.009677834,0.03688623,0.00013812698,0.000042526495,0.00046574904,2.1055733e-7,3.367684e-7,0.0002663129,0.00017969038,0.95220226],"study_design_scores_gemma":[0.0015419248,0.00048934564,0.09592845,0.15834881,0.011409684,0.001112592,0.001389985,0.0028716677,0.00003972266,0.0047064973,0.7213392,0.00082210766],"about_ca_topic_score_codex":0.00010835886,"about_ca_topic_score_gemma":0.000038717593,"teacher_disagreement_score":0.9513802,"about_ca_system_score_codex":0.00003139198,"about_ca_system_score_gemma":0.00032612722,"threshold_uncertainty_score":0.95350856},"labels":[],"label_agreement":null},{"id":"W4401830230","doi":"10.18280/ria.380426","title":"Developing a 3D Segmentation Technique by a Region-Growing Algorithm of CT Scan Lung Images","year":2024,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Segmentation; Region growing; Artificial intelligence; Computed tomography; Computer science; Computer vision; Image segmentation; Algorithm; Radiology; Medicine; Scale-space segmentation","score_opus":0.020128048732196525,"score_gpt":0.3206936777248674,"score_spread":0.30056562899267086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401830230","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0076059867,0.0028890579,0.98435605,0.0032207642,0.00026921573,0.00042204224,0.0000046111827,0.00015534872,0.0010769359],"genre_scores_gemma":[0.82273763,0.001157356,0.17206214,0.00053875207,0.00031645157,0.00011468196,0.00006839969,0.00007806031,0.002926501],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9986704,0.00004600673,0.00047102734,0.00035156307,0.00020583412,0.00025516533],"domain_scores_gemma":[0.99936545,0.00015647987,0.000080931175,0.00022615437,0.00007622795,0.00009475787],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00051699794,0.00015317669,0.00026504646,0.00020266017,0.00008763137,0.000053305273,0.00012419483,0.00004577694,0.00007626632],"category_scores_gemma":[0.00018174412,0.00014128367,0.000108394466,0.0005240453,0.00012297339,0.00016921593,0.000048157523,0.00036195727,0.000030389288],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013351656,0.00007189506,0.00053646293,0.0011234247,0.00009002314,0.00032172754,0.0008711067,0.00074887107,0.25072953,0.0010940549,0.005948151,0.7384514],"study_design_scores_gemma":[0.0000469577,0.00006576728,0.0000118346525,0.0020050223,0.00006327293,0.00055872527,0.0005436594,0.45616794,0.5314837,0.00039268908,0.008498874,0.00016156562],"about_ca_topic_score_codex":0.00008461522,"about_ca_topic_score_gemma":3.039532e-7,"teacher_disagreement_score":0.81513166,"about_ca_system_score_codex":0.00015347089,"about_ca_system_score_gemma":0.00012701798,"threshold_uncertainty_score":0.5761381},"labels":[],"label_agreement":null},{"id":"W4401831083","doi":"10.5194/gmd-2024-58-rc3","title":"Comment on gmd-2024-58","year":2024,"lang":"en","type":"peer-review","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Fisheries and Oceans Canada","funders":"","keywords":"Mathematics; Statistics","score_opus":0.02675399261026792,"score_gpt":0.3661918624705807,"score_spread":0.3394378698603128,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401831083","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000010572013,0.031978663,0.0001099532,0.626552,0.006413918,0.00042576017,0.000029071798,0.00014558737,0.33434403],"genre_scores_gemma":[0.000010953095,0.00930092,0.0005566523,0.35061768,0.0013501311,0.00003223319,0.0006358633,0.00006866099,0.6374269],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977909,0.00005634337,0.00046124012,0.0005563603,0.00079518877,0.0003399735],"domain_scores_gemma":[0.99874234,0.0001557534,0.00008757074,0.0006263624,0.00007910758,0.00030887252],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00069765677,0.00038177278,0.0009572041,0.00019728177,0.000045847028,0.000048295547,0.00019912842,0.00021267505,0.010752218],"category_scores_gemma":[0.00048038023,0.00025464463,0.00038239005,0.00019498811,0.00006592465,0.000011053814,0.00013156519,0.0024896676,0.0027422605],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007862934,0.00007178241,0.000005140773,0.009086078,0.00018580636,0.00028240704,0.000010910761,6.4198e-7,0.0000014426188,0.0010524594,0.95157063,0.03772484],"study_design_scores_gemma":[0.00032204806,0.00019774691,0.0000043794366,0.027903162,0.0007716435,0.00010462425,0.000007311204,0.00072670734,0.0000038627795,0.0001546289,0.9695668,0.00023706601],"about_ca_topic_score_codex":0.00016681418,"about_ca_topic_score_gemma":0.000003205235,"teacher_disagreement_score":0.30308288,"about_ca_system_score_codex":0.00018474626,"about_ca_system_score_gemma":0.00020025793,"threshold_uncertainty_score":0.9999906},"labels":[],"label_agreement":null},{"id":"W4401872828","doi":"10.1016/j.acra.2024.08.030","title":"Quantitative CT Imaging Features Associated with Stable PRISm using Machine Learning","year":2024,"lang":"en","type":"article","venue":"Academic Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre; University of British Columbia; University of Toronto","funders":"University of Toronto; Toronto Metropolitan University; Dalhousie University; University of Ottawa; Queen's University; Johns Hopkins University; McGill University","keywords":"Prism; Computer science; Artificial intelligence; Nuclear medicine; Medicine; Optics; Physics","score_opus":0.01902843526492356,"score_gpt":0.3283168117572728,"score_spread":0.30928837649234925,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401872828","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9457112,0.036450617,0.007139229,0.007240324,0.0005339121,0.00030626456,0.000005454036,0.0005270882,0.0020858967],"genre_scores_gemma":[0.9875022,0.0018305868,0.006460839,0.0015071976,0.00032387316,0.000012595718,0.00013114129,0.000108958804,0.0021226082],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99792314,0.00029100207,0.00035916083,0.00054238475,0.00026917446,0.00061513815],"domain_scores_gemma":[0.9987133,0.0007574377,0.00013123828,0.00015763073,0.000045091576,0.00019527067],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0010696404,0.0002765447,0.00055594696,0.00063249265,0.00019632874,0.000038918402,0.00015774758,0.00015159434,0.00006800597],"category_scores_gemma":[0.0015471658,0.00020518269,0.00009741043,0.0008349135,0.00033335332,0.00017121232,0.000059254813,0.0037572202,0.000018617351],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007711826,0.00013280626,0.659636,0.00050583825,0.002746586,0.0086389305,0.0053416607,0.006620702,0.22232509,0.01674095,0.026140543,0.0503997],"study_design_scores_gemma":[0.0018425115,0.0004621664,0.017103665,0.0014857783,0.00061612134,0.011382776,0.00039088813,0.89364,0.00088808016,0.0009242082,0.07071551,0.00054831937],"about_ca_topic_score_codex":0.00036961577,"about_ca_topic_score_gemma":0.0000039550605,"teacher_disagreement_score":0.8870193,"about_ca_system_score_codex":0.00019748021,"about_ca_system_score_gemma":0.00020123163,"threshold_uncertainty_score":0.9985412},"labels":[],"label_agreement":null},{"id":"W4401876009","doi":"10.1016/s2152-2650(24)01390-9","title":"MPN-086 Time-Dependent Transfusion Status as an Independent Predictor of Overall Survival: A Post Hoc Analysis of 3 Phase 3 Trials","year":2024,"lang":"en","type":"article","venue":"Clinical Lymphoma Myeloma & Leukemia","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre","funders":"","keywords":"Medicine; Post-hoc analysis; Oncology; Internal medicine; Post hoc; Phase (matter)","score_opus":0.034297783247627604,"score_gpt":0.39510527755382924,"score_spread":0.3608074943062016,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401876009","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9927912,0.0013494767,0.0016266499,0.00061389455,0.0010984726,0.0007119821,0.00037148938,0.00022249331,0.0012143737],"genre_scores_gemma":[0.99473876,0.0016810456,0.0008155171,0.00051847246,0.00064756395,0.000020479589,0.0006564689,0.00010120109,0.00082050834],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99216616,0.0012474052,0.0034017959,0.001063551,0.0015010033,0.0006200942],"domain_scores_gemma":[0.993974,0.0030314913,0.00066559226,0.00096401025,0.00037193077,0.0009929788],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0073444205,0.0004507265,0.0030281188,0.00081492594,0.00007611254,0.000077220495,0.00040495026,0.0005316686,0.0016990723],"category_scores_gemma":[0.005102159,0.00035610513,0.0017540896,0.0010000243,0.000444829,0.00021823436,0.00012926548,0.0007019632,0.000068525],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.009721479,0.0021994202,0.013014108,0.00052343454,0.0075897505,0.0008541138,0.0010428008,0.00030735406,0.044991773,0.0007263067,0.00075366313,0.9182758],"study_design_scores_gemma":[0.039141055,0.013212853,0.6145734,0.0014503822,0.021460872,0.00017673503,0.00039182854,0.29126745,0.0030903255,0.0008825405,0.01335541,0.0009971132],"about_ca_topic_score_codex":0.0011447115,"about_ca_topic_score_gemma":0.000036651098,"teacher_disagreement_score":0.9172787,"about_ca_system_score_codex":0.00053690147,"about_ca_system_score_gemma":0.0023539555,"threshold_uncertainty_score":0.9998891},"labels":[],"label_agreement":null},{"id":"W4401937918","doi":"10.1038/s41598-024-70208-w","title":"CT radiomics-based biomarkers can predict response to immunotherapy in hepatocellular carcinoma","year":2024,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Nanjing University; Nanjing University of Chinese Medicine; Government of Jiangsu Province","keywords":"Immunotherapy; Radiomics; Artificial intelligence; AdaBoost; Computer science; Naive Bayes classifier; Random forest; Hepatocellular carcinoma; Machine learning; Feature (linguistics); Support vector machine; Medicine; Oncology; Cancer; Internal medicine","score_opus":0.010055917211508714,"score_gpt":0.27261893957061184,"score_spread":0.2625630223591031,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401937918","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9822842,0.0013294495,0.00097131147,0.008025221,0.00610529,0.00069445773,0.0000041372277,0.00018629442,0.00039967784],"genre_scores_gemma":[0.9953713,0.0000051627235,0.0013079335,0.0005336878,0.000099256875,0.00004539972,0.000062737665,0.000056756155,0.0025178022],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99706763,0.00015360523,0.00064159866,0.0009789935,0.00066838315,0.0004897818],"domain_scores_gemma":[0.99840266,0.00013848336,0.00008067596,0.00093798916,0.00006556586,0.00037460175],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0053430335,0.00021209063,0.00034045888,0.0010798783,0.00014090305,0.00031388903,0.00014179137,0.00005412751,0.00015334146],"category_scores_gemma":[0.0007239628,0.00018341589,0.00017926129,0.0014205349,0.0002628419,0.0000663169,0.000039458075,0.00038050776,0.00002072548],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009229198,0.00016946754,0.39689916,0.00023992459,0.00011102255,0.059950173,0.001203127,0.00040868061,0.4801172,0.000024571127,0.034816902,0.025136843],"study_design_scores_gemma":[0.001959409,0.00038646703,0.07345574,0.0014451097,0.00009705579,0.0051732636,0.0001715383,0.2775188,0.047483567,0.00077099906,0.59086704,0.0006709669],"about_ca_topic_score_codex":0.0003931642,"about_ca_topic_score_gemma":0.000011265018,"teacher_disagreement_score":0.5560502,"about_ca_system_score_codex":0.0003726455,"about_ca_system_score_gemma":0.0011442847,"threshold_uncertainty_score":0.7479483},"labels":[],"label_agreement":null},{"id":"W4401953142","doi":"10.1148/ryai.230296","title":"Precise Image-level Localization of Intracranial Hemorrhage on Head CT Scans with Deep Learning Models Trained on Study-level Labels","year":2024,"lang":"en","type":"article","venue":"Radiology Artificial Intelligence","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Science North","funders":"National Institute of Neurological Disorders and Stroke; Northwestern Memorial Foundation; Northwestern University","keywords":"Head (geology); Artificial intelligence; Medicine; Radiology; Deep learning; Computed tomography; Computer science; Computer vision; Geology","score_opus":0.07135883899809214,"score_gpt":0.33877764259056603,"score_spread":0.2674188035924739,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401953142","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3905134,0.00013077965,0.60656893,0.0007911488,0.00029068667,0.0005265921,0.000011970824,0.00013463676,0.0010318687],"genre_scores_gemma":[0.9927356,0.000055104327,0.0060279514,0.00031183084,0.00035287283,0.000038566333,0.000036912545,0.00006771327,0.00037343107],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974212,0.00031535368,0.0006916451,0.0006929483,0.00042707162,0.00045179884],"domain_scores_gemma":[0.998601,0.0005895542,0.00013167424,0.00033493922,0.00015370203,0.00018912634],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00097604893,0.00032750424,0.00062125793,0.00035478533,0.00018351914,0.000050390725,0.00021335436,0.000117503136,0.00020450604],"category_scores_gemma":[0.0007666237,0.00025563277,0.00010472033,0.00059266324,0.00045333005,0.00013330895,0.000033269112,0.0011326617,0.00007986661],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018966874,0.0010001699,0.0008433769,0.00022289176,0.00023826824,0.0021343976,0.0030061489,0.29286215,0.0054241926,0.010387962,0.000075230164,0.68190855],"study_design_scores_gemma":[0.00031567106,0.0034714246,0.00033829483,0.00040122058,0.00016830923,0.0005791288,0.00097399496,0.98472893,0.006343111,0.0023204547,0.000099595105,0.00025984403],"about_ca_topic_score_codex":0.00013327804,"about_ca_topic_score_gemma":0.00006211463,"teacher_disagreement_score":0.6918668,"about_ca_system_score_codex":0.00012210681,"about_ca_system_score_gemma":0.00016773386,"threshold_uncertainty_score":0.99998957},"labels":[],"label_agreement":null},{"id":"W4402024380","doi":"10.1016/j.nuclcard.2024.101925","title":"Association of Medical Therapy on Survival in Patients Undergoing SPECT MPI","year":2024,"lang":"en","type":"article","venue":"Journal of Nuclear Cardiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Medicine; Association (psychology); Internal medicine","score_opus":0.012278931424206387,"score_gpt":0.2988317213492704,"score_spread":0.286552789925064,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402024380","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9844335,0.00033310367,0.000057473724,0.010922112,0.0013877592,0.000048615115,7.806872e-7,0.000010051167,0.0028066307],"genre_scores_gemma":[0.9973406,0.0012719873,0.00009084738,0.0005768289,0.00065562857,1.4800446e-7,0.0000013848767,0.000019199308,0.00004332711],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99849486,0.00021411637,0.0003997921,0.00009453455,0.00065483246,0.00014184951],"domain_scores_gemma":[0.9991652,0.00044736202,0.00015551959,0.00007228928,0.00007012522,0.00008953076],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018303544,0.00007121305,0.00045608214,0.00022251792,0.000013727073,0.0000099397175,0.00009696895,0.00012500503,0.000113237584],"category_scores_gemma":[0.0015417597,0.00005144075,0.00019488734,0.00012367217,0.00003814309,0.00003572831,0.000019621353,0.00082779076,0.000010597817],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008232441,0.00023777233,0.89434284,0.00012735368,0.0011858604,0.0013954298,0.0006672855,0.00035544994,0.00053730805,0.001831306,0.027608765,0.07088736],"study_design_scores_gemma":[0.005513253,0.0027351915,0.9248346,0.0008648276,0.000097062344,0.0003063601,0.00011954733,0.0027336867,0.000018060131,0.0004247146,0.06224755,0.00010512066],"about_ca_topic_score_codex":0.000008756804,"about_ca_topic_score_gemma":0.0000011109208,"teacher_disagreement_score":0.07078224,"about_ca_system_score_codex":0.0001929719,"about_ca_system_score_gemma":0.00014110321,"threshold_uncertainty_score":0.35963848},"labels":[],"label_agreement":null},{"id":"W4402182221","doi":"10.1007/s13246-024-01475-0","title":"PET radiomics-based lymphovascular invasion prediction in lung cancer using multiple segmentation and multi-machine learning algorithms","year":2024,"lang":"en","type":"article","venue":"Physical and Engineering Sciences in Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Douglas Mental Health University Institute","funders":"Université de Genève; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung","keywords":"Radiomics; Lymphovascular invasion; Artificial intelligence; Computer science; Segmentation; Lung cancer; Machine learning; Algorithm; Cancer; Pattern recognition (psychology); Medicine; Oncology; Metastasis; Internal medicine","score_opus":0.01736689042447078,"score_gpt":0.31241336902248107,"score_spread":0.2950464785980103,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402182221","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9508946,0.005607213,0.042083103,0.00084303814,0.00028748982,0.00019884399,0.0000019553124,0.000074400625,0.00000934788],"genre_scores_gemma":[0.9896148,0.0005987569,0.009405172,0.00010114435,0.00021629162,0.000018823146,0.000013742069,0.00001814148,0.000013116228],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988108,0.000035443318,0.00022764488,0.000383309,0.0002960693,0.0002466856],"domain_scores_gemma":[0.9995782,0.0002121384,0.000026418154,0.000060988725,0.000014219655,0.00010803884],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007296562,0.00015954516,0.00030715848,0.00039150147,0.00007934181,0.000034133926,0.000051179108,0.000032826847,0.000006949595],"category_scores_gemma":[0.0003170387,0.00012026068,0.000029541761,0.00061299244,0.00022532497,0.00016050502,0.000030334637,0.00042465943,2.536964e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004059908,0.00013156797,0.27763137,0.001564275,0.000051667575,0.00022634935,0.0032861794,0.5007098,0.15225948,0.00008829834,0.000016883467,0.06399356],"study_design_scores_gemma":[0.0017679622,0.00010898312,0.020493438,0.0017269255,0.0000543188,0.000060189745,0.000105044484,0.97515625,0.0003069428,0.000011979805,0.000097644246,0.000110335925],"about_ca_topic_score_codex":0.0012114616,"about_ca_topic_score_gemma":0.000016982529,"teacher_disagreement_score":0.47444648,"about_ca_system_score_codex":0.00013821662,"about_ca_system_score_gemma":0.000055724817,"threshold_uncertainty_score":0.4904088},"labels":[],"label_agreement":null},{"id":"W4402233200","doi":"10.1038/s41746-026-02642-1","title":"Predicting Clinically Significant Prostate Cancer with or Without Digital Rectal Exam and MRI Data Using Claritydx Prostate Models","year":2024,"lang":"en","type":"preprint","venue":"npj Digital Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Alberta Innovates; Prostate Cancer Canada; Alberta Cancer Foundation; Movember Foundation","keywords":"Prostate cancer; Prostate; Rectal examination; Medicine; Radiology; Oncology; Urology; Internal medicine; Cancer","score_opus":0.07383024008731685,"score_gpt":0.3753172845287043,"score_spread":0.3014870444413874,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402233200","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96624464,0.0031509353,0.0036555785,0.011015602,0.0014926065,0.0035663343,0.0017436426,0.0007328684,0.008397766],"genre_scores_gemma":[0.987027,0.001511263,0.0037255818,0.0007640245,0.0021649033,0.00010185327,0.0017623162,0.00032409423,0.002618998],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9934632,0.00007187092,0.0016555504,0.0023882452,0.0014869208,0.0009342143],"domain_scores_gemma":[0.99592257,0.00046877874,0.00067833107,0.0015751014,0.00035296398,0.0010022692],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0012965892,0.0009931249,0.001996445,0.00036655454,0.00017192785,0.0008542962,0.0006607985,0.00046429053,0.00003926104],"category_scores_gemma":[0.0018719994,0.0006106914,0.00011539844,0.00042734866,0.0014332016,0.0008134874,0.0029962035,0.0044537256,0.0000064918513],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.011592687,0.0009566609,0.5491542,0.015235998,0.0041336236,0.0072650653,0.010386713,0.0048907963,0.0006549842,0.00015181764,0.0061209025,0.3894565],"study_design_scores_gemma":[0.0059555937,0.0026242794,0.001404456,0.030290289,0.0022876712,0.0015147906,0.0013525101,0.9466511,0.0000129871905,0.0031681499,0.0035097583,0.0012284237],"about_ca_topic_score_codex":0.000604934,"about_ca_topic_score_gemma":0.000021125716,"teacher_disagreement_score":0.9417603,"about_ca_system_score_codex":0.00023116067,"about_ca_system_score_gemma":0.0017596049,"threshold_uncertainty_score":0.99963444},"labels":[],"label_agreement":null},{"id":"W4402260278","doi":"10.1038/s41698-024-00695-7","title":"A multimodal neural network with gradient blending improves predictions of survival and metastasis in sarcoma","year":2024,"lang":"en","type":"article","venue":"npj Precision Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; University of Toronto; McGill University Health Centre","funders":"National Cancer Institute; Fondation du cancer des Cèdres; Strong","keywords":"Artificial neural network; Sarcoma; Metastasis; Multimodal therapy; Computer science; Artificial intelligence; Medicine; Internal medicine; Cancer; Pathology","score_opus":0.01680357438550552,"score_gpt":0.3281118091944795,"score_spread":0.311308234808974,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402260278","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9868197,0.0017518135,0.005902864,0.0025499896,0.00078924815,0.00033017618,0.000005468052,0.000062780375,0.0017879517],"genre_scores_gemma":[0.9878628,0.00022940089,0.01146238,0.00008658808,0.00018692545,0.000022219192,0.00000956608,0.000021335156,0.000118756594],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99874,0.00014656236,0.00033539967,0.00031002145,0.00020776408,0.00026025844],"domain_scores_gemma":[0.99890155,0.00072182226,0.00006011914,0.00014308191,0.000037027123,0.00013640022],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007621202,0.00012353569,0.0004289656,0.00022836836,0.00005069201,0.00001696103,0.000064406,0.00008905927,0.00004101827],"category_scores_gemma":[0.00024154325,0.0000867268,0.000056059493,0.00033252154,0.00016949065,0.00006740372,0.00007624523,0.0005279123,0.0000014779815],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00089909846,0.0003180443,0.060491677,0.00022109275,0.00022196835,0.0005524615,0.0013564802,0.0052305046,0.005734073,0.001784259,0.0010420843,0.9221482],"study_design_scores_gemma":[0.0033077756,0.0028247617,0.1620379,0.00062639575,0.00023219305,0.00078752544,0.0004361795,0.80745053,0.000119938224,0.0005993767,0.021410376,0.00016706233],"about_ca_topic_score_codex":0.0001282809,"about_ca_topic_score_gemma":0.00006942693,"teacher_disagreement_score":0.9219812,"about_ca_system_score_codex":0.00009114988,"about_ca_system_score_gemma":0.000117610274,"threshold_uncertainty_score":0.35366166},"labels":[],"label_agreement":null},{"id":"W4402266297","doi":"10.1158/1538-7445.pediatric24-b023","title":"Abstract B023: Multicenter histology image integration and multiscale deep learning for pediatric sarcoma subtype classification","year":2024,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Histology; Medicine; Sarcoma; Pathology; Artificial intelligence; Computer science","score_opus":0.05485079013210358,"score_gpt":0.4273828383025217,"score_spread":0.37253204817041813,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402266297","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96612275,0.008847807,0.013944483,0.008977396,0.00045429426,0.00067332265,0.0000041922094,0.000110501926,0.0008652466],"genre_scores_gemma":[0.9935662,0.001984138,0.0020658663,0.00007432876,0.0006697461,0.0001763799,0.000052610656,0.00003842181,0.0013723171],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99874806,0.00008413665,0.00020193956,0.00036373996,0.0002668692,0.00033523553],"domain_scores_gemma":[0.99895966,0.00051119097,0.000032651875,0.00012469114,0.00022030578,0.0001515053],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00096398516,0.000096737655,0.000162669,0.00030787295,0.00017747449,0.000094340394,0.00007518906,0.00009420539,0.00015291665],"category_scores_gemma":[0.0010428634,0.00008001035,0.000050904728,0.00023339092,0.0001794524,0.00011034697,0.00003588111,0.0010383032,0.00003453678],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00043717783,0.00010833272,0.053591873,0.0016599909,0.000058592555,0.00008354853,0.001631303,0.000023045666,0.31309617,0.00078999135,0.008602838,0.61991715],"study_design_scores_gemma":[0.0024813528,0.00037912442,0.32416502,0.0003832456,0.00013440987,0.00005095684,0.0007027429,0.591898,0.0024139206,0.00036416054,0.07676631,0.00026072876],"about_ca_topic_score_codex":0.00019620916,"about_ca_topic_score_gemma":0.00003366363,"teacher_disagreement_score":0.61965644,"about_ca_system_score_codex":0.00022885416,"about_ca_system_score_gemma":0.00013479122,"threshold_uncertainty_score":0.45109686},"labels":[],"label_agreement":null},{"id":"W4402358838","doi":"10.1002/uog.29025","title":"EP24.18: A novel machine learning model for automatic assessment of quality of transvaginal ultrasound images","year":2024,"lang":"en","type":"article","venue":"Ultrasound in Obstetrics and Gynecology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Computer science; Ultrasound; Quality (philosophy); Quality assessment; Artificial intelligence; Medicine; Radiology; Engineering; Reliability engineering; Evaluation methods; Philosophy","score_opus":0.030861509226901326,"score_gpt":0.3584101368028643,"score_spread":0.327548627575963,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402358838","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8054632,0.0045820707,0.18711787,0.00066672737,0.00046608437,0.0005421212,0.00011456453,0.000059223436,0.0009881707],"genre_scores_gemma":[0.9595891,0.0016609168,0.038103055,0.00014298172,0.000026007976,0.00003183661,0.00007798751,0.000033723547,0.0003343898],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99808776,0.00009633522,0.0008264122,0.00037646954,0.00027876112,0.0003342626],"domain_scores_gemma":[0.9600585,0.0393442,0.00017991436,0.00018166256,0.00012032233,0.00011540595],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0015190581,0.00019713634,0.00076137285,0.00044853377,0.000058446836,0.000030232992,0.00011483372,0.00016036128,0.000083966996],"category_scores_gemma":[0.031138653,0.00017637033,0.00015628076,0.0004723635,0.000268178,0.00008175723,0.00002351659,0.00063975225,3.8241433e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012193867,0.0021728736,0.297222,0.011587446,0.00076389324,0.000059133727,0.004055544,0.018143618,0.47994983,0.0365213,0.0003978813,0.14900455],"study_design_scores_gemma":[0.0030964932,0.000646429,0.06197689,0.0002327798,0.00020157642,0.000100280704,0.00021492703,0.92830783,0.00040274407,0.0022688017,0.002319243,0.00023197706],"about_ca_topic_score_codex":0.00010695517,"about_ca_topic_score_gemma":0.0000130082335,"teacher_disagreement_score":0.91016424,"about_ca_system_score_codex":0.00011644914,"about_ca_system_score_gemma":0.00025535526,"threshold_uncertainty_score":0.97702247},"labels":[],"label_agreement":null},{"id":"W4402358974","doi":"10.1002/uog.29036","title":"EP24.30: Pilot study of intra‐ and interoperator agreement of a proposed image quality scoring system for transvaginal ultrasound images","year":2024,"lang":"en","type":"article","venue":"Ultrasound in Obstetrics and Gynecology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Ultrasound; Transvaginal ultrasound; Image quality; Quality (philosophy); Scoring system; Artificial intelligence; Image (mathematics); Medicine; Computer vision; Computer science; Radiology; Surgery; Physics","score_opus":0.02069571260996524,"score_gpt":0.31490388454200197,"score_spread":0.29420817193203674,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402358974","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99268484,0.0029890032,0.00203438,0.00016591928,0.00066817726,0.0011564904,0.000035894478,0.000031555985,0.0002337659],"genre_scores_gemma":[0.9972703,0.00063938193,0.0018657602,0.000044590517,0.00004876657,0.00004231923,0.000012357944,0.000027377062,0.000049166316],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99804294,0.00016768956,0.00080634764,0.00045305208,0.00023002457,0.00029995514],"domain_scores_gemma":[0.98522544,0.014155436,0.00013293418,0.0002071736,0.0001517869,0.0001272352],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0012594576,0.00020249296,0.00071279507,0.00037591893,0.00006296134,0.000058906768,0.00010412653,0.00006999349,0.00002940152],"category_scores_gemma":[0.012648964,0.00016855008,0.00005150185,0.00036182272,0.0002881736,0.000090416885,0.00003492971,0.00037368844,7.996461e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005563623,0.0035357042,0.19326678,0.012781572,0.0007121657,0.00023756744,0.009851134,0.000031576867,0.71908104,0.0037160725,0.00014750911,0.056082524],"study_design_scores_gemma":[0.055462703,0.08539819,0.7131574,0.005064323,0.0027382511,0.0014274756,0.07095109,0.008515436,0.045710362,0.00137227,0.007882183,0.0023203164],"about_ca_topic_score_codex":0.0002617671,"about_ca_topic_score_gemma":0.000030427635,"teacher_disagreement_score":0.67337066,"about_ca_system_score_codex":0.00012391208,"about_ca_system_score_gemma":0.00009838839,"threshold_uncertainty_score":0.99566793},"labels":[],"label_agreement":null},{"id":"W4402424385","doi":"10.2139/ssrn.4934721","title":"Scarf: Auto-Segmentation Clinical Acceptability &amp; Reproducibility Framework for Benchmarking Essential Radiation Therapy Targets in Head and Neck Cancer","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto; University Health Network","funders":"","keywords":"Benchmarking; Head and neck cancer; Reproducibility; Segmentation; Radiation therapy; Medical physics; Head and neck; Medicine; Computer science; Artificial intelligence; Radiology; Business; Surgery; Mathematics; Statistics; Marketing","score_opus":0.026828264398512405,"score_gpt":0.4120697710673899,"score_spread":0.3852415066688775,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402424385","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90242654,0.035587378,0.04806902,0.009640381,0.0029134585,0.0012657339,0.000011221266,0.00005768217,0.000028584682],"genre_scores_gemma":[0.92751724,0.054201316,0.012749367,0.00040042156,0.004720534,0.00012175274,0.0001221539,0.000070448856,0.00009677931],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99512124,0.0003974555,0.0011972345,0.0014875657,0.00042699484,0.0013695379],"domain_scores_gemma":[0.9981056,0.0003544679,0.00050000416,0.00069352554,0.00015052322,0.00019591935],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.013929053,0.00034455347,0.00078902364,0.00022623783,0.000166684,0.00016757757,0.00019586472,0.0004974316,0.00009943347],"category_scores_gemma":[0.0025891694,0.00029931834,0.00039470693,0.000187513,0.00015398882,0.000088393914,0.0002008018,0.010489729,0.0000019167867],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00073048734,0.00025156105,0.2655688,0.00034772776,0.00046057932,0.000004405043,0.0006634612,0.00033594604,0.000163467,0.0015521987,0.00013823745,0.7297831],"study_design_scores_gemma":[0.004009606,0.0006098085,0.2967688,0.0010187041,0.00039385335,0.0001471371,0.00018828562,0.020501187,0.000086292675,0.67319924,0.002583567,0.0004935019],"about_ca_topic_score_codex":0.000595417,"about_ca_topic_score_gemma":0.0005998287,"teacher_disagreement_score":0.72928965,"about_ca_system_score_codex":0.001838825,"about_ca_system_score_gemma":0.004369158,"threshold_uncertainty_score":0.9999459},"labels":[],"label_agreement":null},{"id":"W4402439209","doi":"10.1371/journal.pone.0307815","title":"Radiomics analysis of baseline computed tomography to predict oncological outcomes in patients treated for resectable colorectal cancer liver metastasis","year":2024,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Cegep regional de Lanaudiere; Ericsson (Canada); Polytechnique Montréal; Hôpital du Sacré-Cœur de Montréal; Université Laval; Université de Montréal; Centre Intégré de Santé et de Services Sociaux des Laurentides; Centre intégré de santé et de services sociaux de Chaudière-Appalaches; Centre Hospitalier de l’Université de Montréal","funders":"Fonds de Recherche du Québec - Santé; Institut de Valorisation des Données","keywords":"Medicine; Concordance; Colorectal cancer; Receiver operating characteristic; Confidence interval; Radiomics; Internal medicine; Oncology; Radiology; Cancer","score_opus":0.03181371587476539,"score_gpt":0.30250701139492864,"score_spread":0.27069329552016325,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402439209","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9958258,0.0004590405,0.0011326268,0.0010954776,0.00006751078,0.0009375435,0.000334502,0.000085391024,0.0000620741],"genre_scores_gemma":[0.98735696,0.00009300153,0.011487493,0.0003626558,0.000063272564,0.00014705294,0.00034839357,0.00002647366,0.00011472458],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99837327,0.00009366952,0.00046092988,0.00037402098,0.00040933694,0.00028874594],"domain_scores_gemma":[0.9988102,0.00058059517,0.00006532642,0.00015707669,0.00019401465,0.00019283591],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005372994,0.00016548258,0.0009809857,0.0011064514,0.00003315729,0.000021207836,0.00011202976,0.00009063529,0.00014852277],"category_scores_gemma":[0.000748115,0.00012639303,0.000278248,0.0021206278,0.00006169423,0.000046728106,0.000048000165,0.00026267895,0.0000018907537],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007807377,0.002863095,0.9770966,0.0003407146,0.007932465,0.000027454842,0.00022344732,0.0007222016,0.0032607412,0.000022365823,0.00073056686,0.005999621],"study_design_scores_gemma":[0.0018236567,0.0010101781,0.52811456,0.00035983158,0.0058266674,3.550901e-7,0.0000105171,0.45989046,0.0026597916,0.0000057875172,0.0001732224,0.00012499587],"about_ca_topic_score_codex":0.0004535947,"about_ca_topic_score_gemma":0.00010675654,"teacher_disagreement_score":0.45916826,"about_ca_system_score_codex":0.00016228388,"about_ca_system_score_gemma":0.00007012769,"threshold_uncertainty_score":0.51541585},"labels":[],"label_agreement":null},{"id":"W4402454018","doi":"10.1101/2024.09.10.24313417","title":"External Control Arm with Synthetic Real-world Data for Comparative Oncology using Single Trial Arm Evidence (ECLIPSE): A Case Study using Lung-MAP S1400I","year":2024,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Calgary; Public Health Ontario; University of Toronto; Health Canada","funders":"","keywords":"Eclipse; Real world data; Real world evidence; Medicine; Control (management); Oncology; Computer science; Internal medicine; Artificial intelligence; Data science","score_opus":0.2076818188546551,"score_gpt":0.4638796729267283,"score_spread":0.25619785407207324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402454018","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9615139,0.0013323517,0.025284735,0.0014692147,0.0034580037,0.006488068,0.00011606013,0.00014707961,0.000190608],"genre_scores_gemma":[0.97660124,0.000027381117,0.01765879,0.0003282292,0.0047158157,0.00022396495,0.00004691577,0.0001475206,0.00025014207],"study_design_codex":"randomized_trial","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99456835,0.0008279484,0.0012309178,0.0018682941,0.0007746733,0.0007297898],"domain_scores_gemma":[0.9939428,0.0024615126,0.0009012139,0.0019406083,0.00030062668,0.00045321838],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0038188577,0.00072046125,0.002304809,0.0005425858,0.00028069632,0.00026133005,0.0007680703,0.00018706058,0.000069379086],"category_scores_gemma":[0.0012384562,0.00055983034,0.00025834565,0.000337334,0.00056484493,0.00013315618,0.0012498562,0.0026980257,0.000007265807],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.31671432,0.038379483,0.14612897,0.019508487,0.022292038,0.29376248,0.04765301,0.053002693,0.01839188,0.00045364155,0.0061257114,0.037587292],"study_design_scores_gemma":[0.033574607,0.0054503917,0.00014214471,0.008519005,0.009105135,0.0057064597,0.0021057732,0.93298954,0.000060759405,0.00035542523,0.0011973607,0.0007934219],"about_ca_topic_score_codex":0.0036561997,"about_ca_topic_score_gemma":0.0010918939,"teacher_disagreement_score":0.8799868,"about_ca_system_score_codex":0.00092801877,"about_ca_system_score_gemma":0.0016609902,"threshold_uncertainty_score":0.99968535},"labels":[],"label_agreement":null},{"id":"W4402474993","doi":"10.1109/ccece59415.2024.10667088","title":"Towards Improving Surgical Margins in Tumour Resection Using Mass Spectrometry Imaging","year":2024,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Surgical resection; Mass spectrometry imaging; Resection; Mass spectrometry; Computer science; Radiology; Medicine; Chemistry; Surgery; Chromatography","score_opus":0.012403682498971176,"score_gpt":0.31344998380859024,"score_spread":0.30104630130961907,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402474993","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8960588,0.0016151555,0.0632555,0.005842911,0.0009218642,0.00021833606,0.0000012020303,0.00030143923,0.03178482],"genre_scores_gemma":[0.97700524,0.00005581127,0.021015337,0.00020737018,0.0007258855,0.0000036920546,0.0000069375687,0.000044925564,0.00093482324],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985062,0.00005358868,0.00030339274,0.00039328155,0.00033829355,0.0004052678],"domain_scores_gemma":[0.9995553,0.000078534096,0.000026240765,0.00015076125,0.000027693788,0.00016147771],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000846412,0.00015372163,0.00026456927,0.00061636075,0.00005721628,0.00013268868,0.00007376263,0.00005897796,0.00042102396],"category_scores_gemma":[0.00020933921,0.00012612941,0.00011177732,0.00070917973,0.000056696772,0.0001738461,0.00005491205,0.00089403323,0.000022899472],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024868004,0.00016331344,0.14296459,0.0011579698,0.00010292211,0.014905252,0.00042500073,0.00038392516,0.7064412,0.0064306115,0.0010979476,0.12567857],"study_design_scores_gemma":[0.0011452624,0.00007589338,0.018561857,0.000563856,0.00006175412,0.00265526,0.00027447537,0.9674879,0.004318172,0.00062131253,0.004001059,0.0002332149],"about_ca_topic_score_codex":0.001001249,"about_ca_topic_score_gemma":0.000010144382,"teacher_disagreement_score":0.96710396,"about_ca_system_score_codex":0.00038927788,"about_ca_system_score_gemma":0.00018502396,"threshold_uncertainty_score":0.5143408},"labels":[],"label_agreement":null},{"id":"W4402501789","doi":"10.11159/icbb24.122","title":"Development And Validation Of An AI-Based Pathomics Biomarker To Predict Response To First-Line Treatment In Metastatic Colorectal Cancers","year":2024,"lang":"en","type":"article","venue":"Proceedings of the World Congress on New Technologies","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Colorectal cancer; Biomarker; Oncology; Internal medicine; Medicine; Computer science; Cancer; Biology","score_opus":0.0192418503198733,"score_gpt":0.3075598880607952,"score_spread":0.2883180377409219,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402501789","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9726785,0.00012496667,0.000044254306,0.02608697,0.00013630497,0.0007075435,0.0000066194584,0.00016609597,0.000048761205],"genre_scores_gemma":[0.9852908,0.000021432093,0.014065667,0.00016020074,0.000008067002,0.00009887902,0.0000020702366,0.000018822206,0.00033404396],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99899876,0.000009080812,0.0003085143,0.00028435208,0.00022642301,0.00017286609],"domain_scores_gemma":[0.9995227,0.00014968959,0.000084128136,0.00011462886,0.00005426174,0.0000745969],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004420183,0.00015666817,0.0003011621,0.00071008253,0.00003925689,0.00003442153,0.00018446347,0.000044382636,0.0000025677255],"category_scores_gemma":[0.00090294663,0.00010276581,0.000038660186,0.00078748167,0.00011536132,0.000058498063,0.00008743131,0.00016978363,5.3727734e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008684227,0.00037350762,0.039660838,0.00081403356,0.0002999015,0.000045657558,0.002460873,0.0017421566,0.19668144,0.0008461094,0.001969285,0.746422],"study_design_scores_gemma":[0.0015064634,0.0012593612,0.0080612665,0.0024465995,0.00010172934,0.0000124411135,0.00056371256,0.01878509,0.9520377,0.00030562698,0.014751044,0.0001689743],"about_ca_topic_score_codex":0.000068487105,"about_ca_topic_score_gemma":0.00010210949,"teacher_disagreement_score":0.75535625,"about_ca_system_score_codex":0.00032104074,"about_ca_system_score_gemma":0.00025354975,"threshold_uncertainty_score":0.4190668},"labels":[],"label_agreement":null},{"id":"W4402501849","doi":"10.11159/icbb24.120","title":"A Fully Automatic Multi-Vendor AI-System To Segment And Predict Resistance To Treatment Of Rectal Cancer On MRI","year":2024,"lang":"en","type":"article","venue":"Proceedings of the World Congress on New Technologies","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Associazione Italiana per la Ricerca sul Cancro; Ministero della Salute","keywords":"Computer science; Colorectal cancer; Vendor; Artificial intelligence; Medicine; Cancer; Internal medicine; Business","score_opus":0.01251713623143737,"score_gpt":0.29869942792586335,"score_spread":0.286182291694426,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402501849","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8899128,0.002457128,0.000060168,0.10276364,0.0007029982,0.0016752036,0.000018657092,0.0010734774,0.0013359549],"genre_scores_gemma":[0.98465747,0.00016966993,0.0057892213,0.00021649532,0.000053251708,0.00020640995,3.707691e-7,0.000030015965,0.008877069],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987328,0.0000049765667,0.00031698612,0.0003772018,0.0003346406,0.0002334181],"domain_scores_gemma":[0.99943155,0.000085051215,0.00011844133,0.00020346364,0.000068034075,0.00009348899],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014187906,0.00021094273,0.0004376733,0.00042065504,0.000057988884,0.000044426197,0.00026108397,0.00006286498,0.000004604452],"category_scores_gemma":[0.0003310422,0.0001270381,0.00008711533,0.0005863905,0.00013295707,0.000039422874,0.00012239734,0.00023313041,0.0000028633106],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013941216,0.0005073048,0.0245584,0.005037784,0.00089622167,0.000059078662,0.0022827869,0.0002058598,0.057183508,0.014267715,0.06527659,0.82833064],"study_design_scores_gemma":[0.0057441792,0.0053455997,0.013818997,0.05862197,0.0008851218,0.00008958019,0.0038006362,0.054478314,0.7102709,0.0006504862,0.14546397,0.000830288],"about_ca_topic_score_codex":0.000048381153,"about_ca_topic_score_gemma":0.00004339285,"teacher_disagreement_score":0.82750034,"about_ca_system_score_codex":0.00028786238,"about_ca_system_score_gemma":0.00006387184,"threshold_uncertainty_score":0.5180463},"labels":[],"label_agreement":null},{"id":"W4402551544","doi":"10.1158/1538-7445.pancreatic24-b066","title":"Abstract B066: An AI approach to unraveling treatment response in pancreatic cancer: Insights from the COMPASS trial leveraging large language models (LLMs)","year":2024,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Pancreatic cancer; Compass; Cancer; Medicine; Oncology; Internal medicine; Geography; Cartography","score_opus":0.09693064355433814,"score_gpt":0.4396428118134847,"score_spread":0.3427121682591465,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402551544","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9760583,0.0098427655,0.001537801,0.010009315,0.00031821727,0.0012888181,0.000053371048,0.00008441155,0.00080698024],"genre_scores_gemma":[0.9955603,0.00063837954,0.00027505343,0.00093974924,0.0012301595,0.0007074728,0.000060571663,0.00006528966,0.0005230127],"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968949,0.00061760016,0.00035119063,0.0006534838,0.0008231625,0.00065966864],"domain_scores_gemma":[0.99804413,0.00096407667,0.000027343496,0.0005228275,0.000090767884,0.0003508258],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002143615,0.00021433838,0.00043066134,0.00036577706,0.00023528574,0.00024413173,0.0003078385,0.0000944861,0.00013086792],"category_scores_gemma":[0.00029455687,0.00013673458,0.00009352973,0.0007131487,0.00009719226,0.00015717877,0.000094050716,0.0013656144,0.000021725105],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.17281885,0.0033322405,0.0067212125,0.0010720628,0.0016623145,0.0037228218,0.31679985,0.11329491,0.16034804,0.0034981617,0.014491579,0.20223796],"study_design_scores_gemma":[0.030415142,0.0009172499,0.015021852,0.0028818587,0.00016344259,0.000016125538,0.0090045845,0.9115936,0.0017370826,0.00094585627,0.02680204,0.00050114485],"about_ca_topic_score_codex":0.027818182,"about_ca_topic_score_gemma":0.0005991154,"teacher_disagreement_score":0.7982987,"about_ca_system_score_codex":0.001176771,"about_ca_system_score_gemma":0.0010855896,"threshold_uncertainty_score":0.97865564},"labels":[],"label_agreement":null},{"id":"W4402556846","doi":"10.1148/radiol.240541","title":"AI for Multistructure Incidental Findings and Mortality Prediction at Chest CT in Lung Cancer Screening","year":2024,"lang":"en","type":"article","venue":"Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"National Cancer Institute; National Heart, Lung, and Blood Institute; National Institutes of Health; Narodowa Agencja Wymiany Akademickiej","keywords":"Medicine; Lung cancer; Lung cancer screening; Radiology; Lung; Oncology; Internal medicine","score_opus":0.011392154726677647,"score_gpt":0.33767790971486683,"score_spread":0.3262857549881892,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402556846","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98817706,0.0035248199,0.0041728728,0.0030018883,0.00067622896,0.00030048226,0.000038458616,0.00006382123,0.000044393873],"genre_scores_gemma":[0.99695176,0.00022268004,0.0011860208,0.00083331787,0.00042804304,0.0000502022,0.00010365139,0.000020417861,0.00020390638],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9991867,0.000030039262,0.00019091243,0.0002996468,0.00007756854,0.00021511115],"domain_scores_gemma":[0.99967235,0.0001250266,0.000021909573,0.00008063328,0.000012465063,0.00008762378],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029276608,0.0001055878,0.00024195906,0.00010622717,0.00006478557,0.000016168557,0.000038112878,0.00007947795,0.000055929384],"category_scores_gemma":[0.00018498648,0.00008952449,0.00004803427,0.00008640846,0.00011491109,0.000056349956,0.000036531474,0.0003900126,6.0516254e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000058256104,0.0000068894196,0.9753003,0.00038365158,0.00009533129,0.00016749531,0.0003603922,0.00014225075,0.0070905057,0.00019380316,0.0044822274,0.011718915],"study_design_scores_gemma":[0.00091354945,0.00004831692,0.6708152,0.000199264,0.00009029924,0.0009917908,0.00001995593,0.31961012,0.00015570773,0.000085477935,0.0069997846,0.000070519054],"about_ca_topic_score_codex":0.00037588563,"about_ca_topic_score_gemma":0.00008816248,"teacher_disagreement_score":0.31946787,"about_ca_system_score_codex":0.00018482137,"about_ca_system_score_gemma":0.00004219484,"threshold_uncertainty_score":0.36507025},"labels":[],"label_agreement":null},{"id":"W4402558328","doi":"10.1016/j.annonc.2024.08.1417","title":"1362P Evaluation of imaging-based prognostication (IPRO) for advanced non-small cell lung cancer (aNSCLC) using deep learning applied to computed tomography (CT)","year":2024,"lang":"en","type":"article","venue":"Annals of Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; Glycemic Index Laboratories; Princess Margaret Cancer Centre; Systems, Applications & Products in Data Processing (Canada); University of Calgary","funders":"","keywords":"Medicine; Lung cancer; Computed tomography; Radiology; Nuclear medicine; Oncology","score_opus":0.0417545052990924,"score_gpt":0.40683021340407205,"score_spread":0.36507570810497963,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402558328","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7663727,0.003306268,0.2237264,0.0030680792,0.00035635312,0.0019935279,0.0000072114694,0.00006727623,0.0011021881],"genre_scores_gemma":[0.96746784,0.00003190247,0.031142414,0.0008546881,0.00014290505,0.00023979202,0.000068423666,0.000039795006,0.000012252075],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984555,0.00010006646,0.00047119276,0.0003598376,0.00031933602,0.00029401307],"domain_scores_gemma":[0.99833524,0.0004217584,0.0002306015,0.00016287316,0.00071995467,0.00012954541],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001486191,0.0001552829,0.00044467163,0.00040927425,0.00006165117,0.0000132216965,0.000109544606,0.000060041395,0.000033971548],"category_scores_gemma":[0.00038273135,0.00014902471,0.0001454513,0.00047301897,0.000089869514,0.000044915178,0.000029099267,0.0002741181,0.0000011125184],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036121547,0.0003171801,0.020264074,0.001767084,0.00016609009,0.0000086744485,0.0009172654,0.18507518,0.15009902,0.0001348692,0.0005459806,0.64034337],"study_design_scores_gemma":[0.0020604366,0.0005747075,0.005730724,0.00058039685,0.00054053444,0.0000059982317,0.00011046484,0.95583236,0.03048205,0.00010406724,0.0038427925,0.00013548924],"about_ca_topic_score_codex":0.00007059163,"about_ca_topic_score_gemma":0.000008748996,"teacher_disagreement_score":0.77075714,"about_ca_system_score_codex":0.000092640075,"about_ca_system_score_gemma":0.0006270176,"threshold_uncertainty_score":0.6077051},"labels":[],"label_agreement":null},{"id":"W4402560674","doi":"10.1016/j.annonc.2024.08.1238","title":"1178P EGFR evaluation in non-small cell lung cancer: An artificial intelligence approach to pre-molecular analysis","year":2024,"lang":"en","type":"article","venue":"Annals of Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Victoria Hospital; McGill University Health Centre","funders":"","keywords":"Medicine; Lung cancer; Oncology; Cancer; Computational biology; Internal medicine","score_opus":0.0657672189633323,"score_gpt":0.44652901930207667,"score_spread":0.38076180033874435,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402560674","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8977964,0.0014426913,0.08782058,0.007013083,0.0002062041,0.00052925927,0.0000031504565,0.000036788162,0.0051518497],"genre_scores_gemma":[0.9925387,0.00016999367,0.0052108197,0.0017241464,0.00014726994,0.00009703083,0.000038895087,0.00002299001,0.000050187402],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984112,0.00019287037,0.00043920396,0.00039655832,0.00029313393,0.00026704674],"domain_scores_gemma":[0.9992391,0.00009695584,0.000074142365,0.0002360706,0.00017828729,0.00017548191],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018668886,0.00012005761,0.0004442421,0.00061853946,0.0000189456,0.000019766338,0.00014810082,0.00012212228,0.000065156826],"category_scores_gemma":[0.0002290232,0.000110011955,0.00013456757,0.00109375,0.000059637907,0.000049795846,0.000042086653,0.00036670404,0.0000041713347],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002021324,0.00092422543,0.0072203027,0.00042484183,0.0005095212,0.0001161985,0.006041876,0.15237638,0.022956721,0.0013454477,0.00087361946,0.80700874],"study_design_scores_gemma":[0.00015275257,0.0006707316,0.006661139,0.00009383566,0.0007901947,0.000006948983,0.0002796777,0.980963,0.008024576,0.0006111278,0.0016244218,0.00012160501],"about_ca_topic_score_codex":0.0009315477,"about_ca_topic_score_gemma":0.00013136641,"teacher_disagreement_score":0.8285866,"about_ca_system_score_codex":0.000109249864,"about_ca_system_score_gemma":0.00040991502,"threshold_uncertainty_score":0.44861573},"labels":[],"label_agreement":null},{"id":"W4402561078","doi":"10.1016/j.annonc.2024.08.995","title":"934P Harnessing artificial intelligence on real-world data to predict recurrence in head and neck squamous cell carcinoma patients: The HNC-TACTIC study","year":2024,"lang":"en","type":"article","venue":"Annals of Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mount Sinai Hospital","funders":"","keywords":"Medicine; Head and neck; Head and neck squamous-cell carcinoma; Basal cell; Oncology; Head and neck cancer; Internal medicine; Surgery; Radiation therapy","score_opus":0.14749092931448096,"score_gpt":0.44252316828667027,"score_spread":0.29503223897218933,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402561078","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98262453,0.00027355936,0.000098841214,0.013708691,0.0004917402,0.00056676375,0.000014997351,0.000022797953,0.0021981047],"genre_scores_gemma":[0.99775875,0.000086015905,0.00022465178,0.0016156076,0.00017941017,0.000016711534,0.000022693734,0.00001806625,0.000078085686],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9982818,0.00023979045,0.00046732294,0.00047083927,0.00025763107,0.00028263268],"domain_scores_gemma":[0.9983728,0.00082450284,0.00010102628,0.000488666,0.00007690137,0.00013613662],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012358858,0.00013940566,0.0003682396,0.00026879695,0.00006507385,0.000038412672,0.00029066764,0.00004537622,0.000017081105],"category_scores_gemma":[0.0011599571,0.00009824594,0.000028982948,0.0005009411,0.0001729657,0.00009053743,0.00022305745,0.00063667534,0.000013141105],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005761484,0.0017399531,0.27837664,0.00017990576,0.000022155915,0.00027808335,0.0036435146,0.00010203712,0.000096802454,0.00031719566,0.0051388047,0.70952874],"study_design_scores_gemma":[0.0009612434,0.016240573,0.90650284,0.00067883346,0.00015568292,0.000025192461,0.0018880323,0.043089967,0.00041675582,0.0007077094,0.029047629,0.00028551643],"about_ca_topic_score_codex":0.0012699006,"about_ca_topic_score_gemma":0.0007680104,"teacher_disagreement_score":0.70924324,"about_ca_system_score_codex":0.000048898135,"about_ca_system_score_gemma":0.00019717401,"threshold_uncertainty_score":0.4006353},"labels":[],"label_agreement":null},{"id":"W4402561845","doi":"10.1016/j.annonc.2024.08.072","title":"64O Clinical validation of a tissue-agnostic genome-wide methylome enrichment assay for MRD in head and neck cancers","year":2024,"lang":"en","type":"article","venue":"Annals of Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University Health Network","funders":"","keywords":"Medicine; Head and neck; Genome; DNA methylation; Head and neck cancer; Computational biology; Genetics; Internal medicine; Gene; Cancer; Surgery; Biology; Gene expression","score_opus":0.08165127544807266,"score_gpt":0.47331035586020564,"score_spread":0.391659080412133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402561845","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9699162,0.0040341527,0.0033776562,0.020956984,0.00039926392,0.00042915993,0.000007705012,0.000013706581,0.0008651267],"genre_scores_gemma":[0.9923776,0.0018152371,0.004054049,0.0013464437,0.00016524563,0.00003081083,0.000025819916,0.000014127614,0.00017068078],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987434,0.00014542986,0.0005805476,0.00022317845,0.000121974794,0.00018547002],"domain_scores_gemma":[0.9974575,0.0021212946,0.00011985565,0.000109704655,0.00008705649,0.000104561186],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002118149,0.000083638835,0.00051376363,0.00017459529,0.000013405264,0.000005955878,0.000057357844,0.000116389994,0.00003383098],"category_scores_gemma":[0.0026119596,0.00007180613,0.000074859214,0.00014774672,0.00014273565,0.000040881605,0.000032003973,0.00025147686,0.000002148591],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008374738,0.0006607232,0.111676395,0.001860525,0.0005079268,0.00021875977,0.0018911465,0.0011252512,0.013703116,0.0018594771,0.010969853,0.85468936],"study_design_scores_gemma":[0.006272169,0.014593426,0.21964897,0.0010473831,0.00041802163,0.00007375665,0.00024300955,0.021136906,0.0075762775,0.0054371683,0.7232534,0.0002994725],"about_ca_topic_score_codex":0.00024832622,"about_ca_topic_score_gemma":0.000018548339,"teacher_disagreement_score":0.8543899,"about_ca_system_score_codex":0.000057358386,"about_ca_system_score_gemma":0.00032679518,"threshold_uncertainty_score":0.31269485},"labels":[],"label_agreement":null},{"id":"W4402561908","doi":"10.1016/j.annonc.2024.08.075","title":"67O Polygenic risk score associations with immune checkpoint inhibitors related endocrine toxicity","year":2024,"lang":"en","type":"article","venue":"Annals of Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre","funders":"National Cancer Institute; Legend Biotech; Genentech; Esperion Therapeutics; EMD Serono; Centre Hospitalier Universitaire Vaudois; Seagen; Incyte; Institut des maladies génétiques Imagine; BioCryst; National Institutes of Health; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; Novavax; Regeneron Pharmaceuticals; Daiichi Sankyo Europe; Sanofi; National Science Foundation; Les Laboratories Pierre Fabre; AstraZeneca; Eli Lilly and Company; Amgen; Université de Lausanne; Pfizer","keywords":"Medicine; Polygenic risk score; Endocrine system; Toxicity; Oncology; Internal medicine; Bioinformatics; Genetics; Gene; Hormone; Single-nucleotide polymorphism; Genotype; Biology","score_opus":0.027698486610285646,"score_gpt":0.35493135236735607,"score_spread":0.32723286575707045,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402561908","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95222193,0.0029222032,0.00018779315,0.03367061,0.0004138262,0.00021947057,0.000017869892,0.0001263575,0.010219929],"genre_scores_gemma":[0.9961605,0.0010077645,0.0007711156,0.0006255797,0.00020145129,0.000010885143,0.000049389193,0.000030880776,0.0011424305],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9985298,0.00012683311,0.00054073974,0.00025440723,0.00023677359,0.0003114697],"domain_scores_gemma":[0.99898934,0.00028225873,0.00022683278,0.00020977251,0.0001431422,0.00014862148],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008405527,0.00013978919,0.0004787193,0.00020059706,0.000075190736,0.000013192411,0.00008921092,0.00012713646,0.00019042604],"category_scores_gemma":[0.000961453,0.000105174484,0.0001958831,0.00040414056,0.00019761242,0.00006702586,0.000052578962,0.0008621049,0.000035823512],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000925183,0.0024023245,0.20574579,0.0007624582,0.0049729366,0.0027952706,0.00512492,0.0006079329,0.11472724,0.008142854,0.041201167,0.6125919],"study_design_scores_gemma":[0.009872978,0.016966503,0.5568948,0.0023832712,0.0019807452,0.002424767,0.00072904775,0.025228238,0.090620965,0.00712999,0.2847213,0.0010474519],"about_ca_topic_score_codex":0.00039452178,"about_ca_topic_score_gemma":0.000021606376,"teacher_disagreement_score":0.6115445,"about_ca_system_score_codex":0.000084025545,"about_ca_system_score_gemma":0.0003678989,"threshold_uncertainty_score":0.4288891},"labels":[],"label_agreement":null},{"id":"W4402565431","doi":"10.1016/j.annonc.2024.08.2226","title":"222P Artificial intelligence (AI) based prognostication from baseline computed tomography (CT) scans in a phase III advanced non-small cell lung cancer (aNSCLC) trial","year":2024,"lang":"en","type":"article","venue":"Annals of Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Glycemic Index Laboratories; Systems, Applications & Products in Data Processing (Canada); Occupational Cancer Research Centre","funders":"","keywords":"Medicine; Lung cancer; Baseline (sea); Computed tomography; Nuclear medicine; Radiology; Oncology","score_opus":0.04412376791264384,"score_gpt":0.4101424405171835,"score_spread":0.3660186726045397,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402565431","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7938952,0.0024848056,0.18359774,0.01706214,0.0010906952,0.001288756,0.00006992649,0.00008583274,0.00042492736],"genre_scores_gemma":[0.9902924,0.00036794526,0.005517586,0.0027981224,0.00057871605,0.00015401552,0.0002367568,0.000031640113,0.00002284944],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979417,0.00018343037,0.0008152537,0.0004789548,0.00022624168,0.00035447234],"domain_scores_gemma":[0.998341,0.00085978035,0.00017570265,0.00023420829,0.00020036114,0.00018893022],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009006816,0.00019819174,0.0006229737,0.00044645648,0.00004045352,0.00002256683,0.00016797935,0.000116690375,0.00020930357],"category_scores_gemma":[0.00034722878,0.0001818469,0.00016373103,0.0007517528,0.00016902192,0.00007139667,0.000027421393,0.0006395852,0.000005098046],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.016158158,0.0031086719,0.002487717,0.00045403096,0.00017078836,0.00047342858,0.00102084,0.005509611,0.019641945,0.00025549863,0.003023077,0.9476962],"study_design_scores_gemma":[0.015470145,0.0023845895,0.00048670065,0.0008903779,0.00022102761,0.0000058018277,0.00009058128,0.9482183,0.021861782,0.0004435969,0.009721468,0.00020565111],"about_ca_topic_score_codex":0.0009960502,"about_ca_topic_score_gemma":0.00021423024,"teacher_disagreement_score":0.9474906,"about_ca_system_score_codex":0.00005919504,"about_ca_system_score_gemma":0.0008402617,"threshold_uncertainty_score":0.74155015},"labels":[],"label_agreement":null},{"id":"W4402565762","doi":"10.1016/j.annonc.2024.08.2029","title":"1943P Updated pan-tumor guidelines for neoadjuvant scoring of pathologic response: A joint SITC and INMC effort","year":2024,"lang":"en","type":"article","venue":"Annals of Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Victoria Hospital","funders":"","keywords":"Medicine; Neoadjuvant therapy; Complete response; Joint (building); Oncology; Surgery; Internal medicine; Cancer; Chemotherapy","score_opus":0.1451970655772216,"score_gpt":0.45844714486034166,"score_spread":0.3132500792831201,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402565762","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95376086,0.0035595663,0.00138243,0.040159833,0.0003387695,0.00033570404,0.000016642034,0.000053608157,0.0003925676],"genre_scores_gemma":[0.98287654,0.00052309636,0.01190926,0.004086309,0.00019742714,0.000024674431,0.000023399924,0.000025214098,0.000334079],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99860394,0.00008526908,0.00064500206,0.00026968753,0.00014369051,0.00025243164],"domain_scores_gemma":[0.99879956,0.00038495805,0.00016329101,0.00017745582,0.00036719663,0.000107530956],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022806607,0.0001308956,0.0006191704,0.00023272392,0.000034850626,0.000008728403,0.000076185424,0.00010318528,0.000027535229],"category_scores_gemma":[0.00300545,0.000097863005,0.00012929046,0.00016002568,0.00021900293,0.000042489584,0.000078269375,0.0002489435,0.000002516526],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0035845693,0.0003179691,0.0049911705,0.0013948192,0.00033135113,0.0016064122,0.0009531914,0.00008588186,0.33838162,0.0017527492,0.0788916,0.5677087],"study_design_scores_gemma":[0.0064723752,0.018735334,0.060653497,0.0027351466,0.00057192316,0.0032849482,0.0007686871,0.06620776,0.052974388,0.0055177817,0.7815341,0.0005440963],"about_ca_topic_score_codex":0.00004546927,"about_ca_topic_score_gemma":0.0000022150684,"teacher_disagreement_score":0.70264244,"about_ca_system_score_codex":0.000019236944,"about_ca_system_score_gemma":0.00027294512,"threshold_uncertainty_score":0.39907375},"labels":[],"label_agreement":null},{"id":"W4402574036","doi":"10.1093/bjr/tqae187","title":"Sensitivity of CT-derived radiomic features to extraction libraries and gray-level discretization in the context of immune biomarker discovery","year":2024,"lang":"en","type":"article","venue":"British Journal of Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Trois-Rivières; Université Laval; Institut universitaire de cardiologie et de pneumologie de Québec","funders":"Fonds de Recherche du Québec - Santé; Institut de Valorisation des Données; Université Laval","keywords":"Radiomics; Medicine; Oncology; Immunotherapy; Internal medicine; Gray (unit); Medical physics; Radiology; Cancer","score_opus":0.011816151747559797,"score_gpt":0.2793663115335012,"score_spread":0.26755015978594143,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402574036","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9702315,0.014307758,0.011188318,0.0037374236,0.00033523823,0.00013262425,0.000017042425,0.000004971268,0.000045148052],"genre_scores_gemma":[0.99674225,0.0019015942,0.00092221674,0.00024301055,0.00012030334,0.0000012867725,0.000012703977,0.000012150234,0.0000444652],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99876475,0.00036968614,0.0004765001,0.000116824434,0.00015097288,0.000121273995],"domain_scores_gemma":[0.9990273,0.000597951,0.00019167461,0.00007631494,0.000054473607,0.000052268344],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013416681,0.00008388392,0.00043899813,0.0002082955,0.000036427766,0.00004039077,0.000065790664,0.00005182082,0.0000072453076],"category_scores_gemma":[0.0009850155,0.00006391303,0.00010358277,0.00018394858,0.00032110256,0.00023871489,0.000022590486,0.00043026646,1.5891857e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009300286,0.00017786116,0.044110082,0.0004496724,0.00040025802,0.0059836106,0.0032859803,0.00009410826,0.72716844,0.0017379933,0.008533946,0.20712802],"study_design_scores_gemma":[0.0009553045,0.00023596341,0.8442333,0.0009817114,0.000096674354,0.14768738,0.0007939074,0.0009275469,0.003360809,0.00030048864,0.0003553651,0.00007157189],"about_ca_topic_score_codex":0.000484095,"about_ca_topic_score_gemma":0.000037969075,"teacher_disagreement_score":0.8001232,"about_ca_system_score_codex":0.000024426308,"about_ca_system_score_gemma":0.000103605504,"threshold_uncertainty_score":0.26062977},"labels":[],"label_agreement":null},{"id":"W4402580595","doi":"10.1038/s41598-024-70321-w","title":"Author Correction: AI is a viable alternative to high throughput screening: a 318-target study","year":2024,"lang":"en","type":"erratum","venue":"Scientific Reports","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Winnipeg; St. Boniface Hospital; Université du Québec à Montréal; McMaster University; Simon Fraser University; McGill University; Université de Montréal; University of Saskatchewan; Hospital for Sick Children; University of Manitoba; St. Joseph’s Healthcare Hamilton; University of Toronto; Montreal Heart Institute; CancerCare Manitoba; Saskatchewan Cancer Agency; University of Alberta","funders":"National Cancer Institute; Medical Research Council; National Institutes of Health","keywords":"Throughput; Computer science; High-throughput screening; Computational biology; Data science; Bioinformatics; Biology; Telecommunications","score_opus":0.01960394428311533,"score_gpt":0.34021244001559514,"score_spread":0.3206084957324798,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402580595","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006423095,0.0017696163,0.011561479,0.02664779,0.9073127,0.0036656272,0.000030882115,0.0007401121,0.04184873],"genre_scores_gemma":[0.017326664,0.000008601345,0.0033828367,0.0022345746,0.005628461,0.00016955308,0.0005724382,0.00018011454,0.9704968],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9924505,0.00012804696,0.0012309129,0.0028656723,0.0025016728,0.0008232382],"domain_scores_gemma":[0.9960378,0.000060115166,0.0005476425,0.001963794,0.0006429863,0.0007477052],"candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0035243481,0.00063745957,0.0011989237,0.000999957,0.0005992748,0.0011454124,0.00034940976,0.00035746887,0.0014681643],"category_scores_gemma":[0.0015616447,0.0005298282,0.00039493098,0.001772549,0.00030420543,0.00017244257,0.0004901554,0.003374002,0.0003735365],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032355012,0.00032729324,0.0009340391,0.00019162087,0.00043036556,0.012507624,0.0033417759,0.00015024935,0.00005726935,0.000009728152,0.9788328,0.0031848894],"study_design_scores_gemma":[0.0002962176,0.0004442328,0.0002600422,0.0015733797,0.0005320866,0.0020993103,0.00053355977,0.0128959045,0.00016123282,0.001964131,0.97873855,0.0005013698],"about_ca_topic_score_codex":0.0012136083,"about_ca_topic_score_gemma":0.00002987347,"teacher_disagreement_score":0.92864805,"about_ca_system_score_codex":0.00033896972,"about_ca_system_score_gemma":0.0012683057,"threshold_uncertainty_score":0.9998915},"labels":[],"label_agreement":null},{"id":"W4402667143","doi":"10.6019/s-biad1372","title":"EMBOR-2022-54786V2 Source Data Microscope Images","year":2024,"lang":"en","type":"dataset","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Microscope; Computer science; Computer graphics (images); Materials science; Optics; Physics","score_opus":0.016740539155052688,"score_gpt":0.34354002013957996,"score_spread":0.32679948098452727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402667143","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000020198593,0.0047618393,0.00037330203,0.0071977973,0.0017417286,0.0003387305,0.9829704,0.00023667402,0.0023592866],"genre_scores_gemma":[0.0000045529487,0.0024437793,0.0022320922,0.005701948,0.0018387422,0.000011276043,0.9627016,0.00009782439,0.02496815],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9971411,0.00006356153,0.0005119654,0.0011537845,0.0006120804,0.0005174845],"domain_scores_gemma":[0.99649924,0.0001559551,0.00012335324,0.0027885444,0.000056832876,0.0003760688],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00074949686,0.00047855877,0.0008054461,0.00031725413,0.00010111364,0.0002523604,0.0012030405,0.00035147113,0.004061169],"category_scores_gemma":[0.00091156753,0.00036047946,0.00015217008,0.0002961922,0.00023274538,0.00009697818,0.0015764193,0.0026722117,0.008658758],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019924499,0.00008568921,0.00002299331,0.0011100074,0.00024689193,0.0005988452,0.000008591354,8.041076e-7,0.00037860748,0.0000029376724,0.9893354,0.008189273],"study_design_scores_gemma":[0.0004857406,0.0000763748,0.000020045965,0.0007799712,0.00089894235,0.00045182856,0.000032366876,0.0008522501,0.00005628368,0.000021955013,0.9959586,0.00036560587],"about_ca_topic_score_codex":0.0007402926,"about_ca_topic_score_gemma":0.000024190735,"teacher_disagreement_score":0.022608863,"about_ca_system_score_codex":0.00007126723,"about_ca_system_score_gemma":0.00039160682,"threshold_uncertainty_score":0.9998847},"labels":[],"label_agreement":null},{"id":"W4402671716","doi":"10.6019/s-biad1373","title":"EMBOR-2022-54786V2 Source Data Microscope Images","year":2024,"lang":"en","type":"dataset","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Microscope; Computer graphics (images); Computer science; Artificial intelligence; Computer vision; Optics; Physics","score_opus":0.016740539155052688,"score_gpt":0.34354002013957996,"score_spread":0.32679948098452727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402671716","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000020198593,0.0047618393,0.00037330203,0.0071977973,0.0017417286,0.0003387305,0.9829704,0.00023667402,0.0023592866],"genre_scores_gemma":[0.0000045529487,0.0024437793,0.0022320922,0.005701948,0.0018387422,0.000011276043,0.9627016,0.00009782439,0.02496815],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9971411,0.00006356153,0.0005119654,0.0011537845,0.0006120804,0.0005174845],"domain_scores_gemma":[0.99649924,0.0001559551,0.00012335324,0.0027885444,0.000056832876,0.0003760688],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00074949686,0.00047855877,0.0008054461,0.00031725413,0.00010111364,0.0002523604,0.0012030405,0.00035147113,0.004061169],"category_scores_gemma":[0.00091156753,0.00036047946,0.00015217008,0.0002961922,0.00023274538,0.00009697818,0.0015764193,0.0026722117,0.008658758],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019924499,0.00008568921,0.00002299331,0.0011100074,0.00024689193,0.0005988452,0.000008591354,8.041076e-7,0.00037860748,0.0000029376724,0.9893354,0.008189273],"study_design_scores_gemma":[0.0004857406,0.0000763748,0.000020045965,0.0007799712,0.00089894235,0.00045182856,0.000032366876,0.0008522501,0.00005628368,0.000021955013,0.9959586,0.00036560587],"about_ca_topic_score_codex":0.0007402926,"about_ca_topic_score_gemma":0.000024190735,"teacher_disagreement_score":0.022608863,"about_ca_system_score_codex":0.00007126723,"about_ca_system_score_gemma":0.00039160682,"threshold_uncertainty_score":0.9998847},"labels":[],"label_agreement":null},{"id":"W4402682822","doi":"10.6019/s-biad1374","title":"EMBOR-2022-54786V2 Source Data Microscope Images","year":2024,"lang":"en","type":"dataset","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Microscope; Computer graphics (images); Computer science; Artificial intelligence; Computer vision; Optics; Physics","score_opus":0.016740539155052688,"score_gpt":0.34354002013957996,"score_spread":0.32679948098452727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402682822","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000020198593,0.0047618393,0.00037330203,0.0071977973,0.0017417286,0.0003387305,0.9829704,0.00023667402,0.0023592866],"genre_scores_gemma":[0.0000045529487,0.0024437793,0.0022320922,0.005701948,0.0018387422,0.000011276043,0.9627016,0.00009782439,0.02496815],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9971411,0.00006356153,0.0005119654,0.0011537845,0.0006120804,0.0005174845],"domain_scores_gemma":[0.99649924,0.0001559551,0.00012335324,0.0027885444,0.000056832876,0.0003760688],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00074949686,0.00047855877,0.0008054461,0.00031725413,0.00010111364,0.0002523604,0.0012030405,0.00035147113,0.004061169],"category_scores_gemma":[0.00091156753,0.00036047946,0.00015217008,0.0002961922,0.00023274538,0.00009697818,0.0015764193,0.0026722117,0.008658758],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019924499,0.00008568921,0.00002299331,0.0011100074,0.00024689193,0.0005988452,0.000008591354,8.041076e-7,0.00037860748,0.0000029376724,0.9893354,0.008189273],"study_design_scores_gemma":[0.0004857406,0.0000763748,0.000020045965,0.0007799712,0.00089894235,0.00045182856,0.000032366876,0.0008522501,0.00005628368,0.000021955013,0.9959586,0.00036560587],"about_ca_topic_score_codex":0.0007402926,"about_ca_topic_score_gemma":0.000024190735,"teacher_disagreement_score":0.022608863,"about_ca_system_score_codex":0.00007126723,"about_ca_system_score_gemma":0.00039160682,"threshold_uncertainty_score":0.9998847},"labels":[],"label_agreement":null},{"id":"W4402686681","doi":"10.47363/jccsr/2024(6)328","title":"Prognosis Disclosure in Oncological Medicine","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Case Studies Reviews & Reports","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute of Cancer Research","funders":"","keywords":"Medicine","score_opus":0.18376869520152384,"score_gpt":0.55147398148195,"score_spread":0.3677052862804262,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402686681","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.50925153,0.44352517,0.00012109119,0.038623303,0.0046749357,0.0006924031,4.4633387e-7,0.000034510755,0.0030766092],"genre_scores_gemma":[0.8218493,0.16911294,0.0027728125,0.0020617316,0.0037206656,0.000020087928,0.0000014656939,0.00002563708,0.00043539805],"study_design_codex":"case_report","study_design_gemma":"not_applicable","domain_scores_codex":[0.99301183,0.000518322,0.005305407,0.0003599153,0.00054499577,0.0002595061],"domain_scores_gemma":[0.9959906,0.001822184,0.0012675415,0.00025334733,0.0002933708,0.0003729725],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.016821245,0.00022706602,0.0027031642,0.00019934517,0.000053771008,0.000019124249,0.00007202349,0.0001386167,0.0001422689],"category_scores_gemma":[0.037098892,0.00011165811,0.00077378185,0.0004643103,0.00045785663,0.00010389641,0.00008520497,0.0019788838,0.0000079791735],"study_design_candidate":"case_report","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000066837296,0.00023808671,0.083436914,0.000921098,0.00032361908,0.51070565,0.00030012958,0.0000020748623,0.000009069234,0.000045098528,0.05714881,0.3468026],"study_design_scores_gemma":[0.0008087363,0.0017866427,0.010593656,0.008284567,0.00089635036,0.2669413,0.00029690532,0.00015672995,0.0000013981829,0.0007077741,0.70939887,0.00012707747],"about_ca_topic_score_codex":0.00000890313,"about_ca_topic_score_gemma":0.0000079832225,"teacher_disagreement_score":0.65225005,"about_ca_system_score_codex":0.00010257163,"about_ca_system_score_gemma":0.00022887153,"threshold_uncertainty_score":0.97101206},"labels":[],"label_agreement":null},{"id":"W4402744437","doi":"10.5194/gmd-2024-116-rc1","title":"Comment on gmd-2024-116","year":2024,"lang":"en","type":"peer-review","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Mathematics; Statistics","score_opus":0.026402792923181737,"score_gpt":0.36506169399811794,"score_spread":0.3386589010749362,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402744437","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000013228249,0.03299447,0.00011293711,0.6487151,0.006502574,0.00042931546,0.000030929874,0.00015330134,0.31106007],"genre_scores_gemma":[0.000012284199,0.00939899,0.0005792531,0.3593931,0.001342541,0.00003214299,0.00065226975,0.00006981979,0.6285196],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977692,0.000055819528,0.0004614397,0.00056649506,0.000799155,0.00034790678],"domain_scores_gemma":[0.9987248,0.00016124174,0.00008750781,0.00063272147,0.00007889975,0.00031483977],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0006950556,0.00038970774,0.0009541083,0.00020073212,0.00004705755,0.00004827485,0.00020248463,0.00021566557,0.00929274],"category_scores_gemma":[0.00048483774,0.0002578933,0.00038966566,0.00019713746,0.00006976393,0.000011504775,0.00013834354,0.0024835716,0.0026556482],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000079049805,0.000074349475,0.0000052586643,0.008138505,0.00018559433,0.00028880415,0.000010697055,5.854083e-7,0.0000015837101,0.0011012572,0.9465613,0.04362419],"study_design_scores_gemma":[0.00033047752,0.00020089195,0.0000044435706,0.026827592,0.00077396334,0.00010553838,0.000006944917,0.0006796063,0.000004315914,0.00017859065,0.9706447,0.00024291672],"about_ca_topic_score_codex":0.0001642111,"about_ca_topic_score_gemma":0.0000032005728,"teacher_disagreement_score":0.31745952,"about_ca_system_score_codex":0.0001867667,"about_ca_system_score_gemma":0.00020659827,"threshold_uncertainty_score":0.9999873},"labels":[],"label_agreement":null},{"id":"W4402832875","doi":"10.1109/nss/mic/rtsd57108.2024.10657702","title":"Exploring Several Novel Strategies to Enhance Prediction of Lung Cancer Survival Time","year":2024,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; BC Cancer Agency","funders":"","keywords":"Lung cancer; Computer science; Oncology; Medicine","score_opus":0.04732704924706255,"score_gpt":0.3527443787338496,"score_spread":0.30541732948678707,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402832875","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8518263,0.00042898147,0.12494581,0.0044163507,0.0013448817,0.0002297034,0.000017651251,0.0002711571,0.016519142],"genre_scores_gemma":[0.99091005,0.00013272019,0.0033405337,0.00019281314,0.00050657126,0.00003555258,0.000009974647,0.000024001276,0.0048477626],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99918205,0.000010352375,0.00019269026,0.00020594809,0.00024411498,0.00016487452],"domain_scores_gemma":[0.9996609,0.000053992495,0.000017269906,0.000111723435,0.00004660746,0.0001094727],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002262319,0.00009079497,0.00018431974,0.00010285401,0.000025580355,0.00003566269,0.000051357154,0.000026381986,0.00039164288],"category_scores_gemma":[0.00005826693,0.000072178045,0.0000520687,0.00020968339,0.000028612685,0.0002192073,0.000029226634,0.00021906049,0.000018251278],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018645215,0.00017260114,0.0069947178,0.0018033446,0.00059230847,0.00006512772,0.0045945314,0.010236754,0.8861982,0.007472019,0.014121948,0.067562],"study_design_scores_gemma":[0.0006170309,0.00025305396,0.03123637,0.0021075276,0.00023424323,0.000041747917,0.00049888593,0.9254942,0.019397145,0.00006866803,0.01979471,0.0002564109],"about_ca_topic_score_codex":0.00037154846,"about_ca_topic_score_gemma":0.000004651384,"teacher_disagreement_score":0.91525745,"about_ca_system_score_codex":0.000061459425,"about_ca_system_score_gemma":0.00013920729,"threshold_uncertainty_score":0.4288215},"labels":[],"label_agreement":null},{"id":"W4402833265","doi":"10.1109/nss/mic/rtsd57108.2024.10657534","title":"Diagnosis of chest X-Rays images with Deep Learning enhanced with discrete wavelet transform","year":2024,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Artificial intelligence; Computer science; Wavelet transform; Wavelet; Discrete wavelet transform; Computer vision; Deep learning; Pattern recognition (psychology); Materials science","score_opus":0.0048981419279987915,"score_gpt":0.2561827450792116,"score_spread":0.2512846031512128,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402833265","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.61516535,0.0015594003,0.30015668,0.013885964,0.00011107144,0.0006092283,0.0000042693828,0.0004725136,0.068035536],"genre_scores_gemma":[0.98041856,0.00053949567,0.016339893,0.00018263474,0.000099902325,0.000046715857,0.000022537026,0.000055896227,0.002294367],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99881727,0.00002481373,0.00022266823,0.00030758174,0.00034916395,0.00027850276],"domain_scores_gemma":[0.9994073,0.0001757855,0.000040548995,0.00015759107,0.000057589936,0.00016122065],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023198429,0.00018724873,0.0003593166,0.00012248763,0.00005944635,0.000043704185,0.00007695028,0.00004940188,0.00039644813],"category_scores_gemma":[0.00007931984,0.00010524061,0.000076453376,0.00029992958,0.0002081418,0.00012228773,0.0000134505035,0.00059090374,0.000011951444],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006552362,0.00021876674,0.032955028,0.0027529816,0.000882519,0.000690384,0.0048915255,0.0009713178,0.020669742,0.001254939,0.00062455924,0.933433],"study_design_scores_gemma":[0.013923536,0.011521811,0.10246328,0.0149214445,0.0032568027,0.0012943856,0.0062531084,0.16772994,0.54047996,0.0004460361,0.13535215,0.0023575157],"about_ca_topic_score_codex":0.00010228149,"about_ca_topic_score_gemma":0.00001924114,"teacher_disagreement_score":0.9310755,"about_ca_system_score_codex":0.00003129533,"about_ca_system_score_gemma":0.00007090795,"threshold_uncertainty_score":0.4340829},"labels":[],"label_agreement":null},{"id":"W4402834257","doi":"10.1109/nss/mic/rtsd57108.2024.10656411","title":"Comparison Between the 3D-CBS Screening and the Liquid Bio and Other Screening of Cancer Procedures","year":2024,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Cancer; Computer science; Cancer detection; Medicine; Internal medicine","score_opus":0.025978338856343368,"score_gpt":0.36193030838635537,"score_spread":0.335951969530012,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402834257","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8770586,0.032427926,0.037341673,0.04772797,0.00010356346,0.0005410573,0.0000065079844,0.00011696064,0.0046757315],"genre_scores_gemma":[0.9943724,0.00025284712,0.002850573,0.001627173,0.00031865714,0.000013554287,0.0000017858641,0.000023361375,0.00053959136],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99915916,0.000055456534,0.00023417552,0.0001866039,0.00020482022,0.00015978533],"domain_scores_gemma":[0.9992545,0.00047024706,0.000051879844,0.00012670853,0.000025236428,0.00007139258],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007229788,0.00011173385,0.00028878095,0.000056743364,0.00012440015,0.000062813735,0.00008149632,0.00004297735,0.00006718746],"category_scores_gemma":[0.00020676563,0.000049258153,0.00004557703,0.00014289185,0.0004980308,0.000036268237,0.00007725924,0.00039815746,7.602053e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005197155,0.000021409529,0.6960304,0.0007829573,0.0007795773,0.000008102132,0.0048181596,0.00016547252,0.0009781814,0.0040744673,0.005075276,0.2867463],"study_design_scores_gemma":[0.0053632157,0.000492465,0.20719407,0.0042523327,0.0016704178,0.00009688419,0.0027364737,0.6091795,0.0023123464,0.00030291954,0.16596349,0.0004358819],"about_ca_topic_score_codex":0.0011561635,"about_ca_topic_score_gemma":0.00003520521,"teacher_disagreement_score":0.60901403,"about_ca_system_score_codex":0.0000054790557,"about_ca_system_score_gemma":0.000041641666,"threshold_uncertainty_score":0.20086892},"labels":[],"label_agreement":null},{"id":"W4402866862","doi":"10.1016/j.cancergen.2024.08.024","title":"22. Advancing personalized prostate cancer care: Utilizing miRNA profiling and machine learning for metastasis prediction","year":2024,"lang":"en","type":"article","venue":"Cancer Genetics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Hospital; Health Sciences Centre; Sunnybrook Health Science Centre","funders":"","keywords":"Profiling (computer programming); Prostate cancer; Metastasis; microRNA; Medicine; Artificial intelligence; Oncology; Computer science; Machine learning; Internal medicine; Computational biology; Cancer; Biology; Operating system","score_opus":0.02091835589154816,"score_gpt":0.32979592955105536,"score_spread":0.3088775736595072,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402866862","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.61960596,0.36287996,0.011405915,0.0026172043,0.0014524044,0.0012702747,0.00018484698,0.00032287967,0.0002605671],"genre_scores_gemma":[0.9345933,0.04182119,0.019807752,0.0005340342,0.0010155989,0.0004980792,0.00017038152,0.00014762422,0.0014120366],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985035,0.000041558113,0.00029425093,0.00049022277,0.00025911324,0.0004113634],"domain_scores_gemma":[0.9993489,0.00009591246,0.0000705614,0.0001243463,0.00014874156,0.00021155854],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003074668,0.00022378544,0.00033232622,0.00013774178,0.00021754619,0.000097129465,0.000058533296,0.000076037126,0.00006292308],"category_scores_gemma":[0.00015784093,0.00019699968,0.000109120185,0.0002087319,0.00010575233,0.000074288575,0.000046392404,0.0005246963,9.983432e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002505462,0.000023129478,0.1367358,0.005052968,0.000505997,0.00004636514,0.00585,0.006029447,0.057243392,0.00016673065,0.0008220859,0.7872735],"study_design_scores_gemma":[0.0021736508,0.00029189064,0.002114458,0.0015501612,0.0011071333,0.000072486764,0.0013069675,0.64835185,0.015007542,0.00008156729,0.3276137,0.0003285816],"about_ca_topic_score_codex":0.00015444639,"about_ca_topic_score_gemma":0.00002346427,"teacher_disagreement_score":0.786945,"about_ca_system_score_codex":0.00027848984,"about_ca_system_score_gemma":0.00030414885,"threshold_uncertainty_score":0.8033414},"labels":[],"label_agreement":null},{"id":"W4402867158","doi":"10.1016/j.cancergen.2024.08.006","title":"4. The clinical implementation of technologies utilized for macrogenomic event detection in solid tumors","year":2024,"lang":"en","type":"article","venue":"Cancer Genetics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; BC Cancer Agency","funders":"","keywords":"Event (particle physics); Computer science; Physics","score_opus":0.030562776567101983,"score_gpt":0.4506858861458413,"score_spread":0.42012310957873933,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402867158","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97859985,0.00986017,0.007902491,0.0025263226,0.00059732527,0.0004454133,0.0000073173533,0.00004796842,0.000013128535],"genre_scores_gemma":[0.9933828,0.0054857824,0.0008131271,0.000058553243,0.00010529572,0.000100272904,0.0000036288982,0.00001432736,0.000036189133],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992625,0.000020472053,0.00036040615,0.00013799453,0.00008124476,0.00013736857],"domain_scores_gemma":[0.9996494,0.00012087581,0.000057870922,0.00011598435,0.00003380651,0.000022030517],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044048938,0.000057688623,0.0001450646,0.00005560035,0.00003567812,0.000012917539,0.00006556658,0.00004527554,0.0000073049755],"category_scores_gemma":[0.000098322926,0.000040571707,0.000074933305,0.00010966155,0.00009791268,0.0000084955955,0.00002444546,0.00017699973,8.056564e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000045517427,0.00000918707,0.013427308,0.00009613515,0.000038825096,0.0000025544794,0.000106679196,0.00008935857,0.011573834,0.000065243556,0.0001936882,0.97435164],"study_design_scores_gemma":[0.004627039,0.0010761485,0.12018822,0.00064464664,0.00037056903,0.00004474532,0.0038260154,0.3692028,0.3486396,0.004806917,0.14628384,0.00028947668],"about_ca_topic_score_codex":0.000058853795,"about_ca_topic_score_gemma":0.00017395061,"teacher_disagreement_score":0.9740622,"about_ca_system_score_codex":0.00009071098,"about_ca_system_score_gemma":0.00016647903,"threshold_uncertainty_score":0.16544662},"labels":[],"label_agreement":null},{"id":"W4402906865","doi":"10.1016/j.ijrobp.2024.07.1443","title":"External Validation of an Artificial Intelligence Screening Tool for Interstitial Lung Disease in Patients Receiving Lung Stereotactic Ablative Radiotherapy","year":2024,"lang":"en","type":"article","venue":"International Journal of Radiation Oncology*Biology*Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto; London Health Sciences Centre; Western University","funders":"","keywords":"Ablative case; Medicine; Lung; Interstitial lung disease; Radiology; Radiation therapy; Medical physics; Stereotactic radiotherapy; Radiosurgery; Internal medicine","score_opus":0.02137428886103429,"score_gpt":0.3693828035459031,"score_spread":0.3480085146848688,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402906865","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5406702,0.00025142592,0.45648807,0.0007270432,0.0015811137,0.00022800949,0.00002207678,0.000015763197,0.000016292577],"genre_scores_gemma":[0.9821399,0.00014209651,0.015431166,0.0002699231,0.0018458724,0.000011938536,0.000116833566,0.0000333278,0.000008962454],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99803704,0.0002321385,0.0009578844,0.00025576726,0.0003183073,0.00019888963],"domain_scores_gemma":[0.9979635,0.0006520428,0.00064908847,0.00010539621,0.0004984743,0.00013150787],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009882706,0.0001679314,0.00039896852,0.00036079684,0.000045305434,0.0000631343,0.00025449388,0.00011609886,0.000049009534],"category_scores_gemma":[0.0009358984,0.00015627379,0.00020959534,0.00017414818,0.00015719979,0.000574622,0.000031889766,0.00055017805,0.0000012947964],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022955702,0.0004929067,0.4091128,0.000072070885,0.0005373551,0.000049608,0.001520567,0.009781862,0.0032470648,0.0049900096,0.000067311375,0.5678328],"study_design_scores_gemma":[0.002851199,0.0013018167,0.08097604,0.0009121886,0.00023967534,0.000041044157,0.0000773562,0.9012146,0.0020894816,0.009601326,0.00047195848,0.00022330388],"about_ca_topic_score_codex":0.000011426303,"about_ca_topic_score_gemma":6.878498e-7,"teacher_disagreement_score":0.89143276,"about_ca_system_score_codex":0.00067401124,"about_ca_system_score_gemma":0.00036642537,"threshold_uncertainty_score":0.63726604},"labels":[],"label_agreement":null},{"id":"W4402907136","doi":"10.1016/j.ijrobp.2024.07.1432","title":"Validation of Known Radiomics Biomarkers for Post-Treatment Local Response for SBRT-Treated NSCLC, Using Machine Learning","year":2024,"lang":"en","type":"article","venue":"International Journal of Radiation Oncology*Biology*Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre; Jewish General Hospital; McGill University","funders":"","keywords":"Radiomics; Medicine; Medical physics; Oncology; Artificial intelligence; Computer science; Radiology","score_opus":0.022129414054754725,"score_gpt":0.3612583986333621,"score_spread":0.3391289845786074,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402907136","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.61359304,0.0012517778,0.37906134,0.003588161,0.0018258573,0.00046020237,0.00013768603,0.00004632552,0.00003557567],"genre_scores_gemma":[0.9747138,0.00041104155,0.022522097,0.0002406372,0.0014617286,0.000019836125,0.00048912346,0.000060371287,0.00008135472],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981313,0.00028005565,0.0008649056,0.00026441852,0.00022052914,0.00023884528],"domain_scores_gemma":[0.9962893,0.0017876647,0.0007402626,0.00010905474,0.00093713443,0.00013654753],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014316834,0.00022000937,0.00056321244,0.00041191862,0.00009449954,0.00003910927,0.000193502,0.00022148262,0.000021802267],"category_scores_gemma":[0.0013868873,0.00018533973,0.00045489712,0.00019183315,0.00025288443,0.00019171722,0.000028077558,0.00035542334,0.0000031376205],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.013955293,0.0007145785,0.046057083,0.00013020368,0.0043314956,0.00006756962,0.0011671146,0.016817927,0.2954669,0.0044993055,0.000514577,0.616278],"study_design_scores_gemma":[0.012014209,0.0065644113,0.0012305813,0.00038860197,0.0010032767,0.0006878213,0.00018256933,0.8412053,0.045562573,0.002465626,0.08841112,0.0002839003],"about_ca_topic_score_codex":0.0000528702,"about_ca_topic_score_gemma":0.0000014022528,"teacher_disagreement_score":0.8243874,"about_ca_system_score_codex":0.001421268,"about_ca_system_score_gemma":0.00091390614,"threshold_uncertainty_score":0.75579345},"labels":[],"label_agreement":null},{"id":"W4402908725","doi":"10.1016/j.ijrobp.2024.08.014","title":"Interim Futility Results of NRG-HN005, A Randomized, Phase II/III Non-Inferiority Trial for Non-Smoking p16+ Oropharyngeal Cancer Patients","year":2024,"lang":"en","type":"article","venue":"International Journal of Radiation Oncology*Biology*Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":70,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; Princess Margaret Cancer Centre; University of Toronto","funders":"","keywords":"Interim; Medicine; Interim analysis; Randomized controlled trial; Cancer; Internal medicine; Oncology; Political science; Law","score_opus":0.02095768943247512,"score_gpt":0.3941854739643185,"score_spread":0.3732277845318434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402908725","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92677945,0.0005206359,0.05496964,0.0042059985,0.011744163,0.0010699668,0.00023759478,0.00003210774,0.00044042914],"genre_scores_gemma":[0.9915863,0.0006435009,0.0015712685,0.00053196296,0.0052787494,0.000058900063,0.00022206188,0.000033776796,0.000073459305],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.997059,0.00023529466,0.0016781604,0.00034031319,0.00041537205,0.00027189363],"domain_scores_gemma":[0.9959957,0.0012406188,0.001336533,0.00015329476,0.0010946573,0.0001792146],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002362944,0.00024524346,0.0012302329,0.00025991988,0.00009557467,0.0000385092,0.00035307716,0.00024800215,0.00006423755],"category_scores_gemma":[0.0021447532,0.00019721109,0.0006599635,0.00017481226,0.00041267887,0.00027223106,0.00010015368,0.0008604848,0.0000020768641],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.5049257,0.0025786248,0.006326701,0.000116126306,0.002626671,0.00005478736,0.0021942242,0.00022750709,0.00428523,0.0012258575,0.0062190387,0.4692195],"study_design_scores_gemma":[0.86048985,0.0059214253,0.000959368,0.00052174984,0.0007688552,0.000048657155,0.000052302505,0.10315,0.0021679876,0.003066424,0.022618983,0.0002343847],"about_ca_topic_score_codex":0.00010288163,"about_ca_topic_score_gemma":0.0000032677194,"teacher_disagreement_score":0.46898514,"about_ca_system_score_codex":0.0006896633,"about_ca_system_score_gemma":0.0010328868,"threshold_uncertainty_score":0.8042035},"labels":[],"label_agreement":null},{"id":"W4402909030","doi":"10.1016/j.ijrobp.2024.07.1938","title":"4DPET/4DCT Image Features to Predict Long-Term Response After Chemo-Radiotherapy for Locally-Advanced Non-Small Cell Lung Cancer","year":2024,"lang":"en","type":"article","venue":"International Journal of Radiation Oncology*Biology*Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; University of Toronto; Princess Margaret Cancer Centre","funders":"","keywords":"Term (time); Radiation therapy; Cancer; Medicine; Lung cancer; Radiology; Oncology; Internal medicine; Physics","score_opus":0.0072827597252259684,"score_gpt":0.3484567154150855,"score_spread":0.34117395568985953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402909030","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.69553035,0.004435034,0.2792732,0.015754486,0.0041218856,0.00060096366,0.000087747176,0.000063057574,0.00013322124],"genre_scores_gemma":[0.95515066,0.0017351473,0.029566146,0.0061143273,0.00638727,0.00014803384,0.00007872287,0.00010316471,0.0007165113],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9981499,0.00015296995,0.0006727034,0.0003747233,0.0003028812,0.00034683273],"domain_scores_gemma":[0.9978265,0.0007372218,0.00038727923,0.0001737456,0.00060084567,0.0002743779],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00094451767,0.00027000534,0.0005475112,0.00030312547,0.00006401875,0.000090235975,0.00039202007,0.00022370675,0.000111973764],"category_scores_gemma":[0.00043456155,0.0002282014,0.00034333696,0.000190063,0.00016357879,0.00022446991,0.000053011165,0.00083187985,0.000009742382],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0133113405,0.0005987158,0.22972478,0.00027821105,0.0019510898,0.00074683136,0.0023667512,0.0032526972,0.18721859,0.00042691515,0.019087257,0.54103684],"study_design_scores_gemma":[0.042131346,0.0102806045,0.51349753,0.003999884,0.0017976995,0.0021689285,0.00018225313,0.14057846,0.051825933,0.0025137304,0.22925836,0.0017652427],"about_ca_topic_score_codex":0.000009437871,"about_ca_topic_score_gemma":0.0000027666317,"teacher_disagreement_score":0.5392716,"about_ca_system_score_codex":0.0011599661,"about_ca_system_score_gemma":0.0010595738,"threshold_uncertainty_score":0.93057835},"labels":[],"label_agreement":null},{"id":"W4402916575","doi":"10.1109/cvprw63382.2024.00242","title":"Codebook VQ-VAE Approach for Prostate Cancer Diagnosis using Multiparametric MRI","year":2024,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Codebook; Prostate cancer; Cancer; Multiparametric MRI; Prostate; Computer science; Artificial intelligence; Medicine; Internal medicine","score_opus":0.03138567594076187,"score_gpt":0.35510541073671703,"score_spread":0.32371973479595517,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402916575","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19636044,0.023510184,0.7507935,0.010081951,0.0017377227,0.004198682,0.00007692826,0.0009354836,0.012305081],"genre_scores_gemma":[0.6985161,0.0020129723,0.27529538,0.0033370075,0.0011118585,0.0017775018,0.00009400051,0.00016487218,0.017690353],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987724,0.00002093173,0.00024088766,0.00039718745,0.0002228199,0.00034576975],"domain_scores_gemma":[0.99928814,0.00026055466,0.000032616746,0.000167525,0.000064788954,0.0001863891],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033765606,0.00015959996,0.0002853754,0.00026236073,0.00008869444,0.00009059932,0.00007490454,0.000069927846,0.00017027665],"category_scores_gemma":[0.0002875651,0.00011602451,0.000140996,0.00040499208,0.00007339315,0.00007271352,0.000034101166,0.00032589756,0.000008856784],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023425477,0.0005205075,0.09119984,0.0042843916,0.0008308714,0.00014795085,0.0016166356,0.013903276,0.0042105247,0.0017737257,0.14311452,0.73816353],"study_design_scores_gemma":[0.00080203474,0.00006815404,0.00039256772,0.00021526251,0.00020270141,0.000037435148,0.000050173105,0.8865557,0.00073635863,0.00006972224,0.11072464,0.00014525386],"about_ca_topic_score_codex":0.0005105701,"about_ca_topic_score_gemma":0.0000023940543,"teacher_disagreement_score":0.8726524,"about_ca_system_score_codex":0.00013629443,"about_ca_system_score_gemma":0.0001600228,"threshold_uncertainty_score":0.47313422},"labels":[],"label_agreement":null},{"id":"W4402946543","doi":"10.1016/j.ijrobp.2024.07.240","title":"A Digital Pathology Multimodal Artificial Intelligence Algorithm is Associated with Pro-Metastatic Genomic Pathways in Oligometastatic Prostate Cancer","year":2024,"lang":"en","type":"article","venue":"International Journal of Radiation Oncology*Biology*Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Decipher Biosciences (Canada)","funders":"","keywords":"Prostate cancer; Digital pathology; Cancer; Oncology; Medicine; Pathology; Internal medicine; Algorithm; Computer science","score_opus":0.023118317339799542,"score_gpt":0.34084173622008895,"score_spread":0.31772341888028943,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402946543","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85412985,0.0015235211,0.1341501,0.007076214,0.0020998232,0.00048424723,0.0002914644,0.00007251456,0.0001722836],"genre_scores_gemma":[0.9877948,0.00070878526,0.009267803,0.0010584868,0.00087092665,0.000035833556,0.00015259186,0.00005203605,0.000058742386],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978251,0.00018559708,0.00095169235,0.00034405425,0.0003519597,0.00034163173],"domain_scores_gemma":[0.9981416,0.0005522844,0.0006029756,0.00010754445,0.00044119792,0.00015442343],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008116523,0.00024085905,0.00061109016,0.00041000696,0.000047283484,0.000104642924,0.0002659841,0.00013361561,0.00007101302],"category_scores_gemma":[0.0006209926,0.00019143047,0.00017131862,0.00038713557,0.00036255247,0.00033209895,0.000053962067,0.0010435453,0.000026743919],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002513462,0.0005004441,0.037631486,0.000026633272,0.0007823117,0.0015082543,0.0022162148,0.0021067795,0.0020612392,0.0019465006,0.00011419777,0.9508546],"study_design_scores_gemma":[0.005859507,0.0038172111,0.017658804,0.0013837955,0.0006032675,0.002830787,0.0006926553,0.89681244,0.0015793935,0.061005183,0.0070691677,0.00068778853],"about_ca_topic_score_codex":0.000021005919,"about_ca_topic_score_gemma":0.0000051829006,"teacher_disagreement_score":0.9501668,"about_ca_system_score_codex":0.00093140797,"about_ca_system_score_gemma":0.001149251,"threshold_uncertainty_score":0.7806308},"labels":[],"label_agreement":null},{"id":"W4402963270","doi":"10.48550/arxiv.2407.18555","title":"How to Segment in 3D Using 2D Models: Automated 3D Segmentation of Prostate Cancer Metastatic Lesions on PET Volumes Using Multi-angle Maximum Intensity Projections and Diffusion Models","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research","keywords":"Prostate cancer; Segmentation; Intensity (physics); Diffusion; 3d model; Prostate; Medicine; Nuclear medicine; Computer science; Biomedical engineering; Artificial intelligence; Cancer; Physics; Optics; Internal medicine","score_opus":0.1088348815255766,"score_gpt":0.28315371815475493,"score_spread":0.17431883662917833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402963270","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86111856,0.00013158069,0.13689929,0.000260565,0.00025293088,0.0011129379,0.00006436496,0.0001352673,0.000024480098],"genre_scores_gemma":[0.9711443,0.00031469646,0.027923357,0.000098494194,0.00002596369,0.00000609957,0.00004250091,0.000047990914,0.00039657086],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99834,0.0001226507,0.00029704714,0.0007783922,0.00016822081,0.0002936618],"domain_scores_gemma":[0.99904954,0.000043655255,0.00020669817,0.00030905285,0.00020019262,0.00019084103],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00026537658,0.0003153658,0.00057314895,0.00078773795,0.00013474583,0.000064170075,0.00011037811,0.00009950858,0.0000053633917],"category_scores_gemma":[0.00006248928,0.00031042783,0.000107362364,0.00054548815,0.00011546882,0.00016082182,0.0005804109,0.000779967,8.2155736e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020199259,0.0002668435,0.0048101293,0.0007611978,0.0001857194,0.00032152818,0.0019030379,0.98518914,0.004809085,0.000113607,0.000021940295,0.0014157523],"study_design_scores_gemma":[0.0012147126,0.000092677765,0.00062408176,0.002309978,0.0006859289,0.000030572544,0.0013869464,0.9917922,0.00013247594,0.0014674617,0.0000038897238,0.0002590579],"about_ca_topic_score_codex":0.005031365,"about_ca_topic_score_gemma":0.0002063256,"teacher_disagreement_score":0.11002575,"about_ca_system_score_codex":0.0007721963,"about_ca_system_score_gemma":0.00031082137,"threshold_uncertainty_score":0.9999348},"labels":[],"label_agreement":null},{"id":"W4402990496","doi":"10.1136/emermed-2024-rcem.26","title":"2772 AI assisted reader evaluation in CT head interpretation (AI-REACT): results from a multi-case multi-reader study","year":2024,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Thomas Hospital","funders":"","keywords":"Head (geology); Interpretation (philosophy); Computer science; Artificial intelligence; Natural language processing; Programming language; Geology","score_opus":0.06760469934268502,"score_gpt":0.4221357942249032,"score_spread":0.3545310948822182,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402990496","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93721867,0.00067695306,0.044418793,0.013688153,0.00088538986,0.0019291181,0.000024989216,0.00033747553,0.000820444],"genre_scores_gemma":[0.98855674,0.000012383068,0.0070148823,0.0023444067,0.00019133481,0.00010949122,0.0003683122,0.000058420654,0.0013440199],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99689615,0.00047187437,0.0008614389,0.00079490937,0.00065053254,0.00032510134],"domain_scores_gemma":[0.99858296,0.00048003026,0.0000925131,0.0004555066,0.00018594129,0.00020305626],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022810095,0.00028158157,0.00044509588,0.0004313231,0.0000701695,0.00015882973,0.00010198107,0.00009815514,0.00024815535],"category_scores_gemma":[0.0027471227,0.00022024575,0.00011852959,0.00048408966,0.000068832545,0.0002949409,0.00005545175,0.0011289957,0.0001387783],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015073603,0.0057217693,0.050180573,0.00026581396,0.0009236399,0.017676637,0.04388238,0.001545727,0.0077071474,0.000053904274,0.0081320265,0.86240304],"study_design_scores_gemma":[0.0100360885,0.00019957696,0.080944724,0.0007382209,0.00036911742,0.00052414875,0.0029707889,0.9027771,0.000089495385,0.000031748874,0.001098575,0.00022043905],"about_ca_topic_score_codex":0.0084007,"about_ca_topic_score_gemma":0.0024206531,"teacher_disagreement_score":0.90123135,"about_ca_system_score_codex":0.0003185228,"about_ca_system_score_gemma":0.00021985527,"threshold_uncertainty_score":0.99820244},"labels":[],"label_agreement":null},{"id":"W4403055402","doi":"10.1088/2057-1976/ad8201","title":"Prediction of prostate cancer recurrence after radiotherapy using a fused machine learning approach: utilizing radiomics from pretreatment T2W MRI images with clinical and pathological information","year":2024,"lang":"en","type":"article","venue":"Biomedical Physics & Engineering Express","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Guelph General Hospital; University of Ottawa; University of Guelph","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Radiomics; Prostate cancer; Radiation therapy; Pathological; Medicine; Artificial intelligence; Medical physics; Cancer; Computer science; Radiology; Internal medicine","score_opus":0.01922426926035153,"score_gpt":0.2808961662478223,"score_spread":0.2616718969874708,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403055402","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.52295595,0.0037253452,0.47232988,0.00012469364,0.00026003172,0.00031253148,0.00012409744,0.00016197648,0.0000054981924],"genre_scores_gemma":[0.8274411,0.0019463258,0.16970496,0.00005631773,0.000489202,0.00007433374,0.0002327627,0.000046085806,0.000008947836],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983007,0.0000678134,0.00052076206,0.00038986953,0.0004334455,0.00028742346],"domain_scores_gemma":[0.99923766,0.00016180743,0.00011111163,0.00019005909,0.00005496406,0.00024442622],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037256902,0.0002699223,0.0004969444,0.00012939086,0.00004929477,0.00007788157,0.00008573844,0.00014958621,0.000011942515],"category_scores_gemma":[0.00009939571,0.00019573321,0.00010074272,0.0002835958,0.00031646265,0.00030531542,0.000057748948,0.0007877106,5.636809e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0027388167,0.0014552515,0.28621906,0.0056278184,0.0024881973,0.00046952534,0.011330023,0.05316369,0.25365666,0.00044904774,0.0005682423,0.38183367],"study_design_scores_gemma":[0.001751268,0.0003557842,0.015481199,0.0014149804,0.00023272535,0.00006450389,0.0000482844,0.9719064,0.0002639798,0.000025069907,0.008250479,0.0002053037],"about_ca_topic_score_codex":0.00013195151,"about_ca_topic_score_gemma":4.8322626e-8,"teacher_disagreement_score":0.9187427,"about_ca_system_score_codex":0.00008682634,"about_ca_system_score_gemma":0.00009640275,"threshold_uncertainty_score":0.7981769},"labels":[],"label_agreement":null},{"id":"W4403057544","doi":"10.1055/s-0044-1789979","title":"Expertenkohorte vs. Krebsregisterdaten – Analyse von Daten zu retroperitonealen Sarkomen","year":2024,"lang":"de","type":"article","venue":"Zeitschrift für Gastroenterologie","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre","funders":"","keywords":"Computer science","score_opus":0.019944474962610943,"score_gpt":0.3183462166396831,"score_spread":0.2984017416770722,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403057544","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.58926773,0.18010317,0.023988476,0.1476635,0.03322214,0.0033342442,0.0007739226,0.0038587844,0.017788041],"genre_scores_gemma":[0.9616969,0.013790677,0.00365626,0.008733273,0.0064267335,0.00006244453,0.0010887234,0.00035819146,0.0041867867],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9918814,0.00062647864,0.0016010694,0.0021765812,0.0012235023,0.0024910057],"domain_scores_gemma":[0.9961985,0.00023794462,0.0003160287,0.0018406924,0.00018978718,0.0012170738],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0018597415,0.001169435,0.0018169103,0.00083439925,0.0003297725,0.0008047311,0.0012840484,0.00054754585,0.0011743422],"category_scores_gemma":[0.0007715848,0.000947657,0.0007972593,0.00072697696,0.00082623144,0.000527251,0.0008880657,0.003116605,0.0023011602],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0038545013,0.00093023205,0.24160305,0.002840428,0.010569736,0.018852672,0.0027603111,0.000307029,0.010790529,0.00047266143,0.5419037,0.16511515],"study_design_scores_gemma":[0.0033103155,0.0034050555,0.019481268,0.0026366378,0.0034631595,0.00039769133,0.0005585135,0.11521841,0.00034794566,0.000026483856,0.8503445,0.0008100478],"about_ca_topic_score_codex":0.00045730083,"about_ca_topic_score_gemma":0.000016651948,"teacher_disagreement_score":0.3724292,"about_ca_system_score_codex":0.0001556531,"about_ca_system_score_gemma":0.0003430545,"threshold_uncertainty_score":0.9997387},"labels":[],"label_agreement":null},{"id":"W4403060138","doi":"10.1109/jbhi.2024.3472609","title":"A Dual-Branch Cross-Modality-Attention Network for Thyroid Nodule Diagnosis Based on Ultrasound Images and Contrast-Enhanced Ultrasound Videos","year":2024,"lang":"en","type":"article","venue":"IEEE Journal of Biomedical and Health Informatics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"National Natural Science Foundation of China","keywords":"Modality (human–computer interaction); Ultrasound; Radiology; Contrast-enhanced ultrasound; Nodule (geology); Contrast (vision); Thyroid; Thyroid nodules; Medicine; Computer science; Artificial intelligence; Internal medicine","score_opus":0.016109975842108996,"score_gpt":0.3453403807313979,"score_spread":0.3292304048892889,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403060138","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.59184784,0.0039440775,0.35947216,0.04138146,0.002205069,0.00082639384,0.00010958271,0.00006829374,0.00014515192],"genre_scores_gemma":[0.9686284,0.0043504736,0.015507863,0.009544304,0.0018134351,0.000022934164,0.000046794932,0.000027633563,0.000058175065],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973415,0.000055658656,0.0014067859,0.00014186709,0.0005958443,0.00045835756],"domain_scores_gemma":[0.9969678,0.0015621235,0.00046134647,0.000119307675,0.0001677602,0.00072168856],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030659747,0.00020774837,0.00062269456,0.0002334628,0.00026618413,0.00023077722,0.000074451484,0.00014512496,0.000026306348],"category_scores_gemma":[0.0008468769,0.00014451494,0.00015272225,0.00022444848,0.0003759921,0.000254222,0.000011321937,0.0007747945,0.0000028321842],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0025287413,0.0017098824,0.053679872,0.033153355,0.0012589511,0.0002107118,0.007108327,0.0015160309,0.014392031,0.0012794832,0.29808053,0.5850821],"study_design_scores_gemma":[0.04857022,0.03170537,0.30064595,0.033798452,0.0016499426,0.0093666585,0.001730061,0.3266079,0.003356284,0.01467921,0.2257992,0.0020907584],"about_ca_topic_score_codex":0.000016586702,"about_ca_topic_score_gemma":0.00000143717,"teacher_disagreement_score":0.5829913,"about_ca_system_score_codex":0.00009607694,"about_ca_system_score_gemma":0.00036682645,"threshold_uncertainty_score":0.5893148},"labels":[],"label_agreement":null},{"id":"W4403088751","doi":"10.1007/978-3-031-72086-4_25","title":"Ensemble of Prior-guided Expert Graph Models for Survival Prediction in Digital Pathology","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Hospital; University of Toronto","funders":"","keywords":"Computer science; Graph; Artificial intelligence; Digital pathology; Theoretical computer science","score_opus":0.023183980015146426,"score_gpt":0.2921533473873863,"score_spread":0.26896936737223986,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403088751","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0036358545,0.00081686553,0.98878336,0.0008566936,0.0015622448,0.00052026904,0.000017077251,0.00005406797,0.0037535792],"genre_scores_gemma":[0.9042614,0.00020389356,0.09215344,0.0010029636,0.0009639471,0.00003116813,0.00006690833,0.00009234172,0.0012239263],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99798095,0.00000803514,0.0004986573,0.00071895774,0.00045691573,0.00033646135],"domain_scores_gemma":[0.9989773,0.00031653602,0.00011636647,0.0003536425,0.00013672646,0.000099438876],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006460511,0.00025337626,0.0005633237,0.000730382,0.000042184114,0.00006133157,0.00030071198,0.00024514765,0.0000068078034],"category_scores_gemma":[0.00023839957,0.00021181465,0.0001424129,0.00023598647,0.0005204336,0.00014209335,0.00017696148,0.0007025541,0.0000022871682],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012595831,0.00012468628,0.0007823576,0.00062885846,0.00005511886,0.00043232308,0.0026446858,0.09131159,0.0027899344,0.017576125,0.00020327221,0.8833251],"study_design_scores_gemma":[0.00068556383,0.00028786075,0.000081321945,0.001177309,0.000019513598,0.000177196,7.29504e-7,0.7479476,0.00031083034,0.24849018,0.0006321521,0.00018978603],"about_ca_topic_score_codex":0.000019859248,"about_ca_topic_score_gemma":0.000009411555,"teacher_disagreement_score":0.9006256,"about_ca_system_score_codex":0.00013025188,"about_ca_system_score_gemma":0.00026157586,"threshold_uncertainty_score":0.8637551},"labels":[],"label_agreement":null},{"id":"W4403088925","doi":"10.1101/2024.10.02.616288","title":"ChIPbinner: An R package for analyzing broad histone marks binned in uniform windows from ChIP-Seq or CUT&amp;RUN/TAG data","year":2024,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; McGill Genome Centre","funders":"Canadian Institutes of Health Research; National Institutes of Health","keywords":"Chip; Computer science; Parallel computing; Telecommunications","score_opus":0.029956914138158305,"score_gpt":0.3074860668748076,"score_spread":0.2775291527366493,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403088925","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9776139,0.0037867469,0.007397273,0.0029249934,0.0029404145,0.0022615509,0.0022395165,0.0007970778,0.000038496695],"genre_scores_gemma":[0.95008767,0.00093682396,0.044124465,0.0010770281,0.0026226626,0.00029429572,0.00019714837,0.0005441998,0.00011568174],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99374497,0.00022695509,0.0014148466,0.0027068637,0.0007311652,0.001175219],"domain_scores_gemma":[0.9934,0.00031448068,0.0005975383,0.0045273225,0.0002929132,0.0008677523],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0023699445,0.001074686,0.0017751809,0.0010615072,0.00021927457,0.00044141748,0.0016854393,0.0009457402,0.00020048316],"category_scores_gemma":[0.0021159258,0.0009686626,0.000295774,0.0010708336,0.00026532562,0.000313131,0.0019205182,0.0037387556,0.00007786525],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0027529495,0.002110239,0.065912426,0.0077317804,0.002890079,0.0025162317,0.00036591693,0.00034830836,0.89786965,0.0009656551,0.015493759,0.0010430058],"study_design_scores_gemma":[0.02732627,0.0014480737,0.33085337,0.030251792,0.008936238,0.0000030664444,0.00013894567,0.28012252,0.049639363,0.00040232178,0.25945777,0.011420279],"about_ca_topic_score_codex":0.001344148,"about_ca_topic_score_gemma":0.00022880867,"teacher_disagreement_score":0.8482303,"about_ca_system_score_codex":0.0008056649,"about_ca_system_score_gemma":0.0017738442,"threshold_uncertainty_score":0.9992764},"labels":[],"label_agreement":null},{"id":"W4403138908","doi":"10.1007/978-3-031-73647-6_7","title":"An Evaluation of Low-Cost Hardware on 3D Ultrasound Reconstruction Accuracy","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University; Université TÉLUQ; NeuroRx Research (Canada); Montreal Neurological Institute and Hospital","funders":"","keywords":"Computer science; Computer hardware; Computer graphics (images); Computer vision; Artificial intelligence","score_opus":0.022727177897913554,"score_gpt":0.32497876496449407,"score_spread":0.3022515870665805,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403138908","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04295527,0.0009662719,0.9247948,0.001764967,0.0070202295,0.0018003997,0.00002593648,0.00019034966,0.0204818],"genre_scores_gemma":[0.9615422,0.000082131446,0.035633314,0.0010748903,0.0012863008,0.0000108585,0.00006162442,0.000057306257,0.0002513604],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973515,0.00003512851,0.0003857423,0.0007553693,0.0012281735,0.00024408757],"domain_scores_gemma":[0.9983137,0.00042542734,0.00019324681,0.0005762513,0.00035560274,0.00013576816],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016347159,0.0002622381,0.00038808282,0.0006094808,0.00008215104,0.000108048305,0.00032802165,0.00020233307,0.00015772555],"category_scores_gemma":[0.00091822585,0.00021532118,0.00008402528,0.0002430409,0.0005440141,0.00015349474,0.0000589754,0.001101173,0.00002491748],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018584693,0.000024923163,0.00017748869,0.00012916328,0.000015720425,0.000019086508,0.0002714436,0.027888697,0.0015055847,0.00047553825,0.000013692761,0.96946007],"study_design_scores_gemma":[0.00065117993,0.0003168974,0.00092073524,0.0043559936,0.00015486359,0.00043808634,9.4996466e-7,0.9557348,0.0028360656,0.03360574,0.00065263454,0.00033205602],"about_ca_topic_score_codex":0.000014669237,"about_ca_topic_score_gemma":0.000008814389,"teacher_disagreement_score":0.969128,"about_ca_system_score_codex":0.0003439093,"about_ca_system_score_gemma":0.0005596037,"threshold_uncertainty_score":0.8780543},"labels":[],"label_agreement":null},{"id":"W4403139160","doi":"10.1007/978-3-031-73647-6_3","title":"Do High-Performance Image-to-Image Translation Networks Enable the Discovery of Radiomic Features? Application to MRI Synthesis from Ultrasound in Prostate Cancer","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Translation (biology); Artificial intelligence; Ultrasound; Prostate cancer; Image translation; Image synthesis; Computer vision; Image (mathematics); Cancer; Radiology; Medicine","score_opus":0.0054691497750264766,"score_gpt":0.25092055958636805,"score_spread":0.2454514098113416,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403139160","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0339124,0.0019339088,0.95576066,0.005778267,0.0007617219,0.0012249616,0.00003651871,0.000041945466,0.00054960314],"genre_scores_gemma":[0.9428893,0.00057547993,0.054137588,0.0012299499,0.000691176,0.00009118439,0.000027769338,0.00005675914,0.00030083337],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977264,0.000025429692,0.00043952122,0.00085523527,0.0005706866,0.0003827752],"domain_scores_gemma":[0.99822474,0.00083946215,0.00014446463,0.0005958066,0.00008316388,0.00011236438],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007537604,0.0003221482,0.00051952177,0.0004513295,0.00010442137,0.00018658335,0.00056373194,0.00014368368,0.000020330119],"category_scores_gemma":[0.00013498224,0.00022514124,0.00007552176,0.00062041194,0.00044289455,0.00021913653,0.00012141037,0.0010859286,0.000008935069],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019341156,0.000035626486,0.0013575667,0.00028095444,0.000051440595,0.00004921544,0.0025809002,0.48366085,0.023641462,0.00024927326,0.00018306941,0.48771623],"study_design_scores_gemma":[0.000724814,0.00019545798,0.015394252,0.006029432,0.00019487344,0.000078934805,0.0000031459888,0.949345,0.015253052,0.010363862,0.001643422,0.0007737524],"about_ca_topic_score_codex":0.0007010311,"about_ca_topic_score_gemma":0.00012602034,"teacher_disagreement_score":0.90897685,"about_ca_system_score_codex":0.00029178662,"about_ca_system_score_gemma":0.00023965475,"threshold_uncertainty_score":0.91809934},"labels":[],"label_agreement":null},{"id":"W4403144265","doi":"10.3389/fnagi.2024.1460293","title":"MRI radiomics combined with machine learning for diagnosing mild cognitive impairment: a focus on the cerebellar gray and white matter","year":2024,"lang":"en","type":"article","venue":"Frontiers in Aging Neuroscience","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Eisai; Northern California Institute for Research and Education; Pfizer; Novartis Pharmaceuticals Corporation; University of Southern California; Biogen; Eli Lilly and Company; Bristol-Myers Squibb; BioClinica; U.S. Department of Defense; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; Alzheimer's Association","keywords":"Artificial intelligence; Support vector machine; Random forest; Machine learning; Gradient boosting; Cross-validation; Neuroimaging; Computer science; White matter; Logistic regression; Gray (unit); Test set; Boosting (machine learning); Cognitive impairment; Pattern recognition (psychology); Medicine; Magnetic resonance imaging; Psychology; Pathology; Disease; Nuclear medicine; Neuroscience; Radiology","score_opus":0.008869560283149712,"score_gpt":0.2530199809836115,"score_spread":0.24415042070046178,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403144265","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7762677,0.0017814134,0.15848702,0.059227552,0.0017254286,0.0016847012,0.000014983305,0.00019033857,0.0006208304],"genre_scores_gemma":[0.9906678,0.00028392038,0.003252721,0.0051100138,0.00007672736,0.00006114809,0.0000063343664,0.00005178751,0.00048950233],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983892,0.000100885874,0.00020381105,0.0005791083,0.00029501363,0.00043200664],"domain_scores_gemma":[0.9991865,0.0004393109,0.000060528513,0.00015532266,0.000025471498,0.00013286885],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006895922,0.00021768181,0.0002789516,0.00028149196,0.0003100804,0.00023008951,0.00015027157,0.000051471354,0.000006170806],"category_scores_gemma":[0.0002973139,0.00013940691,0.000057437122,0.0004927203,0.00042098592,0.00012038984,0.000058655518,0.001014052,0.0000018768187],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040839525,0.000099453784,0.9816658,0.00025839766,0.000028403083,0.00024323455,0.0020386928,0.0009527318,0.00042934102,0.00019462004,0.007267153,0.006413788],"study_design_scores_gemma":[0.0027277367,0.0012079508,0.08572245,0.0022568782,0.0001222281,0.00023116036,0.00044146006,0.9007795,0.0006123498,0.0006282557,0.0049206256,0.00034939626],"about_ca_topic_score_codex":0.000020990032,"about_ca_topic_score_gemma":0.000002132658,"teacher_disagreement_score":0.89982677,"about_ca_system_score_codex":0.00007031924,"about_ca_system_score_gemma":0.000058164973,"threshold_uncertainty_score":0.5684849},"labels":[],"label_agreement":null},{"id":"W4403148236","doi":"10.1007/s00261-024-04597-x","title":"Artificial intelligence for detection and characterization of focal hepatic lesions: a review","year":2024,"lang":"en","type":"review","venue":"Abdominal Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Hepatology; Medicine; Internal medicine; Pathology; General surgery; Gastroenterology; Radiology","score_opus":0.05082748852917917,"score_gpt":0.38968807911833314,"score_spread":0.33886059058915396,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403148236","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00010740285,0.9573116,0.04041715,0.0004287002,0.00041703117,0.0012652236,0.000012724187,0.000023245286,0.000016943788],"genre_scores_gemma":[0.00022497277,0.9977247,0.0009832183,0.00022012707,0.00039897725,0.00021610367,0.00013828426,0.00003959473,0.000054005257],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99835795,0.00015442821,0.0008603988,0.00035419618,0.000093032875,0.0001799665],"domain_scores_gemma":[0.99898624,0.00038780816,0.00030494828,0.00017566531,0.000055611996,0.00008973682],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00072311616,0.00023145095,0.0017495474,0.00020557297,0.00004011977,0.000007915912,0.00007825068,0.00022532574,0.000020596663],"category_scores_gemma":[0.001075065,0.0001645464,0.0003208017,0.00020164545,0.00017724311,0.000021385506,0.000036717363,0.00046593172,0.000012186963],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002906277,0.00001719973,4.5980082e-7,0.094018586,0.00010151288,0.000014633641,0.000016731143,3.0245715e-8,0.00023873299,0.0003267431,0.000039472314,0.90519685],"study_design_scores_gemma":[0.00009481192,0.00093012565,0.000007850726,0.12504491,0.009663114,0.0039120344,0.000008421923,0.006710302,0.00004398654,0.0010078759,0.8522892,0.00028738938],"about_ca_topic_score_codex":0.0000064086844,"about_ca_topic_score_gemma":7.724536e-7,"teacher_disagreement_score":0.90490943,"about_ca_system_score_codex":0.0000545246,"about_ca_system_score_gemma":0.00015347138,"threshold_uncertainty_score":0.6710008},"labels":[],"label_agreement":null},{"id":"W4403183629","doi":"10.1371/journal.pcbi.1012490","title":"Conditional probabilistic diffusion model driven synthetic radiogenomic applications in breast cancer","year":2024,"lang":"en","type":"article","venue":"PLoS Computational Biology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lawson Health Research Institute; Children’s Health Research Institute; University of Winnipeg; Western University","funders":"Canadian Institutes of Health Research; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Probabilistic logic; Computer science; Receiver operating characteristic; Artificial intelligence; Concordance; Computational biology; Pattern recognition (psychology); Medicine; Bioinformatics; Biology; Machine learning","score_opus":0.013135528880107177,"score_gpt":0.298956759556628,"score_spread":0.2858212306765208,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403183629","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8505533,0.0008492034,0.12977375,0.017045096,0.00013237982,0.00069553655,0.00033443124,0.000158449,0.00045787255],"genre_scores_gemma":[0.99421704,0.00004758671,0.0039783427,0.0005263046,0.0001648724,0.0001952286,0.00078702776,0.000018863133,0.000064741704],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99914557,0.000038319824,0.00022619298,0.0003121114,0.00011420538,0.00016360263],"domain_scores_gemma":[0.99946517,0.00028606784,0.000030223724,0.0000783772,0.00005510182,0.000085074586],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008093355,0.00010788196,0.00019391476,0.00018911094,0.0000581384,0.000015575102,0.00007143981,0.000066356486,0.00015688958],"category_scores_gemma":[0.00003431637,0.000088777575,0.000056171386,0.00016009732,0.00016352154,0.000028036175,0.00003130147,0.00026257097,0.000037159636],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006352243,0.00052837405,0.06942212,0.0003857324,0.00019675466,0.000032487682,0.00029800087,0.7508231,0.016395492,0.15275104,0.0006503623,0.008453005],"study_design_scores_gemma":[0.00032013102,0.000018237964,0.027277369,0.00011853121,0.000046939305,0.000107552725,0.0000062455015,0.9273991,0.000005529726,0.044234354,0.00038080377,0.000085234446],"about_ca_topic_score_codex":0.000021516782,"about_ca_topic_score_gemma":0.0000017330735,"teacher_disagreement_score":0.17657597,"about_ca_system_score_codex":0.00016666362,"about_ca_system_score_gemma":0.00025609747,"threshold_uncertainty_score":0.36202443},"labels":[],"label_agreement":null},{"id":"W4403222552","doi":"10.1145/3640457.3687116","title":"VideoRecSys + LargeRecSys 2024","year":2024,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Google (Canada)","funders":"","keywords":"Computer science","score_opus":0.00944146722145776,"score_gpt":0.3083812974718999,"score_spread":0.29893983025044213,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403222552","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.058091972,0.0058991998,0.039160043,0.063913554,0.003888059,0.000295386,0.0000032999596,0.0012179125,0.82753056],"genre_scores_gemma":[0.8530847,0.00015425701,0.008298985,0.003578316,0.0008004999,0.000009181298,0.000013189645,0.000038267608,0.1340226],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99926746,0.0000158013,0.00013945797,0.00020733764,0.0001850146,0.00018493061],"domain_scores_gemma":[0.99958956,0.00008444729,0.0000070987244,0.00014420068,0.000019243773,0.00015543921],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00030563245,0.00008481516,0.00014614384,0.00011083296,0.000031145933,0.000063717736,0.000045993547,0.000045346645,0.0044632326],"category_scores_gemma":[0.00015542575,0.000058103724,0.00009452424,0.00020166134,0.000040832445,0.00005036165,0.000024300789,0.00037472253,0.0010391588],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020368292,0.00006157137,0.0038368613,0.0004486007,0.00016398568,0.0009915405,0.00025901955,0.000008117279,0.0070738033,0.06965128,0.61810875,0.29937613],"study_design_scores_gemma":[0.00022836715,0.000055065142,0.00095909496,0.00025190203,0.00006426632,0.00037771396,0.000045055032,0.056615703,0.00053708506,0.0011808823,0.93958884,0.0000960115],"about_ca_topic_score_codex":0.000036754183,"about_ca_topic_score_gemma":9.821925e-7,"teacher_disagreement_score":0.79499274,"about_ca_system_score_codex":0.000031132487,"about_ca_system_score_gemma":0.00007205382,"threshold_uncertainty_score":0.99973863},"labels":[],"label_agreement":null},{"id":"W4403226303","doi":"10.1016/j.cjca.2024.08.236","title":"A NOVEL APPROACH IN VASCULAR IMAGING: 3D RECONSTRUCTION FROM 2D ULTRASOUND VIA ADVANCED DEEP LEARNING","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Cardiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine; Deep learning; Radiology; Ultrasound imaging; Ultrasound; Artificial intelligence","score_opus":0.00669614594245572,"score_gpt":0.23555223062386735,"score_spread":0.22885608468141164,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403226303","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46334323,0.015337267,0.5066847,0.0014272169,0.002790215,0.00017550851,0.0000054707634,0.00003247708,0.01020388],"genre_scores_gemma":[0.9850444,0.00021983228,0.013226805,0.0001973602,0.001229582,0.000002695074,0.000019280722,0.00003012187,0.000029914961],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99879557,0.00012444808,0.0003919234,0.00022389242,0.00013124982,0.00033288778],"domain_scores_gemma":[0.9990711,0.00016934237,0.000089201574,0.00012382005,0.00008964829,0.00045684545],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006852576,0.00013405901,0.00050478545,0.0005265594,0.00006132097,0.000042240987,0.00010842195,0.00010496357,0.00003681249],"category_scores_gemma":[0.00063244475,0.00012057495,0.0002096519,0.00022509207,0.00017732919,0.00012022998,0.000006803782,0.0013509959,0.0000057998946],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000059028916,0.000006303084,0.17661507,0.0000880499,0.000639709,0.001719613,0.0012723438,0.058616854,0.023785088,0.00010826322,0.0005125443,0.73657715],"study_design_scores_gemma":[0.006834266,0.00043357024,0.27285865,0.0014844576,0.0010256508,0.06344513,0.0029257378,0.2159072,0.000097013886,0.0016607227,0.43249854,0.00082904793],"about_ca_topic_score_codex":0.0014239321,"about_ca_topic_score_gemma":0.00016041305,"teacher_disagreement_score":0.73574805,"about_ca_system_score_codex":0.00029771187,"about_ca_system_score_gemma":0.0005696778,"threshold_uncertainty_score":0.586948},"labels":[],"label_agreement":null},{"id":"W4403352027","doi":"10.1007/978-3-031-72787-0_12","title":"Do Sites Benefit Equally from Distributed Learning in Medical Image Analysis?","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut Universitaire de Gériatrie de Montréal; Hotchkiss Brain Institute; Alberta Children's Hospital; Women and Children’s Health Research Institute; Université de Montréal; University of Alberta; University of Calgary","funders":"","keywords":"Computer science; Artificial intelligence; Image (mathematics); Computer vision","score_opus":0.010602241721144256,"score_gpt":0.2892868563020302,"score_spread":0.27868461458088595,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403352027","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0116796885,0.0024910332,0.975344,0.006101659,0.0006410035,0.00024853792,0.000026978687,0.00018173883,0.0032853459],"genre_scores_gemma":[0.93739337,0.0002991317,0.05624643,0.0027790575,0.0014618377,0.000008456385,0.0006414877,0.00010280122,0.0010674098],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99557745,0.000032427914,0.00070782023,0.0014016184,0.0016737544,0.00060689787],"domain_scores_gemma":[0.9977712,0.0009288165,0.00017410716,0.0005905903,0.00013189553,0.00040341506],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0014280439,0.00046985928,0.001044131,0.001449057,0.000105998144,0.00033068663,0.0008002648,0.00045959276,0.00064296694],"category_scores_gemma":[0.0011584985,0.00038731625,0.00028701866,0.0013122552,0.00078888255,0.00011762794,0.0006448993,0.0037601741,0.00006815974],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008413794,0.00013859387,0.03326297,0.0002832992,0.0006824701,0.00841989,0.0017579371,0.09858822,0.0009795747,0.004851223,0.00008974494,0.85086197],"study_design_scores_gemma":[0.00058301946,0.00011946007,0.0045966324,0.0016760499,0.0003315392,0.00006746279,0.0000011112902,0.9495595,0.000060104514,0.040615868,0.0019230153,0.00046622963],"about_ca_topic_score_codex":0.0002023769,"about_ca_topic_score_gemma":0.00021713888,"teacher_disagreement_score":0.9257137,"about_ca_system_score_codex":0.00034819022,"about_ca_system_score_gemma":0.00047253133,"threshold_uncertainty_score":0.9998579},"labels":[],"label_agreement":null},{"id":"W4403410155","doi":"10.1016/j.jtho.2024.09.546","title":"P3.03H.01 Tumour Educated Platelets Display a Distinct RNA Content Profile Across Metastatic Patterns in NSCLC.","year":2024,"lang":"en","type":"article","venue":"Journal of Thoracic Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Trinity College","funders":"","keywords":"Medicine; Oncology; Platelet; Internal medicine","score_opus":0.036810013516444175,"score_gpt":0.43994512838387484,"score_spread":0.40313511486743064,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403410155","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9767507,0.0013673952,0.0027210426,0.016261086,0.0019720797,0.00027635114,0.000018746552,0.00003196315,0.00060068216],"genre_scores_gemma":[0.995483,0.000121671554,0.00201781,0.0007574188,0.0006205327,0.000013687306,0.00001985438,0.000044607357,0.0009214183],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99757975,0.0002979842,0.0009793016,0.00025965614,0.00038996505,0.00049333536],"domain_scores_gemma":[0.9984831,0.000501621,0.00037725622,0.00015483385,0.00013843371,0.00034471333],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019924338,0.00022008909,0.0008751724,0.00030375484,0.00006098682,0.00007176078,0.00021227954,0.00011275926,0.0003022277],"category_scores_gemma":[0.0009252557,0.00015194294,0.00023737198,0.0003127987,0.0001305974,0.00015441392,0.000074360054,0.001723818,0.00004281293],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0028242376,0.0016124301,0.03506467,0.0015095255,0.000793536,0.041748438,0.004973545,0.00009945759,0.03875429,0.000096081065,0.008893656,0.8636301],"study_design_scores_gemma":[0.012130774,0.0127809895,0.58097583,0.016807573,0.0030045107,0.09359528,0.009600873,0.13020346,0.007805195,0.0012225442,0.1303194,0.0015535316],"about_ca_topic_score_codex":0.000121936646,"about_ca_topic_score_gemma":0.00006773615,"teacher_disagreement_score":0.8620766,"about_ca_system_score_codex":0.000473131,"about_ca_system_score_gemma":0.00066559203,"threshold_uncertainty_score":0.74892277},"labels":[],"label_agreement":null},{"id":"W4403410443","doi":"10.1016/j.jtho.2024.09.013","title":"PL02.07 Neocoast-2: Efficacy and Safety of Neoadjuvant Durvalumab (D) + Novel Anticancer Agents + CT and Adjuvant D ± Novel Agents in Resectable NSCLC","year":2024,"lang":"fr","type":"article","venue":"Journal of Thoracic Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Centre Hospitalier de l’Université de Montréal","funders":"","keywords":"Medicine; Durvalumab; Adjuvant; Oncology; Internal medicine; Cancer; Immunotherapy","score_opus":0.03654236561430961,"score_gpt":0.42623399955929653,"score_spread":0.3896916339449869,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403410443","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88726276,0.07547149,0.0047846516,0.023011634,0.006844298,0.0005574379,0.00004543703,0.000016674134,0.0020055869],"genre_scores_gemma":[0.9717456,0.016237276,0.0078066094,0.00080809736,0.0014177032,0.000004155728,0.0000070887013,0.000077371835,0.0018960957],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99583584,0.00039688378,0.001786374,0.0005029613,0.00068508,0.00079286547],"domain_scores_gemma":[0.9968027,0.0013614038,0.0007371375,0.0002701723,0.00021751296,0.0006111107],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.004428469,0.00038978673,0.0016724741,0.00070597045,0.000100508856,0.000072768766,0.0002873171,0.00024950822,0.00041053636],"category_scores_gemma":[0.0019449507,0.00032838114,0.00020102962,0.0005348797,0.0007592074,0.00032893848,0.00029236736,0.0023811408,0.000013946551],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0041445973,0.001904124,0.012428828,0.0023346012,0.0008902368,0.007228556,0.002942964,0.001133479,0.018559778,0.00064534764,0.004829747,0.94295776],"study_design_scores_gemma":[0.021662077,0.0066584293,0.2559138,0.030567221,0.0029266854,0.030917779,0.0018110208,0.19618559,0.0008549117,0.00045782223,0.45122325,0.0008214079],"about_ca_topic_score_codex":0.00045115952,"about_ca_topic_score_gemma":0.000053913598,"teacher_disagreement_score":0.94213635,"about_ca_system_score_codex":0.00065149873,"about_ca_system_score_gemma":0.0012119656,"threshold_uncertainty_score":0.9999204},"labels":[],"label_agreement":null},{"id":"W4403443939","doi":"10.48550/arxiv.2409.19483","title":"MedCLIP-SAMv2: Towards Universal Text-Driven Medical Image Segmentation","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Segmentation; Image (mathematics); Computer science; Computer vision; Artificial intelligence; Image segmentation","score_opus":0.03577876684421793,"score_gpt":0.2441456071711638,"score_spread":0.20836684032694586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403443939","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8563475,0.00041928538,0.0888961,0.010049716,0.0027324914,0.000940156,0.00006816706,0.00089278456,0.039653823],"genre_scores_gemma":[0.9864615,0.00090663123,0.0032725083,0.0007569814,0.0006519504,0.0000016832726,0.00025847196,0.000091702146,0.00759856],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99745435,0.00016090868,0.0003398739,0.0011368159,0.0004378562,0.00047022902],"domain_scores_gemma":[0.9981876,0.00011324689,0.0001809828,0.00064125215,0.0001648593,0.00071207865],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00049143477,0.00043896586,0.0006370013,0.000469465,0.00012069678,0.00008552667,0.00056042685,0.0005834996,0.001427984],"category_scores_gemma":[0.0003535982,0.00044346802,0.00042279245,0.00048305816,0.0004356751,0.0001097608,0.0014426163,0.0028644658,0.0004562264],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0033986964,0.0035986241,0.044489834,0.016429216,0.01198873,0.17876464,0.008517278,0.07175879,0.010921965,0.20195104,0.14483643,0.30334476],"study_design_scores_gemma":[0.0037304421,0.00024729548,0.0025902544,0.0021170392,0.0020642853,0.0002492477,0.0008692885,0.9562615,0.00035268877,0.017668452,0.01285672,0.0009927768],"about_ca_topic_score_codex":0.00046750606,"about_ca_topic_score_gemma":0.000023846122,"teacher_disagreement_score":0.8845027,"about_ca_system_score_codex":0.000609682,"about_ca_system_score_gemma":0.0010951192,"threshold_uncertainty_score":0.9998017},"labels":[],"label_agreement":null},{"id":"W4403459655","doi":"10.1097/mnm.0000000000001895","title":"Combination of FDG PET/CT radiomics and clinical parameters for outcome prediction in patients with non-Hodgkin’s lymphoma","year":2024,"lang":"en","type":"article","venue":"Nuclear Medicine Communications","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; Public Health Ontario; Hospital for Sick Children; Women's College Hospital; University of Toronto; University Health Network; Mount Sinai Hospital","funders":"","keywords":"Medicine; Contouring; Nuclear medicine; Radiomics; PET-CT; Lymphoma; Positron emission tomography; Radiology; Internal medicine","score_opus":0.029490869241270503,"score_gpt":0.3512600869928267,"score_spread":0.3217692177515562,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403459655","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9843894,0.00033284942,0.0009207397,0.012173531,0.00027326087,0.0007884281,0.000015557061,0.0000755254,0.0010306916],"genre_scores_gemma":[0.9857187,0.0004167773,0.012961109,0.0005677791,0.000040981373,0.000021884074,0.00016422168,0.000045178225,0.00006333106],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.998592,0.0000952858,0.0006843029,0.00023909874,0.00023454089,0.00015478105],"domain_scores_gemma":[0.9982155,0.0007298347,0.00012609894,0.00067416095,0.00012463234,0.00012978155],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009503193,0.00013206775,0.0004304206,0.00027749446,0.00008848674,0.000016048984,0.00021941304,0.000028029015,0.00001629177],"category_scores_gemma":[0.0007845623,0.00010143286,0.00006853034,0.00027916033,0.0005781522,0.00009882566,0.00008185247,0.00037277638,0.0000031299783],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031562836,0.0008202889,0.90059084,0.00043769754,0.00022173602,0.000016008815,0.0007026135,0.000013855401,0.000044637807,0.004370152,0.0036722987,0.08879426],"study_design_scores_gemma":[0.008511947,0.0015615359,0.7790368,0.0010162174,0.00035976197,0.000069626076,0.0002746855,0.19505063,0.0000015225074,0.00023866589,0.013765827,0.000112748035],"about_ca_topic_score_codex":0.000101803795,"about_ca_topic_score_gemma":0.0000084846515,"teacher_disagreement_score":0.19503677,"about_ca_system_score_codex":0.00009739073,"about_ca_system_score_gemma":0.00006185567,"threshold_uncertainty_score":0.4136312},"labels":[],"label_agreement":null},{"id":"W4403464952","doi":"10.1016/j.jtho.2024.09.1052","title":"EP.08B.03 Prognostic Value of Irradiated Cardiac and Metabolic Tumor Volume in Unresected LA-NSCLC Treated with Concurrent Chemo-Radiotherapy.","year":2024,"lang":"en","type":"article","venue":"Journal of Thoracic Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hamilton Health Sciences; McMaster University; Niagara Health System; Juravinski Cancer Centre","funders":"","keywords":"Medicine; Radiation therapy; Internal medicine; Oncology; Volume (thermodynamics); Radiology","score_opus":0.0093149249322927,"score_gpt":0.36574370777628645,"score_spread":0.35642878284399376,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403464952","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9741612,0.020580122,0.00023749837,0.003802506,0.00041477222,0.00030913678,0.000006776283,0.000028353941,0.00045959992],"genre_scores_gemma":[0.9959686,0.0011147573,0.0021748834,0.00017605635,0.0002870875,0.000008644905,0.000007306563,0.000042076623,0.00022062201],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9980157,0.0005098786,0.0006632847,0.00021904254,0.00031078456,0.00028132446],"domain_scores_gemma":[0.9986572,0.00046717422,0.00032711148,0.00012439364,0.00017403362,0.00025006678],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012953068,0.00019853302,0.0010940444,0.0005314967,0.000025766565,0.000029919362,0.00011256402,0.00013038817,0.000046876386],"category_scores_gemma":[0.0005654181,0.00013478445,0.000140462,0.00059501483,0.0002585627,0.00009798968,0.000023270484,0.0010665224,0.0000020379828],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0036421039,0.0012212171,0.32701766,0.0013974734,0.0027179816,0.008616523,0.0027212573,0.00044519024,0.058053937,0.00043531798,0.004442921,0.5892884],"study_design_scores_gemma":[0.005204069,0.0059167435,0.8186645,0.0031399573,0.0023563039,0.008974664,0.0004236555,0.059209045,0.001521323,0.00010322894,0.09410405,0.0003824447],"about_ca_topic_score_codex":0.00007391749,"about_ca_topic_score_gemma":0.0000036891895,"teacher_disagreement_score":0.588906,"about_ca_system_score_codex":0.00018038055,"about_ca_system_score_gemma":0.0007141766,"threshold_uncertainty_score":0.549635},"labels":[],"label_agreement":null},{"id":"W4403486871","doi":"10.3390/cancers16203511","title":"Enhancing Lymphoma Diagnosis, Treatment, and Follow-Up Using 18F-FDG PET/CT Imaging: Contribution of Artificial Intelligence and Radiomics Analysis","year":2024,"lang":"en","type":"review","venue":"Cancers","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Shahid Beheshti University of Medical Sciences; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Radiomics; Medicine; Positron emission tomography; Pet imaging; Lymphoma; Medical imaging; Radiology; Medical physics; Pathology","score_opus":0.03709246266534801,"score_gpt":0.36646225975161467,"score_spread":0.3293697970862667,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403486871","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0103339935,0.98506737,0.003314902,0.000069882175,0.000589333,0.0005058498,0.000058145608,0.000039375518,0.00002116992],"genre_scores_gemma":[0.023811715,0.9749641,0.00062173756,0.00004556364,0.00025294206,0.000054908734,0.00014485858,0.0000559055,0.00004828648],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99798894,0.00009803862,0.00077028206,0.0006199449,0.00018808838,0.00033472248],"domain_scores_gemma":[0.99875826,0.0002670816,0.00038290795,0.0002758537,0.00007447506,0.0002414273],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004062554,0.00043167363,0.0021530725,0.00061041524,0.00010480868,0.00008262451,0.00008712443,0.000035770485,0.000020361564],"category_scores_gemma":[0.00035548254,0.00033979642,0.00055597257,0.0008519954,0.00029806467,0.00006237739,0.00006030021,0.00026766147,0.000002001041],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002100711,0.000017029495,0.00054910494,0.004029039,0.002276458,0.00042586905,0.00009845379,0.000049702758,0.000017352217,0.00014663681,0.000037744907,0.9923316],"study_design_scores_gemma":[0.0014392342,0.00035553347,0.000036446072,0.0385653,0.15285769,0.004878096,0.00050911563,0.19381803,0.0004627871,0.00030770994,0.60538566,0.0013844058],"about_ca_topic_score_codex":0.0011693594,"about_ca_topic_score_gemma":0.000066012486,"teacher_disagreement_score":0.9909472,"about_ca_system_score_codex":0.0021084347,"about_ca_system_score_gemma":0.0011039524,"threshold_uncertainty_score":0.9999054},"labels":[],"label_agreement":null},{"id":"W4403549023","doi":"10.3390/engproc2024076026","title":"An Intelligent System for the Early Detection of Prostate Cancer","year":2024,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Regina","funders":"","keywords":"Computer science; Prostate cancer; Cancer detection; Cancer; Medicine; Internal medicine","score_opus":0.01239421268577786,"score_gpt":0.3210194542837812,"score_spread":0.30862524159800336,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403549023","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7739266,0.0039578415,0.21538189,0.0035222361,0.0014105618,0.00089289655,0.0000056615845,0.00020959153,0.00069267483],"genre_scores_gemma":[0.9982416,0.00011278519,0.00034158406,0.00008977894,0.00021153019,0.00006615053,0.0000014416562,0.000013423802,0.0009217221],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995872,0.000010889471,0.0001230699,0.00009997018,0.00009589491,0.00008302381],"domain_scores_gemma":[0.99971586,0.00007771313,0.000017995802,0.000101644335,0.00004320004,0.00004356667],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027438396,0.000044466036,0.0000857065,0.000029015058,0.000034857138,0.00002334495,0.000038578713,0.00001924315,0.00001837717],"category_scores_gemma":[0.000030655225,0.000022978395,0.000047708876,0.00007982523,0.000030778046,0.00002887095,0.000005652613,0.00011374797,0.0000029628502],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012263711,0.000025914289,0.0024181916,0.0012992804,0.00015640241,0.0000071395707,0.0013747101,0.0003508441,0.074205704,0.0030721284,0.00035357583,0.91661346],"study_design_scores_gemma":[0.00033916233,0.00044276938,0.003627109,0.0005912832,0.00023070931,0.000037894904,0.00087667955,0.88435996,0.07531685,0.00008292416,0.034022152,0.000072523944],"about_ca_topic_score_codex":0.0005637642,"about_ca_topic_score_gemma":0.00001272813,"teacher_disagreement_score":0.9165409,"about_ca_system_score_codex":0.00003992601,"about_ca_system_score_gemma":0.000037630787,"threshold_uncertainty_score":0.09370317},"labels":[],"label_agreement":null},{"id":"W4403585735","doi":"10.5194/sp-2024-8-rc1","title":"Comment on sp-2024-8","year":2024,"lang":"en","type":"peer-review","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Environmental science","score_opus":0.026913729817442843,"score_gpt":0.36487839898363594,"score_spread":0.3379646691661931,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403585735","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[9.816664e-7,0.029465156,0.00009141234,0.6342498,0.006068067,0.00037034357,0.000024819568,0.0001291675,0.32960024],"genre_scores_gemma":[0.000007240738,0.008302137,0.00057583937,0.36736745,0.0012270405,0.000026241982,0.00057903875,0.00005936153,0.6218557],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99805075,0.000043923894,0.000397417,0.00049703836,0.0007122276,0.00029862497],"domain_scores_gemma":[0.9989001,0.0001283265,0.00007215086,0.0005590179,0.00006666211,0.0002737386],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00060386205,0.0003385366,0.0008445991,0.00017646381,0.000037891037,0.00004074894,0.00016896919,0.00018474642,0.011891958],"category_scores_gemma":[0.00041303338,0.00022383426,0.00034538802,0.00017186403,0.000058470287,0.000009156735,0.0001164476,0.0022964189,0.0028085252],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000065430554,0.00006338757,0.000004044612,0.008095508,0.0001565009,0.00028544795,0.000008525279,4.7284868e-7,0.0000011160688,0.0010248113,0.9478372,0.04251647],"study_design_scores_gemma":[0.00027335578,0.00018131349,0.0000057575107,0.026070245,0.0007029734,0.000101136335,0.0000037729878,0.00060680666,0.000003537366,0.00016507534,0.9716775,0.00020852897],"about_ca_topic_score_codex":0.00013982799,"about_ca_topic_score_gemma":0.0000026534137,"teacher_disagreement_score":0.2922554,"about_ca_system_score_codex":0.00015593815,"about_ca_system_score_gemma":0.0001764507,"threshold_uncertainty_score":0.9979679},"labels":[],"label_agreement":null},{"id":"W4403620826","doi":"10.48550/arxiv.2409.06821","title":"Sam2Rad: A Segmentation Model for Medical Images with Learnable Prompts","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Alberta Innovates; Arthritis Society; Compute Canada; Canadian Institute for Advanced Research","keywords":"Segmentation; Computer science; Artificial intelligence; Computer vision; Computer graphics (images); Pattern recognition (psychology)","score_opus":0.044066117890538464,"score_gpt":0.24113784715386852,"score_spread":0.19707172926333005,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403620826","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32922503,0.00023246942,0.6623132,0.003353303,0.00030283394,0.0011537205,0.00003322066,0.00030695618,0.0030792528],"genre_scores_gemma":[0.9672782,0.0002412371,0.008330044,0.00047563837,0.00023794897,0.000010706336,0.00015989323,0.00007602445,0.023190316],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983587,0.000040810162,0.00020384416,0.0008260121,0.00022847735,0.00034210784],"domain_scores_gemma":[0.99892515,0.0000869989,0.00012294794,0.0003786782,0.00013993039,0.00034631768],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004144079,0.0002850913,0.00043449568,0.00022952176,0.00010405298,0.00005746718,0.00025308828,0.00028050493,0.00009518965],"category_scores_gemma":[0.00017163657,0.0002477395,0.00019101567,0.0002062358,0.00018715102,0.000064618645,0.00039379537,0.0013658183,0.000029428676],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014471886,0.0005251454,0.0049323584,0.0058494057,0.001386136,0.0032188976,0.0010008664,0.9305457,0.00084031787,0.024173157,0.016221039,0.009859825],"study_design_scores_gemma":[0.0016884321,0.00015407441,0.000083903265,0.0009229245,0.0006614209,0.0000561394,0.000107011314,0.98352194,0.000097423756,0.012000642,0.0004418042,0.0002642663],"about_ca_topic_score_codex":0.0000984804,"about_ca_topic_score_gemma":0.000012774971,"teacher_disagreement_score":0.6539832,"about_ca_system_score_codex":0.00022110232,"about_ca_system_score_gemma":0.0008116377,"threshold_uncertainty_score":0.9999975},"labels":[],"label_agreement":null},{"id":"W4403630026","doi":"10.1152/physiolgenomics.00011.2024","title":"Artificial intelligence and omics in malignant gliomas","year":2024,"lang":"en","type":"review","venue":"Physiological Genomics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Genome Canada","funders":"Mohammed Bin Rashid University of Medicine and Health Sciences; Saudi Heart Association; Al Jalila Foundation","keywords":"Omics; Precision medicine; Artificial intelligence; Big data; Computer science; Data science; Metabolomics; Computational biology; Biomarker discovery; Biomarker; Systems biology; Machine learning; Biology; Scale (ratio); Bioinformatics; Proteomics; Data mining; Gene","score_opus":0.11253730237888655,"score_gpt":0.38494337240541765,"score_spread":0.2724060700265311,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403630026","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013622264,0.99705195,0.00021006327,0.00019965207,0.00032387674,0.0005591836,0.000013808252,0.000068118134,0.00021110156],"genre_scores_gemma":[0.00090660504,0.9965901,0.001453713,0.00021131543,0.00056436646,0.000043053977,0.00010089503,0.00006121359,0.00006877234],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978515,0.000100444246,0.0008011279,0.0007125636,0.00013397534,0.0004003885],"domain_scores_gemma":[0.9991947,0.0001608218,0.00013533131,0.00028479664,0.000017306538,0.00020706489],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00040449767,0.00042563333,0.0018015043,0.0002472332,0.000041485167,0.00006067326,0.00019946814,0.00037687612,0.0000276675],"category_scores_gemma":[0.0002711149,0.00026949018,0.0003407898,0.00036130237,0.0002435853,0.000020468997,0.0002980392,0.0014533773,0.00015906988],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014801208,0.000078164274,0.0000019257384,0.005202794,0.000069913214,0.0003229365,0.00004551224,0.00001042334,0.000090258356,0.0035205109,0.00009915477,0.9905436],"study_design_scores_gemma":[0.00007698737,0.00030952765,0.000026538582,0.00887782,0.0012311426,0.0005461209,0.000046429683,0.0074627707,0.000008465839,0.020663597,0.96009046,0.0006601424],"about_ca_topic_score_codex":0.000013456046,"about_ca_topic_score_gemma":0.0000010239095,"teacher_disagreement_score":0.9898835,"about_ca_system_score_codex":0.00017860213,"about_ca_system_score_gemma":0.00018440117,"threshold_uncertainty_score":0.99997574},"labels":[],"label_agreement":null},{"id":"W4403684294","doi":"10.1097/rlu.0000000000005526","title":"Fully Automated Region-Specific Human-Perceptive-Equivalent Image Quality Assessment: Application to 18F-FDG PET Scans","year":2024,"lang":"en","type":"article","venue":"Clinical Nuclear Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Hôpitaux Universitaires de Genève; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Medicine; Image quality; Artificial intelligence; Nuclear medicine; Quality assurance; Radiology; Pattern recognition (psychology); Computer science; Image (mathematics); Pathology","score_opus":0.0811899017269002,"score_gpt":0.4844294036184694,"score_spread":0.4032395018915692,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403684294","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7130079,0.0006829756,0.03926269,0.20534277,0.002597005,0.0018654657,0.000017608088,0.003928892,0.0332947],"genre_scores_gemma":[0.977589,0.00059196795,0.006682003,0.010768243,0.0029596782,0.00003763864,0.00014995244,0.00015148116,0.0010700485],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99545395,0.0003954835,0.0016054132,0.0011172484,0.000886581,0.00054132764],"domain_scores_gemma":[0.9969642,0.0006866389,0.00019021341,0.00096235756,0.00023137692,0.0009651931],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0034188374,0.00036484963,0.0010377015,0.0002873642,0.00024484773,0.00008684499,0.0003728221,0.00014669445,0.001392605],"category_scores_gemma":[0.0011500547,0.00028208425,0.0003151034,0.00065572374,0.00089368504,0.00012828845,0.0001702003,0.0016560308,0.0009761513],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041713813,0.00096359814,0.0075093783,0.0009321712,0.0004030385,0.001996221,0.0013765596,0.000031779116,0.048907448,0.030484358,0.8002588,0.10671952],"study_design_scores_gemma":[0.0034668657,0.001966263,0.2616846,0.0020265724,0.00034024182,0.00050088257,0.00087402645,0.07508511,0.00000728974,0.0009757098,0.6525477,0.0005247149],"about_ca_topic_score_codex":0.0001114065,"about_ca_topic_score_gemma":0.0000030696133,"teacher_disagreement_score":0.26458108,"about_ca_system_score_codex":0.00027433177,"about_ca_system_score_gemma":0.00012386988,"threshold_uncertainty_score":0.9999631},"labels":[],"label_agreement":null},{"id":"W4403754242","doi":"10.48550/arxiv.2409.14256","title":"POI-SIMEX for Conditionally Poisson Distributed Biomarkers from Tissue Histology","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; BC Cancer Foundation; Terry Fox Research Institute","keywords":"Histology; Poisson distribution; Poisson regression; Medicine; Computer science; Internal medicine; Mathematics; Environmental health; Statistics","score_opus":0.03931931306270522,"score_gpt":0.23623710993139463,"score_spread":0.1969177968686894,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403754242","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.77970016,0.0012675157,0.1986415,0.009450906,0.0029177612,0.0012397828,0.0026157897,0.0005297333,0.0036368566],"genre_scores_gemma":[0.9881697,0.00011129514,0.0015197727,0.0005289753,0.00039795385,0.0000046609384,0.005760195,0.000061541454,0.0034458977],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998168,0.000075217526,0.00027290813,0.0010173533,0.00010284842,0.00036367777],"domain_scores_gemma":[0.99852616,0.00032371056,0.00018601333,0.0005144101,0.00014252841,0.00030715409],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002166834,0.0003367204,0.0006013255,0.00027304044,0.00010873659,0.000039121125,0.00032816883,0.00045816906,0.00041106236],"category_scores_gemma":[0.00029781615,0.00036317078,0.00031392172,0.0002265683,0.00027562233,0.000036426867,0.00047441912,0.0010602897,0.00011868956],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0058416612,0.0018126239,0.034784533,0.0061299857,0.016503586,0.023343937,0.0012760593,0.046026636,0.017538548,0.29297492,0.5348213,0.01894622],"study_design_scores_gemma":[0.006011547,0.0004430339,0.00983809,0.0014218448,0.004499608,0.00011282343,0.00026550604,0.524241,0.0005778578,0.2882189,0.16302684,0.0013429731],"about_ca_topic_score_codex":0.00055997766,"about_ca_topic_score_gemma":0.000021829257,"teacher_disagreement_score":0.47821435,"about_ca_system_score_codex":0.00045131493,"about_ca_system_score_gemma":0.00036623536,"threshold_uncertainty_score":0.99988204},"labels":[],"label_agreement":null},{"id":"W4403759165","doi":"10.1016/j.brachy.2024.08.109","title":"GSOR11 Presentation Time: 12:20 PM","year":2024,"lang":"en","type":"article","venue":"Brachytherapy","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Health; Alberta Health Services","funders":"","keywords":"Medicine; Presentation (obstetrics); Medical physics; Surgery","score_opus":0.010651194972315247,"score_gpt":0.31500864339450335,"score_spread":0.3043574484221881,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403759165","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7816239,0.014923768,0.02616196,0.06995413,0.0025882532,0.0015467966,0.000010685788,0.0016183764,0.101572104],"genre_scores_gemma":[0.87150806,0.0011465722,0.008319655,0.0077287788,0.0033769924,0.000085108644,0.00019650444,0.00015776882,0.10748053],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99912375,0.00004020013,0.00018169089,0.00023002061,0.00024306323,0.0001812549],"domain_scores_gemma":[0.99955696,0.00011364874,0.000025183323,0.00016989897,0.00002244116,0.00011185255],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00025870878,0.000109680754,0.00020422477,0.00010880288,0.000049293933,0.0000747156,0.000057855217,0.000056287387,0.001181935],"category_scores_gemma":[0.00007732392,0.00008386329,0.000113562695,0.00014482306,0.000051100677,0.00009801213,0.000010825487,0.00030767458,0.0004977576],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041782987,0.00018072288,0.005870134,0.00026475714,0.00036786197,0.00048240455,0.0013057227,0.00010828821,0.08794485,0.0023877681,0.16468404,0.73598564],"study_design_scores_gemma":[0.00331929,0.0003307583,0.01025709,0.00032067767,0.000111095535,0.0004401834,0.00003519748,0.20339379,0.0012934901,0.0015050473,0.77875865,0.00023471714],"about_ca_topic_score_codex":0.000019473704,"about_ca_topic_score_gemma":8.133589e-7,"teacher_disagreement_score":0.7357509,"about_ca_system_score_codex":0.000032060954,"about_ca_system_score_gemma":0.0000670561,"threshold_uncertainty_score":0.9997311},"labels":[],"label_agreement":null},{"id":"W4403763639","doi":"10.5194/sp-2024-8-rc3","title":"Comment on sp-2024-8","year":2024,"lang":"en","type":"peer-review","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Art","score_opus":0.026913729817442843,"score_gpt":0.36487839898363594,"score_spread":0.3379646691661931,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403763639","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[9.816664e-7,0.029465156,0.00009141234,0.6342498,0.006068067,0.00037034357,0.000024819568,0.0001291675,0.32960024],"genre_scores_gemma":[0.000007240738,0.008302137,0.00057583937,0.36736745,0.0012270405,0.000026241982,0.00057903875,0.00005936153,0.6218557],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99805075,0.000043923894,0.000397417,0.00049703836,0.0007122276,0.00029862497],"domain_scores_gemma":[0.9989001,0.0001283265,0.00007215086,0.0005590179,0.00006666211,0.0002737386],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00060386205,0.0003385366,0.0008445991,0.00017646381,0.000037891037,0.00004074894,0.00016896919,0.00018474642,0.011891958],"category_scores_gemma":[0.00041303338,0.00022383426,0.00034538802,0.00017186403,0.000058470287,0.000009156735,0.0001164476,0.0022964189,0.0028085252],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000065430554,0.00006338757,0.000004044612,0.008095508,0.0001565009,0.00028544795,0.000008525279,4.7284868e-7,0.0000011160688,0.0010248113,0.9478372,0.04251647],"study_design_scores_gemma":[0.00027335578,0.00018131349,0.0000057575107,0.026070245,0.0007029734,0.000101136335,0.0000037729878,0.00060680666,0.000003537366,0.00016507534,0.9716775,0.00020852897],"about_ca_topic_score_codex":0.00013982799,"about_ca_topic_score_gemma":0.0000026534137,"teacher_disagreement_score":0.2922554,"about_ca_system_score_codex":0.00015593815,"about_ca_system_score_gemma":0.0001764507,"threshold_uncertainty_score":0.9979679},"labels":[],"label_agreement":null},{"id":"W4403777619","doi":"10.21203/rs.3.rs-5314367/v1","title":"Validation of new, circulating biomarkers for gliomas","year":2024,"lang":"en","type":"preprint","venue":"Research Square","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; University of Toronto","funders":"","keywords":"Glioma; Medicine; Internal medicine; Oncology; Computer science; Cancer research","score_opus":0.08061472382285467,"score_gpt":0.45664745261003464,"score_spread":0.37603272878717997,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403777619","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9653203,0.0038722372,0.007724531,0.012452329,0.0009032375,0.0029271818,0.000070031194,0.00017382167,0.0065563535],"genre_scores_gemma":[0.987592,0.00009039828,0.00935958,0.000030931136,0.0009911662,0.00010210852,0.0003797516,0.00008659346,0.0013675038],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974019,0.00014083646,0.00043805933,0.00052789244,0.0010514965,0.00043980576],"domain_scores_gemma":[0.9980715,0.0005246748,0.00010895707,0.0004958699,0.00051105523,0.0002879477],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028389383,0.0001754152,0.0004319675,0.0008255383,0.000088368826,0.00009151359,0.00020179719,0.0002699159,0.0000938376],"category_scores_gemma":[0.003818831,0.00015450409,0.00031347913,0.00049318484,0.0001464376,0.000021548176,0.0006196778,0.0016765511,0.000019317466],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011798175,0.0005379597,0.02419311,0.10322679,0.0031346406,0.0006044012,0.0062573766,0.0033995674,0.17758732,0.008231071,0.16260909,0.50903887],"study_design_scores_gemma":[0.007367252,0.002080214,0.014684252,0.049377732,0.001226353,0.00026948832,0.0027285963,0.6047632,0.071278736,0.19456463,0.05026141,0.001398155],"about_ca_topic_score_codex":0.00046782204,"about_ca_topic_score_gemma":0.0000014187794,"teacher_disagreement_score":0.6013636,"about_ca_system_score_codex":0.00021491692,"about_ca_system_score_gemma":0.0010942912,"threshold_uncertainty_score":0.7283873},"labels":[],"label_agreement":null},{"id":"W4403796859","doi":"10.5194/sp-2024-9-rc1","title":"Comment on sp-2024-9","year":2024,"lang":"en","type":"peer-review","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Environment and Climate Change Canada","funders":"","keywords":"Computer science","score_opus":0.02688487755783025,"score_gpt":0.3643419248972721,"score_spread":0.3374570473394418,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403796859","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[9.802036e-7,0.029351983,0.0000902464,0.6341262,0.0060616024,0.00036994982,0.000024371564,0.00012904323,0.32984564],"genre_scores_gemma":[0.0000073197307,0.008339641,0.00057416194,0.3686437,0.0012236729,0.000026188129,0.00057598564,0.000059242644,0.6205501],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980515,0.000043884134,0.00039732974,0.00049683533,0.00071199326,0.00029845693],"domain_scores_gemma":[0.99890053,0.00012824213,0.000072137394,0.0005587801,0.00006664219,0.0002736457],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0006031647,0.0003384812,0.000844293,0.0001764021,0.000037872815,0.00004076627,0.00016900171,0.00018470436,0.011481445],"category_scores_gemma":[0.0004128439,0.00022380837,0.0003453343,0.00017177276,0.00005843414,0.000009162085,0.000116458636,0.0022952915,0.0028401099],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000065529653,0.000063495645,0.000004084178,0.0081078475,0.00015680076,0.00028590867,0.000008524805,4.7447148e-7,0.0000011010749,0.0010062361,0.94981635,0.04054261],"study_design_scores_gemma":[0.00027356067,0.00018111317,0.000005926568,0.026055284,0.0007028157,0.00010109291,0.0000037680766,0.0006154977,0.0000034607085,0.0001639636,0.971685,0.00020849744],"about_ca_topic_score_codex":0.00014213784,"about_ca_topic_score_gemma":0.0000027168303,"teacher_disagreement_score":0.29070443,"about_ca_system_score_codex":0.00015588677,"about_ca_system_score_gemma":0.00017636645,"threshold_uncertainty_score":0.9979363},"labels":[],"label_agreement":null},{"id":"W4403841929","doi":"10.1007/978-3-031-75431-9_4","title":"Region of Interest Features and Classification of MRI Brain Lesions","year":2024,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Medicine; Artificial intelligence","score_opus":0.07063792325245556,"score_gpt":0.35021698212427776,"score_spread":0.2795790588718222,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403841929","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012333973,0.007850922,0.08904596,0.06470171,0.0006981403,0.0015421357,0.000041644777,0.00012838075,0.82365716],"genre_scores_gemma":[0.95590705,0.010494141,0.027768748,0.00086270185,0.000043656957,0.000008983607,0.000108412394,0.000014504921,0.0047918214],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991858,0.000011770839,0.0004596004,0.000116835174,0.00015687312,0.000069141286],"domain_scores_gemma":[0.9987173,0.00018453263,0.00023073798,0.0006193467,0.0001883376,0.000059747497],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00054879684,0.000091603804,0.0002101826,0.00069427904,0.00007751942,0.000048300208,0.00032457692,0.00007969076,0.0000027713465],"category_scores_gemma":[0.00011714198,0.00007865221,0.000030411225,0.0001706596,0.001240219,0.00052511645,0.0004320866,0.00042537745,0.000002520489],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000074192926,0.00001404315,0.0002182976,0.00028838753,0.000010564072,5.1255313e-7,0.0014868741,0.00001347308,0.00011326553,0.77458924,0.0015744979,0.2216834],"study_design_scores_gemma":[0.0011730541,0.00038039862,0.06556716,0.007892247,0.00012315404,0.0006447342,0.00031756688,0.55109096,0.0000754581,0.032801256,0.33949324,0.00044076072],"about_ca_topic_score_codex":0.00001020638,"about_ca_topic_score_gemma":0.000004109736,"teacher_disagreement_score":0.94357306,"about_ca_system_score_codex":0.000035451252,"about_ca_system_score_gemma":0.000116035786,"threshold_uncertainty_score":0.45696384},"labels":[],"label_agreement":null},{"id":"W4403845331","doi":"10.5194/essd-2024-204-rc3","title":"Comment on essd-2024-204","year":2024,"lang":"en","type":"peer-review","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; McGill University","funders":"","keywords":"Computer science","score_opus":0.02568580258237292,"score_gpt":0.36533729560585754,"score_spread":0.33965149302348463,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403845331","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000010754534,0.033296186,0.00012067833,0.6416206,0.006577737,0.0004275565,0.000034614204,0.000154333,0.31776723],"genre_scores_gemma":[0.000011284569,0.008510828,0.0005839393,0.34941766,0.0013244298,0.00003917227,0.00074405415,0.000072915034,0.6392957],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977397,0.00005619071,0.0004660926,0.00057982036,0.00080778217,0.00035043072],"domain_scores_gemma":[0.9987044,0.00016113752,0.000091453636,0.0006455097,0.000083490406,0.0003140247],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0006875306,0.00039823205,0.0009795423,0.00019802607,0.00004827507,0.000052923933,0.00021043589,0.00022179369,0.012719216],"category_scores_gemma":[0.00048227393,0.0002661431,0.00038495232,0.00020398108,0.00007010863,0.000012452143,0.0001436562,0.002592592,0.0024601333],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007688967,0.00007905306,0.0000043637815,0.009174684,0.00019166025,0.00030026978,0.0000116782985,8.028899e-7,0.0000013115875,0.001161536,0.94737816,0.0416888],"study_design_scores_gemma":[0.00033699325,0.00018981897,0.0000051131397,0.028551167,0.0007956926,0.00010211898,0.000005163219,0.000775503,0.000004443298,0.00020760456,0.96877736,0.00024899782],"about_ca_topic_score_codex":0.00016735515,"about_ca_topic_score_gemma":0.0000035764344,"teacher_disagreement_score":0.3215285,"about_ca_system_score_codex":0.0001872093,"about_ca_system_score_gemma":0.00021805814,"threshold_uncertainty_score":0.9999791},"labels":[],"label_agreement":null},{"id":"W4403846150","doi":"10.1002/cam4.70359","title":"Differential Radiomics‐Based Signature Predicts Lung Cancer Risk Accounting for Imaging Parameters in <scp>NLST</scp> Cohort","year":2024,"lang":"en","type":"article","venue":"Cancer Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; Centre hospitalier de l'Université Laval; Institut universitaire de cardiologie et de pneumologie de Québec","funders":"Natural Sciences and Engineering Research Council of Canada; National Cancer Institute; Fonds de Recherche du Québec - Santé; Institut de Valorisation des Données","keywords":"Artificial intelligence; Feature selection; Support vector machine; Boosting (machine learning); Computer science; Radiomics; Cross-validation; Medicine; Receiver operating characteristic; Lung cancer; Pattern recognition (psychology); Machine learning; Oncology","score_opus":0.007996464326820748,"score_gpt":0.30837306151568883,"score_spread":0.30037659718886806,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403846150","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8843693,0.05437747,0.03685577,0.015031516,0.0063190623,0.0019815818,0.00012623015,0.00039933162,0.0005397144],"genre_scores_gemma":[0.9867065,0.0032396596,0.0011640934,0.0036657436,0.003648603,0.00070462393,0.00019934808,0.00016321152,0.0005082116],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99678075,0.00008494118,0.000703668,0.00090300274,0.0006679574,0.00085965387],"domain_scores_gemma":[0.99757254,0.001298709,0.00021367759,0.0003729291,0.00014927369,0.00039284327],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00092176365,0.00046114373,0.0009182746,0.0006003128,0.00015360262,0.00008133622,0.0002607328,0.00019933544,0.00018847204],"category_scores_gemma":[0.0020927114,0.00035925,0.00021520989,0.00067798106,0.0003492397,0.00016822522,0.000050431754,0.0016440608,0.0000022768984],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017698633,0.00009793147,0.7764446,0.0029811286,0.0007701238,0.00036044503,0.0021969331,0.0051288363,0.012721885,0.00011049799,0.11641973,0.082590915],"study_design_scores_gemma":[0.00582463,0.00011168081,0.05262782,0.0066075274,0.0016106238,0.00003374105,0.00026227,0.90193254,0.001168005,0.00012586452,0.029491855,0.00020344062],"about_ca_topic_score_codex":0.0013552096,"about_ca_topic_score_gemma":0.000053718864,"teacher_disagreement_score":0.8968037,"about_ca_system_score_codex":0.00066577276,"about_ca_system_score_gemma":0.0005777959,"threshold_uncertainty_score":0.999886},"labels":[],"label_agreement":null},{"id":"W4403855182","doi":"10.1016/s1470-2045(24)00316-4","title":"Artificial Intelligence for Response Assessment in Neuro Oncology (AI-RANO), part 1: review of current advancements","year":2024,"lang":"en","type":"review","venue":"The Lancet Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":23,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"DOD Peer Reviewed Cancer Research Program; National Institute of Neurological Disorders and Stroke; National Cancer Institute; Centre For Medical Engineering, King’s College London; Engineering and Physical Sciences Research Council; Servier; Siemens Healthineers; Deutsche Forschungsgemeinschaft; National Institutes of Health; Novocure; National Center for Advancing Translational Sciences; Wellcome Trust; Stryker; University of Wisconsin-Madison; Medical Research Council; Musella Foundation For Brain Tumor Research and Information; U.S. Department of Veterans Affairs; U.S. Department of Defense","keywords":"Current (fluid); Medical physics; Computer science; Medicine; Neuroscience; Engineering; Psychology; Electrical engineering","score_opus":0.21247130692308325,"score_gpt":0.5590866697953906,"score_spread":0.3466153628723073,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403855182","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000042571887,0.9651911,0.0023800258,0.026196847,0.0028238336,0.002741515,0.000054146756,0.000035148118,0.0005730827],"genre_scores_gemma":[0.000007547912,0.99144095,0.0014242241,0.0046233595,0.0012900728,0.0009302558,0.00012026663,0.000059473572,0.00010385029],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9948721,0.0019873143,0.001752908,0.0005521172,0.00029890396,0.00053667976],"domain_scores_gemma":[0.9951741,0.003278286,0.00068451045,0.0006405199,0.00010711904,0.000115432005],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.00801253,0.00037776228,0.0039632563,0.00024085063,0.000047155412,0.000010978315,0.0005261153,0.00024078846,0.000110237066],"category_scores_gemma":[0.0031491383,0.00022893393,0.00049440126,0.00049146416,0.00028415537,0.000025879535,0.00020959618,0.002521114,0.00004303937],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037997376,0.00024867625,0.0000032283483,0.101127185,0.00010848676,0.00009280215,0.000046372843,0.000002052102,0.0000032644639,0.00198483,0.013760016,0.8822431],"study_design_scores_gemma":[0.00026957496,0.0010342291,0.0000034318548,0.08920908,0.0017268106,0.00015163202,0.000010284599,0.00033024143,7.1165465e-7,0.0009582304,0.9061498,0.00015596952],"about_ca_topic_score_codex":0.0000048266265,"about_ca_topic_score_gemma":0.0000069649113,"teacher_disagreement_score":0.8923898,"about_ca_system_score_codex":0.00074069994,"about_ca_system_score_gemma":0.0027149583,"threshold_uncertainty_score":0.9997801},"labels":[],"label_agreement":null},{"id":"W4403855186","doi":"10.1016/s1470-2045(24)00315-2","title":"Artificial Intelligence for Response Assessment in Neuro Oncology (AI-RANO), part 2: recommendations for standardisation, validation, and good clinical practice","year":2024,"lang":"en","type":"review","venue":"The Lancet Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":27,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Department of Radiology, Weill Cornell Medical College; DOD Peer Reviewed Cancer Research Program; National Institute of Neurological Disorders and Stroke; Servier; National Cancer Institute; Centre For Medical Engineering, King’s College London; European Research Council; Dana Foundation; Engineering and Physical Sciences Research Council; Perelman School of Medicine, University of Pennsylvania; National Institutes of Health; Siemens Healthineers; Deutsche Forschungsgemeinschaft; Novocure; U.S. Department of Defense; European Commission; University of Pennsylvania; Musella Foundation For Brain Tumor Research and Information; Stryker; Instituto Tecnológico de Costa Rica; University of Wisconsin-Madison; Medical Research Council; National Center for Advancing Translational Sciences; Wellcome Trust; U.S. Department of Veterans Affairs","keywords":"Medical physics; Clinical Practice; Artificial intelligence; Computer science; Psychology; Engineering; Medicine; Family medicine","score_opus":0.2640646117355813,"score_gpt":0.592935452089632,"score_spread":0.32887084035405073,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403855186","genre_codex":"commentary","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00002101223,0.4092954,0.076351576,0.50443614,0.00388563,0.0047957264,0.0002733282,0.00008632908,0.0008548515],"genre_scores_gemma":[0.00002986613,0.95072067,0.037372,0.0072313705,0.0027324762,0.0012894019,0.00038023948,0.00006362307,0.00018037483],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9943203,0.0029134203,0.0016302075,0.00057790754,0.00017518851,0.00038300175],"domain_scores_gemma":[0.9734948,0.025148194,0.0006031354,0.00039782142,0.00023358603,0.00012242803],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.019202184,0.0002682301,0.0020250245,0.00019244275,0.00016453817,0.00006844766,0.00023497382,0.00041809148,0.000033403678],"category_scores_gemma":[0.020008037,0.00018045388,0.00027342484,0.00027629774,0.00027405345,0.00007010118,0.00010940829,0.0018702188,0.000011261574],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011795487,0.00022669857,0.0000111590125,0.0019304617,0.0002199402,0.000023705077,0.00021883922,0.000005058753,7.8704846e-7,0.011347152,0.038174946,0.9466617],"study_design_scores_gemma":[0.00063736946,0.0016762785,0.000012133935,0.0013486166,0.0024143616,0.00028824963,0.00017323792,0.0015509875,4.114527e-7,0.005451485,0.9862894,0.00015748957],"about_ca_topic_score_codex":0.000008400163,"about_ca_topic_score_gemma":0.000017605893,"teacher_disagreement_score":0.94811445,"about_ca_system_score_codex":0.00055016787,"about_ca_system_score_gemma":0.002928742,"threshold_uncertainty_score":0.98824686},"labels":[],"label_agreement":null},{"id":"W4403869490","doi":"10.1002/mp.17490","title":"Myocardial perfusion SPECT radiomic features reproducibility assessment: Impact of image reconstruction and harmonization","year":2024,"lang":"en","type":"article","venue":"Medical Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Reproducibility; Medical physics; Nuclear medicine; Single-photon emission computed tomography; Myocardial perfusion imaging; Harmonization; Medicine; Medical imaging; Radiology; Computer science; Artificial intelligence; Perfusion; Mathematics; Statistics; Physics","score_opus":0.009065593274364462,"score_gpt":0.32715045462129205,"score_spread":0.3180848613469276,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403869490","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9525378,0.00062798185,0.042687196,0.001907993,0.0005947911,0.00020736498,0.0000071473564,0.0001036103,0.0013261193],"genre_scores_gemma":[0.9965044,0.00040338098,0.0016694618,0.00008572506,0.001177296,0.000003311381,0.00005155636,0.000025043635,0.00007978311],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9983897,0.00008384194,0.0002780309,0.0005602088,0.0005216262,0.00016658645],"domain_scores_gemma":[0.9991469,0.00012413251,0.000060016977,0.0003817801,0.0000661023,0.00022108393],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001215209,0.00013699243,0.0003534314,0.00006865295,0.000070685484,0.000030506591,0.000059156057,0.0000850607,0.00020282267],"category_scores_gemma":[0.001193115,0.0001023355,0.00017958866,0.00026102512,0.00062756863,0.00012878135,0.000053152624,0.0006930369,0.000003980333],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010266513,0.00017125456,0.09968851,0.0005303676,0.00022770536,0.00017032218,0.00045578385,0.000018515066,0.048838075,0.000558819,0.0045137405,0.84472424],"study_design_scores_gemma":[0.0029815803,0.00091651233,0.8035631,0.0016936047,0.000645451,0.0033702005,0.00006562574,0.15797535,0.01788889,0.010093508,0.0003359709,0.00047020908],"about_ca_topic_score_codex":0.00008881141,"about_ca_topic_score_gemma":2.514975e-7,"teacher_disagreement_score":0.844254,"about_ca_system_score_codex":0.00013157087,"about_ca_system_score_gemma":0.00042346682,"threshold_uncertainty_score":0.41731206},"labels":[],"label_agreement":null},{"id":"W4403869916","doi":"10.5194/sp-2024-9-rc2","title":"Comment on sp-2024-9","year":2024,"lang":"en","type":"peer-review","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Environment and Climate Change Canada","funders":"","keywords":"Computer science","score_opus":0.02688487755783025,"score_gpt":0.3643419248972721,"score_spread":0.3374570473394418,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403869916","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[9.802036e-7,0.029351983,0.0000902464,0.6341262,0.0060616024,0.00036994982,0.000024371564,0.00012904323,0.32984564],"genre_scores_gemma":[0.0000073197307,0.008339641,0.00057416194,0.3686437,0.0012236729,0.000026188129,0.00057598564,0.000059242644,0.6205501],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980515,0.000043884134,0.00039732974,0.00049683533,0.00071199326,0.00029845693],"domain_scores_gemma":[0.99890053,0.00012824213,0.000072137394,0.0005587801,0.00006664219,0.0002736457],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0006031647,0.0003384812,0.000844293,0.0001764021,0.000037872815,0.00004076627,0.00016900171,0.00018470436,0.011481445],"category_scores_gemma":[0.0004128439,0.00022380837,0.0003453343,0.00017177276,0.00005843414,0.000009162085,0.000116458636,0.0022952915,0.0028401099],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000065529653,0.000063495645,0.000004084178,0.0081078475,0.00015680076,0.00028590867,0.000008524805,4.7447148e-7,0.0000011010749,0.0010062361,0.94981635,0.04054261],"study_design_scores_gemma":[0.00027356067,0.00018111317,0.000005926568,0.026055284,0.0007028157,0.00010109291,0.0000037680766,0.0006154977,0.0000034607085,0.0001639636,0.971685,0.00020849744],"about_ca_topic_score_codex":0.00014213784,"about_ca_topic_score_gemma":0.0000027168303,"teacher_disagreement_score":0.29070443,"about_ca_system_score_codex":0.00015588677,"about_ca_system_score_gemma":0.00017636645,"threshold_uncertainty_score":0.9979363},"labels":[],"label_agreement":null},{"id":"W4403889525","doi":"10.1038/s42256-024-00912-9","title":"Results from the autoPET challenge on fully automated lesion segmentation in oncologic PET/CT imaging","year":2024,"lang":"en","type":"article","venue":"Nature Machine Intelligence","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":31,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; University of Toronto; University Health Network","funders":"Deutsche Forschungsgemeinschaft","keywords":"Segmentation; Medicine; Radiology; Lesion; Nuclear medicine; Computer science; Medical physics; Computer vision; Artificial intelligence; Pathology","score_opus":0.01694126655382513,"score_gpt":0.3551445904687203,"score_spread":0.3382033239148952,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403889525","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.67616975,0.027725363,0.00859011,0.24501969,0.0058517354,0.002150831,0.00021147155,0.003220226,0.031060824],"genre_scores_gemma":[0.99244934,0.0009947222,0.0018790949,0.0036995204,0.00036706484,0.000018502527,0.0002807553,0.000037885977,0.00027308214],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978798,0.00018947996,0.00049583876,0.00061840046,0.0005027932,0.00031369424],"domain_scores_gemma":[0.99820423,0.0011748613,0.000091287366,0.00037701722,0.000049698232,0.00010290709],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0010567226,0.00026039075,0.00028912985,0.00020014615,0.00011007428,0.0001109086,0.0002972156,0.00005290003,0.00011428975],"category_scores_gemma":[0.0014650724,0.00015882331,0.0001081741,0.0004829923,0.00010051105,0.00010038085,0.00008700029,0.0028573263,0.0001324073],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008549518,0.0005074449,0.0028705674,0.00016070419,0.00011675404,0.013663781,0.0019734195,0.0038906955,0.0036483407,0.0037030948,0.017680695,0.9509295],"study_design_scores_gemma":[0.0006817279,0.00026729578,0.008136016,0.0013797998,0.00006665488,0.00054246717,0.00029370116,0.96148354,0.0018243958,0.0016779399,0.023398602,0.00024785128],"about_ca_topic_score_codex":0.00071013405,"about_ca_topic_score_gemma":0.000084701256,"teacher_disagreement_score":0.95759284,"about_ca_system_score_codex":0.0002584952,"about_ca_system_score_gemma":0.00011703265,"threshold_uncertainty_score":0.9994431},"labels":[],"label_agreement":null},{"id":"W4403896839","doi":"10.1016/j.giec.2024.09.004","title":"The Role of Artificial Intelligence and Big Data for Gastrointestinal Disease","year":2024,"lang":"en","type":"review","venue":"Gastrointestinal Endoscopy Clinics of North America","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia Hospital; Vancouver General Hospital","funders":"","keywords":"Medicine; Big data; Disease; Gastrointestinal disease; Internal medicine; Data science; Gastroenterology; Data mining; Computer science","score_opus":0.07855417605609456,"score_gpt":0.3895521195393348,"score_spread":0.3109979434832402,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403896839","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00004191617,0.9514574,0.04520779,0.00036541806,0.00031970543,0.0011632146,0.0013414585,0.000055031534,0.00004808346],"genre_scores_gemma":[0.00014949997,0.89151293,0.10640908,0.00004808961,0.00073982356,0.00006188955,0.0009234752,0.00010802478,0.00004721194],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99603915,0.00016246752,0.0019179358,0.0008623563,0.00046472187,0.00055338646],"domain_scores_gemma":[0.99219894,0.0044104955,0.0012665171,0.0013463151,0.00026246122,0.0005152861],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010103843,0.00053751434,0.0019209969,0.00021413885,0.00012569147,0.000054815515,0.0009356541,0.00004035969,0.000005886621],"category_scores_gemma":[0.014748006,0.00035500532,0.000554376,0.0004431034,0.0013970995,0.000046833953,0.0006588243,0.0011750321,0.000009359672],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039017887,0.00014194203,0.0008917443,0.008241109,0.000108338194,0.000057273206,0.000007537966,0.000008895483,0.0000014816476,0.0001539509,0.00024630304,0.9897512],"study_design_scores_gemma":[0.00021860501,0.0025344805,0.00013161996,0.04847195,0.0061557693,0.002331584,0.00011617442,0.036236055,3.611453e-7,0.0012994467,0.9020969,0.00040702175],"about_ca_topic_score_codex":0.000038729086,"about_ca_topic_score_gemma":0.000007794507,"teacher_disagreement_score":0.98934424,"about_ca_system_score_codex":0.000035159523,"about_ca_system_score_gemma":0.0013219872,"threshold_uncertainty_score":0.9998902},"labels":[],"label_agreement":null},{"id":"W4403954888","doi":"10.1007/s00259-024-06921-5","title":"Long-axial field-of-view PET/CT improves radiomics feature reliability","year":2024,"lang":"en","type":"article","venue":"European Journal of Nuclear Medicine and Molecular Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency; University of British Columbia; Spinal Cord Injury BC","funders":"","keywords":"Radiomics; Nuclear medicine; Medicine; Feature (linguistics); Medical physics; Reliability (semiconductor); Field (mathematics); Radiology; Physics; Mathematics","score_opus":0.006362928695201583,"score_gpt":0.27677006489470957,"score_spread":0.27040713619950796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403954888","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7652552,0.04081777,0.008563417,0.17100075,0.0018026881,0.00027504287,0.0000019761574,0.000096849464,0.012186321],"genre_scores_gemma":[0.98244625,0.0020830056,0.005538425,0.009080327,0.0007034912,1.6857923e-7,0.00000328032,0.000081906626,0.000063134896],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983167,0.00023069356,0.0005846952,0.00024778963,0.00039737375,0.00022275573],"domain_scores_gemma":[0.99896646,0.00013804101,0.00020888611,0.0002435034,0.00014828012,0.00029482917],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001805572,0.00019928173,0.0005216239,0.00026338623,0.000057951016,0.00004830688,0.00017569916,0.000008584063,0.000060379],"category_scores_gemma":[0.0011859303,0.0001404894,0.00020865475,0.00020390138,0.00027077703,0.00012463614,0.000081898885,0.0010470941,0.000004765496],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039466837,0.00013109899,0.0020068581,0.002188903,0.00046592366,0.097379744,0.0018276579,0.000015661031,0.1931554,0.0006663152,0.120321795,0.581446],"study_design_scores_gemma":[0.004937433,0.002131036,0.005555476,0.008835857,0.0014482868,0.07284317,0.001017242,0.014543948,0.0014277691,0.00026295058,0.8865409,0.00045592198],"about_ca_topic_score_codex":0.00000967183,"about_ca_topic_score_gemma":5.164103e-8,"teacher_disagreement_score":0.7662191,"about_ca_system_score_codex":0.00003135689,"about_ca_system_score_gemma":0.00007950218,"threshold_uncertainty_score":0.57289916},"labels":[],"label_agreement":null},{"id":"W4404052340","doi":"","title":"Modern applications of positron emission tomography/computed tomography (PET/CT) imaging in veterinary oncology - A brief overview.","year":2024,"lang":"en","type":"article","venue":"PubMed","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Positron emission tomography; Positron Emission Tomography-Computed Tomography; Medicine; Medical physics; Computed tomography; Tomography; Nuclear medicine; Preclinical imaging; Radiology","score_opus":0.014668865527054906,"score_gpt":0.300657952238102,"score_spread":0.28598908671104706,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404052340","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9412051,0.026169209,0.013729636,0.007318801,0.00051195355,0.0021209607,0.000016029642,0.00040966398,0.008518643],"genre_scores_gemma":[0.9962809,0.0002397273,0.0018471157,0.00055385317,0.00014004562,0.00074366195,0.000043625965,0.000036468733,0.0001146183],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9984592,0.0000913375,0.0004172291,0.00040173854,0.00024385193,0.00038661817],"domain_scores_gemma":[0.9992259,0.00014619663,0.00007707611,0.0002856353,0.00004176109,0.0002234295],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005898386,0.00016368469,0.00036134978,0.00071225496,0.000043137756,0.000034541823,0.00016357983,0.000022231387,0.000014340954],"category_scores_gemma":[0.000055421122,0.00014846835,0.00019510112,0.0009402446,0.00012499893,0.000104749,0.00010016158,0.0004800618,0.0000016979938],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007398864,0.00027143522,0.03090423,0.00052830664,0.000072002586,0.0009271371,0.00014906705,0.00003328559,0.004288671,0.00035868125,0.00107581,0.96131736],"study_design_scores_gemma":[0.0026920757,0.00021302895,0.6428823,0.00093026547,0.00029078696,0.0038708884,0.00008884835,0.14810902,0.0008717737,0.004280386,0.19529821,0.0004724296],"about_ca_topic_score_codex":0.00014615133,"about_ca_topic_score_gemma":0.0000016528445,"teacher_disagreement_score":0.96084493,"about_ca_system_score_codex":0.000103812905,"about_ca_system_score_gemma":0.00007522773,"threshold_uncertainty_score":0.6054363},"labels":[],"label_agreement":null},{"id":"W4404052844","doi":"10.17816/dd630885","title":"Detecting new lung cancer cases using artificial intelligence: clinical and economic evaluation of a retrospective analysis of computed tomography scans 2 years after the COVID-19 pandemic","year":2024,"lang":"en","type":"article","venue":"Digital Diagnostics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Pandemic; Coronavirus disease 2019 (COVID-19); Lung cancer; 2019-20 coronavirus outbreak; Retrospective cohort study; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Medicine; Cancer; Virology; Internal medicine; Infectious disease (medical specialty); Disease","score_opus":0.08343619341510838,"score_gpt":0.4346985242194399,"score_spread":0.3512623308043315,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404052844","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9776615,0.0030600873,0.018388867,0.0002548964,0.0002573441,0.0002312103,0.00010054799,0.000023102923,0.00002243298],"genre_scores_gemma":[0.9990542,0.0003102005,0.00023080598,0.00017243404,0.00019292229,0.000006183993,0.000018261671,0.00001302682,0.0000019672557],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988451,0.000066546374,0.00047409412,0.00024060612,0.0002526479,0.00012102411],"domain_scores_gemma":[0.9972968,0.0022121836,0.00012312108,0.00013774437,0.00008868477,0.000141455],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008568691,0.000095062846,0.00033777687,0.0002763848,0.0000316929,0.00007334957,0.000056324374,0.000060865194,0.000043660002],"category_scores_gemma":[0.0049221083,0.00007511659,0.00018519814,0.0005472722,0.0002961473,0.000072244955,0.000046397166,0.00024239179,4.0330804e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000045313027,0.00002628553,0.90410244,0.000055665278,0.0008639822,0.000023434935,0.000547417,0.01642242,0.0000113512915,0.0001428972,0.000063767344,0.077695],"study_design_scores_gemma":[0.0001186136,0.00006284016,0.2566887,0.0001592733,0.0031402623,0.000027552327,0.00014372414,0.73871356,0.0000148295785,0.0008269051,0.000036381625,0.000067363464],"about_ca_topic_score_codex":0.0007964914,"about_ca_topic_score_gemma":0.00020947876,"teacher_disagreement_score":0.7222911,"about_ca_system_score_codex":0.00014606137,"about_ca_system_score_gemma":0.0004733456,"threshold_uncertainty_score":0.5892579},"labels":[],"label_agreement":null},{"id":"W4404055034","doi":"10.1016/j.media.2024.103389","title":"Editorial for Special Issue on Foundation Models for Medical Image Analysis","year":2024,"lang":"en","type":"editorial","venue":"Medical Image Analysis","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Foundation (evidence); Computer science; Image (mathematics); Artificial intelligence; Data science; Geography","score_opus":0.0070945737540653265,"score_gpt":0.34453436390558956,"score_spread":0.33743979015152425,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404055034","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00001255028,0.00015945616,0.29063773,0.010586609,0.69398046,0.0009798389,0.00053809787,0.000234984,0.0028702791],"genre_scores_gemma":[0.000042499232,0.00069508277,0.007925931,0.0011182268,0.9602225,0.00054417906,0.02142545,0.0002660117,0.007760126],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9838141,0.00029839086,0.0022875662,0.0024192699,0.009854056,0.0013265742],"domain_scores_gemma":[0.98795676,0.0061100684,0.0006578281,0.0013406995,0.0018362022,0.0020984537],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.007003233,0.0011294807,0.0041653244,0.0032069238,0.00040272644,0.0006241797,0.001203951,0.0034003248,0.009721879],"category_scores_gemma":[0.05078726,0.00092886685,0.005215892,0.003823323,0.00076104485,0.00029623014,0.00029459293,0.0046914,0.00033399957],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00083141885,0.00044573317,0.0000075217768,0.00084773323,0.02302562,0.0002371043,0.00014278674,0.00013812147,0.0000117911,0.00010661911,0.94729435,0.026911221],"study_design_scores_gemma":[0.0025064307,0.00034888426,0.0000019121715,0.00028722503,0.05248849,0.0000027340507,0.00003052734,0.3335982,0.000008186795,0.000818637,0.6093972,0.000511628],"about_ca_topic_score_codex":0.00042594213,"about_ca_topic_score_gemma":0.00024401181,"teacher_disagreement_score":0.33789718,"about_ca_system_score_codex":0.0006579233,"about_ca_system_score_gemma":0.0026661286,"threshold_uncertainty_score":0.9993162},"labels":[],"label_agreement":null},{"id":"W4404058668","doi":"10.3390/curroncol31110503","title":"Detecting Clinically Significant Prostate Cancer in PI-RADS 3 Lesions Using T2w-Derived Radiomics Feature Maps in 3T Prostate MRI","year":2024,"lang":"en","type":"article","venue":"Current Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"UCB Pharma; Respicardia; St. Jude Medical; Samsung; Sirtex Medical; Symphogen; TauRx Pharmaceuticals; Seagen; Sarepta Therapeutics; Friedrich-Schiller-Universität Jena; Taiho Pharmaceutical; Vertex Pharmaceuticals; Servier; Spectrum Pharmaceuticals; Teva Pharmaceutical Industries; Sanofi","keywords":"Radiomics; Medicine; Prostate cancer; Prostate; BI-RADS; Multiparametric MRI; Feature (linguistics); T2 weighted; Radiology; Cancer; Magnetic resonance imaging; Pathology; Internal medicine; Breast cancer; Mammography","score_opus":0.06282517380177242,"score_gpt":0.4335975263796165,"score_spread":0.3707723525778441,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404058668","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97281504,0.008087682,0.0016575922,0.012152113,0.0038128553,0.0011238249,0.000027685524,0.00014361022,0.00017961655],"genre_scores_gemma":[0.9888143,0.0053630243,0.004261258,0.0004383604,0.00069693994,0.00012669069,0.000045643937,0.000086483335,0.00016727771],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971467,0.00031072253,0.00084534154,0.00072408986,0.0002574564,0.00071564974],"domain_scores_gemma":[0.99880505,0.00041614383,0.00017895624,0.0002520967,0.000079986916,0.00026777128],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0014356127,0.00029793588,0.00074948266,0.0004967281,0.00009266098,0.000058331436,0.0001733444,0.00025987692,0.000039523253],"category_scores_gemma":[0.00083966646,0.00025342446,0.00014329058,0.0007244684,0.00024075316,0.000101896454,0.0001295396,0.002785221,0.000010573271],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006711866,0.00062370056,0.19791876,0.0011659322,0.00009539179,0.001920531,0.0064568566,0.00423687,0.042297963,0.00015662723,0.0016894898,0.7427667],"study_design_scores_gemma":[0.009196912,0.0011826461,0.050358284,0.008110358,0.00037931302,0.00044209458,0.0015606354,0.77365696,0.0007304237,0.0012974213,0.15211892,0.0009660071],"about_ca_topic_score_codex":0.00018131045,"about_ca_topic_score_gemma":0.00009995234,"teacher_disagreement_score":0.7694201,"about_ca_system_score_codex":0.0009833928,"about_ca_system_score_gemma":0.0012635557,"threshold_uncertainty_score":0.9999918},"labels":[],"label_agreement":null},{"id":"W4404069189","doi":"10.7759/cureus.73082","title":"Radiomics As Biomarkers for the Treatment of Non-small Cell Lung Cancer With Stereotactic Body Radiation Therapy: A Review of Concepts","year":2024,"lang":"en","type":"review","venue":"Cureus","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Jewish General Hospital; McGill University","funders":"","keywords":"Medicine; Radiomics; Lung cancer; Context (archaeology); Radiosurgery; Radiation therapy; Medical physics; Personalized medicine; Stage (stratigraphy); Precision medicine; Radiology; Oncology; Bioinformatics; Pathology","score_opus":0.02714503397714242,"score_gpt":0.39066123542744924,"score_spread":0.36351620145030683,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404069189","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007702238,0.9940908,0.00016955374,0.00042961515,0.0004949073,0.0043930626,0.00006477533,0.00001730027,0.00026294022],"genre_scores_gemma":[0.000037339865,0.99765825,0.00028435435,0.00023128091,0.00031952388,0.0007012607,0.00015672571,0.00009472098,0.00051652704],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984785,0.000088331406,0.00065054017,0.0003407809,0.00022491501,0.00021696305],"domain_scores_gemma":[0.9981476,0.00047030192,0.0006729494,0.000500358,0.0001076401,0.000101127676],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003543299,0.00038447272,0.0017973635,0.00008957033,0.000040198403,0.000015256566,0.00018824288,0.00012951366,0.00006028252],"category_scores_gemma":[0.000076326665,0.0001844294,0.0006525856,0.00027761722,0.00012218636,0.00002349291,0.000013547222,0.0002312452,0.0000026968034],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000060484897,0.00015935396,0.000047963775,0.17463873,0.0031005298,0.00001232487,0.00028570605,6.5638505e-7,0.000007190399,0.000014524102,0.003225798,0.81844676],"study_design_scores_gemma":[0.0012781653,0.00088502956,0.000008430678,0.09718767,0.013826868,0.00004414488,0.000014318303,0.0008583803,0.0000139509375,0.0000019074196,0.8857176,0.00016355873],"about_ca_topic_score_codex":0.00021680695,"about_ca_topic_score_gemma":0.0000030009408,"teacher_disagreement_score":0.88249177,"about_ca_system_score_codex":0.00033743453,"about_ca_system_score_gemma":0.0010124773,"threshold_uncertainty_score":0.7520813},"labels":[],"label_agreement":null},{"id":"W4404108367","doi":"10.17816/dd633363","title":"Challenges and benefits of using texture analysis of computed tomography and magnetic resonance imaging scans in diagnosis of bladder cancer","year":2024,"lang":"en","type":"article","venue":"Digital Diagnostics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Defence Medical Centre","funders":"","keywords":"Bladder cancer; Medicine; Radiology; Cancer; Medical physics; Internal medicine","score_opus":0.016794418938949365,"score_gpt":0.2823634569857024,"score_spread":0.2655690380467531,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404108367","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.69529533,0.30380803,0.00007233829,0.00037136395,0.00004004679,0.000089805006,0.00011675953,0.000009330193,0.00019696387],"genre_scores_gemma":[0.96328855,0.03623353,0.00036102376,0.000048995495,0.000025816002,0.000005702695,0.000016284106,0.00001641733,0.0000036664112],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99907386,0.000015158611,0.00033283263,0.0002378862,0.00019362746,0.00014661171],"domain_scores_gemma":[0.99889874,0.0007387042,0.0000738323,0.00012620418,0.00008500747,0.00007747863],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000107243446,0.000124322,0.00047586934,0.0005856826,0.00001096744,0.000022034956,0.000050925733,0.00004645854,0.000008387705],"category_scores_gemma":[0.0003983547,0.0001107967,0.0000809269,0.0007555301,0.00025837737,0.000088982124,0.000060538412,0.00015281828,5.3692183e-8],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000877444,0.000073489326,0.64822066,0.00038776043,0.00013933449,0.000022910435,0.00060227525,0.00077302085,0.000042877644,0.000270572,0.000030232193,0.3494281],"study_design_scores_gemma":[0.0003360738,0.00006723061,0.8698775,0.0020903233,0.0007717475,0.000008996913,0.00015554843,0.12615205,0.00013584169,0.00009411692,0.00021660283,0.00009395208],"about_ca_topic_score_codex":0.00016968507,"about_ca_topic_score_gemma":0.00005079797,"teacher_disagreement_score":0.34933412,"about_ca_system_score_codex":0.000012536162,"about_ca_system_score_gemma":0.000033195534,"threshold_uncertainty_score":0.4518158},"labels":[],"label_agreement":null},{"id":"W4404185764","doi":"10.1016/j.jhepr.2024.101263","title":"Comparative evaluation of multimarker algorithms for early-stage HCC detection in multicenter prospective studies","year":2024,"lang":"en","type":"article","venue":"JHEP Reports","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; Toronto General Hospital","funders":"Ipsen; Eisai; Bayer HealthCare; FibroGen; EA Pharma Co., Ltd.; Gilead Sciences; Amgen; Pfizer; AstraZeneca; Eli Lilly and Company; Bristol-Myers Squibb","keywords":"Stage (stratigraphy); Algorithm; Oncology; Internal medicine; Medicine; Computer science; Biology","score_opus":0.0700108056272081,"score_gpt":0.43591009182488194,"score_spread":0.36589928619767387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404185764","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99058056,0.0015952034,0.0044876956,0.0002058495,0.0008037312,0.0015872319,0.0000026601188,0.000047520014,0.0006895441],"genre_scores_gemma":[0.99631053,0.000026197975,0.0027545833,0.000028527402,0.00012621787,0.0002480967,0.000008412132,0.000016438375,0.00048097732],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99867076,0.00006265067,0.0004299471,0.00031079727,0.0003844549,0.00014137589],"domain_scores_gemma":[0.99914503,0.00015891998,0.00013659542,0.00014124616,0.0003747259,0.000043457563],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017434476,0.000108058724,0.00034877984,0.00016401129,0.000036112244,0.000016334845,0.000019206609,0.00004606229,0.000022378877],"category_scores_gemma":[0.0009952085,0.00008521364,0.00008900507,0.00016840672,0.00008050943,0.000100347635,0.000019503354,0.00022081846,0.0000016138218],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011448644,0.0011327915,0.4780164,0.0029672363,0.0025363471,0.0013485037,0.051181916,0.00429612,0.046782542,0.000087739696,0.0014485135,0.40905702],"study_design_scores_gemma":[0.0015651194,0.00021121262,0.21617602,0.00056973496,0.0003004033,0.0000759816,0.0009557845,0.7659528,0.012375809,0.00036874198,0.0013341829,0.000114194685],"about_ca_topic_score_codex":0.00011869572,"about_ca_topic_score_gemma":0.000032861266,"teacher_disagreement_score":0.7616567,"about_ca_system_score_codex":0.00025610486,"about_ca_system_score_gemma":0.000086028536,"threshold_uncertainty_score":0.34749115},"labels":[],"label_agreement":null},{"id":"W4404213337","doi":"10.1007/978-3-031-64892-2_18","title":"Computational Modeling and AI in Radiation Neuro-Oncology and Radiosurgery","year":2024,"lang":"en","type":"review","venue":"Advances in experimental medicine and biology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Radiosurgery; Radiation oncology; Medical physics; Medicine; Radiation therapy; Internal medicine","score_opus":0.04149226910689644,"score_gpt":0.44770100972494364,"score_spread":0.4062087406180472,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404213337","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024037787,0.9947594,0.00017476118,0.0015892595,0.0005079143,0.00034357657,0.0000022035583,0.00001816171,0.00020094178],"genre_scores_gemma":[0.013872009,0.98371446,0.00045850957,0.0014269107,0.00032932332,0.000049858172,0.00011896771,0.000023529225,0.0000064353744],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984946,0.00014888913,0.0005755248,0.000494005,0.00007109162,0.00021584368],"domain_scores_gemma":[0.9992254,0.00048341847,0.000093687944,0.0000712548,0.000009665464,0.00011661024],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003632202,0.00026312063,0.0013244917,0.0004911154,0.000030614185,0.0000074700356,0.00004044213,0.00020781421,0.000007713988],"category_scores_gemma":[0.00020480843,0.00017916769,0.000040627256,0.00018448083,0.00041837886,0.000077016004,0.00007906221,0.0006993705,8.926037e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025065528,0.00003570186,0.00046721043,0.0019929914,0.000025788837,0.00012412407,0.000326575,0.000020803936,0.00004152459,0.0006658528,0.000069682595,0.9962047],"study_design_scores_gemma":[0.0017051867,0.00075793144,0.000018175502,0.0072312406,0.0002267451,0.0016581236,0.0003225466,0.054222845,9.458384e-7,0.0013789993,0.93222713,0.00025010452],"about_ca_topic_score_codex":0.000042102074,"about_ca_topic_score_gemma":0.0000029288515,"teacher_disagreement_score":0.9959546,"about_ca_system_score_codex":0.00008960247,"about_ca_system_score_gemma":0.0000812298,"threshold_uncertainty_score":0.7306247},"labels":[],"label_agreement":null},{"id":"W4404294044","doi":"10.1109/tetc.2024.3487258","title":"Deep Learning Based Intelligent Tumor Analytics Framework for Quantitative Grading and Analyzing Cancer Metastasis: Case of Lymph Node Breast Cancer","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Emerging Topics in Computing","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University","funders":"North China University of Technology; National Natural Science Foundation of China","keywords":"Computer science; Grading (engineering); Breast cancer; Lymph node metastasis; Deep learning; Artificial intelligence; Cancer; Cancer metastasis; Metastasis; Medicine; Internal medicine","score_opus":0.03162139103909787,"score_gpt":0.3747895964033675,"score_spread":0.3431682053642696,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404294044","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1762599,0.0016816887,0.8190779,0.0020615659,0.0006536076,0.00017277207,0.000014961218,0.000068961126,0.000008628347],"genre_scores_gemma":[0.9250602,0.00027161665,0.0742483,0.00018335436,0.00015236792,0.000022120243,0.000002008729,0.00004308791,0.0000169344],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985241,0.000084356456,0.00049431133,0.00040228508,0.00017551838,0.00031941175],"domain_scores_gemma":[0.998706,0.00082604354,0.00011862542,0.00013567728,0.000101724116,0.0001119572],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00062492327,0.00020619949,0.0004297059,0.0005383887,0.00023164021,0.000055578545,0.00007040698,0.00006877534,0.00003219489],"category_scores_gemma":[0.00010504204,0.00019882205,0.00016656135,0.0006336277,0.00009265715,0.000063350235,0.000003994162,0.0008248645,3.106434e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000057029072,0.000062686515,0.003916725,0.00078251236,0.0002678555,0.00024773995,0.0016765406,0.7462288,0.00015333395,0.0009033637,0.000002374142,0.24570103],"study_design_scores_gemma":[0.00043841227,0.000051899387,0.00027185233,0.003412253,0.00040801417,0.00025311025,0.0010393502,0.9929408,0.00066950056,0.00026103904,0.00007534469,0.00017843957],"about_ca_topic_score_codex":0.00069137115,"about_ca_topic_score_gemma":0.000063877895,"teacher_disagreement_score":0.7488003,"about_ca_system_score_codex":0.0002196303,"about_ca_system_score_gemma":0.00011403776,"threshold_uncertainty_score":0.8107728},"labels":[],"label_agreement":null},{"id":"W4404318930","doi":"10.1093/bjro/tzae039","title":"Artificial intelligence research in radiation oncology: a practical guide for the clinician on concepts and methods","year":2023,"lang":"en","type":"review","venue":"BJR|Open","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"National Cancer Institute","keywords":"Radiation oncology; Medical physics; Medicine; Computer science; Radiation therapy; Internal medicine","score_opus":0.6606041854093458,"score_gpt":0.7412279265834195,"score_spread":0.08062374117407367,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404318930","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000003025852,0.9352539,0.008522689,0.03537132,0.0010077766,0.0115091745,0.00002111382,0.000040744155,0.008270218],"genre_scores_gemma":[0.0000039985084,0.96397,0.031825423,0.0010204744,0.00079374126,0.0010669527,0.00006774488,0.00006627517,0.0011854101],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99534714,0.0023223707,0.0009990352,0.0006108693,0.00030596438,0.00041460272],"domain_scores_gemma":[0.9726098,0.026349261,0.0003084098,0.0004653501,0.000099667566,0.000167469],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.025834423,0.00020749959,0.0013845161,0.0002735556,0.00022109131,0.00025017041,0.00071923586,0.00034615656,0.000045613146],"category_scores_gemma":[0.02631696,0.0001294752,0.00014164892,0.00062798127,0.00031618294,0.00007533199,0.00069953984,0.0022190548,0.00008129147],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011372002,0.00008834822,0.00000380475,0.0012359044,0.00008494905,0.000059047903,0.00014831855,0.0000014944738,3.3421642e-7,0.007633553,0.010757558,0.97987294],"study_design_scores_gemma":[0.00022351192,0.000512372,0.00001532641,0.005716196,0.00027874095,0.000052137006,0.00026501922,0.0039000234,0.0000010413679,0.003947923,0.9849622,0.00012549473],"about_ca_topic_score_codex":0.0003879195,"about_ca_topic_score_gemma":0.00007680815,"teacher_disagreement_score":0.9797475,"about_ca_system_score_codex":0.0002967753,"about_ca_system_score_gemma":0.0017242052,"threshold_uncertainty_score":0.9818848},"labels":[],"label_agreement":null},{"id":"W4404359250","doi":"10.1161/circ.150.suppl_1.4144409","title":"Abstract 4144409: Visualizing Chronic Myocardial Infarction using Native T1-weighted Signal Intensity Patterns with Similar Image Contrast as LGE MRI","year":2024,"lang":"en","type":"article","venue":"Circulation","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Medicine; Contrast (vision); Myocardial infarction; Magnetic resonance imaging; Intensity (physics); Cardiology; Radiology; Cardiac magnetic resonance; Dynamic contrast; Internal medicine; Artificial intelligence","score_opus":0.013549224863505332,"score_gpt":0.30569265490695363,"score_spread":0.2921434300434483,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404359250","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86491144,0.00025912386,0.13225937,0.00092673796,0.00037871941,0.00035494333,0.000006122388,0.00019018985,0.00071333384],"genre_scores_gemma":[0.9978656,0.000027572987,0.0005368637,0.0003777884,0.0009873676,0.0000072529247,0.00013506613,0.000052496554,0.000009999486],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985536,0.00005593055,0.00028839993,0.00039485752,0.00042756848,0.00027965242],"domain_scores_gemma":[0.9993139,0.00010072118,0.00010072197,0.00014508428,0.0001977818,0.00014182078],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038754518,0.00020349293,0.00030315216,0.00022052259,0.00016385414,0.00013588392,0.00004636098,0.000109093235,0.00021225055],"category_scores_gemma":[0.000092145434,0.00017455526,0.000116137715,0.00026571046,0.000104538,0.00032644335,0.000021930531,0.0006260662,0.000027349262],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005534278,0.00020258062,0.14829779,0.0012217566,0.0014613502,0.0011955829,0.003608536,0.00848018,0.7870431,0.0009507029,0.0003646293,0.04662039],"study_design_scores_gemma":[0.0011887373,0.00013316551,0.29503116,0.001142198,0.00033015563,0.0004131076,0.00017789868,0.69738436,0.003090148,0.00025671942,0.000592636,0.0002597029],"about_ca_topic_score_codex":0.00033334122,"about_ca_topic_score_gemma":0.000004902004,"teacher_disagreement_score":0.7839529,"about_ca_system_score_codex":0.00054857973,"about_ca_system_score_gemma":0.00025417138,"threshold_uncertainty_score":0.7118157},"labels":[],"label_agreement":null},{"id":"W4404377478","doi":"10.1038/s41598-024-78189-6","title":"AI tool for predicting MGMT methylation in glioblastoma for clinical decision support in resource limited settings","year":2024,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"London Health Sciences Centre","funders":"","keywords":"Glioblastoma; Methylation; Computer science; Resource (disambiguation); Decision support system; Bioinformatics; Computational biology; Data science; Medicine; Artificial intelligence; Biology; Cancer research; Gene; Computer network; Genetics","score_opus":0.020437010251250443,"score_gpt":0.37535588876177023,"score_spread":0.3549188785105198,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404377478","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9578026,0.00027276974,0.02908801,0.0054088156,0.00560643,0.0014804506,0.0000043910595,0.00015586779,0.00018067968],"genre_scores_gemma":[0.97866654,0.000009710438,0.01742575,0.000994475,0.0005465465,0.00015201421,0.00018197342,0.000059854556,0.00196312],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9966677,0.0000638051,0.0013992919,0.000977715,0.00048806705,0.0004034355],"domain_scores_gemma":[0.99784565,0.00123914,0.00020201647,0.00043184057,0.00013968359,0.00014166647],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.014203591,0.00014377049,0.0003762686,0.0006429057,0.00012364914,0.00024189391,0.00008310633,0.00015549682,0.00002452127],"category_scores_gemma":[0.011128881,0.00012429903,0.00021330174,0.0008039523,0.00013213149,0.00018039494,0.000056468718,0.000512843,0.000003992727],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006843393,0.00028118253,0.19545895,0.00078718865,0.00005119164,0.0017303256,0.0012633912,0.0007127506,0.0072238343,0.00012312707,0.25053713,0.5411466],"study_design_scores_gemma":[0.0012840057,0.00033689884,0.009191838,0.0012689937,0.00006935581,0.00040262286,0.000107565575,0.35296327,0.0011050118,0.004920016,0.62816775,0.00018267673],"about_ca_topic_score_codex":0.000007197443,"about_ca_topic_score_gemma":0.000013846415,"teacher_disagreement_score":0.5409639,"about_ca_system_score_codex":0.00011634839,"about_ca_system_score_gemma":0.0003180749,"threshold_uncertainty_score":0.9972008},"labels":[],"label_agreement":null},{"id":"W4404419666","doi":"10.1016/b978-0-443-21901-6.00016-1","title":"Artificial intelligence in transplant oncology","year":2024,"lang":"en","type":"book-chapter","venue":"Elsevier eBooks","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network","funders":"","keywords":"Medicine; Oncology; Internal medicine","score_opus":0.023472444009348174,"score_gpt":0.3132040833235789,"score_spread":0.28973163931423074,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404419666","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000894042,0.0019563313,0.000089140165,0.0020866056,0.0008402343,0.00041588253,0.000010488258,0.00008385817,0.99442804],"genre_scores_gemma":[0.0066835545,0.0005005334,0.00074441795,0.0011739782,0.0008121546,0.000022264148,0.00004064662,0.000108761946,0.9899137],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99824715,0.000018453982,0.0006463592,0.0004858486,0.00029427357,0.00030789466],"domain_scores_gemma":[0.9992978,0.00010530722,0.00008976813,0.00028645858,0.000030441059,0.00019021571],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00045584186,0.00031953395,0.00072744937,0.0003562587,0.00003085752,0.000023924418,0.00014891106,0.00041846503,0.0004474725],"category_scores_gemma":[0.00003407634,0.00027193525,0.00023114194,0.000021311507,0.00022041562,0.000011478527,0.000048478283,0.0021479467,0.0005400187],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000057751175,0.000017060665,0.0000060134544,0.00026484294,0.00007552415,0.0026160732,0.0005024724,0.000002864869,0.00007489459,0.050832476,0.000057102665,0.9454929],"study_design_scores_gemma":[0.00008362932,0.00018345568,0.0000059994372,0.0021921636,0.0002500246,0.0003942368,0.00001252278,0.0012029199,0.00004129897,0.07987353,0.9155135,0.00024672563],"about_ca_topic_score_codex":0.0000021644748,"about_ca_topic_score_gemma":0.000035538727,"teacher_disagreement_score":0.9452462,"about_ca_system_score_codex":0.00021732844,"about_ca_system_score_gemma":0.00028722844,"threshold_uncertainty_score":0.9999733},"labels":[],"label_agreement":null},{"id":"W4404420206","doi":"10.1177/08465371241296834","title":"Improving Deep Learning Models for Pediatric Low-Grade Glioma Tumours Molecular Subtype Identification Using MRI-based 3D Probability Distributions of Tumour Location","year":2024,"lang":"en","type":"article","venue":"Canadian Association of Radiologists Journal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"SickKids Foundation; Vector Institute; Hospital for Sick Children; Mental Health Research Canada; University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"Medicine; Neuroradiology; Receiver operating characteristic; Confidence interval; Fluid-attenuated inversion recovery; Convolutional neural network; Neuroradiologist; Glioma; Radiology; Artificial intelligence; Nuclear medicine; Magnetic resonance imaging; Internal medicine; Neurology; Computer science","score_opus":0.015544136130045435,"score_gpt":0.2746954579531733,"score_spread":0.25915132182312783,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404420206","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49346292,0.0008558382,0.5036552,0.0013262623,0.0003186284,0.00030242914,0.00003360642,0.000027206599,0.00001790634],"genre_scores_gemma":[0.98945487,0.000043659737,0.009957328,0.00003958075,0.00027771867,0.000012181034,0.00016117263,0.000027715212,0.000025776513],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980501,0.0002235849,0.0007337304,0.00026321324,0.0003460092,0.00038337184],"domain_scores_gemma":[0.997655,0.00028403293,0.0007779284,0.00013733632,0.0008202711,0.00032543857],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025276958,0.00015001894,0.00035327248,0.00054919225,0.0002289141,0.000083812556,0.0001378079,0.00018126408,0.000009976899],"category_scores_gemma":[0.0047957096,0.00015032981,0.00020946296,0.0006383129,0.000081541984,0.00017757823,0.000008777961,0.00062145444,9.4826333e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010068638,0.00019537949,0.16661061,0.0022236574,0.00033012097,0.00012339123,0.00051836215,0.7151383,0.10208953,0.0036906477,0.0007640385,0.008215222],"study_design_scores_gemma":[0.00073164277,0.00012189692,0.023973174,0.00016877538,0.00040563347,0.00011791072,0.000050973184,0.971079,0.0016927805,0.0014412435,0.00006643062,0.00015056567],"about_ca_topic_score_codex":0.0015129593,"about_ca_topic_score_gemma":0.00029020308,"teacher_disagreement_score":0.49599195,"about_ca_system_score_codex":0.0022538279,"about_ca_system_score_gemma":0.0020551847,"threshold_uncertainty_score":0.61302716},"labels":[],"label_agreement":null},{"id":"W4404527135","doi":"10.5194/sp-2024-27-rc1","title":"Comment on sp-2024-27","year":2024,"lang":"en","type":"peer-review","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Environment and Climate Change Canada","funders":"","keywords":"Computer science","score_opus":0.026580434450455014,"score_gpt":0.36266671095650865,"score_spread":0.33608627650605366,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404527135","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000012529612,0.03177442,0.00010254601,0.632947,0.0088257,0.0004046743,0.000027509934,0.0001339598,0.32578292],"genre_scores_gemma":[0.000006202664,0.0100616915,0.0005889454,0.3484075,0.0013336751,0.000020723779,0.0006062178,0.000065614986,0.6389094],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978699,0.000051258165,0.0004410774,0.000542975,0.00076310727,0.00033170186],"domain_scores_gemma":[0.9987871,0.00014712008,0.000082874176,0.0006073993,0.00007357631,0.00030191522],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0006740592,0.00037329574,0.0009209586,0.00018977436,0.00003791599,0.00004626949,0.00019200952,0.00020338652,0.0129487235],"category_scores_gemma":[0.000462378,0.000248741,0.00037222324,0.00018791249,0.00006587005,0.000010703207,0.00013158184,0.0024581538,0.003451757],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007439359,0.000071556366,0.000007831313,0.008225242,0.00017449177,0.0003050581,0.000010611524,4.6944743e-7,0.0000012780663,0.0010183544,0.95837975,0.031797934],"study_design_scores_gemma":[0.0003061529,0.00019062732,0.0000066419066,0.025614737,0.0007516692,0.00010582204,0.000004719031,0.0005924074,0.0000038913486,0.00017644472,0.9720143,0.00023260103],"about_ca_topic_score_codex":0.00016017216,"about_ca_topic_score_gemma":0.0000034313236,"teacher_disagreement_score":0.3131265,"about_ca_system_score_codex":0.00017137312,"about_ca_system_score_gemma":0.00019218342,"threshold_uncertainty_score":0.9999965},"labels":[],"label_agreement":null},{"id":"W4404541836","doi":"10.34297/ajbsr.2024.21.002879","title":"Artificial Intelligence in Nuclear Medicine: Current Applications and Future Prospects","year":2024,"lang":"en","type":"article","venue":"American Journal of Biomedical Science & Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hospital for Sick Children","funders":"","keywords":"Current (fluid); Engineering ethics; Data science; Computer science; Engineering; Electrical engineering","score_opus":0.03137257137755711,"score_gpt":0.44128152368060625,"score_spread":0.40990895230304913,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404541836","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.66517556,0.01513964,0.016544152,0.29829922,0.0016052602,0.0009131783,0.0000030961603,0.000074894364,0.0022450106],"genre_scores_gemma":[0.99228346,0.003079701,0.0022938931,0.00021341503,0.0020982784,0.000007178267,7.609435e-7,0.000013235388,0.0000100967945],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.996503,0.00010517825,0.0005194427,0.00033534053,0.0020390165,0.000498005],"domain_scores_gemma":[0.99836993,0.00029281818,0.000083943196,0.00016283088,0.00028527106,0.0008051826],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.006512862,0.000097326934,0.0003116423,0.0014028978,0.00017738913,0.00010462853,0.0004072597,0.000032330787,0.000113942224],"category_scores_gemma":[0.00078333647,0.00006167349,0.000044697266,0.005015785,0.00944403,0.0001569925,0.00012409115,0.0018200828,0.000017467302],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035700865,0.00010447355,0.0002832464,0.00006169574,0.000006497465,0.00015171578,0.001145319,4.6490067e-7,0.0049627735,0.010537598,0.00045880693,0.9822517],"study_design_scores_gemma":[0.00041946422,0.0057605426,0.01610748,0.002762783,0.000061641906,0.002857383,0.014434673,0.046239622,0.00024028098,0.022502711,0.8882722,0.00034118866],"about_ca_topic_score_codex":0.00005989013,"about_ca_topic_score_gemma":0.0000012274276,"teacher_disagreement_score":0.9819105,"about_ca_system_score_codex":0.00020822574,"about_ca_system_score_gemma":0.0008249206,"threshold_uncertainty_score":0.9932517},"labels":[],"label_agreement":null},{"id":"W4404580874","doi":"10.1016/j.jlb.2024.100224","title":"PAN-CANCER ANALYSIS OF PRE-TREATMENT CIRCULATING TUMOR DNA (CTDNA) IN PATIENTS FROM THE PRINCESS MARGARET LIQUID BIOPSY PROGRAM","year":2024,"lang":"en","type":"article","venue":"The Journal of Liquid Biopsy","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kingston Health Sciences Centre; Princess Margaret Cancer Centre","funders":"","keywords":"Liquid biopsy; Circulating tumor DNA; Cancer; DNA; Medicine; Internal medicine; Oncology; Biopsy; Biology; Genetics","score_opus":0.013787821082641507,"score_gpt":0.3197902269119754,"score_spread":0.3060024058293339,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404580874","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99194723,0.002478415,0.00018633345,0.0044588875,0.00037957184,0.00041533838,0.000025522384,0.000027401864,0.000081285805],"genre_scores_gemma":[0.9981895,0.00036491794,0.0007138559,0.00022441863,0.00040369097,0.000014764282,0.000020391502,0.000029638075,0.000038789905],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9977663,0.00024894113,0.00085914234,0.0002022752,0.00063645525,0.0002868717],"domain_scores_gemma":[0.99844325,0.00040504758,0.0005235372,0.00034203613,0.00016601912,0.000120087825],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011366823,0.00021662409,0.0006398272,0.00028976402,0.00007609418,0.000050516664,0.00034713538,0.00006232689,0.00010511243],"category_scores_gemma":[0.00024342856,0.00010222189,0.00036029657,0.0010680642,0.00018638285,0.000095582865,0.00007781642,0.0005491229,0.0000019792315],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.009647531,0.0026661057,0.7638312,0.00039108988,0.014333661,0.0007574082,0.016475009,0.0032578458,0.07129547,0.00010827983,0.00036375405,0.11687264],"study_design_scores_gemma":[0.0023834042,0.0039556534,0.9473311,0.0024417148,0.006953211,0.00018036547,0.00069322996,0.029947074,0.0038076784,0.00004592205,0.001990171,0.00027047904],"about_ca_topic_score_codex":0.00078068604,"about_ca_topic_score_gemma":0.000024761353,"teacher_disagreement_score":0.1834999,"about_ca_system_score_codex":0.00021375593,"about_ca_system_score_gemma":0.00021578901,"threshold_uncertainty_score":0.41684878},"labels":[],"label_agreement":null},{"id":"W4404732167","doi":"10.32920/27912744","title":"Quantitative ultrasound radiomics for therapy response monitoring in patients with locally advanced breast cancer: Multi-institutional study results","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Radiomics; Medicine; Breast cancer; Oncology; Ultrasound; Cancer; Internal medicine; Radiology","score_opus":0.02385601765412083,"score_gpt":0.3540405144371038,"score_spread":0.330184496782983,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404732167","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9864472,0.0007612751,0.0051530953,0.0017066329,0.0013217776,0.0039526434,0.00046349235,0.00013613762,0.000057708403],"genre_scores_gemma":[0.95399314,0.0003242121,0.04411053,0.00013787764,0.0002324023,0.0005425463,0.00018223475,0.000093767514,0.0003832652],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9971574,0.00016870405,0.0006918353,0.0009834426,0.0005876267,0.00041102068],"domain_scores_gemma":[0.9979784,0.00075063034,0.00021520446,0.00044360707,0.00041302247,0.00019911937],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012041418,0.00049143686,0.0007759615,0.0004011562,0.00012193283,0.00009714671,0.00023016338,0.00018676129,0.000010356526],"category_scores_gemma":[0.0008327198,0.00033649322,0.00014532822,0.0002759765,0.00018269614,0.00007062412,0.0001579413,0.0015711521,0.0000034520697],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.23142503,0.004711883,0.6346357,0.00066584226,0.0018043924,0.00020193956,0.007153451,0.06319133,0.0011067343,0.00019723142,0.00026221407,0.054644246],"study_design_scores_gemma":[0.04098903,0.0024237887,0.92962277,0.003446469,0.00020991979,0.000024117515,0.0012531701,0.02075905,0.00008859437,0.00012811273,0.0004192151,0.0006357713],"about_ca_topic_score_codex":0.0006903508,"about_ca_topic_score_gemma":0.00007866772,"teacher_disagreement_score":0.29498705,"about_ca_system_score_codex":0.000725585,"about_ca_system_score_gemma":0.0011997109,"threshold_uncertainty_score":0.9999087},"labels":[],"label_agreement":null},{"id":"W4404746650","doi":"10.58530/2024/4223","title":"Gray matter loss and cognitive impairment in lung cancer is associated with blood-brain barrier permeability","year":2024,"lang":"en","type":"article","venue":"Proceedings on CD-ROM - International Society for Magnetic Resonance in Medicine. Scientific Meeting and Exhibition/Proceedings of the International Society for Magnetic Resonance in Medicine, Scientific Meeting and Exhibition","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Cognitive impairment; Blood–brain barrier; Gray (unit); Permeability (electromagnetism); Medicine; Lung cancer; Pathology; Internal medicine; Central nervous system; Chemistry; Radiology; Disease","score_opus":0.010951029965023196,"score_gpt":0.2810184007475088,"score_spread":0.2700673707824856,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404746650","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94385546,0.012435453,0.000014846566,0.038697124,0.0013695908,0.0018670534,0.00017584892,0.000058870704,0.0015257422],"genre_scores_gemma":[0.98768526,0.0014091205,0.001777425,0.0026090322,0.0006343596,0.0007437041,0.0001316711,0.00007413189,0.0049353107],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99384135,0.000023159682,0.001436538,0.0019086982,0.001981366,0.0008089044],"domain_scores_gemma":[0.99655586,0.0011640398,0.0005268363,0.00016129602,0.0013352688,0.00025669512],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.007760139,0.0005718522,0.000835437,0.0005022746,0.0006310494,0.0005128996,0.00048225073,0.00029492425,0.00011277005],"category_scores_gemma":[0.0032808015,0.00042815803,0.0003744335,0.0012700119,0.0032059243,0.00044555543,0.00020248801,0.00094139384,7.304621e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017037188,0.0010206582,0.56259596,0.0066768806,0.00040810718,0.000022474285,0.06811485,0.00007321524,0.10188021,0.003853078,0.23013936,0.023511464],"study_design_scores_gemma":[0.026099067,0.0026482919,0.4606846,0.1293329,0.0012033487,0.00033594845,0.03409875,0.28618154,0.0027510787,0.011186689,0.04364325,0.0018345336],"about_ca_topic_score_codex":0.0004502189,"about_ca_topic_score_gemma":0.000093825256,"teacher_disagreement_score":0.28610831,"about_ca_system_score_codex":0.00055989536,"about_ca_system_score_gemma":0.00029889235,"threshold_uncertainty_score":0.999817},"labels":[],"label_agreement":null},{"id":"W4404751837","doi":"10.32920/27912744.v1","title":"Quantitative ultrasound radiomics for therapy response monitoring in patients with locally advanced breast cancer: Multi-institutional study results","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Medicine; Breast cancer; Internal medicine; Cancer; Oncology","score_opus":0.02385601765412083,"score_gpt":0.3540405144371038,"score_spread":0.330184496782983,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404751837","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9864472,0.0007612751,0.0051530953,0.0017066329,0.0013217776,0.0039526434,0.00046349235,0.00013613762,0.000057708403],"genre_scores_gemma":[0.95399314,0.0003242121,0.04411053,0.00013787764,0.0002324023,0.0005425463,0.00018223475,0.000093767514,0.0003832652],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9971574,0.00016870405,0.0006918353,0.0009834426,0.0005876267,0.00041102068],"domain_scores_gemma":[0.9979784,0.00075063034,0.00021520446,0.00044360707,0.00041302247,0.00019911937],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012041418,0.00049143686,0.0007759615,0.0004011562,0.00012193283,0.00009714671,0.00023016338,0.00018676129,0.000010356526],"category_scores_gemma":[0.0008327198,0.00033649322,0.00014532822,0.0002759765,0.00018269614,0.00007062412,0.0001579413,0.0015711521,0.0000034520697],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.23142503,0.004711883,0.6346357,0.00066584226,0.0018043924,0.00020193956,0.007153451,0.06319133,0.0011067343,0.00019723142,0.00026221407,0.054644246],"study_design_scores_gemma":[0.04098903,0.0024237887,0.92962277,0.003446469,0.00020991979,0.000024117515,0.0012531701,0.02075905,0.00008859437,0.00012811273,0.0004192151,0.0006357713],"about_ca_topic_score_codex":0.0006903508,"about_ca_topic_score_gemma":0.00007866772,"teacher_disagreement_score":0.29498705,"about_ca_system_score_codex":0.000725585,"about_ca_system_score_gemma":0.0011997109,"threshold_uncertainty_score":0.9999087},"labels":[],"label_agreement":null},{"id":"W4404782122","doi":"10.5194/gmd-2024-126-rc2","title":"Comment on gmd-2024-126","year":2024,"lang":"en","type":"peer-review","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Environment and Climate Change Canada","funders":"","keywords":"Statistics; Mathematics","score_opus":0.02673241850364262,"score_gpt":0.36567950810849037,"score_spread":0.33894708960484776,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404782122","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000013884443,0.03338342,0.00011073702,0.64791405,0.006527347,0.00043170195,0.00003043834,0.00015382754,0.31144705],"genre_scores_gemma":[0.00001296509,0.009345844,0.000594843,0.36041218,0.0013393963,0.000032237745,0.0006707204,0.000070157774,0.62752163],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99776185,0.000055907545,0.00046273362,0.00056750886,0.00080370693,0.00034829226],"domain_scores_gemma":[0.9987234,0.00015904971,0.00008773883,0.00063483056,0.000079139136,0.00031587557],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0006990067,0.0003908571,0.00095829857,0.00020135718,0.000047382186,0.000049040496,0.00020330254,0.00021680734,0.008995474],"category_scores_gemma":[0.0004853546,0.0002609336,0.00039011755,0.00020011449,0.00006970429,0.000011496533,0.0001388153,0.0025682284,0.0026657274],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007833018,0.0000787475,0.0000054538214,0.008271715,0.00018615363,0.0002913986,0.000011187552,6.2563964e-7,0.0000015171139,0.001069548,0.94747216,0.042603675],"study_design_scores_gemma":[0.0003390082,0.00020512761,0.0000047153794,0.02598589,0.0007865799,0.00010704073,0.0000071748054,0.0007197204,0.0000043066234,0.00017732807,0.9714193,0.000243838],"about_ca_topic_score_codex":0.00016719,"about_ca_topic_score_gemma":0.0000031557347,"teacher_disagreement_score":0.31607458,"about_ca_system_score_codex":0.00018328927,"about_ca_system_score_gemma":0.00020403524,"threshold_uncertainty_score":0.99998426},"labels":[],"label_agreement":null},{"id":"W4404816742","doi":"10.7554/elife.97827.3.sa0","title":"eLife Assessment: CPT1A mediates radiation sensitivity in colorectal cancer","year":2024,"lang":"en","type":"peer-review","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre","funders":"","keywords":"Colorectal cancer; Sensitivity (control systems); Radiation sensitivity; Oncology; Internal medicine; Cancer; Medicine; Physics; Engineering; Irradiation; Nuclear physics","score_opus":0.015133682388503475,"score_gpt":0.3768161187531301,"score_spread":0.3616824363646266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404816742","genre_codex":"commentary","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008958241,0.17414215,0.00042930126,0.747649,0.013303035,0.0021973192,0.00030592713,0.00044315442,0.052571874],"genre_scores_gemma":[0.07797586,0.41226733,0.0037434513,0.09131976,0.011887717,0.00082495547,0.0117409695,0.00049939635,0.38974056],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974402,0.00016062963,0.00057217735,0.00061307,0.00081691105,0.00039701632],"domain_scores_gemma":[0.99893683,0.00030962887,0.00016475905,0.00021279005,0.00013573555,0.00024023112],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0017018203,0.00037232277,0.0011213183,0.0003235881,0.000037976006,0.000049406462,0.0000880503,0.00031496203,0.0013467554],"category_scores_gemma":[0.00074799394,0.00029119264,0.0002284526,0.00042659813,0.000086013795,0.00005468091,0.00009418582,0.0022916656,0.000102120124],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010295387,0.00006194882,0.003517445,0.004831124,0.00014884616,0.0004405748,0.000042824948,0.000020518286,0.00019560651,0.00006908415,0.9138127,0.076849066],"study_design_scores_gemma":[0.000680952,0.000063146326,0.011757927,0.011166262,0.0006640707,0.000099318415,0.000010906675,0.03527315,0.000069258116,0.00004518922,0.9398247,0.000345147],"about_ca_topic_score_codex":0.0028929731,"about_ca_topic_score_gemma":0.00093320274,"teacher_disagreement_score":0.6563292,"about_ca_system_score_codex":0.0005735304,"about_ca_system_score_gemma":0.0010848986,"threshold_uncertainty_score":0.99995404},"labels":[],"label_agreement":null},{"id":"W4404823900","doi":"10.3233/xst-2010-027000270","title":"Intensity modulated radiation therapy versus three dimensional conformal radiation therapy for treatment of high grade glioma: A radiobiological modeling study","year":2010,"lang":"en","type":"article","venue":"Journal of X-Ray Science and Technology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency","funders":"","keywords":"Radiation therapy; Glioma; Medicine; Intensity (physics); Nuclear medicine; Radiation; Radiology; Cancer research; Physics; Optics","score_opus":0.024691611713113307,"score_gpt":0.3138811815676559,"score_spread":0.2891895698545426,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404823900","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9943191,0.00049962493,0.0011730061,0.0029470657,0.00059739244,0.00043911792,0.0000011928179,0.000020429474,0.000003077133],"genre_scores_gemma":[0.99742836,0.00029684673,0.0020765255,0.00005482363,0.00012716206,0.000006529156,0.000002396383,0.0000059483245,0.0000013809013],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99891067,0.000014266936,0.0003803301,0.00018368008,0.0003088885,0.00020217568],"domain_scores_gemma":[0.9988389,0.00008977699,0.00028497292,0.00014539783,0.0005441107,0.00009685502],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00092381117,0.00011679444,0.00041199883,0.00053383334,0.00016376349,0.000017615275,0.00014670432,0.00012538866,0.0000046799682],"category_scores_gemma":[0.00047527003,0.00007106153,0.000062805266,0.00044701362,0.0004923079,0.00014770034,0.00001815686,0.00025126603,1.7441354e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003054717,0.001453019,0.05126006,0.0000049955884,0.0002393285,0.000043780557,0.0004401759,0.0012786959,0.49912855,0.0005780522,0.00001848797,0.44250014],"study_design_scores_gemma":[0.047505204,0.03591727,0.1418065,0.00003191931,0.00016559784,0.0008429361,0.00046863346,0.7430659,0.025395423,0.0040346486,0.00051148504,0.00025447996],"about_ca_topic_score_codex":0.00004482285,"about_ca_topic_score_gemma":0.0000030044903,"teacher_disagreement_score":0.7417872,"about_ca_system_score_codex":0.000059321133,"about_ca_system_score_gemma":0.00022507699,"threshold_uncertainty_score":0.2897805},"labels":[],"label_agreement":null},{"id":"W4404877572","doi":"10.5194/gmd-2024-89-rc2","title":"Comment on gmd-2024-89","year":2024,"lang":"en","type":"peer-review","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Statistics; Mathematics","score_opus":0.02664474710624248,"score_gpt":0.3656371313961157,"score_spread":0.3389923842898732,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404877572","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000001374412,0.033550445,0.00010875323,0.64878434,0.006461267,0.0004242879,0.000029550234,0.00015059806,0.3104894],"genre_scores_gemma":[0.000012771675,0.0094171725,0.00058422156,0.36087328,0.0013261025,0.000031452706,0.000658817,0.000068637906,0.6270275],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977953,0.000054842003,0.0004546907,0.0005575022,0.0007958347,0.00034187557],"domain_scores_gemma":[0.99874425,0.0001565759,0.00008589135,0.0006241799,0.00007883643,0.0003102822],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0006941158,0.00038339986,0.00094369706,0.00019707749,0.00004641273,0.000048293616,0.00019954525,0.00021257818,0.0091707045],"category_scores_gemma":[0.00048558283,0.00025556408,0.00038243207,0.00019582457,0.00006823007,0.000011200627,0.00013632447,0.0025351723,0.0026793887],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000076087163,0.00007357662,0.000005484342,0.008199584,0.00018250264,0.00028519816,0.000010972446,6.282982e-7,0.0000015314197,0.0010437461,0.94717354,0.043015648],"study_design_scores_gemma":[0.000321203,0.00020178151,0.0000047869044,0.025825188,0.00077189825,0.00010431961,0.000007019208,0.00071735296,0.0000042657093,0.00017474065,0.97162855,0.00023892465],"about_ca_topic_score_codex":0.00016525312,"about_ca_topic_score_gemma":0.0000031024538,"teacher_disagreement_score":0.31653816,"about_ca_system_score_codex":0.00018000793,"about_ca_system_score_gemma":0.00020172542,"threshold_uncertainty_score":0.9999897},"labels":[],"label_agreement":null},{"id":"W4405029255","doi":"10.3390/radiation4040027","title":"Predicting Tumor Progression in Patients with Cervical Cancer Using Computer Tomography Radiomic Features","year":2024,"lang":"en","type":"article","venue":"Radiation","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; University of Toronto; Sunnybrook Health Science Centre","funders":"Terry Fox Foundation","keywords":"Cervical cancer; Medicine; Tomography; Computed tomography; Radiology; Cancer; Medical physics; Internal medicine","score_opus":0.004652358827414445,"score_gpt":0.28216463722186674,"score_spread":0.2775122783944523,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405029255","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99598765,0.001155066,0.0013730127,0.0005444243,0.00043588763,0.00033963803,0.0000036245408,0.00010687029,0.00005385119],"genre_scores_gemma":[0.9949736,0.000013964187,0.00407965,0.00029157972,0.0005349767,0.000014294469,0.000049639468,0.00002933524,0.000012947844],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99904263,0.000039739076,0.0001761358,0.0002517163,0.00029441447,0.00019537668],"domain_scores_gemma":[0.99969524,0.0000405529,0.000048517362,0.0000904498,0.000030943713,0.00009431439],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015812434,0.00011406931,0.00017376928,0.00027177072,0.00006221714,0.000044421664,0.00004085025,0.00005013984,0.00002552877],"category_scores_gemma":[0.000023260258,0.000082578576,0.0000439618,0.0003888959,0.000041680836,0.00012520117,0.000015294187,0.00037633293,0.0000016176135],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008918852,0.00005902688,0.93558365,0.00015588215,0.00003596847,0.00004839636,0.000309948,0.0012150613,0.00011125588,0.000021591331,0.00021683965,0.06215319],"study_design_scores_gemma":[0.00094255037,0.000100435755,0.68682474,0.00076204824,0.00004484592,0.000021488902,0.0000043249884,0.3109204,0.0000407485,0.000007117762,0.0002602188,0.0000710998],"about_ca_topic_score_codex":0.00014474585,"about_ca_topic_score_gemma":0.0000056784643,"teacher_disagreement_score":0.30970532,"about_ca_system_score_codex":0.0001604684,"about_ca_system_score_gemma":0.00009742681,"threshold_uncertainty_score":0.33674565},"labels":[],"label_agreement":null},{"id":"W4405032522","doi":"10.48550/arxiv.2412.00068","title":"Enhanced Lung Cancer Survival Prediction using Semi-Supervised Pseudo-Labeling and Learning from Diverse PET/CT Datasets","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Lung cancer; Artificial intelligence; Computer science; Supervised learning; Machine learning; Medicine; Oncology","score_opus":0.05764184288930582,"score_gpt":0.255998741930017,"score_spread":0.19835689904071116,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405032522","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9807459,0.0010420114,0.015062849,0.00014736899,0.0015917906,0.00038995693,0.00041571766,0.0002878254,0.00031654682],"genre_scores_gemma":[0.9944263,0.0022269508,0.00092617556,0.00011451714,0.0005419937,0.0000017360533,0.0010670818,0.00007935888,0.0006158604],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974962,0.00022901638,0.00031154449,0.0013237044,0.0002121979,0.00042736542],"domain_scores_gemma":[0.9986361,0.00019157407,0.00020356216,0.00050394813,0.00010101731,0.0003637498],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.00044702567,0.0004427188,0.0006470404,0.0003013825,0.00032920088,0.00011928989,0.00025856897,0.00010112192,0.00022863568],"category_scores_gemma":[0.00022611165,0.00048286276,0.00017903547,0.00032926467,0.00018099716,0.00015420871,0.0013440056,0.0030151499,0.000013879175],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004952472,0.00021258238,0.15633337,0.0028902164,0.002794799,0.011330132,0.0013629745,0.78917974,0.029072633,0.00053987897,0.0011515496,0.004636882],"study_design_scores_gemma":[0.0015563811,0.000034173267,0.0013951876,0.0020884946,0.0021422745,0.000060194146,0.00059187895,0.9909275,0.00018288466,0.00039369948,0.00021563692,0.00041167872],"about_ca_topic_score_codex":0.0048546293,"about_ca_topic_score_gemma":0.000052646978,"teacher_disagreement_score":0.20174778,"about_ca_system_score_codex":0.00044330812,"about_ca_system_score_gemma":0.0003122238,"threshold_uncertainty_score":0.9997623},"labels":[],"label_agreement":null},{"id":"W4405098296","doi":"10.1088/2057-1976/ad9b30","title":"Development of a machine learning tool to predict deep inspiration breath hold requirement for locoregional right-sided breast radiation therapy patients","year":2024,"lang":"en","type":"article","venue":"Biomedical Physics & Engineering Express","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Foothills Medical Centre; Alberta Cancer Foundation; University of Calgary","funders":"","keywords":"Logistic regression; Random forest; Robustness (evolution); Artificial intelligence; Medicine; Breast cancer; Support vector machine; Machine learning; Computer science; Nuclear medicine; Cancer; Internal medicine","score_opus":0.010824829344982355,"score_gpt":0.2531279911575913,"score_spread":0.24230316181260897,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405098296","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37852657,0.00020954959,0.6198239,0.00025261796,0.000376268,0.0006076693,0.00002436303,0.00017006327,0.000009014813],"genre_scores_gemma":[0.9021708,0.000027816144,0.095528744,0.00017217283,0.00081102026,0.00022185093,0.00094346533,0.00007753859,0.00004663188],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99814796,0.000015759924,0.000496545,0.0003641532,0.00066489406,0.000310681],"domain_scores_gemma":[0.9992949,0.00011133941,0.0000779298,0.0001659753,0.0001071855,0.0002426724],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032221907,0.00023335763,0.00032167847,0.00018850814,0.00007674675,0.00004164468,0.00012422816,0.00009204211,0.0000195808],"category_scores_gemma":[0.00015243917,0.0001945816,0.00011855474,0.00030351925,0.00004107144,0.00012255408,0.000050087354,0.00029283043,0.000005156434],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028649223,0.0006887731,0.001718795,0.0009135027,0.00039094753,0.000012863396,0.0022004505,0.0049840165,0.41855347,0.0010787112,0.0012068315,0.56796515],"study_design_scores_gemma":[0.0027780652,0.00045526703,0.008991241,0.0010684172,0.00006920826,0.000012074363,0.000010405604,0.6451239,0.00353187,0.00006700342,0.33754635,0.00034621876],"about_ca_topic_score_codex":0.000009905017,"about_ca_topic_score_gemma":6.9596304e-8,"teacher_disagreement_score":0.6401399,"about_ca_system_score_codex":0.00016844562,"about_ca_system_score_gemma":0.00013201605,"threshold_uncertainty_score":0.79348075},"labels":[],"label_agreement":null},{"id":"W4405098987","doi":"10.22215/etd/2024-16302","title":"Opening the Black Box: Utilizing Everyday Textures as Concept-Based Explanations for Deep Learning Model Prediction of Glioma Biomarker Status","year":2024,"lang":"en","type":"dissertation","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Convolutional neural network; Deep learning; Context (archaeology); Computer science; Artificial intelligence; Comprehension; Black box; Artificial neural network; Machine learning; Biomarker; Isocitrate dehydrogenase; Biology","score_opus":0.022335247593374144,"score_gpt":0.3342377055185044,"score_spread":0.31190245792513027,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405098987","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6167072,0.010168066,0.25909328,0.0043430673,0.0035989685,0.006049887,0.00029721408,0.0010145667,0.09872775],"genre_scores_gemma":[0.97101784,0.00010907721,0.006610233,0.00030818582,0.00020946066,0.00017415822,0.0053476077,0.00014843409,0.01607498],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99764,0.00009146134,0.00068948686,0.0005258092,0.0006248385,0.00042840748],"domain_scores_gemma":[0.9982741,0.0005670154,0.00034259367,0.0003023742,0.00033989706,0.00017405525],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00064491725,0.00036299645,0.00054198445,0.00045106895,0.000293643,0.00011356814,0.00019572719,0.00031690492,0.00021480527],"category_scores_gemma":[0.0014628923,0.00025559403,0.00034403638,0.00037977498,0.00015176313,0.000103721606,0.000029205617,0.0010232773,0.000011208553],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004900145,0.00077433605,0.0027593889,0.011563384,0.0051743747,0.00024474366,0.053124685,0.37569246,0.17570499,0.022823775,0.07089154,0.2763462],"study_design_scores_gemma":[0.0013718717,0.00019798613,0.00086236716,0.0011036654,0.0008739902,0.000022685404,0.0077042156,0.97663647,0.003008381,0.00044139664,0.007551935,0.00022505074],"about_ca_topic_score_codex":0.0002322916,"about_ca_topic_score_gemma":0.00003055543,"teacher_disagreement_score":0.600944,"about_ca_system_score_codex":0.00012187478,"about_ca_system_score_gemma":0.0005366775,"threshold_uncertainty_score":0.9999896},"labels":[],"label_agreement":null},{"id":"W4405193998","doi":"10.5194/sp-2024-22-rc1","title":"Comment on sp-2024-22","year":2024,"lang":"en","type":"peer-review","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Environment and Climate Change Canada","funders":"","keywords":"Computer science; Geology","score_opus":0.02560010457084697,"score_gpt":0.3623691702366397,"score_spread":0.33676906566579273,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405193998","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000013573537,0.029382098,0.000098208824,0.6167974,0.00619744,0.00039962374,0.000027577646,0.00013619644,0.3469601],"genre_scores_gemma":[0.000009027467,0.008811067,0.0005917205,0.35268345,0.0013224785,0.00003080336,0.00062977505,0.00006679713,0.63585484],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99786144,0.000052113377,0.00043910334,0.00054243347,0.00077494123,0.00032993665],"domain_scores_gemma":[0.9987909,0.000145198,0.000083144936,0.00060861604,0.00007289101,0.00029920047],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00068203197,0.00037086118,0.00091586576,0.00019167755,0.00004347968,0.000045681707,0.00019301802,0.00019845073,0.0174347],"category_scores_gemma":[0.0004590799,0.00024815,0.0003710897,0.00018870838,0.00006518245,0.000010649657,0.00013510439,0.0024721783,0.0026789487],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000075211765,0.00007334346,0.0000060148623,0.0079763895,0.00017200458,0.00030653656,0.000009035022,6.332681e-7,0.0000013118741,0.0010911827,0.94837546,0.04198058],"study_design_scores_gemma":[0.00031618646,0.00019792585,0.0000050234703,0.024339268,0.0007421755,0.0001434303,0.000004731971,0.0006687237,0.000003275156,0.00018724606,0.9731599,0.00023207799],"about_ca_topic_score_codex":0.000165671,"about_ca_topic_score_gemma":0.0000026298958,"teacher_disagreement_score":0.28889477,"about_ca_system_score_codex":0.00017620626,"about_ca_system_score_gemma":0.0001910174,"threshold_uncertainty_score":0.9999971},"labels":[],"label_agreement":null},{"id":"W4405270793","doi":"10.1109/cvmi61877.2024.10782874","title":"Longitudinal Volumetric Study for the Progression of Alzheimer’s Disease from Structural MRI","year":2024,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Institute of Aging","keywords":"Disease; Magnetic resonance imaging; Computer science; Medicine; Radiology; Pathology","score_opus":0.029914559359121858,"score_gpt":0.3766253933460374,"score_spread":0.34671083398691555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405270793","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9463223,0.021115603,0.021215696,0.008030318,0.0010565136,0.0018192154,0.00002268538,0.00014385032,0.00027379254],"genre_scores_gemma":[0.9958162,0.000026618136,0.0033451794,0.00009622299,0.0003656561,0.000040398132,0.000022568342,0.000018842644,0.0002683605],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99909955,0.000023899847,0.00020567988,0.0002314763,0.0002997731,0.00013959309],"domain_scores_gemma":[0.9992556,0.00031221256,0.000035069617,0.00022049036,0.000049285944,0.0001273601],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002612494,0.000096756434,0.00018254326,0.000095430674,0.00007729919,0.00004026013,0.00009612691,0.00002039534,0.00022288754],"category_scores_gemma":[0.00025614758,0.00004762861,0.00011463454,0.0002455968,0.000074354546,0.00004368958,0.0000478633,0.00019941108,0.000004954126],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033995637,0.00022135778,0.6227879,0.00014640136,0.0009195254,0.000116952935,0.0004990859,0.00010880056,0.00017540313,0.00065301027,0.010260469,0.36377114],"study_design_scores_gemma":[0.0007946192,0.00031154745,0.59297144,0.00012423626,0.0011916304,0.000005437504,0.00019507892,0.40130743,0.000055932127,0.0002218072,0.0027512703,0.0000695245],"about_ca_topic_score_codex":0.0001755695,"about_ca_topic_score_gemma":0.0000027687413,"teacher_disagreement_score":0.40119866,"about_ca_system_score_codex":0.000009956872,"about_ca_system_score_gemma":0.00007052802,"threshold_uncertainty_score":0.24404623},"labels":[],"label_agreement":null},{"id":"W4405352360","doi":"10.1200/cci.24.00133","title":"Real-World and Clinical Trial Validation of a Deep Learning Radiomic Biomarker for PD-(L)1 Immune Checkpoint Inhibitor Response in Advanced Non–Small Cell Lung Cancer","year":2024,"lang":"en","type":"article","venue":"JCO Clinical Cancer Informatics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Medical Center, University of Rochester; Massachusetts General Hospital; University of Toronto; Ohio State University; University of Rochester; School of Medicine and Public Health, University of Wisconsin-Madison","keywords":"Medicine; Hazard ratio; Oncology; Biomarker; Lung cancer; Internal medicine; Clinical trial; Propensity score matching; Cancer; Confidence interval","score_opus":0.03941949459110772,"score_gpt":0.42862745522122636,"score_spread":0.38920796063011864,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405352360","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98750067,0.0018539712,0.004912249,0.0011384351,0.0023094036,0.0018327275,0.000019520669,0.000078932135,0.0003540865],"genre_scores_gemma":[0.97781456,0.0078284945,0.011889303,0.00039309578,0.0009110906,0.00030256572,0.000058327303,0.00007580216,0.0007267829],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99484056,0.00030787152,0.0037133743,0.0003587922,0.00034789063,0.00043152386],"domain_scores_gemma":[0.99485314,0.0035988253,0.0007688352,0.00031950686,0.00017066821,0.00028903244],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007850856,0.00028149443,0.0011267234,0.00039517693,0.000075057374,0.00007337965,0.00016611401,0.00030333526,0.000060376424],"category_scores_gemma":[0.0036551836,0.0002370839,0.00046762047,0.000556537,0.00025841835,0.00023482867,0.000121263016,0.0014266381,0.0000035373578],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.19268018,0.0008256032,0.2261597,0.008375135,0.00071597786,0.000051667994,0.00513697,0.0036861347,0.0044106157,0.000067216206,0.0013070881,0.5565837],"study_design_scores_gemma":[0.06176179,0.0020479017,0.06858336,0.00270377,0.00071379414,0.0000091689,0.00043626645,0.8497,0.0010137323,0.00004482429,0.0125666335,0.0004187724],"about_ca_topic_score_codex":0.0002463235,"about_ca_topic_score_gemma":0.000060096692,"teacher_disagreement_score":0.84601384,"about_ca_system_score_codex":0.0002816237,"about_ca_system_score_gemma":0.0007890844,"threshold_uncertainty_score":0.96680015},"labels":[],"label_agreement":null},{"id":"W4405428503","doi":"10.7759/cureus.75819","title":"Models and Biomarkers for Local Response Prediction in Early-Stage and Oligometastatic Non-small Cell Lung Cancer Patients Treated With Stereotactic Body Radiation Therapy Using Machine Learning","year":2024,"lang":"en","type":"article","venue":"Cureus","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Jewish General Hospital","funders":"","keywords":"Medicine; Response Evaluation Criteria in Solid Tumors; Stage (stratigraphy); Institutional review board; SABR volatility model; Receiver operating characteristic; Lung cancer; Radiosurgery; Recursive partitioning; non-small cell lung cancer (NSCLC); Retrospective cohort study; Radiation therapy; Radiology; Oncology; Internal medicine; Disease; Progressive disease; Surgery","score_opus":0.014400192484656285,"score_gpt":0.28845141901066024,"score_spread":0.27405122652600394,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405428503","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9776786,0.0047581424,0.01653866,0.00011896159,0.00008175125,0.00073018734,0.000025293662,0.00004700753,0.000021383694],"genre_scores_gemma":[0.99798447,0.00087171065,0.0007238277,0.00005852333,0.000035119585,0.00004711572,0.00005804778,0.00004845526,0.00017275292],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99903464,0.00010242837,0.00020616788,0.00030653208,0.00013777998,0.00021242398],"domain_scores_gemma":[0.99950504,0.00019153752,0.00006469083,0.00008136555,0.00003994572,0.000117394775],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039997997,0.00016084185,0.00022039474,0.00021461207,0.000080167985,0.00006973476,0.000027566051,0.00006081236,0.000006357973],"category_scores_gemma":[0.00005490909,0.00012440089,0.000026315749,0.00019623208,0.000060745162,0.00018790254,0.000014206142,0.00026805495,1.960649e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0034984457,0.00012693304,0.9694504,0.00063965644,0.00028409407,0.00005717127,0.0030731845,0.004822522,0.00488844,0.0000058635933,0.000022082642,0.013131215],"study_design_scores_gemma":[0.0037429354,0.0006883733,0.1141458,0.00035278485,0.00015991746,0.000011559266,0.00006018587,0.8803582,0.00019878686,0.00000692364,0.00016541053,0.000109104156],"about_ca_topic_score_codex":0.001189574,"about_ca_topic_score_gemma":0.00002101515,"teacher_disagreement_score":0.87553567,"about_ca_system_score_codex":0.00017292211,"about_ca_system_score_gemma":0.00008588781,"threshold_uncertainty_score":0.5072921},"labels":[],"label_agreement":null},{"id":"W4405487475","doi":"10.4018/979-8-3693-7728-4.ch011","title":"Enhancing Throat Cancer Prediction and Detection","year":2024,"lang":"en","type":"book-chapter","venue":"Advances in medical diagnosis, treatment, and care (AMDTC) book series","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"New York Institute of Technology","funders":"","keywords":"Overfitting; Interpretability; Computer science; Artificial intelligence; Machine learning; Convolutional neural network; Recurrent neural network; Deep learning; Throat; Artificial neural network; Medicine; Surgery","score_opus":0.006539896866378853,"score_gpt":0.28952405390138114,"score_spread":0.2829841570350023,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405487475","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0092868125,0.890265,0.00009823954,0.0037604282,0.0020715164,0.001087835,0.0001595431,0.0002981281,0.092972495],"genre_scores_gemma":[0.03470954,0.92995775,0.000109957175,0.00074177096,0.0010746553,0.000519996,0.00015806501,0.00010928649,0.032619],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976708,0.000030265646,0.00053982716,0.00084708736,0.00052813196,0.00038382894],"domain_scores_gemma":[0.9988719,0.00025102732,0.00014496385,0.00023929481,0.00006968816,0.00042311335],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00014993417,0.000577152,0.0008719039,0.00023817465,0.00018584906,0.00006362913,0.0000755579,0.0005091797,0.0004826175],"category_scores_gemma":[0.00017298358,0.00045226316,0.00014933184,0.00006229602,0.0006584142,0.0006373802,0.00008621164,0.00088168366,0.000010403957],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023778912,0.000098569275,0.015072011,0.0028329692,0.00048787566,0.0010254898,0.0041101603,0.0000074826485,0.000060233822,0.0076693958,0.00029530062,0.9681027],"study_design_scores_gemma":[0.0016851032,0.0012573197,0.0007494668,0.0073791924,0.00087276794,0.00033669692,0.0009969295,0.00006995564,0.00066293206,0.0024519784,0.9831058,0.00043190375],"about_ca_topic_score_codex":0.00024417994,"about_ca_topic_score_gemma":0.002365454,"teacher_disagreement_score":0.98281044,"about_ca_system_score_codex":0.00045708424,"about_ca_system_score_gemma":0.00018709093,"threshold_uncertainty_score":0.99979293},"labels":[],"label_agreement":null},{"id":"W4405499503","doi":"10.1148/radiol.241711","title":"Methodological Challenges in Evaluating Large Language Models in Radiology","year":2024,"lang":"en","type":"letter","venue":"Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Medicine; Medical physics; Radiology","score_opus":0.20321644140985679,"score_gpt":0.44120404212996656,"score_spread":0.23798760072010977,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405499503","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02987473,0.09102664,0.0011348589,0.8680218,0.0014617668,0.00069247454,0.000017669925,0.00018714371,0.0075829136],"genre_scores_gemma":[0.04113055,0.017802672,0.022627672,0.9024495,0.011591218,0.0003835613,0.0010163721,0.00032354842,0.0026749142],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9937721,0.0027691112,0.0008478379,0.0011778285,0.00029492023,0.0011382046],"domain_scores_gemma":[0.99676484,0.0023856822,0.00016006388,0.00055152766,0.000031452877,0.00010645333],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.0055183545,0.00048102436,0.0019995114,0.0009399119,0.000029875477,0.0000137270545,0.0003425751,0.0021154124,0.00022169105],"category_scores_gemma":[0.0027501544,0.00038430563,0.00025328633,0.0002742362,0.00022765792,0.000042230175,0.00018462999,0.008610948,0.000075649834],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003823752,0.00026435454,0.002672698,0.0036431234,0.00060090725,0.08985948,0.008960476,0.0017009927,0.0014755613,0.0066565718,0.7428365,0.14094701],"study_design_scores_gemma":[0.006700872,0.0015561038,0.0037428574,0.002030254,0.00044816104,0.018238893,0.00084409356,0.3235544,0.00001202022,0.031968165,0.60953647,0.0013677473],"about_ca_topic_score_codex":0.000094047326,"about_ca_topic_score_gemma":0.00003039236,"teacher_disagreement_score":0.3218534,"about_ca_system_score_codex":0.0003245095,"about_ca_system_score_gemma":0.0002060136,"threshold_uncertainty_score":0.9998609},"labels":[],"label_agreement":null},{"id":"W4405540996","doi":"10.1016/j.cmpbup.2024.100170","title":"Predictive analysis of clinical features for HPV status in oropharynx squamous cell carcinoma: A machine learning approach with explainability","year":2024,"lang":"en","type":"article","venue":"Computer Methods and Programs in Biomedicine Update","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Surgical Specialties (Canada)","funders":"Erasmus+; Agència per a la Competitivitat de l’Empresa; Instituto de Salud Carlos III; Agència de Gestió d'Ajuts Universitaris i de Recerca; Generalitat de Catalunya; European Commission","keywords":"Basal cell; Medicine; Oncology; Artificial intelligence; Dermatology; Internal medicine; Computer science","score_opus":0.036075757641731154,"score_gpt":0.39151067233364395,"score_spread":0.3554349146919128,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405540996","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48067966,0.0076220646,0.50954306,0.00062308594,0.00025020173,0.0010436098,0.000015861458,0.000077328405,0.0001451452],"genre_scores_gemma":[0.60769457,0.00018385616,0.39141452,0.00012761886,0.00015607059,0.00006510334,0.0003043657,0.000025888929,0.000028031047],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966629,0.00072254735,0.0009670417,0.00086179416,0.00028930194,0.00049638085],"domain_scores_gemma":[0.9980348,0.0010722284,0.00017839465,0.00030851513,0.00010960967,0.00029646372],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005308712,0.0003014434,0.0014202235,0.0009960994,0.000049383118,0.000045303714,0.00013876084,0.0001706371,0.000010982603],"category_scores_gemma":[0.00030909988,0.0001992362,0.00021889473,0.002027384,0.0005167897,0.000076295015,0.00011989563,0.0011127315,1.2642163e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00079336186,0.0004987566,0.39664388,0.0013195823,0.0002825288,0.0001104758,0.0015651579,0.00044157135,0.00004606855,0.00007103229,0.00004838665,0.5981792],"study_design_scores_gemma":[0.0039718933,0.0026914529,0.23567617,0.00015496467,0.001052806,0.000040748084,0.00022239331,0.75019926,0.000023657449,0.000115400035,0.0056713033,0.00017994226],"about_ca_topic_score_codex":0.00041272194,"about_ca_topic_score_gemma":0.000015817328,"teacher_disagreement_score":0.7497577,"about_ca_system_score_codex":0.00006144697,"about_ca_system_score_gemma":0.00014082209,"threshold_uncertainty_score":0.8124617},"labels":[],"label_agreement":null},{"id":"W4405641483","doi":"10.1002/mp.17586","title":"Predicting early stage lung cancer recurrence and survival from combined tumor motion amplitude and radiomics on free‐breathing 4D‐CT","year":2024,"lang":"en","type":"article","venue":"Medical Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier de l’Université de Montréal; Polytechnique Montréal","funders":"Varian Medical Systems","keywords":"Medicine; Lung cancer; Radiation therapy; Logistic regression; Receiver operating characteristic; Stage (stratigraphy); Cancer; Radiology; Radiation treatment planning; Cohort; Primary tumor; Medical imaging; Retrospective cohort study; Proportional hazards model; Metastasis; Oncology; Internal medicine","score_opus":0.012479549627677687,"score_gpt":0.29975164286348255,"score_spread":0.2872720932358049,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405641483","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96557546,0.0019869204,0.026692217,0.0037867632,0.0011385316,0.00025625553,0.00006581333,0.0002014096,0.00029664004],"genre_scores_gemma":[0.9964511,0.00055137003,0.0005202907,0.0009101849,0.0013515983,0.000020262749,0.000058548416,0.000053110376,0.000083562205],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99784607,0.00008906832,0.00032716704,0.0005648342,0.0008292006,0.0003436629],"domain_scores_gemma":[0.9984781,0.00063736347,0.0000737228,0.00027630443,0.00003793586,0.00049657084],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00066615955,0.00024177298,0.0004404149,0.000063008854,0.00017702839,0.00018821235,0.0001521306,0.00007409226,0.000068856876],"category_scores_gemma":[0.001030415,0.00020500184,0.000067790694,0.00019122081,0.0003921778,0.00015153665,0.0001487516,0.0013348984,0.000002655065],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002623845,0.00032802112,0.6032327,0.0016747797,0.0005936065,0.0018701687,0.0037306566,0.000099808705,0.0010029125,0.008623969,0.0019218575,0.37665915],"study_design_scores_gemma":[0.004224232,0.00037167143,0.090415396,0.005735663,0.0004691734,0.00011132664,0.00012867914,0.8908486,0.0006263097,0.005345797,0.001185207,0.0005379621],"about_ca_topic_score_codex":0.001926513,"about_ca_topic_score_gemma":0.000013330008,"teacher_disagreement_score":0.8907488,"about_ca_system_score_codex":0.00010820616,"about_ca_system_score_gemma":0.00018003165,"threshold_uncertainty_score":0.8359732},"labels":[],"label_agreement":null},{"id":"W4405647140","doi":"10.59350/yr6m5-qem07","title":"Find me at ICHG!","year":2011,"lang":"en","type":"preprint","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Business","score_opus":0.02583078636556079,"score_gpt":0.30564591897964766,"score_spread":0.27981513261408686,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405647140","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34085625,0.0009863486,0.004194137,0.007172647,0.0016047952,0.00049159717,0.0000049470823,0.00031463185,0.64437467],"genre_scores_gemma":[0.69881195,0.0005213202,0.026540285,0.007046282,0.0012801203,0.00004253378,0.00024137522,0.00012179507,0.26539433],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986999,0.00003152843,0.00027597693,0.00044416552,0.00027601662,0.00027240574],"domain_scores_gemma":[0.9989101,0.0000438572,0.00010532685,0.0006033657,0.0000552217,0.0002821138],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00029534826,0.00022790156,0.00046904117,0.00010424206,0.000054773904,0.000019764895,0.00018333583,0.00028491463,0.005808961],"category_scores_gemma":[0.0002554769,0.00017292832,0.00019984628,0.000041145606,0.00010033797,0.000013521255,0.00077486585,0.0012083375,0.0005358576],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005466264,0.0008269726,0.11232504,0.0031110626,0.0017026798,0.0014527669,0.003331898,0.0001868314,0.014696303,0.011309772,0.7352085,0.11530156],"study_design_scores_gemma":[0.00704504,0.00060173764,0.16171055,0.0031127888,0.0021651117,0.0014845805,0.00015057522,0.045301996,0.009032024,0.026909681,0.7398683,0.0026176393],"about_ca_topic_score_codex":0.00027190562,"about_ca_topic_score_gemma":0.0000052217865,"teacher_disagreement_score":0.3789803,"about_ca_system_score_codex":0.00010755803,"about_ca_system_score_gemma":0.00012918744,"threshold_uncertainty_score":0.99509984},"labels":[],"label_agreement":null},{"id":"W4405738470","doi":"10.5194/sp-2024-26-rc2","title":"Comment on sp-2024-26","year":2024,"lang":"en","type":"peer-review","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mathematics","score_opus":0.02688323107277995,"score_gpt":0.36316620717587705,"score_spread":0.3362829761030971,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405738470","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000012579918,0.032052312,0.00011337183,0.6742831,0.0067187194,0.00043151143,0.000022195769,0.00023556002,0.286142],"genre_scores_gemma":[0.000009763069,0.008988445,0.0006152828,0.36173543,0.0013755809,0.00003020532,0.00036267136,0.000094374474,0.62678826],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978667,0.000051249157,0.00044235773,0.00054344314,0.0007641198,0.0003321486],"domain_scores_gemma":[0.99878633,0.00014609743,0.00008308734,0.00060829945,0.00007376166,0.00030242105],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0006755132,0.00037344274,0.0009250156,0.00018912092,0.000043229356,0.000046351153,0.00019150227,0.00020365526,0.011043706],"category_scores_gemma":[0.00045785544,0.00024887387,0.00037301722,0.0001876144,0.0000660021,0.000010713836,0.00013097073,0.0024621636,0.0037043234],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007590734,0.000071183524,0.000005343158,0.008142525,0.00017338888,0.00030541123,0.000010477845,6.274424e-7,0.000001359387,0.0009989851,0.94892186,0.041361276],"study_design_scores_gemma":[0.00031120336,0.00019769078,0.000007112452,0.02570173,0.00075530744,0.00010671286,0.0000047419917,0.0006692276,0.0000039960596,0.00017926734,0.9718304,0.00023257469],"about_ca_topic_score_codex":0.00016552761,"about_ca_topic_score_gemma":0.0000035823666,"teacher_disagreement_score":0.34064624,"about_ca_system_score_codex":0.00017230451,"about_ca_system_score_gemma":0.00019251525,"threshold_uncertainty_score":0.99999636},"labels":[],"label_agreement":null},{"id":"W4405739105","doi":"10.1364/laop.2024.w4a.16","title":"Characterizing Breast Tissue Samples with Integrated Imaging","year":2024,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; Toronto Metropolitan University; St. Michael's Hospital","funders":"","keywords":"Breast tissue; Computer science; Biomedical engineering; Medicine; Breast cancer; Internal medicine; Cancer","score_opus":0.008350827297156423,"score_gpt":0.27881822526390987,"score_spread":0.27046739796675345,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405739105","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.60701966,0.002186093,0.21032472,0.10795294,0.0010726649,0.0006266303,0.000027708924,0.002577868,0.068211734],"genre_scores_gemma":[0.98578656,0.00003126934,0.008480354,0.0020088875,0.00031344674,0.0000071556587,0.00007180761,0.00004576595,0.0032547654],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.999173,0.000016386415,0.00014571227,0.00025786893,0.0001784354,0.00022859455],"domain_scores_gemma":[0.9995919,0.00005595969,0.000016684871,0.00014440069,0.00004234971,0.0001487313],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017992589,0.00013294685,0.00018749369,0.00013291204,0.000051394934,0.0001350504,0.000056773373,0.00002393702,0.00076709164],"category_scores_gemma":[0.000041603093,0.000080895334,0.000034652832,0.00023716791,0.00007947896,0.00012052965,0.000022555036,0.00039616437,0.00009348275],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006385354,0.000049446597,0.02085643,0.00028135834,0.00012958627,0.0009698738,0.000501487,0.00000338645,0.13144504,0.0030056955,0.0050041773,0.8376897],"study_design_scores_gemma":[0.0014667148,0.00022866798,0.05858562,0.0036783828,0.00033338738,0.015306486,0.00095330435,0.12363448,0.010237928,0.0002015289,0.784746,0.0006275336],"about_ca_topic_score_codex":0.00020955851,"about_ca_topic_score_gemma":0.0000029540602,"teacher_disagreement_score":0.8370621,"about_ca_system_score_codex":0.00004419913,"about_ca_system_score_gemma":0.00009695428,"threshold_uncertainty_score":0.8399115},"labels":[],"label_agreement":null},{"id":"W4405847812","doi":"10.3390/diagnostics15010038","title":"Quantitative Physiologic MRI Combined with Feature Engineering for Developing Machine Learning-Based Prediction Models to Distinguish Glioblastomas from Single Brain Metastases","year":2024,"lang":"en","type":"article","venue":"Diagnostics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Douglas Mental Health University Institute","funders":"","keywords":"Artificial intelligence; Random forest; Receiver operating characteristic; Diffusion MRI; Fractional anisotropy; Computer science; Feature selection; Machine learning; Pattern recognition (psychology); Magnetic resonance imaging; Medicine; Radiology","score_opus":0.02161781213461082,"score_gpt":0.27542207718101197,"score_spread":0.25380426504640113,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405847812","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15432823,0.0011650671,0.8349746,0.00754461,0.0004177996,0.0006935028,0.00032464854,0.00051722897,0.000034349883],"genre_scores_gemma":[0.78491336,0.000043756147,0.2116727,0.0013115479,0.0003136897,0.00012807896,0.001420494,0.00009892415,0.00009744475],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986374,0.000052329757,0.00023800634,0.0004638942,0.00026786604,0.0003405368],"domain_scores_gemma":[0.99604064,0.0033949018,0.000063265936,0.00016186082,0.00016187059,0.00017744728],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002582423,0.00027992282,0.000411999,0.00019284322,0.00012530635,0.00010601635,0.00009842774,0.00008847394,0.000007820265],"category_scores_gemma":[0.0053097853,0.00021919636,0.00009514362,0.000393746,0.000052655578,0.00007925371,0.00003999449,0.0005248562,0.0000058635173],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014595112,0.00034408298,0.002990484,0.00091597665,0.00072616595,0.00046969377,0.0015500056,0.9456829,0.01368819,0.0053719063,0.020455979,0.006345122],"study_design_scores_gemma":[0.0011495836,0.0025694917,0.0010587154,0.0017352788,0.00025916132,0.000010205686,0.00007245403,0.97573066,0.0019466114,0.0003472569,0.01485599,0.00026459145],"about_ca_topic_score_codex":0.00007148535,"about_ca_topic_score_gemma":0.000022256214,"teacher_disagreement_score":0.63058513,"about_ca_system_score_codex":0.00012919326,"about_ca_system_score_gemma":0.00011861116,"threshold_uncertainty_score":0.8938568},"labels":[],"label_agreement":null},{"id":"W4405852731","doi":"10.1007/978-3-031-76163-8_27","title":"Exploring Compound Loss Functions for Brain Tumor Segmentation","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Computer science; Segmentation; Artificial intelligence; Computer vision","score_opus":0.042337335104010575,"score_gpt":0.3037801112908157,"score_spread":0.26144277618680517,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405852731","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019916128,0.00033210454,0.9849406,0.0072972835,0.0029888821,0.00055659394,0.00000975021,0.00011754114,0.0017656292],"genre_scores_gemma":[0.3179966,0.00016230415,0.63243943,0.019956408,0.009354097,0.00026211515,0.00029859174,0.00035874065,0.0191717],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99813133,0.000007849541,0.00032181194,0.0007240821,0.00047311356,0.00034183505],"domain_scores_gemma":[0.99883175,0.0004996829,0.00009317798,0.00031883369,0.00010693894,0.00014961201],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006105404,0.0002687889,0.00036353033,0.0005419603,0.00017786284,0.00017279503,0.00024355375,0.00007669717,0.000032001597],"category_scores_gemma":[0.00019229116,0.00023191157,0.00013237937,0.00022158098,0.00043085573,0.00016502924,0.00014342561,0.0008263736,0.000034864916],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006118263,0.000048446003,0.00022582481,0.000764278,0.000080096084,0.00046319354,0.0012926314,0.020095214,0.002192832,0.0071091377,0.0006159244,0.96705127],"study_design_scores_gemma":[0.0013262322,0.0005598675,0.0002087475,0.0029655846,0.00016398264,0.0008378997,0.0000036914214,0.88000757,0.00094669795,0.06377342,0.048501898,0.00070443546],"about_ca_topic_score_codex":0.000017217239,"about_ca_topic_score_gemma":0.000010990382,"teacher_disagreement_score":0.9663468,"about_ca_system_score_codex":0.00029353256,"about_ca_system_score_gemma":0.0002486707,"threshold_uncertainty_score":0.9457079},"labels":[],"label_agreement":null},{"id":"W4405907056","doi":"10.1109/access.2024.3524116","title":"Automatic Calculation of Cardiometric Coefficients on Chest X-Ray Images","year":2024,"lang":"en","type":"article","venue":"IEEE Access","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Analytical Center for the Government of the Russian Federation","keywords":"Computer science; Computer graphics (images)","score_opus":0.022706633888283683,"score_gpt":0.35856815750395626,"score_spread":0.33586152361567256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405907056","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96984243,0.00046820083,0.022520209,0.00090830814,0.0011104345,0.00022406527,0.0000050140516,0.00016136354,0.004759953],"genre_scores_gemma":[0.9987634,0.00003184872,0.00037784083,0.00021444427,0.00022223592,0.000007537424,0.000012386754,0.000023993516,0.00034633058],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989724,0.000032421784,0.00023048122,0.0002057394,0.000405109,0.00015381031],"domain_scores_gemma":[0.9994244,0.00018205673,0.000047684138,0.00020347974,0.0000545768,0.00008782289],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034257342,0.0000996571,0.00024537352,0.0005755045,0.000033636028,0.000075192955,0.00013446316,0.00004778871,0.00007890805],"category_scores_gemma":[0.0003600551,0.000076404554,0.000096033684,0.0010514777,0.00006337245,0.000100473306,0.00002409224,0.00023629764,0.000042225638],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039398827,0.00031464896,0.02694184,0.002591817,0.00031588238,0.0003187988,0.00043817447,0.010640175,0.01676994,0.00020902403,0.023288064,0.91813225],"study_design_scores_gemma":[0.0010852728,0.00029560298,0.27681434,0.0014289485,0.0003208161,0.000054197924,0.000022588212,0.7002498,0.011859411,0.00009299329,0.007543781,0.0002322431],"about_ca_topic_score_codex":0.000058335107,"about_ca_topic_score_gemma":1.4002815e-7,"teacher_disagreement_score":0.91789997,"about_ca_system_score_codex":0.000047582205,"about_ca_system_score_gemma":0.000056374087,"threshold_uncertainty_score":0.31156874},"labels":[],"label_agreement":null},{"id":"W4405934686","doi":"10.3390/cancers17010058","title":"Machine Learning and Computed Tomography Radiomics to Predict Disease Progression to Upfront Pembrolizumab Monotherapy in Advanced Non-Small-Cell Lung Cancer: A Pilot Study","year":2024,"lang":"en","type":"article","venue":"Cancers","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of British Columbia","funders":"BC Cancer Foundation; Michael Smith Health Research BC","keywords":"Pembrolizumab; Medicine; Lung cancer; Oncology; Internal medicine; Cohort; Retrospective cohort study; Logistic regression; Response Evaluation Criteria in Solid Tumors; non-small cell lung cancer (NSCLC); Radiomics; Radiology; Progressive disease; Disease; Medical physics; Cancer; Immunotherapy","score_opus":0.007912524727895366,"score_gpt":0.30442250394066683,"score_spread":0.29650997921277145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405934686","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9712955,0.018098857,0.004736664,0.0022740362,0.00058250275,0.0026175177,0.000018241131,0.00021181817,0.00016490919],"genre_scores_gemma":[0.9944962,0.0009649061,0.002525193,0.0009003919,0.00023519396,0.000512152,0.00002062642,0.00009267934,0.00025261557],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980384,0.000084344436,0.00035270312,0.00073465146,0.00031982115,0.0004700502],"domain_scores_gemma":[0.99881124,0.00006313632,0.000055954617,0.00022994734,0.00004760033,0.0007921243],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00031458822,0.00030968737,0.00047329164,0.0005455609,0.00011505332,0.000092457965,0.00014828761,0.00003693901,0.000027453376],"category_scores_gemma":[0.000060424165,0.000269903,0.000065824715,0.0008065839,0.000041260035,0.000074602816,0.00009095059,0.00067614205,0.000002333167],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0054386877,0.00034725212,0.72918105,0.0010144686,0.00023976735,0.00066223374,0.006292986,0.06433216,0.0084585305,0.000009981091,0.0015033352,0.18251953],"study_design_scores_gemma":[0.008816051,0.0043367175,0.08204109,0.00304375,0.00024061426,0.000014477793,0.00042841898,0.8866686,0.0001555881,0.000009136797,0.013743245,0.0005022902],"about_ca_topic_score_codex":0.0010052846,"about_ca_topic_score_gemma":0.0001657869,"teacher_disagreement_score":0.82233644,"about_ca_system_score_codex":0.00094577303,"about_ca_system_score_gemma":0.0005650509,"threshold_uncertainty_score":0.9999753},"labels":[],"label_agreement":null},{"id":"W4405954304","doi":"10.1371/journal.pone.0311910","title":"Predefined and data-driven CT radiomics predict recurrence-free and overall survival in patients with pulmonary metastases treated with stereotactic body radiotherapy","year":2024,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; University of Toronto; Sunnybrook Health Science Centre","funders":"","keywords":"Medicine; Proportional hazards model; Radiosurgery; Radiomics; Lung cancer; Multivariate analysis; Radiology; Kurtosis; Survival analysis; Nuclear medicine; Radiation therapy; Oncology; Internal medicine","score_opus":0.024012428600381403,"score_gpt":0.25934113067322956,"score_spread":0.23532870207284814,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405954304","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99575776,0.0020624315,0.00008269161,0.00087929773,0.00003484146,0.00068008126,0.00019634269,0.000102569305,0.00020399847],"genre_scores_gemma":[0.9921718,0.0013217479,0.0053683594,0.00012267142,0.00009602059,0.000022501692,0.0006637431,0.000067054185,0.0001660982],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9982905,0.000107786516,0.00025403322,0.0005980298,0.00046947875,0.00028020184],"domain_scores_gemma":[0.9989031,0.0002098178,0.000066137145,0.00057786674,0.00004157937,0.00020150923],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027375575,0.00024799566,0.00054527266,0.00020123884,0.000050818835,0.00010322863,0.00017039958,0.000037951366,0.000031643427],"category_scores_gemma":[0.00017565666,0.00016957519,0.00001676275,0.00022693824,0.0001762188,0.0002951398,0.00009940285,0.0004607663,7.803465e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015414708,0.0012068874,0.98809814,0.0006352,0.001251458,0.0005137961,0.0001341581,0.0000087594635,0.0003623446,0.00003649403,0.00021377286,0.0059975386],"study_design_scores_gemma":[0.011733949,0.0027235993,0.7896368,0.0037335933,0.0016065174,0.000198109,0.000028627213,0.189173,0.00007645311,0.00004166744,0.00058996154,0.00045773247],"about_ca_topic_score_codex":0.00015125216,"about_ca_topic_score_gemma":0.000011819661,"teacher_disagreement_score":0.19846132,"about_ca_system_score_codex":0.00006892681,"about_ca_system_score_gemma":0.00009178114,"threshold_uncertainty_score":0.6915075},"labels":[],"label_agreement":null},{"id":"W4405980019","doi":"10.1101/2024.12.27.630495","title":"Subregional Biomarkers in FDG PET for Alzheimer’s Diagnosis and Staging: An Interpretable and Explainable model","year":2024,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Eisai; Northern California Institute for Research and Education; Pfizer; Novartis Pharmaceuticals Corporation; University of Southern California; Biogen; Boğaziçi Üniversitesi; Eli Lilly and Company; Bristol-Myers Squibb; BioClinica; U.S. Department of Defense; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; Alzheimer's Association","keywords":"Pet imaging; Positron emission tomography; Medicine; Radiology","score_opus":0.02513350126142693,"score_gpt":0.28247560853916986,"score_spread":0.2573421072777429,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405980019","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9823081,0.009979558,0.002664612,0.002996043,0.0004576324,0.0012192109,0.00013178105,0.00022634206,0.000016715538],"genre_scores_gemma":[0.97472996,0.0013189561,0.022317965,0.00059951306,0.00021250082,0.0006466138,0.0000020702987,0.00016330584,0.000009121629],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99741554,0.00007065832,0.0004814331,0.0011732749,0.0002822795,0.00057681167],"domain_scores_gemma":[0.99846184,0.00015265116,0.00015249086,0.0005754992,0.0001623442,0.00049515796],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001071524,0.0004903603,0.0007192634,0.0005284631,0.00011434838,0.00026421383,0.00020388489,0.0002595455,0.000011211926],"category_scores_gemma":[0.00036394285,0.00049175764,0.00010525165,0.0002419673,0.0002321347,0.00015546018,0.00053038396,0.0010781516,0.0000022846439],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0023274766,0.0026087356,0.69048774,0.027948702,0.008414611,0.003846406,0.0012340803,0.0029355562,0.22018433,0.019754076,0.019355426,0.0009028693],"study_design_scores_gemma":[0.0023038543,0.0002363481,0.022279654,0.003454678,0.0011047175,9.931675e-7,0.00004198001,0.96177584,0.0037701568,0.00022109126,0.0037258787,0.0010848105],"about_ca_topic_score_codex":0.00019988154,"about_ca_topic_score_gemma":0.0000032154378,"teacher_disagreement_score":0.9588403,"about_ca_system_score_codex":0.00016534077,"about_ca_system_score_gemma":0.00053899735,"threshold_uncertainty_score":0.9997534},"labels":[],"label_agreement":null},{"id":"W4406018731","doi":"10.1016/j.ccell.2024.12.002","title":"Classification of non-TCGA cancer samples to TCGA molecular subtypes using compact feature sets","year":2025,"lang":"en","type":"article","venue":"Cancer Cell","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre","funders":"National Human Genome Research Institute; Eisai; National Cancer Institute; National Institutes of Health; Boston Scientific Corporation; Gilead Sciences; Pfizer","keywords":"Biology; Cancer research; Feature (linguistics); Computational biology; Oncology; Internal medicine; Medicine","score_opus":0.021524466788702307,"score_gpt":0.3587207373482867,"score_spread":0.3371962705595844,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406018731","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9751866,0.004145666,0.0075889453,0.007307433,0.0004767834,0.00031699505,0.000023782799,0.000028622631,0.0049251844],"genre_scores_gemma":[0.9930282,0.0003235481,0.0031575344,0.002244415,0.00010747952,0.000013638747,0.000020023946,0.000022164591,0.0010829526],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99914885,0.00002761354,0.00018179588,0.0002508177,0.00018298041,0.00020793216],"domain_scores_gemma":[0.99936277,0.000039870778,0.000090683905,0.0002531489,0.00012176942,0.00013174186],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000118989105,0.00013155512,0.00030348724,0.00009394084,0.000052792144,0.000015151624,0.00011404776,0.00007983665,0.00013022646],"category_scores_gemma":[0.00005843985,0.00011566218,0.000076606404,0.00028467682,0.00005962206,0.000034315686,0.000026321803,0.00024704382,0.000002346315],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010086886,0.00006529776,0.10407743,0.0004966869,0.00009304492,0.000010143706,0.00036044628,0.003728278,0.8567796,0.00010931922,0.017575638,0.01660329],"study_design_scores_gemma":[0.0025959215,0.00012797076,0.6163376,0.0023714446,0.0006888289,0.000005571654,0.00043085948,0.097414084,0.18852778,0.00013027289,0.090927795,0.00044189388],"about_ca_topic_score_codex":0.0024562692,"about_ca_topic_score_gemma":0.000050444043,"teacher_disagreement_score":0.66825175,"about_ca_system_score_codex":0.00026220237,"about_ca_system_score_gemma":0.00034827483,"threshold_uncertainty_score":0.47165668},"labels":[],"label_agreement":null},{"id":"W4406035971","doi":"10.3934/mbe.2025005","title":"Computational physics and imaging in medicine","year":2025,"lang":"en","type":"article","venue":"Mathematical Biosciences & Engineering","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto; University Health Network","funders":"","keywords":"Medical physics; Medical imaging; Medicine; Computer science; Radiology","score_opus":0.007463828576908736,"score_gpt":0.28968269658714557,"score_spread":0.2822188680102368,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406035971","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32259238,0.0005559635,0.654522,0.0149976015,0.00019585191,0.00020269427,4.737485e-7,0.00011178825,0.006821218],"genre_scores_gemma":[0.97283614,0.000009949771,0.02648885,0.0005283748,0.000043991,0.0000048493557,0.0000013269419,0.000005433022,0.000081082006],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992677,0.000006875633,0.00019700165,0.00017080571,0.00018289319,0.00017473595],"domain_scores_gemma":[0.9996075,0.00020745206,0.000017604747,0.00007352257,0.000017560458,0.000076362354],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003534922,0.00008691805,0.00020549243,0.00014644061,0.000035280857,0.0000208738,0.000065009044,0.000018875087,0.000020059977],"category_scores_gemma":[0.0005404828,0.000065264125,0.000018563911,0.00036972866,0.00018340559,0.000055405373,0.00004240371,0.00016676243,0.0000027181657],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017109549,0.0002387222,0.08244991,0.0011595772,0.000033445118,0.00011545805,0.0015535197,0.01903968,0.023850864,0.78738374,0.0006560844,0.083501905],"study_design_scores_gemma":[0.0004567693,0.000016223044,0.01826039,0.000645409,0.000014913026,0.00003396504,0.0000780547,0.9606611,0.00009373558,0.019181129,0.0004890487,0.00006925003],"about_ca_topic_score_codex":0.0000067762367,"about_ca_topic_score_gemma":1.2896167e-7,"teacher_disagreement_score":0.9416214,"about_ca_system_score_codex":0.000026693026,"about_ca_system_score_gemma":0.000025973699,"threshold_uncertainty_score":0.26613936},"labels":[],"label_agreement":null},{"id":"W4406047229","doi":"10.15562/bmj.v13i3.5345","title":"Correlation of triple diagnostic (clinical, thyroid ultrasound, and FNAB) with histopathology in thyroid cancer patient","year":2024,"lang":"en","type":"article","venue":"Bali Medical Journal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Histopathology; Medicine; Thyroid cancer; Thyroid; Radiology; Ultrasound; Pathology; Internal medicine","score_opus":0.010003737829008465,"score_gpt":0.31907650572206486,"score_spread":0.3090727678930564,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406047229","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9667521,0.016777623,0.0066079837,0.007553883,0.0015510996,0.00018477885,0.0000040008704,0.000026641963,0.0005418993],"genre_scores_gemma":[0.9886533,0.008651835,0.00070689665,0.0013283599,0.00048095224,0.000010065154,0.0000074969003,0.000022625649,0.00013848614],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99793595,0.00020154471,0.0007283887,0.00023993733,0.00064689224,0.00024726382],"domain_scores_gemma":[0.9978671,0.0013492648,0.0001503015,0.0001106035,0.00007018259,0.00045254946],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014362711,0.00013120296,0.00043447726,0.0001760935,0.000052067546,0.000026884349,0.00008479289,0.0001592034,0.00044596646],"category_scores_gemma":[0.006262258,0.00008551829,0.00007801277,0.00021622592,0.00041987168,0.00007198052,0.000029051831,0.0015670989,0.000003933995],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035999194,0.0003848777,0.71058065,0.0002021798,0.00010006625,0.0049522948,0.0013280802,0.00010978854,0.0008011804,0.00030767694,0.019290688,0.2615825],"study_design_scores_gemma":[0.01100299,0.0048099337,0.8387193,0.007823119,0.0006684867,0.028720675,0.0006759792,0.048816543,0.00006608705,0.0011699133,0.057040684,0.00048628898],"about_ca_topic_score_codex":0.0000917393,"about_ca_topic_score_gemma":0.000026469288,"teacher_disagreement_score":0.2610962,"about_ca_system_score_codex":0.00009269581,"about_ca_system_score_gemma":0.0005636751,"threshold_uncertainty_score":0.7496961},"labels":[],"label_agreement":null},{"id":"W4406060080","doi":"10.1016/j.rcl.2024.11.005","title":"Artificial Intelligence in Gastrointestinal Imaging","year":2025,"lang":"en","type":"review","venue":"Radiologic Clinics of North America","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Michael's Hospital; Western University","funders":"","keywords":"Medicine; Medical imaging; Radiology","score_opus":0.04538925226682104,"score_gpt":0.39454797785989715,"score_spread":0.3491587255930761,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406060080","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00006380255,0.98604643,0.011688213,0.00027509243,0.00025366715,0.0006648182,0.00002912095,0.00006291322,0.00091591274],"genre_scores_gemma":[0.00018135137,0.98138744,0.017430406,0.00038492962,0.00023595826,0.000035678975,0.00023686483,0.000030847845,0.000076508724],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9963871,0.00027166915,0.0019645954,0.0006531623,0.0002418861,0.00048156708],"domain_scores_gemma":[0.9960702,0.0022130616,0.0008976061,0.0005557708,0.00008731184,0.0001760161],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006723333,0.00043655574,0.0030933467,0.00055666314,0.00004122883,0.00001290848,0.00046480252,0.00010926601,0.000059277176],"category_scores_gemma":[0.0066099647,0.00034282415,0.0007207762,0.0009639466,0.0005536364,0.000027654673,0.00016737553,0.0018308343,0.00002784546],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026136546,0.00015118661,0.0077552735,0.00615624,0.00003882288,0.0003154922,0.000010502387,0.00006154067,4.5034955e-8,0.00004321299,0.00020696185,0.98523456],"study_design_scores_gemma":[0.00021890402,0.0007688655,0.0014442301,0.07608809,0.0011933951,0.0014266653,0.00005454693,0.011669202,8.567279e-8,0.0007183553,0.9056797,0.00073794974],"about_ca_topic_score_codex":0.000040031275,"about_ca_topic_score_gemma":0.0000039185347,"teacher_disagreement_score":0.98449665,"about_ca_system_score_codex":0.00011995073,"about_ca_system_score_gemma":0.00087412883,"threshold_uncertainty_score":0.99990237},"labels":[],"label_agreement":null},{"id":"W4406087248","doi":"10.1158/2159-8290.cd-24-0760","title":"The Hallmarks of Predictive Oncology","year":2025,"lang":"en","type":"article","venue":"Cancer Discovery","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada); Vector Institute; Public Health Ontario; University Health Network; University of Toronto; Université de Montréal; Simon Fraser University; Princess Margaret Cancer Centre","funders":"Moonshot Research and Development Program; Argonne National Laboratory; Frederick National Laboratory for Cancer Research; National Cancer Institute; National Institutes of Health; National Institute of General Medical Sciences; Schmidt Family Foundation; American Cancer Society; Cancer Moonshot; U.S. Department of Energy","keywords":"Interpretability; Benchmarking; Generalizability theory; Computer science; Standardization; Relevance (law); Set (abstract data type); Precision medicine; Precision oncology; Personalized medicine; Data science; Medical physics; Artificial intelligence; Medicine; Psychology; Bioinformatics; Biology; Pathology","score_opus":0.007514707090446018,"score_gpt":0.335857931246317,"score_spread":0.328343224155871,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406087248","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.58966154,0.020947108,0.021672074,0.07013862,0.0036467356,0.00068002025,0.000024483741,0.0000662038,0.2931632],"genre_scores_gemma":[0.98599064,0.002035281,0.00010125066,0.0017641033,0.00015725556,0.00003954392,0.000003998133,0.000006962511,0.00990094],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9994504,0.000032695523,0.00016559807,0.000116054296,0.000105911975,0.00012934208],"domain_scores_gemma":[0.99946177,0.00022201955,0.00006248179,0.00016968406,0.000048100355,0.00003593407],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020670482,0.00005783775,0.0001822619,0.0000372645,0.000068937974,0.000012459859,0.00009199149,0.000043264165,0.00001999033],"category_scores_gemma":[0.00024832878,0.000034910125,0.00006829706,0.00011864515,0.00024724298,0.000045372308,0.000046079735,0.00024288392,9.123682e-7],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016551585,0.0002660646,0.18707938,0.0004274596,0.0010314913,0.000043638727,0.00070012454,0.0007408895,0.009438788,0.033466436,0.13608845,0.6290621],"study_design_scores_gemma":[0.003024526,0.00041013653,0.21640223,0.0009873275,0.00045207795,0.000016087239,0.0008206318,0.012454797,0.003760767,0.003615063,0.75791544,0.00014092708],"about_ca_topic_score_codex":0.00012893729,"about_ca_topic_score_gemma":0.000015613512,"teacher_disagreement_score":0.6289212,"about_ca_system_score_codex":0.00012314247,"about_ca_system_score_gemma":0.00051434006,"threshold_uncertainty_score":0.14235936},"labels":[],"label_agreement":null},{"id":"W4406152263","doi":"10.1038/s41591-024-03425-5","title":"The TRIPOD-LLM reporting guideline for studies using large language models","year":2025,"lang":"en","type":"review","venue":"Nature Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":355,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada); University of Alberta","funders":"National Institute on Minority Health and Health Disparities; National Center for Advancing Translational Sciences; U.S. National Library of Medicine; Department of Health and Social Care; National Cancer Institute; National Institutes of Health; National Science Foundation; Cancer Research UK; Engineering and Physical Sciences Research Council; National Institute for Health and Care Research; Radiological Society of North America; Fogarty International Center; National Heart, Lung, and Blood Institute; National Institute of Biomedical Imaging and Bioengineering; Gordon and Betty Moore Foundation","keywords":"Tripod (photography); Checklist; Guideline; Standardization; Computer science; Health care; Comparability; Delphi; Medicine; Psychology; Engineering; Political science","score_opus":0.07907597815907866,"score_gpt":0.5092562311739407,"score_spread":0.43018025301486207,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406152263","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000037731083,0.97793764,0.009191836,0.006553353,0.0027243188,0.0020666823,0.000029868159,0.00013313272,0.0013594117],"genre_scores_gemma":[0.000010148233,0.97819406,0.007612108,0.0036519212,0.0043844474,0.00012347485,0.0004588628,0.00010718247,0.005457785],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9938525,0.00018222467,0.0037610158,0.0007336306,0.0007536492,0.00071698753],"domain_scores_gemma":[0.9926697,0.002575503,0.0029708366,0.0009301843,0.0006443617,0.00020940906],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.008336406,0.0006543772,0.0039881887,0.00039211052,0.0005325318,0.000027813654,0.00040693796,0.00078116247,0.000016270953],"category_scores_gemma":[0.055267822,0.00032232777,0.00077652617,0.00072483736,0.0002600291,0.000048452395,0.00020060666,0.0034301607,0.0000012434208],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031913023,0.00004267563,0.0000014296716,0.028193768,0.0009585471,0.00021351327,0.00028069675,0.000008094994,0.0000043045743,0.0011198904,0.08593412,0.883211],"study_design_scores_gemma":[0.0013649145,0.000115271345,1.4210147e-7,0.05952769,0.004856208,0.00036805688,0.0005592989,0.008272637,0.0000011036473,0.00044602618,0.9242456,0.00024304206],"about_ca_topic_score_codex":0.00002199308,"about_ca_topic_score_gemma":0.000006573379,"teacher_disagreement_score":0.882968,"about_ca_system_score_codex":0.00031382256,"about_ca_system_score_gemma":0.0008175445,"threshold_uncertainty_score":0.9999229},"labels":[],"label_agreement":null},{"id":"W4406221583","doi":"10.18280/ts.410604","title":"DoubleSENeXt: Investigations on Enchondroma Detection","year":2024,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Enchondroma; Computer science; Medicine; Radiology; Chondrosarcoma","score_opus":0.016981826749104766,"score_gpt":0.2823547893230102,"score_spread":0.26537296257390547,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406221583","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9454878,0.00029494058,0.027871966,0.012120347,0.00075689505,0.00036561815,0.000004572278,0.00042330776,0.012674575],"genre_scores_gemma":[0.99604225,0.000015965426,0.00096148293,0.0013956969,0.00058134465,0.000029214103,0.000025047955,0.000022532604,0.00092646887],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990937,0.000027753375,0.00018568429,0.00022815882,0.00029461138,0.00017008599],"domain_scores_gemma":[0.99961513,0.00007556245,0.000019744915,0.00010317991,0.00002182276,0.00016458216],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023277335,0.00010880119,0.00011969181,0.00016918368,0.00009093828,0.00007070764,0.000046811783,0.000043401287,0.0006825328],"category_scores_gemma":[0.000048983806,0.00008796365,0.00007987557,0.0002100405,0.00006456994,0.000066929155,0.000010736268,0.00034076304,0.00017691188],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001794585,0.000399989,0.0026759128,0.000535946,0.00036470641,0.0007084098,0.0015573027,0.0016332984,0.4311287,0.023098934,0.021867592,0.51584977],"study_design_scores_gemma":[0.0030965633,0.0017037912,0.02061943,0.0014061417,0.00040344495,0.00065355364,0.00015616501,0.5137814,0.04471451,0.0040627085,0.40888545,0.0005168238],"about_ca_topic_score_codex":0.000023839406,"about_ca_topic_score_gemma":0.000002649213,"teacher_disagreement_score":0.51533294,"about_ca_system_score_codex":0.000078726785,"about_ca_system_score_gemma":0.000064005166,"threshold_uncertainty_score":0.74732554},"labels":[],"label_agreement":null},{"id":"W4406264582","doi":"10.1109/euvip61797.2024.10772785","title":"Thyroidiomics: An Automated Pipeline for Segmentation and Classification of Thyroid Pathologies from Scintigraphy Images","year":2024,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; BC Cancer Foundation","keywords":"Computer science; Segmentation; Pipeline (software); Artificial intelligence; Image segmentation; Scintigraphy; Computer vision; Pattern recognition (psychology); Radiology; Medicine","score_opus":0.01872848475131374,"score_gpt":0.3413704217057034,"score_spread":0.3226419369543897,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406264582","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87552327,0.0021996866,0.11714735,0.0034002007,0.00018042413,0.0003709275,0.00005051499,0.0006415462,0.00048606994],"genre_scores_gemma":[0.9400167,0.00037729854,0.058800053,0.00022130516,0.00011498457,0.000021179845,0.00028900948,0.00001954948,0.00013995968],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992257,0.000031352458,0.0002509762,0.0002650264,0.00011777953,0.00010921441],"domain_scores_gemma":[0.9994881,0.0001677364,0.00005303375,0.0001453618,0.00007895693,0.00006677001],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003290334,0.00009744459,0.00019149562,0.00016606557,0.000041214567,0.000058132795,0.000047175392,0.000056981753,0.000017307802],"category_scores_gemma":[0.00018915588,0.000072697556,0.000054913417,0.00013243126,0.0001283416,0.00015958337,0.000015204543,0.00011276024,0.000002230798],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006763203,0.00005251801,0.0048894007,0.00015206149,0.00004483106,0.0000058165915,0.0004009089,0.0000139813255,0.9090831,0.0007604702,0.009514288,0.075014964],"study_design_scores_gemma":[0.0010372472,0.00027805648,0.06856334,0.00013380795,0.00017472095,0.000019837897,0.0008700169,0.89183193,0.034384646,0.0018534969,0.0007368859,0.000116004754],"about_ca_topic_score_codex":0.00006599969,"about_ca_topic_score_gemma":0.000002854568,"teacher_disagreement_score":0.891818,"about_ca_system_score_codex":0.000014757482,"about_ca_system_score_gemma":0.00003521805,"threshold_uncertainty_score":0.29645205},"labels":[],"label_agreement":null},{"id":"W4406354429","doi":"10.5194/gmd-2024-116-rc2","title":"Comment on gmd-2024-116","year":2025,"lang":"en","type":"peer-review","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Calgary; Université Laval","funders":"","keywords":"Mathematics","score_opus":0.02232085540829062,"score_gpt":0.3637260897442552,"score_spread":0.3414052343359646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406354429","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[7.012071e-7,0.01190987,0.00035416495,0.57597667,0.003247657,0.0004432723,0.000021251692,0.00008106204,0.40796533],"genre_scores_gemma":[0.0000056769286,0.011840029,0.00085278536,0.4008454,0.0005573519,0.000028924107,0.0006165398,0.000026031908,0.58522725],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979848,0.00007693503,0.0004649533,0.00048404883,0.0006601604,0.0003290464],"domain_scores_gemma":[0.99855834,0.00025154205,0.00012325215,0.0007046309,0.0001175893,0.00024462832],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00062783144,0.00035554604,0.0010389662,0.00020654916,0.00006757057,0.000025605563,0.00023856429,0.00021819644,0.0062712915],"category_scores_gemma":[0.0009916915,0.0002509488,0.00033137968,0.00020213977,0.00006270083,0.000010847563,0.00013283576,0.0018771682,0.0003382534],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011147511,0.00010493227,0.000021536465,0.005349132,0.00014520666,0.000075096636,0.0000047446356,8.1376066e-7,8.5675026e-7,0.0010684746,0.9248956,0.06832245],"study_design_scores_gemma":[0.00061831105,0.00014698232,0.000014572451,0.023838436,0.0005226822,0.000024663346,0.0000055863798,0.0003713611,0.0000054035927,0.00007581922,0.9741695,0.00020671554],"about_ca_topic_score_codex":0.00019813914,"about_ca_topic_score_gemma":0.0000029422365,"teacher_disagreement_score":0.17726192,"about_ca_system_score_codex":0.00017637442,"about_ca_system_score_gemma":0.00031556503,"threshold_uncertainty_score":0.9999943},"labels":[],"label_agreement":null},{"id":"W4406390612","doi":"10.1016/s1541-9800(05)70234-9","title":"10.1016/s1541-9800(05)70234-9","year":2000,"lang":"en","type":"article","venue":"Time to knit","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medical physics; Medicine; Psychology; Computer science; Nuclear medicine","score_opus":0.004885729791606959,"score_gpt":0.2152971596112557,"score_spread":0.21041142981964875,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406390612","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029155647,0.0000958526,0.000009737218,0.0035517127,0.0000040720497,0.00019577469,0.000003006396,0.00021038976,0.9930139],"genre_scores_gemma":[0.00045626034,0.0000012084682,0.0008571503,0.0007210696,0.00040151764,0.000011602278,0.000025965554,0.000041196265,0.997484],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99889463,0.00003358282,0.0002065511,0.0002612357,0.00027406696,0.00032993068],"domain_scores_gemma":[0.9991926,0.00005619617,0.000026192398,0.00031467632,0.000037715738,0.00037262842],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0002575455,0.00014729792,0.00026616652,0.00009244253,0.00007378496,0.000029699018,0.00013889998,0.000065435685,0.99597687],"category_scores_gemma":[0.00019129981,0.00012755784,0.00008592826,0.00019731271,0.00005826655,0.00004682593,0.000031486932,0.00033800013,0.9861787],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007448493,0.00004805204,0.0000023695877,0.000011248633,0.000020900712,0.000044396707,0.000018074159,0.000038160615,0.00013853655,7.252345e-7,0.38563386,0.6139692],"study_design_scores_gemma":[0.000715443,0.00022469701,0.0002539101,0.000069122776,0.000050597846,0.00015079918,0.0000011018253,0.0032115348,0.000032605352,0.000008685483,0.9951365,0.00014500893],"about_ca_topic_score_codex":0.000037021124,"about_ca_topic_score_gemma":5.0776144e-8,"teacher_disagreement_score":0.6138242,"about_ca_system_score_codex":0.000047027002,"about_ca_system_score_gemma":0.000048381797,"threshold_uncertainty_score":0.5201658},"labels":[],"label_agreement":null},{"id":"W4406390929","doi":"10.1016/s1879-8497(16)69713-3","title":"10.1016/s1879-8497(16)69713-3","year":2000,"lang":"en","type":"article","venue":"Time to knit","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"DICOM; Nuclear medicine; Computer science; Medicine; Artificial intelligence","score_opus":0.004569581472322967,"score_gpt":0.2132867000200121,"score_spread":0.20871711854768912,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406390929","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00208184,0.00011942598,0.000011598997,0.004142995,0.00000350764,0.00019683441,0.0000028236416,0.00017708272,0.9932639],"genre_scores_gemma":[0.0006738079,0.0000011159319,0.00052928185,0.00070869474,0.0004021594,0.000011681865,0.000029061313,0.000041270723,0.99760294],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988907,0.000034367666,0.00020881474,0.00026212545,0.0002743241,0.0003296441],"domain_scores_gemma":[0.9991838,0.00005675601,0.000026799096,0.00031806776,0.000038639202,0.00037598223],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0002466468,0.00014913913,0.0002693672,0.00009289948,0.00007653084,0.000030702253,0.00013822,0.000066095745,0.9963023],"category_scores_gemma":[0.00019324546,0.00012937284,0.00008815681,0.00019558998,0.000058587324,0.000046546684,0.000031175237,0.0003362876,0.9853105],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007452188,0.00004578435,0.0000016943908,0.000010882275,0.000019983147,0.000026883235,0.000013708491,0.000019716585,0.0000995692,0.0000010394566,0.42267916,0.57700706],"study_design_scores_gemma":[0.00070411916,0.00020576619,0.0001686939,0.00007457011,0.0000522457,0.00010483232,9.810551e-7,0.002190973,0.0000487054,0.000008827582,0.99629307,0.00014720616],"about_ca_topic_score_codex":0.0000454434,"about_ca_topic_score_gemma":5.478906e-8,"teacher_disagreement_score":0.57685983,"about_ca_system_score_codex":0.00006371424,"about_ca_system_score_gemma":0.0000475,"threshold_uncertainty_score":0.52756715},"labels":[],"label_agreement":null},{"id":"W4406412026","doi":"10.59275/j.melba.2024-24gc","title":"Finding Reproducible and Prognostic Radiomic Features in Variable Slice Thickness Contrast Enhanced CT of Colorectal Liver Metastases","year":2025,"lang":"en","type":"article","venue":"The Journal of Machine Learning for Biomedical Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"National Cancer Institute; National Institutes of Health","keywords":"Reproducibility; Medicine; Radiology; Thresholding; Feature (linguistics); Artificial intelligence; Nuclear medicine; Computer science; Mathematics; Statistics; Image (mathematics)","score_opus":0.007204905557761505,"score_gpt":0.28794906708576895,"score_spread":0.28074416152800746,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406412026","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9152972,0.010212732,0.06582785,0.007239146,0.00044600313,0.0005955911,0.000008305343,0.000032773023,0.00034038143],"genre_scores_gemma":[0.98785454,0.00042571555,0.0108352285,0.00044663963,0.00014013177,0.000007770461,0.000017855575,0.000028218483,0.00024392465],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977161,0.00039236477,0.00081684615,0.00027131508,0.0004186754,0.0003846513],"domain_scores_gemma":[0.9965355,0.0023625721,0.0005507876,0.00018553965,0.00020858871,0.00015703718],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005757206,0.00021857493,0.0007774492,0.0005731766,0.00022424839,0.000032899643,0.00026634822,0.0000519127,0.00003050342],"category_scores_gemma":[0.0090590315,0.00014308156,0.00013635056,0.0006357897,0.0005871045,0.00013066441,0.00011486873,0.0014753548,3.9040307e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0067049195,0.0012982503,0.23734994,0.0036471717,0.0015637759,0.0006882088,0.0048027486,0.0036139677,0.57322747,0.0019003291,0.0042925533,0.16091067],"study_design_scores_gemma":[0.042107247,0.003320006,0.2565179,0.014677446,0.0057684868,0.023694847,0.0031832492,0.5692147,0.04923361,0.0029009671,0.028122343,0.001259215],"about_ca_topic_score_codex":0.00026085967,"about_ca_topic_score_gemma":0.0000033747203,"teacher_disagreement_score":0.56560075,"about_ca_system_score_codex":0.00007624274,"about_ca_system_score_gemma":0.0003091069,"threshold_uncertainty_score":0.9992881},"labels":[],"label_agreement":null},{"id":"W4406465146","doi":"10.1016/s0029-7437(07)70258-6","title":"10.1016/s0029-7437(07)70258-6","year":2000,"lang":"en","type":"article","venue":"Time to knit","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine; Psychology","score_opus":0.0053889608385547585,"score_gpt":0.22126212722278876,"score_spread":0.215873166384234,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406465146","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021838872,0.00010490145,0.000012883275,0.003869494,7.2721207e-7,0.00019607384,0.0000029143102,0.00019919753,0.9934299],"genre_scores_gemma":[0.00039808816,0.0000011209838,0.0010007501,0.00060676783,0.00041733234,0.000011414252,0.000023573799,0.00003966332,0.9975013],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988982,0.00003287673,0.0002095409,0.00026147623,0.00027363573,0.0003242521],"domain_scores_gemma":[0.99918795,0.00005824901,0.000026107078,0.00031981268,0.000038945942,0.00036893354],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0002447046,0.00014678568,0.00026766452,0.00008797061,0.000075468386,0.000030163137,0.00014022204,0.000065574124,0.9979319],"category_scores_gemma":[0.00019960543,0.00012755812,0.00008659182,0.00017602133,0.00005698264,0.00004702523,0.000031376596,0.00033982098,0.9931733],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000072095114,0.00004671724,0.0000014475023,0.000010525342,0.000020174477,0.000028784474,0.0000156059,0.000035375717,0.000104448925,9.200306e-7,0.59935635,0.40030754],"study_design_scores_gemma":[0.0006898905,0.0002034841,0.00020403098,0.00007273639,0.000050342333,0.00010360231,0.0000010471805,0.0037310885,0.00004103507,0.00000902125,0.9947495,0.00014424404],"about_ca_topic_score_codex":0.000029462208,"about_ca_topic_score_gemma":2.976938e-8,"teacher_disagreement_score":0.4001633,"about_ca_system_score_codex":0.000043445736,"about_ca_system_score_gemma":0.000046210756,"threshold_uncertainty_score":0.5201669},"labels":[],"label_agreement":null},{"id":"W4406476022","doi":"10.1016/s0967-0653(97)89070-9","title":"10.1016/s0967-0653(97)89070-9","year":2000,"lang":"en","type":"article","venue":"Time to knit","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Tomography; Geology; Radiology; Medicine","score_opus":0.0062472535999024996,"score_gpt":0.21600906754559165,"score_spread":0.20976181394568916,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406476022","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00056946836,0.00012639818,0.000009743042,0.0038887155,0.0000033175475,0.0001889049,0.0000026076123,0.00017253088,0.99503833],"genre_scores_gemma":[0.000116046,0.0000011348174,0.00084029563,0.0006153059,0.00041184828,0.000011593316,0.000025564555,0.000039453473,0.99793875],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989094,0.00003436132,0.00020543071,0.00025763543,0.00027098358,0.000322152],"domain_scores_gemma":[0.999202,0.000053856773,0.000026020272,0.00030933248,0.00003866646,0.00037009077],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00024451115,0.00014639006,0.00026227796,0.00008713253,0.00007539568,0.000030479467,0.00013836549,0.00006564703,0.99831027],"category_scores_gemma":[0.00019347933,0.00012615182,0.00008475005,0.00019470473,0.00005831072,0.000048236594,0.00003036335,0.00034261416,0.99884486],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009528805,0.000052983272,5.883353e-7,0.0000132744835,0.000023653945,0.000044794604,0.000022442719,0.000043983462,0.000032585383,0.0000011424047,0.14042714,0.85924214],"study_design_scores_gemma":[0.0007402604,0.00020243043,0.000029758043,0.00007026466,0.00005141947,0.00009321296,0.0000014173055,0.0031415601,0.0000433604,0.000008102293,0.9954738,0.00014443255],"about_ca_topic_score_codex":0.00003260156,"about_ca_topic_score_gemma":3.7901636e-8,"teacher_disagreement_score":0.85909766,"about_ca_system_score_codex":0.000042080428,"about_ca_system_score_gemma":0.00004516319,"threshold_uncertainty_score":0.5144322},"labels":[],"label_agreement":null},{"id":"W4406486749","doi":"10.1016/s0024-7804(97)83191-0","title":"10.1016/s0024-7804(97)83191-0","year":2000,"lang":"en","type":"article","venue":"Time to knit","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine","score_opus":0.005415572829933302,"score_gpt":0.2136889677754007,"score_spread":0.2082733949454674,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406486749","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013548889,0.00013116217,0.00001001462,0.0044288477,0.000002943041,0.0001957918,0.000002682456,0.00017575832,0.9936979],"genre_scores_gemma":[0.0003728858,0.0000011190317,0.00087100524,0.00067861145,0.00041217203,0.0000115437715,0.000023751796,0.00004053201,0.9975884],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989037,0.0000333818,0.00020628962,0.00026067955,0.00027221852,0.00032373992],"domain_scores_gemma":[0.999198,0.000054945664,0.000025674548,0.00031329543,0.00003803869,0.00037003812],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00024356564,0.00014740071,0.00026465647,0.000091925394,0.00007407975,0.000030209187,0.00013669049,0.00006561409,0.9969846],"category_scores_gemma":[0.00019005926,0.0001274258,0.000086399625,0.00019393592,0.000057354868,0.000046176745,0.00003094244,0.00034388786,0.99251246],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008303038,0.000051739244,0.0000021867484,0.000012931965,0.000023730161,0.00003868079,0.000017119137,0.000036802016,0.00010822497,0.0000016379731,0.28402928,0.71559465],"study_design_scores_gemma":[0.00069187407,0.0002061542,0.00014686237,0.00007296043,0.00005299168,0.000093732786,0.0000010166154,0.004420861,0.000036561072,0.0000100128,0.99412215,0.00014484357],"about_ca_topic_score_codex":0.0000358748,"about_ca_topic_score_gemma":3.3699553e-8,"teacher_disagreement_score":0.7154498,"about_ca_system_score_codex":0.00004196524,"about_ca_system_score_gemma":0.00004360697,"threshold_uncertainty_score":0.5196273},"labels":[],"label_agreement":null},{"id":"W4406493065","doi":"10.1136/bmjpo-2025-gosh.96","title":"178 Increasing diagnostic yield from short-read WGS data","year":2025,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hospital for Sick Children","funders":"National Institute for Health and Care Research","keywords":"Yield (engineering); Computer science; Materials science","score_opus":0.034086834700737347,"score_gpt":0.3405434596966526,"score_spread":0.30645662499591525,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406493065","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.79144806,0.0016820338,0.046162777,0.025378719,0.000863172,0.0003570585,0.000030850682,0.00031042105,0.13376692],"genre_scores_gemma":[0.97832394,0.00019466123,0.010313133,0.0076402854,0.00033698036,0.000005243216,0.0003564936,0.000018033514,0.0028112128],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9988772,0.00004482116,0.00024882623,0.00039409252,0.00020656548,0.0002284449],"domain_scores_gemma":[0.99657583,0.002346859,0.000023792472,0.00086662953,0.000032701606,0.00015418124],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00045305802,0.000128251,0.00027790756,0.00009524937,0.000082160645,0.000049576858,0.00031581163,0.00007589183,0.00090034725],"category_scores_gemma":[0.01092343,0.00010204656,0.000041804862,0.00015123263,0.0000778638,0.00009275707,0.00032192326,0.0004429358,0.000049522187],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000106833206,0.00021932046,0.47902074,0.00008842872,0.00028951574,0.00029415102,0.00010137034,0.000010322733,0.005914664,0.002034013,0.114120476,0.39780015],"study_design_scores_gemma":[0.0022854107,0.00011891537,0.5696852,0.0027416733,0.0010896121,0.000110095854,0.00033398828,0.12777247,0.0013150057,0.0029514204,0.29104558,0.00055059546],"about_ca_topic_score_codex":0.0042995717,"about_ca_topic_score_gemma":0.00004782346,"teacher_disagreement_score":0.39724958,"about_ca_system_score_codex":0.00003281912,"about_ca_system_score_gemma":0.000113841335,"threshold_uncertainty_score":0.997408},"labels":[],"label_agreement":null},{"id":"W4406496047","doi":"10.1016/s0029-7437(07)70272-0","title":"10.1016/s0029-7437(07)70272-0","year":2000,"lang":"en","type":"article","venue":"Time to knit","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mammography; Medicine; Radiology; Medical physics; Breast cancer; Internal medicine; Cancer","score_opus":0.005456691512800478,"score_gpt":0.2210989787005794,"score_spread":0.21564228718777892,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406496047","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001956193,0.000107112144,0.000011896642,0.004776803,6.97646e-7,0.00019584583,0.0000028731931,0.00020635204,0.99274224],"genre_scores_gemma":[0.00044003178,0.0000011132088,0.0009878626,0.000608778,0.00040670688,0.000011250866,0.000023846129,0.00004072974,0.9974797],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989005,0.000032989115,0.00020764368,0.00026110967,0.0002710311,0.00032674125],"domain_scores_gemma":[0.9991917,0.000054839446,0.000026363114,0.00031668827,0.000037780766,0.00037264833],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00024349826,0.00014765095,0.00026688993,0.000086326996,0.000075258395,0.000029936811,0.00013926688,0.000065421315,0.9978281],"category_scores_gemma":[0.00018986386,0.00012807529,0.0000863319,0.0001738083,0.00005725118,0.00004726443,0.000031244486,0.00034129925,0.99306494],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007354479,0.000048590864,0.000001469054,0.000011441292,0.000021213393,0.000030353829,0.000016922586,0.000037213795,0.000115001836,9.263516e-7,0.6228689,0.37677443],"study_design_scores_gemma":[0.0006928033,0.00020882109,0.00018185073,0.000071941795,0.000051828454,0.0001075098,0.0000010681334,0.0038510864,0.00004292959,0.00000847882,0.99463594,0.00014572257],"about_ca_topic_score_codex":0.00002974646,"about_ca_topic_score_gemma":2.8986854e-8,"teacher_disagreement_score":0.37662873,"about_ca_system_score_codex":0.000042835967,"about_ca_system_score_gemma":0.00004649819,"threshold_uncertainty_score":0.52227587},"labels":[],"label_agreement":null},{"id":"W4406497767","doi":"10.3390/cancers17020285","title":"Enhanced Lung Cancer Survival Prediction Using Semi-Supervised Pseudo-Labeling and Learning from Diverse PET/CT Datasets","year":2025,"lang":"en","type":"article","venue":"Cancers","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Lung cancer; Artificial intelligence; Computer science; Machine learning; Medicine; Oncology","score_opus":0.0194462013172064,"score_gpt":0.32120198205913286,"score_spread":0.30175578074192644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406497767","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98675674,0.0022431267,0.00829405,0.0003985823,0.0013236621,0.00024348451,0.00011718041,0.00011280582,0.00051039195],"genre_scores_gemma":[0.99453455,0.0014468648,0.0021024314,0.0007965937,0.0003574821,0.000019682535,0.00035983042,0.000030338279,0.0003522188],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986127,0.000096884134,0.0002594522,0.00046462897,0.00025160113,0.00031472786],"domain_scores_gemma":[0.9993131,0.0001449428,0.00008933889,0.00021394447,0.000059074056,0.00017957385],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029931977,0.00019288494,0.00035313395,0.00012568492,0.0003305024,0.00005159852,0.000096827964,0.000025134696,0.00018381471],"category_scores_gemma":[0.00035229223,0.00018949737,0.000054477023,0.00025200404,0.00012249293,0.00014588784,0.00010007717,0.0007341328,0.0000015238761],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00056371227,0.000054970216,0.41132438,0.0010629923,0.0014760591,0.0005890557,0.0018535333,0.1324845,0.36022514,0.00008928831,0.008561402,0.08171497],"study_design_scores_gemma":[0.0029620626,0.00003183082,0.0057780393,0.001314152,0.00059413334,0.000026116237,0.000994878,0.98323685,0.0018166121,0.000016047023,0.0030204756,0.00020880118],"about_ca_topic_score_codex":0.0074470234,"about_ca_topic_score_gemma":0.000063935164,"teacher_disagreement_score":0.85075235,"about_ca_system_score_codex":0.00089429127,"about_ca_system_score_gemma":0.00054561807,"threshold_uncertainty_score":0.9991625},"labels":[],"label_agreement":null},{"id":"W4406500434","doi":"10.1016/s0029-7437(06)72188-7","title":"10.1016/s0029-7437(06)72188-7","year":2000,"lang":"en","type":"article","venue":"Time to knit","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine; Gynecology; Computer science; Obstetrics","score_opus":0.0053905556451466176,"score_gpt":0.22051174700986934,"score_spread":0.2151211913647227,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406500434","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003629488,0.00010181699,0.00001188904,0.0043865764,3.369202e-7,0.00019723138,0.0000029080497,0.00020648063,0.99146324],"genre_scores_gemma":[0.000466535,0.0000010223728,0.00092703506,0.0006373454,0.00044421852,0.000011492595,0.000031059946,0.000040718034,0.9974406],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99890417,0.000034803317,0.00020642312,0.0002607218,0.000269308,0.00032457663],"domain_scores_gemma":[0.99919426,0.000058647114,0.00002504959,0.00031455298,0.000036649453,0.00037081706],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0002575872,0.00014714358,0.00026443298,0.00008822928,0.000077655604,0.000030250587,0.00013590256,0.000065320935,0.9963787],"category_scores_gemma":[0.00020081716,0.00012774704,0.00008348496,0.00018767174,0.00005653316,0.000044890632,0.00003086363,0.00034151686,0.99055374],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000059711616,0.000048287144,0.0000018396989,0.000011183693,0.000021090338,0.000026919646,0.000024001782,0.000039319362,0.00014951447,7.756794e-7,0.6773135,0.32230383],"study_design_scores_gemma":[0.0008402662,0.00019192765,0.00017399045,0.000068072615,0.00003991669,0.000111929556,0.0000010549904,0.00450446,0.0000415764,0.00000805557,0.9938736,0.00014514811],"about_ca_topic_score_codex":0.00002745013,"about_ca_topic_score_gemma":3.4276834e-8,"teacher_disagreement_score":0.3221587,"about_ca_system_score_codex":0.000042504947,"about_ca_system_score_gemma":0.000044632267,"threshold_uncertainty_score":0.5209373},"labels":[],"label_agreement":null},{"id":"W4406506544","doi":"10.1016/j.yort.2014.12.019","title":"10.1016/j.yort.2014.12.019","year":2000,"lang":"en","type":"article","venue":"Time to knit","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine; Propensity score matching; Osteosarcoma; Matching (statistics); Oncology; Surgery; Internal medicine; Pathology","score_opus":0.004642020398262207,"score_gpt":0.2117918470468495,"score_spread":0.2071498266485873,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406506544","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025991353,0.00009531956,0.0000099204435,0.003893057,0.000003543027,0.00018863885,0.0000023796215,0.00016334932,0.9930447],"genre_scores_gemma":[0.00047716137,0.0000014274034,0.0006999596,0.00064147776,0.00037835367,0.000009195348,0.000026084934,0.00003778706,0.9977285],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989748,0.000029828652,0.00019377227,0.00024611404,0.00025501128,0.00030048267],"domain_scores_gemma":[0.99924606,0.000049043378,0.000025578374,0.00030939732,0.000029325147,0.00034059855],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0002355756,0.00013538677,0.00025085307,0.000083157065,0.00006448376,0.000026322725,0.00012581695,0.000060268725,0.99569637],"category_scores_gemma":[0.00013998189,0.000116420495,0.00008056484,0.00011100804,0.000050922994,0.000042313208,0.00002764935,0.00030579197,0.9871177],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000680335,0.000040845403,0.0000047877747,0.0000102363565,0.000019680823,0.00003139887,0.000015029021,0.000036446112,0.00011242466,8.2950635e-7,0.4280077,0.5716526],"study_design_scores_gemma":[0.0006227876,0.00018495542,0.00039890606,0.000057179015,0.000048904294,0.000091399044,8.423019e-7,0.0030954925,0.00003603399,0.0000062844033,0.9953236,0.00013362188],"about_ca_topic_score_codex":0.000038109418,"about_ca_topic_score_gemma":4.3893053e-8,"teacher_disagreement_score":0.57151896,"about_ca_system_score_codex":0.000028513397,"about_ca_system_score_gemma":0.000050223236,"threshold_uncertainty_score":0.474749},"labels":[],"label_agreement":null},{"id":"W4406520914","doi":"10.1016/s0029-7437(05)70746-1","title":"10.1016/s0029-7437(05)70746-1","year":2000,"lang":"en","type":"article","venue":"Time to knit","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mammography; Medicine; Radiology; Medical physics; Breast cancer; Internal medicine; Cancer","score_opus":0.005467664626954318,"score_gpt":0.22084746769543742,"score_spread":0.21537980306848312,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406520914","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020181548,0.0000963389,0.000012239469,0.0048047756,8.448934e-7,0.00019644552,0.0000029504592,0.00020696971,0.9926613],"genre_scores_gemma":[0.00037295575,0.0000010804862,0.0010309123,0.0007432177,0.00041125255,0.000011526214,0.00002498101,0.000040645526,0.99736345],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99889505,0.00003385418,0.00020972363,0.000261406,0.0002693826,0.00033056166],"domain_scores_gemma":[0.9991835,0.000056671328,0.000026701624,0.00031747954,0.000037821996,0.00037782738],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00025260003,0.0001481444,0.00027076047,0.000089974,0.00007550443,0.000029450777,0.00013843775,0.00006529592,0.9966063],"category_scores_gemma":[0.00019698254,0.0001280907,0.00008716356,0.00019429323,0.000057319627,0.000047218164,0.000031011514,0.00033906882,0.9862773],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006760428,0.00004566343,0.0000011132961,0.000010585403,0.00001955986,0.000032895565,0.000016978112,0.00003654294,0.00011749,7.9245916e-7,0.6231451,0.37650567],"study_design_scores_gemma":[0.00070074847,0.00023144849,0.00014815619,0.00007217926,0.000052159656,0.00012899659,0.000001159645,0.0039362,0.000045643927,0.0000087604785,0.9945294,0.00014513973],"about_ca_topic_score_codex":0.0000348891,"about_ca_topic_score_gemma":3.6081502e-8,"teacher_disagreement_score":0.37636054,"about_ca_system_score_codex":0.00004377644,"about_ca_system_score_gemma":0.000045701614,"threshold_uncertainty_score":0.5223387},"labels":[],"label_agreement":null},{"id":"W4406547900","doi":"10.1016/s1541-9800(05)70203-9","title":"10.1016/s1541-9800(05)70203-9","year":2000,"lang":"en","type":"article","venue":"Time to knit","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine; Radiology; Computer science; Nuclear medicine; Psychology","score_opus":0.004906078952613213,"score_gpt":0.21492905006533236,"score_spread":0.21002297111271914,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406547900","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022886656,0.0001022525,0.0000102207405,0.0052030394,0.0000040034247,0.00019767735,0.0000030049923,0.0001783149,0.9920128],"genre_scores_gemma":[0.00048165658,0.0000010987163,0.0009201084,0.0008085361,0.0004153465,0.000011512209,0.000026561887,0.00004032825,0.99729484],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988969,0.00003346468,0.00020712003,0.00026121153,0.00027312434,0.00032820215],"domain_scores_gemma":[0.9991889,0.00005365971,0.000026341988,0.00031387174,0.000037385038,0.00037986183],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000239328,0.00014779899,0.00026822463,0.0000894439,0.00007508979,0.000029821904,0.00013892772,0.00006508241,0.996175],"category_scores_gemma":[0.00019085337,0.0001279219,0.0000863063,0.00019642574,0.000057658865,0.000046726353,0.0000312259,0.00033902065,0.98508024],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007624432,0.000048359034,0.0000011205749,0.000011703371,0.000020565873,0.000047846617,0.000017997736,0.00003592916,0.00014697605,9.1068586e-7,0.42930987,0.57028246],"study_design_scores_gemma":[0.0007418088,0.00023372618,0.00015975749,0.0000726044,0.00005171931,0.00013079775,0.0000011202975,0.0037864638,0.00005183629,0.000009466686,0.9946155,0.00014519478],"about_ca_topic_score_codex":0.000032632746,"about_ca_topic_score_gemma":3.4161125e-8,"teacher_disagreement_score":0.57013726,"about_ca_system_score_codex":0.000044366014,"about_ca_system_score_gemma":0.000047348814,"threshold_uncertainty_score":0.5216504},"labels":[],"label_agreement":null},{"id":"W4406565515","doi":"10.1016/j.endend.2011.08.053","title":"10.1016/j.endend.2011.08.053","year":2000,"lang":"en","type":"article","venue":"Time to knit","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Test (biology); Geology; Paleontology","score_opus":0.005255698778690829,"score_gpt":0.21518436835658603,"score_spread":0.2099286695778952,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406565515","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021473472,0.00011649015,0.000012381389,0.0041813734,0.000003838669,0.0001748395,0.0000031814275,0.00016632439,0.9931942],"genre_scores_gemma":[0.00058473606,0.000001186959,0.00076841546,0.0005533155,0.00040132308,0.000010264347,0.000023284943,0.00003831203,0.99761915],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989305,0.00003225164,0.00019570343,0.0002547829,0.0002720819,0.00031466578],"domain_scores_gemma":[0.9992203,0.000049942944,0.000024498526,0.00030969817,0.00003575583,0.0003597851],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00023374331,0.0001408109,0.00025072604,0.00009123068,0.00006997736,0.000025835732,0.0001356866,0.00006351482,0.9980555],"category_scores_gemma":[0.000119868644,0.00012188957,0.00008116179,0.00011487381,0.000053386197,0.00005943122,0.000030621693,0.00033053366,0.9932954],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000084775034,0.000052558647,0.0000017627084,0.000012165422,0.000025277543,0.00005471642,0.000018775829,0.000031366726,0.00015609091,0.0000014989026,0.31717974,0.6823813],"study_design_scores_gemma":[0.000701004,0.00018784542,0.00017758393,0.000048627517,0.000050172093,0.00014653582,0.0000010786629,0.0024189544,0.000046096156,0.000010659617,0.9960731,0.00013834234],"about_ca_topic_score_codex":0.000028507553,"about_ca_topic_score_gemma":3.501521e-8,"teacher_disagreement_score":0.68224293,"about_ca_system_score_codex":0.000040566374,"about_ca_system_score_gemma":0.000046008605,"threshold_uncertainty_score":0.49705124},"labels":[],"label_agreement":null},{"id":"W4406575910","doi":"10.1016/s1553-3212(12)70192-9","title":"10.1016/s1553-3212(12)70192-9","year":2000,"lang":"en","type":"article","venue":"Time to knit","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science","score_opus":0.004918139851119911,"score_gpt":0.21142823277960016,"score_spread":0.20651009292848024,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406575910","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023130085,0.0000876669,0.000010677697,0.004182946,0.0000035737978,0.00019872593,0.000002799944,0.00017519335,0.9930254],"genre_scores_gemma":[0.00047839232,0.0000011037431,0.00073379796,0.00067993184,0.00040661206,0.000011018203,0.000025828456,0.000039898594,0.99762344],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989003,0.000033399876,0.00020714536,0.0002586945,0.0002739297,0.0003265336],"domain_scores_gemma":[0.99919814,0.000054451928,0.000026640684,0.00031690416,0.000033070133,0.00037080355],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0002436315,0.0001472579,0.00026693637,0.00009155385,0.0000746367,0.000029967074,0.00013839854,0.00006476391,0.9958638],"category_scores_gemma":[0.0001905039,0.00012761232,0.00008635243,0.00015571156,0.000056790865,0.000048563124,0.00003117321,0.00034061237,0.9835428],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000089035566,0.00004910135,0.0000017591051,0.0000124386415,0.000022849741,0.00003977361,0.000021103324,0.00004514673,0.0001280275,8.781715e-7,0.4005085,0.5990814],"study_design_scores_gemma":[0.0006977045,0.00021682928,0.00023148209,0.00006998962,0.00005100124,0.00010038459,0.0000010964548,0.003636843,0.000045036384,0.000007890329,0.9947963,0.0001454382],"about_ca_topic_score_codex":0.000035462148,"about_ca_topic_score_gemma":5.3768268e-8,"teacher_disagreement_score":0.59893596,"about_ca_system_score_codex":0.000043325042,"about_ca_system_score_gemma":0.00004674361,"threshold_uncertainty_score":0.52038795},"labels":[],"label_agreement":null},{"id":"W4406599528","doi":"10.2147/jpr.s484680","title":"Hippocampal Functional Radiomic Features for Identification of the Cognitively Impaired Patients from Low-Back-Related Pain: A Prospective Machine Learning Study","year":2025,"lang":"en","type":"article","venue":"Journal of Pain Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"National Natural Science Foundation of China","keywords":"Medicine; Hippocampal formation; Physical medicine and rehabilitation; Functional connectivity; Identification (biology); Neuroscience; Physical therapy; Internal medicine","score_opus":0.02114165330754393,"score_gpt":0.344198528482581,"score_spread":0.32305687517503706,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406599528","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9881713,0.0005197845,0.007012071,0.0023946003,0.00032773294,0.0014586493,0.000017453127,0.000009769035,0.000088636196],"genre_scores_gemma":[0.9976688,0.00001951919,0.00022219216,0.00013709952,0.00019009641,0.000028577799,0.000036076464,0.000021619657,0.0016759865],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9951407,0.002455411,0.00079058495,0.0002359678,0.0011045753,0.0002728169],"domain_scores_gemma":[0.99445903,0.002888303,0.00049535575,0.00018193875,0.001860603,0.0001147621],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.014083628,0.00013351554,0.00041098683,0.0004500393,0.00036213826,0.00004100133,0.00025168646,0.00009379805,0.00006768986],"category_scores_gemma":[0.018070742,0.00008763742,0.0002463489,0.0006734828,0.00027100433,0.000077561264,0.000078140256,0.001680517,0.0000021152869],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002245026,0.0013640588,0.9641842,0.00016701121,0.000781709,0.000014771498,0.0017631728,0.00025153943,0.006778687,0.0000308213,0.009360309,0.013058674],"study_design_scores_gemma":[0.0075377305,0.0014540718,0.96578,0.00063574716,0.0001362386,0.00000923376,0.0018097701,0.020431343,0.00061916205,0.0012708529,0.00024081062,0.00007503813],"about_ca_topic_score_codex":0.00011539661,"about_ca_topic_score_gemma":0.0000068338845,"teacher_disagreement_score":0.020179804,"about_ca_system_score_codex":0.0002674257,"about_ca_system_score_gemma":0.0004977705,"threshold_uncertainty_score":0.99020046},"labels":[],"label_agreement":null},{"id":"W4406641502","doi":"10.1016/b978-2-294-71497-9.00034-1","title":"10.1016/b978-2-294-71497-9.00034-1","year":2000,"lang":"en","type":"book-chapter","venue":"Time to knit","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science","score_opus":0.0071884530662016536,"score_gpt":0.21064997061476687,"score_spread":0.2034615175485652,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406641502","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000023263835,0.000607547,0.0000062076424,0.0020525013,0.000011318279,0.00048707944,0.000029651559,0.00026186503,0.9965415],"genre_scores_gemma":[0.0000019079675,0.000005863889,0.0005306815,0.000670335,0.001343911,0.000014230829,0.00023827412,0.000221506,0.9969733],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99780077,0.00002159115,0.0004876349,0.0006204914,0.0006001873,0.00046933396],"domain_scores_gemma":[0.9983253,0.00009554584,0.00013532593,0.00072387914,0.00009056206,0.00062940863],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00027994023,0.00051285094,0.0008706893,0.00034061263,0.000097519165,0.00005155555,0.0003002652,0.00039995863,0.9967065],"category_scores_gemma":[0.00011642721,0.00047426255,0.00030190274,0.000060717633,0.000148796,0.000041899857,0.00011162989,0.0013118045,0.98987764],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011453605,0.000025733167,5.0322033e-8,0.000048650163,0.00012345768,0.00019062363,0.000009811159,0.000009908567,0.000013939434,0.00006229288,0.35861945,0.6407815],"study_design_scores_gemma":[0.00071384566,0.00033009076,0.0000032323958,0.00064886734,0.0003171625,0.00021901242,2.434018e-7,0.00037492145,0.0000048190805,0.00028324817,0.9966334,0.00047114718],"about_ca_topic_score_codex":0.000019302244,"about_ca_topic_score_gemma":6.786664e-8,"teacher_disagreement_score":0.6403104,"about_ca_system_score_codex":0.00014122363,"about_ca_system_score_gemma":0.00017083083,"threshold_uncertainty_score":0.9997709},"labels":[],"label_agreement":null},{"id":"W4406648879","doi":"10.1016/b978-2-294-73068-9.00609-5","title":"10.1016/b978-2-294-73068-9.00609-5","year":2000,"lang":"en","type":"book-chapter","venue":"Time to knit","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine","score_opus":0.0071830167985141285,"score_gpt":0.21079927477964544,"score_spread":0.2036162579811313,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406648879","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000002263192,0.00052293757,0.000006788565,0.0022064196,0.000011231239,0.00047419555,0.000029342784,0.00025993434,0.9964869],"genre_scores_gemma":[0.000001928584,0.000004951372,0.00048834615,0.0006664259,0.0014385832,0.000012714433,0.00023579726,0.00021633887,0.9969349],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978538,0.000020829117,0.00047271553,0.000608429,0.000584141,0.00046008252],"domain_scores_gemma":[0.99838686,0.00009925237,0.0001352772,0.0006761101,0.00009086843,0.0006116031],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00026944018,0.0005021726,0.0008507635,0.00034066214,0.00009626986,0.000049516664,0.00028572365,0.00039308547,0.9962925],"category_scores_gemma":[0.00014096704,0.00046526027,0.00030296226,0.000057894475,0.00014014193,0.000041459385,0.00010689284,0.0012741599,0.9892158],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000112281785,0.000025189269,4.0328217e-8,0.00004702876,0.000119105105,0.00019063341,0.000009626279,0.000011053438,0.000017365524,0.000054926935,0.36092433,0.6384884],"study_design_scores_gemma":[0.0006900567,0.00032187995,0.000002626326,0.00064442045,0.0003092882,0.00021860623,2.603237e-7,0.00038766157,0.000006213272,0.00022812001,0.9967287,0.0004621724],"about_ca_topic_score_codex":0.000019279325,"about_ca_topic_score_gemma":8.012084e-8,"teacher_disagreement_score":0.63802624,"about_ca_system_score_codex":0.00013668595,"about_ca_system_score_gemma":0.00017033123,"threshold_uncertainty_score":0.99977994},"labels":[],"label_agreement":null},{"id":"W4406657221","doi":"10.1007/978-3-031-77389-1_9","title":"Investigating the Impact of a Foundational Medical Image Model for CT Classification","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Okanagan University College; University of British Columbia, Okanagan Campus; University of British Columbia; BC Cancer Agency","funders":"","keywords":"Computer science; Artificial intelligence; Medical imaging; Natural language processing; Computer vision","score_opus":0.030429612255669886,"score_gpt":0.34808939530828115,"score_spread":0.3176597830526113,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406657221","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008545936,0.00008756826,0.9892759,0.0071070353,0.0002025833,0.00041926728,0.000008207278,0.000022130827,0.0020227171],"genre_scores_gemma":[0.57197523,0.000036532158,0.42319575,0.0033049518,0.0006476502,0.000025114785,0.00007976954,0.000035391364,0.00069959555],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99811375,0.000017451826,0.00041625038,0.0004492716,0.00076760113,0.0002356979],"domain_scores_gemma":[0.9980149,0.0009803394,0.00022855897,0.00038765452,0.000256294,0.00013223103],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001364278,0.00020058062,0.00035726212,0.0002774721,0.00014568825,0.00006124454,0.0005298932,0.00010918343,0.000029020579],"category_scores_gemma":[0.0026570044,0.00012595092,0.00017961115,0.00019566997,0.0012451893,0.00007160114,0.00016262564,0.0008109083,0.0000010916947],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024672157,0.000053167932,0.0011285916,0.0002866324,0.00007740067,0.000011403955,0.00062693,0.071279585,0.0011373942,0.015653318,0.0006860709,0.90903485],"study_design_scores_gemma":[0.00034716842,0.00006489809,0.0005259434,0.00072801806,0.000025133879,0.00003230122,2.2848113e-7,0.9394065,0.00004694374,0.058647618,0.00007537473,0.000099833655],"about_ca_topic_score_codex":0.0000368176,"about_ca_topic_score_gemma":0.00000820453,"teacher_disagreement_score":0.908935,"about_ca_system_score_codex":0.00021129221,"about_ca_system_score_gemma":0.0026109314,"threshold_uncertainty_score":0.5136129},"labels":[],"label_agreement":null},{"id":"W4406688164","doi":"10.1093/ecco-jcc/jjae190.1406","title":"P1232 A Novel Inflammatory Bowel Disease Registry Powered by Artificial Intelligence and Natural Language Processing","year":2025,"lang":"en","type":"article","venue":"Journal of Crohn s and Colitis","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Children's Hospital; Université de Montréal; Centre Hospitalier de l’Université de Montréal; St. Paul's Hospital","funders":"","keywords":"Medicine; Inflammatory bowel disease; Crohn's disease; Disease; Artificial intelligence; Intensive care medicine; Pathology","score_opus":0.006850251624959467,"score_gpt":0.287067241911452,"score_spread":0.28021699028649255,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406688164","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96907073,0.020870214,0.004114266,0.0052002007,0.0002041131,0.00008740654,0.0000059976774,0.000010948078,0.00043611065],"genre_scores_gemma":[0.9971677,0.00035410706,0.0006144192,0.0010366546,0.00018241532,0.0000012746718,0.0000024134233,0.000007832616,0.0006331698],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99922264,0.00001710069,0.00032228595,0.000113617745,0.00017791612,0.00014641538],"domain_scores_gemma":[0.9993993,0.000045414796,0.00016451336,0.0000733354,0.000097756536,0.00021966161],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002369132,0.00009168085,0.00020195462,0.00008956025,0.00008903646,0.00009831749,0.00006041006,0.00004075565,0.000011243655],"category_scores_gemma":[0.00041278265,0.000072829105,0.000048872113,0.00007281166,0.00016419489,0.000099538425,0.000032875265,0.00041581984,2.3097466e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0042388877,0.00026423373,0.012768851,0.001301703,0.00015567751,0.0018365388,0.0016292621,0.000008977401,0.0048090033,0.0026238216,0.0043427115,0.96602035],"study_design_scores_gemma":[0.002262203,0.0002569327,0.92263293,0.0040612724,0.00044659575,0.0016589119,0.003445942,0.03127142,0.0010751523,0.0028754696,0.029626803,0.0003863642],"about_ca_topic_score_codex":0.000014996722,"about_ca_topic_score_gemma":0.0000017143408,"teacher_disagreement_score":0.965634,"about_ca_system_score_codex":0.000027874397,"about_ca_system_score_gemma":0.00020053594,"threshold_uncertainty_score":0.29698846},"labels":[],"label_agreement":null},{"id":"W4406703652","doi":"10.1093/ecco-jcc/jjae190.0545","title":"P0371 Building a Robust Artificial Intelligence Solution for Use in Ulcerative Colitis Clinical Trials","year":2025,"lang":"en","type":"article","venue":"Journal of Crohn s and Colitis","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary; Vancouver General Hospital; University of British Columbia","funders":"","keywords":"Medicine; Ulcerative colitis; Internal medicine; Gastroenterology; Disease","score_opus":0.1216176835573955,"score_gpt":0.4392623705043633,"score_spread":0.3176446869469678,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406703652","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.61092794,0.00034196215,0.38061923,0.0067122104,0.00077494245,0.00042468344,0.000009218882,0.0000068509307,0.00018298405],"genre_scores_gemma":[0.9686913,0.00061808777,0.028488344,0.0011432443,0.00074440707,0.000011745136,0.0000023129335,0.000010334206,0.00029025594],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99759656,0.00039261786,0.0014559363,0.00016300428,0.00016974067,0.00022211883],"domain_scores_gemma":[0.9970988,0.0019506104,0.00043117013,0.000078970625,0.00027573694,0.0001647215],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006084576,0.000104293926,0.00077629386,0.00024216442,0.00009193995,0.0001135777,0.00006689791,0.00011360582,0.000030430641],"category_scores_gemma":[0.009375171,0.00008455285,0.00023302675,0.00016975346,0.00014698316,0.00014965632,0.000027811147,0.0005312702,4.3380385e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.011964747,0.00029460486,0.008502011,0.00014767607,0.00022038247,0.00028642218,0.00027920085,0.00017793584,0.0001366576,0.029070329,0.0056753634,0.9432447],"study_design_scores_gemma":[0.0044834553,0.001452172,0.76514554,0.0028716282,0.0005450866,0.00047814162,0.00071255805,0.15951613,0.0004978805,0.035994865,0.028038522,0.00026404133],"about_ca_topic_score_codex":0.00009694194,"about_ca_topic_score_gemma":0.0000881498,"teacher_disagreement_score":0.94298065,"about_ca_system_score_codex":0.00009148947,"about_ca_system_score_gemma":0.0003224318,"threshold_uncertainty_score":0.99896926},"labels":[],"label_agreement":null},{"id":"W4406703674","doi":"10.1093/ecco-jcc/jjae190.0625","title":"P0451 Using a machine learning model to assess agreement between inflammation in the rectosigmoid and entire colon in patients with ulcerative colitis","year":2025,"lang":"en","type":"article","venue":"Journal of Crohn s and Colitis","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Medicine; Ulcerative colitis; Gastroenterology; Inflammation; Colitis; Internal medicine; Inflammatory bowel disease; Disease","score_opus":0.01804037308001756,"score_gpt":0.30311664182845643,"score_spread":0.2850762687484389,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406703674","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9944293,0.000106750646,0.002408078,0.0024219549,0.000029134095,0.0003378966,0.000003167226,0.000002315801,0.00026139047],"genre_scores_gemma":[0.99771667,0.00006877111,0.001639775,0.0004338776,0.00006212504,0.000005461038,0.0000046280925,0.000006719218,0.00006195562],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9989541,0.00012875104,0.00037162282,0.000114928676,0.00026996728,0.00016058318],"domain_scores_gemma":[0.99944466,0.00012196381,0.00016504552,0.000056649034,0.0001283328,0.000083327985],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007615358,0.00009874044,0.00031250477,0.00025057283,0.00009198526,0.00007520887,0.00005417714,0.000042316926,0.0000043111227],"category_scores_gemma":[0.00020201877,0.00006701166,0.000023224133,0.00022472285,0.000046672125,0.00011524967,0.000033032826,0.000484171,8.226837e-8],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019322239,0.00006125289,0.9447361,0.00011016041,0.00006152376,0.00008456539,0.002807532,0.0017433002,0.00008020116,0.00030343616,0.000041311483,0.04803835],"study_design_scores_gemma":[0.0028949708,0.0004622648,0.96554714,0.00088284444,0.00006877843,0.000023582921,0.0003108812,0.028971499,0.00005112543,0.00018493686,0.0005359714,0.000065998385],"about_ca_topic_score_codex":0.00020789648,"about_ca_topic_score_gemma":0.00016532453,"teacher_disagreement_score":0.04797235,"about_ca_system_score_codex":0.00011078545,"about_ca_system_score_gemma":0.000112955226,"threshold_uncertainty_score":0.2732656},"labels":[],"label_agreement":null},{"id":"W4406739905","doi":"10.1016/j.pathol.2024.12.150","title":"Using machine learning to uncover the predictive power of the tumour microenvironment","year":2025,"lang":"en","type":"article","venue":"Pathology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Actua; University of Waterloo","funders":"","keywords":"Predictive power; Computer science; Tumor microenvironment; Computational biology; Medicine; Biology; Cancer research; Physics; Tumor cells","score_opus":0.008396150445413062,"score_gpt":0.2769736280185962,"score_spread":0.2685774775731831,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406739905","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97669685,0.00044606216,0.009139212,0.010735981,0.0003783691,0.00029143982,0.0000038213047,0.000015403646,0.0022928377],"genre_scores_gemma":[0.9930403,0.000021285616,0.0013075332,0.004394478,0.000039488965,0.0000071830978,0.0000018779971,0.000011991373,0.001175843],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9991089,0.00018577125,0.00019406351,0.0001851559,0.00014072123,0.00018537251],"domain_scores_gemma":[0.9994922,0.00010988283,0.00007599864,0.0002550878,0.000023803404,0.000043005166],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004266387,0.000095869436,0.00020401792,0.00005957807,0.00013309276,0.0000053080057,0.00015551913,0.000047956833,0.00006268879],"category_scores_gemma":[0.00058248284,0.000051747385,0.00008349644,0.0001702788,0.00020636615,0.000011473385,0.00021315049,0.00051809655,0.0000067889887],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022299359,0.00016243881,0.50372833,0.000061584324,0.00013930297,0.000085298656,0.0034194915,0.0118499445,0.4747001,0.0007171251,0.0011904461,0.0037229664],"study_design_scores_gemma":[0.0023042855,0.0005301024,0.8538272,0.00046643562,0.00048422237,0.00059662765,0.0011436964,0.054974336,0.022321517,0.000768486,0.062363237,0.00021988037],"about_ca_topic_score_codex":0.00005459236,"about_ca_topic_score_gemma":0.000002657868,"teacher_disagreement_score":0.45237857,"about_ca_system_score_codex":0.00006488066,"about_ca_system_score_gemma":0.000054285047,"threshold_uncertainty_score":0.22509006},"labels":[],"label_agreement":null},{"id":"W4406778756","doi":"10.1002/jmri.29691","title":"<scp>MRI</scp> Radiomics Analysis in the Diagnostic Differentiation of Malignant Soft Tissue Myxoid Sarcomas From Benign Soft Tissue Musculoskeletal Myxomas","year":2025,"lang":"en","type":"article","venue":"Journal of Magnetic Resonance Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sinai Health System; Women's College Hospital; University of Toronto; University Health Network; Mount Sinai Hospital","funders":"","keywords":"Intraclass correlation; Medicine; Sarcoma; Myxoma; Receiver operating characteristic; Soft tissue; Magnetic resonance imaging; Radiology; Soft tissue sarcoma; Pathology; Internal medicine","score_opus":0.004904832373627547,"score_gpt":0.27125098486996524,"score_spread":0.2663461524963377,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406778756","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8787105,0.062395,0.05133755,0.006173013,0.00045276742,0.00039625008,0.000013867452,0.000018318615,0.00050273834],"genre_scores_gemma":[0.98938555,0.0022639274,0.006942305,0.0006298774,0.00034368964,0.000008493878,0.000026877284,0.000032568798,0.00036669683],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99652994,0.00037358468,0.0013714643,0.0003709887,0.0008852858,0.00046871806],"domain_scores_gemma":[0.99557585,0.0027822773,0.0007216348,0.0005113029,0.00025552316,0.00015340495],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014784108,0.00031122137,0.0010210553,0.0008912273,0.00011089109,0.000102064085,0.00056978903,0.000097310985,0.00006880955],"category_scores_gemma":[0.004439613,0.000227549,0.00037598098,0.0012718142,0.0002527058,0.00018570828,0.000095040734,0.0009569331,0.000003827777],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000066088396,0.00045904302,0.52470285,0.00019552739,0.00027176543,0.0007546209,0.0017860092,0.0011528422,0.020815544,0.00018914379,0.0033831394,0.4462234],"study_design_scores_gemma":[0.0027658327,0.00030171484,0.91191614,0.000956356,0.0021776406,0.00017106245,0.00076567347,0.04406513,0.0015836793,0.0012514732,0.03391212,0.00013320676],"about_ca_topic_score_codex":0.00032837092,"about_ca_topic_score_gemma":0.00002661546,"teacher_disagreement_score":0.4460902,"about_ca_system_score_codex":0.00012620667,"about_ca_system_score_gemma":0.00020255295,"threshold_uncertainty_score":0.9279179},"labels":[],"label_agreement":null},{"id":"W4406821406","doi":"10.1016/j.compbiolchem.2025.108363","title":"NAVT-net neuron attention visual taylor network for lung cancer detection using CT images","year":2025,"lang":"en","type":"article","venue":"Computational Biology and Chemistry","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Lung cancer; Computer science; Artificial intelligence; Visual attention; Pattern recognition (psychology); Computer vision; Radiology; Neuroscience; Medicine; Pathology; Psychology","score_opus":0.0069451269747038994,"score_gpt":0.3432960146900033,"score_spread":0.3363508877152994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406821406","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83887,0.0010642987,0.15875688,0.0008713663,0.00022200093,0.00009658608,0.00000675154,0.000024866673,0.00008727238],"genre_scores_gemma":[0.9957668,0.000030522526,0.0028842993,0.00058735587,0.00037820707,0.000008421094,0.00015907909,0.0000060801453,0.0001792096],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99951667,0.000015196769,0.00012670258,0.00018486872,0.000034556797,0.00012203812],"domain_scores_gemma":[0.9997055,0.0001176361,0.00005045852,0.000033600452,0.000055794924,0.000037020494],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009793872,0.00007535733,0.00012536912,0.00001887038,0.00014770846,0.0000107798305,0.000024217046,0.00005228035,0.000015924968],"category_scores_gemma":[0.000074743606,0.00007035199,0.000039938604,0.00006455843,0.000088604334,0.000017286773,0.0000211402,0.00015186841,1.4399129e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041181294,0.00011092065,0.30825529,0.0011791221,0.00038772568,0.000013024341,0.00002753664,0.04093707,0.53224444,0.00028128733,0.002412632,0.11373913],"study_design_scores_gemma":[0.0010109963,0.000028232147,0.03722541,0.000108328946,0.00012878129,0.000057316778,0.000012727839,0.95603627,0.003161088,0.0012512457,0.00089316734,0.000086453],"about_ca_topic_score_codex":0.000014393835,"about_ca_topic_score_gemma":2.9350605e-7,"teacher_disagreement_score":0.9150992,"about_ca_system_score_codex":0.000032087068,"about_ca_system_score_gemma":0.000046023728,"threshold_uncertainty_score":0.2868871},"labels":[],"label_agreement":null},{"id":"W4406834106","doi":"10.1158/1557-3265.targetedtherap-p008","title":"Abstract P008: Evaluating associations between genomic classifier and digital pathology based mutli-modal AI biomarkers in oligometastatic castration-sensitive prostate cancer","year":2025,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Prostate cancer; Medicine; Classifier (UML); Pathology; Digital pathology; Cancer; Oncology; Internal medicine; Artificial intelligence; Computer science","score_opus":0.15360829387418082,"score_gpt":0.5487248457129404,"score_spread":0.3951165518387596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406834106","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9731603,0.0005238098,0.0001780207,0.024099704,0.00020723749,0.0008091876,0.00017247185,0.000026583735,0.0008226401],"genre_scores_gemma":[0.99728537,0.00029354042,0.00048638566,0.0011304534,0.0002364346,0.00014481357,0.00010626309,0.000027036074,0.0002897308],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99679047,0.0005613902,0.0008795068,0.0006148385,0.0005649621,0.00058885064],"domain_scores_gemma":[0.9952781,0.0036424412,0.00014908522,0.00023020475,0.0004372474,0.0002628882],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0054959077,0.00016328909,0.0005880051,0.00044554405,0.00020785844,0.00013424817,0.00011987387,0.00018519316,0.00006946722],"category_scores_gemma":[0.005914469,0.00014716153,0.00010458073,0.0006756458,0.00069049816,0.00012456944,0.000107353146,0.0019257804,0.000009935403],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028788694,0.00012493473,0.7987823,0.00011639627,0.00023881203,0.00011373382,0.00020431276,0.00015615538,0.0016869261,0.000036449997,0.0007179529,0.19753416],"study_design_scores_gemma":[0.0033230162,0.00021327927,0.97600824,0.00044889475,0.000090109585,0.0000024360147,0.00020668127,0.018611334,0.00008078441,0.00050296454,0.00038418584,0.00012806203],"about_ca_topic_score_codex":0.0012139685,"about_ca_topic_score_gemma":0.0002883266,"teacher_disagreement_score":0.1974061,"about_ca_system_score_codex":0.0005040494,"about_ca_system_score_gemma":0.002235838,"threshold_uncertainty_score":0.83666646},"labels":[],"label_agreement":null},{"id":"W4406869684","doi":"10.1200/jco.2025.43.4_suppl.106","title":"Frequency of surveillance CT scan ordering in patients with stage II/III colorectal cancer.","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Health Sciences Centre; Sunnybrook Health Science Centre; University of Toronto","funders":"","keywords":"Medicine; Stage (stratigraphy); Colorectal cancer; Cancer; Radiology; Computed tomography; Oncology; Internal medicine","score_opus":0.024111992701773076,"score_gpt":0.41852142187774644,"score_spread":0.3944094291759734,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406869684","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9913108,0.00027078137,0.00017036663,0.0036409125,0.0008725428,0.00014561077,0.0000025439292,0.0000051274965,0.0035813153],"genre_scores_gemma":[0.99634886,0.0002903325,0.002234184,0.0007712382,0.00016445933,0.0000021311012,0.0000017827665,0.000009658549,0.00017737657],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9974733,0.00021899318,0.0016728186,0.00014820187,0.00028802405,0.00019864312],"domain_scores_gemma":[0.9973259,0.00092640385,0.0011353764,0.00010617151,0.00034225677,0.00016390435],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002347587,0.00010234135,0.0012749454,0.00017606985,0.000031811505,0.0000035328,0.00015515092,0.000105429644,0.000084560976],"category_scores_gemma":[0.003532506,0.00006972486,0.00014727545,0.0002827305,0.00024798652,0.00006605493,0.000053214873,0.0012210852,3.4650046e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014915614,0.00075746916,0.931172,0.000043950273,0.00016512832,0.00013943367,0.00004378103,0.00017200442,0.0001059189,0.00008114632,0.00029797727,0.065529615],"study_design_scores_gemma":[0.012256563,0.003847253,0.97892666,0.0003802203,0.000060246428,0.000012264508,0.00003365649,0.0004602007,0.000037766247,0.000058996702,0.003865443,0.00006074413],"about_ca_topic_score_codex":0.00038870322,"about_ca_topic_score_gemma":0.00036332593,"teacher_disagreement_score":0.06546887,"about_ca_system_score_codex":0.00017896952,"about_ca_system_score_gemma":0.0018892699,"threshold_uncertainty_score":0.53050756},"labels":[],"label_agreement":null},{"id":"W4406916359","doi":"10.1016/b978-0-443-24838-2.00007-0","title":"Recent advancement in molecular tools for breast cancer diagnosis and therapy decision: Trends in future perspective","year":2025,"lang":"en","type":"book-chapter","venue":"Elsevier eBooks","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Perspective (graphical); Breast cancer; Medicine; Medical physics; Cancer; Computer science; Artificial intelligence; Internal medicine","score_opus":0.014325046731616239,"score_gpt":0.32484785631146085,"score_spread":0.3105228095798446,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406916359","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008794693,0.1564583,0.00010317354,0.030226646,0.0009234737,0.0023453657,0.00023503829,0.000042787837,0.80878574],"genre_scores_gemma":[0.0009660936,0.30487654,0.0048539834,0.009196647,0.001220186,0.0022304514,0.0001028135,0.00018069992,0.6763726],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984084,0.000022887893,0.00041098456,0.0005974936,0.00027779813,0.00028248536],"domain_scores_gemma":[0.9991732,0.0001571876,0.00011965758,0.0002885358,0.00013401565,0.00012737652],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00026887038,0.00035668156,0.0007257314,0.00047550155,0.00004164689,0.00003749358,0.00011239812,0.00023388457,0.00038805895],"category_scores_gemma":[0.00006589804,0.00029751682,0.00015767266,0.000054516622,0.00008130193,0.00003506236,0.000060245846,0.00072085863,7.3130246e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033494632,0.000037520327,0.0002637124,0.000060902883,0.00011201438,0.00010826475,0.00030360135,0.0000045619176,0.00001058016,0.003235703,0.00030934875,0.9952189],"study_design_scores_gemma":[0.003312487,0.00012358834,0.001761684,0.0023941686,0.000089734735,0.000022281665,0.0000753887,0.000089406756,0.000013285898,0.0031783849,0.9886658,0.00027376376],"about_ca_topic_score_codex":0.0000065965437,"about_ca_topic_score_gemma":0.00006144745,"teacher_disagreement_score":0.9949451,"about_ca_system_score_codex":0.0004664091,"about_ca_system_score_gemma":0.00016703097,"threshold_uncertainty_score":0.99994767},"labels":[],"label_agreement":null},{"id":"W4406940698","doi":"10.1101/2025.01.28.25321302","title":"OPPORTUNISTIC ASSESSMENT OF CARDIOVASCULAR RISK USING AI-DERIVED STRUCTURAL AORTIC AND CARDIAC PHENOTYPES FROM NON-CONTRAST CHEST COMPUTED TOMOGRAPHY","year":2025,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computed tomography; Medicine; Contrast (vision); Radiology; Cardiology; Internal medicine; Artificial intelligence; Computer science","score_opus":0.014379798543097835,"score_gpt":0.29677744610241874,"score_spread":0.2823976475593209,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406940698","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91978383,0.003900984,0.073664814,0.00018598852,0.0012755615,0.0006598163,0.00028297582,0.00006667373,0.00017937637],"genre_scores_gemma":[0.9711739,0.00062466523,0.027297849,0.00010179045,0.00039979175,0.000016466369,0.0003293272,0.000042943757,0.000013280603],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99728644,0.00029438047,0.00068469334,0.00078403996,0.0006010971,0.00034932347],"domain_scores_gemma":[0.99798423,0.00022774772,0.0003803412,0.0008849185,0.00021813286,0.00030461434],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000718165,0.00045307726,0.0018242578,0.00029739286,0.00013242713,0.000064193526,0.00024296227,0.00027760727,0.000024939834],"category_scores_gemma":[0.0002640865,0.00040507584,0.00074416545,0.00020768326,0.0003398756,0.000036480542,0.0004561891,0.00159146,3.187686e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004763183,0.00006224114,0.94402784,0.0014987543,0.008376765,0.00010148544,0.0003525136,0.009290054,0.0074728024,0.000048968897,0.00003428452,0.028686663],"study_design_scores_gemma":[0.0009001396,0.000035619476,0.6123895,0.00092027255,0.0042145993,0.0000038061712,0.000039588,0.38058233,0.00020660028,0.00026416266,0.00018262683,0.00026076386],"about_ca_topic_score_codex":0.003149309,"about_ca_topic_score_gemma":0.0000030365518,"teacher_disagreement_score":0.3712923,"about_ca_system_score_codex":0.00008739109,"about_ca_system_score_gemma":0.00048621785,"threshold_uncertainty_score":0.9998401},"labels":[],"label_agreement":null},{"id":"W4406967001","doi":"10.36227/techrxiv.173816115.56881499/v1","title":"Deep Learning-Based Analysis of Ultrasound Colon Videos for Enhanced Medical Imaging of Motor Patterns and Content Flow","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Canadian Institutes of Health Research","keywords":"Content (measure theory); Ultrasound; Content analysis; Flow (mathematics); Ultrasound imaging; Motor learning; Computer science; Artificial intelligence; Medicine; Psychology; Radiology; Neuroscience; Mathematics; Sociology","score_opus":0.012155761933575256,"score_gpt":0.30488718159362516,"score_spread":0.2927314196600499,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406967001","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3430146,0.0005027376,0.6535036,0.0017047005,0.00021217819,0.00068667287,0.00006704488,0.000047794692,0.00026065888],"genre_scores_gemma":[0.98690337,0.0003447213,0.010536483,0.000955622,0.0000847234,0.00009568077,0.00054147514,0.000026342652,0.00051155646],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99740577,0.00013232944,0.0009220138,0.00059288176,0.0006535519,0.0002934492],"domain_scores_gemma":[0.9966958,0.0017049586,0.00049252796,0.00040127456,0.00043170046,0.00027374522],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010621741,0.00030480578,0.0015789965,0.0007062338,0.000053503754,0.000021738982,0.00023083821,0.0002690896,0.0003925928],"category_scores_gemma":[0.004952743,0.0002561233,0.0005962931,0.00026251716,0.00025721474,0.000019869933,0.00018781537,0.000962876,2.2210659e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016297766,0.0009488985,0.7286189,0.012417987,0.011920057,0.000050458315,0.0013191031,0.05367682,0.030561501,0.00019575135,0.00041575477,0.15824495],"study_design_scores_gemma":[0.0024002164,0.0001594724,0.03753452,0.0013394961,0.0043994877,0.0000036781248,0.00024441074,0.9488128,0.0046838387,0.000028730048,0.00019285275,0.0002005105],"about_ca_topic_score_codex":0.00093955715,"about_ca_topic_score_gemma":0.00010055656,"teacher_disagreement_score":0.89513594,"about_ca_system_score_codex":0.0000757161,"about_ca_system_score_gemma":0.0003435218,"threshold_uncertainty_score":0.9999891},"labels":[],"label_agreement":null},{"id":"W4406981628","doi":"10.1016/j.jocmr.2024.101445","title":"Radiomics provides incremental value in distinguishing between ATTR and AL on cardiac magnetic resonance imaging","year":2025,"lang":"en","type":"article","venue":"Journal of Cardiovascular Magnetic Resonance","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Angiology; Radiomics; Medicine; Magnetic resonance imaging; Cardiac magnetic resonance; Cardiac magnetic resonance imaging; Value (mathematics); Cardiac imaging; Radiology; Cardiology; Computer science; Machine learning","score_opus":0.007642225338531649,"score_gpt":0.2584787628022216,"score_spread":0.25083653746368995,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406981628","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49319038,0.50125134,0.00033580957,0.0022560698,0.00046953437,0.00036985023,0.000005331743,0.000018824636,0.0021028242],"genre_scores_gemma":[0.97260606,0.017532729,0.007549924,0.0011328907,0.0007945055,0.000014640084,0.000004459825,0.0000630118,0.00030176368],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9967451,0.0003870863,0.0009262065,0.00046939612,0.0009872504,0.00048496368],"domain_scores_gemma":[0.9985463,0.00038301834,0.00018707475,0.0004944923,0.00016891574,0.000220184],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.003056106,0.00031377902,0.0012443415,0.00044180106,0.00012471905,0.00011803905,0.00028101308,0.00009316354,0.0000063135435],"category_scores_gemma":[0.001923363,0.00028076812,0.0006369877,0.00048669105,0.00027787476,0.00014855513,0.0001322929,0.001178876,0.0000016648161],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016849038,0.000049293943,0.23096313,0.00014486269,0.00011556628,0.00068523164,0.00013809226,0.00013257179,0.00019228431,0.00017712935,0.0011690129,0.76606435],"study_design_scores_gemma":[0.003569671,0.00035566444,0.5547221,0.0021815456,0.00052972854,0.0003210163,0.00009391943,0.004477772,0.00014073834,0.00024727674,0.43313238,0.00022823062],"about_ca_topic_score_codex":0.00017993222,"about_ca_topic_score_gemma":8.388385e-7,"teacher_disagreement_score":0.7658361,"about_ca_system_score_codex":0.00027868908,"about_ca_system_score_gemma":0.0002452968,"threshold_uncertainty_score":0.9999645},"labels":[],"label_agreement":null},{"id":"W4406993451","doi":"10.1161/str.56.suppl_1.wmp85","title":"Abstract WMP85: Site vs Core-lab CT ASPECTS read in the SELECT2 trial – assessment of trial eligibility and EVT treatment effect","year":2025,"lang":"en","type":"article","venue":"Stroke","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Medicine; Clinical trial; Core (optical fiber); Randomized controlled trial; Nuclear medicine; Internal medicine","score_opus":0.015383505659119407,"score_gpt":0.3820322978140915,"score_spread":0.3666487921549721,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406993451","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98462623,0.00021059401,0.00006020203,0.0014332768,0.00040544895,0.0018126748,0.000013282143,0.000024395773,0.011413904],"genre_scores_gemma":[0.99870455,0.000099011224,0.00034308818,0.00021416429,0.00023923205,0.000049129816,0.000026198757,0.000009554277,0.00031504768],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.9984696,0.00021701137,0.00041948695,0.00032326573,0.000329309,0.00024131131],"domain_scores_gemma":[0.998406,0.0010085785,0.00012853737,0.00035554593,0.000029704708,0.0000716214],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016489952,0.00018652815,0.0006012423,0.00012851668,0.00006240975,0.000029080533,0.00009628396,0.00005592892,0.000037902246],"category_scores_gemma":[0.0008014084,0.000108944594,0.00014636909,0.00019196224,0.000113325725,0.000029583054,0.000028526341,0.0004368517,0.0000014860811],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.3834338,0.004364853,0.35905516,0.00097616285,0.0010750877,0.0006433074,0.00136076,0.00008260019,0.02470761,0.0034069696,0.0030375056,0.21785621],"study_design_scores_gemma":[0.5189175,0.012011466,0.45715865,0.00036015446,0.00061921845,0.000038809223,0.000109178356,0.0037478101,0.0012998622,0.0005442212,0.0049791187,0.00021402439],"about_ca_topic_score_codex":0.0008038164,"about_ca_topic_score_gemma":0.000075909215,"teacher_disagreement_score":0.21764219,"about_ca_system_score_codex":0.00017495843,"about_ca_system_score_gemma":0.00028191588,"threshold_uncertainty_score":0.44426316},"labels":[],"label_agreement":null},{"id":"W4407011499","doi":"10.1016/j.acra.2025.01.008","title":"Expiration CT Gas Trapping Measures with Texture-Based Radiomics Improves Association with Lung Function and Lung Function Decline in COPD","year":2025,"lang":"en","type":"article","venue":"Academic Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Victoria Hospital; McGill University Health Centre; University of British Columbia; Western University; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Keck School of Medicine of USC; Université de Sherbrooke; University of Toronto; Dalhousie University; Queen's University; Canada Research Chairs; University of Calgary; McGill University; University of Ottawa; University of Saskatchewan; Johns Hopkins University","keywords":"Expiration; Lung function; Radiomics; COPD; Lung; Medicine; Air trapping; Lung volumes; Radiology; Internal medicine; Respiratory system","score_opus":0.006956312520341199,"score_gpt":0.2653165552496331,"score_spread":0.2583602427292919,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407011499","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8692232,0.0033674296,0.1097454,0.01610394,0.00033678557,0.00062541116,0.0000012988369,0.00010857655,0.00048797377],"genre_scores_gemma":[0.99202925,0.000574119,0.0007370545,0.005954995,0.00027804976,0.0000658679,0.00008610211,0.000028389244,0.0002461699],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9982285,0.00021998824,0.00045166718,0.00047100353,0.00025633923,0.00037249734],"domain_scores_gemma":[0.9989796,0.0003908525,0.0002703645,0.00016801509,0.00009052334,0.00010058789],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012433879,0.00023596158,0.00049485004,0.00071250583,0.0001293433,0.000023471359,0.00008021905,0.00031949944,0.000007757009],"category_scores_gemma":[0.0005669671,0.00018270675,0.00004197897,0.0007235521,0.00012875412,0.00015961492,0.000018301535,0.0014238271,7.849833e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021144347,0.00005226619,0.9085467,0.00021065517,0.00034294,0.000025437208,0.00017251179,0.0028467614,0.039879706,0.00090610964,0.005573764,0.039328713],"study_design_scores_gemma":[0.015927577,0.0011124942,0.4990727,0.00088734424,0.0012251466,0.00036715844,0.00025088227,0.46189594,0.0013363602,0.00086373306,0.016564157,0.0004964951],"about_ca_topic_score_codex":0.00010286414,"about_ca_topic_score_gemma":0.000051616018,"teacher_disagreement_score":0.45904917,"about_ca_system_score_codex":0.00040371268,"about_ca_system_score_gemma":0.00023402588,"threshold_uncertainty_score":0.74505645},"labels":[],"label_agreement":null},{"id":"W4407052516","doi":"10.1158/1538-7445.dnamethylation-b008","title":"Abstract B008: <i>Machine-learning modelling of lung cancer metastasis to the brain using alterations in DNA methylation</i>","year":2025,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hospital for Sick Children; University Health Network; Thompson Rivers University; University of Toronto","funders":"","keywords":"DNA methylation; Cancer; Lung cancer; Methylation; Metastasis; Brain metastasis; Cancer research; Medicine; Computational biology; DNA; Oncology; Biology; Internal medicine; Genetics; Gene; Gene expression","score_opus":0.09172627303431077,"score_gpt":0.4598031114538534,"score_spread":0.36807683841954264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407052516","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9015945,0.0073644277,0.04528203,0.04320328,0.00021358617,0.0008215001,0.000019390975,0.000025711593,0.0014755472],"genre_scores_gemma":[0.99543804,0.0005980199,0.0017852488,0.0009390687,0.00016482676,0.0001445731,0.000010432257,0.000026108677,0.00089369406],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979849,0.00029717598,0.000401368,0.00031576675,0.00058302336,0.00041778095],"domain_scores_gemma":[0.998533,0.00069197867,0.00006637012,0.00027530125,0.00030829426,0.00012503374],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029662177,0.000120519,0.0003042619,0.0005887497,0.0003053574,0.00005689235,0.00022142332,0.00005744791,0.00018877051],"category_scores_gemma":[0.00096034823,0.00009104704,0.000078739555,0.0014919944,0.0001125881,0.0000878626,0.00011367333,0.0013064563,0.0000020142015],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014055245,0.0000553113,0.013325135,0.0003348933,0.00014733858,0.000010793667,0.0017000759,0.88708174,0.0690438,0.0005656188,0.002040271,0.02555449],"study_design_scores_gemma":[0.0007466803,0.000026064923,0.0023399033,0.0011725808,0.000063793355,0.0000019498495,0.00025151978,0.9731091,0.009079811,0.00014974725,0.012952994,0.00010585052],"about_ca_topic_score_codex":0.011551011,"about_ca_topic_score_gemma":0.00061462016,"teacher_disagreement_score":0.0938435,"about_ca_system_score_codex":0.0003758565,"about_ca_system_score_gemma":0.00071948994,"threshold_uncertainty_score":0.9950312},"labels":[],"label_agreement":null},{"id":"W4407135853","doi":"10.1148/radiol.242134","title":"Leveraging Large Language Models to Generate Clinical Histories for Oncologic Imaging Requisitions","year":2025,"lang":"en","type":"article","venue":"Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":35,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre","funders":"","keywords":"Requisition; Medicine; Interpretation (philosophy); Medical physics; Radiology; Cancer imaging; Cancer; Linguistics; Archaeology; Internal medicine","score_opus":0.03855689954147529,"score_gpt":0.39575862673777185,"score_spread":0.35720172719629656,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407135853","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35623187,0.0019918778,0.5971098,0.03494502,0.0019731955,0.0005790138,0.000013662157,0.00019329117,0.006962292],"genre_scores_gemma":[0.930578,0.000064846594,0.037161916,0.027022615,0.0007597733,0.00009304145,0.000080438316,0.000022991799,0.004216362],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985319,0.00013421291,0.0004070463,0.00039424893,0.000072103394,0.00046050453],"domain_scores_gemma":[0.9989867,0.0004062646,0.00006414607,0.0002798693,0.00008789209,0.0001751301],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011751378,0.00013581921,0.0004814219,0.00018684557,0.00019340358,0.000015953297,0.0001329997,0.00010223037,0.00003736507],"category_scores_gemma":[0.00093235157,0.00011959372,0.00015521068,0.00016457905,0.00012170701,0.000046359877,0.00007394699,0.00038704253,0.000009459016],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00105654,0.0007859159,0.06755119,0.00039915915,0.00068643264,0.0007601483,0.007279617,0.005076529,0.022542339,0.1690038,0.50534254,0.2195158],"study_design_scores_gemma":[0.008320845,0.00051306566,0.0154655585,0.00023777985,0.00050855736,0.0004924394,0.0017677307,0.4242241,0.00023440633,0.016230313,0.5314333,0.00057189265],"about_ca_topic_score_codex":0.000027508884,"about_ca_topic_score_gemma":0.000004453585,"teacher_disagreement_score":0.5743461,"about_ca_system_score_codex":0.0002086983,"about_ca_system_score_gemma":0.00021263678,"threshold_uncertainty_score":0.48768905},"labels":[],"label_agreement":null},{"id":"W4407219956","doi":"10.1007/s10278-025-01421-w","title":"The Effect of Ultrasound Image Pre-Processing on Radiomics Feature Quality: A Study on Shoulder Ultrasound","year":2025,"lang":"en","type":"article","venue":"Journal of Imaging Informatics in Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Reproducibility; Medicine; Ultrasound; Image processing; Intraclass correlation; Radiology; Artificial intelligence; Computer science; Mathematics; Statistics","score_opus":0.009373434589140332,"score_gpt":0.36669355366964385,"score_spread":0.35732011908050354,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407219956","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97050434,0.001221405,0.007015167,0.01092893,0.0010057451,0.0007897721,0.0000021491371,0.000025549487,0.008506919],"genre_scores_gemma":[0.9947367,0.00029652895,0.0019030768,0.0024477667,0.0003264852,0.00000668253,0.0000053680797,0.000029359233,0.00024807637],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9959463,0.00033819623,0.0019426864,0.000141298,0.0012501605,0.00038139411],"domain_scores_gemma":[0.9927894,0.0049910336,0.0012461173,0.00048704827,0.0003244718,0.00016196609],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.008567349,0.00033233623,0.0011613532,0.000789229,0.00019953177,0.00008870316,0.00046678408,0.00008639492,0.00001015563],"category_scores_gemma":[0.013625909,0.00017747369,0.00017814011,0.0007156181,0.00056571147,0.00023213914,0.000044522178,0.0023358571,0.0000010861434],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.007662584,0.0011969876,0.6719346,0.0038524303,0.0012146037,0.00041133564,0.03726634,0.002802608,0.015858093,0.00056295947,0.055374455,0.20186298],"study_design_scores_gemma":[0.098405,0.024439108,0.6227747,0.050352618,0.0041186833,0.0050692833,0.09341102,0.05645272,0.012041915,0.002319642,0.029078165,0.0015371108],"about_ca_topic_score_codex":0.000023152083,"about_ca_topic_score_gemma":0.0000016322718,"teacher_disagreement_score":0.20032586,"about_ca_system_score_codex":0.00025999846,"about_ca_system_score_gemma":0.00021312395,"threshold_uncertainty_score":0.9999658},"labels":[],"label_agreement":null},{"id":"W4407255120","doi":"10.7554/elife.104079.1.sa0","title":"Reviewer #2 (Public review): Intrinsic bioenergetic adaptations compensate for reduced mitochondrial content in HER2-driven mammary tumors","year":2025,"lang":"en","type":"peer-review","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Bioenergetics; Biology; Mitochondrion; Cell biology; Chemistry","score_opus":0.05755793962204673,"score_gpt":0.3423713946730697,"score_spread":0.28481345505102296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407255120","genre_codex":"commentary","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000017288894,0.4509742,0.003462769,0.52468723,0.0077577345,0.007196002,0.000104186955,0.00015506305,0.0056455503],"genre_scores_gemma":[0.000028544826,0.61157,0.019181546,0.09280846,0.0014983492,0.0015844642,0.0053894753,0.00010364971,0.2678355],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9948351,0.0004299387,0.002166872,0.0010874192,0.0007453817,0.0007353365],"domain_scores_gemma":[0.99525505,0.0004318459,0.0006766985,0.0011805922,0.00200898,0.00044684965],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013115074,0.0007155582,0.0032305794,0.0005841127,0.00011281613,0.000058807684,0.0006507851,0.00029796813,0.00066037534],"category_scores_gemma":[0.017839024,0.0005716946,0.00090760353,0.000850898,0.00016201,0.000081116836,0.00024400855,0.0016704103,0.00003913966],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022772625,0.00014873134,0.000011943447,0.04183254,0.00016672623,0.00005291748,0.000008799066,0.0000024497404,0.00003537881,0.00064478733,0.864423,0.092650004],"study_design_scores_gemma":[0.0018137296,0.00014631345,0.00014674525,0.15387471,0.00091812,0.00005159051,0.000005578514,0.0010866222,0.0000029457724,0.00004602236,0.8414753,0.00043231103],"about_ca_topic_score_codex":0.00046061559,"about_ca_topic_score_gemma":0.000117851734,"teacher_disagreement_score":0.43187875,"about_ca_system_score_codex":0.0003678825,"about_ca_system_score_gemma":0.0015765432,"threshold_uncertainty_score":0.9996734},"labels":[],"label_agreement":null},{"id":"W4407255563","doi":"10.7554/elife.104079.1.sa1","title":"Reviewer #1 (Public review): Intrinsic bioenergetic adaptations compensate for reduced mitochondrial content in HER2-driven mammary tumors","year":2025,"lang":"en","type":"peer-review","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Bioenergetics; Mitochondrion; Biology; Cell biology; Chemistry","score_opus":0.05755793962204673,"score_gpt":0.3423713946730697,"score_spread":0.28481345505102296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407255563","genre_codex":"commentary","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000016661626,0.4531624,0.003759939,0.52215046,0.0078080995,0.007145111,0.00010581797,0.0001550477,0.005696471],"genre_scores_gemma":[0.000029900686,0.60647047,0.018197384,0.093183115,0.0014542664,0.0015599838,0.005262972,0.00010342275,0.2737385],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9948424,0.0004279337,0.0021746042,0.0010855125,0.0007372523,0.00073230336],"domain_scores_gemma":[0.99522346,0.0004323511,0.0006762838,0.001175131,0.0020502955,0.00044248567],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013006919,0.0007168106,0.0032337022,0.0005869469,0.00011109108,0.000058399135,0.00065594545,0.00029284263,0.00064705085],"category_scores_gemma":[0.01838573,0.0005715492,0.0009232504,0.00084117724,0.00016377901,0.00008105295,0.0002457456,0.0016872586,0.00003881059],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024010275,0.00015103232,0.000012022521,0.041927572,0.00016980368,0.000053849453,0.000008951511,0.0000022505083,0.000036156325,0.0006320197,0.86823046,0.08875188],"study_design_scores_gemma":[0.0017972148,0.00014846954,0.00013495529,0.16089405,0.000894832,0.000053636777,0.000006029555,0.0011211032,0.0000029470705,0.00004290389,0.834479,0.00042489637],"about_ca_topic_score_codex":0.00047161416,"about_ca_topic_score_gemma":0.00012445617,"teacher_disagreement_score":0.42896733,"about_ca_system_score_codex":0.00036854544,"about_ca_system_score_gemma":0.0015468918,"threshold_uncertainty_score":0.9996736},"labels":[],"label_agreement":null},{"id":"W4407258499","doi":"10.12688/f1000research.127142.3","title":"Med-ImageTools: An open-source Python package for robust data processing pipelines and curating medical imaging data","year":2025,"lang":"en","type":"preprint","venue":"F1000Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; Kingston Health Sciences Centre; Princess Margaret Cancer Centre; University Health Network; University of Toronto; Queen's University","funders":"Canadian Institutes of Health Research; Canadian Cancer Society","keywords":"Open source; Python (programming language); Open peer review; Open science; Open data; Plant biology; Computer science; Medical imaging; Medicine; Medical physics; Computer graphics (images); Data science; Computational biology; Artificial intelligence; Programming language; World Wide Web; Biology; Software; Mathematics","score_opus":0.17901364626441604,"score_gpt":0.4858526822339002,"score_spread":0.30683903596948414,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407258499","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005321764,0.015888138,0.8630983,0.09824686,0.001143104,0.0067079547,0.002351227,0.00091203366,0.006330596],"genre_scores_gemma":[0.07571168,0.0074472306,0.7690558,0.012080771,0.014063734,0.00097504363,0.09943736,0.0013038754,0.019924514],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9924609,0.0005612595,0.0010536745,0.002831177,0.002012646,0.0010803378],"domain_scores_gemma":[0.99123466,0.0013961246,0.0003283309,0.0053016124,0.0006604414,0.0010788108],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","open_science","research_integrity"],"consensus_categories":["open_science"],"category_scores_codex":[0.0129504055,0.00056250714,0.0011686853,0.00047746603,0.00067899824,0.0019052703,0.007935179,0.00041894286,0.00016450368],"category_scores_gemma":[0.029645965,0.0004877115,0.000060696926,0.00040300167,0.0006893163,0.001166912,0.036264624,0.004308731,0.0000053340314],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026715396,0.000302257,0.0053237304,0.005378623,0.00013798459,0.0002626687,0.00044427565,0.00008496168,0.00045182425,0.000060721104,0.10155803,0.88572776],"study_design_scores_gemma":[0.0019232617,0.00006402993,0.0005026493,0.004848617,0.00023705751,0.00016444708,0.00064959395,0.9013609,0.00003823553,0.00034250724,0.089442715,0.0004259536],"about_ca_topic_score_codex":0.0012307642,"about_ca_topic_score_gemma":0.000113045644,"teacher_disagreement_score":0.901276,"about_ca_system_score_codex":0.00011419628,"about_ca_system_score_gemma":0.0035821244,"threshold_uncertainty_score":0.99975747},"labels":[],"label_agreement":null},{"id":"W4407392303","doi":"10.2147/dmso.s480317","title":"Support Vector Machine for Stratification of Cognitive Impairment Using 3D T1WI in Patients with Type 2 Diabetes Mellitus","year":2025,"lang":"en","type":"article","venue":"Diabetes Metabolic Syndrome and Obesity","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Health Commission of Shanxi Province","keywords":"Stratification (seeds); Cognitive impairment; Diabetes mellitus; Risk stratification; Type 2 Diabetes Mellitus; Medicine; Support vector machine; Internal medicine; Cognition; Computer science; Artificial intelligence; Endocrinology; Psychiatry; Biology","score_opus":0.00681001900251557,"score_gpt":0.25763775203625244,"score_spread":0.2508277330337369,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407392303","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9969774,0.0017336512,0.00021925401,0.000077358636,0.0001145824,0.00076134736,0.000036651414,0.000016963497,0.000062776526],"genre_scores_gemma":[0.997691,0.00006845047,0.0017541744,0.00020050694,0.000015408528,0.000022213208,0.00019650752,0.000014959909,0.000036825644],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99893904,0.000045248376,0.00030286342,0.00026939224,0.00017197631,0.00027150498],"domain_scores_gemma":[0.9993437,0.0001404025,0.00011607084,0.0001465482,0.00016254313,0.000090714086],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000374259,0.00015869742,0.0005587775,0.00020536242,0.00006171316,0.000015572594,0.00005601293,0.00006274508,0.000026738386],"category_scores_gemma":[0.00021231285,0.00012556922,0.000048525493,0.0003238511,0.00010875271,0.00007724319,0.000029625699,0.00015521675,8.350569e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008041257,0.00044951012,0.9901561,0.00031948733,0.00018194366,0.0000012363896,0.00010649796,0.000005933559,0.0004834359,0.00010572288,0.00000890922,0.0081007825],"study_design_scores_gemma":[0.0028291713,0.0005294632,0.9897032,0.00040558798,0.00040922768,8.02414e-7,0.000020955185,0.0040177894,0.0017675791,0.0001036026,0.00009457418,0.00011806721],"about_ca_topic_score_codex":0.000033306256,"about_ca_topic_score_gemma":0.0000026528576,"teacher_disagreement_score":0.007982716,"about_ca_system_score_codex":0.000025737623,"about_ca_system_score_gemma":0.00009607466,"threshold_uncertainty_score":0.5120564},"labels":[],"label_agreement":null},{"id":"W4407489644","doi":"10.1117/12.3048943","title":"Performance evaluation of a stacked classifier for predicting treatment response in unresectable colorectal liver metastases","year":2025,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Medicine; Colorectal cancer; Classifier (UML); Computer science; Internal medicine; Radiology; Artificial intelligence; Cancer","score_opus":0.0378348318336033,"score_gpt":0.35818453262464534,"score_spread":0.320349700791042,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407489644","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9938919,0.00024144552,0.00086685346,0.0006409293,0.0000855002,0.0009103389,0.000006284603,0.000021684655,0.0033350564],"genre_scores_gemma":[0.99527246,0.000050190498,0.0029352559,0.00008822911,0.000022341681,0.0001588457,0.0000228516,0.000008038582,0.001441778],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989642,0.00018168386,0.00026381595,0.00017344207,0.00024766612,0.00016919304],"domain_scores_gemma":[0.9990527,0.0005525053,0.000058884412,0.0001210638,0.00017261942,0.00004223866],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023522598,0.00008823902,0.00024694123,0.00023116279,0.0000456359,0.0000076828055,0.000039822153,0.00004232081,0.0000974037],"category_scores_gemma":[0.0018026127,0.000065458546,0.000060310733,0.00023710796,0.00005109043,0.000057138033,0.000016857772,0.00009287115,9.2134627e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.03154571,0.0013822826,0.51476926,0.00059024955,0.00061253586,0.000018031431,0.0020670162,0.0065669073,0.07451887,0.0006046032,0.0018296746,0.36549485],"study_design_scores_gemma":[0.0060013174,0.0010656902,0.14173749,0.00021029291,0.00027991517,0.00000457083,0.00027231773,0.83539397,0.013895772,0.000023326478,0.001065104,0.000050244904],"about_ca_topic_score_codex":0.0001452145,"about_ca_topic_score_gemma":0.000030988722,"teacher_disagreement_score":0.8288271,"about_ca_system_score_codex":0.0002805986,"about_ca_system_score_gemma":0.00048029938,"threshold_uncertainty_score":0.26693222},"labels":[],"label_agreement":null},{"id":"W4407489859","doi":"10.1117/12.3046948","title":"A study on the performance of U-Net modifications in retroperitoneal tumor segmentation","year":2025,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Net (polyhedron); Segmentation; Artificial intelligence; Mathematics; Geometry","score_opus":0.019139726075030505,"score_gpt":0.3249126988814192,"score_spread":0.3057729728063887,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407489859","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.983295,0.000010726399,0.00015198528,0.0049439496,0.00004521731,0.00036091148,3.0889655e-7,0.000011776605,0.0111801205],"genre_scores_gemma":[0.99750096,0.000005159765,0.00034340442,0.0008618104,0.0000127171725,0.000032927725,0.0000021268575,0.0000032531707,0.0012376207],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.999528,0.000039162354,0.00016168674,0.000088426576,0.000118466916,0.00006427879],"domain_scores_gemma":[0.99971175,0.00006546835,0.000027709251,0.0001562003,0.000023402914,0.000015466198],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028906917,0.000041360494,0.00009508236,0.00008606015,0.00003617556,0.0000055826704,0.00005670746,0.000008936396,0.00003370311],"category_scores_gemma":[0.00012457592,0.000024127243,0.00001543099,0.00022199734,0.000036555095,0.000017395269,0.000013649483,0.00017215154,0.0000044188896],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013688327,0.000996524,0.96626276,0.0000613323,0.000047597707,0.000009250105,0.0020309156,0.0006463259,0.015370875,0.004564355,0.0020407313,0.007832426],"study_design_scores_gemma":[0.0011938817,0.00038889388,0.9127676,0.00012593965,0.000028206196,0.0000032377393,0.0039615165,0.07666505,0.004614182,0.00002121045,0.00019059658,0.000039704904],"about_ca_topic_score_codex":0.00009847612,"about_ca_topic_score_gemma":0.000005301114,"teacher_disagreement_score":0.07601873,"about_ca_system_score_codex":0.000030461712,"about_ca_system_score_gemma":0.000039552568,"threshold_uncertainty_score":0.09838804},"labels":[],"label_agreement":null},{"id":"W4407490009","doi":"10.1117/12.3045828","title":"Predicting future lung cancer risk in low-dose CT screening patients with AI tools","year":2025,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Lung cancer; Medicine; Lung; Cancer; Computer science; Medical physics; Oncology; Radiology; Internal medicine","score_opus":0.003855484045460256,"score_gpt":0.28030234231139206,"score_spread":0.2764468582659318,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407490009","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98410684,0.00041838628,0.0059665944,0.004104081,0.0003136024,0.00044011872,0.000006968647,0.00009625596,0.004547147],"genre_scores_gemma":[0.9916635,0.00010092059,0.0032489207,0.0037211946,0.00026640494,0.0000321532,0.00003074761,0.000023344845,0.0009128262],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.998782,0.00005042707,0.0002689503,0.00030286657,0.00028216618,0.0003136358],"domain_scores_gemma":[0.9994193,0.000097324075,0.000079863894,0.00020554897,0.00008139276,0.00011659531],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028494408,0.00015690242,0.0002844498,0.0001783863,0.000106692954,0.000047012556,0.000094165654,0.000047030106,0.00014122725],"category_scores_gemma":[0.00033008138,0.00010968029,0.000047982692,0.00040484534,0.000044985605,0.00014175373,0.000056003562,0.0009006966,0.0000013823403],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012731004,0.000069590045,0.8989376,0.000117276555,0.00007829875,0.000028619479,0.00012558451,0.0009106379,0.000009900156,0.000060354374,0.0012300909,0.09830475],"study_design_scores_gemma":[0.0040284735,0.00004673346,0.87436616,0.0013402867,0.00010966058,0.0000026427542,0.00014160288,0.11789002,0.00003088419,0.000010463936,0.00192065,0.000112395384],"about_ca_topic_score_codex":0.0014907114,"about_ca_topic_score_gemma":0.00013840263,"teacher_disagreement_score":0.11697938,"about_ca_system_score_codex":0.00009565617,"about_ca_system_score_gemma":0.00012965294,"threshold_uncertainty_score":0.44726324},"labels":[],"label_agreement":null},{"id":"W4407490272","doi":"10.1117/12.3046813","title":"Is segmentation performance of deep-learning models affected by cancer type? A performance analysis on PET/CT","year":2025,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Segmentation; Artificial intelligence; Computer science; Deep learning; Cancer; Machine learning; Medicine; Internal medicine","score_opus":0.009121825037143311,"score_gpt":0.2998814277911506,"score_spread":0.2907596027540073,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407490272","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9872987,0.0003046096,0.0035492394,0.00071954844,0.00008632255,0.00016010649,0.0000015609365,0.000057950336,0.007821925],"genre_scores_gemma":[0.9896907,0.0010361044,0.001019218,0.0011707289,0.000019530798,0.0000160365,0.000050804316,0.000012772606,0.006984082],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99899286,0.000039906798,0.00025239933,0.00024437616,0.0002781381,0.00019231805],"domain_scores_gemma":[0.99948806,0.000053062784,0.000102445345,0.00017882398,0.00011402365,0.00006358623],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022710132,0.00013315024,0.00033849766,0.0003134079,0.00009440908,0.00001352313,0.00008106185,0.000014007006,0.0004091662],"category_scores_gemma":[0.000055146258,0.00010702223,0.000095842486,0.0010507787,0.00004913295,0.000095941665,0.000024766778,0.00034964844,0.000007708831],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00052385125,0.00034892728,0.6249078,0.00092757214,0.0023425263,0.000019819898,0.00056566205,0.15976398,0.025468368,0.00014697787,0.004515878,0.18046865],"study_design_scores_gemma":[0.0007719837,0.00021073582,0.028858282,0.00016682109,0.0006435041,0.0000062267254,0.0000657026,0.9545385,0.014300606,0.000004176265,0.00033837158,0.00009507713],"about_ca_topic_score_codex":0.00019966363,"about_ca_topic_score_gemma":0.000004228778,"teacher_disagreement_score":0.79477453,"about_ca_system_score_codex":0.00008898957,"about_ca_system_score_gemma":0.00005615894,"threshold_uncertainty_score":0.4480083},"labels":[],"label_agreement":null},{"id":"W4407490379","doi":"10.1117/12.3048815","title":"The search for CT imaging subtypes of colorectal liver metastases and the impacts of slice thickness","year":2025,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Computed tomography; Radiology; Medicine; Computer science","score_opus":0.008360731373403103,"score_gpt":0.30950455714002245,"score_spread":0.30114382576661936,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407490379","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96458864,0.005099712,0.005330164,0.019645508,0.00013097597,0.0006415419,0.0000067406904,0.000017791885,0.0045389025],"genre_scores_gemma":[0.9972919,0.00040945763,0.0011890611,0.0006349982,0.000021029515,0.000010175072,0.000002709686,0.0000066618777,0.00043396288],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993031,0.00009778659,0.00019306285,0.00010302722,0.00015354705,0.00014947746],"domain_scores_gemma":[0.9972178,0.0024035184,0.00005684167,0.0001432478,0.00013878447,0.000039827868],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016760284,0.00006872189,0.00023538055,0.000051883555,0.0001295924,0.000019762258,0.0001053984,0.000011295401,0.000012562255],"category_scores_gemma":[0.001129487,0.000030324361,0.00007693637,0.00013641865,0.0006240282,0.000029097499,0.00006888884,0.00017007776,2.5612906e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0076011266,0.00035070506,0.25355157,0.0030380052,0.0019058028,0.000036853362,0.0046961033,0.000098933255,0.054374266,0.3509194,0.021140784,0.30228645],"study_design_scores_gemma":[0.027674165,0.0006239963,0.22750026,0.0014207519,0.002463474,0.00047651242,0.010912011,0.4892994,0.20175382,0.004810011,0.032638278,0.0004273466],"about_ca_topic_score_codex":0.0008282297,"about_ca_topic_score_gemma":0.000020564543,"teacher_disagreement_score":0.48920044,"about_ca_system_score_codex":0.000009212237,"about_ca_system_score_gemma":0.000112071844,"threshold_uncertainty_score":0.22992578},"labels":[],"label_agreement":null},{"id":"W4407490603","doi":"10.1117/12.3046738","title":"Interpretable deep learning model for distinguishing tumor pseudoprogression from true progression using MRI imaging of glioblastoma patients","year":2025,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"CancerCare Manitoba; University of Manitoba","funders":"","keywords":"Glioblastoma; Artificial intelligence; Magnetic resonance imaging; Medicine; Radiology; Computer science; Cancer research","score_opus":0.006944710085044911,"score_gpt":0.3134703303684576,"score_spread":0.3065256202834127,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407490603","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.55161715,0.00026138293,0.4462141,0.00021900298,0.00023248115,0.00043024533,0.000003643372,0.0001028502,0.0009191433],"genre_scores_gemma":[0.8629788,0.00000622706,0.13628317,0.00028146678,0.00008341837,0.000023775305,0.00004507702,0.000039959636,0.0002580542],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981635,0.00005566862,0.0005842349,0.00046340103,0.0003374411,0.00039573832],"domain_scores_gemma":[0.99879193,0.00022839576,0.00030909,0.00024774508,0.00028002803,0.00014282146],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041735472,0.000232807,0.00052725594,0.0002319402,0.00024400592,0.000065846616,0.00017288809,0.00006551678,0.000032472934],"category_scores_gemma":[0.0018457876,0.00018631185,0.00016639836,0.00024136549,0.00010760793,0.00017105264,0.00019707395,0.00048096298,6.761769e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010862988,0.00044121596,0.71490365,0.00058796885,0.00012663002,0.000017386017,0.0010461529,0.014342042,0.01781565,0.0002198722,0.0004776752,0.24893545],"study_design_scores_gemma":[0.0023072525,0.00012105386,0.002342694,0.0030808197,0.00017514631,0.0000048938823,0.00018925029,0.9871837,0.0036232919,0.0005692172,0.00023874982,0.00016392216],"about_ca_topic_score_codex":0.00010159238,"about_ca_topic_score_gemma":0.0000029695811,"teacher_disagreement_score":0.9728417,"about_ca_system_score_codex":0.00011933722,"about_ca_system_score_gemma":0.00010631211,"threshold_uncertainty_score":0.7597577},"labels":[],"label_agreement":null},{"id":"W4407636543","doi":"10.1007/s00330-025-11454-y","title":"PI-CAI: a landmark AI study for prostate cancer detection on MRI","year":2025,"lang":"en","type":"editorial","venue":"European Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sinai Health System; University of Toronto","funders":"","keywords":"Neuroradiology; Medicine; Prostate cancer; Landmark; Interventional radiology; Magnetic resonance imaging; Ultrasound; Radiology; Prostate; Cancer detection; Cancer; Nuclear medicine; Medical physics; Neurology; Artificial intelligence; Internal medicine; Computer science","score_opus":0.007347612824828573,"score_gpt":0.3185114875799718,"score_spread":0.3111638747551432,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407636543","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004785039,0.00073374546,0.00271988,0.0030773284,0.97790664,0.0026981279,0.00015517439,0.00027504654,0.0076490287],"genre_scores_gemma":[0.01596325,0.0008720382,0.0002265489,0.0022254752,0.949179,0.0003161887,0.0006167924,0.00021690365,0.030383812],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972676,0.0006705729,0.000481223,0.000813869,0.0003055734,0.00046117842],"domain_scores_gemma":[0.99810797,0.00082878914,0.00022516462,0.0004735626,0.00020681691,0.00015766874],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013061531,0.000386748,0.00084315334,0.00030370394,0.00017239574,0.00003925763,0.00025411992,0.00026873988,0.000040028874],"category_scores_gemma":[0.002789744,0.00031324307,0.00018839812,0.00014968473,0.00010403177,0.000021727456,0.000083659754,0.0021056647,0.000039323953],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001190867,0.00018627579,0.0006798297,0.0002499358,0.00037688977,0.00023308079,0.00033279098,0.00008665475,0.00008262414,0.0000060856364,0.9515128,0.04506216],"study_design_scores_gemma":[0.0048992448,0.0027614392,0.0013093193,0.00034641902,0.00045420686,0.000019898223,0.00003702571,0.0007768685,0.000011360138,0.000019763746,0.9891052,0.00025922604],"about_ca_topic_score_codex":0.00013202101,"about_ca_topic_score_gemma":0.000035827525,"teacher_disagreement_score":0.04480293,"about_ca_system_score_codex":0.00021869913,"about_ca_system_score_gemma":0.00032810794,"threshold_uncertainty_score":0.999932},"labels":[],"label_agreement":null},{"id":"W4407642482","doi":"10.3390/applbiosci4010011","title":"SALM: A Unified Model for 2D and 3D Region of Interest Segmentation in Lung CT Scans Using Vision Transformers","year":2025,"lang":"en","type":"article","venue":"Applied Biosciences","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"Alliance de recherche numérique du Canada; New Brunswick Innovation Foundation","keywords":"Segmentation; Transformer; Computer vision; Artificial intelligence; Computer science; Engineering; Electrical engineering","score_opus":0.035068421098630925,"score_gpt":0.34721164320129577,"score_spread":0.3121432221026649,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407642482","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.78223807,0.00005179897,0.21597734,0.000817699,0.000048479134,0.00032788745,0.0000010259453,0.00000846128,0.0005292243],"genre_scores_gemma":[0.98932964,0.000064359316,0.010262604,0.00027970033,0.000007758294,0.0000093800845,0.0000044182852,0.0000037178745,0.00003842279],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994104,0.0000079437605,0.00018531394,0.0001856605,0.00008724841,0.00012344672],"domain_scores_gemma":[0.9997952,0.000050949042,0.00005063013,0.000050385323,0.000015430858,0.000037406608],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003010493,0.000065006294,0.00014631993,0.00019994969,0.000062135776,0.000015170203,0.000052782863,0.000023247541,7.735614e-7],"category_scores_gemma":[0.000032078693,0.00005084921,0.00001910599,0.0002879764,0.0002027979,0.000058792903,0.000013131325,0.000078518206,3.0625337e-8],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038211237,0.00015885205,0.01434948,0.00083494675,0.00002738134,0.0000053558756,0.0020735923,0.0068777693,0.7591561,0.008205186,0.00016986385,0.20775935],"study_design_scores_gemma":[0.0010175725,0.000048534428,0.0016308926,0.00023479629,0.000035901205,0.0000051777033,0.0007609627,0.9903276,0.00510873,0.0007485434,0.000028481,0.000052806867],"about_ca_topic_score_codex":0.000088963214,"about_ca_topic_score_gemma":0.00003136225,"teacher_disagreement_score":0.9834498,"about_ca_system_score_codex":0.000036132515,"about_ca_system_score_gemma":0.00008928606,"threshold_uncertainty_score":0.20735706},"labels":[],"label_agreement":null},{"id":"W4407677715","doi":"10.3390/curroncol32020116","title":"MRI in Oral Tongue Squamous Cell Carcinoma: A Radiomic Approach in the Local Recurrence Evaluation","year":2025,"lang":"en","type":"article","venue":"Current Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Cancer Institute","keywords":"Medicine; Basal cell; Tongue; Tongue Neoplasm; Pathology; Radiology; Dermatology","score_opus":0.056766496415875084,"score_gpt":0.40429284385643205,"score_spread":0.347526347440557,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407677715","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95494074,0.006167088,0.013009563,0.006209268,0.001556879,0.0012506525,0.0000015984044,0.000022996895,0.016841222],"genre_scores_gemma":[0.9984285,0.00008575674,0.00053641427,0.0005540598,0.00011664073,0.00016988508,0.00006134034,0.000008479218,0.000038917566],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979103,0.0007013677,0.00039806025,0.00036663687,0.0002856637,0.0003379703],"domain_scores_gemma":[0.9992013,0.00031960264,0.0000801435,0.00027143813,0.000064607724,0.00006288678],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002498634,0.00014740456,0.00036912312,0.00032756463,0.000047234767,0.000013792401,0.00024451243,0.00012545344,0.00003060127],"category_scores_gemma":[0.0004032383,0.000108647684,0.00006458386,0.0006027269,0.0001974016,0.000039195773,0.000059220652,0.0011558364,0.000009339468],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002077831,0.002260663,0.3624487,0.0003936984,0.000007131563,0.0000675221,0.0034324029,0.0016368808,0.00011877025,0.0010798309,0.0153670525,0.6129796],"study_design_scores_gemma":[0.009125612,0.00034955726,0.25494003,0.000117878924,0.00014524178,0.00007636858,0.00138563,0.6909746,0.000029397548,0.0006334443,0.042049438,0.00017281403],"about_ca_topic_score_codex":0.0001530407,"about_ca_topic_score_gemma":0.00005148897,"teacher_disagreement_score":0.6893377,"about_ca_system_score_codex":0.00064731605,"about_ca_system_score_gemma":0.00068172894,"threshold_uncertainty_score":0.50215983},"labels":[],"label_agreement":null},{"id":"W4407699726","doi":"10.1200/jco.2025.43.5_suppl.399","title":"Decipher score as a predictor of response to treatment intensification in the NRG Oncology-RTOG 0534 (SPPORT) phase III randomized post-prostatectomy salvage radiotherapy trial.","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University Health Network; McMaster University; McGill University Health Centre; Centre hospitalier universitaire de Québec","funders":"National Institutes of Health","keywords":"Medicine; Prostatectomy; DECIPHER; Oncology; Internal medicine; Radiation therapy; Randomized controlled trial; Prostate cancer; Cancer; Bioinformatics","score_opus":0.06896096030624796,"score_gpt":0.505670688163185,"score_spread":0.43670972785693696,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407699726","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9003344,0.0006508283,0.0022991423,0.0920716,0.0014306669,0.0022094809,0.0000033478257,0.000011937311,0.0009886014],"genre_scores_gemma":[0.9707023,0.0014916585,0.0052104383,0.021013618,0.0007158949,0.000093443174,0.000007532374,0.000023044606,0.0007420868],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.99030924,0.0044474322,0.0042111995,0.00029411484,0.0004511351,0.00028689505],"domain_scores_gemma":[0.978791,0.017650492,0.002129803,0.0004099183,0.0006800608,0.00033872275],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.024708722,0.00021745823,0.0033061574,0.0004934546,0.00004923881,0.00001528816,0.00033357722,0.00039232062,0.0001398263],"category_scores_gemma":[0.04829718,0.00011816786,0.0008610106,0.00042908793,0.00054200814,0.00006505784,0.000034268738,0.0012838343,0.000004598848],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.7858779,0.004507106,0.0014471492,0.000014667061,0.0006157376,0.00064676563,0.0015625594,0.000024583209,0.0026522172,0.00010781418,0.0024562955,0.20008722],"study_design_scores_gemma":[0.82646716,0.041766666,0.011265266,0.0002851459,0.0007246014,0.00018692638,0.0006627632,0.0009919988,0.00010091421,0.000338595,0.11712004,0.00008990707],"about_ca_topic_score_codex":0.00012273958,"about_ca_topic_score_gemma":0.000022500699,"teacher_disagreement_score":0.19999732,"about_ca_system_score_codex":0.000547061,"about_ca_system_score_gemma":0.0047113667,"threshold_uncertainty_score":0.9597194},"labels":[],"label_agreement":null},{"id":"W4407701538","doi":"10.1200/jco.2025.43.5_suppl.647","title":"Machine learning model integrating CT radiomics and circulating microRNAs to predict residual disease histology in metastatic non-seminoma testicular cancer (mNSTC).","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; BC Cancer Agency","funders":"","keywords":"Medicine; Seminoma; Radiomics; Testicular cancer; Histology; Disease; Cancer; Oncology; Nomogram; Pathology; Internal medicine; Radiology; Chemotherapy","score_opus":0.04860227002937559,"score_gpt":0.4369785461505426,"score_spread":0.388376276121167,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407701538","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95877504,0.0031298003,0.019083451,0.017546322,0.00064814626,0.00027282684,0.0000038390313,0.000014474989,0.00052609557],"genre_scores_gemma":[0.9425304,0.0006754159,0.051458325,0.004727638,0.00032900405,0.00001039945,0.000005145405,0.000026641621,0.00023702339],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99604404,0.0005264336,0.002427882,0.0003573967,0.0002753665,0.00036889614],"domain_scores_gemma":[0.99508435,0.0028590476,0.0010160649,0.00016946194,0.00022411079,0.0006469892],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0044918023,0.0002193813,0.0016934691,0.00046937334,0.00009265524,0.000020112404,0.0001957076,0.00013059839,0.000018199402],"category_scores_gemma":[0.028118957,0.00017261924,0.0002395998,0.00029368864,0.00026309333,0.000084345156,0.00013685248,0.0027312364,0.0000011063595],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012930909,0.00043299407,0.734511,0.00017637359,0.0003046843,0.002764302,0.00027333072,0.02912017,0.0015461382,0.00015503823,0.00084748596,0.22857538],"study_design_scores_gemma":[0.0071897064,0.0013540381,0.19609605,0.0011500504,0.00086347584,0.00071611436,0.00015154583,0.7868795,0.000021975782,0.0010567674,0.004341906,0.00017887712],"about_ca_topic_score_codex":0.00020559729,"about_ca_topic_score_gemma":0.00005704809,"teacher_disagreement_score":0.75775933,"about_ca_system_score_codex":0.00035923804,"about_ca_system_score_gemma":0.0023784323,"threshold_uncertainty_score":0.9995695},"labels":[],"label_agreement":null},{"id":"W4407798126","doi":"10.3389/fdata.2025.1515341","title":"A review of AI-based radiogenomics in neurodegenerative disease","year":2025,"lang":"en","type":"review","venue":"Frontiers in Big Data","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba; University of Winnipeg","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Radiogenomics; Disease; Genomics; Medical diagnosis; Radiomics; Precision medicine; Data science; Artificial intelligence; Computer science; Medicine; Pathology; Biology; Genome; Genetics","score_opus":0.0713215444427707,"score_gpt":0.37826892134799045,"score_spread":0.3069473769052198,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407798126","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[3.3144298e-7,0.9877558,0.007301924,0.0012355458,0.0013600898,0.0013216685,0.0008575045,0.000014067847,0.00015309396],"genre_scores_gemma":[4.5553344e-7,0.98100746,0.007724784,0.0037853133,0.00019799432,0.0000615421,0.007042616,0.00004370089,0.00013614171],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9971842,0.00044094704,0.0010694254,0.0007650381,0.00024958316,0.0002907951],"domain_scores_gemma":[0.9973592,0.00016037835,0.00031462143,0.0019310749,0.00004051834,0.00019419647],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010495227,0.0003655883,0.00275646,0.00074734114,0.000019213057,0.0000121742205,0.00096385536,0.00014323776,0.000011942377],"category_scores_gemma":[0.0032964584,0.000305598,0.0002517557,0.0009725744,0.0001428907,0.00005154521,0.00034293623,0.0012061786,0.0000020749894],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001845764,0.000084247586,0.0005388129,0.2208122,0.000047770063,0.00012973417,0.0000031889595,0.0000039244096,3.3889922e-8,0.000007767875,0.11003986,0.668314],"study_design_scores_gemma":[0.00044409733,0.000013729056,0.000017380004,0.29877692,0.0007708638,0.000004123503,0.0000011588372,0.002653567,6.896117e-8,0.000013735901,0.6971561,0.00014830238],"about_ca_topic_score_codex":0.000033336823,"about_ca_topic_score_gemma":0.000003739951,"teacher_disagreement_score":0.6681657,"about_ca_system_score_codex":0.00020513847,"about_ca_system_score_gemma":0.0026760725,"threshold_uncertainty_score":0.9999396},"labels":[],"label_agreement":null},{"id":"W4407823567","doi":"10.1615/critrevbiomedeng.2025057015","title":"State of the Practice for Medical Imaging Software Based on Open Source Repositories","year":2025,"lang":"en","type":"review","venue":"Critical Reviews in Biomedical Engineering","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Joseph’s Healthcare Hamilton; McMaster University Medical Centre; McMaster University","funders":"","keywords":"Open source software; Open source; Software; Computer science; Medical imaging; State (computer science); Software engineering; Medical physics; Data science; Medicine; Operating system; Artificial intelligence; Programming language","score_opus":0.01759314291820541,"score_gpt":0.3950369578077944,"score_spread":0.377443814889589,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407823567","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.5657363e-7,0.85156846,0.13910261,0.005221127,0.0014346675,0.0023437506,0.000024576639,0.000057223475,0.0002474153],"genre_scores_gemma":[0.0000074804016,0.96840787,0.027685056,0.0023913004,0.00044915665,0.00067867636,0.00006621388,0.000103345956,0.00021090316],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99499565,0.0004361265,0.0021332756,0.0007211406,0.0010784433,0.00063537486],"domain_scores_gemma":[0.98439276,0.013526758,0.00034243532,0.0009917828,0.00016923169,0.0005770463],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0044962238,0.00055627414,0.0032333722,0.00037343975,0.000096846,0.00008605488,0.0012962272,0.0003417,0.000040241805],"category_scores_gemma":[0.2528733,0.00034371257,0.000837556,0.0011084354,0.000478949,0.00009122232,0.0005795081,0.0022719058,0.0000045981906],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023326571,0.00026540965,0.000005220905,0.084970556,0.000041166495,0.000080459184,0.000014070792,0.00001798816,5.716403e-7,0.00041720812,0.0025564632,0.91160756],"study_design_scores_gemma":[0.00052013836,0.00006972897,0.0000017615553,0.20031455,0.0006108567,0.00010684015,0.0000032720266,0.01814396,9.071372e-7,0.00003059837,0.7799717,0.00022565444],"about_ca_topic_score_codex":0.000017427763,"about_ca_topic_score_gemma":3.4014013e-7,"teacher_disagreement_score":0.9113819,"about_ca_system_score_codex":0.00027276532,"about_ca_system_score_gemma":0.0015164247,"threshold_uncertainty_score":0.9999015},"labels":[],"label_agreement":null},{"id":"W4407868563","doi":"10.1101/2025.02.19.635300","title":"Artificial intelligence-enabled automated analysis of transmission electron micrographs to evaluate chemotherapy impact on mitochondrial morphology in triple negative breast cancer","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Triple-negative breast cancer; Electron micrographs; Micrograph; Morphology (biology); Transmission electron microscopy; Chemotherapy; Breast cancer; Materials science; Cancer; Oncology; Biology; Internal medicine; Medicine; Nanotechnology; Physics; Electron microscope; Scanning electron microscope; Optics; Composite material; Zoology","score_opus":0.011602503191711902,"score_gpt":0.3170246130433978,"score_spread":0.3054221098516859,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407868563","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9907709,0.00030037528,0.0039005696,0.0023965247,0.0005856794,0.0014843269,0.00030456032,0.00025076975,0.000006315268],"genre_scores_gemma":[0.9937153,0.00052456843,0.004647879,0.00061257055,0.00021696261,0.00020226481,0.0000034814964,0.00007018611,0.0000067717165],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9963467,0.00034310587,0.0010340551,0.0010861817,0.00050825824,0.0006816959],"domain_scores_gemma":[0.99776906,0.00015885789,0.000439278,0.0007762843,0.0004869323,0.00036959414],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008267878,0.00060570386,0.0017063909,0.0025660659,0.000072613475,0.000056696776,0.00038940963,0.00053885486,0.00024954707],"category_scores_gemma":[0.0002650302,0.00052464247,0.00059740944,0.0039051694,0.00013777263,0.00004264829,0.00008670727,0.0013761461,0.0000043315727],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0038954313,0.0007285716,0.009538932,0.0002764712,0.0032385804,0.00005964926,0.00012491785,0.022905318,0.9583816,0.000041179894,0.00036122964,0.00044810542],"study_design_scores_gemma":[0.0016071463,0.0004656528,0.35607687,0.00180659,0.002710511,8.644493e-8,0.0000067006467,0.22045879,0.4160612,0.00001064327,0.00009915014,0.0006966614],"about_ca_topic_score_codex":0.0018302035,"about_ca_topic_score_gemma":0.000017081351,"teacher_disagreement_score":0.54232043,"about_ca_system_score_codex":0.00070472836,"about_ca_system_score_gemma":0.001369405,"threshold_uncertainty_score":0.9997205},"labels":[],"label_agreement":null},{"id":"W4407868937","doi":"10.5194/gmd-2024-175-rc1","title":"Comment on gmd-2024-175","year":2025,"lang":"en","type":"peer-review","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Defence Research and Development Canada; Memorial University of Newfoundland","funders":"","keywords":"Statistics; Environmental science; Mathematics","score_opus":0.022588663572809153,"score_gpt":0.3638109593603314,"score_spread":0.3412222957875223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407868937","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[5.6214344e-7,0.013334466,0.00044010044,0.5748466,0.003270509,0.00044613174,0.000020983774,0.000080466045,0.40756014],"genre_scores_gemma":[0.0000037833938,0.013324782,0.0010834831,0.38884923,0.00056314515,0.000029460449,0.0006437401,0.000026480842,0.5954759],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979843,0.00007620364,0.0004644752,0.0004832521,0.0006632044,0.00032858702],"domain_scores_gemma":[0.9985636,0.00024636777,0.00012317623,0.00070446753,0.00011776269,0.00024466682],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006272223,0.0003560254,0.0010406711,0.00020683337,0.0000677645,0.000025895977,0.0002375835,0.0002186343,0.00616194],"category_scores_gemma":[0.00095439027,0.00025362076,0.00033110345,0.00020437341,0.00006140512,0.000010788955,0.00013232097,0.0019319893,0.00033339194],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010839461,0.00010532675,0.000023173709,0.0053281053,0.00014531243,0.00007508759,0.000004283844,8.9331456e-7,9.786031e-7,0.00073381595,0.9248757,0.068696484],"study_design_scores_gemma":[0.00060898793,0.0001493543,0.00001846161,0.022947382,0.0005293412,0.00002493114,0.000005339394,0.0003906017,0.0000063034377,0.000059597278,0.9750524,0.00020726769],"about_ca_topic_score_codex":0.00015306995,"about_ca_topic_score_gemma":0.0000028757438,"teacher_disagreement_score":0.18791576,"about_ca_system_score_codex":0.00016995592,"about_ca_system_score_gemma":0.0003107305,"threshold_uncertainty_score":0.9999916},"labels":[],"label_agreement":null},{"id":"W4407898368","doi":"10.2196/64000","title":"Leveraging Digital Twins for Stratification of Patients with Breast Cancer and Treatment Optimization in Geriatric Oncology: Multivariate Clustering Analysis","year":2025,"lang":"en","type":"article","venue":"JMIR Cancer","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Preprint; Breast cancer; Medicine; Oncology; Multivariate analysis; Internal medicine; Multivariate statistics; Geriatric oncology; Stratification (seeds); Risk stratification; Cancer; Computer science; World Wide Web; Biology; Machine learning","score_opus":0.010515804625779328,"score_gpt":0.32326744800941143,"score_spread":0.3127516433836321,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407898368","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9339441,0.000109708,0.06344921,0.0014419858,0.00006171768,0.00075832044,0.000067140274,0.000013662586,0.00015416023],"genre_scores_gemma":[0.99615663,0.000083451865,0.003163497,0.000075418495,0.000031663192,0.0002700092,0.000084538195,0.000008362917,0.0001264202],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99943995,0.000011073381,0.00018752992,0.00018485464,0.0000720835,0.00010450602],"domain_scores_gemma":[0.9996576,0.000041402865,0.00010027963,0.000079843994,0.000084886546,0.000035996523],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000051300707,0.000083273095,0.00024919875,0.0002369061,0.000031618638,0.000018300134,0.000023450459,0.00003682975,0.000016826352],"category_scores_gemma":[0.000014032788,0.00006225115,0.000035901077,0.00040096432,0.00002868449,0.00007693544,0.0000105306235,0.000057163492,3.4115352e-8],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041636956,0.00017663775,0.71805793,0.00007860665,0.00033326243,6.7430597e-7,0.0005418264,0.12783237,0.00008230639,0.000006532165,0.000012582431,0.15246089],"study_design_scores_gemma":[0.0028873982,0.00007184343,0.6351513,0.00008539181,0.00031691126,2.609897e-7,0.000051320556,0.36118546,0.00001420424,0.000002739878,0.00018586757,0.00004725285],"about_ca_topic_score_codex":0.0006574455,"about_ca_topic_score_gemma":0.00014803765,"teacher_disagreement_score":0.2333531,"about_ca_system_score_codex":0.00033961103,"about_ca_system_score_gemma":0.00014941784,"threshold_uncertainty_score":0.25385284},"labels":[],"label_agreement":null},{"id":"W4407905767","doi":"10.5194/gmd-2024-175-rc2","title":"Comment on gmd-2024-175","year":2025,"lang":"en","type":"peer-review","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Defence Research and Development Canada; Memorial University of Newfoundland","funders":"","keywords":"Environmental science; Mathematics; Statistics","score_opus":0.022588663572809153,"score_gpt":0.3638109593603314,"score_spread":0.3412222957875223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407905767","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[5.6214344e-7,0.013334466,0.00044010044,0.5748466,0.003270509,0.00044613174,0.000020983774,0.000080466045,0.40756014],"genre_scores_gemma":[0.0000037833938,0.013324782,0.0010834831,0.38884923,0.00056314515,0.000029460449,0.0006437401,0.000026480842,0.5954759],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979843,0.00007620364,0.0004644752,0.0004832521,0.0006632044,0.00032858702],"domain_scores_gemma":[0.9985636,0.00024636777,0.00012317623,0.00070446753,0.00011776269,0.00024466682],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006272223,0.0003560254,0.0010406711,0.00020683337,0.0000677645,0.000025895977,0.0002375835,0.0002186343,0.00616194],"category_scores_gemma":[0.00095439027,0.00025362076,0.00033110345,0.00020437341,0.00006140512,0.000010788955,0.00013232097,0.0019319893,0.00033339194],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010839461,0.00010532675,0.000023173709,0.0053281053,0.00014531243,0.00007508759,0.000004283844,8.9331456e-7,9.786031e-7,0.00073381595,0.9248757,0.068696484],"study_design_scores_gemma":[0.00060898793,0.0001493543,0.00001846161,0.022947382,0.0005293412,0.00002493114,0.000005339394,0.0003906017,0.0000063034377,0.000059597278,0.9750524,0.00020726769],"about_ca_topic_score_codex":0.00015306995,"about_ca_topic_score_gemma":0.0000028757438,"teacher_disagreement_score":0.18791576,"about_ca_system_score_codex":0.00016995592,"about_ca_system_score_gemma":0.0003107305,"threshold_uncertainty_score":0.9999916},"labels":[],"label_agreement":null},{"id":"W4407916116","doi":"10.3390/cancers17050778","title":"Editorial for Special Issue “Image Analysis and Machine Learning in Cancers”","year":2025,"lang":"en","type":"editorial","venue":"Cancers","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"SAIT Polytechnic","funders":"","keywords":"Computer science; Artificial intelligence; Machine learning","score_opus":0.005292104878603426,"score_gpt":0.3010226206648843,"score_spread":0.29573051578628085,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407916116","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000082205435,0.0010659772,0.0009219724,0.0007088155,0.99253535,0.00053976313,0.00022543894,0.00006508451,0.0038553902],"genre_scores_gemma":[0.000048365804,0.0021907245,0.0011006894,0.0001639198,0.9840435,0.000112916685,0.0012818261,0.000060306375,0.010997773],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99739856,0.00008072243,0.0005133503,0.000790409,0.0006976801,0.00051926635],"domain_scores_gemma":[0.99809164,0.00088589883,0.00024808713,0.00027920865,0.00025556365,0.00023962375],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.00076600304,0.00040193793,0.0013194114,0.00078589405,0.0001451243,0.0000904942,0.00019920203,0.0007336181,0.00026286693],"category_scores_gemma":[0.0046514757,0.00039529876,0.00030925177,0.00079604593,0.00019247357,0.00006736027,0.00008711676,0.0025756813,0.0000031535367],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00056339684,0.000007812257,0.0006119001,0.0005383631,0.0007132072,0.000023716826,0.00021675353,0.0007888249,0.000028666109,0.0000044845033,0.9832004,0.013302491],"study_design_scores_gemma":[0.0034428774,0.00018107449,0.000046949037,0.0004099021,0.0019742926,6.249367e-7,0.00006036358,0.014413512,0.000011841388,0.000026356249,0.9791131,0.00031908983],"about_ca_topic_score_codex":0.008760778,"about_ca_topic_score_gemma":0.0018050078,"teacher_disagreement_score":0.013624687,"about_ca_system_score_codex":0.003322863,"about_ca_system_score_gemma":0.0039672353,"threshold_uncertainty_score":0.9998499},"labels":[],"label_agreement":null},{"id":"W4407953145","doi":"10.1145/3701551.3703557","title":"Fusion Matters: Learning Fusion in Deep Click-through Rate Prediction Models","year":2025,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Fusion; Computer science; Deep learning; Artificial intelligence; Click-through rate; Machine learning; Information retrieval; Philosophy","score_opus":0.01152382472462066,"score_gpt":0.2902368676375455,"score_spread":0.27871304291292487,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407953145","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.52284753,0.00037093952,0.3848906,0.030407302,0.0006183087,0.00048404626,6.6495267e-7,0.00033629476,0.060044322],"genre_scores_gemma":[0.97297996,0.0006340866,0.0064695706,0.011534467,0.00013735934,0.000021743725,0.00005596175,0.00002679836,0.008140074],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99866116,0.0001246266,0.00037759033,0.000341474,0.0002044669,0.00029069738],"domain_scores_gemma":[0.99950856,0.00010697222,0.000060685947,0.00019569113,0.000048178128,0.0000799407],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006157828,0.00014915079,0.00027869985,0.00023246232,0.0001225959,0.000033525615,0.00008013511,0.00011874348,0.00023724773],"category_scores_gemma":[0.00021926727,0.00012348835,0.000071421884,0.00038781753,0.000054659784,0.00020550063,0.00009681067,0.0007497238,0.000029788021],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013579443,0.0010588327,0.22861159,0.0011992952,0.0002242353,0.00037745625,0.0065366984,0.16448344,0.112664476,0.018696629,0.04180738,0.422982],"study_design_scores_gemma":[0.0023858019,0.00010870383,0.014755764,0.00059869105,0.000050195868,0.000021428868,0.0004572159,0.95396054,0.0005021515,0.0032154347,0.023820793,0.0001233083],"about_ca_topic_score_codex":0.0003864744,"about_ca_topic_score_gemma":0.000015826483,"teacher_disagreement_score":0.78947705,"about_ca_system_score_codex":0.00011723053,"about_ca_system_score_gemma":0.000055604567,"threshold_uncertainty_score":0.50357085},"labels":[],"label_agreement":null},{"id":"W4407963344","doi":"10.3390/app15052516","title":"Review of the AI-Based Analysis of Abdominal Organs from Routine CT Scans","year":2025,"lang":"en","type":"article","venue":"Applied Sciences","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Medicine; Nuclear medicine","score_opus":0.009194561854094983,"score_gpt":0.31735213863946493,"score_spread":0.3081575767853699,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407963344","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8629958,0.013264474,0.025313606,0.04890795,0.0002875356,0.000725735,0.00003540957,0.00004134736,0.04842812],"genre_scores_gemma":[0.98837405,0.00024436982,0.0018913894,0.009384425,0.000015674874,0.0000045324923,0.000008156555,0.0000023825746,0.000075026255],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9990346,0.000034434954,0.00029723768,0.00018975469,0.0003303541,0.000113656264],"domain_scores_gemma":[0.999322,0.0001833726,0.00014523412,0.00026110158,0.000051526316,0.00003679119],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00085314707,0.000069133035,0.00039782637,0.00015194179,0.00008295581,0.000006920883,0.00029951707,0.000013798653,0.0002406172],"category_scores_gemma":[0.00034388778,0.000039292958,0.00012787295,0.002700319,0.000604341,0.000012958861,0.000042484364,0.00014119914,9.417805e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010571427,0.00049090135,0.7607038,0.0041222833,0.001799229,0.000006847445,0.00044214068,0.003976516,0.07554415,0.018165529,0.017442804,0.11720008],"study_design_scores_gemma":[0.0037690864,0.00020391749,0.4988544,0.017909786,0.017523134,0.000004940152,0.000867605,0.327703,0.10045745,0.002231466,0.02996002,0.0005151942],"about_ca_topic_score_codex":0.00034991992,"about_ca_topic_score_gemma":0.000025285992,"teacher_disagreement_score":0.32372648,"about_ca_system_score_codex":0.000014963735,"about_ca_system_score_gemma":0.00028771796,"threshold_uncertainty_score":0.26345897},"labels":[],"label_agreement":null},{"id":"W4408038439","doi":"10.18280/ts.420112","title":"UMS-Net++: Modified SwinTransformer for Cardiac MRI Segmentation and Classification","year":2025,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Segmentation; Net (polyhedron); Computer science; Artificial intelligence; Pattern recognition (psychology); Mathematics","score_opus":0.015844364952194233,"score_gpt":0.30167613111019814,"score_spread":0.28583176615800393,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408038439","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27926058,0.00036710317,0.69746387,0.015054329,0.00030571027,0.0014520459,0.00001666076,0.00008046566,0.005999231],"genre_scores_gemma":[0.9917333,0.00013869011,0.005680602,0.0012722409,0.00016563889,0.00013861232,0.00014446155,0.000012478132,0.00071394973],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992127,0.00002578582,0.00023126409,0.00021072598,0.00015430234,0.00016523477],"domain_scores_gemma":[0.99966365,0.00008306814,0.00004108271,0.00007992192,0.000053991946,0.0000783008],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003488678,0.00010253683,0.00018472577,0.0000977106,0.00010385462,0.00003233468,0.000037345515,0.00004769643,0.000047442252],"category_scores_gemma":[0.0000282026,0.000089557056,0.00006919427,0.00008857549,0.00005361264,0.00006054749,0.0000068604336,0.000116777715,0.0000024216313],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00077417516,0.00030042374,0.019364407,0.0008191061,0.00055259885,0.000003981029,0.0012153626,0.00044395513,0.3650685,0.029710773,0.02328486,0.55846184],"study_design_scores_gemma":[0.014272661,0.0007836823,0.19538042,0.0004776043,0.0013769545,0.000012268361,0.0010601599,0.641581,0.020391483,0.0033081917,0.1208242,0.0005314049],"about_ca_topic_score_codex":0.000012391189,"about_ca_topic_score_gemma":7.3162465e-7,"teacher_disagreement_score":0.71247274,"about_ca_system_score_codex":0.00005537541,"about_ca_system_score_gemma":0.000053101085,"threshold_uncertainty_score":0.36520305},"labels":[],"label_agreement":null},{"id":"W4408040739","doi":"10.18280/ts.420127","title":"Adaptive 3D Trans-ResUnet and Multiscale Trans-RAN for Enhanced Kidney Tumor Segmentation and Classification","year":2025,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Segmentation; Ran; Computer science; Artificial intelligence; Pattern recognition (psychology); Computer network","score_opus":0.015704575455364432,"score_gpt":0.29406146314651793,"score_spread":0.2783568876911535,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408040739","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37335718,0.00021334035,0.61709416,0.007221968,0.00009906803,0.001216122,0.00003722879,0.000054032113,0.00070690474],"genre_scores_gemma":[0.9814284,0.00007083379,0.015931208,0.001883172,0.0000757804,0.0001441701,0.00010743334,0.000014500064,0.0003445137],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990606,0.000042704996,0.00027031754,0.00029338634,0.00015295386,0.00018007019],"domain_scores_gemma":[0.99953854,0.00012547888,0.00005609428,0.0000702984,0.00004753256,0.00016207191],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002882465,0.00013634,0.00021995849,0.00010029327,0.00012429782,0.000030400966,0.000038898957,0.00004339827,0.00006499887],"category_scores_gemma":[0.000054186854,0.000122282,0.000045597502,0.00008544209,0.00011386595,0.00007741983,0.0000053418175,0.00014486143,5.846726e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010376414,0.00022462057,0.0024323247,0.0004945733,0.00017448794,0.0000048256547,0.0028865198,0.000054367378,0.7552362,0.000966013,0.0018319172,0.23465653],"study_design_scores_gemma":[0.03376919,0.0017406674,0.15314357,0.0011883772,0.0012150034,0.000031039515,0.0022984063,0.7267983,0.05980605,0.000944824,0.018450232,0.0006143442],"about_ca_topic_score_codex":0.000020750167,"about_ca_topic_score_gemma":0.0000056051904,"teacher_disagreement_score":0.72674394,"about_ca_system_score_codex":0.00003774642,"about_ca_system_score_gemma":0.00005965891,"threshold_uncertainty_score":0.49865153},"labels":[],"label_agreement":null},{"id":"W4408062444","doi":"10.18280/ts.420137","title":"Advanced Lung Cancer Segmentation Using Bilateral UNet and Hybrid Classification Using CT Images","year":2025,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Segmentation; Medicine; Lung cancer; Computer science; Radiology; Artificial intelligence; Lung; Pattern recognition (psychology); Oncology; Internal medicine","score_opus":0.017898176968242453,"score_gpt":0.3460526444306708,"score_spread":0.3281544674624283,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408062444","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9362248,0.0006351802,0.061070103,0.001336552,0.00017706187,0.0003501777,0.0000074036902,0.000041086827,0.00015763874],"genre_scores_gemma":[0.9870565,0.00010753991,0.011695844,0.0008117096,0.00012110199,0.000016409203,0.000039140272,0.000015230342,0.00013652343],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990727,0.00004314383,0.00026216815,0.00024933674,0.00018283517,0.00018987352],"domain_scores_gemma":[0.9996674,0.000033271543,0.00009169365,0.00008358936,0.00004845185,0.00007560639],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020951667,0.00012827398,0.0001859736,0.00014121682,0.00014162983,0.00004942244,0.00004130478,0.000016544313,0.00012109227],"category_scores_gemma":[0.000020536858,0.00011550815,0.000038295755,0.0001319115,0.0000705147,0.00013995763,0.000022928303,0.00016120895,4.0580787e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011200093,0.00007199888,0.11618232,0.0002690342,0.00013006854,0.000031271917,0.00015764682,0.005322061,0.77692074,0.00010538538,0.0004077798,0.10028969],"study_design_scores_gemma":[0.002343946,0.00003876041,0.05190021,0.0004764952,0.00030709768,0.00004630975,0.00012402616,0.9294736,0.01439675,0.00006026229,0.0006922728,0.0001402961],"about_ca_topic_score_codex":0.00015571421,"about_ca_topic_score_gemma":0.0000013334334,"teacher_disagreement_score":0.9241515,"about_ca_system_score_codex":0.00018214696,"about_ca_system_score_gemma":0.000093120056,"threshold_uncertainty_score":0.47102857},"labels":[],"label_agreement":null},{"id":"W4408148355","doi":"10.1101/2025.02.28.25322740","title":"Automated diagnosis of usual interstitial pneumonia on chest CT via the mean curvature of isophotes","year":2025,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakeshore General Hospital; Université de Montréal; McGill University Health Centre; Centre Hospitalier de l’Université de Montréal; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Medicine; Pneumonia; Radiology; Nuclear medicine; Internal medicine","score_opus":0.01410094897507485,"score_gpt":0.3067367028327824,"score_spread":0.29263575385770757,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408148355","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9865827,0.00072617596,0.0003036149,0.008515859,0.0014123817,0.0004874961,0.00006609232,0.00017639349,0.001729312],"genre_scores_gemma":[0.9976978,0.0003685551,0.00049215654,0.00077381916,0.00026359904,0.000047594087,0.00007600167,0.0000331638,0.00024733675],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99802434,0.00018203139,0.0006144457,0.00043144438,0.0005036709,0.0002440593],"domain_scores_gemma":[0.99798554,0.0005866929,0.0004172864,0.0007532364,0.00014749878,0.00010973183],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006772043,0.0003212517,0.0008403234,0.00023064353,0.00005359324,0.000016772316,0.0005060448,0.00019380506,0.00007917328],"category_scores_gemma":[0.0012836555,0.00021219728,0.0003310036,0.00024142755,0.000359691,0.000016718834,0.00040666654,0.001808687,0.0000050563476],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00074196345,0.0017773864,0.8753377,0.008522173,0.0028672048,0.0004835556,0.0049360604,0.0030937535,0.024018256,0.0011443046,0.018861901,0.05821571],"study_design_scores_gemma":[0.0038345815,0.0013646989,0.6330657,0.018929465,0.00262453,0.00013319624,0.00025535477,0.23360936,0.08001737,0.0012694204,0.023881737,0.0010146004],"about_ca_topic_score_codex":0.00049456494,"about_ca_topic_score_gemma":0.000014017615,"teacher_disagreement_score":0.24227205,"about_ca_system_score_codex":0.00006148129,"about_ca_system_score_gemma":0.00020048751,"threshold_uncertainty_score":0.8653154},"labels":[],"label_agreement":null},{"id":"W4408272740","doi":"10.1093/ejcts/ezaf076","title":"Reply to Novkunskaya <i>et al</i>.","year":2025,"lang":"en","type":"article","venue":"European Journal of Cardio-Thoracic Surgery","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Work & Health; Institute of Health Services and Policy Research; Toronto General Hospital; University of Toronto","funders":"","keywords":"Philosophy","score_opus":0.01825475836914643,"score_gpt":0.32190088525627253,"score_spread":0.3036461268871261,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408272740","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5094387,0.0050489497,0.074937955,0.2577685,0.0054708202,0.0002948415,0.000004573395,0.0001452705,0.14689036],"genre_scores_gemma":[0.8005973,0.00060887076,0.006536682,0.18905647,0.00067361846,0.0000012464046,0.0000050556205,0.00007756792,0.002443194],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9965814,0.0013276774,0.0009101306,0.00024683826,0.00058237015,0.00035159147],"domain_scores_gemma":[0.9978636,0.0005793275,0.0002953715,0.00042837986,0.00037390966,0.00045943534],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013529982,0.0001933688,0.0007679315,0.00067248655,0.000082301965,0.000072956136,0.00020019822,0.00001859977,0.000045091474],"category_scores_gemma":[0.0040966286,0.00015835634,0.0006168527,0.0005904759,0.00006943568,0.00011553953,0.00009290673,0.00085149286,0.000074344236],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003619611,0.000055431985,0.016989449,0.000058892365,0.00030331084,0.0041746036,0.00013561842,0.00020326019,0.0020143632,0.000024891846,0.67397547,0.30170277],"study_design_scores_gemma":[0.00030704233,0.000096313415,0.028417429,0.0010459542,0.00016014995,0.0016011146,0.00007668572,0.000050421455,0.0006402387,0.000016085753,0.9674493,0.0001392681],"about_ca_topic_score_codex":0.0000053976546,"about_ca_topic_score_gemma":7.287246e-8,"teacher_disagreement_score":0.3015635,"about_ca_system_score_codex":0.00008608539,"about_ca_system_score_gemma":0.00035784804,"threshold_uncertainty_score":0.6457584},"labels":[],"label_agreement":null},{"id":"W4408280719","doi":"10.1109/access.2025.3549702","title":"Machine Learning Evaluation Metric Discrepancies Across Programming Languages and Their Components in Medical Imaging Domains: Need for Standardization","year":2025,"lang":"en","type":"article","venue":"IEEE Access","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Teck (Canada); University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Standardization; Computer science; Metric (unit); Programming language; Artificial intelligence; Medical imaging; Natural language processing; Machine learning","score_opus":0.020848145540029655,"score_gpt":0.40473889449582173,"score_spread":0.38389074895579206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408280719","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.77701724,0.0034441578,0.21333802,0.0045560612,0.00028075016,0.0009388498,0.00000952459,0.00009915766,0.0003162262],"genre_scores_gemma":[0.9978124,0.0001916195,0.0010023194,0.0005598726,0.00011063324,0.00010555391,0.00013243919,0.000021423008,0.00006376392],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99846405,0.00013504401,0.00033766395,0.00030544237,0.00044557927,0.00031224196],"domain_scores_gemma":[0.99915403,0.0003597961,0.00010597549,0.0001314657,0.00014687466,0.00010182895],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002450302,0.00015306009,0.00033292093,0.0003167604,0.00020572702,0.00018070218,0.00015252491,0.000067639485,0.000012719288],"category_scores_gemma":[0.0029818288,0.00011757111,0.0000564081,0.000621134,0.00011317048,0.00022532756,0.00009416799,0.0003822122,2.6941794e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012683701,0.00007657463,0.32751,0.00026672834,0.00005907328,0.000015115076,0.00085883384,0.0006170517,0.0010628026,0.00011169512,0.0000700888,0.6692252],"study_design_scores_gemma":[0.0060567777,0.000055837056,0.07984294,0.0007826384,0.00009973928,0.000031923068,0.001457147,0.9012712,0.00081025553,0.00045734976,0.00894959,0.00018460442],"about_ca_topic_score_codex":0.00046771122,"about_ca_topic_score_gemma":0.000081795755,"teacher_disagreement_score":0.90065414,"about_ca_system_score_codex":0.00012374214,"about_ca_system_score_gemma":0.00010552618,"threshold_uncertainty_score":0.47944108},"labels":[],"label_agreement":null},{"id":"W4408301970","doi":"10.3390/info16030215","title":"Performance of Commercial Deep Learning-Based Auto-Segmentation Software for Prostate Cancer Radiation Therapy Planning: A Systematic Review","year":2025,"lang":"en","type":"review","venue":"Information","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Prostate cancer; Radiation therapy; Segmentation; Computer science; Artificial intelligence; Radiation treatment planning; Deep learning; Cancer; Software; Medical physics; Medicine; Internal medicine","score_opus":0.01967788407781012,"score_gpt":0.35868445584692243,"score_spread":0.3390065717691123,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408301970","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00002081229,0.98157454,0.010968762,0.00013631971,0.00023995573,0.006884734,0.000033012435,0.00008701094,0.00005483191],"genre_scores_gemma":[0.00004118842,0.99271375,0.00093248824,0.0008627313,0.0000631101,0.0021165176,0.003149837,0.000024115936,0.00009626971],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9977658,0.00014435106,0.0013983197,0.00013839289,0.00035919296,0.00019394199],"domain_scores_gemma":[0.9973465,0.00037748084,0.0016673249,0.00021410584,0.0003328062,0.000061742],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00085228414,0.0002873326,0.0017262906,0.00036193125,0.00012123576,0.000035035217,0.00013680733,0.00016271234,0.000017722517],"category_scores_gemma":[0.0014936663,0.00021582376,0.00030737463,0.0004316566,0.000033351604,0.00030421413,0.00001473853,0.00040857357,0.0000068270447],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023114044,0.000010448655,0.00006476556,0.5155325,0.00007389718,1.3511726e-7,0.00015093909,0.00027848536,6.3913305e-8,0.0000013532015,0.00023274684,0.48363155],"study_design_scores_gemma":[0.0011826302,0.00026749316,0.000045793284,0.75811905,0.0021435241,0.0000073124206,0.000015071131,0.03775325,0.0000031034426,8.9270003e-7,0.20025238,0.00020946436],"about_ca_topic_score_codex":0.000011885205,"about_ca_topic_score_gemma":2.1216256e-7,"teacher_disagreement_score":0.48342207,"about_ca_system_score_codex":0.00023764573,"about_ca_system_score_gemma":0.00067362544,"threshold_uncertainty_score":0.88010377},"labels":[],"label_agreement":null},{"id":"W4408354418","doi":"10.1109/icassp49660.2025.10890468","title":"SOLVE: Spatially Optimized Lung Volume Evidence Model for Efficient Nodule Malignancy Classification","year":2025,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; Sunnybrook Health Science Centre; Concordia University","funders":"","keywords":"Volume (thermodynamics); Nodule (geology); Malignancy; Computer science; Lung; Radiology; Artificial intelligence; Medicine; Pathology; Geology; Internal medicine; Physics","score_opus":0.02806661351415894,"score_gpt":0.33930191354846473,"score_spread":0.3112353000343058,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408354418","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015222675,0.00044289452,0.95884436,0.019859131,0.00027139773,0.0008081031,0.0000025019426,0.0001319957,0.0044169626],"genre_scores_gemma":[0.7317298,0.00009106961,0.23987557,0.0025737823,0.000097265955,0.00013615367,0.00003234642,0.000023835612,0.025440155],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987774,0.00002189603,0.0003475628,0.00036003502,0.00022429095,0.00026885408],"domain_scores_gemma":[0.9991092,0.00016653168,0.00008179141,0.00033538774,0.00019323414,0.000113849484],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00058308436,0.00013514173,0.00028181882,0.00012711974,0.00012842526,0.00004244974,0.00014143762,0.000081051585,0.000076208016],"category_scores_gemma":[0.0011649366,0.00011158097,0.00013010518,0.00017229795,0.000064944514,0.000053709537,0.000046096433,0.0002021891,0.000012006354],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014629272,0.00084900623,0.013512054,0.0019708741,0.00031921564,0.000018858615,0.00082215184,0.66179556,0.074422166,0.049240697,0.10143902,0.09414748],"study_design_scores_gemma":[0.001631797,0.000039640192,0.0022307683,0.00047478182,0.00015055826,0.0000035128267,0.000021555761,0.993885,0.00042059564,0.0001857587,0.00084854645,0.00010751644],"about_ca_topic_score_codex":0.000035195895,"about_ca_topic_score_gemma":0.0000012697895,"teacher_disagreement_score":0.71896875,"about_ca_system_score_codex":0.000112813424,"about_ca_system_score_gemma":0.00028111268,"threshold_uncertainty_score":0.455014},"labels":[],"label_agreement":null},{"id":"W4408356212","doi":"10.1109/icassp49660.2025.10890564","title":"ARIG-GCN: Anatomical Relationship and Isomorphic Graph Approximation Guided Graph Convolutional Network for Automated ASPECTS Scoring on Non-Contrast CT","year":2025,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Research and Development; National Natural Science Foundation of China","keywords":"Computer science; Graph; Contrast (vision); Artificial intelligence; Theoretical computer science","score_opus":0.017192157913372995,"score_gpt":0.3021186496301007,"score_spread":0.28492649171672774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408356212","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7422976,0.0003719503,0.2283143,0.013790904,0.0008026589,0.0016069735,0.000012380736,0.00074782025,0.012055419],"genre_scores_gemma":[0.98231727,0.000020773916,0.015018981,0.0018419059,0.00018544005,0.00006523597,0.0001843993,0.000017539633,0.00034844253],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985914,0.000056563884,0.00041399468,0.0003782878,0.00022137935,0.00033833942],"domain_scores_gemma":[0.998833,0.0006072375,0.00009571613,0.00019567653,0.00010795243,0.00016043829],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00069532933,0.00018557443,0.0003471097,0.00030062994,0.0003114906,0.000054475913,0.00007432262,0.000090402566,0.000025776195],"category_scores_gemma":[0.0008385979,0.00016115663,0.000108368054,0.0004654359,0.00016256048,0.0000807115,0.000027465954,0.00041646132,0.000006093466],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045079342,0.0002757256,0.28557107,0.00047282054,0.0004030734,0.000038946644,0.000080268954,0.0064034583,0.0016003657,0.59832793,0.10252117,0.003854382],"study_design_scores_gemma":[0.0040053274,0.00011346405,0.24469313,0.00045283596,0.00015749589,0.00006981165,0.000027967239,0.7201026,0.0001571708,0.029277457,0.00076415075,0.00017857569],"about_ca_topic_score_codex":0.000050925508,"about_ca_topic_score_gemma":0.000006257887,"teacher_disagreement_score":0.71369916,"about_ca_system_score_codex":0.000079694524,"about_ca_system_score_gemma":0.00013603657,"threshold_uncertainty_score":0.6571776},"labels":[],"label_agreement":null},{"id":"W4408362903","doi":"10.1186/s40644-025-00857-1","title":"Robust vs. Non-robust radiomic features: the quest for optimal machine learning models using phantom and clinical studies","year":2025,"lang":"en","type":"article","venue":"Cancer Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Douglas Mental Health University Institute","funders":"Université de Genève; Tehran University of Medical Sciences and Health Services; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Medicine; Imaging phantom; Medical physics; Radiomics; Artificial intelligence; Machine learning; Radiology; Nuclear medicine; Computer science","score_opus":0.08290751362502226,"score_gpt":0.4053803599199855,"score_spread":0.32247284629496326,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408362903","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43197036,0.0982438,0.432017,0.032046713,0.0028177607,0.0017238482,0.000033107215,0.00027273296,0.0008746883],"genre_scores_gemma":[0.9421677,0.009351465,0.03769191,0.0069018872,0.0014560587,0.00011118865,0.000036301048,0.00010895813,0.002174543],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980176,0.0001191533,0.0005291273,0.00061010604,0.00021912844,0.0005048886],"domain_scores_gemma":[0.9984857,0.000664563,0.00018693526,0.00029168464,0.00021180513,0.00015933656],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001443113,0.0003060125,0.0007247888,0.0001736671,0.0007423718,0.00010094947,0.00020606614,0.0000790217,0.000009041277],"category_scores_gemma":[0.00079313933,0.00021746765,0.00020269315,0.00025633344,0.0006573211,0.00019225744,0.00018654352,0.0011309094,4.44594e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001573418,0.00023200946,0.3913174,0.00193648,0.0026441745,0.0002154903,0.004206008,0.4255514,0.0020839167,0.0010571362,0.02731027,0.1418723],"study_design_scores_gemma":[0.0031268916,0.000056249577,0.003502079,0.001070295,0.0007528933,0.00014505057,0.0006518651,0.9855741,0.0000745432,0.00015273987,0.0046666414,0.00022661663],"about_ca_topic_score_codex":0.0005617422,"about_ca_topic_score_gemma":0.000026567077,"teacher_disagreement_score":0.5600227,"about_ca_system_score_codex":0.00022293361,"about_ca_system_score_gemma":0.00033162575,"threshold_uncertainty_score":0.8868073},"labels":[],"label_agreement":null},{"id":"W4408403210","doi":"10.1101/2025.03.10.25323646","title":"A 20-feature radiomic signature of triple-negative breast cancer identifies patients at high risk of death","year":2025,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Breast cancer; Signature (topology); Triple-negative breast cancer; Feature (linguistics); Medicine; Oncology; Internal medicine; Computer science; Cancer; Mathematics; Philosophy","score_opus":0.0068358971192994085,"score_gpt":0.276730628229868,"score_spread":0.2698947311105686,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408403210","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9895297,0.0023391934,0.00016789173,0.0018086449,0.0023446009,0.00090044644,0.0023360038,0.000051713858,0.0005217805],"genre_scores_gemma":[0.9873762,0.0020053643,0.0012449005,0.00021360796,0.00030704204,0.00006505253,0.00035724448,0.00004955914,0.008381016],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9972898,0.0002645786,0.00069463387,0.00068332383,0.00072863663,0.00033905127],"domain_scores_gemma":[0.99719816,0.00028125368,0.001041258,0.00073856756,0.0005519604,0.00018880518],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.00050486776,0.000451356,0.0013720973,0.00040367513,0.000087171604,0.000015676751,0.00043932418,0.00057760376,0.00025457714],"category_scores_gemma":[0.0010174835,0.00035736753,0.00045672146,0.00031518273,0.00027218135,0.000042040952,0.0005996389,0.0023061698,0.0000027799222],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007777359,0.0002755093,0.97228384,0.002447416,0.0014298785,0.000027311393,0.001090531,0.00072043116,0.0021302474,0.00005079172,0.013997222,0.0047690566],"study_design_scores_gemma":[0.003947344,0.00009089985,0.979759,0.0038376213,0.0016509164,0.000011688625,0.00004151412,0.0028416375,0.0059253494,0.000779186,0.00078574556,0.00032910437],"about_ca_topic_score_codex":0.0022859047,"about_ca_topic_score_gemma":0.000067664245,"teacher_disagreement_score":0.013211477,"about_ca_system_score_codex":0.0002836688,"about_ca_system_score_gemma":0.000405305,"threshold_uncertainty_score":0.9999955},"labels":[],"label_agreement":null},{"id":"W4408403791","doi":"10.3390/tomography11030033","title":"Prediction of Chemotherapy Response in Locally Advanced Breast Cancer Patients at Pre-Treatment Using CT Textural Features and Machine Learning: Comparison of Feature Selection Methods","year":2025,"lang":"en","type":"article","venue":"Tomography","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University; Health Sciences Centre; University of Toronto; Sunnybrook Health Science Centre","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Feature selection; Breast cancer; Artificial intelligence; Pattern recognition (psychology); Wavelet; Computer science; Wavelet transform; Feature (linguistics); Medicine; Cancer; Internal medicine","score_opus":0.010512167308577913,"score_gpt":0.34379935470242634,"score_spread":0.33328718739384844,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408403791","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9948915,0.0027561598,0.0011542824,0.0005899612,0.00010374233,0.00040457724,0.000021666277,0.000033063297,0.000045016397],"genre_scores_gemma":[0.9911151,0.00025999648,0.008251957,0.00007158196,0.000018669532,0.000013733239,0.00003084266,0.000016027261,0.00022211716],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9988743,0.0002559405,0.0002895208,0.0002450574,0.00017124217,0.00016391718],"domain_scores_gemma":[0.99941444,0.00013087197,0.00018911046,0.00010414707,0.00009966262,0.000061793144],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029793644,0.00016536949,0.0004482886,0.00044472588,0.00006964661,0.000006658468,0.00004261729,0.00007333235,0.000013853345],"category_scores_gemma":[0.00008126886,0.00012982349,0.0000990064,0.0006537118,0.00011771341,0.000048332262,0.000024069222,0.00032282792,2.5291714e-8],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0058099357,0.0002862485,0.8332427,0.000120419034,0.0001433322,9.891925e-7,0.0005077841,0.0019335683,0.05686853,0.0000028396414,0.00006110832,0.101022534],"study_design_scores_gemma":[0.00391806,0.00071371015,0.9261035,0.00046163256,0.0001249299,0.000021545246,0.00004827518,0.053335004,0.014605741,0.000009819899,0.0005842479,0.000073588],"about_ca_topic_score_codex":0.00054054364,"about_ca_topic_score_gemma":0.000041024294,"teacher_disagreement_score":0.100948945,"about_ca_system_score_codex":0.0001581472,"about_ca_system_score_gemma":0.000059351787,"threshold_uncertainty_score":0.5294048},"labels":[],"label_agreement":null},{"id":"W4408546473","doi":"10.1038/s41598-025-94335-0","title":"International expert consensus on the current status and future prospects of artificial intelligence in metabolic and bariatric surgery","year":2025,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Current (fluid); Consensus conference; MEDLINE; Medicine; Computer science; Political science; Engineering; Internal medicine","score_opus":0.01652816418014824,"score_gpt":0.3143769066112699,"score_spread":0.29784874243112164,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408546473","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9752412,0.0059503014,0.00013283385,0.009316635,0.008068924,0.00028216615,9.1909357e-7,0.0000133203475,0.000993698],"genre_scores_gemma":[0.9984809,0.00083505054,0.00027374618,0.000114992494,0.00016408485,0.000009868321,0.0000068800446,0.0000045483334,0.00010993214],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99876094,0.000044637185,0.0004120996,0.00033780508,0.0002914921,0.00015303287],"domain_scores_gemma":[0.999273,0.00020671826,0.00013823734,0.00023283144,0.00008291286,0.000066289496],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014583311,0.00008031836,0.00020444364,0.00034793938,0.0000787841,0.00007212523,0.00003812053,0.000025613917,0.000026619362],"category_scores_gemma":[0.0011432178,0.000052040352,0.00003790364,0.00044953648,0.00031161736,0.00002191265,0.00005124908,0.00024868044,4.379393e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006118846,0.00016374311,0.08869874,0.00006960205,0.00003507837,0.00015411095,0.00080865563,0.0000123251875,0.0020758947,0.013623864,0.0049653,0.8893315],"study_design_scores_gemma":[0.000345529,0.000054927805,0.2798986,0.0009368679,0.00010953742,0.00035234325,0.0012514938,0.020023827,0.009830334,0.044790447,0.64206135,0.0003447466],"about_ca_topic_score_codex":0.000033810615,"about_ca_topic_score_gemma":0.000004432033,"teacher_disagreement_score":0.88898677,"about_ca_system_score_codex":0.000020283427,"about_ca_system_score_gemma":0.00019458984,"threshold_uncertainty_score":0.2122144},"labels":[],"label_agreement":null},{"id":"W4408661073","doi":"10.21105/joss.07361","title":"RT-utils: A Minimal Python Library for RT-struct Manipulation","year":2025,"lang":"en","type":"article","venue":"The Journal of Open Source Software","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"struct; Python (programming language); Computer science; Programming language; Mathematics","score_opus":0.022712486077395132,"score_gpt":0.33364222613587624,"score_spread":0.3109297400584811,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408661073","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7355793,0.0019762449,0.22395132,0.033450786,0.0007841717,0.0011740342,0.00001047736,0.00010493916,0.002968699],"genre_scores_gemma":[0.9047799,0.00014903805,0.073523015,0.006314612,0.00088349776,0.00000978709,0.000026023601,0.00008863982,0.014225475],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.998871,0.000117288204,0.0004653622,0.000110940004,0.00023751114,0.00019788119],"domain_scores_gemma":[0.9987241,0.000501724,0.00032850043,0.00022659266,0.00010512897,0.00011397696],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010504657,0.000125922,0.0003635981,0.00013447485,0.0001996686,0.0001399034,0.0005662031,0.00006591972,0.0001294181],"category_scores_gemma":[0.0009722595,0.00007919829,0.00015533251,0.0002030778,0.000082015664,0.000310354,0.00020361308,0.0005091146,0.0000038050323],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0058050575,0.00027611625,0.119710796,0.00062919746,0.0007860056,0.00009963877,0.0036413595,0.0018019424,0.0021543065,0.0011081093,0.25658894,0.6073985],"study_design_scores_gemma":[0.012072317,0.0013208588,0.12911573,0.0030522845,0.0016298733,0.001935051,0.0029083632,0.01782187,0.0016947201,0.011435255,0.81657654,0.00043713936],"about_ca_topic_score_codex":0.000014395153,"about_ca_topic_score_gemma":4.7558513e-7,"teacher_disagreement_score":0.60696137,"about_ca_system_score_codex":0.00003820312,"about_ca_system_score_gemma":0.00023094333,"threshold_uncertainty_score":0.32296124},"labels":[],"label_agreement":null},{"id":"W4408776808","doi":"10.1016/j.labinv.2024.103175","title":"941 OCEAN Challenge: Advancing AI for Generalized Ovarian Cancer Diagnosis","year":2025,"lang":"en","type":"article","venue":"Laboratory Investigation","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary; Vancouver General Hospital; Canadian Centre for Applied Research in Cancer Control; BC Cancer Agency; BC Cancer Foundation; University of British Columbia","funders":"","keywords":"Ovarian cancer; Cancer; Medicine; Computational biology; Internal medicine; Biology","score_opus":0.012251384667623965,"score_gpt":0.3204720121160677,"score_spread":0.3082206274484437,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408776808","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8346732,0.002960213,0.010814332,0.14817977,0.001374369,0.0009935898,0.000057539517,0.0002756207,0.0006713548],"genre_scores_gemma":[0.9121282,0.0009706991,0.019295417,0.06449463,0.0010606262,0.0008483558,0.00021799204,0.00007181439,0.0009122412],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989726,0.00006624747,0.00027075977,0.00028674913,0.00016083632,0.00024279636],"domain_scores_gemma":[0.99913347,0.00010672191,0.00009163922,0.00021197519,0.0002738377,0.00018235462],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038796343,0.0001422322,0.00025296432,0.00014366575,0.00016224427,0.00003534833,0.00007670447,0.00010335642,0.000046914414],"category_scores_gemma":[0.00092876254,0.00013498653,0.000055577955,0.0004027573,0.00009630155,0.00013503295,0.000020415262,0.00027077572,0.000002690296],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021037733,0.00020697899,0.56018364,0.002065454,0.00042741888,0.000028550687,0.0017781035,0.0014096742,0.039870508,0.06693774,0.27698,0.049901534],"study_design_scores_gemma":[0.009801915,0.00027052467,0.056414116,0.0020500752,0.000926341,0.0000038334997,0.0002482342,0.097604446,0.047958035,0.016494833,0.76756126,0.00066638447],"about_ca_topic_score_codex":0.00008887118,"about_ca_topic_score_gemma":0.000021384385,"teacher_disagreement_score":0.5037696,"about_ca_system_score_codex":0.00015046743,"about_ca_system_score_gemma":0.0005006321,"threshold_uncertainty_score":0.5504591},"labels":[],"label_agreement":null},{"id":"W4408776835","doi":"10.1016/j.labinv.2024.103098","title":"865 Comparison of Prostate Cancer Detection and Characterization in a Contemporary Cohort of Paired Systematic and MRI-targeted biopsies: Implications for Sampling Protocols","year":2025,"lang":"en","type":"article","venue":"Laboratory Investigation","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University Health Network","funders":"","keywords":"Prostate cancer; Sampling (signal processing); Cohort; Medicine; Cancer; Prostate; Pathology; Cancer detection; Characterization (materials science); Oncology; Radiology; Medical physics; Internal medicine; Computer science; Materials science; Nanotechnology","score_opus":0.037202735329253514,"score_gpt":0.3564073788326719,"score_spread":0.3192046435034184,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408776835","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9832058,0.00037137166,0.00450109,0.00095603283,0.000041825177,0.010834451,0.000060013048,0.000023595529,0.000005837358],"genre_scores_gemma":[0.99374264,0.000024135348,0.0012314578,0.00014405347,0.000013900109,0.0047265766,0.00009869941,0.000009635256,0.000008875404],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.999067,0.000080859594,0.0005423768,0.00016229015,0.00007463457,0.000072807175],"domain_scores_gemma":[0.99910986,0.00011226528,0.00036375356,0.00010978625,0.00025734035,0.0000470024],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046203373,0.000082654755,0.00037548813,0.00017937609,0.000048360183,0.000013426893,0.00002541152,0.000063775304,4.946311e-7],"category_scores_gemma":[0.0005263393,0.000076777564,0.0000144607975,0.0003737843,0.00012593498,0.00010320942,0.000010627664,0.000092093316,3.0057773e-8],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000431727,0.000021555192,0.62965727,0.010871148,0.000027042233,4.376998e-8,0.00058419973,0.000019476232,0.35823318,0.00017981156,0.00000713018,0.00035598446],"study_design_scores_gemma":[0.0012020571,0.00010347822,0.91007805,0.007482974,0.000086255845,6.376497e-7,0.00024322682,0.036669433,0.04364311,0.00034240144,0.00007477593,0.00007358964],"about_ca_topic_score_codex":0.00004949776,"about_ca_topic_score_gemma":0.000009064121,"teacher_disagreement_score":0.31459007,"about_ca_system_score_codex":0.000042458247,"about_ca_system_score_gemma":0.00020633686,"threshold_uncertainty_score":0.31308982},"labels":[],"label_agreement":null},{"id":"W4408793525","doi":"10.1109/raaicon64172.2024.10928428","title":"Lung Cancer Prediction and Risk Assessment: A Machine Learning Approach Integrating Symptoms and Etiological Factors","year":2024,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Institute of Cancer Research","keywords":"Etiology; Computer science; Lung cancer; Cancer; Artificial intelligence; Machine learning; Risk analysis (engineering); Medicine; Oncology; Internal medicine","score_opus":0.009283514437527507,"score_gpt":0.31000884461250183,"score_spread":0.3007253301749743,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408793525","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93094504,0.005380883,0.05638608,0.00073596986,0.00017569275,0.00021952379,0.00001013566,0.0003345605,0.0058121067],"genre_scores_gemma":[0.99072134,0.0028427509,0.0052863793,0.00010513043,0.00018118632,0.000023756338,0.00006435486,0.000024058258,0.00075104064],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989231,0.00010664831,0.00020695024,0.00038462653,0.00017797369,0.00020066445],"domain_scores_gemma":[0.99949837,0.00019557853,0.000042250413,0.00007047134,0.000024469302,0.00016888084],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005165423,0.00016526156,0.0002517298,0.000112012676,0.00018179863,0.00013348465,0.000032055723,0.000100220335,0.00011702612],"category_scores_gemma":[0.00029880574,0.00010123499,0.000046010035,0.00013604405,0.000119239696,0.000107806336,0.00006102178,0.0013093244,4.226759e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009680094,0.000020957086,0.9477946,0.00020667778,0.00015695313,0.000009348324,0.00051001075,0.00014098069,0.0005750087,0.0012095736,0.00013443962,0.049231738],"study_design_scores_gemma":[0.00034401045,0.00012066471,0.1855801,0.00018696436,0.00020656291,0.00007428643,0.00021200805,0.81113434,0.000008638819,0.00004888726,0.0019970268,0.00008649203],"about_ca_topic_score_codex":0.00058297627,"about_ca_topic_score_gemma":0.0000039918145,"teacher_disagreement_score":0.8109934,"about_ca_system_score_codex":0.000063991254,"about_ca_system_score_gemma":0.00004260659,"threshold_uncertainty_score":0.5688436},"labels":[],"label_agreement":null},{"id":"W4408795703","doi":"10.1016/j.labinv.2024.103922","title":"1677 Artificial Intelligence-Based Image Analysis to Quantify Response of Pleural Mesothelioma to Neoadjuvant Therapy – Establishment and Validation of an AI Model Created by the Aiforia AI Platform","year":2025,"lang":"en","type":"article","venue":"Laboratory Investigation","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Mesothelioma; Neoadjuvant therapy; Artificial intelligence; Medicine; Computer science; Oncology; Pathology; Radiology; Internal medicine; Cancer","score_opus":0.023762293780441635,"score_gpt":0.33789156096299955,"score_spread":0.3141292671825579,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408795703","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8965313,0.0000500915,0.08933985,0.013454943,0.0000568147,0.0004583902,0.000068977526,0.000030429412,0.000009201176],"genre_scores_gemma":[0.9865131,0.00000684311,0.0071706898,0.0060699987,0.000022275972,0.00003083293,0.00014924355,0.0000143722655,0.000022647131],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9984725,0.00021553514,0.00053392403,0.00027293316,0.0003502097,0.00015486988],"domain_scores_gemma":[0.9986518,0.00017936899,0.0001652467,0.00035237492,0.00046671453,0.00018446361],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014899308,0.00014859908,0.00033190785,0.0005451397,0.00009569445,0.00006319612,0.00012804565,0.00007886276,0.000014264214],"category_scores_gemma":[0.0009036296,0.00011095421,0.000053050997,0.0020504633,0.00018558186,0.00019038889,0.000023121538,0.0001940368,0.0000010368594],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019717389,0.0001125633,0.0064374125,0.00004452212,0.00018613889,0.0000020608707,0.0020977373,0.03704,0.94484025,0.0015320935,0.0006216125,0.005113897],"study_design_scores_gemma":[0.0002888257,0.0002634319,0.004767994,0.00006632797,0.00018684819,2.9180453e-7,0.000259105,0.39070442,0.60224116,0.0010422447,0.000101456455,0.00007790435],"about_ca_topic_score_codex":0.00021091408,"about_ca_topic_score_gemma":0.000015501277,"teacher_disagreement_score":0.35366443,"about_ca_system_score_codex":0.00006662082,"about_ca_system_score_gemma":0.00037319592,"threshold_uncertainty_score":0.45245814},"labels":[],"label_agreement":null},{"id":"W4408795762","doi":"10.1016/j.labinv.2024.103627","title":"1389 A Comprehensive Study for Evaluation of a Deep Learning Algorithm to Identify Lymph Node Metastasis","year":2025,"lang":"en","type":"article","venue":"Laboratory Investigation","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ministère de l’Emploi et de la Solidarité Sociale (Québec)","funders":"","keywords":"Lymph node metastasis; Metastasis; Lymph node; Algorithm; Medicine; Artificial intelligence; Computer science; Pathology; Internal medicine; Cancer","score_opus":0.02972065607950178,"score_gpt":0.37833467049691766,"score_spread":0.34861401441741585,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408795762","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9411408,0.00034570813,0.055298403,0.0013042727,0.0002761131,0.0014582027,0.000012341072,0.00006121572,0.00010300077],"genre_scores_gemma":[0.96830285,0.000005059643,0.029324787,0.0018418996,0.00008775848,0.00027159852,0.00009174789,0.000022463048,0.000051840616],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981801,0.00038800895,0.00040853364,0.00030478032,0.00055325887,0.00016531162],"domain_scores_gemma":[0.9977158,0.00018576284,0.00017041262,0.0002254664,0.0015667924,0.00013579769],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014026806,0.00013743337,0.00033524286,0.00031625503,0.00013100124,0.000031824053,0.000084894345,0.000059826718,0.000020249503],"category_scores_gemma":[0.0024913861,0.00013556052,0.00005818188,0.000836298,0.00007557249,0.00009791342,0.000037076443,0.0001864064,0.0000058758924],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025981583,0.00070194923,0.24418889,0.0010129472,0.0013116163,0.000012198827,0.010224406,0.023222588,0.21773277,0.00089054886,0.0020150705,0.4984272],"study_design_scores_gemma":[0.008000939,0.0003870956,0.432951,0.0004224441,0.0019972776,0.0000027944377,0.0050981017,0.5343654,0.012074473,0.0013184856,0.003136834,0.00024513376],"about_ca_topic_score_codex":0.000053040323,"about_ca_topic_score_gemma":0.0000039924485,"teacher_disagreement_score":0.5111428,"about_ca_system_score_codex":0.00016123343,"about_ca_system_score_gemma":0.00034144422,"threshold_uncertainty_score":0.5527997},"labels":[],"label_agreement":null},{"id":"W4408795901","doi":"10.1016/j.labinv.2024.103637","title":"1399 Diagnostic Performance of Artificial Intelligence in Detecting Lymph Node Metastasis in Breast Cancer: Evidence from a Systematic Review and Meta-Analysis","year":2025,"lang":"en","type":"review","venue":"Laboratory Investigation","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Meta-analysis; Breast cancer; Medicine; Lymph node metastasis; Oncology; Metastasis; Lymph node; Cancer; Pathology; Internal medicine","score_opus":0.05815130436890817,"score_gpt":0.35900399548558715,"score_spread":0.300852691116679,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408795901","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015529055,0.99595493,0.000209176,0.0005941594,0.000043565746,0.0014529314,0.000171756,0.000018838617,0.0000017519076],"genre_scores_gemma":[0.0031650101,0.9943407,0.0010751184,0.0005944883,0.000024994284,0.0007092971,0.00006144683,0.000023441911,0.000005502081],"study_design_codex":"systematic_review","study_design_gemma":"meta_analysis","domain_scores_codex":[0.99581355,0.0010477648,0.0019730362,0.0005617928,0.00038722184,0.00021662646],"domain_scores_gemma":[0.9953239,0.0027448651,0.001085768,0.0005027325,0.00021096274,0.00013178517],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0022891439,0.00038871437,0.005818148,0.0008089392,0.000041000847,0.00003277304,0.00021493301,0.00016729259,0.00004880634],"category_scores_gemma":[0.0083067715,0.0002933637,0.00043695094,0.00404543,0.00015136412,0.00018099473,0.00006894208,0.00060563005,0.000002891083],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000037372552,0.0000238898,0.0023602743,0.96667516,0.00999018,0.000013755829,0.00016286531,0.00024901243,0.000005141762,0.000012734258,0.0000026513715,0.02050059],"study_design_scores_gemma":[0.000041945877,0.000010757952,0.0003005382,0.44287744,0.5503373,0.0000070385663,0.000031885727,0.0060985554,0.000016622149,0.000024027659,0.000022952965,0.00023093112],"about_ca_topic_score_codex":0.0011071607,"about_ca_topic_score_gemma":0.00008686248,"teacher_disagreement_score":0.5403471,"about_ca_system_score_codex":0.000255872,"about_ca_system_score_gemma":0.0008295184,"threshold_uncertainty_score":0.99995184},"labels":[],"label_agreement":null},{"id":"W4408796265","doi":"10.1016/j.labinv.2024.102798","title":"567 Cell-Centered UNI Feature Extraction Accurately Classifies Colon Polyps and Highlights Microenvironmental Remodeling","year":2025,"lang":"en","type":"article","venue":"Laboratory Investigation","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Research in Immunology and Cancer; Centre Hospitalier de l’Université de Montréal; Concordia University; Université de Montréal","funders":"","keywords":"Feature (linguistics); Computational biology; Cell; Feature extraction; Medicine; Biology; Pathology; Artificial intelligence; Computer science; Genetics","score_opus":0.015563178684460593,"score_gpt":0.28400897507490264,"score_spread":0.268445796390442,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408796265","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98184735,0.0009820866,0.00080107304,0.0149789695,0.00038786267,0.00024119695,0.000009285386,0.00008863394,0.0006635642],"genre_scores_gemma":[0.9906764,0.00034827355,0.004138974,0.0035528615,0.00013143754,0.000010111217,0.000120984696,0.000019351664,0.0010016189],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99905664,0.000090808775,0.00021498084,0.00029573918,0.00016863455,0.00017321798],"domain_scores_gemma":[0.9994623,0.000050505296,0.00011650069,0.0001706078,0.000052891668,0.0001471913],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018669594,0.00015583182,0.0001905226,0.00013508863,0.00019285541,0.000064707245,0.00005296736,0.00015253223,0.000011868905],"category_scores_gemma":[0.000079413585,0.00014445833,0.000027615342,0.000244119,0.00017792071,0.0002120968,0.00003090393,0.00043375016,0.0000073439355],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008464877,0.000048315673,0.027662324,0.00016375874,0.00003113131,0.000018848492,0.0003779723,0.0000499079,0.961973,0.00058643194,0.006820508,0.0021831116],"study_design_scores_gemma":[0.00572325,0.00026954696,0.21557304,0.0012097973,0.0004957199,0.0000727,0.0014301199,0.059423912,0.5185901,0.0013415497,0.19524397,0.0006263011],"about_ca_topic_score_codex":0.00002577046,"about_ca_topic_score_gemma":0.000004906087,"teacher_disagreement_score":0.44338295,"about_ca_system_score_codex":0.0001372571,"about_ca_system_score_gemma":0.00012335097,"threshold_uncertainty_score":0.589084},"labels":[],"label_agreement":null},{"id":"W4408796312","doi":"10.1016/j.labinv.2024.103604","title":"1366 Open-Source, Cross-Platform Drag and Drop Pipeline for Real-Time Whole-Slide Image Anonymization","year":2025,"lang":"en","type":"article","venue":"Laboratory Investigation","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre","funders":"","keywords":"Pipeline (software); Open source; Drag; Drop (telecommunication); Computer science; Computer graphics (images); Geology; Physics; Mechanics; Operating system; Telecommunications; Software","score_opus":0.009982862077453395,"score_gpt":0.3123311307093829,"score_spread":0.3023482686319295,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408796312","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9185513,0.00017683934,0.06741092,0.008475913,0.00027578115,0.0012544544,0.00005510587,0.00023967268,0.0035599668],"genre_scores_gemma":[0.7643754,0.00033877423,0.15949331,0.028146168,0.0013577599,0.00042071802,0.0035558424,0.00026447757,0.042047564],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987505,0.00005075834,0.00041115115,0.0003773813,0.0001802412,0.00022998576],"domain_scores_gemma":[0.99878055,0.00014665927,0.00016766941,0.00028004588,0.0004176843,0.00020738799],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00079646363,0.00017813292,0.00031322162,0.00016947598,0.00027253362,0.00028923948,0.00013781934,0.00013712596,0.00003806216],"category_scores_gemma":[0.0014566854,0.0001692602,0.00003389006,0.0005035994,0.00029885434,0.0005056526,0.00008714997,0.00023639809,0.000018421088],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034978057,0.0001300551,0.0783187,0.00088091445,0.00010891201,0.000017809964,0.00091842684,0.00039845178,0.8067876,0.005384587,0.0676601,0.03904464],"study_design_scores_gemma":[0.010511152,0.00030725484,0.07267431,0.0010979899,0.00039376115,0.000020410465,0.00015901706,0.6201275,0.046533845,0.009655912,0.23786488,0.0006539429],"about_ca_topic_score_codex":0.000062389954,"about_ca_topic_score_gemma":0.000005530618,"teacher_disagreement_score":0.7602538,"about_ca_system_score_codex":0.000088084606,"about_ca_system_score_gemma":0.00035689428,"threshold_uncertainty_score":0.69022304},"labels":[],"label_agreement":null},{"id":"W4408796506","doi":"10.1016/j.labinv.2024.103271","title":"1037 AI-Assisted Assignment of Endometrial Carcinoma Molecular Subtype","year":2025,"lang":"en","type":"article","venue":"Laboratory Investigation","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"London Health Sciences Centre; Western University","funders":"","keywords":"Carcinoma; Medicine; Oncology; Gynecology; Internal medicine; Cancer research","score_opus":0.010530682751350022,"score_gpt":0.28088283869153446,"score_spread":0.27035215594018447,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408796506","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9881135,0.00042279903,0.0036807086,0.0053676567,0.00042971468,0.00026422105,0.000006664142,0.000052851,0.0016618834],"genre_scores_gemma":[0.9932127,0.0000070580327,0.0021480948,0.0042685573,0.00007786862,0.000014396096,0.000047265145,0.0000132535415,0.00021081882],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99890417,0.00012474402,0.00033182316,0.00019971859,0.00029722275,0.00014234736],"domain_scores_gemma":[0.99917346,0.000082570834,0.00013052669,0.0002479303,0.00023542072,0.0001300616],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000409055,0.00010984961,0.00025976115,0.0002753412,0.00004587425,0.000016224372,0.00007555694,0.00012855315,0.000054327684],"category_scores_gemma":[0.0013085878,0.00010272148,0.000055043212,0.00095497386,0.00016606784,0.000058655,0.000026021202,0.0003658617,0.000006603967],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008905779,0.000072882816,0.20636263,0.0002122773,0.00009267031,0.000035800247,0.00010083615,0.000056162466,0.77304363,0.010325565,0.004082767,0.005525707],"study_design_scores_gemma":[0.0055999295,0.00033243696,0.33941513,0.000442463,0.00039155042,0.000007826393,0.00008041694,0.0062805167,0.62617177,0.002480529,0.018556645,0.00024077976],"about_ca_topic_score_codex":0.000043033047,"about_ca_topic_score_gemma":9.052823e-7,"teacher_disagreement_score":0.14687185,"about_ca_system_score_codex":0.00010186085,"about_ca_system_score_gemma":0.0005160983,"threshold_uncertainty_score":0.41888607},"labels":[],"label_agreement":null},{"id":"W4408803805","doi":"10.5194/essd-2024-556-rc1","title":"Comment on essd-2024-556","year":2025,"lang":"en","type":"peer-review","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science","score_opus":0.02207886647073661,"score_gpt":0.3658488875201618,"score_spread":0.3437700210494252,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408803805","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[6.4208524e-7,0.012024314,0.00041580558,0.5699783,0.003275036,0.0004352696,0.00002087391,0.000080931386,0.41376883],"genre_scores_gemma":[0.000005922261,0.011515882,0.0008608334,0.39127585,0.00054627034,0.00003394775,0.0006541191,0.000026939582,0.59508026],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99796,0.00007812838,0.0004670613,0.0004896498,0.0006758076,0.00032937774],"domain_scores_gemma":[0.99854374,0.00025145683,0.00012691744,0.00071184564,0.00012399892,0.00024202291],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00063419336,0.00035975882,0.0010625139,0.00020705833,0.00006932693,0.00002723472,0.0002448837,0.00022216626,0.0075286],"category_scores_gemma":[0.0009666582,0.00025634866,0.0003295817,0.00020750755,0.00006433588,0.000011352008,0.00013395298,0.0019514409,0.00031206448],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010850617,0.00011039347,0.000018663543,0.0058332137,0.00014911576,0.00007528222,0.000005151043,0.0000010535806,8.999061e-7,0.0012291771,0.9246814,0.06788475],"study_design_scores_gemma":[0.0006228051,0.00016747195,0.000015827103,0.024381042,0.00054746337,0.000023486302,0.000004321069,0.00043702495,0.0000053786484,0.00008218742,0.973503,0.0002100157],"about_ca_topic_score_codex":0.00020885987,"about_ca_topic_score_gemma":0.0000032788582,"teacher_disagreement_score":0.18131143,"about_ca_system_score_codex":0.00016947555,"about_ca_system_score_gemma":0.00031353012,"threshold_uncertainty_score":0.99998885},"labels":[],"label_agreement":null},{"id":"W4408810153","doi":"10.1109/tip.2025.3552198","title":"Pruning Sparse Tensor Neural Networks Enables Deep Learning for 3D Ultrasound Localization Microscopy","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute; Polytechnique Montréal","funders":"Canadian Institutes of Health Research; Alliance de recherche numérique du Canada; Institut TransMedTech; Natural Sciences and Engineering Research Council of Canada; Institut de Valorisation des Données; Canada First Research Excellence Fund; Canada Foundation for Innovation","keywords":"Artificial intelligence; Artificial neural network; Computer science; Pruning; Deep learning; Pattern recognition (psychology); Microscopy; Computer vision; Optics; Biology; Physics","score_opus":0.008951995204154253,"score_gpt":0.29451325981881177,"score_spread":0.28556126461465753,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408810153","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0068975636,0.0007260663,0.98996115,0.00069354184,0.00045374382,0.00047155228,0.0000016502651,0.0002718868,0.00052285165],"genre_scores_gemma":[0.92991894,0.00011174068,0.06630735,0.001383732,0.000161789,0.000087865585,0.000028583925,0.000070115195,0.001929876],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984428,0.000065289794,0.00039393836,0.00044349357,0.00019182102,0.00046265224],"domain_scores_gemma":[0.9990482,0.0002843545,0.00012888637,0.00017277767,0.00023552588,0.00013028097],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033945628,0.0002541864,0.00034725215,0.00029179596,0.0009413706,0.00023954544,0.0001079665,0.00013674723,0.000044724133],"category_scores_gemma":[0.00019612344,0.00024128494,0.00013372714,0.0005220953,0.00018363383,0.0002735651,0.0000018133646,0.0008447422,0.0000031147165],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037412136,0.00022251664,0.0009025164,0.0007837853,0.0000930941,0.00001634232,0.00049354054,0.52872115,0.032894943,0.0000075130824,0.00019968346,0.43529078],"study_design_scores_gemma":[0.0015157806,0.00011969081,0.00012625313,0.00069961144,0.00029511555,0.000062220795,0.0003041176,0.9853074,0.008866858,0.00004353729,0.0024509134,0.00020851364],"about_ca_topic_score_codex":0.000022053468,"about_ca_topic_score_gemma":0.0000055300984,"teacher_disagreement_score":0.9236538,"about_ca_system_score_codex":0.00011597579,"about_ca_system_score_gemma":0.00010719643,"threshold_uncertainty_score":0.9839314},"labels":[],"label_agreement":null},{"id":"W4408835753","doi":"10.1186/s12885-025-13850-5","title":"Radiomic-based approaches in the multi-metastatic setting: a quantitative review","year":2025,"lang":"en","type":"review","venue":"BMC Cancer","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto; Queen's University; University Health Network","funders":"National Cancer Institute; National Institutes of Health","keywords":"Surgical oncology; Lesion; Medicine; Computer science; Medical physics; Radiology; Pathology; Oncology","score_opus":0.19154655790361644,"score_gpt":0.4570939773193255,"score_spread":0.26554741941570903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408835753","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[7.083745e-7,0.9905704,0.003499915,0.0021710277,0.00021733246,0.0028670484,0.000037880756,0.00003400523,0.00060164667],"genre_scores_gemma":[0.0000010449647,0.97221035,0.021129766,0.0041285334,0.00011369337,0.0014540289,0.00017871961,0.000049588583,0.00073428586],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9969883,0.0009315162,0.0008286809,0.00053694536,0.0003606291,0.00035395165],"domain_scores_gemma":[0.99718916,0.0017095153,0.00041171288,0.0005591847,0.00004114269,0.000089256566],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002014153,0.0004316228,0.0022682361,0.00028857208,0.000065965905,0.000034059594,0.00039849814,0.00010953449,0.00008340447],"category_scores_gemma":[0.002425853,0.00024925833,0.00065165735,0.00090913073,0.00014038385,0.000028140998,0.000043661104,0.0012704157,0.000019227935],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009074433,0.00010842644,0.00007156793,0.279679,0.000117058735,0.000041863364,0.00009137366,0.000022153197,4.3731095e-8,0.0001477493,0.007619037,0.71209264],"study_design_scores_gemma":[0.00069901714,0.000025721602,0.000020193896,0.24591267,0.002162527,0.0000328002,0.00004071293,0.004094524,4.500898e-8,0.0000048588868,0.7468135,0.00019347282],"about_ca_topic_score_codex":0.00014259454,"about_ca_topic_score_gemma":0.000053024676,"teacher_disagreement_score":0.7391944,"about_ca_system_score_codex":0.00025551947,"about_ca_system_score_gemma":0.0023642988,"threshold_uncertainty_score":0.99999595},"labels":[],"label_agreement":null},{"id":"W4408854836","doi":"10.1038/s41598-025-92610-8","title":"Ultrasound-enhanced fine-needle biopsy improves tissue yield in head and neck tumors ex vivo","year":2025,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Business Finland; Academy of Finland","keywords":"Ex vivo; Ultrasound; Head and neck; Biopsy; Medicine; Pathology; In vivo; Radiology; Anatomy; Biology; Surgery","score_opus":0.008079283485824085,"score_gpt":0.28666473704833917,"score_spread":0.2785854535625151,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408854836","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98056626,0.0005077742,0.0006135652,0.001501661,0.0031516084,0.0003465486,7.4065895e-7,0.0000705421,0.013241312],"genre_scores_gemma":[0.97216177,0.00001180107,0.0016378806,0.00025388823,0.00007337608,0.000014257784,0.000016971875,0.000014103374,0.025815941],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99807304,0.000022578884,0.0005236496,0.0007119153,0.00031268515,0.00035612952],"domain_scores_gemma":[0.9989554,0.00011032157,0.00013882539,0.0005554685,0.00007224658,0.00016773256],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010369803,0.00015819192,0.00033751808,0.0003472073,0.00015444601,0.00017539444,0.00008128063,0.000077139215,0.00012661713],"category_scores_gemma":[0.0019404012,0.00013471159,0.000051583724,0.00070476666,0.00033535957,0.00010022248,0.00006704347,0.0003469077,0.000007435989],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022166518,0.00010559558,0.03810399,0.00016051739,0.000016937012,0.0008613371,0.00047329944,0.000017374534,0.93372416,0.00008038417,0.01372546,0.012708789],"study_design_scores_gemma":[0.0026398096,0.00030277733,0.25390655,0.0042096605,0.00016268637,0.0060874457,0.0008928145,0.0032762685,0.5939713,0.012980734,0.120634384,0.000935561],"about_ca_topic_score_codex":0.00032183673,"about_ca_topic_score_gemma":0.000047648933,"teacher_disagreement_score":0.33975285,"about_ca_system_score_codex":0.000050027043,"about_ca_system_score_gemma":0.00020471847,"threshold_uncertainty_score":0.5493379},"labels":[],"label_agreement":null},{"id":"W4408901683","doi":"10.1055/s-0045-1805649","title":"A selective resection algorithm for barrett’s neoplasia optimizes oncological outcomes","year":2025,"lang":"en","type":"article","venue":"Endoscopy","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Medicine; Resection; General surgery; Algorithm; Surgery","score_opus":0.012239410291446588,"score_gpt":0.34524525957509444,"score_spread":0.33300584928364785,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408901683","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.084675476,0.00081707817,0.85847414,0.02984067,0.0029861154,0.0019901218,0.000015717716,0.00045943167,0.02074126],"genre_scores_gemma":[0.39403012,0.00010471551,0.58269715,0.006955423,0.0005893806,0.00043064114,0.00006262778,0.000043379965,0.015086539],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989971,0.00005475374,0.00021803522,0.00029408166,0.0001568167,0.00027922375],"domain_scores_gemma":[0.9991062,0.0004939672,0.000050947227,0.00015316483,0.00008848172,0.00010721088],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031323193,0.00013994946,0.00036680038,0.00014618774,0.00015459213,0.000028041979,0.00008267736,0.00011334837,0.00006841697],"category_scores_gemma":[0.0012098217,0.0001062921,0.00014329741,0.00021768741,0.000077969,0.000044378867,0.000032912438,0.00042087352,0.000009549144],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022655008,0.0009897406,0.2185203,0.00039858776,0.0013422511,0.0001302289,0.00080140826,0.00039967394,0.007278296,0.0058462657,0.22025073,0.541777],"study_design_scores_gemma":[0.030988708,0.0042856494,0.17997782,0.0008284703,0.0009060031,0.000082130486,0.0007092336,0.5752446,0.032041755,0.007975088,0.1661631,0.0007974401],"about_ca_topic_score_codex":0.000039711456,"about_ca_topic_score_gemma":0.0000029838977,"teacher_disagreement_score":0.57484496,"about_ca_system_score_codex":0.0001509265,"about_ca_system_score_gemma":0.0001682039,"threshold_uncertainty_score":0.43344662},"labels":[],"label_agreement":null},{"id":"W4408905851","doi":"10.1016/j.semcancer.2025.03.004","title":"From classical approaches to artificial intelligence, old and new tools for PDAC risk stratification and prediction","year":2025,"lang":"en","type":"review","venue":"Seminars in Cancer Biology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Pancreas Centre (Canada)","funders":"European Cooperation in Science and Technology; European Commission; Orta Doğu Teknik Üniversitesi; Cancer Research UK; Pancreatic Cancer UK","keywords":"Risk stratification; Stratification (seeds); Artificial intelligence; Computer science; Computational biology; Biology; Medicine; Internal medicine","score_opus":0.178276850204085,"score_gpt":0.4096658170760843,"score_spread":0.23138896687199928,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408905851","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00042743215,0.9741186,0.021068033,0.0018713815,0.00058276317,0.0013978133,0.00040927363,0.00002536927,0.00009933035],"genre_scores_gemma":[0.0001235829,0.98888326,0.008469952,0.00013904212,0.0009927024,0.00038797667,0.0006825253,0.000019339011,0.00030162564],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984441,0.00011660785,0.00052557694,0.00063454296,0.000063156294,0.00021603757],"domain_scores_gemma":[0.99853134,0.0009346077,0.00016710078,0.00019713628,0.000017647115,0.00015218914],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038611738,0.00023223316,0.00096111925,0.00022064052,0.00005166686,0.000039077793,0.00009433767,0.00042416534,0.000014721206],"category_scores_gemma":[0.0008223266,0.00018614644,0.000084422754,0.00021136689,0.00014383151,0.00003181798,0.000059550985,0.0005978797,8.693159e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000055177607,0.000025458208,0.00024082325,0.0015900914,0.00007000486,0.0000010674067,0.00019174712,0.0000043147265,0.000008201482,0.0015734357,0.0010357848,0.9952039],"study_design_scores_gemma":[0.00023604685,0.00036745146,0.00015027673,0.013540911,0.001001468,0.0000124968155,0.00015186914,0.0034667137,0.000017547085,0.012545743,0.96824926,0.00026020597],"about_ca_topic_score_codex":0.00039929236,"about_ca_topic_score_gemma":0.000086667795,"teacher_disagreement_score":0.9949437,"about_ca_system_score_codex":0.00012560573,"about_ca_system_score_gemma":0.00036150758,"threshold_uncertainty_score":0.75908315},"labels":[],"label_agreement":null},{"id":"W4408961980","doi":"10.1007/978-3-031-75653-5_13","title":"Correction to: Enhanced 3D X-Ray Tomography: Deep Learning-Based Advanced Algorithms for Fiber Instance Segmentation","year":2025,"lang":"en","type":"book-chapter","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; University of British Columbia; University of British Columbia Hospital","funders":"","keywords":"Segmentation; Computer science; Artificial intelligence; Tomography; Algorithm; Fiber; Materials science; Optics; Physics; Composite material","score_opus":0.007835723288193559,"score_gpt":0.2858559378206044,"score_spread":0.2780202145324109,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408961980","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007684018,0.00037355904,0.69172364,0.00083054183,0.0023179932,0.0017098374,0.000010305558,0.0003135189,0.30264375],"genre_scores_gemma":[0.0013820544,0.00012582995,0.16752301,0.0029886079,0.0003657512,0.00021868251,0.0006368293,0.00010371117,0.8266555],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979701,0.00002412848,0.00051142427,0.0007182579,0.00042201122,0.00035406285],"domain_scores_gemma":[0.9984642,0.0003992479,0.00025561743,0.00031132394,0.0003343319,0.00023524229],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00027036958,0.0004384551,0.00065524667,0.0005004196,0.00018884984,0.00004245666,0.00012218388,0.0002504126,0.00085174234],"category_scores_gemma":[0.00048477654,0.00041533122,0.0003263853,0.00014141444,0.000074347605,0.00006649816,0.000031074756,0.00094675494,0.000052637708],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005226266,0.00005224185,0.000036131427,0.00035790485,0.00019833689,0.000010659215,0.0001006282,0.015787967,0.0010501562,0.00041266214,0.011151938,0.97031873],"study_design_scores_gemma":[0.0045631793,0.0013491682,0.00015122746,0.002853593,0.00054607354,0.000007518346,0.00006292749,0.19921887,0.0019703328,0.00025153125,0.78821474,0.0008108605],"about_ca_topic_score_codex":0.00002152219,"about_ca_topic_score_gemma":0.000022051752,"teacher_disagreement_score":0.9695079,"about_ca_system_score_codex":0.0002432425,"about_ca_system_score_gemma":0.00018627259,"threshold_uncertainty_score":0.9998298},"labels":[],"label_agreement":null},{"id":"W4408969474","doi":"10.1186/s12868-025-00938-8","title":"Hippocampal functional imaging-derived radiomics features for diagnosing cognitively impaired patients with Parkinson’s disease","year":2025,"lang":"en","type":"article","venue":"BMC Neuroscience","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"National Natural Science Foundation of China","keywords":"Functional magnetic resonance imaging; Magnetic resonance imaging; Medicine; Voxel; Neuroimaging; Audiology; Psychology; Neuroscience; Radiology","score_opus":0.013460569758193246,"score_gpt":0.2710906306278307,"score_spread":0.2576300608696374,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408969474","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8912636,0.0001579103,0.10375319,0.0026947304,0.0009663128,0.00086252857,0.000036190628,0.000114765164,0.00015078069],"genre_scores_gemma":[0.988966,0.000014260078,0.0032641096,0.007154919,0.00014349389,0.00009254053,0.00004730167,0.000024149558,0.00029325],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9984383,0.0000495231,0.0001909467,0.0005644973,0.00037632303,0.000380427],"domain_scores_gemma":[0.9988908,0.0003465597,0.00009163081,0.00020635092,0.00017099419,0.00029367447],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019588435,0.00019030429,0.000219202,0.00016506304,0.0003563022,0.00010922485,0.00014990882,0.00002548934,0.0000062407257],"category_scores_gemma":[0.001986104,0.0001505388,0.00009726165,0.0003402027,0.0004071717,0.00015680828,0.000057672685,0.0002319138,0.0000012591008],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011100203,0.0002822766,0.979766,0.000115167524,0.0000074314007,0.000023844279,0.000039872277,0.00023431896,0.0026696215,0.00016433855,0.0046638525,0.01092324],"study_design_scores_gemma":[0.0033190309,0.00011328139,0.96480733,0.00019512724,0.00010135741,0.000011475506,0.000020676507,0.024551395,0.00025113524,0.00015476755,0.0063181613,0.00015624707],"about_ca_topic_score_codex":0.000008133534,"about_ca_topic_score_gemma":0.0000013199123,"teacher_disagreement_score":0.10048907,"about_ca_system_score_codex":0.00007290737,"about_ca_system_score_gemma":0.00045342935,"threshold_uncertainty_score":0.61387944},"labels":[],"label_agreement":null},{"id":"W4408979510","doi":"10.1016/s1556-0864(25)00298-9","title":"103P: Enhancing survival prediction in advanced non-small cell lung cancer (aNSCLC): A comparison of artificial intelligence (AI) derived prognostication and RECIST assessments in MYSTIC phase III trial","year":2025,"lang":"en","type":"article","venue":"Journal of Thoracic Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Glycemic Index Laboratories; University of Calgary","funders":"","keywords":"Medicine; Lung cancer; Internal medicine; Oncology","score_opus":0.030698747181751845,"score_gpt":0.4878925963278135,"score_spread":0.45719384914606165,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408979510","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8516096,0.00050494284,0.14495698,0.00091837754,0.0011675932,0.00058894465,0.0000019122147,0.000004949865,0.00024668447],"genre_scores_gemma":[0.9918885,0.00020474431,0.007540484,0.00008111162,0.00018923765,0.000028449924,0.0000058502396,0.000009596701,0.00005201638],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99774826,0.00027386475,0.0013566727,0.00019731437,0.00022017107,0.000203729],"domain_scores_gemma":[0.9983013,0.00057699427,0.00071901904,0.00010004765,0.00020704078,0.000095548996],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017029278,0.00012449954,0.0007743706,0.00047854293,0.000038726324,0.000014478631,0.00010675671,0.00014235202,0.00002188136],"category_scores_gemma":[0.0009952119,0.00011287013,0.000060785256,0.0003761084,0.00008076353,0.00010225921,0.000037097587,0.0008825177,1.9559882e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.049044617,0.0024000825,0.06384927,0.0005353257,0.00008590341,0.00008356107,0.0016434188,0.0028377192,0.13780887,0.000024421997,0.00005653283,0.74163026],"study_design_scores_gemma":[0.049050998,0.008318807,0.049715567,0.005711347,0.0011926306,0.000068644964,0.004197615,0.82156974,0.05886897,0.0006044096,0.000406861,0.00029442905],"about_ca_topic_score_codex":0.000097502576,"about_ca_topic_score_gemma":0.00023282018,"teacher_disagreement_score":0.818732,"about_ca_system_score_codex":0.00043113573,"about_ca_system_score_gemma":0.00085464545,"threshold_uncertainty_score":0.46027103},"labels":[],"label_agreement":null},{"id":"W4408979645","doi":"10.1016/s1556-0864(25)00311-9","title":"116P: Predicting overall survival (OS) differences and treatment duration from longitudinal ai-driven imaging-based prognostication (IPRO) and first-line (1L) treatment status among patients with advanced non-small cell lung cancer (aNSCLC)","year":2025,"lang":"en","type":"article","venue":"Journal of Thoracic Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Glycemic Index Laboratories; University of Calgary","funders":"Deutsche Krebshilfe","keywords":"Medicine; Oncology; Internal medicine; Overall survival; Lung cancer","score_opus":0.00943801842358994,"score_gpt":0.33754746496335103,"score_spread":0.3281094465397611,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408979645","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9870536,0.0011494763,0.0072619705,0.0033845713,0.00034721784,0.0006692735,0.000023013741,0.000016891725,0.0000939953],"genre_scores_gemma":[0.9935466,0.0008490496,0.0051194755,0.00013871721,0.00017557177,0.000048010148,0.00004857775,0.000018145076,0.000055873275],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99856716,0.000121814155,0.00051503454,0.0003070267,0.0002218826,0.00026705462],"domain_scores_gemma":[0.9983902,0.0004204573,0.00058054633,0.00012328988,0.00026866377,0.0002168332],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016980528,0.00023820346,0.0006002593,0.00018197474,0.00014094032,0.000048088554,0.000058314232,0.00008171002,0.000015826134],"category_scores_gemma":[0.00013582752,0.00015638978,0.0000616231,0.00010045007,0.00013953382,0.00015398252,0.00002413332,0.00029440143,1.5169562e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016472841,0.00063486834,0.87625515,0.00009987711,0.00023534363,0.000059945552,0.00051601883,0.00088486186,0.00022652258,0.0000015935586,0.000014346527,0.11942419],"study_design_scores_gemma":[0.006521738,0.0030240533,0.8884927,0.00068136596,0.0012306811,0.000008034449,0.000095533425,0.09931295,0.00025644412,0.00001871419,0.00024506403,0.00011269833],"about_ca_topic_score_codex":0.0007212334,"about_ca_topic_score_gemma":0.00056629465,"teacher_disagreement_score":0.11931149,"about_ca_system_score_codex":0.0006797864,"about_ca_system_score_gemma":0.0005020695,"threshold_uncertainty_score":0.637739},"labels":[],"label_agreement":null},{"id":"W4408986412","doi":"10.1101/2025.03.25.645236","title":"Data Processing in Multidimensional MRI For Biomarker Identification: Is It Necessary?","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute of Aging","funders":"","keywords":"A priori and a posteriori; Identification (biology); Pattern recognition (psychology); Computer science; Artificial intelligence; Regression; Biomarker; Regression analysis; Statistics; Mathematics; Data mining; Machine learning; Biology","score_opus":0.03751735558260559,"score_gpt":0.3245818146157514,"score_spread":0.2870644590331458,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408986412","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5773688,0.016102606,0.25829372,0.11951768,0.009154094,0.01136901,0.0064564804,0.0014590088,0.00027862244],"genre_scores_gemma":[0.907471,0.0005786076,0.08578754,0.004642972,0.0007323813,0.00040386213,0.000035590307,0.0001527975,0.00019522922],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963355,0.0000900567,0.00093481224,0.0015851978,0.00052013964,0.00053426565],"domain_scores_gemma":[0.99656034,0.0001441476,0.00045099936,0.0020327112,0.0005485369,0.00026324432],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0017814811,0.0004795232,0.0007571336,0.0005315815,0.00018237649,0.00017707967,0.00080068666,0.00048354932,0.000059361337],"category_scores_gemma":[0.0012438756,0.00049197377,0.00013701696,0.00061075756,0.00015952146,0.00021539755,0.00094665505,0.0011309586,0.000017830034],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009632744,0.0023646865,0.10994457,0.022134356,0.0011851051,0.00049047946,0.0001969096,0.0005316221,0.66596484,0.0011664098,0.19421323,0.000844548],"study_design_scores_gemma":[0.0043712715,0.000045637094,0.19576553,0.0078002643,0.00077286334,2.0000186e-7,0.000018668221,0.5828079,0.017969463,0.000012181835,0.18912578,0.00131026],"about_ca_topic_score_codex":0.000056233563,"about_ca_topic_score_gemma":0.0000025238965,"teacher_disagreement_score":0.64799535,"about_ca_system_score_codex":0.00024277593,"about_ca_system_score_gemma":0.001636665,"threshold_uncertainty_score":0.9997532},"labels":[],"label_agreement":null},{"id":"W4409097243","doi":"10.3390/computation13040088","title":"MedMAE: A Self-Supervised Backbone for Medical Imaging Tasks","year":2025,"lang":"en","type":"article","venue":"Computation","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia, Okanagan Campus; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Medical imaging; Artificial intelligence; Psychology","score_opus":0.007432130035135333,"score_gpt":0.32313623417533105,"score_spread":0.31570410414019573,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409097243","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06398661,0.0005433984,0.8933988,0.035938803,0.00067086454,0.0005028369,0.0000015053735,0.000274152,0.0046830378],"genre_scores_gemma":[0.9259704,0.00003485151,0.0651074,0.007980144,0.00031701117,0.000043988934,0.00013453074,0.00002430086,0.00038741442],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989781,0.000038028636,0.0002700808,0.00023327774,0.00028292168,0.00019762912],"domain_scores_gemma":[0.99929017,0.0002750605,0.000045155877,0.00011435447,0.00012900263,0.00014622892],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005032146,0.00010319311,0.00022362056,0.00014912005,0.00010489002,0.000031902473,0.0000829655,0.00006160657,0.00005394049],"category_scores_gemma":[0.0008041343,0.0000933047,0.000084236795,0.00021177417,0.00005119299,0.0000483698,0.00003741737,0.00023730814,0.000012487492],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011024536,0.00023704147,0.01213466,0.0005525865,0.00014163268,0.00005355688,0.00046019885,0.00031150528,0.0009460451,0.0033372687,0.04656262,0.93515265],"study_design_scores_gemma":[0.0030210325,0.000031405536,0.006160189,0.00024617816,0.00009824455,0.00004148453,0.00005817277,0.9706023,0.000077487806,0.001971641,0.017606983,0.000084914675],"about_ca_topic_score_codex":0.0000142852805,"about_ca_topic_score_gemma":7.5109995e-7,"teacher_disagreement_score":0.9702908,"about_ca_system_score_codex":0.00006627632,"about_ca_system_score_gemma":0.00023437124,"threshold_uncertainty_score":0.3804855},"labels":[],"label_agreement":null},{"id":"W4409107652","doi":"10.1117/12.3043835","title":"Assessing the impact of a pre-processing pipeline on a tumor localization model in prostate MRI within a large multi-institutional dataset (NRG-GU005)","year":2025,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Polytechnique Montréal","funders":"","keywords":"Pipeline (software); Computer science; Prostate; Magnetic resonance imaging; Artificial intelligence; Medicine; Radiology; Internal medicine; Cancer","score_opus":0.0200883141684854,"score_gpt":0.39037405366447686,"score_spread":0.3702857394959915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409107652","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21855228,0.000116898926,0.77855384,0.0014071303,0.00004749061,0.00046253807,0.00009963632,0.000040307506,0.00071985245],"genre_scores_gemma":[0.9863442,0.000010404797,0.0107838055,0.0018486273,0.000029317966,0.000018043525,0.00067680085,0.000013891518,0.00027490314],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99865496,0.0000717104,0.00047007948,0.00027438145,0.00027746547,0.0002513793],"domain_scores_gemma":[0.9993647,0.00007145816,0.00015097037,0.00024559736,0.00009296374,0.00007434989],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001026222,0.00016885133,0.00029749685,0.00021938674,0.00015313232,0.000071105605,0.0001233226,0.00004027757,0.000019087704],"category_scores_gemma":[0.00076825,0.000092533635,0.000066916116,0.00045729542,0.00013874189,0.00022181869,0.00006461772,0.00046332157,0.0000016027639],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040759772,0.00094931026,0.03825083,0.0003756769,0.00005283605,0.000055172073,0.00090161554,0.9453,0.0020073715,0.0014694703,0.0046748687,0.00555526],"study_design_scores_gemma":[0.0026720555,0.000048252004,0.010667304,0.0009964599,0.00004057042,0.000024206807,0.00015065796,0.98469085,0.00026633302,0.00019766283,0.0001592702,0.000086369095],"about_ca_topic_score_codex":0.0004352687,"about_ca_topic_score_gemma":0.0000370612,"teacher_disagreement_score":0.7677919,"about_ca_system_score_codex":0.00015254588,"about_ca_system_score_gemma":0.00088298926,"threshold_uncertainty_score":0.3773412},"labels":[],"label_agreement":null},{"id":"W4409158860","doi":"10.1117/12.3048474","title":"Prospective study on the reproducibility of radiomic features in the setting of variable CT contrast timing: initial results","year":2025,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Reproducibility; Contrast (vision); Computer science; Variable (mathematics); Medical physics; Nuclear medicine; Biomedical engineering; Artificial intelligence; Medicine; Mathematics; Statistics","score_opus":0.018092964301217172,"score_gpt":0.33830819877797924,"score_spread":0.3202152344767621,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409158860","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9281413,0.000046051035,0.0001436371,0.012937395,0.00010955102,0.0013155423,0.0000044650033,0.00001658334,0.057285458],"genre_scores_gemma":[0.99799275,0.0000019827937,0.0003990245,0.001095483,0.00006341986,0.000024365914,0.0000034796378,0.000006515726,0.0004129468],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9981868,0.00039096098,0.00048456984,0.00049204804,0.00029098662,0.00015458855],"domain_scores_gemma":[0.9968701,0.0018173747,0.00014831433,0.0010508643,0.00009252046,0.000020841031],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.007950438,0.00010674245,0.00035934758,0.00009481621,0.00008288162,0.000009704095,0.00020605816,0.000026030513,0.00002211011],"category_scores_gemma":[0.014918989,0.00005217429,0.000056759567,0.00045635484,0.00017143047,0.00002184727,0.00005247717,0.0006212746,4.376918e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0027714777,0.002936014,0.9383529,0.00020855937,0.00039413458,0.00006162309,0.01816998,0.00031326225,0.0061964085,0.016393384,0.0108510945,0.0033511966],"study_design_scores_gemma":[0.003569976,0.0004561338,0.9819409,0.0002647411,0.00011007196,0.0000214916,0.0057832645,0.0014670305,0.004845167,0.0013794977,0.000099710705,0.00006196289],"about_ca_topic_score_codex":0.00095735793,"about_ca_topic_score_gemma":0.000020863912,"teacher_disagreement_score":0.069851466,"about_ca_system_score_codex":0.000044196895,"about_ca_system_score_gemma":0.00015135667,"threshold_uncertainty_score":0.99337876},"labels":[],"label_agreement":null},{"id":"W4409158918","doi":"10.1117/12.3047247","title":"Worse is better? Performance and bias implications of feature selection in radiomics-based survival analysis","year":2025,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Radiomics; Feature selection; Computer science; Selection (genetic algorithm); Artificial intelligence; Selection bias; Feature (linguistics); Machine learning; Pattern recognition (psychology); Statistics; Mathematics","score_opus":0.011981602620444176,"score_gpt":0.3011312971999913,"score_spread":0.28914969457954715,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409158918","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96719205,0.00009451157,0.011012744,0.019597476,0.000028399209,0.00010594847,0.0000019235772,0.000022421586,0.0019445429],"genre_scores_gemma":[0.9917831,0.00008145559,0.005680942,0.0014498044,0.00001742945,0.0000066582115,0.000017117469,0.000005211778,0.00095829164],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99940896,0.000027478554,0.00018208793,0.0001768788,0.00008818132,0.00011642214],"domain_scores_gemma":[0.9996439,0.00007863471,0.00004990803,0.00012637056,0.000052091596,0.000049099697],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028373557,0.00007608994,0.00026300215,0.00042605566,0.00004128595,0.0000104999135,0.000045991135,0.000059641094,0.000047983805],"category_scores_gemma":[0.00005719781,0.00006364316,0.00006485472,0.0014132153,0.000055928213,0.000031261996,0.000013739381,0.00024153378,5.707229e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032698168,0.000044282355,0.9747228,0.00008325307,0.00016326469,6.2399977e-7,0.000046059613,0.0003309928,0.001941677,0.00016904254,0.00072870497,0.021736622],"study_design_scores_gemma":[0.0006613731,0.000024856541,0.79705405,0.00006102703,0.00027878577,0.0000019569582,0.000022149516,0.20005225,0.0009504592,0.000030973955,0.00081779226,0.000044334603],"about_ca_topic_score_codex":0.0001754505,"about_ca_topic_score_gemma":0.000045543497,"teacher_disagreement_score":0.19972125,"about_ca_system_score_codex":0.000042018673,"about_ca_system_score_gemma":0.00007098356,"threshold_uncertainty_score":0.25952926},"labels":[],"label_agreement":null},{"id":"W4409205157","doi":"10.1186/s40658-025-00750-7","title":"Impact of harmonization and oversampling methods on radiomics analysis of multi-center imbalanced datasets: application to PET-based prediction of lung cancer subtypes","year":2025,"lang":"en","type":"article","venue":"EJNMMI Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Science and Technology Planning Project of Guangdong Province; Natural Science Foundation of Inner Mongolia; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Radiomics; Oversampling; Lung cancer; Harmonization; Center (category theory); Medicine; Medical physics; Computer science; Oncology; Radiology","score_opus":0.014848816675637288,"score_gpt":0.39577642225435966,"score_spread":0.38092760557872235,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409205157","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4121158,0.000068911555,0.58712894,0.000085941676,0.00003680304,0.00018578899,0.00035551397,0.000009193753,0.000013105133],"genre_scores_gemma":[0.96946985,0.00006806316,0.029381286,0.000114594535,0.000030331277,0.000011902357,0.0009076297,0.000010719062,0.0000056140107],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992147,0.00005133252,0.00029610316,0.00020203914,0.00014114068,0.00009469694],"domain_scores_gemma":[0.999211,0.00013333316,0.00022034768,0.00026079448,0.00012115051,0.00005337999],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025389364,0.000099163895,0.00040074816,0.00024248952,0.000025284085,0.000005102138,0.00006105386,0.000031592117,0.0000045937823],"category_scores_gemma":[0.00017215952,0.00008856096,0.00011476839,0.0008407465,0.00006223477,0.000040644118,0.000022036016,0.000114132585,6.809852e-8],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036558538,0.00052274595,0.65556383,0.0003366407,0.0015672127,3.5478172e-7,0.0002532969,0.14600332,0.15799966,0.00025444187,0.00029562233,0.036837302],"study_design_scores_gemma":[0.0012555637,0.00006670916,0.22153862,0.0001615086,0.00092831766,1.3862088e-7,0.000010032,0.7637384,0.012207716,0.000011661935,0.000039147206,0.000042209795],"about_ca_topic_score_codex":0.0002744997,"about_ca_topic_score_gemma":0.000002583916,"teacher_disagreement_score":0.6177351,"about_ca_system_score_codex":0.00009790055,"about_ca_system_score_gemma":0.00008367909,"threshold_uncertainty_score":0.36114112},"labels":[],"label_agreement":null},{"id":"W4409224354","doi":"10.1117/12.3055539","title":"Development and translation of 3D ultrasound-based imaging systems for diagnostic and image-guided interventions","year":2025,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Translation (biology); Computer science; Medical imaging; Ultrasound; Ultrasound imaging; Medical physics; Computer vision; Artificial intelligence; Radiology; Medicine","score_opus":0.022010414272084937,"score_gpt":0.3330116116407992,"score_spread":0.31100119736871423,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409224354","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23838268,0.0035136591,0.75307626,0.0025797854,0.00014755213,0.00066427846,0.0000036555248,0.00004529532,0.0015868577],"genre_scores_gemma":[0.89324397,0.000059361206,0.10609552,0.00022904783,0.000016720594,0.00004734298,0.00003106076,0.000008564067,0.00026840996],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993706,0.000018552717,0.00030251866,0.00013779265,0.00007336259,0.00009720233],"domain_scores_gemma":[0.99900967,0.00075502147,0.000049715403,0.00006835239,0.0000669718,0.000050282124],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003657776,0.0000722195,0.00018384776,0.000127919,0.00006256741,0.000027223448,0.000023598968,0.000020823907,0.000008196896],"category_scores_gemma":[0.000815055,0.000060576196,0.000038032784,0.000071572504,0.00007401343,0.00003751415,0.0000074995846,0.000069748916,2.2056656e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021678269,0.0006442667,0.32059234,0.026366355,0.0006022236,0.00002418513,0.0020105098,0.00045703823,0.07629625,0.011346122,0.0075493376,0.5538946],"study_design_scores_gemma":[0.016608585,0.00021185097,0.16924001,0.011753218,0.0012486695,0.00015922838,0.0015432066,0.75340724,0.012995494,0.0005854486,0.03170613,0.00054088834],"about_ca_topic_score_codex":0.00005013402,"about_ca_topic_score_gemma":0.0000035708106,"teacher_disagreement_score":0.75295025,"about_ca_system_score_codex":0.000019088442,"about_ca_system_score_gemma":0.00006389919,"threshold_uncertainty_score":0.24702255},"labels":[],"label_agreement":null},{"id":"W4409258035","doi":"10.5194/essd-2024-556-rc2","title":"Comment on essd-2024-556","year":2025,"lang":"en","type":"peer-review","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Tsinghua University","keywords":"Computer science","score_opus":0.02207886647073661,"score_gpt":0.3658488875201618,"score_spread":0.3437700210494252,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409258035","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[6.4208524e-7,0.012024314,0.00041580558,0.5699783,0.003275036,0.0004352696,0.00002087391,0.000080931386,0.41376883],"genre_scores_gemma":[0.000005922261,0.011515882,0.0008608334,0.39127585,0.00054627034,0.00003394775,0.0006541191,0.000026939582,0.59508026],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99796,0.00007812838,0.0004670613,0.0004896498,0.0006758076,0.00032937774],"domain_scores_gemma":[0.99854374,0.00025145683,0.00012691744,0.00071184564,0.00012399892,0.00024202291],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00063419336,0.00035975882,0.0010625139,0.00020705833,0.00006932693,0.00002723472,0.0002448837,0.00022216626,0.0075286],"category_scores_gemma":[0.0009666582,0.00025634866,0.0003295817,0.00020750755,0.00006433588,0.000011352008,0.00013395298,0.0019514409,0.00031206448],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010850617,0.00011039347,0.000018663543,0.0058332137,0.00014911576,0.00007528222,0.000005151043,0.0000010535806,8.999061e-7,0.0012291771,0.9246814,0.06788475],"study_design_scores_gemma":[0.0006228051,0.00016747195,0.000015827103,0.024381042,0.00054746337,0.000023486302,0.000004321069,0.00043702495,0.0000053786484,0.00008218742,0.973503,0.0002100157],"about_ca_topic_score_codex":0.00020885987,"about_ca_topic_score_gemma":0.0000032788582,"teacher_disagreement_score":0.18131143,"about_ca_system_score_codex":0.00016947555,"about_ca_system_score_gemma":0.00031353012,"threshold_uncertainty_score":0.99998885},"labels":[],"label_agreement":null},{"id":"W4409324328","doi":"10.1016/j.xpro.2025.103705","title":"Protocol for obtaining cancer type and subtype predictions using subSCOPE","year":2025,"lang":"en","type":"article","venue":"STAR Protocols","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre","funders":"National Institutes of Health; Canada's Michael Smith Genome Sciences Centre; National Cancer Institute; Foundation for the National Institutes of Health","keywords":"Protocol (science); Type (biology); Cancer; Computational biology; Computer science; Biology; Medicine; Genetics; Pathology; Paleontology","score_opus":0.06690811567861747,"score_gpt":0.46261359128293317,"score_spread":0.3957054756043157,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409324328","genre_codex":"protocol","genre_gemma":"protocol","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"protocol","genre_consensus":"protocol","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035930853,0.00001630973,0.009545558,0.0013533209,0.000084261424,0.9825597,0.000007985259,0.0001123939,0.002727378],"genre_scores_gemma":[0.002621342,0.000001070392,0.0151805505,0.0006004348,0.00019226449,0.9802234,0.0000052989885,0.000025847541,0.0011497597],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990687,0.000034017256,0.00024352116,0.00026598762,0.0001326618,0.00025513576],"domain_scores_gemma":[0.99933726,0.000067159286,0.00007851563,0.00018489733,0.0002246429,0.00010751006],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034631265,0.00013105554,0.00024543182,0.00011356968,0.00020784346,0.000048212307,0.000067199035,0.00007490058,0.00008480843],"category_scores_gemma":[0.0004819743,0.00010858246,0.000037883197,0.0003171353,0.00009128138,0.00006559016,0.000062923194,0.00025882784,0.0000012111931],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.010873743,0.0011498714,0.5544388,0.018244803,0.0011790962,0.000072090275,0.0018690022,0.0013981852,0.078695245,0.02000386,0.063575566,0.24849972],"study_design_scores_gemma":[0.012571266,0.0010748642,0.01350323,0.0053911987,0.00019717518,0.00003275881,0.00013496495,0.16787787,0.0029347944,0.0028004185,0.79312754,0.00035390016],"about_ca_topic_score_codex":0.000087302986,"about_ca_topic_score_gemma":0.000005321913,"teacher_disagreement_score":0.729552,"about_ca_system_score_codex":0.00008844983,"about_ca_system_score_gemma":0.00060031464,"threshold_uncertainty_score":0.44278643},"labels":[],"label_agreement":null},{"id":"W4409341299","doi":"10.1007/s00261-025-04884-1","title":"Improving radiologists’ diagnostic accuracy for lymphovascular invasion in colorectal cancer: insights from a multicenter CT-based study","year":2025,"lang":"en","type":"article","venue":"Abdominal Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Minnow Environmental (Canada)","funders":"High-level Hospital Construction Project of Guangdong Provincial People's Hospital","keywords":"Medicine; Hepatology; Colorectal cancer; Lymphovascular invasion; Internal medicine; Radiology; Multicenter study; Oncology; Cancer; General surgery; Medical physics; Metastasis","score_opus":0.010127234944652168,"score_gpt":0.3049101834497456,"score_spread":0.2947829485050934,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409341299","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9826253,0.0028866343,0.010167247,0.0014079548,0.0008088485,0.0019835152,0.000008014852,0.00005839486,0.00005407487],"genre_scores_gemma":[0.99400043,0.00012849942,0.0028333883,0.0019376966,0.00024315905,0.0007267251,0.00007857984,0.000028651499,0.000022838532],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99779207,0.00034106022,0.000577154,0.00068838376,0.0001513496,0.00044996652],"domain_scores_gemma":[0.9939695,0.0053446754,0.00016508224,0.00030556737,0.00007953281,0.00013562875],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00049563695,0.00027921912,0.00084804726,0.0003399756,0.00012806279,0.000022903494,0.00025365283,0.00012811196,0.000036247708],"category_scores_gemma":[0.009610693,0.00022865468,0.00019364503,0.0002623161,0.00019121985,0.000060134487,0.00008179618,0.00047308736,0.0000050086023],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0032122298,0.0010601,0.83912706,0.00019837508,0.0004201772,0.0010630635,0.00071479636,0.0013277101,0.049044088,0.00008300731,0.0006186616,0.10313076],"study_design_scores_gemma":[0.034123648,0.0013269142,0.690107,0.000551866,0.0007448086,0.00006974169,0.0008576063,0.26447085,0.0053950204,0.00028515208,0.0016531212,0.00041428464],"about_ca_topic_score_codex":0.0044678757,"about_ca_topic_score_gemma":0.00044230395,"teacher_disagreement_score":0.26314315,"about_ca_system_score_codex":0.0004189108,"about_ca_system_score_gemma":0.00044564836,"threshold_uncertainty_score":0.9987318},"labels":[],"label_agreement":null},{"id":"W4409367057","doi":"10.3390/curroncol32040223","title":"Computed Tomography-Based Radiomic Nomogram to Predict Occult Pleural Metastasis in Lung Cancer","year":2025,"lang":"en","type":"article","venue":"Current Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Peking University People's Hospital; Peking University","keywords":"Medicine; Nomogram; Radiomics; Occult; Lung cancer; Computed tomography; Radiology; Metastasis; Cancer; Pathology; Oncology; Internal medicine","score_opus":0.03914368060249034,"score_gpt":0.4240551749817113,"score_spread":0.38491149437922095,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409367057","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9422567,0.0075590885,0.022766694,0.020423636,0.0043383925,0.0013135244,0.000036985533,0.00020935101,0.0010956244],"genre_scores_gemma":[0.9908098,0.00010939436,0.004552874,0.00375321,0.00029593,0.00024881092,0.00011593221,0.000024842413,0.000089236986],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982073,0.0001830739,0.0004613329,0.00045533082,0.0002063401,0.00048664445],"domain_scores_gemma":[0.9990602,0.00021275584,0.00008743567,0.00026507536,0.000100307385,0.00027418433],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045107675,0.00021959693,0.00064437086,0.00083374,0.00006880885,0.000020918691,0.0002187275,0.00011376541,0.00010215838],"category_scores_gemma":[0.00027130058,0.00019433895,0.00017854915,0.0011344576,0.00013786885,0.000034103305,0.000083296625,0.00076591154,0.000006141161],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029597475,0.0006601956,0.64083385,0.00037165574,0.00015605876,0.00006912462,0.00018752413,0.0016701638,0.00049762486,0.0001546777,0.034674715,0.3204284],"study_design_scores_gemma":[0.007878257,0.0003869808,0.30598977,0.0009652027,0.00043779027,0.000018198105,0.000055359273,0.33834752,0.00023358951,0.000037840313,0.3453722,0.00027725726],"about_ca_topic_score_codex":0.00018057767,"about_ca_topic_score_gemma":0.000083529005,"teacher_disagreement_score":0.33667737,"about_ca_system_score_codex":0.00048038163,"about_ca_system_score_gemma":0.00057607674,"threshold_uncertainty_score":0.79249126},"labels":[],"label_agreement":null},{"id":"W4409402564","doi":"10.1101/2025.04.11.25325702","title":"Peritoneal Metastasis Prediction in Gastric Cancer: A Machine Learning Approach","year":2025,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University","funders":"","keywords":"Metastasis; Cancer; Computer science; Medicine; Artificial intelligence; Machine learning; Internal medicine","score_opus":0.020037948116381283,"score_gpt":0.30202599380911516,"score_spread":0.2819880456927339,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409402564","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9512837,0.01037784,0.014924481,0.004535647,0.0017569474,0.0013240464,0.00016426296,0.000464302,0.015168807],"genre_scores_gemma":[0.973857,0.003430376,0.013729344,0.0005097854,0.0007956653,0.00047291897,0.0007233539,0.0000808782,0.0064006676],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99710685,0.00030478853,0.0006577647,0.0008731797,0.0005581706,0.0004992227],"domain_scores_gemma":[0.9988783,0.00008985263,0.0002289574,0.00047606914,0.0000913603,0.000235431],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0011562109,0.00042111287,0.00096398505,0.00080518704,0.00011020431,0.000058198333,0.0002954689,0.00033317856,0.00019264882],"category_scores_gemma":[0.0006749362,0.0003821256,0.00026883022,0.00061003066,0.00010969926,0.000044603148,0.00047135985,0.004367513,0.0000071810905],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012137579,0.00029868077,0.9088239,0.0014511708,0.00031217016,0.000120706565,0.0005821237,0.030883348,0.00047922358,0.000049208298,0.0005116015,0.0563665],"study_design_scores_gemma":[0.002137102,0.00011817867,0.13454731,0.0015150267,0.00067955244,0.00011980844,0.00009657007,0.8369853,0.00011877808,0.00008772989,0.02320932,0.000385345],"about_ca_topic_score_codex":0.0017226633,"about_ca_topic_score_gemma":0.000028696852,"teacher_disagreement_score":0.8061019,"about_ca_system_score_codex":0.00034310884,"about_ca_system_score_gemma":0.00047988744,"threshold_uncertainty_score":0.9998631},"labels":[],"label_agreement":null},{"id":"W4409403480","doi":"10.1101/2025.04.11.25325700","title":"Measured intrapatient radiomic variability as a predictor of treatment response in multi-metastatic soft tissue sarcoma patients","year":2025,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; Princess Margaret Cancer Centre; University of Toronto","funders":"Sarcoma Alliance for Research through Collaboration","keywords":"Medicine; Sarcoma; Soft tissue sarcoma; Oncology; Biopsy; Soft tissue; Internal medicine; Pathology","score_opus":0.02276686643766902,"score_gpt":0.3218531291122758,"score_spread":0.2990862626746068,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409403480","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9909067,0.00030622934,0.004277997,0.0008014944,0.00094815873,0.002377574,0.00015877905,0.000082810635,0.00014022118],"genre_scores_gemma":[0.98915005,0.00010866193,0.009531943,0.00017223983,0.000051436797,0.00024549308,0.00024866685,0.000046657602,0.00044483348],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9952302,0.001461076,0.0013042698,0.00091742387,0.0006278929,0.0004591317],"domain_scores_gemma":[0.9968857,0.00094167946,0.00046591187,0.001124202,0.00026379,0.0003187144],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0025297082,0.00052394177,0.0014583829,0.00063796964,0.000048543578,0.000021419308,0.00035016664,0.00027788515,0.00009320717],"category_scores_gemma":[0.008701422,0.0004391112,0.00027842371,0.00034091252,0.0002526429,0.000035255485,0.00029876299,0.0010469725,0.000008739345],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.006074926,0.0046756063,0.94339126,0.0018154427,0.0006399722,0.0001557963,0.003913764,0.0014803197,0.005280845,0.000026072068,0.00011048619,0.03243553],"study_design_scores_gemma":[0.015788373,0.0032176487,0.9011275,0.0028084225,0.0008410456,0.000018979075,0.00006270703,0.06917383,0.0030201655,0.0005131773,0.0028796212,0.00054849725],"about_ca_topic_score_codex":0.0007890829,"about_ca_topic_score_gemma":0.000018828543,"teacher_disagreement_score":0.06769351,"about_ca_system_score_codex":0.0011710941,"about_ca_system_score_gemma":0.0014620884,"threshold_uncertainty_score":0.99980605},"labels":[],"label_agreement":null},{"id":"W4409503838","doi":"10.1148/ryai.240528","title":"The BraTS-Africa Dataset: Expanding the Brain Tumor Segmentation Data to Capture African Populations","year":2025,"lang":"en","type":"article","venue":"Radiology Artificial Intelligence","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Montreal Neurological Institute and Hospital; Lawson Health Research Institute; McGill University; University of British Columbia","funders":"National Cancer Institute","keywords":"Segmentation; Computer science; Artificial intelligence","score_opus":0.08928174279245121,"score_gpt":0.40137051459818235,"score_spread":0.31208877180573114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409503838","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045334164,0.0018735868,0.54066867,0.40364817,0.0028931568,0.0017784426,0.00037127384,0.00016357902,0.0032689786],"genre_scores_gemma":[0.98376215,0.000042066185,0.0037524719,0.01013126,0.00040719382,0.000064257685,0.0007033948,0.00001828653,0.0011189202],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983471,0.0002550582,0.0004358761,0.00042605225,0.00017778021,0.00035814187],"domain_scores_gemma":[0.9976889,0.0010624862,0.0000961149,0.0009888307,0.000052102823,0.000111598456],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014048953,0.00014593563,0.0002108586,0.0001064378,0.00087118737,0.00009268244,0.0007446517,0.000059415852,0.00008140588],"category_scores_gemma":[0.003428572,0.00008660214,0.000040781666,0.0005559254,0.00037082442,0.00008176918,0.00025337673,0.00053361274,0.000076718265],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042532588,0.00015417431,0.0029201952,0.000038298105,0.00022817458,0.000085267944,0.0041569243,0.0032827172,0.028084377,0.11474447,0.5834493,0.2624308],"study_design_scores_gemma":[0.000262574,0.00030962692,0.008515775,0.00023431575,0.00045317752,0.00041296356,0.015331965,0.24174154,0.0048048836,0.02913942,0.6982046,0.00058916135],"about_ca_topic_score_codex":0.00021584392,"about_ca_topic_score_gemma":0.00023262166,"teacher_disagreement_score":0.938428,"about_ca_system_score_codex":0.0000755856,"about_ca_system_score_gemma":0.000133151,"threshold_uncertainty_score":0.6700557},"labels":[],"label_agreement":null},{"id":"W4409609524","doi":"10.1007/s10143-025-03528-8","title":"MRI histogram and Visually AcceSAble Rembrandt Images features nomogram to predict PD-L1 levels in glioblastoma","year":2025,"lang":"en","type":"article","venue":"Neurosurgical Review","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"National Natural Science Foundation of China","keywords":"Glioblastoma; Medicine; Nomogram; Neurosurgery; Histogram; Radiology; Nuclear medicine; Artificial intelligence; Oncology; Image (mathematics); Cancer research","score_opus":0.010685525215394884,"score_gpt":0.33828092931235004,"score_spread":0.32759540409695515,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409609524","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33032134,0.39086583,0.0029183133,0.19679554,0.0018709262,0.007863136,0.00004012243,0.00087488623,0.068449914],"genre_scores_gemma":[0.7282239,0.16919313,0.003326319,0.08439076,0.0003459357,0.00029180504,0.000021147544,0.00011519721,0.014091777],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99782616,0.00019017364,0.000577973,0.000608239,0.00036636632,0.00043109406],"domain_scores_gemma":[0.9987602,0.00032453844,0.00008176398,0.00037897236,0.000070359696,0.000384139],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007917711,0.00026927685,0.0008839868,0.00022706663,0.00008007803,0.00008219183,0.00021336437,0.00010027242,0.00013541263],"category_scores_gemma":[0.0022853208,0.00020683098,0.00016741626,0.000865829,0.00014262456,0.00008405956,0.00017797331,0.0008036522,0.00001971687],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00065093685,0.00064187613,0.025063349,0.011430373,0.00007960592,0.0015061814,0.000059730493,0.00003917154,0.0037270144,0.0010683102,0.1366773,0.81905615],"study_design_scores_gemma":[0.001796429,0.00046069646,0.09974125,0.0097452765,0.00016407653,0.00028226656,0.0000030755477,0.00046909272,0.00018083482,0.000081161576,0.8868529,0.00022294334],"about_ca_topic_score_codex":0.00003514492,"about_ca_topic_score_gemma":0.000006759888,"teacher_disagreement_score":0.81883323,"about_ca_system_score_codex":0.000059907466,"about_ca_system_score_gemma":0.000105281026,"threshold_uncertainty_score":0.8434323},"labels":[],"label_agreement":null},{"id":"W4409614269","doi":"10.14740/gr2011","title":"Large Language Models in Gastroenterology and Gastrointestinal Surgery: A New Frontier in Patient Communication and Education","year":2025,"lang":"en","type":"review","venue":"Gastroenterology Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine; Frontier; General surgery; Gastroenterology; Internal medicine","score_opus":0.039561562576874466,"score_gpt":0.3960311331025263,"score_spread":0.3564695705256518,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409614269","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08544358,0.9107267,0.00050748506,0.0019013399,0.000086174456,0.0011008241,0.000013395202,0.000019977553,0.00020048732],"genre_scores_gemma":[0.007888429,0.9879712,0.0026575215,0.0005020083,0.00006814122,0.0002211914,0.00029466292,0.000039566636,0.00035728584],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.9957311,0.0017706067,0.00074611563,0.0006104552,0.00025862374,0.0008830988],"domain_scores_gemma":[0.99840033,0.0005909313,0.00016323665,0.0004895864,0.00008139106,0.0002745495],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0021296777,0.0002964249,0.0015235066,0.0018439388,0.00006819452,0.000037271904,0.00020333921,0.00018696164,0.00002280931],"category_scores_gemma":[0.0008493052,0.0002692763,0.00011193128,0.00032899392,0.00030049527,0.00008370934,0.00051256653,0.0024731997,0.0000027242095],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005516332,0.0005484961,0.27735934,0.0071402923,0.00005919664,0.0002340408,0.000727246,0.0000027797798,0.0000014058738,0.00009136115,0.0076021696,0.70568204],"study_design_scores_gemma":[0.022468045,0.0072239423,0.18691179,0.4061718,0.0015779623,0.033274725,0.0072541474,0.019678216,6.2185643e-7,0.004592361,0.3092299,0.0016164493],"about_ca_topic_score_codex":0.00053599227,"about_ca_topic_score_gemma":0.0005735658,"teacher_disagreement_score":0.7040656,"about_ca_system_score_codex":0.00021658429,"about_ca_system_score_gemma":0.0007857849,"threshold_uncertainty_score":0.9999759},"labels":[],"label_agreement":null},{"id":"W4409616278","doi":"10.1101/2025.04.17.25325994","title":"Mammographic density, pathogenic breast cancer susceptibility gene variants and breast cancer risk","year":2025,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency; Queen's University","funders":"NIHR Cambridge Biomedical Research Centre; European Commission; Department of Health and Social Care; National Cancer Institute; National Institutes of Health; Cancer Research UK; Government of Canada; Fondation du cancer du sein du Québec; Canadian Institutes of Health Research; National Institute for Health and Care Research; Genome Canada","keywords":"Breast cancer; MAMMOGRAPHIC DENSITY; Oncology; Gene; Cancer; Medicine; Internal medicine; Biology; Genetics; Mammography","score_opus":0.009814827238769929,"score_gpt":0.2877462909703295,"score_spread":0.2779314637315596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409616278","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9819952,0.004441446,0.00073790626,0.008198512,0.001711866,0.00070940185,0.0018405083,0.0001750478,0.00019006761],"genre_scores_gemma":[0.9792222,0.016809935,0.0009695631,0.0010964836,0.001016901,0.00012789259,0.00008307739,0.00006517179,0.00060881494],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9964463,0.00033686354,0.00062470644,0.0013813765,0.0005785613,0.0006321676],"domain_scores_gemma":[0.9975275,0.00012692557,0.00037120687,0.0010842576,0.00033827522,0.0005518696],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0013031476,0.000583057,0.001093703,0.0003504252,0.00023410397,0.00009285014,0.00036552115,0.0004904291,0.0005247963],"category_scores_gemma":[0.00021216071,0.000500723,0.0003489525,0.0003932986,0.00040707138,0.00005143656,0.0009880458,0.002663212,0.0000062563136],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017210472,0.0001512566,0.95168865,0.0008956468,0.0005690546,0.00017423183,0.00013482086,0.00011372794,0.0035447737,0.000018804363,0.0004304891,0.04210643],"study_design_scores_gemma":[0.001211369,0.000020274989,0.9865642,0.0011771467,0.0012979377,0.0005243333,0.000016115899,0.007870095,0.0000719396,0.0005518462,0.00027055113,0.00042414403],"about_ca_topic_score_codex":0.010536197,"about_ca_topic_score_gemma":0.0008573147,"teacher_disagreement_score":0.041682288,"about_ca_system_score_codex":0.00021964844,"about_ca_system_score_gemma":0.0007713915,"threshold_uncertainty_score":0.9997444},"labels":[],"label_agreement":null},{"id":"W4409624640","doi":"10.1158/1538-7445.am2025-1911","title":"Abstract 1911: Platform agnostic lung cancer plasma signature identified using multidimensional proteomics and explainable machine learning","year":2025,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto; Princess Margaret Cancer Centre","funders":"","keywords":"Signature (topology); Lung cancer; Proteomics; Computer science; Computational biology; Cancer; Medicine; Oncology; Internal medicine; Biology; Mathematics; Biochemistry","score_opus":0.0410544893370022,"score_gpt":0.4100107171718888,"score_spread":0.36895622783488663,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409624640","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9849661,0.009697055,0.0005215751,0.0027517916,0.0003717254,0.0009282401,0.000014723614,0.00006503297,0.00068375195],"genre_scores_gemma":[0.99105394,0.0019920284,0.002024984,0.000307757,0.00029200377,0.00018733143,0.00003451039,0.000051615232,0.0040558497],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99758375,0.000086821434,0.0003273563,0.0005483346,0.00072685524,0.0007268595],"domain_scores_gemma":[0.99850845,0.0005513262,0.00008278523,0.00022816601,0.00034543755,0.00028385784],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.001335858,0.00021905605,0.0003859629,0.0004668303,0.000703625,0.00010815201,0.0001557911,0.00019370935,0.00035272408],"category_scores_gemma":[0.0013803802,0.00018964194,0.000069033136,0.0005650496,0.00029023032,0.00016666378,0.00024711396,0.0028370265,0.0000041219464],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015261582,0.00021208698,0.11298176,0.0034642385,0.00057445234,0.0006211509,0.0011096237,0.021946564,0.81772035,0.0009424158,0.0070505706,0.031850625],"study_design_scores_gemma":[0.006074851,0.000120360666,0.027761817,0.005372945,0.00021929137,0.00007839875,0.00043490482,0.90366966,0.038911253,0.00027280857,0.016597759,0.0004859391],"about_ca_topic_score_codex":0.0038145378,"about_ca_topic_score_gemma":0.00008566366,"teacher_disagreement_score":0.8817231,"about_ca_system_score_codex":0.00059041753,"about_ca_system_score_gemma":0.00089143036,"threshold_uncertainty_score":0.99946344},"labels":[],"label_agreement":null},{"id":"W4409628583","doi":"10.1158/1538-7445.am2025-5043","title":"Abstract 5043: reVUE: repository for variants with unexpected effects","year":2025,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Institute for Cancer Research","funders":"","keywords":"Biology; Medicine; Computational biology; Genetics","score_opus":0.026517021448140166,"score_gpt":0.41739399071652933,"score_spread":0.39087696926838916,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409628583","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94531536,0.0026004845,0.0030719019,0.013550922,0.00069819466,0.0016661762,0.0000042247143,0.00012351657,0.032969244],"genre_scores_gemma":[0.9809986,0.000107328495,0.0013396661,0.00043083733,0.0004977094,0.00043817572,0.000010428619,0.000030017849,0.016147258],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99871236,0.00006283072,0.00015834153,0.0003353894,0.00032315537,0.00040792677],"domain_scores_gemma":[0.99859965,0.0005609392,0.000032208576,0.00032476007,0.00032341864,0.0001590472],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00066495803,0.000095302305,0.00023403039,0.00021921303,0.00022700886,0.000048470192,0.00014421955,0.00007395919,0.000036479247],"category_scores_gemma":[0.0008415199,0.00007265903,0.00004877061,0.00046430877,0.0001706633,0.000039438048,0.000039886363,0.0007207823,0.000005095837],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003193977,0.00039541718,0.031610735,0.0071266186,0.00070457073,0.0009832163,0.00064324215,0.0001293297,0.7178717,0.0036617455,0.12930769,0.10437175],"study_design_scores_gemma":[0.01918825,0.0018741866,0.60846555,0.015531887,0.00040462386,0.00019130007,0.0004126981,0.0099391425,0.13957478,0.0019353098,0.20179638,0.0006858923],"about_ca_topic_score_codex":0.0003202942,"about_ca_topic_score_gemma":0.0000087015105,"teacher_disagreement_score":0.57829696,"about_ca_system_score_codex":0.0002202717,"about_ca_system_score_gemma":0.0005975759,"threshold_uncertainty_score":0.31314808},"labels":[],"label_agreement":null},{"id":"W4409629526","doi":"10.1158/1538-7445.am2025-6250","title":"Abstract 6250: Clinical significance of co localization index in rectal cancer: a deep learning approach to cell interaction analysis","year":2025,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Colorectal cancer; Cancer; Medicine; Oncology; Internal medicine","score_opus":0.0606715627317647,"score_gpt":0.48088089536944556,"score_spread":0.42020933263768084,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409629526","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93341756,0.00084955205,0.048987016,0.00152991,0.00020365349,0.00067279127,0.000003682598,0.000032450676,0.014303408],"genre_scores_gemma":[0.99715656,0.0009835263,0.00026206137,0.00028721656,0.00014608279,0.00018581444,0.000029009025,0.00001869803,0.000931035],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99757785,0.0003690994,0.0006017031,0.0004906478,0.0005820352,0.0003786833],"domain_scores_gemma":[0.9986431,0.00042258066,0.00012024044,0.00024637167,0.00033863678,0.0002290467],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026622606,0.00011714658,0.0005012757,0.0011808872,0.000094529925,0.00003436515,0.00019176248,0.00013489852,0.00017434575],"category_scores_gemma":[0.0014729975,0.00010993035,0.00013367184,0.0031179597,0.00018262054,0.00006845061,0.00006903937,0.001750906,0.0000056817817],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00067631534,0.00034018865,0.71749455,0.00044561768,0.00023601088,0.000011049367,0.0006437377,0.18358864,0.0053490563,0.000035897527,0.0014867648,0.0896922],"study_design_scores_gemma":[0.0019045267,0.00017722248,0.40407753,0.00065753656,0.00019143679,0.0000011637466,0.001225623,0.57360035,0.0035123623,0.000037109712,0.014427239,0.00018792477],"about_ca_topic_score_codex":0.0058691013,"about_ca_topic_score_gemma":0.00030278263,"teacher_disagreement_score":0.3900117,"about_ca_system_score_codex":0.000484007,"about_ca_system_score_gemma":0.0006049713,"threshold_uncertainty_score":0.8872365},"labels":[],"label_agreement":null},{"id":"W4409630493","doi":"10.1158/1538-7445.am2025-7442","title":"Abstract 7442: Transforming breast cancer treatment decisions: AI tools improve Ki67 risk assessments with 90 pathologists","year":2025,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University Health Network; Toronto Metropolitan University","funders":"","keywords":"Medicine; Breast cancer; Oncology; Cancer; Risk assessment; Internal medicine; Gynecology; Computer science","score_opus":0.06110342346838599,"score_gpt":0.4816820623252491,"score_spread":0.42057863885686314,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409630493","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97282875,0.002582128,0.0023427836,0.015812298,0.00036228015,0.0013034487,0.00023382896,0.00007907865,0.004455431],"genre_scores_gemma":[0.9859195,0.008551639,0.0006587976,0.00070492795,0.0002929489,0.0008248042,0.000026845064,0.00004271105,0.002977854],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9973358,0.00013279975,0.00033885444,0.00061102095,0.0008210742,0.0007604744],"domain_scores_gemma":[0.99827087,0.00047176474,0.00007154777,0.0004777518,0.0003911174,0.00031692613],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011224226,0.00023928564,0.0004423889,0.00032196258,0.00039163005,0.00015412834,0.00023937458,0.00013075535,0.00047541474],"category_scores_gemma":[0.0003234548,0.00015577234,0.000113302434,0.00060043257,0.000331846,0.00018322324,0.00005909591,0.0013924399,0.000016368069],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00092313375,0.0002668328,0.059404254,0.00012343953,0.0002934723,0.00028635404,0.0002453887,0.00021448635,0.012765461,0.00007879785,0.0017382381,0.92366016],"study_design_scores_gemma":[0.019027462,0.002065393,0.8505556,0.0072464794,0.0007192226,0.00018062424,0.0016210243,0.006614749,0.015421614,0.0009939229,0.09468768,0.0008662406],"about_ca_topic_score_codex":0.0053788093,"about_ca_topic_score_gemma":0.00033785825,"teacher_disagreement_score":0.9227939,"about_ca_system_score_codex":0.001241005,"about_ca_system_score_gemma":0.0018295755,"threshold_uncertainty_score":0.81311864},"labels":[],"label_agreement":null},{"id":"W4409630494","doi":"10.1158/1538-7445.am2025-7433","title":"Abstract 7433: Predicting overall survival (OS) differences using longitudinal AI-driven imaging-based prognostication (IPRO) in patients with advanced non-small cell lung cancer (aNSCLC)","year":2025,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Lung cancer; Medicine; Internal medicine; Cancer; Lung; Oncology","score_opus":0.026888659920506756,"score_gpt":0.3791821962755002,"score_spread":0.35229353635499344,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409630494","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99242455,0.0008718955,0.0023954723,0.0018431955,0.00029008425,0.0014316723,0.000019124749,0.00005005356,0.0006739281],"genre_scores_gemma":[0.9981349,0.00009142893,0.0008921195,0.00021013801,0.00016583163,0.00029935053,0.000040931005,0.000046508478,0.00011879767],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9970817,0.00012896795,0.00040242836,0.00068323687,0.0009081783,0.0007955067],"domain_scores_gemma":[0.9983535,0.0003322245,0.00012815026,0.00033612523,0.0006344505,0.00021558207],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00072580006,0.00024814266,0.00041825883,0.0004851271,0.00024890088,0.00010830228,0.00028317203,0.0000850856,0.00010954313],"category_scores_gemma":[0.00033812015,0.00020409057,0.000060087998,0.00070834695,0.00025479376,0.00017652538,0.00009868957,0.0014390626,0.0000016468455],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006264275,0.00028264592,0.98020846,0.0008989689,0.000051375253,0.0000270226,0.00020753138,0.0063985228,0.0037180595,0.000011634037,0.00011168602,0.007457684],"study_design_scores_gemma":[0.004290543,0.00009892881,0.8345389,0.0029825296,0.00006636673,3.5689584e-7,0.00006144671,0.15692976,0.0007886817,0.000013524313,0.000061873994,0.00016708653],"about_ca_topic_score_codex":0.0035875791,"about_ca_topic_score_gemma":0.00029293803,"teacher_disagreement_score":0.15053123,"about_ca_system_score_codex":0.0007943319,"about_ca_system_score_gemma":0.0015721902,"threshold_uncertainty_score":0.8322572},"labels":[],"label_agreement":null},{"id":"W4409632226","doi":"10.1158/1538-7445.am2025-5781","title":"Abstract 5781: Comparing prognostic association of manual vs. artificial intelligence derived quantifications from baseline computed tomography scans in MYSTIC, a global phase 3 trial for treatment of metastatic non-small cell lung cancer","year":2025,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Medicine; Computed tomography; Baseline (sea); Internal medicine; Nuclear medicine; Oncology; Radiology; Biology","score_opus":0.09449158892061528,"score_gpt":0.46828333748308754,"score_spread":0.37379174856247227,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409632226","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9486396,0.0010188894,0.045814894,0.0013574667,0.00030582023,0.0024770983,0.0003102932,0.000015074806,0.00006087973],"genre_scores_gemma":[0.99585646,0.0002182455,0.0028221605,0.000024917836,0.00014902015,0.00069075887,0.00019273808,0.000013447364,0.000032230102],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978691,0.00019216047,0.00076253293,0.0003689859,0.00042778937,0.00037944128],"domain_scores_gemma":[0.99733764,0.0015402811,0.0002446161,0.00022198423,0.00053623406,0.00011926273],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012068088,0.0001466426,0.00062509376,0.00037399266,0.00009094446,0.000030670355,0.00016624694,0.000069381895,0.000068727866],"category_scores_gemma":[0.00083574466,0.00013427962,0.0001433109,0.00093188614,0.00013665057,0.000035380403,0.000030760624,0.00022963641,7.2776385e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.069272004,0.015454396,0.495204,0.005118526,0.002626181,0.000055041524,0.005435916,0.026047897,0.17601101,0.0010573422,0.001980929,0.20173676],"study_design_scores_gemma":[0.04069835,0.0011968911,0.06761144,0.0019586761,0.000923461,4.1735836e-7,0.00090650946,0.8178651,0.067887925,0.0004992907,0.0002176014,0.00023436935],"about_ca_topic_score_codex":0.009676992,"about_ca_topic_score_gemma":0.0025369064,"teacher_disagreement_score":0.7918172,"about_ca_system_score_codex":0.0007986741,"about_ca_system_score_gemma":0.0010679594,"threshold_uncertainty_score":0.99691767},"labels":[],"label_agreement":null},{"id":"W4409632514","doi":"10.1158/1538-7445.am2025-4657","title":"Abstract 4657: Investigating the role of circulating bone cells in melanoma patients on immune checkpoint inhibitor therapy","year":2025,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Melanoma; Medicine; Immune system; Cancer research; Immune checkpoint; Immunology; Immunotherapy","score_opus":0.031107553960477367,"score_gpt":0.3728583107759894,"score_spread":0.34175075681551204,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409632514","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9898013,0.002020609,0.0000025792838,0.0025712813,0.00013545713,0.0004949523,0.0000027047533,0.000012738253,0.004958416],"genre_scores_gemma":[0.99904317,0.00023809404,0.00008467648,0.00028112726,0.00012331954,0.00006729623,0.000006004689,0.000019562909,0.00013675693],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99824625,0.00014699146,0.00042503222,0.0002388727,0.00058816775,0.00035470258],"domain_scores_gemma":[0.99895465,0.00039282313,0.00009578647,0.00029998596,0.00017594546,0.000080799546],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017838338,0.00010408101,0.0002572886,0.000254593,0.00013172485,0.000026372281,0.00017397887,0.0000666392,0.00006923932],"category_scores_gemma":[0.00085647014,0.00007111749,0.00006859321,0.0005720993,0.00025275588,0.00003440263,0.00008418914,0.0012232908,0.000005412379],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001170238,0.00016250162,0.13967866,0.00013913265,0.00003700165,0.000009102984,0.0010638008,0.00021244818,0.7247574,0.00018867195,0.00017542137,0.13345887],"study_design_scores_gemma":[0.0028936754,0.00020345302,0.5109585,0.002430659,0.000007621934,0.0000010156489,0.0007459155,0.0037486958,0.4748728,0.0010872261,0.002939798,0.0001106636],"about_ca_topic_score_codex":0.0020913514,"about_ca_topic_score_gemma":0.000015016623,"teacher_disagreement_score":0.37127984,"about_ca_system_score_codex":0.0002072041,"about_ca_system_score_gemma":0.00031355256,"threshold_uncertainty_score":0.53146577},"labels":[],"label_agreement":null},{"id":"W4409683061","doi":"10.1007/978-3-031-85572-6_22","title":"Radiomics Prediction of Pathologic Complete Response to Neoadjuvant Chemotherapy in Breast Cancer: Interpretation and Imaging Pitfalls","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Radiomics; Medicine; Breast cancer; Radiology; Complete response; Chemotherapy; Neoadjuvant therapy; Oncology; Cancer; Internal medicine","score_opus":0.01094596437970714,"score_gpt":0.2592891055959499,"score_spread":0.2483431412162428,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409683061","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03087499,0.0008978577,0.9524598,0.013627997,0.00043266208,0.0010013509,0.00027629614,0.000038419275,0.00039061837],"genre_scores_gemma":[0.28982857,0.0007942473,0.70803666,0.0011255976,0.000089667,0.000025773468,0.000048091224,0.000018958237,0.000032437827],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99914217,0.000013703416,0.00048701762,0.00010746307,0.00012983294,0.00011983247],"domain_scores_gemma":[0.99917495,0.0002384966,0.00023983615,0.00020962866,0.00010027039,0.000036798836],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048597515,0.0001524637,0.00035935792,0.00030364396,0.00016874712,0.00003641137,0.0002930202,0.0000885889,6.1725285e-7],"category_scores_gemma":[0.00009240845,0.00012298477,0.00007974286,0.0001528274,0.0002843121,0.00008311472,0.0001817549,0.00032934835,3.0427827e-8],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001937045,0.00003663898,0.001016581,0.00096486363,0.00013570247,6.794218e-7,0.006379767,0.72609854,0.0012019941,0.003823547,0.00010365604,0.2600443],"study_design_scores_gemma":[0.0006233846,0.000062507526,0.006554471,0.0013414974,0.00005739931,0.000039073853,0.000010011672,0.98774344,0.000030572024,0.00019496506,0.003224142,0.00011852681],"about_ca_topic_score_codex":0.00006494005,"about_ca_topic_score_gemma":0.000011617122,"teacher_disagreement_score":0.2616449,"about_ca_system_score_codex":0.00008178049,"about_ca_system_score_gemma":0.0001367365,"threshold_uncertainty_score":0.50151736},"labels":[],"label_agreement":null},{"id":"W4409683529","doi":"10.1109/tnnls.2025.3555188","title":"Synchronous Image-Label Diffusion Probability Model With Application to Stroke Lesion Segmentation on Non-Contrast CT","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks and Learning Systems","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"High Performance Computing Platform of Jiangsu University; National Key Research and Development Program of China","keywords":"Contrast (vision); Artificial intelligence; Stroke (engine); Lesion; Segmentation; Diffusion; Image (mathematics); Medicine; Computer science; Radiology; Computer vision; Pattern recognition (psychology); Pathology; Physics","score_opus":0.00819196763442221,"score_gpt":0.2650268826317307,"score_spread":0.2568349149973085,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409683529","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3958036,0.00003187442,0.60227,0.00059362734,0.00017749156,0.00084260583,0.000001934497,0.00008654089,0.00019229208],"genre_scores_gemma":[0.99644065,0.00005516798,0.0014235176,0.00044079436,0.00009064524,0.00020481403,0.000013749147,0.00003197098,0.0012986897],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984807,0.0001406834,0.00032268077,0.000502059,0.0002679274,0.0002859466],"domain_scores_gemma":[0.9992385,0.00016324077,0.000101858015,0.00023388845,0.00007939435,0.00018312597],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003580776,0.00023822596,0.00035532805,0.00017641667,0.0005023656,0.00009888615,0.000067493165,0.00007437912,0.00000281434],"category_scores_gemma":[0.000015482563,0.00018326334,0.00005668613,0.0002580796,0.00006670555,0.00008568978,0.0000024875478,0.0009870505,0.0000036292527],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046801424,0.00019537433,0.0005991476,0.00014571704,0.000040313254,0.0000067509113,0.00009552413,0.87342453,0.009327497,0.000018269777,0.000054546606,0.11562432],"study_design_scores_gemma":[0.0017710659,0.00077227666,0.0011509219,0.0005408201,0.00011538991,0.00003902298,0.00012691822,0.99495214,0.00026993075,0.0000029558428,0.000099477475,0.0001590513],"about_ca_topic_score_codex":0.00018492159,"about_ca_topic_score_gemma":0.00001172362,"teacher_disagreement_score":0.6008465,"about_ca_system_score_codex":0.00013813906,"about_ca_system_score_gemma":0.00003817987,"threshold_uncertainty_score":0.74732625},"labels":[],"label_agreement":null},{"id":"W4409690662","doi":"10.1158/1538-7445.am2025-155","title":"Abstract 155: Spatial analysis of tumor-immune-stromal cellular phenotypes and microenvironments in pancreatic cancer","year":2025,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University Health Network; Ontario Institute for Cancer Research; University of Toronto; Mount Sinai Hospital","funders":"","keywords":"Stromal cell; Pancreatic cancer; Immune system; Cancer; Phenotype; Tumor microenvironment; Cancer research; Biology; Medicine; Immunology; Internal medicine; Genetics; Gene","score_opus":0.019861948647651964,"score_gpt":0.36648423665327234,"score_spread":0.3466222880056204,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409690662","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9907604,0.0070764604,0.00009521136,0.0010525365,0.000060299473,0.0002305582,0.000014256226,0.0000067619985,0.0007035496],"genre_scores_gemma":[0.9977651,0.0012144856,0.00012278507,0.00011196861,0.000052472176,0.000058551017,0.000014893829,0.000012577273,0.00064714503],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.998601,0.00008527292,0.0003002455,0.00029039924,0.0003864255,0.00033662742],"domain_scores_gemma":[0.99941427,0.00014558971,0.00005444966,0.00023451408,0.000053736312,0.00009741945],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006879826,0.00010045126,0.00044611312,0.00064836955,0.00006267464,0.000017217377,0.0001247785,0.000047381844,0.0006512453],"category_scores_gemma":[0.00017791343,0.00008852034,0.00007141449,0.000781831,0.0003028771,0.00003105041,0.00009625953,0.0005861075,0.000002241885],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020261678,0.00008997326,0.63560474,0.00029051895,0.00056950434,0.000060026417,0.00021979188,0.0004156527,0.3436591,0.0000297672,0.0001432157,0.018715082],"study_design_scores_gemma":[0.0011207694,0.00004490248,0.972125,0.0004767904,0.00040325185,7.570961e-7,0.00012804191,0.0073228213,0.017175354,0.0000458176,0.0010815138,0.00007498584],"about_ca_topic_score_codex":0.017450651,"about_ca_topic_score_gemma":0.00042842052,"teacher_disagreement_score":0.33652025,"about_ca_system_score_codex":0.00021748342,"about_ca_system_score_gemma":0.00021539739,"threshold_uncertainty_score":0.98909223},"labels":[],"label_agreement":null},{"id":"W4409737710","doi":"10.1007/s10334-025-01245-3","title":"Rethinking MRI as a measurement device through modular and portable pipelines","year":2025,"lang":"en","type":"review","venue":"Magnetic Resonance Materials in Physics Biology and Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke; Université de Montréal; Polytechnique Montréal; Montreal Heart Institute","funders":"Tamkeen; University College Cork; Irish Research eLibrary; New York University Abu Dhabi","keywords":"Workflow; Computer science; Benchmarking; Pipeline (software); Modular design; Software portability; Software engineering; Debugging; Modularity (biology); SPARK (programming language); Terminology; Data science; Systems engineering; Engineering","score_opus":0.04404799996137496,"score_gpt":0.36476894503238116,"score_spread":0.3207209450710062,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409737710","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00051849475,0.9945985,0.000262493,0.0012772518,0.00071799004,0.0009993551,0.000014956864,0.00004098363,0.0015699853],"genre_scores_gemma":[0.00033247194,0.9944751,0.0016055609,0.0017205438,0.0010197042,0.00013835377,0.00013311797,0.0000425003,0.000532636],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99707675,0.0003561213,0.0009942194,0.00080772466,0.00028262244,0.00048254267],"domain_scores_gemma":[0.9987513,0.00028073997,0.00030394754,0.0004308246,0.00011417509,0.0001190412],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0016809077,0.0005425622,0.0028509665,0.00014807387,0.0001113694,0.000022674876,0.00017480316,0.00043250312,0.00009013313],"category_scores_gemma":[0.0009911292,0.00037405585,0.00007655582,0.00031552435,0.00063017715,0.000043048218,0.0001874623,0.00065590785,0.0000044588487],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051953983,0.00005071563,0.00009402892,0.018759463,0.000051034403,0.00009296746,0.0002832536,2.6226076e-7,0.00036648716,0.003361086,0.0005245218,0.97636425],"study_design_scores_gemma":[0.0015227975,0.00044519827,0.000092039314,0.06159667,0.00092247163,0.00019450938,0.000027022319,0.000049866383,0.000039833547,0.019639293,0.91513777,0.00033255157],"about_ca_topic_score_codex":0.00048498233,"about_ca_topic_score_gemma":0.0000070745455,"teacher_disagreement_score":0.97603166,"about_ca_system_score_codex":0.0000673454,"about_ca_system_score_gemma":0.0003053848,"threshold_uncertainty_score":0.99987113},"labels":[],"label_agreement":null},{"id":"W4409760701","doi":"10.3390/bioengineering12050450","title":"A Radiomic Model for Gliomas Grade and Patient Survival Prediction","year":2025,"lang":"en","type":"article","venue":"Bioengineering","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"National Natural Science Foundation of China","keywords":"Computer science; Glioblastoma; Glioma; Medicine; Cancer research","score_opus":0.011376498743801818,"score_gpt":0.2639964093979357,"score_spread":0.2526199106541339,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409760701","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49187857,0.0008555823,0.5042731,0.0018283513,0.00048162127,0.00031096785,0.000008828243,0.0001416851,0.00022128211],"genre_scores_gemma":[0.9859788,0.000060619393,0.013412759,0.0001983956,0.00007947637,0.00003552518,0.000013036692,0.000017638034,0.00020374714],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994269,0.0000047555404,0.00015112551,0.00016693384,0.00008439664,0.0001659117],"domain_scores_gemma":[0.9997308,0.000041161085,0.000018222054,0.00010432327,0.000022218072,0.00008322979],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010299829,0.00009478084,0.00016173167,0.00015402294,0.00004967668,0.000016727188,0.00003059301,0.0000481972,0.0000012184881],"category_scores_gemma":[0.00012933167,0.00008746877,0.00004749935,0.000109073146,0.000025032856,0.00003249916,0.000022777971,0.00012285136,3.2051278e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005702172,0.0004126865,0.028277284,0.003096752,0.0008931383,0.00006225109,0.0024743124,0.20572759,0.43205887,0.028213117,0.014312837,0.28390095],"study_design_scores_gemma":[0.0009834322,0.000057344947,0.0025499118,0.00012196178,0.000056299195,0.00001791014,0.000026719134,0.9906654,0.00079606735,0.00013684643,0.0045223795,0.00006575115],"about_ca_topic_score_codex":0.00000729964,"about_ca_topic_score_gemma":3.130308e-7,"teacher_disagreement_score":0.7849378,"about_ca_system_score_codex":0.000047246358,"about_ca_system_score_gemma":0.000030880394,"threshold_uncertainty_score":0.3566873},"labels":[],"label_agreement":null},{"id":"W4409788861","doi":"10.1007/s12032-025-02732-2","title":"Retraction Note: Artificial intelligence and machine learning in precision and genomic medicine","year":2025,"lang":"en","type":"article","venue":"Medical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":true,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Emergent BioSolutions (Canada)","funders":"","keywords":"Hematology; Artificial intelligence; Precision medicine; Computer science; Machine learning; Internal medicine; Medical physics; Medicine; Pathology","score_opus":0.026851474927089374,"score_gpt":0.37187913617071205,"score_spread":0.34502766124362266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409788861","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6958923,0.005396958,0.077605404,0.20703852,0.0018415158,0.00054445205,7.253984e-7,0.00012819895,0.011551936],"genre_scores_gemma":[0.99020445,0.0031429334,0.0018814608,0.0038455077,0.00036506192,0.0000114941895,0.000013843805,0.000013662888,0.0005215743],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983101,0.00021772807,0.0005310172,0.00036916824,0.0003175443,0.00025448232],"domain_scores_gemma":[0.9984747,0.0010183589,0.000084653366,0.00011443585,0.00003682505,0.0002709883],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002221988,0.0001375923,0.0005036093,0.0003374564,0.00009158876,0.000009510635,0.00008169105,0.00041353583,0.00032285493],"category_scores_gemma":[0.007362502,0.00010687318,0.000024408417,0.00028247133,0.000536306,0.000038915277,0.00012289177,0.0019609572,0.0000067402866],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028213178,0.000103397506,0.022782035,0.00007566507,0.000014641564,0.00023598432,0.00035240492,0.000014533076,0.0021240246,0.0019248665,0.00036026046,0.97173005],"study_design_scores_gemma":[0.003300219,0.0023763853,0.1630813,0.0014003203,0.00018760981,0.0011076307,0.0005254937,0.52854156,0.00029326393,0.013080915,0.285809,0.0002962966],"about_ca_topic_score_codex":0.00040652254,"about_ca_topic_score_gemma":0.00015766465,"teacher_disagreement_score":0.97143376,"about_ca_system_score_codex":0.00016011832,"about_ca_system_score_gemma":0.00024741425,"threshold_uncertainty_score":0.88141346},"labels":[{"model":"gemma","categories":["research_integrity"],"domain":null,"study_design":"not_applicable","genre":"editorial","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"editorial","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W4409790695","doi":"10.1002/mp.17840","title":"Geometrically focused training and evaluation of organs‐at‐risk segmentation via deep learning","year":2025,"lang":"en","type":"article","venue":"Medical Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; Princess Margaret Cancer Centre; University Health Network; University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"Artificial intelligence; Deep learning; Segmentation; Training (meteorology); Medical imaging; Image segmentation; Computer science; Medical physics; Computer vision; Medicine; Physics","score_opus":0.017912671572933792,"score_gpt":0.32299022902319646,"score_spread":0.30507755745026266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409790695","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.68120337,0.00052713876,0.31485847,0.0012005128,0.00014204539,0.00023347362,6.423533e-7,0.000044515848,0.001789858],"genre_scores_gemma":[0.9972402,0.00017934208,0.0017685574,0.0004770281,0.00015221976,0.000012925393,0.00003730655,0.000016655853,0.00011578196],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99782544,0.00019003972,0.00034613773,0.0002449327,0.0011963563,0.00019706212],"domain_scores_gemma":[0.9988942,0.00042962914,0.0001556676,0.00013140136,0.00019716712,0.00019194848],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002036733,0.0001169924,0.00033628484,0.0001426117,0.00012898551,0.000010855554,0.00007389622,0.000104625346,0.00020361028],"category_scores_gemma":[0.004628285,0.0001033196,0.00006323378,0.00060919864,0.00022482118,0.000050050574,0.0000694878,0.00059906935,0.000004964382],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003123789,0.00008610852,0.039017074,0.00008824919,0.00009658192,0.000004195557,0.0008226556,0.0002225893,0.0016832143,0.00009081181,0.00008827091,0.95776904],"study_design_scores_gemma":[0.009057867,0.00039322153,0.09825862,0.00049579504,0.0013080164,0.00002614009,0.00035355065,0.8743916,0.0068049207,0.0075659826,0.0010937852,0.00025050057],"about_ca_topic_score_codex":0.00003182902,"about_ca_topic_score_gemma":0.0000024145695,"teacher_disagreement_score":0.9575185,"about_ca_system_score_codex":0.000120796205,"about_ca_system_score_gemma":0.00020217137,"threshold_uncertainty_score":0.55408233},"labels":[],"label_agreement":null},{"id":"W4409846769","doi":"10.71044/qsurjvol820252","title":"Behind the Screens: A Literature Review for High Throughput Proteomic Screens Related to RET","year":2025,"lang":"en","type":"review","venue":"Queen s Science Undergraduate Research Journal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Throughput; Computer science; Computational biology; Biology; Operating system","score_opus":0.05476329495680391,"score_gpt":0.4674446340475816,"score_spread":0.41268133909077764,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409846769","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000024208684,0.80852693,0.0014243225,0.18158884,0.000406371,0.0066990233,0.000041188807,0.000047198013,0.0012637269],"genre_scores_gemma":[0.000015437796,0.9767669,0.008854912,0.0023205164,0.00070398464,0.00043308816,0.00007879444,0.000088634944,0.010737734],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98958915,0.0016774317,0.0016522239,0.0013094798,0.0037622985,0.0020094123],"domain_scores_gemma":[0.9924465,0.0016662976,0.00062105973,0.0014503889,0.0025623944,0.0012533899],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.028940568,0.00066126126,0.002395758,0.0019383001,0.0029358773,0.001272918,0.0027415766,0.0003593916,0.000040685434],"category_scores_gemma":[0.021590138,0.00036013097,0.0009261932,0.0064250776,0.0018122775,0.0004179857,0.0007804592,0.008970099,0.00007286169],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004632736,0.000082244114,0.000004929643,0.038474035,0.0002521578,0.00037177023,0.00010438742,0.0000034180566,0.000010970694,0.008031739,0.13816933,0.81444865],"study_design_scores_gemma":[0.00046430426,0.000441928,0.0000065937766,0.31754044,0.0005254672,0.002407337,0.000018097295,0.00009405115,0.0000023376197,0.0068109278,0.6714096,0.0002789235],"about_ca_topic_score_codex":0.000077177196,"about_ca_topic_score_gemma":0.0000027612057,"teacher_disagreement_score":0.81416976,"about_ca_system_score_codex":0.0011567974,"about_ca_system_score_gemma":0.0098781595,"threshold_uncertainty_score":0.99991006},"labels":[],"label_agreement":null},{"id":"W4409888060","doi":"10.21203/rs.3.rs-6398087/v1","title":"A deep learning-based framework for standardized analysis of trabecular bone compartments from micro-CT imaging data in the mouse tibia","year":2025,"lang":"en","type":"preprint","venue":"Research Square","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Medical Research Council; Queensland University of Technology; Centre National de la Recherche Scientifique; Royal Academy of Engineering","keywords":"Tibia; Trabecular bone; Bone imaging; Biomedical engineering; Anatomy; Medicine; Nuclear medicine; Pathology; Osteoporosis","score_opus":0.057626905125293684,"score_gpt":0.4489783205486542,"score_spread":0.39135141542336055,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409888060","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5489804,0.010019221,0.42252046,0.010361916,0.00016838865,0.0044709696,0.0031308027,0.00010254467,0.00024527984],"genre_scores_gemma":[0.9494188,0.00042075274,0.03374796,0.00043490686,0.00015274939,0.00022062354,0.015439761,0.000054508808,0.00010993389],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9941935,0.0014959731,0.0007821267,0.0010619622,0.001774662,0.00069177407],"domain_scores_gemma":[0.99290377,0.0037443622,0.00027071853,0.0024188939,0.00047829724,0.00018395463],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0072393357,0.00032248994,0.0014364556,0.0014183224,0.00021735903,0.00017326213,0.0013255691,0.00016993335,0.00013206854],"category_scores_gemma":[0.007891713,0.00024966715,0.00050871144,0.0015008588,0.000337237,0.000044045537,0.0009218211,0.004295669,0.0000021795772],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0051483256,0.0034096688,0.7508457,0.010161006,0.013233373,0.0013900301,0.0067802235,0.13579668,0.00325459,0.00062790903,0.009570752,0.05978179],"study_design_scores_gemma":[0.0034380276,0.00011384103,0.02047973,0.0028487265,0.0021594502,0.0000017835836,0.0011751316,0.9575053,0.000387827,0.0011589362,0.01046492,0.0002663684],"about_ca_topic_score_codex":0.0023140453,"about_ca_topic_score_gemma":0.00015929164,"teacher_disagreement_score":0.82170856,"about_ca_system_score_codex":0.00028811526,"about_ca_system_score_gemma":0.00072736194,"threshold_uncertainty_score":0.9999955},"labels":[],"label_agreement":null},{"id":"W4409963810","doi":"10.3390/cancers17091520","title":"Pre-Treatment Prediction of Breast Cancer Response to Neoadjuvant Chemotherapy Using Intratumoral and Peritumoral Radiomics from T2-Weighted and Contrast-Enhanced T1-Weighted MRI","year":2025,"lang":"en","type":"article","venue":"Cancers","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Toronto Metropolitan University; Health Sciences Centre; Sunnybrook Health Science Centre","funders":"Natural Sciences and Engineering Research Council of Canada; Terry Fox Research Institute; University of Toronto; Terry Fox Foundation","keywords":"Medicine; Radiomics; Breast cancer; Magnetic resonance imaging; Radiology; Oncology; Cancer; Internal medicine","score_opus":0.007480982367676307,"score_gpt":0.2854992856950121,"score_spread":0.2780183033273358,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409963810","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9877036,0.001980483,0.005322567,0.0036230166,0.00042159235,0.00063140347,0.0002127196,0.000054603897,0.000050002585],"genre_scores_gemma":[0.99273264,0.0013309655,0.0045084218,0.00095198693,0.00020031322,0.000045926474,0.000027730222,0.000029535562,0.00017246502],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99870425,0.000083497565,0.00033462996,0.00042857896,0.00016753396,0.00028152653],"domain_scores_gemma":[0.9992319,0.000093977535,0.000112205526,0.0002112053,0.00010131926,0.0002494298],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017174812,0.00023581975,0.00055716507,0.00017901645,0.00010339062,0.000034714492,0.00006276594,0.000092824506,0.000051135077],"category_scores_gemma":[0.000039552193,0.00019937586,0.00005530177,0.00027441196,0.00023495728,0.00007518983,0.000027241307,0.00020758362,2.0594618e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.014852338,0.00008492085,0.048881356,0.00012722577,0.0005844826,0.00003992497,0.0033506835,0.0006774947,0.8290632,0.000042457752,0.00051779894,0.10177812],"study_design_scores_gemma":[0.018623978,0.0010403958,0.49235472,0.002130326,0.0007086992,0.00012340862,0.0006752683,0.40975115,0.07107418,0.00016809136,0.002916816,0.00043299427],"about_ca_topic_score_codex":0.0036015776,"about_ca_topic_score_gemma":0.00004987452,"teacher_disagreement_score":0.757989,"about_ca_system_score_codex":0.0012694238,"about_ca_system_score_gemma":0.00081357756,"threshold_uncertainty_score":0.8130312},"labels":[],"label_agreement":null},{"id":"W4410049147","doi":"10.1007/s00259-025-07314-y","title":"Should end-to-end deep learning replace handcrafted radiomics?","year":2025,"lang":"en","type":"letter","venue":"European Journal of Nuclear Medicine and Molecular Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"End-to-end principle; Radiomics; Deep learning; Artificial intelligence; Medicine; Computer science","score_opus":0.012666938472408948,"score_gpt":0.27278094737996494,"score_spread":0.260114008907556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410049147","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002229988,0.0054616663,0.009554479,0.95976204,0.0009978171,0.00028399433,0.0000022492588,0.00009404521,0.021613747],"genre_scores_gemma":[0.018698001,0.001257809,0.0073250653,0.96618605,0.004918143,9.929557e-7,0.000058157035,0.00031346965,0.0012423276],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9953842,0.00092792086,0.0012802554,0.0006495759,0.0010908399,0.0006671741],"domain_scores_gemma":[0.9974064,0.0002696831,0.00079020206,0.0005273412,0.00040718532,0.00059916056],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0027779602,0.00061092444,0.0014017369,0.0013241454,0.00022928343,0.00013797753,0.0004937389,0.00015396872,0.00026994487],"category_scores_gemma":[0.0030950466,0.0005007762,0.00036381875,0.00043143475,0.0004054328,0.00011348597,0.0002820211,0.00685036,0.000025678339],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016994463,0.000023751792,0.00017421196,0.0003585299,0.0003866123,0.04062593,0.0011502387,0.000030842526,0.010219429,0.000016412536,0.87327623,0.073567875],"study_design_scores_gemma":[0.0032014085,0.0006610838,0.00022333054,0.0041148993,0.0011230565,0.006600757,0.000432148,0.00205417,0.000051605726,0.000018317705,0.9811217,0.00039753367],"about_ca_topic_score_codex":0.00002316917,"about_ca_topic_score_gemma":1.3403867e-7,"teacher_disagreement_score":0.10784547,"about_ca_system_score_codex":0.00014145992,"about_ca_system_score_gemma":0.00014842997,"threshold_uncertainty_score":0.9997444},"labels":[],"label_agreement":null},{"id":"W4410051951","doi":"10.1038/s41746-025-01652-9","title":"Multimodal GPT model for assisting thyroid nodule diagnosis and management","year":2025,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Nodule (geology); Thyroid; Thyroid nodules; Medicine; Radiology; Medical physics; Computer science; Pathology; Internal medicine; Biology","score_opus":0.016335792338386838,"score_gpt":0.31319797271692323,"score_spread":0.2968621803785364,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410051951","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34574834,0.003449338,0.40576273,0.072066694,0.00094988977,0.0026652506,0.00004386515,0.00042269452,0.16889118],"genre_scores_gemma":[0.9785376,0.00032613706,0.0096469745,0.0038305684,0.00024096871,0.00016333186,0.00006574092,0.000028551876,0.0071601174],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987408,0.0000060454536,0.00032692656,0.0003741554,0.0002496734,0.00030240667],"domain_scores_gemma":[0.99916637,0.00027791358,0.00006365227,0.00022746217,0.00007145475,0.00019314142],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027447855,0.00018618605,0.00039184777,0.00019236933,0.000120693665,0.00004037449,0.00009664985,0.000062627965,0.000013326105],"category_scores_gemma":[0.0011555873,0.00014176052,0.00006610116,0.00017157782,0.00020405394,0.00010036457,0.00009607921,0.0002162184,0.0000030434624],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026607618,0.0003376127,0.054509144,0.0018023233,0.0003966723,0.00009251961,0.0005116966,0.00038607774,0.000608789,0.01450923,0.055998072,0.8705818],"study_design_scores_gemma":[0.007870845,0.00042114579,0.017143883,0.0020834545,0.0004481268,0.00003473052,0.00029530097,0.9277854,0.000076813245,0.0046822256,0.038902607,0.00025549225],"about_ca_topic_score_codex":0.000013254976,"about_ca_topic_score_gemma":0.0000011280949,"teacher_disagreement_score":0.9273993,"about_ca_system_score_codex":0.00005565823,"about_ca_system_score_gemma":0.000029746529,"threshold_uncertainty_score":0.5780826},"labels":[],"label_agreement":null},{"id":"W4410128651","doi":"10.3390/jimaging11050146","title":"Quantitative Ultrasound Texture Analysis of Breast Tumors: A Comparison of a Cart-Based and a Wireless Ultrasound Scanner","year":2025,"lang":"en","type":"article","venue":"Journal of Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; University of Toronto; Sunnybrook Health Science Centre","funders":"National Cancer Institute; Natural Sciences and Engineering Research Council of Canada","keywords":"Ultrasound; Feature (linguistics); Breast ultrasound; Scanner; Imaging phantom; Medicine; Breast imaging; Artificial intelligence; Computer science; Radiology; Breast cancer; Mammography; Cancer","score_opus":0.008145557992533251,"score_gpt":0.33072011889712294,"score_spread":0.3225745609045897,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410128651","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96898913,0.001809309,0.026596392,0.0019933742,0.000080114994,0.00008316029,0.000015480502,0.0000066624084,0.0004263665],"genre_scores_gemma":[0.9948134,0.000034250694,0.0047901794,0.00027204648,0.000038455873,7.30365e-7,0.000007388964,0.0000120527875,0.00003152021],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99833184,0.00010658843,0.0008366599,0.00015270119,0.00039490394,0.0001773076],"domain_scores_gemma":[0.9975074,0.0008913408,0.0007956866,0.00016119143,0.00051463157,0.00012975298],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007671156,0.00014952672,0.0010544376,0.0009780356,0.000054896245,0.000030995747,0.00012266694,0.000037772345,0.000026619284],"category_scores_gemma":[0.00087278086,0.000115231065,0.00029306093,0.0010057978,0.0003287978,0.000102009784,0.00001830013,0.0005226364,1.350789e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036650585,0.00028893002,0.8195725,0.00032081796,0.0016583877,0.000048836,0.0014068963,0.001718662,0.16661373,0.00032457506,0.0006956705,0.006984516],"study_design_scores_gemma":[0.0037076601,0.0003136022,0.7368936,0.0032993818,0.0064582718,0.0006851523,0.007538567,0.23454784,0.0060174195,0.00014408154,0.0001973182,0.00019713075],"about_ca_topic_score_codex":0.00018668416,"about_ca_topic_score_gemma":0.000012459997,"teacher_disagreement_score":0.23282917,"about_ca_system_score_codex":0.000058634956,"about_ca_system_score_gemma":0.0002629197,"threshold_uncertainty_score":0.46989864},"labels":[],"label_agreement":null},{"id":"W4410189351","doi":"10.1007/s11701-025-02350-0","title":"Costs of robot-assisted vs. open approaches for 5 major cancers","year":2025,"lang":"en","type":"article","venue":"Journal of Robotic Surgery","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; McGill University Health Centre","funders":"","keywords":"Medicine; Open surgery; Surgery","score_opus":0.054472313521754356,"score_gpt":0.33245027694997575,"score_spread":0.2779779634282214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410189351","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45477742,0.008370231,0.4261049,0.08556783,0.010741361,0.0022411274,0.000010724156,0.00005487318,0.012131525],"genre_scores_gemma":[0.97795,0.00014080403,0.018920051,0.0011854733,0.00024073075,0.000009948627,0.0000071321047,0.000023174558,0.0015227215],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9985638,0.000077384255,0.00076179265,0.00013226953,0.0002520912,0.00021260952],"domain_scores_gemma":[0.99766636,0.0012117954,0.0005609327,0.00017815984,0.00023226232,0.00015051024],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017941974,0.000119140226,0.00088641426,0.0003416004,0.000055726676,0.000036396927,0.00022349521,0.00007095488,0.000032334465],"category_scores_gemma":[0.0021876467,0.00009148888,0.00032689286,0.00029599125,0.00009339431,0.000101462465,0.00005879267,0.00031339543,5.2968005e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0032483786,0.0006744537,0.16056217,0.0014671563,0.00214027,0.00022814721,0.00020587837,0.02856277,0.0034062548,0.0019831546,0.1933494,0.60417193],"study_design_scores_gemma":[0.024336662,0.0015100625,0.75548726,0.020216495,0.005085112,0.0025747851,0.0017625882,0.13148378,0.0055542374,0.0022692245,0.04865889,0.0010608889],"about_ca_topic_score_codex":0.00012783888,"about_ca_topic_score_gemma":0.0000051082325,"teacher_disagreement_score":0.6031111,"about_ca_system_score_codex":0.00024555039,"about_ca_system_score_gemma":0.0010787796,"threshold_uncertainty_score":0.37308085},"labels":[],"label_agreement":null},{"id":"W4410198708","doi":"10.1101/2025.05.07.25327158","title":"EchoGraph System for Automated Quality Assessment of Echocardiography Reports","year":2025,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Quality (philosophy); Computer science; Philosophy; Epistemology","score_opus":0.02516659960978853,"score_gpt":0.38390372365373016,"score_spread":0.35873712404394165,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410198708","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8634499,0.0011044901,0.10377942,0.0015608552,0.0057091773,0.0036658053,0.0002112244,0.0021874194,0.018331725],"genre_scores_gemma":[0.9598717,0.0001024966,0.038857285,0.0001525765,0.00020577226,0.0002898142,0.0002905309,0.000041004903,0.0001888101],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9964844,0.00025546263,0.0014325412,0.00080906955,0.0006655023,0.0003530352],"domain_scores_gemma":[0.9966944,0.0003178275,0.00095996086,0.001365677,0.000447623,0.00021451135],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.003640616,0.00036931518,0.0015772764,0.00072440156,0.000083983265,0.000035375953,0.00024892675,0.00040682603,0.0000079946585],"category_scores_gemma":[0.00071367365,0.00032239585,0.0012071143,0.00046877717,0.00015302002,0.000021905482,0.00028456328,0.001017465,3.251052e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000062261155,0.00021081878,0.97092754,0.016853087,0.0016187,0.0001621841,0.0000798246,0.0015134518,0.0016024066,0.0011348639,0.00291746,0.0029173808],"study_design_scores_gemma":[0.0018714543,0.00018220888,0.83408785,0.0072237817,0.0019026842,0.00009708084,0.00014800772,0.14534637,0.001003906,0.0007655632,0.00678545,0.00058561756],"about_ca_topic_score_codex":0.00021451751,"about_ca_topic_score_gemma":0.000001155399,"teacher_disagreement_score":0.14383292,"about_ca_system_score_codex":0.00012953063,"about_ca_system_score_gemma":0.0005676583,"threshold_uncertainty_score":0.9999228},"labels":[],"label_agreement":null},{"id":"W4410205295","doi":"10.2196/67379","title":"Prediction of a Panel of Programmed Cell Death Protein-1 (PD-1) Inhibitor–Sensitive Biomarkers Using Multiphase Computed Tomography Imaging Textural Features: Retrospective Cohort Analysis","year":2025,"lang":"en","type":"article","venue":"JMIR Cancer","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Microsatellite instability; Retrospective cohort study; Medicine; Cancer; Biomarker; Oncology; Pembrolizumab; Internal medicine; Imaging biomarker; Radiology; Magnetic resonance imaging; Immunotherapy; Microsatellite; Biology","score_opus":0.012684032891199954,"score_gpt":0.3000340435125254,"score_spread":0.2873500106213254,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410205295","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98675466,0.0006324204,0.009628229,0.00032967908,0.00020138256,0.0018477547,0.0000925927,0.00008598917,0.00042728602],"genre_scores_gemma":[0.9915313,0.000021757214,0.007867716,0.00013407471,0.000112547794,0.00012045297,0.00009245795,0.000023342887,0.000096366835],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9981603,0.0001019435,0.0005062842,0.00046885744,0.0004495261,0.00031309132],"domain_scores_gemma":[0.99862325,0.000057091624,0.00037592676,0.00028788258,0.00052428915,0.00013158613],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032087014,0.00023973352,0.00073854026,0.00086976076,0.0000949012,0.000021888067,0.000091428505,0.00010495534,0.000013391588],"category_scores_gemma":[0.00010564146,0.00020633999,0.00039647592,0.0021481516,0.00028941646,0.000083334126,0.000056433022,0.00042639248,1.2509275e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004999124,0.00028988958,0.83401793,0.00036221213,0.0021810355,0.000027749842,0.0004803833,0.00038887226,0.1558915,0.000016662565,0.0002262598,0.005617612],"study_design_scores_gemma":[0.002694206,0.00010858362,0.7995863,0.000917179,0.0020251158,0.000008435827,0.00029998785,0.1599466,0.03418279,0.000016125201,0.000066009175,0.00014866024],"about_ca_topic_score_codex":0.0026165075,"about_ca_topic_score_gemma":0.000025460859,"teacher_disagreement_score":0.15955773,"about_ca_system_score_codex":0.0003278367,"about_ca_system_score_gemma":0.00022663361,"threshold_uncertainty_score":0.84143007},"labels":[],"label_agreement":null},{"id":"W4410206452","doi":"10.1007/978-3-031-77610-6_24","title":"Correction to: Medical Image Computing and Computer Assisted Intervention – MICCAI 2024 Workshops","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Computer graphics (images); Multimedia; Information retrieval","score_opus":0.008540598845464657,"score_gpt":0.30006140513790175,"score_spread":0.2915208062924371,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410206452","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007970477,0.00038479475,0.9810531,0.004612847,0.008942673,0.00041416305,0.0000017540386,0.00011444927,0.0036791428],"genre_scores_gemma":[0.20157732,0.00019171082,0.7537165,0.026841918,0.005538402,0.000013377812,0.000098746656,0.00015026533,0.011871729],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99680334,0.000054347784,0.00062171597,0.0011109691,0.0009446391,0.00046499024],"domain_scores_gemma":[0.9979036,0.0007790336,0.00018046038,0.00043158096,0.00021056374,0.00049474696],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0014167934,0.00040961453,0.0006842621,0.000904237,0.00019997612,0.0002679569,0.00046316747,0.0003258061,0.00015385373],"category_scores_gemma":[0.0012215306,0.00036509917,0.00016227372,0.00047192615,0.00063861435,0.0001035928,0.00083590095,0.0021504527,0.000016216445],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028430482,0.00004385909,0.00037089924,0.00016363799,0.00003143741,0.00019926317,0.0002098208,0.00086272834,0.00006120421,0.00016052525,0.0031252324,0.994743],"study_design_scores_gemma":[0.00078846264,0.00024880533,0.0030742306,0.009090428,0.000058739563,0.0006169394,7.1722246e-7,0.9807405,0.000055531124,0.0009816957,0.0039814794,0.00036248076],"about_ca_topic_score_codex":0.00006688385,"about_ca_topic_score_gemma":0.00004868162,"teacher_disagreement_score":0.9943805,"about_ca_system_score_codex":0.00029508382,"about_ca_system_score_gemma":0.00042069523,"threshold_uncertainty_score":0.9998801},"labels":[],"label_agreement":null},{"id":"W4410245613","doi":"10.1016/j.ibmed.2025.100250","title":"Implementation of artificial intelligence in detection, classification, and prognostication of osteosarcoma utilizing different assessment techniques: a systematic review","year":2025,"lang":"en","type":"review","venue":"Intelligence-Based Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Osteosarcoma; Computer science; Artificial intelligence; Medicine; Pathology","score_opus":0.06044898505339841,"score_gpt":0.4431549052129858,"score_spread":0.3827059201595874,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410245613","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000017740276,0.8291822,0.16408257,0.0006098657,0.00012469936,0.005815836,0.000009668273,0.000041403346,0.0001160075],"genre_scores_gemma":[0.011856901,0.9844313,0.0022123894,0.00017095814,0.00006976993,0.0010373193,0.00017625607,0.00003429999,0.000010804253],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.99431384,0.0005410904,0.003672792,0.0005503859,0.0006608523,0.00026106343],"domain_scores_gemma":[0.9954431,0.001591878,0.0017633345,0.0006196263,0.00044507065,0.00013699231],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0023029074,0.00045354708,0.0034731235,0.0011297466,0.00004519893,0.000009775427,0.00026635724,0.0002099747,0.000061723396],"category_scores_gemma":[0.003081794,0.0003168555,0.00024705802,0.0012491295,0.0003879996,0.00004293309,0.00005457626,0.0006964201,0.000001010578],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006129378,0.00008472853,0.0000723775,0.47768837,0.000054672168,0.0000033133754,0.000049668397,1.8398053e-7,0.000030025774,0.0009191141,0.000004271432,0.5210871],"study_design_scores_gemma":[0.000114044386,0.0006245185,0.00008684354,0.9894231,0.0045121103,0.000042057185,0.00077565707,0.0020160016,0.0008447595,0.00042760416,0.00090326404,0.00023005717],"about_ca_topic_score_codex":0.00015375225,"about_ca_topic_score_gemma":0.00003334,"teacher_disagreement_score":0.5208571,"about_ca_system_score_codex":0.00031530208,"about_ca_system_score_gemma":0.00074687327,"threshold_uncertainty_score":0.99992836},"labels":[],"label_agreement":null},{"id":"W4410271219","doi":"10.1164/ajrccm.2025.211.abstracts.a3364","title":"Computed Tomography Imaging-based Clusters for Chronic Obstructive Pulmonary Disease Lung Function Decline","year":2025,"lang":"en","type":"article","venue":"American Journal of Respiratory and Critical Care Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"St. Paul's Hospital; Toronto Metropolitan University","funders":"","keywords":"Medicine; Pulmonary disease; Lung function; Computed tomography; Pulmonary function testing; Lung; Tomography; Lung disease; Radiology; COPD; Obstructive lung disease; Internal medicine","score_opus":0.006807666653937649,"score_gpt":0.3083301082114963,"score_spread":0.30152244155755864,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410271219","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3359561,0.087827116,0.50199455,0.07044534,0.0021753625,0.0007613317,0.000023323268,0.000091327944,0.00072554883],"genre_scores_gemma":[0.98043764,0.000017334336,0.0013023427,0.017361099,0.0008294209,0.000010430316,0.000013768772,0.000020141484,0.000007833767],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9984103,0.00014019353,0.0005448647,0.00026368635,0.00035971406,0.00028127123],"domain_scores_gemma":[0.99761695,0.0007851817,0.00018055395,0.00017641865,0.00068386114,0.0005570529],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00050613616,0.00019901006,0.00059923454,0.00046253827,0.00016034699,0.000019336021,0.00011281891,0.000034245073,0.000020039763],"category_scores_gemma":[0.0014220767,0.0001499307,0.0001923841,0.00043198882,0.0016023207,0.00008379199,0.000034641907,0.0005149162,1.5661924e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004679923,0.00016303924,0.29106304,0.0019345048,0.00019708813,0.000553544,0.00017564291,0.00016795097,0.0013197851,0.0013465183,0.0021085392,0.69629043],"study_design_scores_gemma":[0.013921103,0.01142515,0.7975943,0.0060207215,0.005365377,0.0003209488,0.006207037,0.0805471,0.00019067609,0.0021509132,0.07560708,0.0006495911],"about_ca_topic_score_codex":0.000008787858,"about_ca_topic_score_gemma":7.1893186e-7,"teacher_disagreement_score":0.69564086,"about_ca_system_score_codex":0.00012729518,"about_ca_system_score_gemma":0.00040873932,"threshold_uncertainty_score":0.61139965},"labels":[],"label_agreement":null},{"id":"W4410273024","doi":"10.1164/ajrccm.2025.211.abstracts.a4755","title":"Personalization of AI-enabled PAP Therapy (CMAP®) Algorithm Shows Improvement in Prediction of Respiratory Events and Preliminary Success in Further Reduction of Therapy Pressure","year":2025,"lang":"en","type":"article","venue":"American Journal of Respiratory and Critical Care Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen Elizabeth II Health Sciences Centre; Dalhousie University","funders":"","keywords":"Medicine; Personalization; Reduction (mathematics); Respiratory system; Intensive care medicine; Internal medicine; Computer science","score_opus":0.01153092762798679,"score_gpt":0.3180661361286934,"score_spread":0.3065352085007066,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410273024","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9714413,0.024854748,0.0013996562,0.0017653169,0.00016693014,0.00029914494,0.000009818901,0.0000043221917,0.000058719903],"genre_scores_gemma":[0.99763656,0.0011311369,0.00022283058,0.0008530543,0.00012562684,0.000008177039,0.0000032511869,0.00001164084,0.000007714768],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99796325,0.00031478933,0.00091666466,0.00020183556,0.0004439981,0.0001594876],"domain_scores_gemma":[0.9986871,0.00018980485,0.00035462563,0.00014177541,0.00050962094,0.0001171012],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010273758,0.00015122768,0.0007266021,0.0005031972,0.000027630704,0.0000033718777,0.00008386993,0.00007915236,0.00002909652],"category_scores_gemma":[0.0004750167,0.00011267949,0.00006232931,0.00042140152,0.0008467009,0.00012159959,0.000022024768,0.00048682225,1.4191988e-8],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002714232,0.00037043673,0.34533203,0.0009739616,0.0001413407,0.000030242567,0.0046372153,0.000036419246,0.09288396,0.00011536456,0.00009763426,0.55266714],"study_design_scores_gemma":[0.023598589,0.052292172,0.8441507,0.008556052,0.0005807876,0.00011080517,0.034742367,0.0022422974,0.02930421,0.0006476338,0.0034519553,0.0003223817],"about_ca_topic_score_codex":0.000111544985,"about_ca_topic_score_gemma":0.0000020464142,"teacher_disagreement_score":0.5523448,"about_ca_system_score_codex":0.000042810952,"about_ca_system_score_gemma":0.00020614734,"threshold_uncertainty_score":0.45949364},"labels":[],"label_agreement":null},{"id":"W4410289291","doi":"10.1088/2057-1976/add73f","title":"Multi-omic feature reliability of deformable image registration-based images","year":2025,"lang":"en","type":"article","venue":"Biomedical Physics & Engineering Express","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lethbridge College; Kelowna General Hospital; University of Lethbridge; University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Innovates; Killam Trusts","keywords":"Image registration; Workflow; Feature (linguistics); Nuclear medicine; Reliability (semiconductor); Artificial intelligence; Cone beam computed tomography; Intraclass correlation; Computer science; Wilcoxon signed-rank test; Pattern recognition (psychology); Medicine; Radiology; Computed tomography; Mathematics; Image (mathematics); Reproducibility; Physics","score_opus":0.005038530140507131,"score_gpt":0.2625752735785936,"score_spread":0.25753674343808647,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410289291","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.044667516,0.00018724463,0.9506981,0.0033641579,0.00039109396,0.00026666178,0.000025123307,0.00018446082,0.0002156537],"genre_scores_gemma":[0.57347924,0.00001748183,0.4249295,0.00038067432,0.00024073312,0.000031774543,0.00013277348,0.000035791152,0.00075205],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99867433,0.000022522046,0.00034052986,0.00030435008,0.00035991715,0.0002983342],"domain_scores_gemma":[0.99896014,0.00016414044,0.00009183548,0.00047039284,0.00012882575,0.00018468383],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030874513,0.00020045303,0.0004074882,0.000116048344,0.000049913135,0.000023611872,0.0001974528,0.00013593194,0.000014873995],"category_scores_gemma":[0.0007108986,0.00017124468,0.00016036254,0.00037001786,0.00025067886,0.00009418913,0.000056055636,0.00055094756,0.000003851636],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006271193,0.0004257613,0.0010573647,0.001318148,0.000059564656,0.00001895681,0.000050734336,0.00454097,0.9742698,0.00024330281,0.015092976,0.0028597082],"study_design_scores_gemma":[0.0034140868,0.000113775735,0.010627439,0.0011469354,0.00016063427,0.0000068369236,0.000022901235,0.8363249,0.0352621,0.00018033847,0.11242992,0.00031017917],"about_ca_topic_score_codex":0.000056783218,"about_ca_topic_score_gemma":3.658217e-8,"teacher_disagreement_score":0.9390077,"about_ca_system_score_codex":0.000083692306,"about_ca_system_score_gemma":0.00019903295,"threshold_uncertainty_score":0.69831556},"labels":[],"label_agreement":null},{"id":"W4410298200","doi":"10.1109/isbi60581.2025.10980964","title":"Atlas Construction and Validation Using Cone-Beam Computed Tomography Images of Healthy Adult Human Hands","year":2025,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Canada Foundation for Innovation","keywords":"Atlas (anatomy); Computed tomography; Cone beam computed tomography; Tomography; Computer science; Medical physics; Medicine; Physics; Optics; Radiology; Anatomy","score_opus":0.010682694890843931,"score_gpt":0.3134997712824702,"score_spread":0.30281707639162625,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410298200","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9601951,0.00013021339,0.035090823,0.0014292462,0.00014315044,0.00016937783,0.0000012871268,0.00005400594,0.0027867553],"genre_scores_gemma":[0.9826373,0.000035440866,0.016460089,0.0006726346,0.000051852738,0.0000015409757,0.000028536213,0.0000069183934,0.000105719926],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99928933,0.00003390905,0.00027140684,0.00016770289,0.00012120497,0.00011643675],"domain_scores_gemma":[0.9995168,0.00005340875,0.0000920842,0.00010973463,0.00015507691,0.000072906296],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000174077,0.000084799365,0.00024211332,0.00025811334,0.00011192019,0.000020355335,0.000030609106,0.00005275499,0.000024301742],"category_scores_gemma":[0.000076290955,0.00007359179,0.00004517,0.0002618633,0.00023532282,0.00005256551,0.000026289494,0.0001679783,2.8797243e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021146018,0.00018214088,0.71559,0.0009992082,0.00024165501,0.00000846517,0.00020440371,0.00012539772,0.22118147,0.017686414,0.0026162828,0.040953103],"study_design_scores_gemma":[0.026490537,0.0018074177,0.4238751,0.0031094213,0.0010805535,0.0004830142,0.0012751601,0.14128403,0.39296705,0.004534308,0.002362792,0.00073060347],"about_ca_topic_score_codex":0.00032569462,"about_ca_topic_score_gemma":0.0000020004477,"teacher_disagreement_score":0.2917149,"about_ca_system_score_codex":0.000019083354,"about_ca_system_score_gemma":0.000047969483,"threshold_uncertainty_score":0.30009863},"labels":[],"label_agreement":null},{"id":"W4410369089","doi":"10.22399/ijcesen.2063","title":"Explainable Multi-Module Semantic Guided Attention Network for Accurate Medical Image Segmentation","year":2025,"lang":"en","type":"article","venue":"International Journal of Computational and Experimental Science and Engineering","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Segmentation; Image (mathematics); Artificial intelligence; Image segmentation; Computer vision; Natural language processing; Information retrieval","score_opus":0.010602287167039506,"score_gpt":0.34119396939123103,"score_spread":0.33059168222419155,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410369089","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7071848,0.00034847908,0.28871274,0.003045826,0.0005655308,0.000085929874,7.923743e-7,0.000008419373,0.00004747575],"genre_scores_gemma":[0.93590945,0.000040390005,0.06336408,0.00046229057,0.00017296306,0.000004792865,0.000006437241,0.0000039671677,0.000035650584],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99904853,0.0000058561764,0.00024778297,0.00010551111,0.00047890435,0.000113422255],"domain_scores_gemma":[0.99938905,0.00006967555,0.000073036485,0.0000212489,0.00033883224,0.00010817965],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000610599,0.00006504081,0.000113831855,0.00016355842,0.000099908175,0.000068575435,0.00009331251,0.000021053189,0.000008128605],"category_scores_gemma":[0.00026815242,0.000054682896,0.000033473592,0.000114717324,0.0000883527,0.00028042556,0.00004859583,0.00009176076,3.01595e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00079083256,0.0007814314,0.026594263,0.00039775553,0.0007889338,0.00023589996,0.0016248907,0.31532168,0.5605426,0.021896137,0.005898908,0.06512667],"study_design_scores_gemma":[0.0023052027,0.00008959206,0.02464034,0.0003250443,0.000019550223,0.00042384633,0.00019304256,0.96769035,0.0031193944,0.00055465504,0.00056681153,0.00007219508],"about_ca_topic_score_codex":0.000007039735,"about_ca_topic_score_gemma":1.2402323e-7,"teacher_disagreement_score":0.65236866,"about_ca_system_score_codex":0.00008358299,"about_ca_system_score_gemma":0.0001265984,"threshold_uncertainty_score":0.22299038},"labels":[],"label_agreement":null},{"id":"W4410406672","doi":"10.1016/j.acra.2025.04.064","title":"External Validation of a CT-Based Radiogenomics Model for the Detection of EGFR Mutation in NSCLC and the Impact of Prevalence in Model Building by Using Synthetic Minority Over Sampling (SMOTE): Lessons Learned","year":2025,"lang":"en","type":"article","venue":"Academic Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University Health Network","funders":"","keywords":"Radiogenomics; Sampling (signal processing); Medicine; Mutation; Computer science; Oncology; Radiology; Radiomics; Biology; Computer vision; Genetics; Gene","score_opus":0.04173479569458079,"score_gpt":0.39029098765674325,"score_spread":0.3485561919621625,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410406672","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5760891,0.0014541838,0.42175105,0.00036512007,0.000020023093,0.0003083619,0.000006828113,0.0000026232503,0.0000027101187],"genre_scores_gemma":[0.9950585,0.0009104847,0.0039199893,0.000057327612,0.000016156217,0.000018858169,0.0000034027778,0.0000092438295,0.0000060549946],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988082,0.00017892048,0.00053960277,0.0002064624,0.00009470588,0.00017209588],"domain_scores_gemma":[0.99815524,0.0012984131,0.00032970504,0.0001509271,0.000041884054,0.000023853177],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018027578,0.00010848748,0.00039791572,0.00033372748,0.000044260552,0.0000030197673,0.0001339408,0.00012701038,7.338598e-7],"category_scores_gemma":[0.0012639227,0.00007394709,0.00009835999,0.0002699633,0.00033373744,0.000050481627,0.000025707439,0.00051409745,9.242964e-9],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00049634586,0.000016282145,0.009281352,0.00014996223,0.000028573186,1.9856986e-7,0.00032916953,0.6069381,0.37229803,0.0003299256,0.0000017227527,0.010130306],"study_design_scores_gemma":[0.0030017798,0.000045140474,0.005506542,0.00032188054,0.00014080724,0.000025103565,0.000036605477,0.9731909,0.013815264,0.0038648942,6.2112696e-7,0.000050442497],"about_ca_topic_score_codex":0.000901309,"about_ca_topic_score_gemma":0.0000033943545,"teacher_disagreement_score":0.4189694,"about_ca_system_score_codex":0.00014534652,"about_ca_system_score_gemma":0.00016370317,"threshold_uncertainty_score":0.3015475},"labels":[],"label_agreement":null},{"id":"W4410447758","doi":"10.3233/shti250403","title":"Does Whole Brain Radiomics on Multimodal Neuroimaging Make Sense in Neuro-Oncology? A Proof of Concept Study","year":2025,"lang":"en","type":"article","venue":"Studies in health technology and informatics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Neuroimaging; Radiomics; Medicine; Radiology; Brain tumor; Modalities; Modality (human–computer interaction); Magnetic resonance imaging; Oncology; Pathology; Internal medicine; Artificial intelligence; Computer science; Psychiatry","score_opus":0.018996044023424703,"score_gpt":0.3756206919994421,"score_spread":0.3566246479760174,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410447758","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9218495,0.001033757,0.00035230632,0.07446744,0.00047031234,0.001303939,0.0000041946955,0.00006730996,0.00045126592],"genre_scores_gemma":[0.9888123,0.00037079005,0.0026344145,0.00804486,0.000015731524,0.00004753107,0.000002629667,0.0000094750685,0.00006225071],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9981517,0.00011582838,0.0010728975,0.00018015495,0.00012805426,0.00035132625],"domain_scores_gemma":[0.99871147,0.0006349033,0.00027288543,0.00027056804,0.00006330169,0.000046892314],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010958479,0.00017065533,0.00078607764,0.0011242374,0.00011010306,0.000004884885,0.00010014316,0.00012747216,6.8760176e-7],"category_scores_gemma":[0.003125091,0.0001169067,0.00002703411,0.0008050705,0.0007856331,0.000050743463,0.00021024818,0.0011437555,3.2349183e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041268914,0.0011671872,0.4178906,0.0033253585,0.00018184994,0.00024095751,0.04349127,0.0011318994,0.00006315147,0.004107915,0.0017942972,0.5261928],"study_design_scores_gemma":[0.041490782,0.013554106,0.117757715,0.007051221,0.00016043564,0.00042611448,0.3777684,0.35891145,0.0008935266,0.008177312,0.07290901,0.00089993584],"about_ca_topic_score_codex":0.000029796673,"about_ca_topic_score_gemma":0.00003959914,"teacher_disagreement_score":0.5252929,"about_ca_system_score_codex":0.00015519097,"about_ca_system_score_gemma":0.00018902033,"threshold_uncertainty_score":0.49691123},"labels":[],"label_agreement":null},{"id":"W4410582236","doi":"10.23919/eucap63536.2025.10999754","title":"Image-to-Image Autoencoders for Quantifying Confidence in Machine Learning Solutions to the Inverse Scattering Problem","year":2025,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Artificial intelligence; Computer science; Image (mathematics); Inverse problem; Inverse; Pattern recognition (psychology); Machine learning; Computer vision; Mathematics; Mathematical analysis; Geometry","score_opus":0.031326384521745076,"score_gpt":0.337111651175627,"score_spread":0.30578526665388195,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410582236","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026020128,0.00009014763,0.8256248,0.13881192,0.00025090238,0.0014527525,0.000003223521,0.00017863567,0.007567468],"genre_scores_gemma":[0.52089673,0.000046478013,0.45021364,0.020528752,0.00013119601,0.00034687034,0.000025053629,0.000053897835,0.007757394],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984533,0.00007375829,0.00037171625,0.00039147507,0.00019004654,0.0005196669],"domain_scores_gemma":[0.999101,0.0002951507,0.000050388633,0.00027323197,0.000099842815,0.00018040104],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013288012,0.00017054043,0.00029244533,0.00036303428,0.0003499095,0.00010471344,0.00023235874,0.000048413956,0.00007514978],"category_scores_gemma":[0.0018208213,0.00012686398,0.00009254954,0.0006223587,0.00010197621,0.0001083273,0.00019540732,0.00061637594,0.00005933343],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009086782,0.0005754968,0.08843422,0.0028297605,0.00042419342,0.0001857448,0.014589839,0.10156633,0.5073297,0.025972448,0.16303995,0.094143644],"study_design_scores_gemma":[0.0013223299,0.00012357351,0.0050803027,0.0007960648,0.00006345895,0.00002252109,0.0011120631,0.93289727,0.00041478456,0.0003289336,0.057636153,0.00020252637],"about_ca_topic_score_codex":0.0011622617,"about_ca_topic_score_gemma":0.000920771,"teacher_disagreement_score":0.83133096,"about_ca_system_score_codex":0.00012627976,"about_ca_system_score_gemma":0.00014631967,"threshold_uncertainty_score":0.51733625},"labels":[],"label_agreement":null},{"id":"W4410639462","doi":"10.3390/curroncol32060300","title":"18F-FDG PET/CT Semiquantitative and Radiomic Features for Assessing Pathologic Axillary Lymph Node Status in Clinical Stage I–III Breast Cancer Patients: A Systematic Review","year":2025,"lang":"en","type":"review","venue":"Current Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Hamilton Health Sciences; Population Health Research Institute; University of Saskatchewan; Wilfrid Laurier University; University of Ottawa; McMaster University","funders":"McMaster University","keywords":"Medicine; Breast cancer; Stage (stratigraphy); Lymph node; Radiology; Cancer; Pathology; Internal medicine","score_opus":0.08677226308907893,"score_gpt":0.5118916021429658,"score_spread":0.4251193390538869,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410639462","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00066638656,0.99048305,0.00015062084,0.00034643375,0.0020953473,0.005618073,0.00045553167,0.000056139157,0.00012842075],"genre_scores_gemma":[0.00007848426,0.99548775,0.0007583125,0.000907715,0.0002065021,0.001422876,0.0008924999,0.00006793373,0.00017794568],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9934079,0.002095183,0.0024818764,0.0010096232,0.00030271732,0.00070269674],"domain_scores_gemma":[0.9936976,0.0036260437,0.001634608,0.00045552832,0.0002635738,0.00032266165],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0028473537,0.0006857811,0.0072426065,0.00045242722,0.00013754974,0.000045014014,0.00028689622,0.00014089992,0.00002845003],"category_scores_gemma":[0.0054354295,0.0004791002,0.0007458727,0.00046489885,0.00037925222,0.00009559944,0.0002192922,0.0017864656,0.0000038103012],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028577291,0.00040567917,0.0039282357,0.6840742,0.00021930135,0.0006238602,0.00003228788,3.5164723e-7,2.9569033e-8,0.00004335467,0.001374407,0.3092697],"study_design_scores_gemma":[0.0034193231,0.0001853334,0.0016806904,0.8153868,0.0067047384,0.0023872785,0.000065488886,0.00022345153,8.225167e-9,0.000012855468,0.16947281,0.00046123983],"about_ca_topic_score_codex":0.000040128154,"about_ca_topic_score_gemma":0.0000059597523,"teacher_disagreement_score":0.30880848,"about_ca_system_score_codex":0.0011428547,"about_ca_system_score_gemma":0.002661507,"threshold_uncertainty_score":0.99976605},"labels":[],"label_agreement":null},{"id":"W4410702293","doi":"10.47363/jcrr/2023(5)179","title":"AI-Driven Advancements in Breast Cancer: Transforming Detection,Diagnosis, Treatment, and Monitoring","year":2023,"lang":"en","type":"article","venue":"Journal of Cancer Research Reviews & Reports","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Breast cancer; Medicine; Cancer; Oncology; Internal medicine","score_opus":0.07029862980511747,"score_gpt":0.4835681498195882,"score_spread":0.4132695200144707,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410702293","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88882357,0.0979585,0.00005569946,0.011669112,0.0006330934,0.0007350945,0.0000025939205,0.000016298003,0.000106012216],"genre_scores_gemma":[0.5002504,0.49863672,0.00010062701,0.00006075646,0.0005908838,0.0001952984,7.5776853e-7,0.000019898513,0.0001446579],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975679,0.00017638001,0.00093718746,0.00024080956,0.00064302573,0.00043469624],"domain_scores_gemma":[0.99875546,0.000098982724,0.00035932194,0.00017399613,0.00029407063,0.00031818094],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026213897,0.00014681196,0.0006412331,0.00058731186,0.00012777295,0.000045581914,0.00007135128,0.000052182557,0.000059230253],"category_scores_gemma":[0.0003047565,0.00010367058,0.00014360885,0.0008379768,0.00009517052,0.00026142082,0.000022525604,0.00080282683,0.0000019890012],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000059128623,0.000054228407,0.41321316,0.000192612,0.000049893755,0.0009987851,0.00023706724,0.00007208184,0.004020789,7.0669756e-7,0.00046075354,0.5806408],"study_design_scores_gemma":[0.002727956,0.00062907324,0.36099958,0.017567452,0.00023137538,0.0046276636,0.00022729964,0.00059969636,0.0048491145,0.00021066875,0.60708624,0.0002438582],"about_ca_topic_score_codex":0.0007644004,"about_ca_topic_score_gemma":0.00009725129,"teacher_disagreement_score":0.6066255,"about_ca_system_score_codex":0.00080447766,"about_ca_system_score_gemma":0.00042106735,"threshold_uncertainty_score":0.42275637},"labels":[],"label_agreement":null},{"id":"W4410759694","doi":"10.5220/0013329700004558","title":"AI-Driven Lung Cancer Screening: A Comparative Analysis of Machine Learning Models","year":2024,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Aurora College","funders":"","keywords":"Computer science; Cancer; Artificial intelligence; Machine learning; Medicine; Internal medicine","score_opus":0.03654636502786698,"score_gpt":0.37136585975990316,"score_spread":0.3348194947320362,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410759694","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21631652,0.011629486,0.7404031,0.010239147,0.00019463888,0.00034229376,0.000025811249,0.00038190465,0.020467054],"genre_scores_gemma":[0.98908705,0.0002577056,0.006247802,0.00072994153,0.00008121868,0.0000133922285,0.00007583895,0.00001858306,0.0034884915],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998765,0.000060666374,0.00031578902,0.00030543684,0.00033835336,0.0002147455],"domain_scores_gemma":[0.99938726,0.00014827543,0.000058550035,0.00015602286,0.00009613508,0.00015375948],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00026004022,0.0001502494,0.00061261083,0.0005774433,0.000059259695,0.000037355945,0.00008662902,0.000054178196,0.0009285627],"category_scores_gemma":[0.000043564163,0.00011179193,0.0002827367,0.0011845661,0.000090487934,0.000111736656,0.000051689716,0.00067216257,0.0000032466694],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011443992,0.0000926484,0.1266441,0.00032070573,0.010623435,0.00010235137,0.0039546485,0.8251515,0.0036156175,0.00901403,0.00452414,0.01584237],"study_design_scores_gemma":[0.00034787835,0.000053320568,0.0027773357,0.00025517854,0.003133637,0.00000772301,0.0001084732,0.9885824,0.00015322682,0.00004545722,0.0044232653,0.00011212943],"about_ca_topic_score_codex":0.0013201813,"about_ca_topic_score_gemma":0.000056966634,"teacher_disagreement_score":0.7727705,"about_ca_system_score_codex":0.00005027924,"about_ca_system_score_gemma":0.000083913925,"threshold_uncertainty_score":0.99998474},"labels":[],"label_agreement":null},{"id":"W4410774918","doi":"10.1016/j.procs.2025.03.180","title":"An Analysis of YOLOvX Deep Learning Models for Colon Cancer Detection","year":2025,"lang":"en","type":"article","venue":"Procedia Computer Science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University","funders":"University Grants Commission","keywords":"Computer science; Deep learning; Artificial intelligence; Cancer; Machine learning; Medicine; Internal medicine","score_opus":0.012664761011906993,"score_gpt":0.32391272529476606,"score_spread":0.31124796428285906,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410774918","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3581436,0.000089614834,0.64108694,0.00025291895,0.00018451021,0.00013232071,4.250231e-7,0.000035593697,0.00007406059],"genre_scores_gemma":[0.95960724,0.000027822682,0.039801974,0.0004110623,0.000075205084,0.000031479292,0.0000032123787,0.000004825079,0.000037171027],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990088,0.000015494894,0.0001867802,0.00034168738,0.00023847577,0.00020878679],"domain_scores_gemma":[0.99927044,0.00007692337,0.000086733016,0.00015091192,0.00031439675,0.000100582656],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00063997315,0.00007631537,0.00024842072,0.0005734026,0.00017002707,0.00003975363,0.00020363054,0.000034351844,0.0000037039365],"category_scores_gemma":[0.00016702511,0.000066426575,0.00007362359,0.0017631598,0.00020169427,0.00018566236,0.000047363945,0.00016104234,2.040267e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000056994708,0.00007263377,0.026875068,0.00012924026,0.00013214775,9.283411e-7,0.0008482242,0.4013557,0.024605146,0.00071322813,0.000011105031,0.5451996],"study_design_scores_gemma":[0.0003160009,0.00016160593,0.01594492,0.000044912187,0.00033581498,0.0000016129632,0.000022315287,0.9789087,0.0038049656,0.0002851947,0.00011523582,0.000058678612],"about_ca_topic_score_codex":0.000080926744,"about_ca_topic_score_gemma":0.000021577524,"teacher_disagreement_score":0.6014636,"about_ca_system_score_codex":0.000077571814,"about_ca_system_score_gemma":0.00020019803,"threshold_uncertainty_score":0.27087972},"labels":[],"label_agreement":null},{"id":"W4410802702","doi":"10.1200/jco.2025.43.16_suppl.e13155","title":"Association of MRI biomarkers on survival in TNBC patients: A retrospective, multi-center cohort study.","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Medicine; Retrospective cohort study; Cohort; Oncology; Center (category theory); Internal medicine","score_opus":0.03379967206470782,"score_gpt":0.4460606835638494,"score_spread":0.4122610114991416,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410802702","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9841203,0.000022779404,0.0002627268,0.008460771,0.0024533842,0.0003316082,0.000001798692,0.0000048207216,0.0043418263],"genre_scores_gemma":[0.9967691,0.0001520622,0.0011251549,0.0013331688,0.0001911714,0.0000025395814,0.0000023731811,0.00000866814,0.00041580095],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9961813,0.0008455933,0.002111387,0.00018193413,0.00050908944,0.00017068388],"domain_scores_gemma":[0.9956603,0.0019310856,0.0016160511,0.00013624801,0.0005270516,0.00012926928],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00845128,0.00009806893,0.0013521382,0.00028543948,0.00002002086,0.0000050262533,0.00012947022,0.00023859732,0.00003360495],"category_scores_gemma":[0.024510702,0.00007237106,0.00028443243,0.00025653746,0.00008346955,0.000046264297,0.000044014614,0.0013614454,0.0000028263462],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017730701,0.011249552,0.96544975,0.000014979878,0.00082126376,0.00009643124,0.00005911236,0.000010837575,0.000009081034,0.00002142246,0.004481268,0.016013203],"study_design_scores_gemma":[0.02541101,0.0054004597,0.96261376,0.00017030782,0.00022268257,0.000002218678,0.00009324256,0.0006465988,0.0000023676516,0.0000418271,0.005349662,0.000045846915],"about_ca_topic_score_codex":0.000052161286,"about_ca_topic_score_gemma":0.00006241548,"teacher_disagreement_score":0.02363794,"about_ca_system_score_codex":0.0006050981,"about_ca_system_score_gemma":0.0004602428,"threshold_uncertainty_score":0.98370624},"labels":[],"label_agreement":null},{"id":"W4410803897","doi":"10.1200/jco.2025.43.16_suppl.3612","title":"Multicentric evaluation of an artificial intelligence model to stratify stage II colon cancer patients from whole slide images.","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Centre Hospitalier de l’Université de Montréal","funders":"","keywords":"Medicine; Stage (stratigraphy); Colorectal cancer; Cancer; Internal medicine; Oncology; Artificial intelligence; Pathology","score_opus":0.16159546099774189,"score_gpt":0.5412015697004228,"score_spread":0.37960610870268086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410803897","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9749006,0.00015910673,0.014829333,0.007999832,0.0012680984,0.00032146528,0.000019288163,0.0000054451752,0.0004968177],"genre_scores_gemma":[0.9799302,0.00009116111,0.016979868,0.0024367184,0.0003985285,0.0000055920445,0.000010312731,0.000009474772,0.00013814351],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99626976,0.0005093474,0.0021510632,0.00020871001,0.0006837099,0.00017740339],"domain_scores_gemma":[0.99610066,0.0009257541,0.0011555344,0.00017077615,0.0013241546,0.00032314035],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004896709,0.000106355474,0.0008891348,0.00018620005,0.000054176504,0.000010655102,0.0002013756,0.00021501645,0.00014046035],"category_scores_gemma":[0.012987626,0.000083210805,0.00018448349,0.00021366322,0.00012397068,0.0001124593,0.00007031785,0.00095443765,0.0000032860305],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021317792,0.0029638072,0.01580873,0.00002441777,0.00019251667,0.000025913485,0.00038060127,0.05406406,0.004786718,0.00010968134,0.0013845033,0.91812724],"study_design_scores_gemma":[0.0039996696,0.0052204193,0.086921066,0.00027454682,0.0010113163,0.0000017773596,0.0002397942,0.8940463,0.0022672226,0.0029182187,0.002992511,0.00010713018],"about_ca_topic_score_codex":0.00018909649,"about_ca_topic_score_gemma":0.00008563019,"teacher_disagreement_score":0.9180201,"about_ca_system_score_codex":0.0002474554,"about_ca_system_score_gemma":0.002493229,"threshold_uncertainty_score":0.9953264},"labels":[],"label_agreement":null},{"id":"W4410808660","doi":"10.1200/jco.2025.43.16_suppl.e13647","title":"Cox models vs. machine learning for survival prediction: Do traditional approaches still hold their ground?","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Princess Margaret Cancer Centre; Mount Sinai Hospital","funders":"","keywords":"Medicine; Proportional hazards model; Artificial intelligence; Machine learning; Oncology; Internal medicine; Computer science","score_opus":0.23888608714313792,"score_gpt":0.4226417471523241,"score_spread":0.1837556600091862,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410808660","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48708686,0.0034491792,0.3520968,0.11595931,0.010737583,0.0009666174,0.000073502975,0.00011801572,0.029512143],"genre_scores_gemma":[0.9816864,0.00072594924,0.010091308,0.003236023,0.0030710762,0.000013380013,0.00004553779,0.000027459566,0.0011028751],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964586,0.000515459,0.002058638,0.00027850101,0.00040308002,0.0002857496],"domain_scores_gemma":[0.99296784,0.005159028,0.0009970586,0.0001579808,0.00035787665,0.0003601922],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.006963933,0.00018721787,0.0014835045,0.0002074892,0.00012563988,0.00003085719,0.00023099863,0.0003949188,0.00007275694],"category_scores_gemma":[0.005877389,0.00013117955,0.00072422664,0.00016935387,0.00033572887,0.00015643395,0.000049865022,0.0025625534,0.0000021256296],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.01693351,0.0057832813,0.13418458,0.00047140726,0.0033020268,0.0003636422,0.00053679146,0.026729733,0.00015112456,0.04681489,0.032170787,0.73255825],"study_design_scores_gemma":[0.015560426,0.008026714,0.06516176,0.00032682464,0.00073846866,0.0005376097,0.00025289107,0.5386678,0.000009543333,0.025583105,0.34496084,0.00017401786],"about_ca_topic_score_codex":0.000009421186,"about_ca_topic_score_gemma":0.0000027110636,"teacher_disagreement_score":0.7323842,"about_ca_system_score_codex":0.00014927232,"about_ca_system_score_gemma":0.0012423872,"threshold_uncertainty_score":0.9997386},"labels":[],"label_agreement":null},{"id":"W4410808825","doi":"10.1200/jco.2025.43.16_suppl.1557","title":"Computational pathology to predict docetaxel benefit for high-risk localized prostate cancer in NRG/RTOG 0521 (NCT00288080).","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"London Health Sciences Centre","funders":"DOD Prostate Cancer Research Program; National Institute of Biomedical Imaging and Bioengineering; DOD Peer Reviewed Cancer Research Program; National Heart, Lung, and Blood Institute; California Breast Cancer Research Program","keywords":"Medicine; Docetaxel; Prostate cancer; Oncology; Internal medicine; Gynecology; Cancer","score_opus":0.031499245250890436,"score_gpt":0.4508992075127031,"score_spread":0.4193999622618127,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410808825","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.898325,0.00086534675,0.027438411,0.0693682,0.0028498273,0.0006357182,0.000030504296,0.00001664341,0.0004703185],"genre_scores_gemma":[0.93557805,0.0012715246,0.044975664,0.016211068,0.0011038516,0.000049218204,0.000012517836,0.00002589913,0.00077221735],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9960917,0.00035820744,0.0025748855,0.0003094022,0.00031121314,0.00035455212],"domain_scores_gemma":[0.9940756,0.0037044785,0.0010981889,0.00015316675,0.0005814379,0.0003871411],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0049559567,0.00016646531,0.0016769537,0.0003641603,0.000064271066,0.000012509182,0.0002177576,0.00034685468,0.0000929796],"category_scores_gemma":[0.010719131,0.00012492173,0.00034124515,0.00029595906,0.00021958014,0.000062194624,0.000079184785,0.0015908051,0.000005674031],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0071795867,0.0009911363,0.4329474,0.0001131636,0.00036753362,0.0004508268,0.00017396644,0.024168078,0.000049681257,0.0014485792,0.010429027,0.521681],"study_design_scores_gemma":[0.03625933,0.00794831,0.7634633,0.00059966487,0.0006473779,0.00019144446,0.000092338334,0.040420394,0.000017818937,0.020366047,0.1298096,0.00018432563],"about_ca_topic_score_codex":0.00017791038,"about_ca_topic_score_gemma":0.00009515307,"teacher_disagreement_score":0.5214967,"about_ca_system_score_codex":0.00023400577,"about_ca_system_score_gemma":0.002014115,"threshold_uncertainty_score":0.997614},"labels":[],"label_agreement":null},{"id":"W4410808834","doi":"10.1200/jco.2025.43.16_suppl.1552","title":"Evaluation of longitudinal image-derived AI prognostication as a predictor of overall survival (OS) in a phase 3 advanced non-small cell lung cancer (aNSCLC) trial.","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Medicine; Lung cancer; Oncology; Cancer; Internal medicine","score_opus":0.06920299580114199,"score_gpt":0.5114228554236663,"score_spread":0.4422198596225243,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410808834","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.982166,0.000931353,0.006349366,0.0060873637,0.0016147294,0.0010108969,0.000003998578,0.0000053415506,0.0018309287],"genre_scores_gemma":[0.9935036,0.0009763067,0.0044231806,0.00047527257,0.00047943136,0.000033963646,0.000005581321,0.000014147422,0.00008855174],"study_design_codex":"design_other","study_design_gemma":"randomized_trial","domain_scores_codex":[0.9947531,0.0010012861,0.003010945,0.00023778336,0.00078888395,0.00020799029],"domain_scores_gemma":[0.9931126,0.0023225807,0.0023148744,0.00019590165,0.0018596178,0.00019438312],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.011824088,0.00014124071,0.0015606943,0.0002829545,0.000020828638,0.0000066269363,0.00019071452,0.0002561906,0.00014375045],"category_scores_gemma":[0.020389896,0.00011228009,0.0003551392,0.00025237523,0.00022611902,0.00011814799,0.000038196464,0.0011611583,8.193081e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.1462015,0.018415751,0.3090714,0.0010781025,0.0014299371,0.00020894871,0.0007725927,0.0026769997,0.058545,0.00019604713,0.0022396683,0.45916405],"study_design_scores_gemma":[0.4241916,0.016798045,0.39450458,0.002086779,0.004641398,0.000027410675,0.00013954008,0.15185544,0.0027482158,0.0013503113,0.0014706778,0.00018600603],"about_ca_topic_score_codex":0.0001021046,"about_ca_topic_score_gemma":0.000033141867,"teacher_disagreement_score":0.45897806,"about_ca_system_score_codex":0.0002491129,"about_ca_system_score_gemma":0.0059080566,"threshold_uncertainty_score":0.99972755},"labels":[],"label_agreement":null},{"id":"W4410816674","doi":"10.1200/jco.2025.43.16_suppl.4181","title":"Multimodal machine learning predictions of treatment response and survival in advanced pancreatic cancer from the COMPASS trial.","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto; Ontario Institute for Cancer Research; Université de Montréal; University Health Network","funders":"Princess Margaret Cancer Foundation","keywords":"Medicine; Pancreatic cancer; Compass; Oncology; Cancer; Internal medicine; Artificial intelligence; Cartography","score_opus":0.06053923847275409,"score_gpt":0.4690654250365223,"score_spread":0.4085261865637682,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410816674","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96849996,0.0019286176,0.0005861932,0.027308596,0.0011064274,0.0002514293,0.0000062686404,0.0000057828847,0.00030674034],"genre_scores_gemma":[0.99341345,0.0033719977,0.0018812692,0.0006370435,0.0003550144,0.000009950782,0.0000026359435,0.000007947542,0.00032071676],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99645454,0.0015428561,0.001557112,0.00014190473,0.0001688062,0.00013475637],"domain_scores_gemma":[0.985518,0.013298538,0.000804809,0.0001242345,0.000121033634,0.00013338149],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003915614,0.00010190474,0.0012531648,0.00010599165,0.00005185574,0.000005600915,0.0000983667,0.00014375811,0.00004407592],"category_scores_gemma":[0.012588865,0.000057714806,0.00021090271,0.00014458479,0.0002489774,0.000035899782,0.000036690228,0.0011418692,3.7559735e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.13763264,0.0009744664,0.6800801,0.000013472393,0.0005244491,0.00008745856,0.0002929388,0.0023631277,0.00047897684,0.000037357084,0.00017817669,0.17733683],"study_design_scores_gemma":[0.09313082,0.008901794,0.82005876,0.00034729455,0.00057701493,0.00001756095,0.0002771175,0.040661935,0.000013609238,0.0001328108,0.03583298,0.000048320147],"about_ca_topic_score_codex":0.0010966056,"about_ca_topic_score_gemma":0.00025955125,"teacher_disagreement_score":0.1772885,"about_ca_system_score_codex":0.00020354685,"about_ca_system_score_gemma":0.0012637216,"threshold_uncertainty_score":0.9957285},"labels":[],"label_agreement":null},{"id":"W4410842945","doi":"10.1038/s41746-025-01729-5","title":"Comparative analysis of natural language processing methodologies for classifying computed tomography enterography reports in Crohn’s disease patients","year":2025,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Alberta Innovates; Canadian Institutes of Health Research; Mitacs; University of Alberta; CIHR Skin Research Training Centre; Alberta Machine Intelligence Institute; Government of Canada; Canadian Institute for Advanced Research; Natural Sciences and Engineering Research Council of Canada; Alberta Health Services","keywords":"Crohn's disease; Computed tomography; Medicine; Disease; Radiology; Crohn disease; Artificial intelligence; Natural language processing; Computer science; Pathology","score_opus":0.02703396727880505,"score_gpt":0.3803729274664553,"score_spread":0.35333896018765026,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410842945","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9781195,0.0038202663,0.014296882,0.0010169995,0.00032210076,0.00066964864,0.000020153206,0.00008308195,0.0016514012],"genre_scores_gemma":[0.995105,0.000007813321,0.003671309,0.00055674673,0.00004539567,0.000033981563,0.0004988615,0.000009591183,0.00007127541],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9982657,0.000055846267,0.00070201606,0.00038604796,0.0003273211,0.00026311478],"domain_scores_gemma":[0.9985783,0.00051514874,0.00029308983,0.00024201993,0.00023149443,0.00013995363],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040353168,0.00020002188,0.0009914596,0.0016046095,0.00005153935,0.000030201407,0.00010585177,0.00005229399,0.0000057854713],"category_scores_gemma":[0.0017353185,0.00014610942,0.00027270862,0.0022324806,0.00036400493,0.00014478766,0.00005589646,0.0002824739,7.93713e-8],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004977821,0.00026729223,0.8978922,0.000532412,0.00086766126,0.00012672441,0.001404118,0.000109948094,0.00027783812,0.00005530257,0.0004919939,0.097476736],"study_design_scores_gemma":[0.0019577155,0.00013308841,0.9618769,0.0012028468,0.0011342943,0.0000021843593,0.00093412574,0.032048915,0.000050891853,0.00019252913,0.00035102112,0.00011546379],"about_ca_topic_score_codex":0.000030638585,"about_ca_topic_score_gemma":0.0000067600286,"teacher_disagreement_score":0.097361274,"about_ca_system_score_codex":0.000044926634,"about_ca_system_score_gemma":0.00006171882,"threshold_uncertainty_score":0.5958169},"labels":[],"label_agreement":null},{"id":"W4410851777","doi":"10.2106/jbjs.oa.25.00055","title":"JBJS Open Access 2024 Award Winners and Journal Update","year":2025,"lang":"en","type":"editorial","venue":"JBJS Open Access","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Hospital; Sunnybrook Health Science Centre","funders":"","keywords":"Library science; Political science; World Wide Web; Computer science","score_opus":0.031166710730827784,"score_gpt":0.47409108000541184,"score_spread":0.44292436927458406,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410851777","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008439838,0.0013490376,0.00048978376,0.03152802,0.89239866,0.0022033935,0.00013832381,0.000072395385,0.07097643],"genre_scores_gemma":[0.00043179278,0.01456469,0.0025129716,0.008882697,0.82020575,0.00021882821,0.0012545063,0.00028737218,0.15164141],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9951429,0.00029704196,0.001112948,0.0012546938,0.0013683833,0.000824037],"domain_scores_gemma":[0.99599034,0.0007104848,0.00083961483,0.0010041052,0.00059848616,0.00085694384],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":["open_science"],"category_scores_codex":[0.0030168006,0.0007292927,0.0019360093,0.0006336041,0.00067730364,0.0288163,0.0129331555,0.00083032006,0.0017977607],"category_scores_gemma":[0.004661029,0.0005854943,0.00021915263,0.0007837213,0.00029655048,0.0046958495,0.019903146,0.0056309463,0.00005356329],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044714662,0.00010889089,0.002232863,0.0005343026,0.0005501582,0.0006154342,0.000056524634,0.000015900894,0.0000063610078,0.0000758462,0.95596707,0.039389502],"study_design_scores_gemma":[0.0046344707,0.00013258152,0.0007901587,0.0025758583,0.00074020255,0.00011285024,0.00005207553,0.0004744022,0.00001618417,0.0011918875,0.98864824,0.00063111586],"about_ca_topic_score_codex":0.0032835775,"about_ca_topic_score_gemma":0.000103405924,"teacher_disagreement_score":0.080664985,"about_ca_system_score_codex":0.00035161254,"about_ca_system_score_gemma":0.0034841269,"threshold_uncertainty_score":0.99965966},"labels":[],"label_agreement":null},{"id":"W4410870007","doi":"10.18280/rces.120101","title":"Predicting Lymph Node Metastasis in T1 Colorectal Cancer Patients Using Interpretable Machine Learning Models: A Multicenter Retrospective Study","year":2025,"lang":"en","type":"article","venue":"Review of Computer Engineering Studies","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Lymph node metastasis; Colorectal cancer; Medicine; Lymph node; Multicenter study; Retrospective cohort study; Metastasis; Cancer; Oncology; Artificial intelligence; General surgery; Internal medicine; Computer science","score_opus":0.016213006433741357,"score_gpt":0.3145116209872639,"score_spread":0.2982986145535225,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410870007","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8708881,0.103351675,0.023961432,0.00017682009,0.0005545057,0.00091887085,0.0000058431006,0.00008693582,0.000055781213],"genre_scores_gemma":[0.9737045,0.017454837,0.008451344,0.00021856934,0.00006184107,0.00006138141,0.0000053131917,0.000029440012,0.000012727255],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99829596,0.00010327899,0.0006825471,0.00034745497,0.00028722628,0.00028354005],"domain_scores_gemma":[0.9992297,0.00013297483,0.0001754125,0.00015135498,0.00025913017,0.00005141245],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006143176,0.00026252508,0.0011476142,0.00027089755,0.00006118246,0.00001336201,0.00012530804,0.000032080035,0.0000044002704],"category_scores_gemma":[0.0006118211,0.0002189525,0.00014409475,0.0004925899,0.000039280705,0.000108966364,0.00027568245,0.00045419057,3.1964436e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034911547,0.00034528968,0.86403716,0.009357826,0.0011547419,0.000013813386,0.0012152026,0.11773398,0.00006197082,0.000013246648,0.000025326071,0.00600654],"study_design_scores_gemma":[0.0015855399,0.00011201715,0.08880041,0.034224145,0.00046133008,0.0000027545532,0.000071514834,0.87451017,0.000022924207,0.0000034020054,0.00006859067,0.00013721296],"about_ca_topic_score_codex":0.00021357472,"about_ca_topic_score_gemma":0.0000049548153,"teacher_disagreement_score":0.7752367,"about_ca_system_score_codex":0.00038716712,"about_ca_system_score_gemma":0.000046633944,"threshold_uncertainty_score":0.8928624},"labels":[],"label_agreement":null},{"id":"W4410958629","doi":"10.3390/curroncol32060323","title":"A Clinical–Radiomics Nomogram for the Preoperative Prediction of Aggressive Micropapillary and a Solid Pattern in Lung Adenocarcinoma","year":2025,"lang":"en","type":"article","venue":"Current Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Soochow University","keywords":"Radiomics; Nomogram; Medicine; Adenocarcinoma; Lung; Radiology; Pathology; Oncology; Internal medicine; Cancer","score_opus":0.05031317146878455,"score_gpt":0.43648215951868297,"score_spread":0.3861689880498984,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410958629","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.944943,0.02716674,0.020258063,0.0045872056,0.0015814626,0.0012799614,0.000025912605,0.000017848719,0.00013978142],"genre_scores_gemma":[0.99341357,0.0050161825,0.0005419265,0.0005533945,0.0002540812,0.00012945646,0.00003172512,0.000011093341,0.000048543272],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9988052,0.00015428178,0.0005167787,0.0002627655,0.00007167557,0.00018928903],"domain_scores_gemma":[0.99845725,0.00090921373,0.000290326,0.00017126107,0.00010744055,0.00006453431],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006748134,0.00011137825,0.00044360824,0.00012747804,0.00006432793,0.00000872755,0.00010009534,0.00011543207,0.0000060762472],"category_scores_gemma":[0.0011439831,0.000076941025,0.00009401411,0.00013787061,0.00033579374,0.000024974172,0.000080688835,0.00053430186,3.426286e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015495442,0.00023632996,0.66174823,0.00026123034,0.00009324882,0.000009744081,0.00057503104,0.000010614324,0.00014510243,0.000058522844,0.0023454034,0.33436158],"study_design_scores_gemma":[0.0059773363,0.0008972346,0.7614763,0.00081822235,0.00039537332,0.00007051667,0.0003779847,0.21147206,0.00008898979,0.00015051321,0.01819334,0.00008213098],"about_ca_topic_score_codex":0.000019292645,"about_ca_topic_score_gemma":0.000011907153,"teacher_disagreement_score":0.33427945,"about_ca_system_score_codex":0.00009135847,"about_ca_system_score_gemma":0.000248961,"threshold_uncertainty_score":0.3137564},"labels":[],"label_agreement":null},{"id":"W4410964753","doi":"10.1038/s41467-025-60522-w","title":"Author Correction: Multi-institutional atlas of brain metastases informs spatial modeling for precision imaging and personalized therapy","year":2025,"lang":"en","type":"erratum","venue":"Nature Communications","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto; University Health Network","funders":"","keywords":"Atlas (anatomy); Computer science; Neuroimaging; Precision medicine; Personalized medicine; Data science; Medical physics; Neuroscience; Medicine; Bioinformatics; Psychology; Pathology; Biology; Anatomy","score_opus":0.030644736399149344,"score_gpt":0.3728927917567456,"score_spread":0.3422480553575963,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410964753","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00060521037,0.22270937,0.64047146,0.09543525,0.026303459,0.0038802489,0.00073893974,0.0003018196,0.009554237],"genre_scores_gemma":[0.2239981,0.060446747,0.45786244,0.011288931,0.0034448726,0.0010235015,0.034973565,0.00027599698,0.20668586],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99845225,0.00012148871,0.000546085,0.00031966236,0.00036017713,0.00020034652],"domain_scores_gemma":[0.9971426,0.0008998477,0.00028694383,0.00096153835,0.0005955717,0.00011347757],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0007830174,0.0002941807,0.0006407731,0.00038570203,0.00051627157,0.000053529202,0.00050185696,0.0005100316,0.00001964922],"category_scores_gemma":[0.0040098233,0.00022875797,0.00028105575,0.00024963668,0.00038430907,0.00010795862,0.00025724887,0.003033049,5.890849e-7],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029705532,0.00028419646,0.0004775718,0.00029170653,0.0004096821,0.0000019755828,0.0005020538,0.0003063679,0.00023119249,0.0023789234,0.83443254,0.16038676],"study_design_scores_gemma":[0.0013929373,0.000034304197,0.00018552462,0.0007093842,0.00012572155,0.000028801245,0.0000763927,0.49639398,0.000013436364,0.00007628528,0.50084746,0.000115748546],"about_ca_topic_score_codex":0.0002659527,"about_ca_topic_score_gemma":0.00010675134,"teacher_disagreement_score":0.4960876,"about_ca_system_score_codex":0.000109827,"about_ca_system_score_gemma":0.00086175324,"threshold_uncertainty_score":0.999267},"labels":[],"label_agreement":null},{"id":"W4410984910","doi":"10.1007/s10278-025-01554-y","title":"PARADIM: A Platform to Support Research at the Interface of Data Science and Medical Imaging","year":2025,"lang":"en","type":"article","venue":"Journal of Imaging Informatics in Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; Centre hospitalier de l'Université Laval; Institut universitaire de cardiologie et de pneumologie de Québec","funders":"Fonds de Recherche du Québec - Santé; Natural Sciences and Engineering Research Council of Canada; Bayerisches Staatsministerium für Wissenschaft und Kunst; Canadian Cancer Society; Bundesministerium für Bildung und Forschung; Deutscher Akademischer Austauschdienst","keywords":"Interface (matter); Computer science; Data science; Human–computer interaction; Medical physics; Medicine; Operating system","score_opus":0.057052427364343454,"score_gpt":0.4765283449928441,"score_spread":0.4194759176285006,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410984910","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6373861,0.005143203,0.03650903,0.27961424,0.0015552215,0.00088506617,0.0000066432667,0.000026196398,0.03887433],"genre_scores_gemma":[0.9832741,0.00085166976,0.0079263495,0.007493742,0.00021139212,0.0000025299125,0.0000044074322,0.000014520291,0.00022126072],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9948692,0.000066962864,0.0016281747,0.00016617772,0.0028011666,0.00046832173],"domain_scores_gemma":[0.99645305,0.0010631528,0.000405615,0.0007062826,0.0009601974,0.0004116943],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.028949296,0.00014856432,0.0005932317,0.0015412493,0.00019911648,0.00004742317,0.0013500112,0.000037890204,0.00011176841],"category_scores_gemma":[0.021651395,0.000085890104,0.00003147212,0.0016143166,0.0028277482,0.0007242195,0.0013504259,0.0016365694,0.0000040736704],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005240491,0.00015568752,0.095319316,0.0010816343,0.00011093994,0.0003740357,0.016512506,0.00011140967,0.0032133325,0.0014866913,0.22335568,0.6577547],"study_design_scores_gemma":[0.012393699,0.00094821904,0.03274829,0.0207086,0.0003368819,0.010621469,0.03346317,0.60336167,0.0017944742,0.0016389667,0.28159598,0.00038861224],"about_ca_topic_score_codex":0.00007769376,"about_ca_topic_score_gemma":0.000007551595,"teacher_disagreement_score":0.6573661,"about_ca_system_score_codex":0.00034736114,"about_ca_system_score_gemma":0.0015265343,"threshold_uncertainty_score":0.99990106},"labels":[],"label_agreement":null},{"id":"W4410995375","doi":"10.1245/s10434-025-17502-7","title":"ASO Visual Abstract: Diagnostic Value of Diffusion-Weighted MRI for the Detection of Peritoneal and Liver Metastases in High-Risk Pancreatic Ductal Adenocarcinoma—A Prospective Pilot Study","year":2025,"lang":"en","type":"article","venue":"Annals of Surgical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hôtel-Dieu de Québec; Université Laval","funders":"","keywords":"Medicine; Surgical oncology; Pancreatic ductal adenocarcinoma; Radiology; Prospective cohort study; Adenocarcinoma; Diffusion MRI; Internal medicine; Oncology; General surgery; Pancreatic cancer; Magnetic resonance imaging; Cancer","score_opus":0.02063441134258543,"score_gpt":0.3469373013874284,"score_spread":0.326302890044843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410995375","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9934336,0.0030927337,0.00031808257,0.0017796884,0.00012262465,0.0011324498,0.000017527662,0.0000085831125,0.00009472499],"genre_scores_gemma":[0.9957579,0.003786145,0.00020374208,0.00006612203,0.00006687582,0.00008111428,0.00000609091,0.0000102788845,0.000021747192],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99857175,0.00022443305,0.0005679624,0.00024682528,0.000198544,0.00019050388],"domain_scores_gemma":[0.99295,0.00638146,0.0002780729,0.00013322945,0.0001899583,0.00006727799],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00096917106,0.00013309062,0.0007544094,0.00017668327,0.000065528795,0.0000043067366,0.0000819534,0.00006938341,0.00002458562],"category_scores_gemma":[0.0010870672,0.000087470566,0.000088268825,0.0002446314,0.0004046625,0.000037355756,0.00007402505,0.0003404637,2.917018e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0069458117,0.0076102912,0.92605275,0.00046662905,0.00087889365,0.00030265423,0.0010765092,0.00008592896,0.004619016,0.0014079402,0.000102808655,0.050450772],"study_design_scores_gemma":[0.005189595,0.01039313,0.9748346,0.00013954582,0.0005833696,0.000041636464,0.0006272173,0.0051810327,0.0021216471,0.00048697958,0.0003301105,0.00007108834],"about_ca_topic_score_codex":0.0025297764,"about_ca_topic_score_gemma":0.00008915777,"teacher_disagreement_score":0.050379682,"about_ca_system_score_codex":0.000028131377,"about_ca_system_score_gemma":0.00011241503,"threshold_uncertainty_score":0.38242823},"labels":[],"label_agreement":null},{"id":"W4411067561","doi":"10.3390/cancers17111892","title":"Effectiveness of Artificial Intelligence Models in Predicting Lung Cancer Recurrence: A Gene Biomarker-Driven Review","year":2025,"lang":"en","type":"review","venue":"Cancers","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Lung cancer; KRAS; Medicine; Oncology; Radiogenomics; Internal medicine; Radiomics; Artificial intelligence; Cancer; Machine learning; Computer science; Radiology; Colorectal cancer","score_opus":0.051194356975905325,"score_gpt":0.41686407007228055,"score_spread":0.3656697130963752,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411067561","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00002977409,0.99027944,0.00584892,0.000059285183,0.00087144814,0.0023150453,0.000069168826,0.000035244077,0.0004917051],"genre_scores_gemma":[0.00013387851,0.998212,0.000524441,0.00008975924,0.00012842307,0.0007187662,0.0001098496,0.000045111738,0.000037783622],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.9969472,0.00049470464,0.0011465886,0.0006595034,0.0003609388,0.00039106375],"domain_scores_gemma":[0.99803334,0.00071245554,0.00052335835,0.00043650172,0.00014286044,0.00015148561],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001445664,0.00041451436,0.0027665938,0.00041994514,0.000044533495,0.000011788272,0.00033513844,0.00024834202,0.00005039428],"category_scores_gemma":[0.0010063724,0.00034746202,0.00047074864,0.0013635913,0.00017671239,0.000063111744,0.000113818685,0.0010511306,0.0000012786367],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023765668,0.000012588432,0.00005935935,0.32128257,0.00017074603,0.00002405688,0.000027662265,0.0009086975,0.000003221462,0.000063232306,0.0001602461,0.67726386],"study_design_scores_gemma":[0.00015282404,0.000041407806,0.000011824325,0.8941145,0.0021398142,0.000029415689,0.000008064858,0.0801906,0.000010400395,0.00009789348,0.022893708,0.00030952654],"about_ca_topic_score_codex":0.00084154896,"about_ca_topic_score_gemma":0.000015491005,"teacher_disagreement_score":0.6769543,"about_ca_system_score_codex":0.0022932708,"about_ca_system_score_gemma":0.004903366,"threshold_uncertainty_score":0.9998977},"labels":[],"label_agreement":null},{"id":"W4411091212","doi":"10.3390/curroncol32060334","title":"Using Machine Learning Approaches on Dynamic Patient-Reported Outcomes to Cluster Cancer Treatment-Related Symptoms","year":2025,"lang":"en","type":"article","venue":"Current Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine; Cancer; Cluster (spacecraft); Artificial intelligence; Machine learning; Bioinformatics; Data science; Intensive care medicine; Computer science; Internal medicine","score_opus":0.08503759980658077,"score_gpt":0.4229042938955958,"score_spread":0.33786669408901504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411091212","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9839135,0.00155506,0.0017632962,0.0070023723,0.00243329,0.0008102213,0.000005676303,0.00015642923,0.0023601553],"genre_scores_gemma":[0.9954685,0.00016558502,0.0008289378,0.0012038279,0.000067017165,0.00011565229,0.00009952795,0.00004330773,0.0020076267],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99808687,0.00019389915,0.0005459814,0.00052268594,0.00020932655,0.00044122804],"domain_scores_gemma":[0.9990163,0.00021238803,0.00020076828,0.00028004518,0.00006391236,0.00022662552],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021311919,0.00030401026,0.00070128345,0.00041604647,0.00017658118,0.000020998874,0.00010066987,0.00015814615,0.000103475],"category_scores_gemma":[0.0004265872,0.0002267183,0.00017868227,0.0003721791,0.00009955185,0.00003461677,0.00009344137,0.00073813845,0.000021673406],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023466973,0.0007587218,0.43101615,0.00006187186,0.0004825284,0.000046869085,0.0006552841,0.0064315395,0.00037757546,0.00011899794,0.00018625539,0.55962956],"study_design_scores_gemma":[0.009439244,0.0019220705,0.056931563,0.00068537006,0.0010855874,0.000095341355,0.00019652424,0.755927,0.00012771487,0.00010311211,0.17305997,0.0004264524],"about_ca_topic_score_codex":0.00019873769,"about_ca_topic_score_gemma":0.000037509595,"teacher_disagreement_score":0.7494955,"about_ca_system_score_codex":0.00120575,"about_ca_system_score_gemma":0.00031680163,"threshold_uncertainty_score":0.9245304},"labels":[],"label_agreement":null},{"id":"W4411141158","doi":"10.1200/edbk-25-472464","title":"Artificial Intelligence for Head and Neck Squamous Cell Carcinoma: From Diagnosis to Treatment","year":2025,"lang":"en","type":"review","venue":"American Society of Clinical Oncology Educational Book","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University Health Network","funders":"","keywords":"Head and neck squamous-cell carcinoma; Medicine; Radiation therapy; Clinical trial; Malignancy; Radiation treatment planning; Oncology; Head and neck cancer; Internal medicine","score_opus":0.11480080505809327,"score_gpt":0.5053163263542124,"score_spread":0.39051552129611916,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411141158","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017686764,0.95380276,0.001086717,0.039671715,0.000703396,0.0017832,0.0001515171,0.000017999515,0.0010140229],"genre_scores_gemma":[0.0005423791,0.92767096,0.056494642,0.009326101,0.0014723781,0.00086340366,0.00032133656,0.000031911,0.0032769165],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9970575,0.00020510121,0.0016254493,0.0006726568,0.00017626597,0.00026300346],"domain_scores_gemma":[0.9778502,0.020500943,0.0007868753,0.00030373113,0.00015621318,0.000402065],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005199322,0.0003114366,0.0030253553,0.00006686028,0.00008837468,0.0000098498485,0.00018172772,0.00029948037,0.00015805183],"category_scores_gemma":[0.002170371,0.00025015412,0.0013007435,0.00020214044,0.00086100295,0.000019758943,0.00007798682,0.00053984433,0.000014915836],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006066706,0.0014000352,0.0020637957,0.0014979412,0.00017690117,0.000001296369,0.00022610878,0.0000014420407,1.6758258e-7,0.0001625244,0.015129256,0.9792799],"study_design_scores_gemma":[0.00031706804,0.0028741101,0.0013898166,0.0009804198,0.0017930439,0.0000038900107,0.00014497526,0.00008700921,0.0000018473847,0.00034299967,0.9918825,0.00018231668],"about_ca_topic_score_codex":0.00053516834,"about_ca_topic_score_gemma":0.000009318604,"teacher_disagreement_score":0.97909755,"about_ca_system_score_codex":0.00037091234,"about_ca_system_score_gemma":0.005534389,"threshold_uncertainty_score":0.99999505},"labels":[],"label_agreement":null},{"id":"W4411152811","doi":"10.22214/ijraset.2025.72039","title":"Exploring Convolutional Neural Network Architectures for Medical Imaging: From Traditional CNNs to Advanced Variants","year":2025,"lang":"en","type":"article","venue":"International Journal for Research in Applied Science and Engineering Technology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Interpretability; Convolutional neural network; Computer science; Artificial intelligence; Deep learning; Medical imaging; Field (mathematics); Segmentation; Machine learning; Feature extraction; Feature (linguistics); Adaptability; Pattern recognition (psychology)","score_opus":0.07005047818288103,"score_gpt":0.3950385245944598,"score_spread":0.3249880464115788,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411152811","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.73931366,0.00026859198,0.16265552,0.09453671,0.0021535025,0.000643989,0.00001788026,0.000084573716,0.00032556636],"genre_scores_gemma":[0.96492,0.000044058623,0.033519145,0.000645134,0.0005510767,0.0002884542,0.0000075308762,0.0000112435855,0.000013371389],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99790657,0.000008669219,0.0002820234,0.000327015,0.00093733094,0.0005383804],"domain_scores_gemma":[0.9986704,0.0005931722,0.0000280239,0.00009995193,0.0003690615,0.00023937979],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024146652,0.00009907437,0.00017567388,0.001568032,0.00025156324,0.00009060703,0.0005786652,0.000057483318,0.00000930238],"category_scores_gemma":[0.0033941506,0.00009051279,0.000036461246,0.0007852185,0.0003844149,0.00006088546,0.00017628381,0.00089978625,7.5786267e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009264779,0.00015304808,0.004285181,0.000056922883,0.00013044631,0.00014797277,0.00018570562,0.047617313,0.06906931,0.2537767,0.0021662503,0.62148464],"study_design_scores_gemma":[0.0032334696,0.00012718886,0.018674484,0.00061911304,0.000009730362,0.00035536702,0.00017792963,0.8562239,0.0009487402,0.092787355,0.026671464,0.00017129073],"about_ca_topic_score_codex":0.000008895508,"about_ca_topic_score_gemma":0.000002102106,"teacher_disagreement_score":0.80860656,"about_ca_system_score_codex":0.00028230966,"about_ca_system_score_gemma":0.00046755173,"threshold_uncertainty_score":0.40633604},"labels":[],"label_agreement":null},{"id":"W4411180354","doi":"10.1148/radiol.243450","title":"Diagnostic Performance of CT/MRI LI-RADS Version 2018 Major Feature Combinations: Individual Participant Data Meta-Analysis","year":2025,"lang":"en","type":"review","venue":"Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier de l’Université de Montréal; McGill University; Queen Elizabeth II Health Sciences Centre; Ottawa Hospital; Juravinski Hospital; Dalhousie University; Hamilton Health Sciences; University of Ottawa","funders":"Canadian Institutes of Health Research; National Natural Science Foundation of China; Fonds de Recherche du Québec - Santé; Mach-Gaensslen Foundation of Canada; RSNA Research and Education Foundation","keywords":"Medicine; Feature (linguistics); BI-RADS; Radiology; Nuclear medicine; Meta-analysis; Medical physics; Pathology; Internal medicine","score_opus":0.12819828791898583,"score_gpt":0.40065708024162666,"score_spread":0.2724587923226408,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411180354","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000064975866,0.99580956,0.00020989493,0.0021432275,0.00041345757,0.0006805968,0.00046932936,0.000038348364,0.00017061489],"genre_scores_gemma":[0.001052758,0.9890376,0.0011385166,0.00030013718,0.00017054605,0.00008006185,0.006882324,0.000030886767,0.0013072089],"study_design_codex":"meta_analysis","study_design_gemma":"meta_analysis","domain_scores_codex":[0.99693686,0.000637351,0.00088449696,0.00075676263,0.00036972572,0.0004147826],"domain_scores_gemma":[0.99481773,0.0027063652,0.0006087793,0.0016099304,0.00008352602,0.00017368115],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001490528,0.0004273754,0.005352647,0.00080642337,0.00011450054,0.000017989869,0.0009497452,0.00030803602,0.0003197381],"category_scores_gemma":[0.0036117623,0.0002920041,0.0013284403,0.0011192977,0.00030384326,0.000075263546,0.00048648458,0.0012155809,0.000036753427],"study_design_candidate":"meta_analysis","study_design_consensus":"meta_analysis","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000379242,0.00050077663,0.0010971818,0.039200377,0.5678881,0.00039360454,0.00014463814,0.00019806033,6.328256e-7,0.00059063366,0.14300619,0.24694188],"study_design_scores_gemma":[0.00034317802,0.00012428347,0.00013445003,0.0010017286,0.5085383,0.00018494147,0.0000063122734,0.001883623,2.3256322e-7,0.0000068241407,0.4876294,0.00014671776],"about_ca_topic_score_codex":0.000048554197,"about_ca_topic_score_gemma":0.0000032027422,"teacher_disagreement_score":0.3446232,"about_ca_system_score_codex":0.000049542683,"about_ca_system_score_gemma":0.00050388824,"threshold_uncertainty_score":0.9999532},"labels":[],"label_agreement":null},{"id":"W4411229896","doi":"10.26779/2786-832x.2025.3.62","title":"Artificial intelligence and radiological diagnostics in hepatology","year":2025,"lang":"en","type":"article","venue":"The Ukrainian Journal of Clinical Surgery","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Education and Early Childhood Development","funders":"","keywords":"Hepatology; Radiological weapon; Internal medicine; Medicine; Medical physics; Radiology","score_opus":0.10979054877526143,"score_gpt":0.4282323022317922,"score_spread":0.3184417534565308,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411229896","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9422512,0.0018017901,0.0018359869,0.052539628,0.0011073995,0.00007070463,3.8970478e-7,0.000006615796,0.00038628824],"genre_scores_gemma":[0.9884906,0.0042802873,0.0007415546,0.0059450176,0.0005076892,0.000001046723,5.6470793e-7,0.0000058054516,0.000027446864],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9973378,0.0005450226,0.0016159134,0.00013490966,0.00015687785,0.00020947163],"domain_scores_gemma":[0.98239446,0.016881494,0.00032911112,0.00014683368,0.00007950891,0.00016861132],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0077192737,0.00009513871,0.00083014136,0.00016595057,0.000044767843,0.000015983378,0.00013467704,0.00013483842,0.00004297841],"category_scores_gemma":[0.03845332,0.000054004577,0.00023847495,0.00023152238,0.00063361257,0.000028176555,0.000052572803,0.0013161754,0.0000033554893],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004208575,0.0001592495,0.49054214,0.000019968178,0.000063242886,0.0006253806,0.00024833772,0.000018167766,0.0000074696704,0.0009635497,0.000976898,0.50595474],"study_design_scores_gemma":[0.00067320577,0.00060806755,0.8781245,0.0009989659,0.0002589612,0.0017705377,0.0002984817,0.009555268,0.00004963395,0.024450969,0.08299947,0.00021195735],"about_ca_topic_score_codex":0.000005853492,"about_ca_topic_score_gemma":0.0000021712276,"teacher_disagreement_score":0.5057428,"about_ca_system_score_codex":0.000016379076,"about_ca_system_score_gemma":0.0003055779,"threshold_uncertainty_score":0.9696462},"labels":[],"label_agreement":null},{"id":"W4411233169","doi":"10.2967/jnumed.124.269425","title":"Summary Report of the SNMMI AI Task Force Radiomics Challenge 2024","year":2025,"lang":"en","type":"editorial","venue":"Journal of Nuclear Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Alberta Innovates - Technology Futures; Society of Nuclear Medicine and Molecular Imaging","keywords":"Radiomics; Ground truth; Artificial intelligence; Machine learning; Binary classification; Outcome (game theory); Computer science; Progression-free survival; Task force; Medicine; Medical physics; Overall survival; Surgery; Support vector machine; Mathematics","score_opus":0.00738005628215292,"score_gpt":0.29839556345731644,"score_spread":0.2910155071751635,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411233169","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00036005356,0.008335035,0.00015791201,0.110085316,0.8605385,0.0003723462,0.000021098276,0.000025807718,0.020103952],"genre_scores_gemma":[0.0017101879,0.013148866,0.000777487,0.0049385084,0.95163924,0.0000020475004,0.00006224453,0.00017788114,0.027543537],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99455935,0.00017968677,0.002098585,0.0003555866,0.0024320649,0.00037475227],"domain_scores_gemma":[0.99432635,0.00088803534,0.00239811,0.00089325086,0.0011390368,0.00035523297],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0029296055,0.00042604937,0.0020132442,0.00053998653,0.00011553105,0.000018669718,0.0008191146,0.0007484061,0.00028412935],"category_scores_gemma":[0.013605748,0.00024953324,0.00068364467,0.00044415615,0.0006127613,0.000089506415,0.00022606258,0.005733804,0.000003535331],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037410588,0.00013684326,0.00006129554,0.0010457234,0.0006586878,0.0018781,0.00039126477,0.00001016437,0.00055972993,0.00008423969,0.9909726,0.0038272452],"study_design_scores_gemma":[0.0032574022,0.0009270561,0.0001042042,0.010191028,0.00172857,0.0016063325,0.00019565636,0.00041022393,0.000008167536,0.00029874657,0.98110104,0.00017156856],"about_ca_topic_score_codex":0.00006417805,"about_ca_topic_score_gemma":0.0000020215512,"teacher_disagreement_score":0.10514681,"about_ca_system_score_codex":0.00030539403,"about_ca_system_score_gemma":0.0014669641,"threshold_uncertainty_score":0.9999957},"labels":[],"label_agreement":null},{"id":"W4411410290","doi":"10.2967/jnumed.125.270429","title":"Summary: Appropriate Use Criteria for<sup>18</sup>F-FDG PET/CT for Initial Staging of Malignant Disease","year":2025,"lang":"en","type":"article","venue":"Journal of Nuclear Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Nuclear medicine; Medicine; Malignant disease; Medical physics; Radiology; Internal medicine; Cancer","score_opus":0.03233972709678557,"score_gpt":0.35854494240170587,"score_spread":0.3262052153049203,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411410290","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9179512,0.0011778278,0.016736625,0.060214084,0.0016329765,0.0012233082,0.00006234614,0.000054133325,0.00094744965],"genre_scores_gemma":[0.9771007,0.00039999228,0.014447869,0.005674798,0.0015226222,0.000008961476,0.000033436823,0.00008264445,0.0007289979],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99772054,0.00009226207,0.0010844676,0.00023955932,0.0005016336,0.00036156763],"domain_scores_gemma":[0.9977119,0.00053215557,0.00047438912,0.0002942033,0.0005510214,0.0004363136],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001594676,0.00023086865,0.00094751385,0.00048582745,0.00011920236,0.00003203156,0.00024285867,0.000024969093,0.00019604701],"category_scores_gemma":[0.0047779307,0.00016423056,0.000328966,0.00021918725,0.00028000836,0.0001890633,0.0000630095,0.0004864486,9.939429e-7],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.03103415,0.00209364,0.020710059,0.011982186,0.003312757,0.0074438476,0.0033952366,0.0014868451,0.05506837,0.012367251,0.7400289,0.11107676],"study_design_scores_gemma":[0.0354915,0.0046176175,0.015331446,0.01760944,0.0045060306,0.001713692,0.0029294235,0.29500133,0.0003909168,0.0048948172,0.6169168,0.0005970057],"about_ca_topic_score_codex":0.000037475882,"about_ca_topic_score_gemma":3.2836658e-7,"teacher_disagreement_score":0.2935145,"about_ca_system_score_codex":0.000091361035,"about_ca_system_score_gemma":0.00028738624,"threshold_uncertainty_score":0.6697128},"labels":[],"label_agreement":null},{"id":"W4411438887","doi":"10.1016/j.media.2025.103677","title":"When evidence modeling meets knowledge distillation: Towards reliable contrast-enhanced knowledge distillation for non-contrast medical image segmentation","year":2025,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Contrast (vision); Computer science; Artificial intelligence; Segmentation; Domain knowledge; Distillation; Pattern recognition (psychology); Machine learning; Chemistry","score_opus":0.01639260718222609,"score_gpt":0.3587668278257788,"score_spread":0.3423742206435527,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411438887","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033174638,0.002083712,0.93664575,0.019716758,0.000544236,0.00090268714,0.000017308661,0.00018919232,0.006725741],"genre_scores_gemma":[0.973042,0.00075171894,0.021139838,0.001012804,0.0008788126,0.00022163808,0.0005186143,0.000056978777,0.0023775648],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.994985,0.00022896592,0.0014571279,0.0010549477,0.0015190282,0.0007549167],"domain_scores_gemma":[0.99590886,0.0011526587,0.00027807878,0.00062349654,0.0010700705,0.0009668249],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0033219447,0.0004784961,0.0014077971,0.00072585465,0.0004182745,0.00018986095,0.00047748364,0.00043089906,0.001721797],"category_scores_gemma":[0.0148239825,0.00040579846,0.0007114957,0.0016591403,0.00045169587,0.0004659164,0.0001916424,0.0008767067,0.0000589292],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001901326,0.002494466,0.014235769,0.004206694,0.009947924,0.0003354471,0.005038734,0.0028517873,0.04057855,0.0011920705,0.05218917,0.8650281],"study_design_scores_gemma":[0.003506735,0.0001091171,0.0026561676,0.0015335821,0.004052091,0.000012891592,0.00021032633,0.9831524,0.0016313578,0.00041838895,0.0023536603,0.00036329543],"about_ca_topic_score_codex":0.00032512122,"about_ca_topic_score_gemma":0.0002005922,"teacher_disagreement_score":0.9803006,"about_ca_system_score_codex":0.00040466175,"about_ca_system_score_gemma":0.0012057486,"threshold_uncertainty_score":0.99983937},"labels":[],"label_agreement":null},{"id":"W4411535114","doi":"10.1007/s10462-025-11268-w","title":"Comprehensive review of reinforcement learning for medical ultrasound imaging","year":2025,"lang":"en","type":"article","venue":"Artificial Intelligence Review","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; École de Technologie Supérieure; Concordia University","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; Khalifa University of Science, Technology and Research; Concordia University","keywords":"Computer science; Reinforcement learning; Software portability; Artificial intelligence; Process (computing); Field (mathematics); Modalities; Data science; Human–computer interaction; Risk analysis (engineering); Machine learning","score_opus":0.03399191280276161,"score_gpt":0.39362435900706383,"score_spread":0.35963244620430224,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411535114","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00013509036,0.72843134,0.2363795,0.029172529,0.0003428659,0.0016104428,9.1486623e-7,0.00006020336,0.0038671214],"genre_scores_gemma":[0.026977256,0.93712413,0.0018905948,0.033388916,0.00012198248,0.00010220168,0.000061007606,0.000020833433,0.00031304485],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975551,0.00011768458,0.0012271027,0.0003107154,0.00048582756,0.0003035729],"domain_scores_gemma":[0.99797624,0.00082805986,0.00025870773,0.00031575185,0.00045098332,0.00017028062],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0016463763,0.00018689658,0.00086706853,0.00009895778,0.000106848085,0.000012504584,0.00022265142,0.000050340474,0.0008202167],"category_scores_gemma":[0.009283472,0.00015266406,0.0003336059,0.00048674096,0.00021372034,0.000050715116,0.00006532903,0.00046621056,0.000032962933],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025790787,0.00007241333,0.00030847496,0.12230997,0.00009342284,0.000012882858,0.000028318602,0.00005475449,0.0005088004,0.011607666,0.0077210222,0.8572565],"study_design_scores_gemma":[0.00012220473,0.000131388,0.00005567754,0.3269839,0.00063369516,0.00009754848,0.00008829,0.019550575,0.002174751,0.0018170379,0.6481221,0.00022288853],"about_ca_topic_score_codex":0.000031316747,"about_ca_topic_score_gemma":5.816974e-7,"teacher_disagreement_score":0.8570336,"about_ca_system_score_codex":0.00005594327,"about_ca_system_score_gemma":0.0003016512,"threshold_uncertainty_score":0.99906176},"labels":[],"label_agreement":null},{"id":"W4411617570","doi":"10.51847/0j8wyfs","title":"10.51847/0j8WYfs","year":2000,"lang":"en","type":"article","venue":"Time to knit","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Deanship of Scientific Research, Prince Sattam bin Abdulaziz University; Prince Sattam bin Abdulaziz University","keywords":"Hormone; Buccal mucosa; Medicine; Physiology; Buccal administration; Endocrine system; Internal medicine; Pharmacology; Dentistry; Oral cavity","score_opus":0.005202180218335363,"score_gpt":0.22455113973336635,"score_spread":0.219348959515031,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411617570","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007817733,0.00006747699,0.000006425907,0.00429681,0.0000037862999,0.0001348468,0.0000013964914,0.00013085174,0.98754066],"genre_scores_gemma":[0.0012768179,9.880257e-7,0.0007886975,0.0010315024,0.00025697445,0.0000066967655,0.000014061172,0.000024845309,0.99659944],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992656,0.000019826415,0.00013438133,0.00017437257,0.0001853466,0.00022044094],"domain_scores_gemma":[0.9994399,0.000033947203,0.000014270121,0.00022030539,0.000024102106,0.00026748877],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00016549781,0.00009337499,0.00017753783,0.00006136231,0.000048752456,0.00001814952,0.000086116925,0.000039946768,0.9900022],"category_scores_gemma":[0.0001271516,0.00007999685,0.000055240922,0.00013998261,0.000035090332,0.00002905718,0.000017866845,0.00019279572,0.9540797],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000072744144,0.00003966351,0.0000044311228,0.000008540663,0.000016341464,0.000036986894,0.000014502363,0.00003845869,0.00026524684,0.0000015544359,0.060255572,0.93924594],"study_design_scores_gemma":[0.00047907908,0.0001561617,0.00036394224,0.000043255084,0.000030681298,0.00007563329,5.165448e-7,0.0029603832,0.000018043414,0.0000023619987,0.99577856,0.00009137564],"about_ca_topic_score_codex":0.000018943663,"about_ca_topic_score_gemma":1.1338693e-8,"teacher_disagreement_score":0.93915457,"about_ca_system_score_codex":0.000026398338,"about_ca_system_score_gemma":0.000031038824,"threshold_uncertainty_score":0.32621768},"labels":[],"label_agreement":null},{"id":"W4411628428","doi":"10.1016/j.esmoop.2025.105273","title":"146P Malignant bowel obstruction (MBO) symptom monitoring through artificial intelligence (AI) based automated calls in gynecologic cancers","year":2025,"lang":"en","type":"article","venue":"ESMO Open","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Medicine; Bowel obstruction; Internal medicine; Pathology; Radiology","score_opus":0.029995895288466013,"score_gpt":0.37430060265291226,"score_spread":0.34430470736444624,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411628428","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95797914,0.00015246627,0.014887515,0.012143894,0.003150603,0.0013156389,0.0000045461297,0.00037955356,0.009986641],"genre_scores_gemma":[0.9901682,0.000051407944,0.007305231,0.0017747995,0.00013048483,0.000085422274,0.000021240414,0.000020283225,0.00044290908],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983907,0.00010687628,0.00047635927,0.00043121044,0.00021470305,0.00038017283],"domain_scores_gemma":[0.9992842,0.00015160003,0.00010054737,0.0003021573,0.00006846266,0.0000930283],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005553143,0.00018413362,0.0003848797,0.00015782085,0.00014531652,0.00012523169,0.00036104288,0.00013878183,0.00019248851],"category_scores_gemma":[0.0006247164,0.00016276022,0.000062078536,0.0005330941,0.00011464794,0.00018305311,0.00015102387,0.0005707089,0.000025766183],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010116573,0.00073774066,0.53946584,0.0006277381,0.00037739583,0.0012193227,0.0024232445,0.1081629,0.014234351,0.012038785,0.007543564,0.31215748],"study_design_scores_gemma":[0.0010855774,0.00017505843,0.3392612,0.0014270261,0.00010623123,0.000020697446,0.00073702954,0.62979734,0.018612165,0.0041670413,0.0042636106,0.00034702258],"about_ca_topic_score_codex":0.010237673,"about_ca_topic_score_gemma":0.00021744471,"teacher_disagreement_score":0.52163446,"about_ca_system_score_codex":0.00061123393,"about_ca_system_score_gemma":0.000582781,"threshold_uncertainty_score":0.99635327},"labels":[],"label_agreement":null},{"id":"W4411655352","doi":"10.3389/fvets.2025.1615947","title":"Commentary: Comparison of radiological interpretation made by veterinary radiologists and state-of-the-art commercial AI software for canine and feline radiographic studies","year":2025,"lang":"en","type":"letter","venue":"Frontiers in Veterinary Science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Guelph","funders":"","keywords":"Radiological weapon; Interpretation (philosophy); Radiography; Veterinary medicine; Medicine; Medical physics; Radiology; Computer science","score_opus":0.02621347478370854,"score_gpt":0.3510894374365018,"score_spread":0.3248759626527932,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411655352","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.66991824,0.014747179,0.02557516,0.28552613,0.0026165862,0.0013482717,0.0002220513,0.000035081895,0.00001130386],"genre_scores_gemma":[0.6523398,0.003553579,0.07332429,0.26934528,0.000403516,0.00013541341,0.00050961325,0.00005386596,0.00033463206],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977131,0.00025572325,0.00069662434,0.00058781065,0.00034524238,0.00040152093],"domain_scores_gemma":[0.9986446,0.00045364958,0.000357987,0.0003235234,0.0001401705,0.00008008226],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.00095637963,0.0003135187,0.0012117939,0.0005714326,0.00018269122,0.000022743114,0.00045014202,0.00019486003,0.0000013049564],"category_scores_gemma":[0.000847147,0.00023554522,0.00010964656,0.00064627884,0.004153448,0.000115697,0.00037515548,0.0011908321,3.2736796e-8],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005831381,0.00006577347,0.08890833,0.0013205163,0.00012558182,0.00004807332,0.000733101,0.0000353854,0.0016353645,0.0000013429321,0.8798878,0.026655594],"study_design_scores_gemma":[0.00895975,0.022420952,0.13671255,0.007856848,0.0008704437,0.0010434361,0.0010669823,0.10123677,0.00030973373,0.0011869301,0.7168238,0.001511807],"about_ca_topic_score_codex":0.000044514993,"about_ca_topic_score_gemma":8.214326e-7,"teacher_disagreement_score":0.163064,"about_ca_system_score_codex":0.00014578777,"about_ca_system_score_gemma":0.00014147678,"threshold_uncertainty_score":0.9985567},"labels":[],"label_agreement":null},{"id":"W4411660132","doi":"10.51847/h24nbtt4r2","title":"10.51847/H24nBtT4R2","year":2000,"lang":"en","type":"article","venue":"Time to knit","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Breast cancer; Medicine; Cancer; Radiology; Oncology; Internal medicine","score_opus":0.005227906670962044,"score_gpt":0.22480312163100544,"score_spread":0.2195752149600434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411660132","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0071563213,0.00007613065,0.000006803385,0.0042782594,0.00000406227,0.00014214207,0.0000014936783,0.00013702615,0.98819774],"genre_scores_gemma":[0.0013105696,0.0000010601382,0.0008152753,0.0010469934,0.00026449966,0.0000071182776,0.000015533025,0.000025801379,0.9965131],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99924093,0.000020374626,0.00013999103,0.00018293125,0.00018667085,0.00022910838],"domain_scores_gemma":[0.999423,0.000034452907,0.000014583443,0.00022651305,0.000025695499,0.00027571025],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00016947227,0.00009808357,0.00018380584,0.0000626944,0.000051206436,0.000019184941,0.000088109846,0.000041857507,0.9905328],"category_scores_gemma":[0.00012952833,0.000083688385,0.000057957262,0.00014648888,0.000036432455,0.00003066096,0.000018866243,0.00020172868,0.9532721],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000718163,0.000041185627,0.0000041328026,0.000008680431,0.0000160141,0.000037128524,0.000014351129,0.000041386895,0.0002506671,0.0000014884231,0.062479395,0.9370338],"study_design_scores_gemma":[0.00048180626,0.00015999482,0.00032028966,0.000045755267,0.00003129453,0.000081317194,5.514474e-7,0.0029019471,0.000018378672,0.000002428399,0.99586004,0.000096212774],"about_ca_topic_score_codex":0.00001917682,"about_ca_topic_score_gemma":1.2688999e-8,"teacher_disagreement_score":0.9369375,"about_ca_system_score_codex":0.000026954052,"about_ca_system_score_gemma":0.000030893047,"threshold_uncertainty_score":0.3412713},"labels":[],"label_agreement":null},{"id":"W4411667236","doi":"10.59275/j.melba.2025-9bd3","title":"The Brain Tumor Segmentation (BraTS-METS) Challenge 2023: Brain Metastasis Segmentation on Pre-treatment MRI","year":2025,"lang":"en","type":"article","venue":"The Journal of Machine Learning for Biomedical Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; Hospital for Sick Children; SickKids Foundation; Montreal Neurological Institute and Hospital; University of Toronto; Windsor Regional Hospital; University of Calgary; McGill University; Centre Hospitalier de l’Université de Montréal; Queen's University","funders":"National Cancer Institute; National Institutes of Health; Children's Hospital of Philadelphia; Yale University","keywords":"Segmentation; Brain metastasis; Medicine; Magnetic resonance imaging; Internal medicine; Metastasis; Artificial intelligence; Computer science; Radiology; Cancer","score_opus":0.010862005629949899,"score_gpt":0.32969527209675975,"score_spread":0.3188332664668099,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411667236","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10182033,0.008060335,0.20878668,0.67633575,0.0018674578,0.0017855996,0.000021305828,0.00012450517,0.0011980138],"genre_scores_gemma":[0.9454589,0.0033750958,0.01621143,0.021537773,0.002016695,0.00013180755,0.00025153355,0.00017717638,0.010839613],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9967125,0.0007504969,0.00093252934,0.00027297554,0.0008326257,0.0004988455],"domain_scores_gemma":[0.994681,0.0038644471,0.0007083669,0.00029756277,0.00020007369,0.0002485419],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0050252085,0.00032728215,0.0005338574,0.0003986081,0.0009096945,0.00013415342,0.00037858626,0.00005638964,0.000067894354],"category_scores_gemma":[0.0033661716,0.00017127715,0.00035429187,0.0004588287,0.00038782076,0.00014647488,0.00008172213,0.0011602226,0.000008580247],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0024622446,0.0006734748,0.00271515,0.0002279958,0.0012943939,0.00010375802,0.0019017493,0.0023743138,0.0235697,0.0007959164,0.038307145,0.9255742],"study_design_scores_gemma":[0.016173916,0.0050715315,0.003936211,0.0013963671,0.0020129129,0.0009960756,0.0035922334,0.364539,0.0049083335,0.002256654,0.594613,0.0005037655],"about_ca_topic_score_codex":0.00011758434,"about_ca_topic_score_gemma":0.000008861673,"teacher_disagreement_score":0.9250704,"about_ca_system_score_codex":0.0003730901,"about_ca_system_score_gemma":0.0002591552,"threshold_uncertainty_score":0.6996727},"labels":[],"label_agreement":null},{"id":"W4411696885","doi":"10.59275/j.melba.2025-f6fg","title":"BraTS-PEDs: Results of the Multi-Consortium International Pediatric Brain Tumor Segmentation Challenge 2023","year":2025,"lang":"en","type":"article","venue":"The Journal of Machine Learning for Biomedical Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Montreal Neurological Institute and Hospital","funders":"","keywords":"Medicine","score_opus":0.012051860635160963,"score_gpt":0.3193921706241968,"score_spread":0.30734030998903583,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411696885","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3587144,0.00639838,0.15265097,0.47276273,0.0059644696,0.0012705614,0.00005184696,0.00009504835,0.0020916073],"genre_scores_gemma":[0.98727185,0.00043619025,0.0060687857,0.0028052973,0.0009404466,0.0000067171636,0.000036634352,0.00003628379,0.0023977729],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997333,0.00035122252,0.0011012736,0.00018817189,0.0007314901,0.00029484273],"domain_scores_gemma":[0.99696773,0.0012954456,0.0010237243,0.00023701672,0.00033464597,0.00014145694],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0041352455,0.00019212245,0.0004115013,0.0004232266,0.00025245477,0.000035204062,0.0005926751,0.000055571894,0.000041481584],"category_scores_gemma":[0.008598542,0.000107922475,0.00030836632,0.00050847494,0.00035805858,0.000115062154,0.00017951072,0.0013749142,0.0000023575458],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008990658,0.0034372758,0.28966853,0.0022518924,0.0024654781,0.00025941513,0.009244634,0.006394657,0.085742764,0.0010638696,0.12994,0.46054083],"study_design_scores_gemma":[0.032342575,0.00095464726,0.056540474,0.0018539059,0.0018590846,0.0012552524,0.00225061,0.7034034,0.002189512,0.00090843806,0.1959622,0.00047990718],"about_ca_topic_score_codex":0.00009029241,"about_ca_topic_score_gemma":0.00000358156,"teacher_disagreement_score":0.6970087,"about_ca_system_score_codex":0.000102999045,"about_ca_system_score_gemma":0.0002859637,"threshold_uncertainty_score":0.99975246},"labels":[],"label_agreement":null},{"id":"W4411792853","doi":"10.18280/ts.420332","title":"Real-Time Detection of Colorectal Adenomas Based on an Enhanced YOLOv5 Network","year":2025,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science","score_opus":0.005722445321198061,"score_gpt":0.26192731050011364,"score_spread":0.2562048651789156,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411792853","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9599179,0.000019973524,0.02868509,0.00057432405,0.00018697823,0.00035365342,0.0000023360908,0.000092908376,0.010166849],"genre_scores_gemma":[0.9964125,0.0000072480525,0.0024375254,0.0005754448,0.00022210574,0.000022870157,0.000034996134,0.000015527852,0.000271753],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99887323,0.00009721099,0.00030030246,0.00023966143,0.0002626039,0.00022697578],"domain_scores_gemma":[0.99946547,0.00012947997,0.000093636256,0.00014769404,0.000056706962,0.00010704557],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046113602,0.00013120916,0.00027643007,0.00012815447,0.00008088334,0.000012203277,0.000083134495,0.00006913354,0.000425504],"category_scores_gemma":[0.00006268154,0.00011618464,0.00008637632,0.00023605714,0.00007664332,0.000034789522,0.000013026785,0.00022483204,0.000009858516],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015222115,0.00043057738,0.0021407567,0.00009504246,0.00009236018,0.000017043136,0.00013737821,0.01253682,0.9415575,0.00027216293,0.0007491083,0.04044902],"study_design_scores_gemma":[0.004694994,0.0030989726,0.07953943,0.00049255026,0.00022950424,0.000005777996,0.000048035523,0.7806103,0.12970018,0.00020801311,0.0011641933,0.00020799844],"about_ca_topic_score_codex":0.000042402342,"about_ca_topic_score_gemma":0.0000032516325,"teacher_disagreement_score":0.81185734,"about_ca_system_score_codex":0.00007719308,"about_ca_system_score_gemma":0.000093628994,"threshold_uncertainty_score":0.4737872},"labels":[],"label_agreement":null},{"id":"W4411792970","doi":"10.18280/ts.420319","title":"A CNN-Based Framework for Automatic Segmentation of Chest X-ray Images and Multi-Type Respiratory Disease Recognition","year":2025,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Segmentation; Artificial intelligence; Computer science; Computer vision; Pattern recognition (psychology)","score_opus":0.029142896104542605,"score_gpt":0.3327058017352768,"score_spread":0.3035629056307342,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411792970","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5332241,0.00036484483,0.46334335,0.0020219549,0.00011071459,0.00080973195,0.000019679854,0.00005637959,0.000049233233],"genre_scores_gemma":[0.8794415,0.000009346999,0.11824456,0.0020285544,0.00006674999,0.000077815435,0.000081409635,0.000013035414,0.000037032136],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99921894,0.00005103214,0.00027637713,0.00017757324,0.00015167346,0.00012439572],"domain_scores_gemma":[0.99934494,0.0002683372,0.00009834748,0.00008972318,0.00009400326,0.00010466359],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034112943,0.00010127777,0.00018445023,0.00012983021,0.000058322,0.000017889724,0.000037525188,0.000040948795,0.00012830485],"category_scores_gemma":[0.00049510965,0.00009063509,0.000055126584,0.000121874175,0.00008665324,0.000042805073,0.00000919575,0.00009631063,0.0000015793707],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014650066,0.0017523854,0.06159523,0.0057725604,0.00032510885,0.000027512224,0.00056100514,0.000538865,0.25195912,0.00047779267,0.002585892,0.67293954],"study_design_scores_gemma":[0.014743648,0.0015228378,0.39513275,0.0040978063,0.0013577912,0.000001590182,0.00044400874,0.5460228,0.03155766,0.0029329038,0.0017786553,0.00040753547],"about_ca_topic_score_codex":0.0000046078026,"about_ca_topic_score_gemma":3.1456423e-7,"teacher_disagreement_score":0.67253196,"about_ca_system_score_codex":0.00003379051,"about_ca_system_score_gemma":0.00010081419,"threshold_uncertainty_score":0.36959916},"labels":[],"label_agreement":null},{"id":"W4411832033","doi":"10.3390/medicina61071170","title":"Systematic Review and Meta-Analysis of AI-Assisted Mammography and the Systemic Immune-Inflammation Index in Breast Cancer: Diagnostic and Prognostic Perspectives","year":2025,"lang":"en","type":"review","venue":"Medicina","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Medicine; Breast cancer; Mammography; Oncology; Meta-analysis; Internal medicine; Medical physics; Diagnostic odds ratio; Cancer","score_opus":0.013091188878970136,"score_gpt":0.33138956506799255,"score_spread":0.3182983761890224,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411832033","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000070565504,0.9892901,0.00008097639,0.005495444,0.000037438847,0.0049273316,0.00003807741,0.00002001526,0.000040050378],"genre_scores_gemma":[0.012079106,0.9865691,0.000014162551,0.00027584756,0.00002897059,0.00089876336,0.000037259262,0.000024743185,0.00007203746],"study_design_codex":"systematic_review","study_design_gemma":"meta_analysis","domain_scores_codex":[0.9960869,0.0011127865,0.0016378699,0.00050393475,0.00043785834,0.00022064087],"domain_scores_gemma":[0.99406797,0.0042090584,0.00094574405,0.00048726518,0.00016642595,0.00012354871],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002823873,0.00045293354,0.009819484,0.0010655858,0.00007135101,0.000032973257,0.00016186824,0.00016227027,0.000026567343],"category_scores_gemma":[0.0046057426,0.00022564249,0.0008449321,0.0017761309,0.0005849134,0.000046008678,0.00009699448,0.0008070321,2.441677e-7],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010376749,0.000023155457,0.0008950242,0.9262219,0.059456907,0.000029396193,0.0005062553,7.343888e-7,9.162336e-8,0.00018823105,0.000020198837,0.012647697],"study_design_scores_gemma":[0.0005973803,0.000018554856,0.001978172,0.31726545,0.6788574,0.0004351113,0.0002762328,0.00031738702,8.7244345e-9,0.000010980693,0.00011153295,0.00013182283],"about_ca_topic_score_codex":0.00047513918,"about_ca_topic_score_gemma":0.000022772854,"teacher_disagreement_score":0.61940044,"about_ca_system_score_codex":0.000079355974,"about_ca_system_score_gemma":0.00020565314,"threshold_uncertainty_score":0.92014337},"labels":[],"label_agreement":null},{"id":"W4411866856","doi":"10.1109/trpms.2025.3584031","title":"Classification-Based Deep Learning Models for Lung Cancer and Disease Using Medical Images","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Radiation and Plasma Medical Sciences","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Specific Research Project of Guangxi for Research Bases and Talents; National Natural Science Foundation of China","keywords":"Lung cancer; Deep learning; Artificial intelligence; Disease; Computer science; Medicine; Machine learning; Pathology","score_opus":0.02899418609351816,"score_gpt":0.34803083284896913,"score_spread":0.31903664675545096,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411866856","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.099797666,0.00079902535,0.85724056,0.041297566,0.00034372602,0.00027188988,0.0000092544215,0.0000569834,0.00018333174],"genre_scores_gemma":[0.99331206,0.0010041032,0.0024244464,0.0029150534,0.000077294084,0.000065234926,0.000007469037,0.000008406134,0.0001859206],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984255,0.00007250812,0.00025272148,0.0003576375,0.00066526595,0.00022638065],"domain_scores_gemma":[0.9983502,0.00077150844,0.000059493177,0.00007096705,0.00004332547,0.00070450664],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008710137,0.00012396078,0.00019705342,0.00023784029,0.00064754527,0.00006816925,0.000093077666,0.00011966101,0.00017508536],"category_scores_gemma":[0.00062625005,0.000098463024,0.00005723337,0.00031813895,0.0005566437,0.00012330373,0.0000017074585,0.00040549613,3.4709504e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021191762,0.00020037711,0.012489946,0.00037094715,0.00008306564,0.000014061407,0.00017727981,0.121384114,0.0002287025,0.0022584025,0.0004482121,0.86213297],"study_design_scores_gemma":[0.0014199597,0.00005732802,0.001406991,0.00030165768,0.00012970004,0.0000074603477,0.00006318061,0.9953445,0.00010933992,0.00021131856,0.00085023884,0.00009830456],"about_ca_topic_score_codex":0.00008649267,"about_ca_topic_score_gemma":0.000013909074,"teacher_disagreement_score":0.8935144,"about_ca_system_score_codex":0.000056622343,"about_ca_system_score_gemma":0.0009129248,"threshold_uncertainty_score":0.498046},"labels":[],"label_agreement":null},{"id":"W4411897422","doi":"10.1186/s12880-025-01774-2","title":"Enhancing radiomics robustness using bayesian penalized likelihood PET reconstruction: application to Phantom and non-small cell lung cancer patient studies","year":2025,"lang":"en","type":"article","venue":"BMC Medical Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"University of Tabriz; Tehran University of Medical Sciences and Health Services; Tabriz University of Medical Sciences","keywords":"Radiomics; Imaging phantom; Robustness (evolution); Bayesian probability; Lung cancer; Computer science; Artificial intelligence; Medical physics; Radiology; Medicine; Oncology","score_opus":0.008800969502012123,"score_gpt":0.31396031464978047,"score_spread":0.3051593451477683,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411897422","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5025811,0.003988229,0.4894338,0.0024777302,0.0006729045,0.000523712,0.000001567332,0.0000702903,0.00025066387],"genre_scores_gemma":[0.88046026,0.0012006669,0.11366374,0.0036912002,0.0006234319,0.00016883381,0.000011947305,0.000059360067,0.000120535755],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99743724,0.0001219887,0.00070676947,0.00068241893,0.00050789706,0.000543711],"domain_scores_gemma":[0.99829257,0.00037460294,0.00018855366,0.0003224183,0.00022762018,0.00059421104],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009000715,0.00030751934,0.00067424186,0.00034816778,0.00030782836,0.00007516325,0.00017085436,0.00007836034,0.00006121064],"category_scores_gemma":[0.0010226717,0.00027586197,0.00010466689,0.0005090362,0.00021891546,0.000117404954,0.00022667591,0.0005867669,0.0000017146725],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003511267,0.0002953029,0.40859464,0.0058840318,0.00047279327,0.00026812125,0.0030962864,0.0027430546,0.047196932,0.000106449654,0.0020758272,0.5289154],"study_design_scores_gemma":[0.0030859113,0.000027645412,0.0021489202,0.004407212,0.0005068254,0.0005642944,0.0024343745,0.9816036,0.0042529977,0.00007179467,0.00053492043,0.0003614863],"about_ca_topic_score_codex":0.00028897435,"about_ca_topic_score_gemma":0.00009699574,"teacher_disagreement_score":0.97886056,"about_ca_system_score_codex":0.0003480843,"about_ca_system_score_gemma":0.00089388806,"threshold_uncertainty_score":0.99996936},"labels":[],"label_agreement":null},{"id":"W4411948899","doi":"10.1109/tmi.2025.3584641","title":"In Vivo Laparoscopic Image De-Smoking Dataset, Evaluation, and Beyond","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Medical Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; Robarts Clinical Trials; Western University","funders":"","keywords":"Computer vision; Image (mathematics); Artificial intelligence; Computer science","score_opus":0.009056886740524706,"score_gpt":0.33933447465443317,"score_spread":0.3302775879139085,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411948899","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13762419,0.0009427347,0.78001666,0.07106348,0.0015245117,0.0007073245,0.00005340101,0.0001425975,0.007925076],"genre_scores_gemma":[0.975027,0.00030153443,0.003061586,0.020975856,0.00010453969,0.00006835913,0.000023340071,0.000027163333,0.0004106144],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980784,0.00014810769,0.00036597275,0.00038686112,0.00065888755,0.00036178465],"domain_scores_gemma":[0.9990493,0.00028617104,0.00004054107,0.00026882414,0.0000622556,0.0002929166],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0016339174,0.00016894106,0.00030255617,0.00041743284,0.00016233377,0.00005422568,0.0001288032,0.000091531605,0.0011475476],"category_scores_gemma":[0.0004246922,0.00015895846,0.00005052358,0.0003894282,0.00028176798,0.0001884465,0.0000048517963,0.0010323251,0.0000072495163],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029081374,0.0012722048,0.017507125,0.00076036033,0.00030166394,0.0011462681,0.0013737747,0.00089560676,0.02670231,0.0005269649,0.079798386,0.8694245],"study_design_scores_gemma":[0.011256586,0.00007194879,0.003313886,0.0017308246,0.0006050102,0.0004922284,0.0005644564,0.93505764,0.015164167,0.0019068011,0.02941926,0.0004171814],"about_ca_topic_score_codex":0.00018168127,"about_ca_topic_score_gemma":0.000025107453,"teacher_disagreement_score":0.934162,"about_ca_system_score_codex":0.00018607195,"about_ca_system_score_gemma":0.00041691982,"threshold_uncertainty_score":0.9997655},"labels":[],"label_agreement":null},{"id":"W4411981242","doi":"10.1007/s10278-025-01585-5","title":"Radiological and Biological Dictionary of Radiomics Features: Addressing Understandable AI Issues in Personalized Prostate Cancer, Dictionary Version PM1.0","year":2025,"lang":"en","type":"article","venue":"Journal of Imaging Informatics in Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; BC Cancer Agency","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Radiomics; Radiological weapon; Prostate cancer; Medical physics; Medicine; Artificial intelligence; Computer science; Cancer; Radiology; Internal medicine","score_opus":0.019210006362488232,"score_gpt":0.35140710500061645,"score_spread":0.33219709863812824,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411981242","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9015546,0.041101918,0.005548984,0.048346963,0.0009698677,0.00041253964,0.000008536444,0.000029441459,0.0020271596],"genre_scores_gemma":[0.95644873,0.030425275,0.008508807,0.004136102,0.00025087546,0.0000050863255,0.000023965264,0.0000141476,0.00018701018],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9978215,0.00011390401,0.0012500101,0.00011948626,0.00043574645,0.0002593366],"domain_scores_gemma":[0.99865246,0.00040636977,0.0004928943,0.000118955475,0.00020088551,0.00012845913],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018981587,0.00018694074,0.0008503151,0.00090285414,0.00008089821,0.000017835628,0.00014389449,0.00011334704,0.00004415569],"category_scores_gemma":[0.0013678651,0.00012428849,0.000079758334,0.0005065978,0.000809431,0.0002816337,0.00006941305,0.0012272345,2.0835421e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0029100296,0.0003290777,0.89286816,0.0014459295,0.00023379606,0.00041892086,0.014233296,0.002485637,0.0029155111,0.0013535667,0.031068848,0.049737215],"study_design_scores_gemma":[0.051102273,0.001946507,0.5149804,0.039981358,0.00061163906,0.0054555465,0.059470475,0.26533803,0.00033307503,0.010426962,0.04963884,0.00071493495],"about_ca_topic_score_codex":0.000082912986,"about_ca_topic_score_gemma":0.0000014220234,"teacher_disagreement_score":0.37788782,"about_ca_system_score_codex":0.0003221201,"about_ca_system_score_gemma":0.00027040424,"threshold_uncertainty_score":0.5331791},"labels":[],"label_agreement":null},{"id":"W4412049133","doi":"10.1016/j.inffus.2025.103457","title":"Anatomic-kinetic fusion network for pituitary gland and microadenoma segmentation in multi-phase DCE-MRI","year":2025,"lang":"en","type":"article","venue":"Information Fusion","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Montreal Neurological Institute and Hospital","funders":"Natural Science Foundation of Heilongjiang Province; China Postdoctoral Science Foundation; National Natural Science Foundation of China; State Key Laboratory of Cognitive Neuroscience and Learning; Key Research and Development Program of Heilongjiang","keywords":"Computer science; Fusion; Segmentation; Phase (matter); Artificial intelligence; Pituitary gland; Computer vision; Medicine; Physics; Internal medicine","score_opus":0.00840593356605223,"score_gpt":0.3124453798184991,"score_spread":0.3040394462524469,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412049133","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87681645,0.00044343196,0.11798635,0.0024259198,0.00033729294,0.0011987244,0.000008725219,0.000051062176,0.00073205447],"genre_scores_gemma":[0.94299453,0.0006218303,0.050526537,0.0044193976,0.00012340573,0.00011108276,0.0008716849,0.000013593716,0.0003179445],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991453,0.000024880566,0.00041046078,0.000118918586,0.000118101816,0.00018231935],"domain_scores_gemma":[0.9995806,0.00007543013,0.000104164516,0.00010766993,0.000061855084,0.000070275535],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036828665,0.000110305744,0.00018186025,0.0002719775,0.00012403863,0.0000430818,0.000046964087,0.000086402004,0.000022660864],"category_scores_gemma":[0.00013508211,0.00009804302,0.00003551552,0.00022242023,0.000034381792,0.00027490547,0.000047636593,0.00017785665,0.0000061304413],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010691409,0.00022062972,0.053481154,0.0007674521,0.00003813481,0.0000099103845,0.002350726,0.0025414212,0.01152002,0.0005727598,0.012717792,0.9147109],"study_design_scores_gemma":[0.019495869,0.00026826974,0.08716842,0.00069637824,0.00007520178,0.000036808164,0.00052932807,0.8189706,0.0008520613,0.00035395456,0.071354926,0.00019819508],"about_ca_topic_score_codex":0.00009058166,"about_ca_topic_score_gemma":0.0000148221625,"teacher_disagreement_score":0.91451263,"about_ca_system_score_codex":0.000073027055,"about_ca_system_score_gemma":0.000053017277,"threshold_uncertainty_score":0.39980784},"labels":[],"label_agreement":null},{"id":"W4412052746","doi":"10.1101/2025.07.03.25330835","title":"Explainable machine learning for post PKR surgery follow-up","year":2025,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Artificial intelligence; Medicine; Computer science; Machine learning","score_opus":0.02264938115557901,"score_gpt":0.29826204171731785,"score_spread":0.27561266056173883,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412052746","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90356624,0.006677867,0.037085835,0.027364446,0.011399996,0.0025326572,0.00012596707,0.00094017934,0.010306823],"genre_scores_gemma":[0.87106234,0.0013424975,0.0077852397,0.004354386,0.0017576513,0.00056932506,0.0023760078,0.00021458183,0.11053796],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99707866,0.00017151814,0.00071376556,0.00087528967,0.00046241487,0.00069835194],"domain_scores_gemma":[0.99724233,0.001058821,0.00032177477,0.0006992362,0.0003489157,0.00032892014],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0019834447,0.0004940057,0.0012825584,0.0005412212,0.00028375912,0.000094446856,0.00032963598,0.00041379922,0.00022125279],"category_scores_gemma":[0.0074386355,0.00044605153,0.0007943728,0.00023482041,0.00010519271,0.000051093248,0.0005138637,0.0024136766,0.000024989931],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015594822,0.0004786791,0.8178507,0.013333081,0.0015887059,0.0006556712,0.0013589902,0.0021003338,0.0028878436,0.001054477,0.05463069,0.10250135],"study_design_scores_gemma":[0.004294185,0.0002829197,0.022102205,0.00470339,0.0012629697,0.0001368274,0.00020966874,0.15616564,0.0012566556,0.0014299145,0.80689585,0.0012597744],"about_ca_topic_score_codex":0.0004095283,"about_ca_topic_score_gemma":0.0000125122715,"teacher_disagreement_score":0.7957485,"about_ca_system_score_codex":0.00015154935,"about_ca_system_score_gemma":0.0007053623,"threshold_uncertainty_score":0.9998878},"labels":[],"label_agreement":null},{"id":"W4412078570","doi":"10.1038/s41467-025-60466-1","title":"Towards fair decentralized benchmarking of healthcare AI algorithms with the Federated Tumor Segmentation (FeTS) challenge","year":2025,"lang":"en","type":"article","venue":"Nature Communications","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; McGill University Health Centre; Centre Hospitalier Universitaire de Sherbrooke; Queen's University; Université de Sherbrooke; Alberta Children's Hospital; Hotchkiss Brain Institute; University of Alberta; University of Calgary; Artificial Intelligence in Medicine (Canada)","funders":"National Center for Advancing Translational Sciences; National Institute of Biomedical Imaging and Bioengineering; National Institute of General Medical Sciences; National Cancer Institute; Canadian Institutes of Health Research; Anschutz Medical Campus, University of Colorado; Sidney Kimmel Comprehensive Cancer Center; Faculty of Medicine and Health, University of Sydney; Université de Sherbrooke; School of Electronic Engineering and Computer Science, Queen Mary University of London; National Institutes of Health; Agencia Nacional de Investigación y Desarrollo; Universitätsklinikum Heidelberg; Universitätsspital Zürich; Canadian Institute for Advanced Research; Inselspital, Universitätsspital Bern; Universität Zürich; China Scholarship Council; Universidad de Concepción; McGill University; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Queen's University; Islamic Azad University; Deutsche Forschungsgemeinschaft; School of Medicine, Indiana University; University of Bern; Universidad Carlos III de Madrid; Ministerstvo Zdravotnictví Ceské Republiky; Business Finland; Frederick National Laboratory for Cancer Research; Cancer Research UK; Varian Medical Systems; Wellcome Trust; Universidad Católica de Cuenca; Deutsches Krebsforschungszentrum; Thomas Jefferson University; Leidos; U.S. Department of Veterans Affairs; University of Pennsylvania; Escuela Superior Politécnica del Litoral; Kepler Universitätsklinikum; Queen Mary University of London; University of Patras; Ohio State University; Higher Education Commision, Pakistan; University of Toronto; Faculty of Arts and Sciences; Silesian University of Technology; Université du Luxembourg; National Science Foundation","keywords":"Benchmarking; Benchmark (surveying); Computer science; Segmentation; Artificial intelligence; Generalization; Machine learning; Algorithm; Federated learning; Data mining","score_opus":0.014400396655500301,"score_gpt":0.3546559547238374,"score_spread":0.34025555806833707,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412078570","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02897576,0.027004842,0.014522942,0.9189144,0.00033615687,0.0013798656,0.000021218148,0.00015993304,0.008684909],"genre_scores_gemma":[0.97103435,0.0015047303,0.019764649,0.0073147197,0.000035035682,0.000041486303,0.00018475224,0.00001399719,0.00010626168],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989909,0.00019592878,0.0002461171,0.00015749647,0.00024189038,0.00016768041],"domain_scores_gemma":[0.9984973,0.00020612584,0.00013118157,0.0007724107,0.00032582614,0.000067136956],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037121875,0.00011688287,0.00023368317,0.00010102335,0.00035875046,0.000031308486,0.00039066092,0.00010740612,0.000018579072],"category_scores_gemma":[0.00017514602,0.00007568293,0.000059492795,0.00047282822,0.00019646731,0.000051624796,0.00012256994,0.001451577,0.0000010495663],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00071865023,0.0016856057,0.037646234,0.0011055231,0.0015519088,0.000035518937,0.008224766,0.00023100659,0.006008353,0.13924487,0.040384814,0.76316273],"study_design_scores_gemma":[0.013845888,0.0010342398,0.15943794,0.0039992244,0.0013578498,0.0001969114,0.0087029915,0.28501704,0.004603285,0.0019220315,0.5190084,0.0008741769],"about_ca_topic_score_codex":0.00028635035,"about_ca_topic_score_gemma":0.0003466277,"teacher_disagreement_score":0.9420586,"about_ca_system_score_codex":0.000093657065,"about_ca_system_score_gemma":0.00030946668,"threshold_uncertainty_score":0.63064605},"labels":[],"label_agreement":null},{"id":"W4412081617","doi":"10.1007/s00345-025-05735-w","title":"Author Correction: Current era HOLEP with MOSES 2.0 technology compared to the gold standard TURP","year":2025,"lang":"en","type":"erratum","venue":"World Journal of Urology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Boston Scientific Corporation","keywords":"Medicine; Nephrology; Gold standard (test); Current (fluid); Urology; Medical physics; General surgery; Internal medicine; Electrical engineering; Engineering","score_opus":0.010016342672935665,"score_gpt":0.3057710196459611,"score_spread":0.29575467697302543,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412081617","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010156402,0.05220221,0.01998782,0.72780025,0.16828242,0.00096609385,0.000032570464,0.00015587988,0.029557116],"genre_scores_gemma":[0.08178323,0.0046895593,0.0062397877,0.022843087,0.019161087,0.00007198839,0.00013181298,0.00022561522,0.86485386],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975904,0.00019379448,0.00080246956,0.0003481406,0.00059996586,0.0004652135],"domain_scores_gemma":[0.9976531,0.00024385046,0.0007407799,0.0004852697,0.000611414,0.0002655828],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0008046338,0.0003635709,0.0012912559,0.0015381123,0.00014933162,0.000047412752,0.00058304373,0.0002816417,0.00015411375],"category_scores_gemma":[0.00096145313,0.00021468988,0.00022069465,0.0011244565,0.00037399976,0.000033345386,0.00014793138,0.008555777,0.000012960762],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009937607,0.00007729247,0.0010682213,0.0000747627,0.0003361527,0.0003624896,0.00010898139,0.00051200396,0.0000079026,0.0001852721,0.89042115,0.105852],"study_design_scores_gemma":[0.0013340566,0.0013376168,0.0011885883,0.00097591383,0.0007678076,0.002514035,0.00006938362,0.00092976657,0.000004194257,0.00017661494,0.9905247,0.00017728943],"about_ca_topic_score_codex":0.00001372274,"about_ca_topic_score_gemma":0.000118580014,"teacher_disagreement_score":0.83529675,"about_ca_system_score_codex":0.00019968553,"about_ca_system_score_gemma":0.0014002797,"threshold_uncertainty_score":0.9937315},"labels":[],"label_agreement":null},{"id":"W4412110787","doi":"10.1148/radiol.242278","title":"Impact of LI-RADS CT and MRI Ancillary Features on Diagnostic Performance: An Individual Participant Data Meta-Analysis","year":2025,"lang":"en","type":"review","venue":"Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen Elizabeth II Health Sciences Centre; Centre Hospitalier de l’Université de Montréal; Queen's University; McMaster University; Juravinski Hospital; Juravinski Cancer Centre; Hamilton Health Sciences; University of Toronto; Jewish General Hospital; University of Ottawa; Ottawa Hospital","funders":"Ministry of Health and Welfare; National Natural Science Foundation of China","keywords":"Medicine; Meta-analysis; Radiology; Medical physics; Nuclear medicine; Pathology","score_opus":0.17341396891994745,"score_gpt":0.4517579780726283,"score_spread":0.27834400915268087,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412110787","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023553227,0.9962201,0.00003435345,0.00017827826,0.0001274476,0.00050432404,0.00043194395,0.0000303551,0.0001178836],"genre_scores_gemma":[0.012748663,0.9832707,0.00032600597,0.00021936615,0.0002179556,0.000047479374,0.0030177901,0.000033454624,0.000118576645],"study_design_codex":"design_other","study_design_gemma":"meta_analysis","domain_scores_codex":[0.9969293,0.0007098235,0.0007886612,0.0008269257,0.00029181773,0.0004534664],"domain_scores_gemma":[0.99552494,0.0021668975,0.00042822032,0.0015440423,0.000044335655,0.000291548],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0015248355,0.00049617863,0.0059803934,0.0007278473,0.00007700619,0.000023253542,0.0005939582,0.000223003,0.00013732398],"category_scores_gemma":[0.0027081834,0.00029089904,0.0012627776,0.00062823744,0.00029407392,0.00006624725,0.00028422714,0.0011476818,0.00000358921],"study_design_candidate":"meta_analysis","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000040928215,0.00024609425,0.0034885954,0.010231796,0.36008254,0.00037502008,0.00013227055,0.0004454283,2.8595983e-7,0.000071181144,0.0067084744,0.6181774],"study_design_scores_gemma":[0.00039744764,0.0010760315,0.009514316,0.0011529281,0.86826926,0.0010738652,0.000007846451,0.0019437469,1.4186674e-7,0.000007839798,0.11624175,0.00031481963],"about_ca_topic_score_codex":0.00012613174,"about_ca_topic_score_gemma":0.0000052849396,"teacher_disagreement_score":0.6178626,"about_ca_system_score_codex":0.000041061892,"about_ca_system_score_gemma":0.0005996257,"threshold_uncertainty_score":0.99995434},"labels":[],"label_agreement":null},{"id":"W4412151081","doi":"10.1038/s41591-025-03780-x","title":"Real-world deployment of a fine-tuned pathology foundation model for lung cancer biomarker detection","year":2025,"lang":"en","type":"article","venue":"Nature Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Institute for Research in Immunology and Cancer; Montreal General Hospital","funders":"National Center for Advancing Translational Sciences; Georgia Clinical and Translational Science Alliance; National Cancer Institute; U.S. Department of Health and Human Services; National Institutes of Health; Memorial Sloan-Kettering Cancer Center; Warren Alpert Foundation","keywords":"Biomarker; Lung cancer; Software deployment; Foundation (evidence); Medicine; Pathology; Cancer; Computational biology; Biology; Computer science; Internal medicine; Geography; Archaeology","score_opus":0.012688771360622901,"score_gpt":0.37364906714853785,"score_spread":0.36096029578791494,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412151081","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36392912,0.0044515193,0.5650596,0.05651167,0.0027273188,0.0017409102,0.000010938035,0.00017206198,0.005396838],"genre_scores_gemma":[0.98700595,0.00036350323,0.005285414,0.0025951357,0.00032220507,0.0001353419,0.00007504579,0.000026268126,0.0041911313],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987727,0.00003966114,0.00040478865,0.0003017317,0.00026198776,0.00021914377],"domain_scores_gemma":[0.99906313,0.00019859348,0.00016199562,0.00024001407,0.00025159435,0.000084660016],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00061720546,0.00015638531,0.0004521297,0.00045498318,0.00007491765,0.0000037468167,0.000084770654,0.00020663299,0.00005889097],"category_scores_gemma":[0.00090389955,0.00011543267,0.00008495835,0.00047627234,0.00014233185,0.000034333025,0.000026934598,0.00055933004,2.925105e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018153912,0.00020153614,0.01828009,0.0018019003,0.00048538062,0.00002785746,0.0005726832,0.000749299,0.4609133,0.0048257466,0.023870632,0.4864562],"study_design_scores_gemma":[0.005000248,0.00015708018,0.017166985,0.0009274744,0.00064727454,0.000012000232,0.000023930785,0.96038586,0.008260772,0.00087924633,0.006431044,0.000108102584],"about_ca_topic_score_codex":0.0002463565,"about_ca_topic_score_gemma":0.0003104512,"teacher_disagreement_score":0.95963657,"about_ca_system_score_codex":0.00018581413,"about_ca_system_score_gemma":0.00016787644,"threshold_uncertainty_score":0.47072074},"labels":[],"label_agreement":null},{"id":"W4412158966","doi":"10.51731/cjht.2025.1165","title":"Hourly MRI Exam Volumes Across Canada in 2022–2023","year":2025,"lang":"en","type":"article","venue":"Canadian Journal of Health Technologies","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Environmental science","score_opus":0.009638817110730492,"score_gpt":0.3077956371914655,"score_spread":0.298156820080735,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412158966","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.55631804,0.073441,0.0005894715,0.36707795,0.0014690422,0.00025315356,0.000025354608,0.00005984817,0.0007661103],"genre_scores_gemma":[0.99413574,0.0008094856,0.00059414806,0.0037636193,0.000017164697,0.000003272535,0.000003122641,0.000011033026,0.00066242996],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.998396,0.000048965187,0.0006052432,0.00014316059,0.0001870171,0.0006196438],"domain_scores_gemma":[0.9992077,0.00008401169,0.0002209157,0.00022185907,0.000111846435,0.00015367758],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010260775,0.0001183231,0.00047727535,0.00041904743,0.00018673371,0.000029328137,0.00031042512,0.00012018311,0.000018907847],"category_scores_gemma":[0.0019146642,0.00010312575,0.000051341805,0.0006590578,0.00019867875,0.000052661093,0.000026491338,0.0012358243,0.0000011904204],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011949714,0.000011065638,0.14621933,0.00016443008,0.000037624155,0.0010180181,0.00016491959,0.00006649495,0.00001400952,0.0002493036,0.10681083,0.74523205],"study_design_scores_gemma":[0.0012909177,0.00020711448,0.18961366,0.0014229596,0.000015862546,0.00044117254,0.00689781,0.00053787185,0.00009499658,0.0011969203,0.79812485,0.00015589417],"about_ca_topic_score_codex":0.869268,"about_ca_topic_score_gemma":0.9384367,"teacher_disagreement_score":0.7450761,"about_ca_system_score_codex":0.0011943507,"about_ca_system_score_gemma":0.011593045,"threshold_uncertainty_score":0.9940103},"labels":[],"label_agreement":null},{"id":"W4412162393","doi":"10.2967/jnumed.124.269424","title":"Recommendations for Standardizing Nuclear Medicine Terminology and Data in the Era of Theranostics and Artificial Intelligence","year":2025,"lang":"en","type":"article","venue":"Journal of Nuclear Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Cancer Institute; Society of Nuclear Medicine and Molecular Imaging","keywords":"Terminology; Data science; Computer science; Artificial intelligence; Medical physics; Medicine; Philosophy","score_opus":0.06837953979724956,"score_gpt":0.40056855165957705,"score_spread":0.3321890118623275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412162393","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21521096,0.0039013643,0.010198124,0.7685815,0.0007045957,0.00042215036,0.000012527443,0.000010800759,0.00095797435],"genre_scores_gemma":[0.9782034,0.003910198,0.008307005,0.00906548,0.00047368428,4.9495515e-7,0.000008974826,0.000018434832,0.000012295129],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986378,0.00010001168,0.0007361584,0.00015206473,0.00023435519,0.00013960419],"domain_scores_gemma":[0.9982238,0.0009873379,0.00029402412,0.00027311782,0.00014891053,0.000072830975],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024437509,0.000103176026,0.0005069459,0.0002351201,0.00008802585,0.000010224786,0.00026542405,0.00006272178,0.000063331354],"category_scores_gemma":[0.0040461333,0.0000595811,0.000026382668,0.0001975336,0.0006111308,0.00007485367,0.00008144156,0.00066595105,1.7288752e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011672465,0.00020553984,0.0019603374,0.000488821,0.00027219614,0.00010315755,0.013719778,0.000007944991,0.01137705,0.029800138,0.054225408,0.8866724],"study_design_scores_gemma":[0.00951518,0.007863678,0.028554432,0.013050191,0.0021957962,0.0026095829,0.059439167,0.06274756,0.0000870907,0.03955314,0.77403706,0.00034711068],"about_ca_topic_score_codex":0.000040237916,"about_ca_topic_score_gemma":0.0000046258438,"teacher_disagreement_score":0.8863253,"about_ca_system_score_codex":0.000022936254,"about_ca_system_score_gemma":0.00006178401,"threshold_uncertainty_score":0.4843892},"labels":[],"label_agreement":null},{"id":"W4412163645","doi":"10.1158/1557-3265.aimachine-a062","title":"Abstract A062: Uncovering Social and Clinical Determinants of Baseline Distress Prior to Radiation Therapy: An Explainable Machine Learning Approach","year":2025,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Baseline (sea); Distress; Medicine; Radiation therapy; Psychology; Intensive care medicine; Psychotherapist; Clinical psychology; Surgery; Political science","score_opus":0.13878671856935565,"score_gpt":0.5319197666372175,"score_spread":0.39313304806786187,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412163645","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99416417,0.0012509485,0.0006649926,0.0022926875,0.00024355683,0.00060256955,0.0000144886635,0.000039725008,0.0007268377],"genre_scores_gemma":[0.99379927,0.003190008,0.0009707099,0.0005128239,0.00075204985,0.00005612702,0.00003709189,0.00003423303,0.0006476733],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99628824,0.0008652461,0.0010770393,0.000657436,0.0006182302,0.0004938316],"domain_scores_gemma":[0.99718267,0.001622462,0.00016526566,0.00031030306,0.00030036073,0.00041896492],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010682283,0.0001669395,0.00073463825,0.0002325997,0.0003318416,0.000062702406,0.00025686403,0.0002311158,0.00008663306],"category_scores_gemma":[0.006000739,0.0001385091,0.0001615923,0.00048377778,0.00047623122,0.00010770629,0.00021542894,0.0020713652,0.0000031586637],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010597495,0.00040997245,0.46616283,0.0002034672,0.000053932385,0.000015915937,0.00013555508,0.000066655855,0.00018279633,0.0000245138,0.00039055626,0.53129405],"study_design_scores_gemma":[0.0046956656,0.00095435034,0.91533715,0.00034815696,0.000054236065,0.0000039747993,0.0002296802,0.056402825,0.00022108154,0.00009275086,0.02147811,0.00018202419],"about_ca_topic_score_codex":0.001234916,"about_ca_topic_score_gemma":0.000061976956,"teacher_disagreement_score":0.531112,"about_ca_system_score_codex":0.0001049315,"about_ca_system_score_gemma":0.00045418701,"threshold_uncertainty_score":0.89991665},"labels":[],"label_agreement":null},{"id":"W4412163652","doi":"10.1158/1557-3265.aimachine-b007","title":"Abstract B007: TheBlueScrubs-v1: A Large-Scale Curated Dataset with ∼11 Billion Oncology Tokens for AI-Driven Cancer Research","year":2025,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Cancer; Scale (ratio); Oncology; Precision oncology; Medicine; Internal medicine; Clinical Oncology; Computer science; Computational biology; Biology; Cartography; Geography","score_opus":0.23548338623858694,"score_gpt":0.6182858435125832,"score_spread":0.38280245727399625,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412163652","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7867119,0.0028441497,0.0016033784,0.19617261,0.0013801103,0.0044203736,0.00222285,0.00015681896,0.004487844],"genre_scores_gemma":[0.96734643,0.007027549,0.0021647604,0.0094839865,0.0029318647,0.0023497683,0.001807118,0.00014995586,0.006738544],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99407923,0.0010322586,0.00093912135,0.0011443928,0.0012241098,0.0015809132],"domain_scores_gemma":[0.9917692,0.004651272,0.00013193885,0.0009620882,0.0017954566,0.00069003715],"candidate_categories":["research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.013053169,0.00025181827,0.0008919205,0.000622899,0.0006734647,0.00012209403,0.00069925666,0.000449604,0.0009333196],"category_scores_gemma":[0.004106336,0.0001762909,0.0001818299,0.0016102811,0.0015315908,0.00013934178,0.000434032,0.004876556,0.000063180065],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.006527693,0.0013729373,0.10537006,0.00069752935,0.00047921925,0.00022561093,0.00036070216,0.00019780833,0.0018131752,0.000545465,0.83538735,0.047022436],"study_design_scores_gemma":[0.0075981095,0.0014563008,0.034215823,0.001197415,0.00011836569,0.0000085100455,0.0005383395,0.013870382,0.00041100176,0.0005023923,0.93986636,0.00021697668],"about_ca_topic_score_codex":0.00387385,"about_ca_topic_score_gemma":0.004698262,"teacher_disagreement_score":0.18668863,"about_ca_system_score_codex":0.0007109229,"about_ca_system_score_gemma":0.0039919573,"threshold_uncertainty_score":0.99998},"labels":[],"label_agreement":null},{"id":"W4412163675","doi":"10.1158/1557-3265.aimachine-b008","title":"Abstract B008: Fine-tuned large language model accurately estimates progression-free survival from radiology reports in immune checkpoint inhibitor–treated cancers","year":2025,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Medicine; Immune checkpoint; Cancer; Oncology; Internal medicine; Radiology; Cancer research; Immunotherapy","score_opus":0.10724996230744933,"score_gpt":0.5259392477263349,"score_spread":0.4186892854188856,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412163675","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9781006,0.007601496,0.00013559908,0.009340124,0.0008828817,0.0008076166,0.000051864892,0.0001193536,0.0029604528],"genre_scores_gemma":[0.99528193,0.0011987288,0.0012404602,0.00038445208,0.0005246216,0.00023982117,0.00019737626,0.00005168133,0.0008808971],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99519634,0.00040470535,0.0015988597,0.00097079325,0.0008347646,0.000994563],"domain_scores_gemma":[0.99580854,0.0021365841,0.0002515597,0.0010888159,0.00032916787,0.00038531952],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.006678934,0.00028068214,0.0010615776,0.00035309035,0.00018175018,0.0000651708,0.00046164164,0.00041984956,0.0004655083],"category_scores_gemma":[0.014720811,0.00022195997,0.00023863495,0.00076849136,0.0006259933,0.00009892602,0.0005172863,0.0032739341,0.000014898424],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004175953,0.0011472619,0.8601295,0.0005523904,0.0005038772,0.005252142,0.0008538221,0.001449033,0.041608784,0.00012629457,0.021210605,0.06299035],"study_design_scores_gemma":[0.01559867,0.00051298755,0.8052765,0.0051947436,0.00016420301,0.000037828806,0.0007395948,0.14993097,0.01413338,0.0044260747,0.003328211,0.00065684476],"about_ca_topic_score_codex":0.011273097,"about_ca_topic_score_gemma":0.0014106773,"teacher_disagreement_score":0.14848194,"about_ca_system_score_codex":0.00057463825,"about_ca_system_score_gemma":0.0020405694,"threshold_uncertainty_score":0.9990255},"labels":[],"label_agreement":null},{"id":"W4412163678","doi":"10.1158/1557-3265.aimachine-a063","title":"Abstract A063: Artificial Intelligence in Cytopathology and Histopathology of Cancer: The Evolution to Precision Pathology","year":2025,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Cytopathology; Histopathology; Pathology; Cancer; Anatomical pathology; Medicine; Premalignant lesion; Cytology; Internal medicine; Immunohistochemistry","score_opus":0.12663274599736044,"score_gpt":0.5545919012089935,"score_spread":0.4279591552116331,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412163678","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95286584,0.004463993,0.0023545742,0.038287725,0.000633341,0.0004076176,0.000004535631,0.000012436967,0.00096992595],"genre_scores_gemma":[0.99578965,0.0021417302,0.00045985478,0.00095546735,0.00021481159,0.00013078276,0.0000016679938,0.000010355494,0.0002956539],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9974113,0.00062510493,0.00079090695,0.00048385008,0.00029422258,0.0003945925],"domain_scores_gemma":[0.99733275,0.0018324521,0.00008357237,0.0003606479,0.00025762874,0.00013296476],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006710542,0.00009694214,0.00045384592,0.00037986177,0.00010007396,0.000010512712,0.0002556311,0.00020451764,0.00009911536],"category_scores_gemma":[0.0063933735,0.00006857322,0.00006805836,0.0006719917,0.0011587684,0.000024013772,0.00026677374,0.0016106551,0.000008678221],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010342279,0.00019272637,0.24341922,0.00010544467,0.000009973684,0.00013511821,0.00030129685,0.00012465457,0.011814849,0.0055755926,0.00079446996,0.73649246],"study_design_scores_gemma":[0.0003966561,0.0004471293,0.98099864,0.0004001535,0.00002551811,0.000020949085,0.00026892265,0.0021803277,0.0004660621,0.010278665,0.0044430215,0.0000739327],"about_ca_topic_score_codex":0.001922846,"about_ca_topic_score_gemma":0.0009691966,"teacher_disagreement_score":0.73757946,"about_ca_system_score_codex":0.00025659,"about_ca_system_score_gemma":0.00061855075,"threshold_uncertainty_score":0.7653927},"labels":[],"label_agreement":null},{"id":"W4412163698","doi":"10.1158/1557-3265.aimachine-a034","title":"Abstract A034: A robust ensemble-feature selection and machine learning approach to identify true somatic variants","year":2025,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Somatic cell; Feature selection; Artificial intelligence; Selection (genetic algorithm); Feature (linguistics); Machine learning; Computer science; Ensemble learning; Computational biology; Biology; Genetics; Gene","score_opus":0.14004128679786548,"score_gpt":0.5022422850503581,"score_spread":0.3622009982524926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412163698","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94324327,0.00432633,0.0100223925,0.023761813,0.0005283366,0.0011856919,0.000004977459,0.00015444073,0.01677278],"genre_scores_gemma":[0.9838137,0.0015354855,0.004317214,0.0012004912,0.00059273944,0.00011846127,0.000020207042,0.000041649528,0.008360067],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9969966,0.00049316284,0.0005276495,0.00070729625,0.000681077,0.0005942425],"domain_scores_gemma":[0.9978118,0.0010442937,0.00007567669,0.0002905035,0.00028895572,0.00048878056],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0052950983,0.00017966243,0.0005401683,0.00040447817,0.0003808257,0.00015530932,0.0002126327,0.00026117289,0.00012146871],"category_scores_gemma":[0.006239559,0.0001482803,0.000116909,0.0009781994,0.0002020551,0.00008215098,0.00021581005,0.003920815,0.00003014088],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016036715,0.0009962331,0.28244615,0.0019556666,0.00055216986,0.000110540095,0.00052837335,0.0032811377,0.011247889,0.0008407471,0.043489724,0.6529477],"study_design_scores_gemma":[0.0039276932,0.00046512688,0.75841534,0.001287927,0.0001520709,0.00006591218,0.00018428628,0.18801694,0.0001819525,0.0007021515,0.046317216,0.00028340542],"about_ca_topic_score_codex":0.0005377909,"about_ca_topic_score_gemma":0.00005525395,"teacher_disagreement_score":0.6526643,"about_ca_system_score_codex":0.0001677757,"about_ca_system_score_gemma":0.00045623365,"threshold_uncertainty_score":0.9983772},"labels":[],"label_agreement":null},{"id":"W4412163706","doi":"10.1158/1557-3265.aimachine-a051","title":"Abstract A051: Multi-omic explainable machine learning improves cancer treatment outcome prediction","year":2025,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Cancer; Outcome (game theory); Medicine; Artificial intelligence; Bioinformatics; Computer science; Internal medicine; Biology; Mathematics","score_opus":0.20157133297784077,"score_gpt":0.5564497345569215,"score_spread":0.3548784015790807,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412163706","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96176386,0.008253227,0.00049678003,0.023086319,0.0016134994,0.0012100857,0.00003857313,0.00023234634,0.0033053046],"genre_scores_gemma":[0.94941115,0.011225126,0.00048826268,0.0010478591,0.0009305035,0.0005266502,0.00004673226,0.00005531599,0.036268417],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99646384,0.00034910924,0.0009660016,0.00077388383,0.00063032063,0.00081683934],"domain_scores_gemma":[0.9975863,0.0010541087,0.00012406324,0.00046300626,0.0003329711,0.00043956126],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.003352069,0.00025008968,0.0007019416,0.00034490137,0.00040565338,0.000089646266,0.00025304136,0.00025554132,0.0007364931],"category_scores_gemma":[0.0028475292,0.0001893036,0.00029404822,0.00052402454,0.00045736422,0.00010399636,0.00016853462,0.0027801264,0.000060129812],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000666656,0.0006102401,0.7493759,0.00030218047,0.00029884712,0.00007608418,0.00013393507,0.00032333398,0.0039223884,0.00006271269,0.0036594672,0.24056828],"study_design_scores_gemma":[0.00789076,0.00081831345,0.6414169,0.00059878075,0.0001735562,0.000005608535,0.00018435065,0.066958465,0.0006847908,0.00008747092,0.28096977,0.0002112225],"about_ca_topic_score_codex":0.00871497,"about_ca_topic_score_gemma":0.0002644495,"teacher_disagreement_score":0.2773103,"about_ca_system_score_codex":0.0009829126,"about_ca_system_score_gemma":0.0009848286,"threshold_uncertainty_score":0.9995205},"labels":[],"label_agreement":null},{"id":"W4412163707","doi":"10.1158/1557-3265.aimachine-pr-07","title":"Abstract PR-07: Automated segmentation pipeline for radiological imaging using UniverSeg and similarity-guided support set retrieval","year":2025,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Pipeline (software); Radiological weapon; Segmentation; Similarity (geometry); Artificial intelligence; Medicine; Computer science; Set (abstract data type); Pattern recognition (psychology); Computer vision; Radiology; Image (mathematics)","score_opus":0.23329529516041245,"score_gpt":0.5787951067437557,"score_spread":0.3454998115833432,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412163707","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9690406,0.0006461188,0.0063370313,0.02044108,0.0006067937,0.001333043,0.00004223512,0.0002455134,0.0013076183],"genre_scores_gemma":[0.9885906,0.00092514075,0.005770401,0.002706141,0.00062675815,0.000025218906,0.00014458949,0.000034239325,0.0011768895],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973826,0.0003024923,0.0007148681,0.0005881671,0.0004651602,0.0005467509],"domain_scores_gemma":[0.9971777,0.0017384099,0.00010828542,0.0002558854,0.00039810376,0.00032160318],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005989264,0.00015539801,0.0004941498,0.00024030349,0.00030888864,0.00007644715,0.00016513944,0.00018894918,0.00023216102],"category_scores_gemma":[0.005369827,0.0001309873,0.00013549223,0.0004167423,0.000695002,0.00009897211,0.00015098629,0.0013369401,0.0000057694824],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.007267406,0.00076379906,0.4197241,0.0017303715,0.0005112105,0.0006767703,0.00045740695,0.0005190613,0.04197807,0.0006146288,0.35927796,0.16647923],"study_design_scores_gemma":[0.010548386,0.00036505025,0.09690753,0.000629336,0.0002479558,0.00006645864,0.0005807943,0.8458922,0.00088800373,0.0008736399,0.042705763,0.00029491057],"about_ca_topic_score_codex":0.00018791,"about_ca_topic_score_gemma":0.000004207962,"teacher_disagreement_score":0.8453731,"about_ca_system_score_codex":0.0002913389,"about_ca_system_score_gemma":0.0009063535,"threshold_uncertainty_score":0.64285725},"labels":[],"label_agreement":null},{"id":"W4412163711","doi":"10.1158/1557-3265.aimachine-pr-06","title":"Abstract PR-06: Analysis of pathologists’ intraobserver, interobserver and AI agreement in breast cancer HER2 scoring: AI-assessed intra-sample tumor heterogeneity relates to lower agreement among pathologists and with AI","year":2025,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Medicine; Breast cancer; Cancer; Pathology; Radiology; Internal medicine","score_opus":0.07702883829687934,"score_gpt":0.47380851972291194,"score_spread":0.3967796814260326,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412163711","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97879964,0.0008915123,0.00047922507,0.018695489,0.00018503623,0.0007955273,0.00007358823,0.000022477892,0.000057484976],"genre_scores_gemma":[0.99378526,0.0016384319,0.0005353381,0.0035848226,0.00009692979,0.00022180729,0.000024489013,0.000024083769,0.00008884235],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9959766,0.00044993262,0.0011123783,0.0010396965,0.0007293834,0.0006919911],"domain_scores_gemma":[0.9972909,0.0008946108,0.00018701007,0.0006157337,0.0005439208,0.00046782664],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0045975465,0.00028722786,0.0010983447,0.0006085709,0.00011701626,0.000103145896,0.0003092959,0.0001873823,0.00024716096],"category_scores_gemma":[0.0014550862,0.00021507802,0.00015998866,0.0014855934,0.0011565465,0.00014169881,0.00047673963,0.0020310285,0.0000017727588],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012451692,0.00053483155,0.9798153,0.00044935726,0.0006724278,0.00031097655,0.00017507254,0.0007544223,0.00062565156,0.00003815152,0.00083442405,0.014544185],"study_design_scores_gemma":[0.002235761,0.00056170765,0.990136,0.0014386104,0.00035004487,0.0000049913842,0.000117512216,0.0041646822,0.00021021652,0.00008751451,0.00049019814,0.00020272056],"about_ca_topic_score_codex":0.013405065,"about_ca_topic_score_gemma":0.008794697,"teacher_disagreement_score":0.015110667,"about_ca_system_score_codex":0.0003372024,"about_ca_system_score_gemma":0.00044757294,"threshold_uncertainty_score":0.9931648},"labels":[],"label_agreement":null},{"id":"W4412163712","doi":"10.1158/1557-3265.aimachine-a017","title":"Abstract A017: Personalizing treatment selection for prostate cancer using causal machine learning","year":2025,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Prostate cancer; Cancer; Selection (genetic algorithm); Prostate; Medicine; Artificial intelligence; Oncology; Computer science; Internal medicine","score_opus":0.22192562760509268,"score_gpt":0.5782361287465765,"score_spread":0.35631050114148377,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412163712","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9761647,0.006677079,0.0009306917,0.012668369,0.000748467,0.0013989257,0.00002495974,0.00010672351,0.0012800952],"genre_scores_gemma":[0.9803445,0.005210629,0.0013355416,0.0006611675,0.0013095256,0.00044488785,0.00003734932,0.000059903465,0.010596508],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99736995,0.00025730237,0.00056853314,0.0006157096,0.00048539948,0.00070312264],"domain_scores_gemma":[0.99781513,0.0011326342,0.000109837514,0.00017947801,0.00047584367,0.00028705996],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028974179,0.00019095912,0.0005149356,0.00025682632,0.00059200625,0.00008555281,0.00012301687,0.00016592666,0.00032165676],"category_scores_gemma":[0.001852635,0.0001526123,0.00024076352,0.0005257159,0.0002963421,0.00006952821,0.00006748475,0.0016144488,0.0000063554025],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0020201977,0.00038638015,0.649823,0.00056300004,0.0005011432,0.000028377337,0.00033258455,0.0017918812,0.01056151,0.00017278598,0.0028224448,0.33099672],"study_design_scores_gemma":[0.010164569,0.0016928649,0.08029993,0.0018997204,0.00042971937,0.000018987057,0.0003407216,0.5178853,0.002012512,0.0003417269,0.3845263,0.00038761046],"about_ca_topic_score_codex":0.010417116,"about_ca_topic_score_gemma":0.0004865388,"teacher_disagreement_score":0.56952304,"about_ca_system_score_codex":0.0009841142,"about_ca_system_score_gemma":0.0016389262,"threshold_uncertainty_score":0.9961726},"labels":[],"label_agreement":null},{"id":"W4412163722","doi":"10.1158/1557-3265.aimachine-a015","title":"Abstract A015: Precision medicine approach to melanoma immunotherapy: Predicting response, adverse events, and hospital admissions using machine learning and explainable artificial intelligence","year":2025,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Immunotherapy; Medicine; Adverse effect; Precision medicine; Melanoma; Artificial intelligence; Machine learning; Intensive care medicine; Medical physics; Computer science; Internal medicine; Cancer; Pathology; Cancer research","score_opus":0.12511467088594824,"score_gpt":0.5043422509448524,"score_spread":0.37922758005890417,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412163722","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9737706,0.0046559647,0.005769053,0.0134198805,0.00036586414,0.0009690337,0.000005576025,0.000065105545,0.0009789026],"genre_scores_gemma":[0.9894615,0.00268772,0.0055277892,0.00044902912,0.00043429976,0.00006684249,0.0000108796185,0.000043702796,0.0013182848],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99616843,0.0007582894,0.00090750185,0.00080316036,0.00075375696,0.00060886686],"domain_scores_gemma":[0.99551487,0.0029658838,0.00012665037,0.00032873245,0.00030432484,0.00075954443],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.010240211,0.00022316852,0.000598993,0.00049868703,0.000662339,0.000037237685,0.00022445606,0.00020973015,0.00019222134],"category_scores_gemma":[0.019887295,0.00017459325,0.00008422043,0.0007786152,0.00050805224,0.00010815887,0.00040273764,0.0024214704,0.0000040154196],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.013985435,0.00091056566,0.4024162,0.00065834326,0.00033851253,0.00012525567,0.0025366652,0.0006856428,0.01598248,0.00068894785,0.0009258894,0.5607461],"study_design_scores_gemma":[0.0062559377,0.0065567396,0.45768607,0.01106941,0.00031248797,0.00011383124,0.010070953,0.4308785,0.001278792,0.0051588467,0.0695942,0.001024257],"about_ca_topic_score_codex":0.00096935924,"about_ca_topic_score_gemma":0.000010722277,"teacher_disagreement_score":0.5597218,"about_ca_system_score_codex":0.000189437,"about_ca_system_score_gemma":0.0005985247,"threshold_uncertainty_score":0.99987996},"labels":[],"label_agreement":null},{"id":"W4412163723","doi":"10.1158/1557-3265.aimachine-b003","title":"Abstract B003: Towards machine learning fairness in glioblastoma: An evaluation of protected attributes in publicly available clinical datasets","year":2025,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Glioblastoma; Computer science; Medicine; Artificial intelligence; Cancer research","score_opus":0.27140211578424217,"score_gpt":0.564677647575961,"score_spread":0.2932755317917188,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412163723","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98960483,0.0015065473,0.00006070392,0.0056770965,0.00030877328,0.0014125238,0.000050947154,0.000045499597,0.0013330936],"genre_scores_gemma":[0.99759996,0.0007942676,0.00031707145,0.00022008964,0.00024403093,0.00024248162,0.00023423602,0.000029623918,0.00031822582],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.991537,0.0031748593,0.0019421013,0.0009395325,0.001703165,0.0007033687],"domain_scores_gemma":[0.9957476,0.0019003716,0.0002347454,0.00071511086,0.001055307,0.00034686583],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.053980373,0.00018942569,0.00090386573,0.0008061164,0.00010313486,0.00006679898,0.0005000671,0.00036945456,0.0011776133],"category_scores_gemma":[0.04267713,0.00016384717,0.00013997772,0.0020555018,0.0006511271,0.00024834118,0.00032942405,0.0050715916,0.000030594656],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014678792,0.0012774651,0.75724006,0.00029413437,0.000056535377,0.000051445793,0.00004497294,0.00037435748,0.0003270476,0.000055701497,0.0034127475,0.23539768],"study_design_scores_gemma":[0.009171192,0.0009149524,0.81872874,0.0011461916,0.00005824943,0.0000034552545,0.00011877302,0.15715003,0.0003308672,0.00037314658,0.011838769,0.00016560055],"about_ca_topic_score_codex":0.009816432,"about_ca_topic_score_gemma":0.003884475,"teacher_disagreement_score":0.23523208,"about_ca_system_score_codex":0.00037902358,"about_ca_system_score_gemma":0.0029551042,"threshold_uncertainty_score":0.9997355},"labels":[],"label_agreement":null},{"id":"W4412163732","doi":"10.1158/1557-3265.aimachine-b020","title":"Abstract B020: Automated classification of thymic epithelial tumors. A novel deep learning approach","year":2025,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Deep learning; Pathology; Medicine; Cancer; Cancer research; Artificial intelligence; Computer science; Internal medicine","score_opus":0.1413354508483994,"score_gpt":0.5147644851405606,"score_spread":0.37342903429216123,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412163732","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.965637,0.0009425736,0.004618609,0.00650064,0.00033519726,0.00065822963,0.000006974446,0.00026031,0.021040464],"genre_scores_gemma":[0.99529994,0.0005087267,0.0020526361,0.00032594058,0.00036755748,0.00007930196,0.000035973957,0.000030371346,0.0012995854],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99695635,0.00031735646,0.0009248099,0.00053889584,0.0007741155,0.00048846507],"domain_scores_gemma":[0.99708813,0.0015535114,0.00018504362,0.0004121129,0.0005118802,0.0002493352],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0055811773,0.00014122525,0.0005652235,0.0003327808,0.00018014558,0.00003793596,0.0003287604,0.00022179971,0.00017413464],"category_scores_gemma":[0.008015063,0.00011630562,0.00019453284,0.0008513029,0.000782115,0.0000535666,0.00014623387,0.0028327426,0.000028510622],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0026191967,0.003116818,0.31062508,0.0024722703,0.00062271464,0.000052014137,0.00058217003,0.0022397153,0.15718162,0.0057028057,0.011547942,0.50323766],"study_design_scores_gemma":[0.0026655253,0.00020874712,0.62916297,0.0005861538,0.000051892574,0.000006236616,0.00021986294,0.35629675,0.0004451896,0.0001450377,0.01010007,0.00011160173],"about_ca_topic_score_codex":0.00045965132,"about_ca_topic_score_gemma":0.0000074753243,"teacher_disagreement_score":0.5031261,"about_ca_system_score_codex":0.00016779426,"about_ca_system_score_gemma":0.0008416647,"threshold_uncertainty_score":0.9994678},"labels":[],"label_agreement":null},{"id":"W4412163736","doi":"10.1158/1557-3265.aimachine-a048","title":"Abstract A048: Weakly supervised prediction of <i>EGFR</i> mutation status and early metastasis of lung adenocarcinoma whole slide histopathology images using artificial intelligence","year":2025,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Histopathology; Adenocarcinoma; Metastasis; Medicine; Lung; Lung cancer; Pathology; Oncology; Cancer; Internal medicine","score_opus":0.147712398576796,"score_gpt":0.49030721034938923,"score_spread":0.3425948117725932,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412163736","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.985597,0.005256778,0.0052977125,0.002825547,0.00031161302,0.000384387,0.0000471684,0.000018468303,0.00026133953],"genre_scores_gemma":[0.9959277,0.001082217,0.0025760974,0.00014657895,0.00015392626,0.000019042987,0.000013170604,0.000017932674,0.00006332688],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99725395,0.00039250168,0.0010405317,0.00041672154,0.00052198354,0.00037433574],"domain_scores_gemma":[0.997758,0.0010254451,0.00018167564,0.00028623245,0.0005566587,0.00019202285],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034575197,0.000117693664,0.00054943236,0.0003830997,0.000106404514,0.000023263929,0.0001388835,0.00014692906,0.00007599015],"category_scores_gemma":[0.0029699046,0.0001068626,0.00012473947,0.00051495293,0.0010497419,0.00010199638,0.00012259626,0.0010495194,0.0000016872714],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013648241,0.0003995322,0.6691496,0.0011919833,0.00015683232,0.00008191986,0.0004656519,0.00015980746,0.09577027,0.0013018729,0.0006317019,0.22932601],"study_design_scores_gemma":[0.0008233695,0.0005788735,0.9611673,0.0006752836,0.0002685107,0.000009066394,0.0004988254,0.01755315,0.014076782,0.003864036,0.0003828008,0.00010200454],"about_ca_topic_score_codex":0.0020031403,"about_ca_topic_score_gemma":0.000019558398,"teacher_disagreement_score":0.2920177,"about_ca_system_score_codex":0.00017282572,"about_ca_system_score_gemma":0.0006321703,"threshold_uncertainty_score":0.4559698},"labels":[],"label_agreement":null},{"id":"W4412163738","doi":"10.1158/1557-3265.aimachine-a064","title":"Abstract A064: Dynamics in automatic CT based body composition and blood biomarkers in predicting mortality on immune therapy treated solid malignancy patients","year":2025,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Malignancy; Medicine; Solid tumor; Immune system; Internal medicine; Oncology; Cancer; Immunology","score_opus":0.06093815350943812,"score_gpt":0.4830402115322952,"score_spread":0.4221020580228571,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412163738","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9951057,0.00044588718,0.0000105292365,0.00237743,0.00014495518,0.00085131766,0.000014401111,0.00004080698,0.0010090182],"genre_scores_gemma":[0.9985595,0.00070412207,0.00007081712,0.00038653234,0.000045947327,0.00009422727,0.00009253168,0.000021010082,0.00002533102],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9971655,0.00052740943,0.00088691805,0.00046882636,0.0005164191,0.00043491452],"domain_scores_gemma":[0.9980178,0.0012840936,0.00010759634,0.00031114952,0.00012358648,0.0001557629],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003671224,0.00015143576,0.0004920079,0.0004391502,0.00010102879,0.000042153704,0.00014438397,0.00011638876,0.000057877365],"category_scores_gemma":[0.0012448783,0.00012751903,0.00008692752,0.00065139856,0.00031720588,0.000051179068,0.000057638295,0.0014137218,0.0000021200076],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00054793264,0.001417952,0.9422764,0.00023027913,0.00013196073,0.00012506952,0.000024167159,0.00004008668,0.00068250025,0.000024121282,0.000043135493,0.05445635],"study_design_scores_gemma":[0.0071408586,0.00036298274,0.8078074,0.0019820018,0.000024445537,7.9258336e-7,0.000030221352,0.18219152,0.00030243897,0.00006680008,0.000012576649,0.000078008045],"about_ca_topic_score_codex":0.0031445846,"about_ca_topic_score_gemma":0.00019124412,"teacher_disagreement_score":0.18215142,"about_ca_system_score_codex":0.00036827434,"about_ca_system_score_gemma":0.00030946106,"threshold_uncertainty_score":0.61419964},"labels":[],"label_agreement":null},{"id":"W4412163750","doi":"10.1158/1557-3265.aimachine-b019","title":"Abstract B019: Clinician-AI evaluation of prognostic information extraction in head and neck cancer using an on-premises LLM","year":2025,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Jewish General Hospital; University of Calgary; McGill University Health Centre; McGill University","funders":"","keywords":"Premises; Head and neck cancer; Medicine; Head and neck; Cancer; Oncology; Internal medicine; Surgery","score_opus":0.2956370655473759,"score_gpt":0.6309681627015147,"score_spread":0.3353310971541388,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412163750","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9924239,0.00081510085,0.000099348494,0.0039900374,0.0003884322,0.00082133,0.0000062266,0.0000157118,0.0014398983],"genre_scores_gemma":[0.99735016,0.0011554343,0.00022035827,0.0008677369,0.00025023217,0.000089262925,0.000016971702,0.000010636559,0.00003920623],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99717927,0.00043910052,0.0008744242,0.00029012386,0.0009319276,0.00028517842],"domain_scores_gemma":[0.99752593,0.0011208976,0.00016098924,0.00025097182,0.0007755382,0.00016569925],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008523128,0.00010187274,0.00034566817,0.00039119396,0.00009304064,0.000046514597,0.00010523168,0.00017508233,0.00016428655],"category_scores_gemma":[0.008569902,0.0000886621,0.00005827753,0.00048761375,0.0002746922,0.0003294026,0.000049497146,0.0014694983,0.0000033432214],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007640718,0.00046923096,0.51805186,0.0003246973,0.000036863774,0.0000035495152,0.00013820369,0.0029093975,0.0005947427,0.00007459097,0.00041457228,0.4762182],"study_design_scores_gemma":[0.0029189116,0.00037107695,0.8061264,0.0019234032,0.00007291653,0.0000014251651,0.00012963737,0.1861798,0.00020217913,0.0004978258,0.0015057463,0.00007065115],"about_ca_topic_score_codex":0.0028937098,"about_ca_topic_score_gemma":0.00033823296,"teacher_disagreement_score":0.47614753,"about_ca_system_score_codex":0.00030938914,"about_ca_system_score_gemma":0.0016033493,"threshold_uncertainty_score":0.9997813},"labels":[],"label_agreement":null},{"id":"W4412163759","doi":"10.1158/1557-3265.aimachine-b001","title":"Abstract B001: Jarvais: A modular framework to standardize machine learning workflows and accelerate reproducible AI in oncology – benchmarking against a human-developed model for predicting emergency department visits during cancer treatment","year":2025,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Princess Margaret Cancer Centre; University Health Network","funders":"","keywords":"Benchmarking; Workflow; Modular design; Medicine; Cancer; Emergency department; Cancer treatment; Oncology; Medical physics; Computer science; Internal medicine; Business; Nursing; Operating system; Database","score_opus":0.16115820120713506,"score_gpt":0.549015948345654,"score_spread":0.38785774713851895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412163759","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97713363,0.0039577456,0.00265924,0.012907366,0.00046685166,0.0022077048,0.000025200354,0.00006696243,0.00057527836],"genre_scores_gemma":[0.97811425,0.01167364,0.005025423,0.0008687725,0.00078367855,0.0018400508,0.00003691358,0.000067911686,0.0015893868],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99527967,0.00035778165,0.0012921238,0.0014423743,0.00057995017,0.0010481244],"domain_scores_gemma":[0.99744177,0.0009443793,0.00017119708,0.0005179834,0.00043046463,0.0004942181],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.005598012,0.00031648457,0.00096703,0.00048345613,0.00067451515,0.00008704194,0.00024139024,0.00030722225,0.00011945043],"category_scores_gemma":[0.004560553,0.0002767396,0.00017690478,0.00084095617,0.0001306072,0.00010494962,0.00034294892,0.0024265286,0.0000022392899],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0033802192,0.00067532645,0.6162219,0.00068258314,0.0005946496,0.00013806966,0.0017649472,0.07660859,0.0064108763,0.000084729814,0.0009836961,0.2924544],"study_design_scores_gemma":[0.009485062,0.0014891305,0.27692243,0.004640055,0.00017996707,0.000004067024,0.00020649603,0.6713353,0.00083120633,0.0011126971,0.033230882,0.0005627009],"about_ca_topic_score_codex":0.0018322263,"about_ca_topic_score_gemma":0.0027431285,"teacher_disagreement_score":0.5947267,"about_ca_system_score_codex":0.0014933002,"about_ca_system_score_gemma":0.00137942,"threshold_uncertainty_score":0.99996847},"labels":[],"label_agreement":null},{"id":"W4412163761","doi":"10.1158/1557-3265.aimachine-b018","title":"Abstract B018: Practical benchmarking of large language models for structuring synthetic prostate cancer histopathology statements in English and Finnish","year":2025,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Prostate cancer; Histopathology; Benchmarking; Medicine; Cancer; Structuring; Pathology; Medical physics; Internal medicine","score_opus":0.09570608012282598,"score_gpt":0.5610822752971152,"score_spread":0.4653761951742892,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412163761","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9912595,0.0024257738,0.00046349686,0.0037001872,0.00044435717,0.0008093777,0.000051844967,0.000019155557,0.0008262817],"genre_scores_gemma":[0.99503523,0.0021578907,0.0015702402,0.00039001947,0.00022593114,0.00020858421,0.000012920907,0.000021739537,0.00037745642],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9976867,0.00022092563,0.00071207056,0.00047847358,0.00035927055,0.00054259173],"domain_scores_gemma":[0.9975102,0.0016648774,0.000119419434,0.00024176385,0.00030616886,0.00015759634],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0047439155,0.00011496064,0.00048555707,0.000240538,0.000089371,0.000024775438,0.00012065945,0.00013994343,0.00010908362],"category_scores_gemma":[0.0044010356,0.00010024835,0.00007329399,0.00023349111,0.00038390825,0.00011212644,0.00017551349,0.0013153601,3.2567394e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004108869,0.001040702,0.58377165,0.0050689057,0.00022791255,0.00040595725,0.006000121,0.0008112667,0.0042535053,0.0038846526,0.0063311025,0.38409534],"study_design_scores_gemma":[0.023090461,0.001315944,0.7531732,0.007105369,0.00029493542,0.000016955815,0.003526548,0.16358268,0.0016900783,0.010670423,0.03489996,0.00063347333],"about_ca_topic_score_codex":0.00067980925,"about_ca_topic_score_gemma":0.00019275927,"teacher_disagreement_score":0.3834619,"about_ca_system_score_codex":0.00017854833,"about_ca_system_score_gemma":0.00063875737,"threshold_uncertainty_score":0.57146585},"labels":[],"label_agreement":null},{"id":"W4412163773","doi":"10.1158/1557-3265.aimachine-b053","title":"Abstract B053: Empowering AI-driven prediction of the tumor microenvironment from histopathology images via molecular annotation","year":2025,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Histopathology; Annotation; Medicine; Pathology; Computer science; Artificial intelligence","score_opus":0.04307666403992606,"score_gpt":0.46314826344673304,"score_spread":0.420071599406807,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412163773","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97940105,0.001285308,0.0028494068,0.014690811,0.00063270895,0.00037638427,0.000026722299,0.000019428475,0.0007181794],"genre_scores_gemma":[0.9971312,0.00034604323,0.00052754726,0.0014091639,0.00018521941,0.0000442981,0.000016284974,0.000015891066,0.0003243096],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99807143,0.00030160177,0.00054216245,0.0003604072,0.00045868923,0.00026573087],"domain_scores_gemma":[0.99883646,0.00041050924,0.00010581111,0.00041586705,0.0001290488,0.000102276754],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014266913,0.00009122183,0.00028811945,0.000101361176,0.000106617605,0.000013387966,0.00022891739,0.000092820024,0.00018390316],"category_scores_gemma":[0.0011209146,0.0000676798,0.00014735291,0.00021299285,0.00068326725,0.00003525103,0.00018410842,0.001371107,0.000009543377],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027104214,0.00026487344,0.39402387,0.0001437743,0.00007720852,0.00008422357,0.000119152915,0.000339226,0.5600487,0.00004553154,0.006428372,0.03815406],"study_design_scores_gemma":[0.0011759348,0.00012840984,0.9687297,0.00040465943,0.0000614526,0.000004185818,0.000041813113,0.003646198,0.01484629,0.0005739524,0.010336496,0.00005091092],"about_ca_topic_score_codex":0.0005770254,"about_ca_topic_score_gemma":0.0000082965535,"teacher_disagreement_score":0.57470584,"about_ca_system_score_codex":0.00020151715,"about_ca_system_score_gemma":0.00024749208,"threshold_uncertainty_score":0.59568536},"labels":[],"label_agreement":null},{"id":"W4412163792","doi":"10.1158/1557-3265.aimachine-a049","title":"Abstract A049: Development of a tri-modal contrast learning model integrating pathology-text and CT-text for clinical oncology tasks","year":2025,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Precision oncology; Medicine; Contrast (vision); Clinical Oncology; Pathology; Modal; Medical physics; Anatomical pathology; Radiology; Computer science; Internal medicine; Artificial intelligence; Cancer; Precision medicine; Immunohistochemistry","score_opus":0.23504182417906772,"score_gpt":0.590668948559425,"score_spread":0.35562712438035726,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412163792","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9713109,0.0020024655,0.011659325,0.009791032,0.00041205928,0.00093031174,0.000008219305,0.000042494925,0.0038432013],"genre_scores_gemma":[0.9746229,0.0018369791,0.020325277,0.0012024359,0.00037097497,0.00020812462,0.000021211335,0.00003419488,0.0013779185],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9955261,0.00062784064,0.0019723403,0.00074170885,0.0004653632,0.0006666816],"domain_scores_gemma":[0.990289,0.008072065,0.00031230258,0.000283787,0.0006237387,0.00041912455],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.016914103,0.00019596529,0.0011966481,0.0002583189,0.000318547,0.00003324458,0.00026767835,0.00033861268,0.00008038927],"category_scores_gemma":[0.020864569,0.00015689105,0.0002530852,0.0002874178,0.0013297469,0.000052544525,0.00027402578,0.0040288903,0.0000064438273],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001679589,0.0005305949,0.069215946,0.00038105078,0.00021776951,0.00005589439,0.00033924714,0.00009042208,0.0014912938,0.00060572964,0.004688662,0.9207038],"study_design_scores_gemma":[0.03394751,0.0043703658,0.30298188,0.00343322,0.00042540667,0.00008378753,0.0023304129,0.4223976,0.00081490836,0.0050319913,0.22344872,0.0007341796],"about_ca_topic_score_codex":0.0001050749,"about_ca_topic_score_gemma":0.00007000783,"teacher_disagreement_score":0.9199696,"about_ca_system_score_codex":0.00020733103,"about_ca_system_score_gemma":0.003736067,"threshold_uncertainty_score":0.99826884},"labels":[],"label_agreement":null},{"id":"W4412163810","doi":"10.1158/1557-3265.aimachine-b059","title":"Abstract B059: Cancer Recurrence and Anxiety/Depression: High Accuracy Artificial Intelligence Predictive Modeling","year":2025,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Depression (economics); Anxiety; Cancer; Medicine; Psychiatry; Clinical psychology; Psychology; Oncology; Internal medicine","score_opus":0.19788921596295983,"score_gpt":0.5589213086711612,"score_spread":0.36103209270820136,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412163810","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94060767,0.012021156,0.013723942,0.028023822,0.0016601479,0.00093215937,0.000031058884,0.00010543868,0.0028946367],"genre_scores_gemma":[0.96922565,0.027583186,0.00061297236,0.0009008997,0.0010946806,0.00020193424,0.000009494152,0.00002398177,0.0003471972],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966651,0.00026272624,0.00082318083,0.0008604558,0.0007765412,0.000611952],"domain_scores_gemma":[0.9965565,0.0018559367,0.000099419005,0.0004518198,0.0005915515,0.00044476945],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0037019784,0.0001870662,0.00049565424,0.00021492084,0.00034537693,0.00010612892,0.00033154257,0.00024182403,0.000469271],"category_scores_gemma":[0.0071691684,0.00015052126,0.000116070856,0.0006357314,0.0007581715,0.00014333765,0.00036258384,0.0031889237,0.000016646492],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011007658,0.00020674056,0.05103853,0.0002664219,0.000104121646,0.000033142336,0.00014715278,0.0019945411,0.00042605487,0.0008266294,0.003975431,0.9398805],"study_design_scores_gemma":[0.0013087144,0.00038232285,0.098329306,0.0054643718,0.00017952561,0.00001585886,0.00055107573,0.854478,0.0014651469,0.024116974,0.013266783,0.00044193087],"about_ca_topic_score_codex":0.0026089149,"about_ca_topic_score_gemma":0.00007297834,"teacher_disagreement_score":0.9394385,"about_ca_system_score_codex":0.00018549645,"about_ca_system_score_gemma":0.0011397928,"threshold_uncertainty_score":0.99911076},"labels":[],"label_agreement":null},{"id":"W4412163818","doi":"10.1158/1557-3265.aimachine-a044","title":"Abstract A044: Developing a digital twin framework for colorectal cancer outcome prediction and robust clinical trial simulation","year":2025,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Colorectal cancer; Outcome (game theory); Medicine; Clinical trial; Cancer; Oncology; Internal medicine; Mathematics","score_opus":0.35160112972281476,"score_gpt":0.6146728912783317,"score_spread":0.2630717615555169,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412163818","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94424456,0.0005947431,0.036584806,0.0131788235,0.0026405698,0.001983954,0.000042713284,0.000081570375,0.00064825907],"genre_scores_gemma":[0.9886767,0.0009264771,0.0044749253,0.0011986801,0.0033337036,0.0003940749,0.000036816265,0.00003582245,0.0009227646],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9964667,0.00021962203,0.0014763791,0.00070967525,0.0005922393,0.00053538306],"domain_scores_gemma":[0.98898256,0.009767294,0.0001634242,0.00024404102,0.0004981631,0.0003444955],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.00604051,0.00017319081,0.00068583543,0.00020162573,0.0002872173,0.00017704126,0.00018099205,0.00048400392,0.00016360088],"category_scores_gemma":[0.028117426,0.00014478296,0.00026496602,0.00043345607,0.0006184496,0.00014632846,0.00016362409,0.0024798086,0.000012782063],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.02769055,0.00032048402,0.67314255,0.00035042342,0.00025936082,0.000012432018,0.000048468766,0.001159484,0.000012877604,0.0007897479,0.0035689748,0.29264465],"study_design_scores_gemma":[0.04719123,0.0015501616,0.7638582,0.0015942868,0.00018325922,0.000002442534,0.00010576046,0.12641844,0.00001748282,0.0053491364,0.05344779,0.00028181213],"about_ca_topic_score_codex":0.000105682266,"about_ca_topic_score_gemma":0.000021942973,"teacher_disagreement_score":0.29236284,"about_ca_system_score_codex":0.00028124137,"about_ca_system_score_gemma":0.0012427951,"threshold_uncertainty_score":0.9998215},"labels":[],"label_agreement":null},{"id":"W4412163824","doi":"10.1158/1557-3265.aimachine-a029","title":"Abstract A029: Validation of a Deep Learning Serial Computed Tomography Response Biomarker for Predicting Overall Survival in Metastatic Kidney Cancer Treated with Immune Checkpoint Inhibitors","year":2025,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Kidney cancer; Medicine; Biomarker; Cancer; Oncology; Immune system; Internal medicine; Immunology; Biology","score_opus":0.07322595110256533,"score_gpt":0.45973526590854913,"score_spread":0.38650931480598383,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412163824","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9922366,0.0006962879,0.00084762485,0.004356242,0.0004110438,0.0011963549,0.00002425747,0.00005285381,0.00017874749],"genre_scores_gemma":[0.9977605,0.00024439665,0.0010558153,0.00012704195,0.00021588914,0.00027507063,0.000081984566,0.00004308557,0.00019626455],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9956499,0.0012375226,0.0012814517,0.0005648735,0.0006961141,0.00057019136],"domain_scores_gemma":[0.9949048,0.0035771555,0.00029212574,0.00028639182,0.00064253603,0.00029698986],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0117663015,0.00020237538,0.0007951207,0.0007042288,0.00015692068,0.000051061877,0.00019611446,0.00015628821,0.00011892937],"category_scores_gemma":[0.009035375,0.00016105117,0.0002513482,0.0013382311,0.0004781132,0.000095151285,0.00010761839,0.001523881,8.9369684e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.041944124,0.000583996,0.8748896,0.0011538937,0.0007394715,0.000050914856,0.0003270184,0.0022371274,0.041079983,0.000025155414,0.00038418255,0.036584496],"study_design_scores_gemma":[0.015344902,0.0011389703,0.910471,0.0035821619,0.0001984731,0.0000029097137,0.00026717782,0.056703527,0.010209285,0.00008969573,0.0017816334,0.00021026532],"about_ca_topic_score_codex":0.0040163635,"about_ca_topic_score_gemma":0.00012683237,"teacher_disagreement_score":0.0544664,"about_ca_system_score_codex":0.000246338,"about_ca_system_score_gemma":0.0011360365,"threshold_uncertainty_score":0.9993119},"labels":[],"label_agreement":null},{"id":"W4412163825","doi":"10.1158/1557-3265.aimachine-b011","title":"Abstract B011: Pan-cancer immunotherapy response prediction using the CURE AI large clinicogenomic foundation model","year":2025,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Immunotherapy; Medicine; Cancer; Foundation (evidence); Cancer immunotherapy; Oncology; Immunology; Internal medicine; History","score_opus":0.18830264592713986,"score_gpt":0.5809798997474049,"score_spread":0.3926772538202651,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412163825","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9216242,0.003461448,0.011814427,0.06037641,0.0012141877,0.00093881355,0.00003231337,0.000115344024,0.00042289365],"genre_scores_gemma":[0.9773473,0.011489306,0.00048570518,0.006841542,0.0011592759,0.00017801026,0.000018810639,0.00007126989,0.0024087715],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960813,0.00090878014,0.0009770211,0.0006085238,0.00077552965,0.0006488482],"domain_scores_gemma":[0.99644125,0.0019774567,0.00016049879,0.0007095575,0.0005309806,0.00018025332],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.014171153,0.00018202445,0.00044487495,0.0002445407,0.00054329576,0.00012876118,0.00039662063,0.0002821593,0.00039679854],"category_scores_gemma":[0.0021430051,0.0001286488,0.00027253682,0.00060884916,0.00061199383,0.0001375836,0.00016367731,0.0033217086,0.000024398869],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.02953136,0.0014454501,0.33207226,0.00041560206,0.0010890381,0.00004833196,0.0009022952,0.0101675885,0.05124833,0.0012348262,0.07385585,0.4979891],"study_design_scores_gemma":[0.0048875907,0.0002298023,0.1919199,0.0007173084,0.000117721174,0.000004670923,0.00015642183,0.56593084,0.0002101808,0.0017598434,0.23390053,0.00016521256],"about_ca_topic_score_codex":0.00046490956,"about_ca_topic_score_gemma":0.000041617015,"teacher_disagreement_score":0.55576324,"about_ca_system_score_codex":0.00052808016,"about_ca_system_score_gemma":0.002686337,"threshold_uncertainty_score":0.99897766},"labels":[],"label_agreement":null},{"id":"W4412163829","doi":"10.1158/1557-3265.aimachine-b027","title":"Abstract B027: Multimodal prediction of pathological complete response in esophageal cancer using automated machine learning and variational autoencoder-based synthetic data augmentation","year":2025,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Autoencoder; Pathological; Artificial intelligence; Esophageal cancer; Medicine; Machine learning; Cancer; Computer science; Pattern recognition (psychology); Deep learning; Pathology; Internal medicine","score_opus":0.23480719697752436,"score_gpt":0.5437777774325331,"score_spread":0.3089705804550087,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412163829","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9884624,0.0009547634,0.004993088,0.0044379625,0.00024510597,0.00051351794,0.00022946276,0.00009606685,0.000067630725],"genre_scores_gemma":[0.9922758,0.00034499425,0.0067271944,0.00022462488,0.00011032806,0.000042501822,0.00019499277,0.00001825317,0.00006133548],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962172,0.0013148024,0.000848703,0.0006233346,0.00065009005,0.00034590194],"domain_scores_gemma":[0.9958926,0.003209807,0.00016034232,0.00032015343,0.00025823427,0.00015890226],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0085895285,0.00013513,0.00045110274,0.00039263567,0.00017619268,0.000037939062,0.00021818581,0.0001862867,0.00028553145],"category_scores_gemma":[0.007532533,0.000117267846,0.000055585817,0.0005289859,0.0005801787,0.00010382729,0.00022839555,0.0016490626,0.0000015654674],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008573144,0.0006751323,0.9118443,0.0004787057,0.0001168119,0.00014781242,0.00012462905,0.029530983,0.022391556,0.000058847516,0.0003441908,0.025713854],"study_design_scores_gemma":[0.002116759,0.00014175277,0.45812365,0.00039965354,0.000031086824,0.0000029539622,0.000018748793,0.5388676,0.000029361476,0.00003261926,0.0001965621,0.000039238825],"about_ca_topic_score_codex":0.0022646002,"about_ca_topic_score_gemma":0.00005547884,"teacher_disagreement_score":0.50933665,"about_ca_system_score_codex":0.000270055,"about_ca_system_score_gemma":0.0011164728,"threshold_uncertainty_score":0.9017689},"labels":[],"label_agreement":null},{"id":"W4412163844","doi":"10.1158/1557-3265.aimachine-a032","title":"Abstract A032: Using machine learning to tackle tumor heterogeneity","year":2025,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Tumor heterogeneity; Cancer; Medicine; Computer science; Internal medicine","score_opus":0.1972787579798199,"score_gpt":0.5708786982592107,"score_spread":0.3735999402793908,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412163844","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9821145,0.0017260594,0.00057890697,0.01074194,0.0005791089,0.00051447365,0.0000064412643,0.00008713036,0.003651441],"genre_scores_gemma":[0.9888666,0.00032523257,0.002505498,0.005116722,0.00074709114,0.000048045786,0.000009967078,0.000043437038,0.0023373617],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99674195,0.00040687405,0.00069343933,0.00065999356,0.0007594406,0.00073827687],"domain_scores_gemma":[0.9974249,0.0010301536,0.00007371636,0.0004641666,0.0003750899,0.00063196296],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0054677906,0.00016938882,0.00054847106,0.00034472108,0.00036878677,0.00008585553,0.00032380497,0.00012869858,0.0005753107],"category_scores_gemma":[0.007188677,0.00014369817,0.00021628785,0.000856572,0.00035276046,0.000054381675,0.00037611576,0.003229726,0.00011361404],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011162625,0.00046697338,0.8588197,0.0004444008,0.00023847002,0.00035264267,0.00009557679,0.0014250859,0.017757662,0.00014979648,0.011584876,0.10754852],"study_design_scores_gemma":[0.0045557693,0.00076576864,0.41098338,0.0018572488,0.00013540899,0.000039512153,0.00014947147,0.08653891,0.004709296,0.00033974013,0.48947617,0.00044930115],"about_ca_topic_score_codex":0.0020345005,"about_ca_topic_score_gemma":0.00011179138,"teacher_disagreement_score":0.4778913,"about_ca_system_score_codex":0.0002830655,"about_ca_system_score_gemma":0.00078576215,"threshold_uncertainty_score":0.99906987},"labels":[],"label_agreement":null},{"id":"W4412163852","doi":"10.1158/1557-3265.aimachine-a054","title":"Abstract A054: Multimodal LLM-Driven Intervention for Precision Risk Prediction in Lung Cancer Surgery","year":2025,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Medicine; Lung cancer; Intervention (counseling); Cancer; Surgery; Oncology; Internal medicine; Nursing","score_opus":0.11368957863770339,"score_gpt":0.5594096166642134,"score_spread":0.44572003802651,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412163852","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98355854,0.0028543344,0.003673457,0.0060708467,0.0018176931,0.0013424718,0.000066296445,0.000056303743,0.00056006084],"genre_scores_gemma":[0.99059844,0.005190891,0.0005072254,0.00023648715,0.00090576295,0.0007219144,0.00005536645,0.000030130677,0.001753804],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9968341,0.00044028895,0.0010486143,0.0005954282,0.0005650039,0.0005165611],"domain_scores_gemma":[0.99447405,0.0044289613,0.00015468399,0.0003216936,0.0004041241,0.00021645949],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008475108,0.00013485563,0.0005154054,0.0005012485,0.00016691785,0.00004986509,0.00018564983,0.0002516264,0.00045197995],"category_scores_gemma":[0.010284939,0.00011519792,0.00036230413,0.0005557556,0.00025126155,0.00010916116,0.0001236592,0.0020719713,0.000008388912],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012750677,0.0003915709,0.62288207,0.0004570275,0.00007008952,0.000009309587,0.000037256228,0.00041255186,0.00014757061,0.0000160363,0.03259785,0.34170356],"study_design_scores_gemma":[0.0032935322,0.000135178,0.8018683,0.002576826,0.00006372221,6.624489e-7,0.0000369376,0.17859453,0.00008138866,0.00028384005,0.012982941,0.00008214562],"about_ca_topic_score_codex":0.0044705314,"about_ca_topic_score_gemma":0.00049093895,"teacher_disagreement_score":0.34162143,"about_ca_system_score_codex":0.0005000173,"about_ca_system_score_gemma":0.0006742492,"threshold_uncertainty_score":0.9980518},"labels":[],"label_agreement":null},{"id":"W4412163856","doi":"10.1158/1557-3265.aimachine-b014","title":"Abstract B014: Are histopathology foundation models clinically ready for survival prediction?","year":2025,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Ontario Institute for Cancer Research; University of Toronto","funders":"","keywords":"Histopathology; Medicine; Foundation (evidence); Pathology; History","score_opus":0.3062119964964399,"score_gpt":0.5841844480305458,"score_spread":0.27797245153410594,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412163856","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.74943143,0.0018977227,0.06440794,0.1102397,0.009421122,0.003767867,0.00012197514,0.00041821424,0.060294017],"genre_scores_gemma":[0.98199815,0.0019947274,0.00235768,0.0026535199,0.0020274932,0.0004382911,0.00013477856,0.000047415986,0.00834796],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9965122,0.00040574427,0.0012010989,0.0007164334,0.00060773623,0.00055682746],"domain_scores_gemma":[0.9941421,0.0037820379,0.0001823699,0.0005536443,0.0010253625,0.00031448985],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.010640938,0.000145019,0.0006194582,0.00023610199,0.00029468175,0.00005238694,0.00029105565,0.00033224473,0.00021177532],"category_scores_gemma":[0.0098670395,0.00012558246,0.00023900937,0.00032723357,0.0007288342,0.0000940835,0.00013250289,0.002066499,0.000041701758],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0055061616,0.0013793836,0.48279315,0.00090975314,0.00026498924,0.000096403615,0.00012909841,0.00057735614,0.00082724355,0.013230117,0.12632337,0.36796296],"study_design_scores_gemma":[0.0075113047,0.0011261252,0.6581335,0.0007545476,0.000182962,0.000008593207,0.00020577839,0.06326248,0.0000230752,0.028078618,0.24048398,0.00022903942],"about_ca_topic_score_codex":0.00024205928,"about_ca_topic_score_gemma":0.000041193303,"teacher_disagreement_score":0.36773393,"about_ca_system_score_codex":0.00027804472,"about_ca_system_score_gemma":0.0012265147,"threshold_uncertainty_score":0.9984733},"labels":[],"label_agreement":null},{"id":"W4412163864","doi":"10.1158/1557-3265.aimachine-b026","title":"Abstract B026: Artificial Intelligence Apps for Medical Image Analysis using pyCERR and Cancer Genomics Cloud","year":2025,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Cloud computing; Genomics; Cancer; Computer science; Data science; Medicine; Computational biology; World Wide Web; Biology; Genome; Genetics; Internal medicine; Operating system; Gene","score_opus":0.21203693097384477,"score_gpt":0.588695933687648,"score_spread":0.37665900271380326,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412163864","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91426766,0.005030917,0.05126335,0.02662453,0.0010254628,0.0008727891,0.000041864274,0.00005425591,0.0008191947],"genre_scores_gemma":[0.97960323,0.009807134,0.0052749254,0.0022924729,0.0022655365,0.00016609616,0.000026816397,0.000049320406,0.00051446736],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99645156,0.0002178761,0.0010469801,0.00075173826,0.00085014116,0.0006816797],"domain_scores_gemma":[0.99581736,0.0025183416,0.00011754648,0.00041049713,0.00051342224,0.00062280893],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0073151807,0.00017972423,0.00076474977,0.00046042376,0.00032547236,0.00011646584,0.00034835775,0.00031300265,0.0008537364],"category_scores_gemma":[0.0066470983,0.00015231105,0.00033002574,0.0011610778,0.001293044,0.00006004296,0.0002702599,0.0020403618,0.000007589089],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014947437,0.00039664432,0.03815754,0.0006149744,0.0016314009,0.000091444956,0.00019132116,0.00044441962,0.0023132195,0.0026722807,0.005220617,0.9467714],"study_design_scores_gemma":[0.0021930197,0.00037482762,0.043308027,0.0012765087,0.0019587064,0.000012512958,0.0007173858,0.8728165,0.0018761243,0.013855131,0.061053507,0.000557757],"about_ca_topic_score_codex":0.0017945509,"about_ca_topic_score_gemma":0.00029287013,"teacher_disagreement_score":0.94621366,"about_ca_system_score_codex":0.0003055679,"about_ca_system_score_gemma":0.0019165486,"threshold_uncertainty_score":0.9347815},"labels":[],"label_agreement":null},{"id":"W4412163873","doi":"10.1158/1557-3265.aimachine-b036","title":"Abstract B036: Machine learning-based and marker-based combined strategy for circulating tumor cells candidates' detection","year":2025,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Circulating tumor cell; Tumor cells; Cancer; Medicine; Computer science; Cancer research; Artificial intelligence; Computational biology; Internal medicine; Biology; Metastasis","score_opus":0.0928434296276607,"score_gpt":0.4815294511441824,"score_spread":0.38868602151652165,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412163873","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98258024,0.0010202135,0.0063411896,0.006937343,0.000490542,0.0013777018,0.00003213247,0.00012762134,0.0010929822],"genre_scores_gemma":[0.9970287,0.000093964925,0.00048745782,0.0011266056,0.00025523655,0.00018227434,0.000057044028,0.00004341472,0.0007252912],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972181,0.0003827265,0.00068638235,0.00062101544,0.00049368147,0.00059814565],"domain_scores_gemma":[0.995246,0.00357289,0.00013777499,0.00029638538,0.00038087854,0.00036607494],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005144349,0.00018994212,0.000517345,0.00029407383,0.00042124244,0.00011013948,0.00016193159,0.00016841854,0.00019763605],"category_scores_gemma":[0.00419143,0.00016532309,0.00017680085,0.00045190894,0.0004692733,0.000043496773,0.000061265266,0.0022383963,0.000006252801],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.011463205,0.0011263859,0.43622082,0.0042411555,0.00039894137,0.00024347207,0.000050835293,0.013051365,0.04597639,0.00014548888,0.005652633,0.4814293],"study_design_scores_gemma":[0.009332643,0.0012835988,0.11151087,0.0007099208,0.000100771525,0.0000030987999,0.000045700053,0.8539315,0.0052314415,0.00029278945,0.017342445,0.00021520762],"about_ca_topic_score_codex":0.0012929024,"about_ca_topic_score_gemma":0.00018140714,"teacher_disagreement_score":0.84088016,"about_ca_system_score_codex":0.00018258777,"about_ca_system_score_gemma":0.0009979034,"threshold_uncertainty_score":0.97248423},"labels":[],"label_agreement":null},{"id":"W4412163877","doi":"10.1158/1557-3265.aimachine-pr-03","title":"Abstract PR-03 Inferring genomic properties and histologic subtypes of solid tumors from H&amp;E whole-slide images","year":2025,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Pathology; Medicine; Cancer research; Computational biology; Biology","score_opus":0.19351091864998232,"score_gpt":0.4968909905268948,"score_spread":0.30338007187691246,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412163877","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9773588,0.0109293405,0.00006652436,0.009149783,0.0002278111,0.0003278979,0.000018033423,0.000037479902,0.0018843218],"genre_scores_gemma":[0.99378794,0.002431004,0.00065270235,0.0005350182,0.00029789,0.00004023675,0.00001067861,0.000021424465,0.002223109],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9977774,0.0002214412,0.0007297742,0.00046704366,0.00039945514,0.00040489447],"domain_scores_gemma":[0.997982,0.0010564951,0.000116909796,0.0003737973,0.0002551543,0.0002156218],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002401563,0.00013735644,0.00062596315,0.00020512786,0.00013731573,0.000035855854,0.00024276716,0.00013823574,0.00018407707],"category_scores_gemma":[0.0048573692,0.000101770616,0.00010840852,0.00020961819,0.0012206575,0.000059780323,0.00028127473,0.0015766271,0.000029781651],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009355428,0.00026633908,0.7651858,0.0007841308,0.00022695147,0.00007428414,0.00029796085,0.00006297737,0.12535594,0.00007990663,0.012550678,0.09417951],"study_design_scores_gemma":[0.0017461854,0.00021605904,0.9497845,0.0015784426,0.000075880685,0.0000059975705,0.00017489972,0.0008608708,0.004062245,0.001246674,0.04008932,0.00015892918],"about_ca_topic_score_codex":0.0026648238,"about_ca_topic_score_gemma":0.00010220577,"teacher_disagreement_score":0.18459873,"about_ca_system_score_codex":0.00012686857,"about_ca_system_score_gemma":0.00065672974,"threshold_uncertainty_score":0.6849748},"labels":[],"label_agreement":null},{"id":"W4412163879","doi":"10.1158/1557-3265.aimachine-a060","title":"Abstract A060: OncoMindPro: An AI-augmented assistant to oncologists","year":2025,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Medicine; Intensive care medicine","score_opus":0.22834382197644307,"score_gpt":0.6400331546755982,"score_spread":0.4116893326991551,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412163879","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8595587,0.0005526993,0.000746407,0.10178588,0.0011175877,0.0010015834,0.000012286277,0.00011960286,0.03510527],"genre_scores_gemma":[0.9772778,0.000303882,0.0011176256,0.013589452,0.00079930975,0.00016749847,0.00001819467,0.00003005215,0.006696164],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.996524,0.00042459505,0.00076640636,0.0007110836,0.0008660677,0.00070788444],"domain_scores_gemma":[0.99664915,0.0012409989,0.000064202366,0.0006745408,0.000511661,0.0008594236],"candidate_categories":["research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.006887766,0.00015645224,0.0005552606,0.00031572353,0.00023204698,0.00009731348,0.00044143279,0.00023037851,0.0010761678],"category_scores_gemma":[0.0061305976,0.0001236932,0.00016031571,0.0007979614,0.00052821415,0.000069457325,0.00025523413,0.0029100978,0.0001432407],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0024499658,0.0014368377,0.15267973,0.00024943126,0.0001945102,0.0004167019,0.00014050253,0.00005237729,0.0040568,0.0008324951,0.20977728,0.6277134],"study_design_scores_gemma":[0.0032560695,0.0013129051,0.56485623,0.00076291617,0.00005379761,0.0000053855674,0.00020276656,0.0023997314,0.0004642566,0.00066433515,0.42583472,0.0001868577],"about_ca_topic_score_codex":0.0010061737,"about_ca_topic_score_gemma":0.00023137213,"teacher_disagreement_score":0.6275265,"about_ca_system_score_codex":0.00042741987,"about_ca_system_score_gemma":0.0017070535,"threshold_uncertainty_score":0.999837},"labels":[],"label_agreement":null},{"id":"W4412163884","doi":"10.1158/1557-3265.aimachine-a007","title":"Abstract A007: Bayesian Counterfactual Machine Learning Individualizes Radiation Modality Selection to Mitigate Immunosuppression","year":2025,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Immunosuppression; Modality (human–computer interaction); Counterfactual thinking; Medicine; Bayesian probability; Selection (genetic algorithm); Machine learning; Artificial intelligence; Computer science; Psychology; Internal medicine","score_opus":0.08295983461883612,"score_gpt":0.5184355499048301,"score_spread":0.435475715285994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412163884","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96436614,0.0015463365,0.0027783914,0.02629056,0.00075492077,0.0007983885,0.000016060385,0.00014346387,0.003305725],"genre_scores_gemma":[0.9940448,0.0009767974,0.000400573,0.0013800112,0.00058860524,0.00009646715,0.00006425055,0.000033786473,0.0024147287],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9962745,0.0007345209,0.00079874194,0.00063747476,0.000938909,0.0006158896],"domain_scores_gemma":[0.997447,0.0013157612,0.00011551693,0.00031182804,0.00037759703,0.00043226843],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0063561844,0.00018444753,0.0004916948,0.00041236082,0.0004719034,0.00013255383,0.00026867003,0.000248143,0.00081427937],"category_scores_gemma":[0.006260235,0.00015691633,0.00016245103,0.0008169047,0.000271247,0.000117347496,0.00020309421,0.0032769185,0.000062849576],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014991541,0.00031383033,0.51891243,0.00025876128,0.0002101162,0.000021692334,0.00032440032,0.0010860263,0.0075299493,0.00018109694,0.014390474,0.45527208],"study_design_scores_gemma":[0.0037077512,0.0006459594,0.79323196,0.0010733404,0.000086084314,0.0000071138156,0.0001290299,0.049754053,0.0032715034,0.000628016,0.14720945,0.00025573096],"about_ca_topic_score_codex":0.00191312,"about_ca_topic_score_gemma":0.000076663,"teacher_disagreement_score":0.45501634,"about_ca_system_score_codex":0.00035297047,"about_ca_system_score_gemma":0.0006643637,"threshold_uncertainty_score":0.99902254},"labels":[],"label_agreement":null},{"id":"W4412163894","doi":"10.1158/1557-3265.aimachine-a047","title":"Abstract A047: Building clinically relevant and interpretable multi-modal machine learning algorithms to predict glioblastoma disease progression","year":2025,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Glioblastoma; Modal; Algorithm; Disease; Medicine; Artificial intelligence; Computer science; Machine learning; Pathology; Cancer research","score_opus":0.06239027585795424,"score_gpt":0.5170713691029938,"score_spread":0.4546810932450395,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412163894","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.959562,0.0040058233,0.0078031216,0.025041658,0.00090892764,0.0016346055,0.000023960572,0.00024234477,0.000777534],"genre_scores_gemma":[0.97971773,0.0020059142,0.012866579,0.0016180958,0.0006821675,0.00022330726,0.000014442621,0.00006615958,0.0028055792],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99509704,0.0005911449,0.0012634243,0.0011229549,0.0010198973,0.00090554735],"domain_scores_gemma":[0.99475986,0.0025678151,0.00014969776,0.000542867,0.00044611786,0.0015336149],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.008022594,0.0002743098,0.0007461438,0.0004321991,0.00052232883,0.00021445086,0.0004011182,0.00023977847,0.00018043083],"category_scores_gemma":[0.021934567,0.00021507943,0.00022702457,0.000710887,0.0008438971,0.00011913898,0.00084396993,0.0044063893,0.000032128817],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0048887976,0.000622051,0.4302121,0.0005090846,0.00015133737,0.0003085255,0.000117637435,0.00016787813,0.0014903992,0.00007111881,0.0027630453,0.55869806],"study_design_scores_gemma":[0.006922283,0.002452824,0.48164532,0.0067019323,0.00018524897,0.000016175947,0.00010948914,0.4000973,0.00020548816,0.00037089337,0.100870684,0.00042237315],"about_ca_topic_score_codex":0.00034274306,"about_ca_topic_score_gemma":0.000026770776,"teacher_disagreement_score":0.55827564,"about_ca_system_score_codex":0.00019776807,"about_ca_system_score_gemma":0.0010803872,"threshold_uncertainty_score":0.9978905},"labels":[],"label_agreement":null},{"id":"W4412163898","doi":"10.1158/1557-3265.aimachine-a053","title":"Abstract A053: A pre-operative Artificial Intelligence-based model to estimate the risk of cancer specific mortality in patients with non-metastatic kidney cancer","year":2025,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Cancer; Kidney cancer; Medicine; Oncology; Internal medicine","score_opus":0.14283247737582186,"score_gpt":0.565024378943111,"score_spread":0.42219190156728914,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412163898","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98176974,0.0003546661,0.006563743,0.008910077,0.00027046577,0.0016387703,0.00015039311,0.000014870941,0.00032726742],"genre_scores_gemma":[0.99594444,0.0006005647,0.0012622756,0.0012358115,0.00013978181,0.0006008628,0.000015710952,0.00003011316,0.00017042841],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99634326,0.0003957941,0.001011255,0.00063277665,0.0010415852,0.00057533896],"domain_scores_gemma":[0.9970295,0.0010798444,0.00017612096,0.0005800675,0.00072741206,0.00040707414],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003880211,0.00020855905,0.00065823493,0.00026014665,0.0001750412,0.00005431482,0.00040005535,0.00009296354,0.0003495404],"category_scores_gemma":[0.0026033388,0.00012616535,0.00013105762,0.0011072136,0.00084250886,0.000059438542,0.00012728716,0.0021352589,0.0000072411426],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0026319406,0.0006590131,0.77016217,0.00024359571,0.00021339019,0.000009879508,0.00036844928,0.14488328,0.00006979398,0.000110497785,0.0016285328,0.07901944],"study_design_scores_gemma":[0.00123303,0.00030351104,0.7350753,0.0015378334,0.000109669134,4.4729042e-8,0.00006287784,0.2602105,0.0004232675,0.00059836585,0.0003230977,0.00012249385],"about_ca_topic_score_codex":0.011513234,"about_ca_topic_score_gemma":0.0043826727,"teacher_disagreement_score":0.11532724,"about_ca_system_score_codex":0.00035523705,"about_ca_system_score_gemma":0.0030937253,"threshold_uncertainty_score":0.9950692},"labels":[],"label_agreement":null},{"id":"W4412163900","doi":"10.1158/1557-3265.aimachine-a033","title":"Abstract A033: Utilizing machine learning algorithms to identify methylation regions predictive of outcome in ICI-treated patients: Insights from the longitudinal RADIOHEAD study","year":2025,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Outcome (game theory); Algorithm; Methylation; Computer science; Machine learning; Medicine; Artificial intelligence; Oncology; Biology; Mathematics; Genetics","score_opus":0.19383250777942687,"score_gpt":0.5438099278505826,"score_spread":0.34997742007115573,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412163900","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99010414,0.0011195594,0.00064742356,0.0053228256,0.00036960116,0.0015229578,0.000015619704,0.000039596598,0.00085830496],"genre_scores_gemma":[0.99856514,0.00026541314,0.00013958724,0.00034818304,0.00022513795,0.00012754415,0.000051765903,0.00002698396,0.0002502561],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9954486,0.0011908885,0.0012644161,0.000661235,0.0010237633,0.00041111303],"domain_scores_gemma":[0.9942407,0.0042546424,0.00018334914,0.0005003074,0.0005918286,0.00022918826],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0040580304,0.00018282152,0.0006958163,0.00044372058,0.0002568487,0.000050100527,0.00038715688,0.00014872497,0.00007592671],"category_scores_gemma":[0.011010068,0.00012555048,0.00015994467,0.0014420912,0.00035157969,0.00009998927,0.0002906643,0.0030973284,0.00001151998],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008057277,0.0008830065,0.96449184,0.000038899434,0.00021929256,0.000039076385,0.0008513307,0.0003134034,0.00018067744,0.000039956994,0.00058411004,0.031552657],"study_design_scores_gemma":[0.0035457336,0.0006780965,0.9839522,0.0005980695,0.00010587213,3.030767e-7,0.00088213786,0.008471815,0.00007927671,0.0002357466,0.001356934,0.00009379826],"about_ca_topic_score_codex":0.01374831,"about_ca_topic_score_gemma":0.0011679109,"teacher_disagreement_score":0.03145886,"about_ca_system_score_codex":0.00031233337,"about_ca_system_score_gemma":0.00023583205,"threshold_uncertainty_score":0.99920255},"labels":[],"label_agreement":null},{"id":"W4412163903","doi":"10.1158/1557-3265.aimachine-b021","title":"Abstract B021: Current oncological large language model research lacks reproducibility, transparency, and long term support","year":2025,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Term (time); Transparency (behavior); Current (fluid); Reproducibility; Medicine; Medical physics; Computer science; Intensive care medicine; Engineering; Computer security; Physics; Statistics; Mathematics","score_opus":0.32363014499013987,"score_gpt":0.6342184687243343,"score_spread":0.3105883237341944,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412163903","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96332675,0.0059586004,0.00044857597,0.01952666,0.0004183912,0.0010004109,0.000030015042,0.00008097636,0.00920963],"genre_scores_gemma":[0.98851573,0.00602894,0.00023047246,0.00062841957,0.000704245,0.00015340622,0.00004113916,0.000029309263,0.0036683264],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9937121,0.00088784425,0.0009747993,0.0018248324,0.0014332779,0.0011671471],"domain_scores_gemma":[0.9950653,0.0021405036,0.000063573425,0.001456465,0.0006146875,0.000659476],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.036391594,0.0001915523,0.00067989674,0.0003564801,0.00039573587,0.00010244959,0.00047809663,0.00029976867,0.00082201627],"category_scores_gemma":[0.012008223,0.00014713683,0.00019172509,0.00073268014,0.0015188279,0.00008502289,0.00056163745,0.006372513,0.00004342965],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00087884703,0.0014661558,0.6020816,0.0010245469,0.000081519094,0.00033150287,0.00053200434,0.000014282582,0.0008759151,0.0006410839,0.029064557,0.36300796],"study_design_scores_gemma":[0.0040654815,0.0006713966,0.9637918,0.0010349018,0.00006998303,0.000013469951,0.0002376131,0.008478228,0.00022838227,0.0020516792,0.019125419,0.00023163554],"about_ca_topic_score_codex":0.00021876582,"about_ca_topic_score_gemma":0.00017108505,"teacher_disagreement_score":0.36277634,"about_ca_system_score_codex":0.000287071,"about_ca_system_score_gemma":0.0018129417,"threshold_uncertainty_score":0.99631405},"labels":[],"label_agreement":null},{"id":"W4412163914","doi":"10.1158/1557-3265.aimachine-b035","title":"Abstract B035: Deep learning-based spatially resolved immune clustering in the tumor microenvironment predicts distant metastasis risk in high-grade prostate cancer","year":2025,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Prostate cancer; Tumor microenvironment; Metastasis; Cancer; Immune system; Medicine; Distant metastasis; Oncology; Internal medicine; Immunology","score_opus":0.048547004041495964,"score_gpt":0.4292443246157977,"score_spread":0.3806973205743017,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412163914","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9657522,0.0071288333,0.0006189694,0.024379892,0.00038872502,0.0014723615,0.00002601343,0.000036983834,0.00019602236],"genre_scores_gemma":[0.9905752,0.006636111,0.00045063984,0.0011257436,0.00022188261,0.0006382367,0.00003555968,0.00004610398,0.00027055413],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9942633,0.0016317336,0.001293785,0.0007887211,0.0010804932,0.00094199274],"domain_scores_gemma":[0.9965251,0.0022901753,0.00022968034,0.00062895246,0.00009861481,0.00022744334],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.01079747,0.0002572051,0.0007319405,0.00038993236,0.00025537665,0.00009981289,0.00055806775,0.00013683237,0.0002515143],"category_scores_gemma":[0.0036641178,0.00018154678,0.0001962024,0.0008833032,0.0007376101,0.000063174455,0.00025795566,0.00523828,0.000011697373],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0026984042,0.0010253323,0.8072123,0.0005897453,0.0001634858,0.00065265363,0.0006721096,0.046957795,0.0016285286,0.000017334658,0.0005533287,0.13782899],"study_design_scores_gemma":[0.0067832316,0.0003305714,0.91299677,0.0014725183,0.000089356065,0.0000021199855,0.0003241201,0.06267952,0.0002836332,0.0001317038,0.014728632,0.00017782736],"about_ca_topic_score_codex":0.01653649,"about_ca_topic_score_gemma":0.0051720906,"teacher_disagreement_score":0.13765118,"about_ca_system_score_codex":0.0006630915,"about_ca_system_score_gemma":0.0007491802,"threshold_uncertainty_score":0.99705666},"labels":[],"label_agreement":null},{"id":"W4412166542","doi":"10.1017/cjn.2025.10282","title":"P.132 The role of large language models in neuroradiology: a scoping review and thematic analysis","year":2025,"lang":"en","type":"review","venue":"Canadian Journal of Neurological Sciences / Journal Canadien des Sciences Neurologiques","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Thematic map; Neuroradiology; Thematic analysis; Linguistics; Psychology; Computer science; Sociology; Geography; Cartography; Philosophy; Neuroscience; Neurology; Qualitative research; Social science","score_opus":0.032339897619357134,"score_gpt":0.3556612034476592,"score_spread":0.3233213058283021,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412166542","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.040507995,0.9558682,0.000023520306,0.0019308563,0.0001535584,0.0005596619,0.000011951294,0.0000063490293,0.000937917],"genre_scores_gemma":[0.03844689,0.95777375,0.00045066272,0.0032222993,0.00007436922,0.000007774739,8.563363e-7,0.000010661101,0.000012739836],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.9943213,0.0019889213,0.001658926,0.000523438,0.00054160086,0.0009658038],"domain_scores_gemma":[0.99531084,0.0018783244,0.0014664232,0.00024352364,0.00019465666,0.00090622157],"candidate_categories":["sts","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.008153442,0.00039881116,0.002787365,0.0021104026,0.0008028421,0.00019372947,0.0016493559,0.00022600897,0.00005877114],"category_scores_gemma":[0.005686906,0.00020587881,0.00068168185,0.0036563934,0.0040015667,0.00029155184,0.00012354682,0.002383305,3.2625863e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006977021,0.00022342241,0.22281234,0.04069794,0.0010518857,0.015395388,0.0022324347,0.003036841,0.0000020564603,0.004674311,0.0005094181,0.7092942],"study_design_scores_gemma":[0.0025176662,0.08953607,0.0141020985,0.4922803,0.04182731,0.22591966,0.0023187182,0.040604327,0.0000041013354,0.037684355,0.049897466,0.0033079358],"about_ca_topic_score_codex":0.0007002571,"about_ca_topic_score_gemma":0.013829738,"teacher_disagreement_score":0.70598626,"about_ca_system_score_codex":0.0001182916,"about_ca_system_score_gemma":0.005426615,"threshold_uncertainty_score":0.9999182},"labels":[],"label_agreement":null},{"id":"W4412196595","doi":"10.1016/j.clinimag.2025.110541","title":"Corrigendum to “Diversity, inclusivity and traceability of mammography datasets used in development of Artificial Intelligence technologies: a systematic review” [Clin Imaging 118 (2025) 110369]","year":2025,"lang":"en","type":"erratum","venue":"Clinical Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"SickKids Foundation","funders":"","keywords":"Traceability; Medicine; Mammography; Diversity (politics); Medical physics; Software engineering; Internal medicine; Engineering; Anthropology","score_opus":0.05418804972057811,"score_gpt":0.39563686120460273,"score_spread":0.3414488114840246,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412196595","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08501428,0.40077737,0.24834935,0.09833356,0.09590956,0.05766257,0.0029751603,0.0033952247,0.0075829],"genre_scores_gemma":[0.71639323,0.05507797,0.19364886,0.019817743,0.0014640421,0.0008621718,0.0055538965,0.00057617563,0.006605931],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.993011,0.00051370944,0.003955997,0.00116454,0.00081381976,0.00054093753],"domain_scores_gemma":[0.99579835,0.0010712763,0.0012711356,0.0012812149,0.0003181729,0.00025985474],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.008112692,0.0005187276,0.0034165767,0.00082647486,0.00017330598,0.000038329847,0.0009219186,0.00031347506,0.000023595008],"category_scores_gemma":[0.021009836,0.00046413596,0.0004042739,0.0012619167,0.000935265,0.00011477062,0.003133199,0.0027349398,0.000005145113],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019109513,0.0015136577,0.24110982,0.4957387,0.0004527296,0.00033598067,0.0010040692,0.0000029305845,0.0000766852,0.000079903,0.12665445,0.13283998],"study_design_scores_gemma":[0.0016730786,0.0003004713,0.024221703,0.9146115,0.0045448374,0.00009056136,0.003936551,0.032814514,0.0003250356,0.002273345,0.013264393,0.0019439822],"about_ca_topic_score_codex":0.00016985401,"about_ca_topic_score_gemma":0.00005838423,"teacher_disagreement_score":0.63137895,"about_ca_system_score_codex":0.00018616479,"about_ca_system_score_gemma":0.0008196683,"threshold_uncertainty_score":0.999781},"labels":[],"label_agreement":null},{"id":"W4412376941","doi":"10.1145/3726302.3730165","title":"Assessing Support for the TREC 2024 RAG Track: A Large-Scale Comparative Study of LLM and Human Evaluations","year":2025,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; National Institute of Standards and Technology","keywords":"Computer science; Track (disk drive); Scale (ratio); Information retrieval; Artificial intelligence; Operating system; Cartography; Geography","score_opus":0.05437345212556912,"score_gpt":0.46370002796214643,"score_spread":0.40932657583657733,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412376941","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9403689,0.00012559912,0.032893077,0.003174281,0.00015425653,0.0011384012,0.000003224454,0.00002528907,0.022116974],"genre_scores_gemma":[0.98792064,0.0000038704557,0.0018135373,0.0003837801,0.000046663423,0.000058175232,0.000011019118,0.0000063825782,0.009755929],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9992105,0.00006342654,0.00025715496,0.00017254768,0.00016793834,0.00012847075],"domain_scores_gemma":[0.9991806,0.00043962296,0.00005953765,0.0001686433,0.00010685826,0.000044737437],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009452131,0.00008107218,0.00026960406,0.00008182396,0.00025225137,0.00004372507,0.000061391926,0.000025850499,0.00019596262],"category_scores_gemma":[0.00015001604,0.00004947013,0.000048848142,0.00015250676,0.00007997,0.00005555452,0.000032548007,0.00019623482,7.671321e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00048212157,0.015382634,0.54245114,0.0010676269,0.003377554,0.000025461533,0.079489134,0.0010646041,0.02303726,0.02336067,0.16256493,0.14769687],"study_design_scores_gemma":[0.012635537,0.0016555584,0.5739543,0.0002317437,0.001894295,0.000016225651,0.09077919,0.29666355,0.00062108046,0.0009006107,0.020453662,0.00019423559],"about_ca_topic_score_codex":0.00007516986,"about_ca_topic_score_gemma":0.00011370996,"teacher_disagreement_score":0.29559895,"about_ca_system_score_codex":0.000017518953,"about_ca_system_score_gemma":0.00009244556,"threshold_uncertainty_score":0.21456534},"labels":[],"label_agreement":null},{"id":"W4412396400","doi":"10.2196/80519","title":"Correction: Large Language Model–Assisted Risk-of-Bias Assessment in Randomized Controlled Trials Using the Revised Risk-of-Bias Tool: Evaluation Study","year":2025,"lang":"en","type":"erratum","venue":"Journal of Medical Internet Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"JMIR Publications","funders":"","keywords":"Randomized controlled trial; Computer science; Risk assessment; Psychology; Data mining; Medicine; Medical physics; Computer security","score_opus":0.1551637847947682,"score_gpt":0.5316779197303239,"score_spread":0.37651413493555563,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412396400","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.67741126,0.058608223,0.12576513,0.017366515,0.069243275,0.031098375,0.00010795602,0.0000661912,0.020333048],"genre_scores_gemma":[0.9401432,0.017103788,0.0013461213,0.00024820978,0.0044403016,0.00026824768,0.0001020396,0.00010485963,0.03624318],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9135394,0.06425432,0.0078086145,0.0005384536,0.0131831495,0.0006760373],"domain_scores_gemma":[0.9315124,0.0536124,0.009156789,0.00096694485,0.0042655035,0.00048597308],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4366267,0.0004605018,0.009284034,0.0020330932,0.00013518622,0.00014364437,0.001172622,0.00081572065,0.0013187751],"category_scores_gemma":[0.543495,0.00023368094,0.0024590036,0.0009860876,0.0005774109,0.00009269111,0.00041085947,0.015859038,0.0000012777055],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.17859286,0.00553058,0.008669086,0.0015092047,0.017810706,0.00091710564,0.006819474,0.0030127435,0.00007654206,0.00011264327,0.7073702,0.06957882],"study_design_scores_gemma":[0.22367546,0.0006331802,0.0008084091,0.0099383425,0.0053019626,0.00007973383,0.0024624243,0.7554946,0.000009065702,0.00011747145,0.0013506864,0.00012866894],"about_ca_topic_score_codex":0.002182932,"about_ca_topic_score_gemma":0.00017623889,"teacher_disagreement_score":0.7524819,"about_ca_system_score_codex":0.0008495175,"about_ca_system_score_gemma":0.009246351,"threshold_uncertainty_score":0.99959415},"labels":[],"label_agreement":null},{"id":"W4412440980","doi":"10.1016/j.esmoop.2025.105509","title":"The use of machine learning models to predict progression-free survival and overall survival outcomes from waterfall plots in randomized clinical trials (MAP-OUTCOMES)","year":2025,"lang":"en","type":"article","venue":"ESMO Open","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; Princess Margaret Cancer Centre; University Health Network","funders":"","keywords":"Waterfall; Clinical endpoint; Confidence interval; Medicine; Randomized controlled trial; Progression-free survival; Logistic regression; Waterfall model; Artificial intelligence; Machine learning; Internal medicine; Statistics; Oncology; Overall survival; Computer science; Mathematics; Software; Cartography","score_opus":0.1472286405677557,"score_gpt":0.4280689458158332,"score_spread":0.2808403052480775,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412440980","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9304025,0.0005440198,0.0075050886,0.05201969,0.0021051716,0.00551974,0.000057397,0.00010134392,0.0017450422],"genre_scores_gemma":[0.9794734,0.00080637424,0.011873008,0.0022954142,0.00015701125,0.0002231501,0.00012022754,0.00007328225,0.00497814],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99129754,0.0049888087,0.0021283482,0.0005714217,0.00061014097,0.0004037431],"domain_scores_gemma":[0.97445303,0.023968192,0.00044857705,0.0007544611,0.00010296119,0.0002727599],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02509921,0.00031271085,0.0032488615,0.00016755958,0.00016985004,0.0002536331,0.00076541264,0.00017615485,0.000058211288],"category_scores_gemma":[0.04557074,0.00016624053,0.00037378253,0.00016418955,0.0002835272,0.00023416028,0.0013665924,0.0010434226,0.0000039350666],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.04169929,0.00031548963,0.90945,0.000051277602,0.0010543838,0.000043770964,0.0004905806,0.0013147182,0.00003247844,0.0022157468,0.0019257981,0.041406453],"study_design_scores_gemma":[0.33028632,0.0002878642,0.39545602,0.0014815506,0.0007220971,0.0000024056683,0.00014097708,0.24697796,0.000037977443,0.006579508,0.01760336,0.00042395387],"about_ca_topic_score_codex":0.010723679,"about_ca_topic_score_gemma":0.0007260067,"teacher_disagreement_score":0.513994,"about_ca_system_score_codex":0.00004155093,"about_ca_system_score_gemma":0.00018252846,"threshold_uncertainty_score":0.995864},"labels":[],"label_agreement":null},{"id":"W4412450116","doi":"10.1186/s12880-025-01823-w","title":"Non-invasive liver fibrosis screening on CT images using radiomics","year":2025,"lang":"en","type":"article","venue":"BMC Medical Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; University of Toronto; Toronto General Hospital; Vector Institute; Princess Margaret Cancer Centre; Canada Research Chairs; Hospital for Sick Children","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Medicine; Radiomics; Logistic regression; Radiology; Receiver operating characteristic; Asymptomatic; Cohort; Neuroradiology; Biopsy; Ultrasound; Nuclear medicine; Artificial intelligence; Internal medicine; Computer science","score_opus":0.01644999647423392,"score_gpt":0.31342088793424555,"score_spread":0.29697089146001165,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412450116","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39792654,0.0020047934,0.5787196,0.0073409392,0.001156751,0.00058536546,0.000006640615,0.00032494008,0.011934401],"genre_scores_gemma":[0.88098043,0.00048444024,0.099066295,0.016864039,0.00102319,0.000023037635,0.00004426153,0.00010123101,0.0014130984],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99686533,0.0001304539,0.0005995127,0.00069165166,0.0009971019,0.0007159544],"domain_scores_gemma":[0.9973582,0.0012061575,0.00014788189,0.0005310489,0.00011909495,0.00063761283],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010706575,0.00037197585,0.00066656934,0.0004984058,0.00032692045,0.00011477605,0.00036348336,0.00009559651,0.00035001565],"category_scores_gemma":[0.004849942,0.00032482136,0.0003054083,0.0005471241,0.0004660742,0.00016365366,0.00023833492,0.0012053906,0.000044419266],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00052425766,0.00055633666,0.46181327,0.0020635643,0.00045010645,0.004294424,0.00034355218,0.0010306237,0.020137379,0.0012384095,0.049602553,0.45794553],"study_design_scores_gemma":[0.0062294775,0.00008696421,0.042737808,0.009198205,0.00053650746,0.0011705928,0.00041239877,0.91972685,0.00974191,0.0002655765,0.009227244,0.0006664713],"about_ca_topic_score_codex":0.00029168726,"about_ca_topic_score_gemma":0.0000059059425,"teacher_disagreement_score":0.9186962,"about_ca_system_score_codex":0.00019641519,"about_ca_system_score_gemma":0.0009752157,"threshold_uncertainty_score":0.99992037},"labels":[],"label_agreement":null},{"id":"W4412479961","doi":"10.1016/j.annonc.2025.05.133","title":"121P Deep learning can predict MSI/MMR status from primary and metastatic colorectal tissue slides","year":2025,"lang":"en","type":"article","venue":"Annals of Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"European Commission; Seerave Foundation; Canadian Institute for Advanced Research; Israel Cancer Research Fund","keywords":"Medicine; Oncology; Internal medicine; Primary (astronomy); Colorectal cancer; Cancer","score_opus":0.021273015231605408,"score_gpt":0.3606876896887121,"score_spread":0.3394146744571067,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412479961","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9625433,0.004366729,0.001375142,0.012259974,0.000274374,0.0002803132,0.000017063905,0.000059866525,0.01882323],"genre_scores_gemma":[0.98697233,0.0019298508,0.0058812383,0.0041033207,0.00010328906,0.000018252907,0.00010672172,0.000020535657,0.0008644532],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985406,0.0002207882,0.0003940358,0.00029380672,0.00018351366,0.00036725117],"domain_scores_gemma":[0.9985481,0.0008108569,0.00016852366,0.00014167542,0.00012216168,0.00020871963],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00050156174,0.0001536557,0.00066797424,0.00018822664,0.00008611671,0.000013843853,0.00009093256,0.00010867938,0.00014354012],"category_scores_gemma":[0.0013409175,0.00013620852,0.000062910454,0.00017500167,0.00031283457,0.000046519428,0.000106854146,0.0005662703,0.0000036416002],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005656356,0.00030240492,0.08244654,0.00029632827,0.00064637157,0.00029051863,0.0015981632,0.00012705095,0.017600214,0.0005850942,0.006892026,0.88864964],"study_design_scores_gemma":[0.006242602,0.0059855487,0.43729636,0.00048560055,0.0007974888,0.00013253634,0.0012657167,0.013092301,0.007307685,0.0032632765,0.5237734,0.0003574942],"about_ca_topic_score_codex":0.0009462174,"about_ca_topic_score_gemma":0.0000856256,"teacher_disagreement_score":0.8882922,"about_ca_system_score_codex":0.000054482607,"about_ca_system_score_gemma":0.00036173713,"threshold_uncertainty_score":0.5554422},"labels":[],"label_agreement":null},{"id":"W4412523035","doi":"10.1053/j.semnuclmed.2025.06.012","title":"Artificial Intelligence for Tumor [18F]FDG PET Imaging: Advancements and Future Trends - Part II","year":2025,"lang":"en","type":"review","venue":"Seminars in Nuclear Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hospital for Sick Children; University of Toronto","funders":"","keywords":"Medicine; Generalizability theory; Medical physics; Positron emission tomography; Artificial intelligence; Radiology; Computer science","score_opus":0.02248319376095519,"score_gpt":0.3682824389657958,"score_spread":0.3457992452048406,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412523035","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000023576762,0.9820417,0.00008538841,0.010859876,0.0019626871,0.00093530596,0.00003510046,0.00008779402,0.0039685643],"genre_scores_gemma":[0.000018083036,0.9893596,0.002863878,0.0019042917,0.0027272357,0.00010274092,0.00034023428,0.00012156426,0.0025623383],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9966172,0.00010578485,0.0012872972,0.00090845703,0.0004569481,0.0006243165],"domain_scores_gemma":[0.99824303,0.0004050849,0.00039574626,0.0005573195,0.00007673375,0.00032209998],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011180714,0.0006380565,0.0024945785,0.000925224,0.00021910273,0.00002479334,0.00033442676,0.00013428969,0.0005305429],"category_scores_gemma":[0.0010904524,0.0004875392,0.00027405238,0.00082285365,0.00048008803,0.000071573086,0.00022967704,0.0013360169,0.000007775118],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007488172,0.000110713554,0.00001520114,0.01194988,0.000073728486,0.000394943,0.00026941163,3.4158867e-7,0.0000014687403,0.0012097815,0.030549811,0.95534986],"study_design_scores_gemma":[0.00044049873,0.00042393105,0.000004227583,0.06308415,0.0010429161,0.00064379175,0.00044382998,0.00094906526,3.5447442e-7,0.0003990418,0.9322307,0.00033747387],"about_ca_topic_score_codex":0.000016081096,"about_ca_topic_score_gemma":0.000002331637,"teacher_disagreement_score":0.9550124,"about_ca_system_score_codex":0.00019816372,"about_ca_system_score_gemma":0.0001857052,"threshold_uncertainty_score":0.99975765},"labels":[],"label_agreement":null},{"id":"W4412534866","doi":"10.1016/j.cgh.2025.06.034","title":"Artificial Intelligence and Endoscopist Diagnostic Agreement as a Framework for Colorectal Polyp Optical Diagnosis Implementation","year":2025,"lang":"en","type":"article","venue":"Clinical Gastroenterology and Hepatology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Fonds de Recherche du Québec - Santé","keywords":"Medicine; Colonoscopy; Colorectal Polyp; Colorectal cancer screening; General surgery; Gastroenterology; Radiology; Internal medicine; Medical physics; Colorectal cancer","score_opus":0.03480557981211141,"score_gpt":0.4247259466775459,"score_spread":0.38992036686543446,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412534866","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.864502,0.00025282003,0.098110005,0.03596426,0.0005920646,0.00049713376,0.0000063374596,0.000023198432,0.00005216164],"genre_scores_gemma":[0.97295153,0.0009212553,0.014189362,0.011492101,0.00017329164,0.00022248851,0.000027179674,0.000009227593,0.000013590066],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9982399,0.0001641145,0.0006822575,0.00046041526,0.00006734264,0.00038598455],"domain_scores_gemma":[0.9953181,0.0041869674,0.000105162406,0.0001295926,0.000049724993,0.0002104603],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00058979704,0.00015293223,0.000551564,0.000098040975,0.00013471152,0.000018668241,0.000075126365,0.00022937368,0.00009139179],"category_scores_gemma":[0.0040390547,0.00013736461,0.00009649916,0.00005659832,0.00083263294,0.000023335506,0.00012100484,0.0005406336,0.000006220216],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001073421,0.00023149377,0.86796004,0.00006093021,0.00013757193,0.00004157808,0.000041382817,5.06955e-7,0.000014287561,0.051416025,0.00039728705,0.07862547],"study_design_scores_gemma":[0.0023027689,0.009403687,0.8876716,0.00021646236,0.0007742867,0.0003357537,0.00038001136,0.003483868,0.00036287738,0.092583284,0.0023197883,0.0001656037],"about_ca_topic_score_codex":0.000038689428,"about_ca_topic_score_gemma":0.000105949635,"teacher_disagreement_score":0.10844949,"about_ca_system_score_codex":0.00002321922,"about_ca_system_score_gemma":0.000076262084,"threshold_uncertainty_score":0.5601566},"labels":[],"label_agreement":null},{"id":"W4412608495","doi":"10.70389/pjc.100010","title":"Radiomics-Based Diagnosis in Cardiology: Advances and Prospects","year":2025,"lang":"en","type":"article","venue":"Premier Journal of Cardiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Radiomics; Medicine; Medical physics; Cardiology; Internal medicine; Radiology","score_opus":0.007589103278724601,"score_gpt":0.29973692934904445,"score_spread":0.29214782607031986,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412608495","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9259141,0.04131839,0.014050547,0.009411633,0.0010562945,0.0002850014,0.0000018887272,0.000018155435,0.007943997],"genre_scores_gemma":[0.9913119,0.0043808767,0.0029756522,0.0008891831,0.00037582064,0.000012674863,0.0000014992386,0.00001001182,0.000042387255],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99885744,0.00018825037,0.00043165093,0.00017785486,0.00011441334,0.00023039112],"domain_scores_gemma":[0.99909675,0.0003986025,0.00014743226,0.00014080075,0.000108368426,0.000108018634],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00095694506,0.0001226912,0.00085457944,0.0003703131,0.000034143894,0.000009630322,0.000108086315,0.00012362907,0.0000042163665],"category_scores_gemma":[0.0011972559,0.00009597271,0.00015645805,0.00018031002,0.00022130611,0.000062832536,0.00003597456,0.00067456916,5.807937e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023986884,0.000013763667,0.96328735,0.00012529903,0.00017161446,0.0005019578,0.00004258482,0.0024124808,0.00056183984,0.00020070019,0.0015187613,0.030923752],"study_design_scores_gemma":[0.0099986475,0.0007435212,0.71889544,0.0009379835,0.0005752468,0.0034124514,0.00012394687,0.0030662601,0.0010347656,0.005378991,0.25556448,0.00026826622],"about_ca_topic_score_codex":0.000003480328,"about_ca_topic_score_gemma":7.614606e-7,"teacher_disagreement_score":0.25404572,"about_ca_system_score_codex":0.0001205065,"about_ca_system_score_gemma":0.00019022624,"threshold_uncertainty_score":0.39136535},"labels":[],"label_agreement":null},{"id":"W4412615448","doi":"10.3390/jor5030011","title":"Nomogram Based on the Most Relevant Clinical, CT, and Radiomic Features, and a Machine Learning Model to Predict EGFR Mutation Status in Non-Small Cell Lung Cancer","year":2025,"lang":"en","type":"article","venue":"Journal of Respiration","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec en Outaouais","funders":"","keywords":"Nomogram; Lung cancer; Radiomics; Mutation; Medicine; Cancer; Computer science; Machine learning; Artificial intelligence; Oncology; Internal medicine; Biology; Genetics; Gene","score_opus":0.015423155534777121,"score_gpt":0.324090044451944,"score_spread":0.30866688891716687,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412615448","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9590186,0.0015147562,0.028998429,0.009686651,0.00013775864,0.00040314486,0.000002716984,0.000008451958,0.00022952052],"genre_scores_gemma":[0.9908425,0.00080963667,0.0040312973,0.0039120377,0.00011877853,0.000010408745,0.0000060417806,0.000014842779,0.00025445945],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987149,0.0001860743,0.00052880775,0.00017422684,0.00023289963,0.0001630379],"domain_scores_gemma":[0.9989631,0.00040597495,0.00027515346,0.00010536033,0.00010275442,0.00014761798],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016891033,0.00011660437,0.00028868407,0.0003265081,0.000113016315,0.00005286054,0.00005894137,0.000047852198,0.000004424728],"category_scores_gemma":[0.0012516514,0.00007760026,0.000052174957,0.00024055131,0.000051040162,0.00006484618,0.000021388869,0.0010086569,1.7181968e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015582746,0.00021239962,0.55827695,0.0002761117,0.000073473006,0.00021628506,0.0007189971,0.325877,0.0055076624,0.000052925774,0.003950595,0.1032793],"study_design_scores_gemma":[0.002900577,0.0005288512,0.09268844,0.00063883467,0.000108392625,0.000043421827,0.000045681045,0.90138566,0.00015386844,0.000030354196,0.001412012,0.000063874686],"about_ca_topic_score_codex":0.00020275246,"about_ca_topic_score_gemma":0.00006847242,"teacher_disagreement_score":0.57550865,"about_ca_system_score_codex":0.000121774676,"about_ca_system_score_gemma":0.00033604237,"threshold_uncertainty_score":0.43821687},"labels":[],"label_agreement":null},{"id":"W4412635260","doi":"10.1016/j.jmir.2025.102067","title":"The many hats of MRTs","year":2025,"lang":"en","type":"editorial","venue":"Journal of medical imaging and radiation sciences","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Government of Nova Scotia","funders":"","keywords":"Psychology","score_opus":0.007251667924619991,"score_gpt":0.3469780636284746,"score_spread":0.3397263957038546,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412635260","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002254766,0.06410922,0.0027055186,0.11950034,0.80944324,0.00013924667,0.0000054768466,0.000015258248,0.001826969],"genre_scores_gemma":[0.02355483,0.118108824,0.0015361441,0.0016264833,0.853348,0.0000032347016,0.0000130541275,0.000026552409,0.0017828683],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99526507,0.00014455005,0.00082643045,0.00018238582,0.0033635302,0.00021802106],"domain_scores_gemma":[0.99503684,0.0032580371,0.00088371674,0.0001277153,0.00040023745,0.00029344848],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.007270104,0.00013881976,0.0005116805,0.0003157679,0.0002952107,0.00013719831,0.0004975089,0.00020493144,0.000024581737],"category_scores_gemma":[0.022123648,0.00007348327,0.00015114907,0.00030679896,0.0012221306,0.00011390079,0.00007888519,0.0014736609,5.7923995e-7],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018543924,0.00002164837,0.00085740443,0.000093114875,0.00004362497,0.00003899242,0.00009628199,0.0000043592763,0.0000092247765,0.00013396156,0.7905151,0.2081677],"study_design_scores_gemma":[0.00092837465,0.00010655224,0.0007464175,0.0013802977,0.00015946962,0.00014954142,0.0004065218,0.012445206,0.0000142485915,0.00036639784,0.9832231,0.00007391475],"about_ca_topic_score_codex":0.000038113118,"about_ca_topic_score_gemma":8.8085926e-7,"teacher_disagreement_score":0.20809378,"about_ca_system_score_codex":0.00004205948,"about_ca_system_score_gemma":0.0022475026,"threshold_uncertainty_score":0.9861134},"labels":[],"label_agreement":null},{"id":"W4412642899","doi":"10.1007/s13246-025-01594-2","title":"An approach for cancer outcomes modelling using a comprehensive synthetic dataset","year":2025,"lang":"en","type":"article","venue":"Physical and Engineering Sciences in Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Surrey Place Centre; Surrey Memorial Hospital; BC Cancer Agency; Spinal Cord Injury BC; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Cancer; Data science; Medicine; Internal medicine","score_opus":0.04469666597854108,"score_gpt":0.37709343449025445,"score_spread":0.3323967685117134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412642899","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6585048,0.000567136,0.33877176,0.0016575212,0.00015442065,0.00022425092,0.000012579733,0.00003171271,0.0000758625],"genre_scores_gemma":[0.9630585,0.000056234385,0.035908323,0.0007302165,0.0001642553,0.000028402557,0.00003354303,0.000008890678,0.000011652137],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990873,0.000012481219,0.000164851,0.00031603762,0.00017531004,0.00024402779],"domain_scores_gemma":[0.9995351,0.00019904887,0.00002453848,0.00012809208,0.000024169336,0.000089062196],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027746707,0.00013090728,0.000397139,0.00018258071,0.000088233915,0.000015960173,0.00011734969,0.000027133156,0.0000018095158],"category_scores_gemma":[0.00011389193,0.000088638415,0.000026040309,0.0003217243,0.00030117665,0.00008088256,0.000027917102,0.00020250524,7.1033185e-8],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026557647,0.00014233444,0.006496726,0.00053566834,0.00003862886,0.0000044532576,0.0005413926,0.9700317,0.012221954,0.0034829343,0.00011154904,0.0063661267],"study_design_scores_gemma":[0.00070255814,0.00008182438,0.0020265183,0.00034814453,0.00006822636,0.00000560508,0.00015644918,0.9954635,0.000046239493,0.00030067988,0.0007119299,0.00008835576],"about_ca_topic_score_codex":0.0003260524,"about_ca_topic_score_gemma":5.6573214e-7,"teacher_disagreement_score":0.30455372,"about_ca_system_score_codex":0.000030857653,"about_ca_system_score_gemma":0.000038778307,"threshold_uncertainty_score":0.36145696},"labels":[],"label_agreement":null},{"id":"W4412691645","doi":"10.21203/rs.3.rs-7125712/v1","title":"Multi-Class Segmentation in 2D Chest CT using Deep Learning","year":2025,"lang":"en","type":"preprint","venue":"Research Square","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Class (philosophy); Segmentation; Artificial intelligence; Deep learning; Computer science; Radiology; Medicine","score_opus":0.07689452307059862,"score_gpt":0.45965886688238533,"score_spread":0.3827643438117867,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412691645","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97742426,0.0024065103,0.011545052,0.002604838,0.0004941752,0.002030576,0.000011861793,0.00016537862,0.0033173503],"genre_scores_gemma":[0.9715295,0.0010751382,0.023085,0.00016016878,0.00040097375,0.00013816892,0.00036071404,0.00006973323,0.003180601],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961989,0.0008404309,0.00049182517,0.0007473218,0.0009687398,0.000752776],"domain_scores_gemma":[0.99833405,0.00047038333,0.000119660355,0.00046877057,0.00033951187,0.00026763027],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0031118474,0.0002740833,0.0005693698,0.0011967437,0.00023635985,0.00014202729,0.00028505723,0.00022894738,0.00013271807],"category_scores_gemma":[0.0033303688,0.00026782966,0.00016668433,0.00069600093,0.00019089637,0.00006455589,0.0008425187,0.0065394267,0.00002699645],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030576123,0.0010095857,0.56643826,0.014689952,0.0003187908,0.0022458213,0.0042876475,0.13786732,0.016987702,0.00015725294,0.0004982681,0.25519365],"study_design_scores_gemma":[0.0020414866,0.000096604635,0.043472107,0.0054098256,0.000050035265,0.000035383408,0.0014195536,0.9427452,0.00044593128,0.00012362227,0.003908593,0.00025165753],"about_ca_topic_score_codex":0.002219526,"about_ca_topic_score_gemma":0.000102451726,"teacher_disagreement_score":0.8048779,"about_ca_system_score_codex":0.0010786022,"about_ca_system_score_gemma":0.0007571398,"threshold_uncertainty_score":0.9999774},"labels":[],"label_agreement":null},{"id":"W4412714393","doi":"10.2139/ssrn.5358219","title":"Volumetric 3d Reconstruction from 2d Ultrasound Images: Comparison between Raw Rf and Pixel Interpolation","year":2025,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Carleton University","funders":"","keywords":"Interpolation (computer graphics); Pixel; Computer vision; Ultrasound; Artificial intelligence; Raw data; Computer science; Computer graphics (images); Image (mathematics); Radiology; Medicine","score_opus":0.010022914823671904,"score_gpt":0.29664648182497566,"score_spread":0.28662356700130376,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412714393","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6800064,0.016274538,0.2972526,0.0021429237,0.0016340076,0.0004355601,0.000030186113,0.000105416424,0.0021183714],"genre_scores_gemma":[0.97938836,0.010903522,0.006017206,0.00015815833,0.0019074709,0.0000068147356,0.00024059894,0.000040983807,0.0013368995],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99683267,0.0001945064,0.0008117968,0.000537939,0.00041204324,0.0012110263],"domain_scores_gemma":[0.99826145,0.00042583948,0.0006198908,0.00031201224,0.00016317566,0.00021763437],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0017825995,0.0003573405,0.00086321845,0.0006913571,0.0002409223,0.00020549617,0.00024300235,0.0003854521,0.0000559921],"category_scores_gemma":[0.0010482037,0.00033495735,0.00021399643,0.0002768361,0.00015707515,0.00012650888,0.00017651838,0.010576489,0.0000070892543],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015023653,0.00008113933,0.45550117,0.00014462379,0.0014724723,0.000005636234,0.00040136089,0.0001042685,0.0018127086,0.00027392147,0.00080015976,0.5392523],"study_design_scores_gemma":[0.01713891,0.0024014083,0.39166406,0.010019198,0.011082028,0.007225035,0.008294503,0.12639654,0.0007064234,0.4085869,0.013162001,0.0033230206],"about_ca_topic_score_codex":0.000803261,"about_ca_topic_score_gemma":0.000076690034,"teacher_disagreement_score":0.53592926,"about_ca_system_score_codex":0.0012329714,"about_ca_system_score_gemma":0.0020488414,"threshold_uncertainty_score":0.99991024},"labels":[],"label_agreement":null},{"id":"W4412726117","doi":"10.3390/brainsci15070730","title":"Diagnostic, Therapeutic, and Prognostic Applications of Artificial Intelligence (AI) in the Clinical Management of Brain Metastases (BMs)","year":2025,"lang":"en","type":"review","venue":"Brain Sciences","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Artificial intelligence; Medicine; Medical physics; Computer science","score_opus":0.10057502105531826,"score_gpt":0.4775187714127895,"score_spread":0.3769437503574712,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412726117","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00005093705,0.9772885,0.013467572,0.006267736,0.000084340645,0.0020588927,0.000013793221,0.000010108001,0.0007581284],"genre_scores_gemma":[0.001197682,0.9939796,0.0033473435,0.0010839249,0.000068427915,0.0002340373,0.000016834105,0.0000075542494,0.000064618645],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99745065,0.0005215962,0.0010013964,0.0004041486,0.0004304729,0.00019171117],"domain_scores_gemma":[0.98584014,0.013417099,0.0003392338,0.00030649727,0.000042311378,0.00005470026],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0054478426,0.00017203348,0.0009355039,0.00027820177,0.000077244455,0.00003591183,0.00053611805,0.00007778952,0.0000147602095],"category_scores_gemma":[0.0034559704,0.00009828908,0.00018864466,0.001210765,0.0014170005,0.00003338021,0.00012633078,0.00040195146,0.0000020314899],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000023321124,0.00016488352,0.00032278965,0.0066159237,0.00006176575,0.000009586086,0.000060947725,0.000002060375,2.2635378e-7,0.023934357,0.00030896394,0.9685162],"study_design_scores_gemma":[0.00018557483,0.00042652112,0.0019029458,0.02524828,0.0018305683,0.000056077835,0.0010654865,0.0008167386,0.0000023206187,0.010336861,0.9578563,0.00027234218],"about_ca_topic_score_codex":0.000021945914,"about_ca_topic_score_gemma":0.00000531191,"teacher_disagreement_score":0.96824384,"about_ca_system_score_codex":0.000009588589,"about_ca_system_score_gemma":0.0002931664,"threshold_uncertainty_score":0.52209973},"labels":[],"label_agreement":null},{"id":"W4412726544","doi":"10.3390/cancers17142386","title":"CT-Based Radiomics for a priori Predicting Response to Chemoradiation in Locally Advanced Lung Adenocarcinoma","year":2025,"lang":"en","type":"article","venue":"Cancers","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Health Sciences Centre; Sunnybrook Health Science Centre","funders":"Natural Sciences and Engineering Research Council of Canada; Terry Fox Foundation","keywords":"Radiomics; A priori and a posteriori; Medicine; Adenocarcinoma; Chemoradiotherapy; Radiology; Oncology; Internal medicine; Radiation therapy; Cancer","score_opus":0.00682544064939506,"score_gpt":0.3031169995775362,"score_spread":0.29629155892814113,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412726544","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9344154,0.0008109305,0.053492527,0.009197263,0.00050919066,0.0011461894,0.000007116779,0.00007638639,0.00034497757],"genre_scores_gemma":[0.98196983,0.000016033033,0.012008229,0.005141593,0.00011945855,0.00020421545,0.000019962312,0.000027544973,0.00049310306],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988559,0.00004606398,0.00029713643,0.00033277218,0.0001513969,0.00031674016],"domain_scores_gemma":[0.9991476,0.0003246149,0.00006890968,0.00022774075,0.000070514776,0.00016064677],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00068264804,0.00013401674,0.00029291603,0.00032385119,0.00006894703,0.000020385929,0.000110004796,0.00004748237,0.0000073667197],"category_scores_gemma":[0.002142365,0.00013996533,0.00007235438,0.0004970089,0.00004381536,0.00004837844,0.000019100326,0.00026704516,0.000001310823],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.025909087,0.00008693823,0.35907304,0.0015468567,0.00017657816,0.00023375795,0.0019261509,0.2987743,0.057381965,0.00043054423,0.012927492,0.2415333],"study_design_scores_gemma":[0.009901935,0.000270534,0.05924704,0.0010549997,0.00008517704,0.000010993299,0.00023698751,0.905038,0.0038509108,0.000042162435,0.020062307,0.00019896838],"about_ca_topic_score_codex":0.000104728475,"about_ca_topic_score_gemma":0.000016970926,"teacher_disagreement_score":0.6062637,"about_ca_system_score_codex":0.002636035,"about_ca_system_score_gemma":0.0019192781,"threshold_uncertainty_score":0.68931395},"labels":[],"label_agreement":null},{"id":"W4412740637","doi":"10.1038/s41598-025-12451-3","title":"Measured intrapatient radiomic variability as a predictor of treatment response in multi-metastatic soft tissue sarcoma patients","year":2025,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto","funders":"National Cancer Institute; Sarcoma Alliance for Research through Collaboration","keywords":"Medicine; Sarcoma; Soft tissue sarcoma; Biopsy; Oncology; Pathology","score_opus":0.014660554280232795,"score_gpt":0.30984508653145854,"score_spread":0.29518453225122576,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412740637","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9924869,0.00012472487,0.0023479601,0.00042276664,0.0030411044,0.0012778288,0.0000064486453,0.00004930374,0.00024294831],"genre_scores_gemma":[0.993979,0.0000046923114,0.0040722876,0.00007122635,0.00001288475,0.00006261007,0.00008936035,0.00001694247,0.0016910168],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.996686,0.00044864792,0.0011157385,0.00080958626,0.00058106333,0.00035897738],"domain_scores_gemma":[0.9978899,0.00029752692,0.0003496025,0.0009783735,0.0002743041,0.00021032963],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004235465,0.00021541391,0.0005874645,0.0005899337,0.00011334594,0.000050102244,0.0001146243,0.00007213901,0.00007603418],"category_scores_gemma":[0.007150058,0.00017324845,0.00013147894,0.0008125627,0.00042957385,0.00007715877,0.00006251246,0.00022198453,0.000005245352],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022192672,0.004528573,0.85581875,0.0003815941,0.0002238886,0.0007683145,0.0029608957,0.00047821243,0.081647724,0.00004432351,0.0017129887,0.049215447],"study_design_scores_gemma":[0.013491814,0.0029116184,0.8711007,0.0014441446,0.00053890905,0.00027893108,0.00023580916,0.037847083,0.0330157,0.0040651397,0.034533758,0.00053636834],"about_ca_topic_score_codex":0.00025276304,"about_ca_topic_score_gemma":0.0000126959885,"teacher_disagreement_score":0.04867908,"about_ca_system_score_codex":0.00064765767,"about_ca_system_score_gemma":0.0011256011,"threshold_uncertainty_score":0.8559804},"labels":[],"label_agreement":null},{"id":"W4412750724","doi":"10.3390/curroncol32080431","title":"A Multimodal MRI-Based Model for Colorectal Liver Metastasis Prediction: Integrating Radiomics, Deep Learning, and Clinical Features with SHAP Interpretation","year":2025,"lang":"en","type":"article","venue":"Current Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Artificial intelligence; Deep learning; Radiomics; Medicine; Feature selection; Machine learning; Lasso (programming language); Interpretability; Computer science","score_opus":0.032012648137387,"score_gpt":0.4055186854596705,"score_spread":0.3735060373222835,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412750724","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16985303,0.0019987803,0.8239185,0.0020289475,0.0007950749,0.00081431743,0.000012619204,0.0001123413,0.000466357],"genre_scores_gemma":[0.9311036,0.0003968843,0.0672742,0.000488724,0.00023490189,0.00013576221,0.00016373296,0.000025933728,0.00017629046],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985708,0.00018769955,0.00042429136,0.00043831574,0.00013021575,0.00024867998],"domain_scores_gemma":[0.9986003,0.00077644753,0.00017526418,0.000100468205,0.00019455158,0.00015299245],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007284864,0.00018973667,0.00051781145,0.00018970006,0.00016123238,0.000032014617,0.0000809546,0.00016832919,0.000013933964],"category_scores_gemma":[0.0014563455,0.00014603949,0.00014066855,0.0001300802,0.0003298471,0.00005878443,0.00004521203,0.0010325629,8.6561766e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0027593547,0.0005490988,0.1423944,0.00033435688,0.00034408493,0.000015344378,0.000919698,0.0049725696,0.00009993911,0.00058684894,0.0021485458,0.84487575],"study_design_scores_gemma":[0.005338094,0.0014357191,0.009535256,0.00028218603,0.00059737876,0.00004427023,0.00019462222,0.9715965,0.000024949371,0.000072194875,0.01076617,0.00011269801],"about_ca_topic_score_codex":0.000010949551,"about_ca_topic_score_gemma":0.000074236734,"teacher_disagreement_score":0.9666239,"about_ca_system_score_codex":0.00018135486,"about_ca_system_score_gemma":0.00034160377,"threshold_uncertainty_score":0.5955317},"labels":[],"label_agreement":null},{"id":"W4412795318","doi":"10.1186/s13244-025-02009-2","title":"An interpretable CT-based machine learning model for predicting recurrence risk in stage II colorectal cancer","year":2025,"lang":"en","type":"article","venue":"Insights into Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Minnow Environmental (Canada)","funders":"National Natural Science Foundation of China","keywords":"Medicine; Stage (stratigraphy); Neuroradiology; Colorectal cancer; Internal medicine; Logistic regression; Oncology; Machine learning; Artificial intelligence; Radiology; Cancer; Neurology; Computer science","score_opus":0.009096821227558605,"score_gpt":0.31519670682055234,"score_spread":0.3060998855929937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412795318","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.74231124,0.0019988813,0.25223926,0.0011032859,0.00041414142,0.00054844504,0.000011670099,0.00019846644,0.0011746234],"genre_scores_gemma":[0.9826561,0.0001423103,0.015121665,0.0010344555,0.000100834615,0.00017545673,0.000064475826,0.00004999468,0.00065469736],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99794877,0.0001371035,0.00053072866,0.0006356572,0.00025785863,0.0004898743],"domain_scores_gemma":[0.9989175,0.00028255474,0.00020236669,0.00027630044,0.00014451952,0.00017671532],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00074927247,0.0002853989,0.00047769837,0.0005123591,0.0005199601,0.000087067434,0.00025623178,0.000053270473,0.0000315256],"category_scores_gemma":[0.0012570294,0.0002552327,0.00011496286,0.00041838587,0.00015813418,0.00031640276,0.00011087208,0.0012944872,0.0000011143475],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040318782,0.0002557362,0.6479507,0.0003629143,0.00006735566,0.00005588933,0.0046253214,0.2144873,0.013644191,0.00034887658,0.0001793514,0.117619194],"study_design_scores_gemma":[0.0023941263,0.00011681941,0.0025695811,0.0011195475,0.00009768317,0.0000048216584,0.00020225452,0.98544466,0.0028190878,0.0007030061,0.0042906664,0.00023772675],"about_ca_topic_score_codex":0.0034280801,"about_ca_topic_score_gemma":0.00052461826,"teacher_disagreement_score":0.7709574,"about_ca_system_score_codex":0.00036181379,"about_ca_system_score_gemma":0.00046036954,"threshold_uncertainty_score":0.99999},"labels":[],"label_agreement":null},{"id":"W4412805201","doi":"10.1016/j.compmedimag.2025.102615","title":"IgCONDA-PET: Weakly-supervised PET anomaly detection using implicitly-guided attention-conditional counterfactual diffusion modeling — a multi-center, multi-cancer, and multi-tracer study","year":2025,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; BC Cancer Agency","funders":"Canadian Institutes of Health Research","keywords":"Computer science; Artificial intelligence; Anomaly detection; Thresholding; Deep learning; Pattern recognition (psychology); Ground truth; Autoencoder; Machine learning; Image (mathematics)","score_opus":0.028991514474840444,"score_gpt":0.3455330713684343,"score_spread":0.31654155689359387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412805201","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5868048,0.0007405312,0.41016212,0.0011768542,0.0005175155,0.00044846116,0.000014401472,0.0001315641,0.0000037307404],"genre_scores_gemma":[0.97450036,0.0008711728,0.021777436,0.0023551327,0.00022950544,0.000046616093,0.0000758862,0.000053580177,0.00009031635],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969425,0.00018828706,0.0008033136,0.00088695844,0.00064179784,0.0005371011],"domain_scores_gemma":[0.9985549,0.00017045304,0.00016181378,0.00030443064,0.00025998458,0.00054844853],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00080110464,0.0004545711,0.0007501034,0.00052722904,0.0006214163,0.00018995829,0.00019304482,0.00011559101,0.000027753136],"category_scores_gemma":[0.00032862826,0.0004072604,0.00017144381,0.0003749715,0.00043953638,0.00021519214,0.0003169814,0.0011136981,0.0000012689427],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010096167,0.012499956,0.6422616,0.0018444516,0.0018063878,0.001824708,0.002668663,0.00086279114,0.12364737,0.00014229884,0.00038403153,0.21104811],"study_design_scores_gemma":[0.024248846,0.00007800079,0.033979006,0.0009346826,0.00029627184,0.000888021,0.0004126537,0.93849516,0.000029426274,0.000031050553,0.00027616892,0.00033074114],"about_ca_topic_score_codex":0.00080722675,"about_ca_topic_score_gemma":0.00005658588,"teacher_disagreement_score":0.9376323,"about_ca_system_score_codex":0.000089978406,"about_ca_system_score_gemma":0.00019225222,"threshold_uncertainty_score":0.99983793},"labels":[],"label_agreement":null},{"id":"W4412810793","doi":"10.12771/emj.2025.00661","title":"The TRIPOD-LLM reporting guideline for studies using large language models: a Korean translation","year":2025,"lang":"en","type":"article","venue":"The Ewha Medical Journal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Center for Advancing Translational Sciences; National Institute of Biomedical Imaging and Bioengineering; National Institutes of Health; National Cancer Institute; National Heart, Lung, and Blood Institute; Fogarty International Center","keywords":"Tripod (photography); Guideline; Translation (biology); Medicine; Natural language processing; Computer science; Engineering; Chemistry; Pathology","score_opus":0.07265662481684229,"score_gpt":0.4402732007668354,"score_spread":0.3676165759499931,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412810793","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08305654,0.030786162,0.71776986,0.16517565,0.0014200681,0.0005074144,0.0000026191674,0.00006554619,0.0012161309],"genre_scores_gemma":[0.9215605,0.005889295,0.041326288,0.02247451,0.0064553767,0.000042991946,0.00003543337,0.00009259384,0.0021229782],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99683774,0.0001855125,0.0016396362,0.00016837314,0.0007498132,0.00041891893],"domain_scores_gemma":[0.99749994,0.001052911,0.00072284276,0.00025258842,0.00026288902,0.0002088118],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.013779439,0.00014505698,0.00039759016,0.00008524739,0.0009995926,0.000075089556,0.00026359744,0.00009058321,0.0000249956],"category_scores_gemma":[0.017046655,0.00006796431,0.0002443715,0.00021068862,0.00021762491,0.00007601003,0.00005917855,0.0011335613,7.0764054e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005210229,0.0001919419,0.00040170606,0.00017971346,0.0010730498,0.00039883718,0.0059119877,0.0009876654,0.0019426402,0.0035633952,0.032278042,0.95255],"study_design_scores_gemma":[0.003108595,0.00008734711,0.000056442175,0.0009090024,0.00046379905,0.001328683,0.006286908,0.9110564,0.000100261524,0.010569554,0.06592918,0.00010385374],"about_ca_topic_score_codex":0.000019203535,"about_ca_topic_score_gemma":0.000011555635,"teacher_disagreement_score":0.95244616,"about_ca_system_score_codex":0.00009477551,"about_ca_system_score_gemma":0.00048541313,"threshold_uncertainty_score":0.99123317},"labels":[],"label_agreement":null},{"id":"W4412851049","doi":"10.1016/j.ajt.2025.07.998","title":"Importance of Data Granularity in Using eGFR Slope as a Surrogate for DCGF","year":2025,"lang":"en","type":"article","venue":"American Journal of Transplantation","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Providence Health Care; University of British Columbia","funders":"","keywords":"Medicine; Granularity; Surrogate endpoint; Internal medicine; Computer science","score_opus":0.02636729163820758,"score_gpt":0.3760027531355344,"score_spread":0.3496354614973268,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412851049","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.907999,0.00019120047,0.08999082,0.0014924252,0.00008659339,0.000110910776,0.0000150247115,0.0000029683586,0.000111048976],"genre_scores_gemma":[0.96253014,0.00043366294,0.036536645,0.00041571553,0.00003554582,6.85896e-7,0.000031830295,0.0000068774957,0.000008882909],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99912304,0.000049899547,0.0004570828,0.0001068007,0.00015687711,0.00010628778],"domain_scores_gemma":[0.9992292,0.00015800701,0.0003303528,0.00013476588,0.00009798169,0.000049697013],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007470443,0.000063969324,0.00032643141,0.0001941663,0.000021576669,0.0000073484366,0.00014190485,0.000016800492,0.0000045452825],"category_scores_gemma":[0.00016472257,0.000055453253,0.00005816641,0.0002676164,0.00010658692,0.00014073418,0.0000062597023,0.00020848057,1.0299599e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005211231,0.00040131062,0.6874739,0.0011237413,0.0003516692,0.00038371564,0.0016451747,0.0014581913,0.04446854,0.00050891534,0.00011821847,0.2568554],"study_design_scores_gemma":[0.023317441,0.002773885,0.78178424,0.00854541,0.0030287018,0.0032643904,0.0022325343,0.16052201,0.008145586,0.0034854782,0.00238404,0.0005162962],"about_ca_topic_score_codex":0.00028950698,"about_ca_topic_score_gemma":0.000027696926,"teacher_disagreement_score":0.2563391,"about_ca_system_score_codex":0.000034664103,"about_ca_system_score_gemma":0.00021690066,"threshold_uncertainty_score":0.2261318},"labels":[],"label_agreement":null},{"id":"W4412881735","doi":"10.21203/rs.3.rs-7173744/v1","title":"Enhancing Medical Images Quality Using Vision Transformer Framework","year":2025,"lang":"en","type":"preprint","venue":"Research Square","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Artificial intelligence; Convolutional neural network; Computer vision; Image quality; Medical imaging; Encoder; Peak signal-to-noise ratio; Transformer; Deep learning; Pattern recognition (psychology); Image (mathematics); Engineering","score_opus":0.06431224867487524,"score_gpt":0.5248664174589434,"score_spread":0.46055416878406813,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412881735","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42861697,0.01010825,0.4733644,0.054579664,0.002456343,0.003695105,0.00015136036,0.0005841672,0.026443722],"genre_scores_gemma":[0.94497293,0.0039468626,0.04377505,0.0015030866,0.0025113537,0.00012189817,0.00026176655,0.00012584834,0.0027811897],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.9915139,0.0012278545,0.00092771236,0.001043139,0.0042046187,0.0010827606],"domain_scores_gemma":[0.99504054,0.0021385842,0.00012659517,0.0010629228,0.00074312126,0.0008882232],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.010344671,0.0003896856,0.0010314096,0.0007788875,0.00042848752,0.00019090448,0.0006142215,0.0012135344,0.0013617964],"category_scores_gemma":[0.015172578,0.00032847145,0.0004625496,0.00067715265,0.000584767,0.00007916353,0.00078568317,0.011485031,0.000039525807],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0023562012,0.0035796384,0.063507855,0.09924071,0.002083257,0.003841849,0.008814704,0.0014580436,0.044804767,0.013779112,0.021995598,0.73453826],"study_design_scores_gemma":[0.012226786,0.0022922114,0.10014953,0.38921392,0.0012765134,0.000600031,0.006490197,0.25480872,0.041214593,0.078691825,0.108058475,0.0049771774],"about_ca_topic_score_codex":0.001391977,"about_ca_topic_score_gemma":0.000024575333,"teacher_disagreement_score":0.7295611,"about_ca_system_score_codex":0.00054480555,"about_ca_system_score_gemma":0.0031055806,"threshold_uncertainty_score":0.99991673},"labels":[],"label_agreement":null},{"id":"W4412939140","doi":"10.1186/s12880-025-01855-2","title":"Open-radiomics: a collection of standardized datasets and a technical protocol for reproducible radiomics machine learning pipelines","year":2025,"lang":"en","type":"article","venue":"BMC Medical Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"SickKids Foundation; Vector Institute; Mental Health Research Canada; University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"Radiomics; Computer science; Protocol (science); Pipeline transport; Open source; Medical physics; Machine learning; Artificial intelligence; Medicine; Software; Operating system; Engineering; Pathology","score_opus":0.024068033846008134,"score_gpt":0.38666837058319325,"score_spread":0.3626003367371851,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412939140","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0077315657,0.0010095943,0.842224,0.018931493,0.00053955236,0.12512916,0.00011527655,0.00042404223,0.0038953002],"genre_scores_gemma":[0.0899587,0.000675541,0.7128764,0.008876371,0.0017349,0.17949955,0.0014766953,0.00039772628,0.00450415],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969931,0.00021299713,0.0009434001,0.00086413464,0.0005642458,0.0004220956],"domain_scores_gemma":[0.997573,0.0009870678,0.0002867269,0.0005904686,0.00020481372,0.00035791157],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0043915403,0.0002750718,0.00090702286,0.00037951302,0.0002871158,0.000113093454,0.0004427164,0.00014581246,0.000092285416],"category_scores_gemma":[0.019591361,0.00023088425,0.00014153836,0.0005860855,0.0004555091,0.0001771212,0.0005438419,0.0008016531,9.151572e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.015198753,0.0018356772,0.35559675,0.011692867,0.0005512407,0.00019333609,0.0003585888,0.00020100229,0.036286056,0.0044297613,0.21514148,0.3585145],"study_design_scores_gemma":[0.03673453,0.00039736592,0.004196064,0.0043274593,0.00042612763,0.0011256465,0.00015016025,0.64580244,0.004107646,0.0019048292,0.3003097,0.0005180433],"about_ca_topic_score_codex":0.00022722028,"about_ca_topic_score_gemma":0.000037286,"teacher_disagreement_score":0.64560145,"about_ca_system_score_codex":0.00013426386,"about_ca_system_score_gemma":0.0013347233,"threshold_uncertainty_score":0.988667},"labels":[],"label_agreement":null},{"id":"W4413006740","doi":"10.1148/ryai.240777","title":"Segmenting Whole-Body MRI and CT for Multiorgan Anatomic Structure Delineation","year":2025,"lang":"en","type":"article","venue":"Radiology Artificial Intelligence","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Leibniz-Gemeinschaft; European Commission; Bundesministerium für Bildung und Forschung; Wilhelm Sander-Stiftung","keywords":"Medicine; Segmentation; Magnetic resonance imaging; Radiology; Artificial intelligence; Retrospective cohort study; Sørensen–Dice coefficient; Medical physics; Nuclear medicine; Computer science; Surgery; Image segmentation","score_opus":0.014852897436273691,"score_gpt":0.3371446896156106,"score_spread":0.3222917921793369,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413006740","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47181192,0.00035643132,0.5218209,0.00509206,0.00042108094,0.00034552152,0.0000074913282,0.000053035354,0.00009153073],"genre_scores_gemma":[0.98353314,0.000070152295,0.01436248,0.0013033983,0.0002670633,0.000016107178,0.000056873534,0.0000146431585,0.00037615394],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998869,0.00005563767,0.0003804203,0.00035661666,0.00007148247,0.0002668307],"domain_scores_gemma":[0.99929994,0.0002735204,0.00008281777,0.00016786743,0.00009447572,0.00008134566],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003627051,0.00014097123,0.00028854265,0.00017116408,0.00021075536,0.000028861043,0.0000912519,0.00009197265,0.00004850023],"category_scores_gemma":[0.0008923186,0.00012691761,0.000057702815,0.00017636667,0.00021864858,0.0000496018,0.000035923542,0.00033189723,0.0000070983974],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027809356,0.00008865225,0.02696873,0.00023300062,0.00020668992,0.00003749542,0.0004256404,0.0015765404,0.263247,0.04598583,0.001982471,0.6589698],"study_design_scores_gemma":[0.00033607654,0.0001596092,0.0040782928,0.00014518041,0.00019695425,0.00023288724,0.00047945403,0.8975403,0.07275604,0.013953934,0.0099020405,0.00021927817],"about_ca_topic_score_codex":0.00002153556,"about_ca_topic_score_gemma":0.000010391713,"teacher_disagreement_score":0.8959637,"about_ca_system_score_codex":0.00005285372,"about_ca_system_score_gemma":0.00007605122,"threshold_uncertainty_score":0.517555},"labels":[],"label_agreement":null},{"id":"W4413019803","doi":"10.1139/facets-2024-0229","title":"X-ray modalities in the era of artificial intelligence: overview of self-supervised learning approach","year":2025,"lang":"en","type":"article","venue":"FACETS","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Vector Institute; University of Toronto","funders":"","keywords":"Modalities; Artificial intelligence; Computer science; Machine learning; Sociology; Social science","score_opus":0.03564166638614795,"score_gpt":0.33045271831314094,"score_spread":0.294811051926993,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413019803","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9673158,0.0024373496,0.0149009125,0.0034181585,0.0001277489,0.00040745203,0.0000020143743,0.0000382369,0.011352308],"genre_scores_gemma":[0.9931384,0.00027046367,0.0059342575,0.00040997745,0.000037071943,0.000012621686,0.0000107730875,0.000007956405,0.00017848035],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988459,0.00017612644,0.00039930604,0.00015180642,0.0002648732,0.00016200062],"domain_scores_gemma":[0.9994593,0.00017023204,0.000080088,0.00020773364,0.000054238677,0.00002839006],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009241964,0.00009714418,0.000337327,0.00010953505,0.00003962573,0.000010990885,0.00017471875,0.00006248401,0.00004358674],"category_scores_gemma":[0.00040971724,0.00006684352,0.00008563948,0.0003885313,0.000104356295,0.000030802403,0.00004295104,0.00064889214,0.0000022802965],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035666936,0.002471326,0.098952174,0.0074808956,0.0005062879,0.000038109192,0.0644379,0.03753606,0.01508305,0.13809696,0.0012298152,0.63381076],"study_design_scores_gemma":[0.0010380046,0.00033198725,0.053337213,0.0017108073,0.00024305609,0.000019247718,0.015231459,0.9132408,0.0033410937,0.005643842,0.0055996426,0.0002628618],"about_ca_topic_score_codex":0.00015130344,"about_ca_topic_score_gemma":0.0000017811371,"teacher_disagreement_score":0.8757047,"about_ca_system_score_codex":0.00002139527,"about_ca_system_score_gemma":0.00010400275,"threshold_uncertainty_score":0.28191495},"labels":[],"label_agreement":null},{"id":"W4413021341","doi":"10.2214/ajr.25.33622","title":"Artificial Intelligence–Assisted MRI Interpretation in Prostate Cancer: Supporting Confidence and Reducing Variability","year":2025,"lang":"en","type":"letter","venue":"American Journal of Roentgenology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Women's College Hospital; Mount Sinai Hospital","funders":"","keywords":"Medicine; Prostate cancer; Interpretation (philosophy); Prostate; Cancer; Magnetic resonance imaging; Multiparametric MRI; Medical physics; Oncology; Radiology; Internal medicine","score_opus":0.011245672494288038,"score_gpt":0.32915076461518417,"score_spread":0.3179050921208961,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413021341","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1641859,0.0005713828,0.0197939,0.81380963,0.0010437972,0.00035974197,0.000008318689,0.000019035726,0.00020829472],"genre_scores_gemma":[0.85223126,0.0014366329,0.0066408617,0.13849495,0.0009864464,0.000015514219,0.00002788272,0.00003583814,0.00013058046],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9970042,0.0004819119,0.00141952,0.00037971066,0.0002836115,0.00043103952],"domain_scores_gemma":[0.997302,0.0005529385,0.0015594898,0.00021000186,0.0002704309,0.000105139115],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0014333319,0.0002349301,0.001114297,0.00062256464,0.000048269056,0.000032576907,0.00019550836,0.00015869353,0.000059716356],"category_scores_gemma":[0.0018730946,0.00020648018,0.0001307897,0.00038409425,0.00071867334,0.00006872649,0.00007208514,0.0033742315,7.1629825e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006066079,0.0000744404,0.018510252,0.0004765829,0.0003354749,0.0022640745,0.002085786,0.00050461886,0.00074662094,0.000060556922,0.014176072,0.9601589],"study_design_scores_gemma":[0.0072744493,0.0294138,0.09286574,0.058816478,0.0108317835,0.055157304,0.025532631,0.29559213,0.005292992,0.056273352,0.35688415,0.006065193],"about_ca_topic_score_codex":0.0007555623,"about_ca_topic_score_gemma":0.00001672867,"teacher_disagreement_score":0.9540937,"about_ca_system_score_codex":0.00028892004,"about_ca_system_score_gemma":0.0007641986,"threshold_uncertainty_score":0.99892503},"labels":[],"label_agreement":null},{"id":"W4413025114","doi":"10.1177/08465371251359867","title":"Radiomics for Early Pancreatic Cancer Detection: From Promise to Practice?","year":2025,"lang":"en","type":"letter","venue":"Canadian Association of Radiologists Journal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sinai Health System; Women's College Hospital; University of Toronto; University Health Network","funders":"","keywords":"Medicine; Radiomics; Pancreatic cancer; Medical physics; Cancer; Radiology; General surgery; Internal medicine","score_opus":0.012012152063557175,"score_gpt":0.29872685957572936,"score_spread":0.2867147075121722,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413025114","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0054721213,0.00091057864,0.0077588744,0.9791118,0.0040296502,0.001084021,0.000580004,0.000032765718,0.0010201973],"genre_scores_gemma":[0.0077093625,0.0012982348,0.018780492,0.92900234,0.01848242,0.0002126614,0.00046679773,0.00011799717,0.023929693],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973906,0.000301908,0.00076525117,0.00039410914,0.00047202595,0.0006760777],"domain_scores_gemma":[0.995567,0.001419792,0.0011895365,0.00028439832,0.0009404505,0.0005987808],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0013317377,0.0003078026,0.0009920697,0.0006876453,0.00025381963,0.0001277564,0.00030334463,0.001009337,0.000106419],"category_scores_gemma":[0.013813453,0.00029431077,0.0003645722,0.00028871687,0.000059187914,0.000102641396,0.000016588436,0.0030099435,0.00000721123],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011783337,0.000011563167,0.0068400903,0.00010889169,0.0011396488,0.00025296008,0.00020301116,0.00007130186,0.00007925794,0.0000054714465,0.9762546,0.014915411],"study_design_scores_gemma":[0.0016845446,0.00024218365,0.0056920946,0.00054330454,0.0011910903,0.00017897315,0.000029779856,0.0005655566,0.000038000173,0.00020907407,0.9893654,0.00025997436],"about_ca_topic_score_codex":0.031023476,"about_ca_topic_score_gemma":0.0050202664,"teacher_disagreement_score":0.050109446,"about_ca_system_score_codex":0.005768521,"about_ca_system_score_gemma":0.0037474558,"threshold_uncertainty_score":0.9999509},"labels":[],"label_agreement":null},{"id":"W4413035771","doi":"10.1186/s13195-025-01827-2","title":"Longitudinal structural MRI-based deep learning and radiomics features for predicting Alzheimer’s disease progression","year":2025,"lang":"en","type":"article","venue":"Alzheimer s Research & Therapy","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Eisai; Northern California Institute for Research and Education; Pfizer; Novartis Pharmaceuticals Corporation; University of Southern California; Biogen; Eli Lilly and Company; Bristol-Myers Squibb; BioClinica; U.S. Department of Defense; Meso Scale Diagnostics; Alzheimer's Association","keywords":"Geriatric psychiatry; Neurology; Disease; Medicine; Radiomics; Artificial intelligence; Internal medicine; Psychiatry; Radiology; Computer science","score_opus":0.049660426728500795,"score_gpt":0.4247021297416508,"score_spread":0.37504170301315,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413035771","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5228315,0.410218,0.013387456,0.043501217,0.00094894675,0.0070521114,0.000025273193,0.00057856354,0.0014569584],"genre_scores_gemma":[0.9854775,0.001986508,0.010716073,0.0006478801,0.0004750692,0.0002792915,0.00013436752,0.00007542862,0.0002078785],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99704766,0.0003440739,0.0003368319,0.0006949791,0.0007495881,0.00082686427],"domain_scores_gemma":[0.99773467,0.00093462237,0.00009079773,0.0003495071,0.00037232556,0.00051809015],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016621792,0.0002891925,0.0004180232,0.0004623698,0.0009468918,0.00020627449,0.00024354915,0.00014202973,0.000048645732],"category_scores_gemma":[0.00084716274,0.00022372579,0.00016539289,0.0004775508,0.0005462914,0.00012794862,0.000110444525,0.0014387793,0.0000020984412],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0041261883,0.0001317156,0.2859686,0.00012473977,0.0013534253,0.00007495496,0.00034713672,0.00034156765,0.0019324189,0.0007481004,0.0021512797,0.70269984],"study_design_scores_gemma":[0.0154201,0.0020122384,0.27296543,0.0012922502,0.0013464234,0.000074281,0.0004582075,0.5921223,0.005027451,0.0025680538,0.1059432,0.0007700759],"about_ca_topic_score_codex":0.00006457748,"about_ca_topic_score_gemma":0.0000043509554,"teacher_disagreement_score":0.7019298,"about_ca_system_score_codex":0.000052486375,"about_ca_system_score_gemma":0.00037457782,"threshold_uncertainty_score":0.9123273},"labels":[],"label_agreement":null},{"id":"W4413050320","doi":"10.1371/journal.pdig.0000980","title":"Development and evaluation of large-language models (LLMs) for oncology: A scoping review","year":2025,"lang":"en","type":"review","venue":"PLOS Digital Health","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hamilton Health Sciences; Population Health Research Institute; McMaster University","funders":"","keywords":"Oncology; Medicine; Internal medicine","score_opus":0.12943350982022492,"score_gpt":0.49753808563260865,"score_spread":0.36810457581238376,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413050320","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00001424869,0.9906371,0.0009558426,0.0004761119,0.00006624638,0.0058428906,0.000055689412,0.000029467783,0.0019224046],"genre_scores_gemma":[0.000013803257,0.9927994,0.0047129206,0.0011139037,0.000060787243,0.00048373197,0.0006586919,0.000030855386,0.00012588839],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.9977306,0.00012821412,0.0010342838,0.00035339,0.00045575475,0.0002977168],"domain_scores_gemma":[0.9984687,0.00039933293,0.0005473725,0.00022044763,0.00017065022,0.00019350798],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023273267,0.00023241829,0.0022686482,0.00017467739,0.00006954678,0.000018524088,0.00008878861,0.0001175377,0.000008348131],"category_scores_gemma":[0.0013750284,0.00018082194,0.00017647025,0.00018334942,0.000033730703,0.00007923601,0.000077959085,0.00031433508,0.0000018439927],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002564291,0.000080922415,4.0694678e-7,0.40705863,0.00006420818,0.0000010335175,0.00011074598,2.3027958e-7,1.08897895e-8,0.00005556208,0.0001977847,0.5924279],"study_design_scores_gemma":[0.0006614153,0.000113761474,2.7694077e-7,0.79031175,0.0008984203,0.000024509014,0.000029852734,0.002046496,2.1000973e-7,0.00004024471,0.20575467,0.00011838892],"about_ca_topic_score_codex":0.000002927025,"about_ca_topic_score_gemma":0.0000032405544,"teacher_disagreement_score":0.5923095,"about_ca_system_score_codex":0.0004196725,"about_ca_system_score_gemma":0.008054973,"threshold_uncertainty_score":0.9975684},"labels":[],"label_agreement":null},{"id":"W4413057136","doi":"10.2139/ssrn.5355709","title":"The Actual Performance of AI/ML Models in Predicting Radiation-Induced Toxicity in Head and Neck Cancer: A Systematic Review and Meta-Analysis","year":2025,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre","funders":"","keywords":"Meta-analysis; Head and neck cancer; Toxicity; Oncology; Head and neck; Medicine; Cancer; Internal medicine; Surgery","score_opus":0.020916648771329076,"score_gpt":0.3266452240829061,"score_spread":0.305728575311577,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413057136","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6110896,0.379444,0.0007417719,0.007650511,0.000042305994,0.0009676592,0.0000063199377,0.000008052986,0.00004978593],"genre_scores_gemma":[0.7678545,0.23135883,0.00006462903,0.0004535369,0.00002947271,0.00007749912,0.0000038900944,0.000010073078,0.00014754699],"study_design_codex":"systematic_review","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970663,0.00037119494,0.0011022061,0.00030872517,0.00036298623,0.0007885421],"domain_scores_gemma":[0.99860096,0.00026850982,0.0006428683,0.0002969888,0.00010437869,0.00008627218],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0058212946,0.00024554555,0.0022916966,0.00037648747,0.000113748385,0.00004632082,0.00021505037,0.00012907616,0.0000046648456],"category_scores_gemma":[0.00068625936,0.00015336987,0.00034769994,0.0004507209,0.000051811916,0.000092089154,0.00013359344,0.0050782515,6.4172205e-8],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004865667,0.00043897214,0.1494515,0.43163174,0.31458843,0.00003371075,0.005039229,0.07308098,0.00007931736,0.008654543,0.00004935237,0.016465656],"study_design_scores_gemma":[0.001652029,0.0002952385,0.00402418,0.022717437,0.32313123,0.0002417135,0.00041026468,0.6393944,0.000014603117,0.007765436,0.000004544242,0.00034893185],"about_ca_topic_score_codex":0.000927713,"about_ca_topic_score_gemma":0.0017677081,"teacher_disagreement_score":0.56631345,"about_ca_system_score_codex":0.0006443651,"about_ca_system_score_gemma":0.0022534784,"threshold_uncertainty_score":0.99721706},"labels":[],"label_agreement":null},{"id":"W4413114846","doi":"10.1101/2025.08.09.25333360","title":"Diagnostic Codes in AI prediction models and Label Leakage of Same-admission Clinical Outcomes","year":2025,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Leakage (economics); Computer science; Reliability engineering; Artificial intelligence; Medicine; Engineering; Economics","score_opus":0.04275382199184965,"score_gpt":0.3868823508937452,"score_spread":0.34412852890189555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413114846","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.978786,0.0012038676,0.010131265,0.0075695836,0.00082528713,0.00055298547,0.000044658053,0.000072199284,0.0008141508],"genre_scores_gemma":[0.99142206,0.002904364,0.0029950424,0.0015679926,0.00014000756,0.0000348571,0.00007045211,0.000024487637,0.00084074214],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9977692,0.0002294543,0.0009243791,0.0005237937,0.00033682917,0.00021636748],"domain_scores_gemma":[0.9970925,0.0019486228,0.00021911028,0.0004388254,0.00008751979,0.00021341884],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0015041162,0.00024208202,0.0010065456,0.00027955155,0.000032713735,0.000017780998,0.00015968306,0.00038871387,0.00002054891],"category_scores_gemma":[0.009411411,0.00019382966,0.000147494,0.00012254958,0.00019851993,0.000046268124,0.0004051405,0.0018616363,0.0000012354446],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006021629,0.00027685688,0.9815649,0.0008649678,0.00009153932,0.000052065203,0.00020676969,0.0009043103,0.000065516484,0.00023810976,0.00066384,0.01501095],"study_design_scores_gemma":[0.0020240145,0.000118394986,0.7631055,0.002975307,0.00024236838,0.000008660223,0.000027827971,0.2266154,0.000044440425,0.004141028,0.0005553075,0.00014170745],"about_ca_topic_score_codex":0.00028345134,"about_ca_topic_score_gemma":0.000013453898,"teacher_disagreement_score":0.22571109,"about_ca_system_score_codex":0.000044608994,"about_ca_system_score_gemma":0.00024894497,"threshold_uncertainty_score":0.9989327},"labels":[],"label_agreement":null},{"id":"W4413136992","doi":"10.1109/tcsvt.2025.3596803","title":"Multi-Task Learning Network for Medical Image Analysis Guided by Lesion Regions and Spatial Relationships of Tissues","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Circuits and Systems for Video Technology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"Natural Science Foundation of Sichuan Province","keywords":"Computer science; Artificial intelligence; Task (project management); Lesion; Computer vision; Pattern recognition (psychology); Image (mathematics); Image processing; Image segmentation; Pathology; Medicine","score_opus":0.02614859617491819,"score_gpt":0.32034437117640135,"score_spread":0.29419577500148314,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413136992","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033026062,0.0023695244,0.9597995,0.0036105623,0.00024215596,0.0007595315,0.00003176255,0.00012617181,0.000034719676],"genre_scores_gemma":[0.99580616,0.00047267746,0.002401683,0.000072193645,0.000041300307,0.00019408547,0.000027162094,0.000020526428,0.0009642219],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986062,0.00008800311,0.0005346813,0.0003636485,0.00016332652,0.00024412257],"domain_scores_gemma":[0.99872553,0.0006422977,0.00015573126,0.00021013847,0.0001550981,0.000111201094],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008277508,0.00015153426,0.0005988696,0.0006123873,0.0004340069,0.000022413744,0.00008644791,0.00033495363,0.00000504818],"category_scores_gemma":[0.0005182652,0.00013512488,0.00013153194,0.000592689,0.00027090262,0.000039022452,0.0000029929497,0.0005462865,3.6561252e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00072288746,0.0016857047,0.08392458,0.0063267783,0.010512622,0.00005703845,0.0014626683,0.023293888,0.091040015,0.021255901,0.030504046,0.7292139],"study_design_scores_gemma":[0.006072423,0.0008005421,0.0015976527,0.0012579468,0.0031742733,0.00013795165,0.0007789364,0.94393224,0.0017436235,0.000836303,0.03932576,0.00034235054],"about_ca_topic_score_codex":0.0003409592,"about_ca_topic_score_gemma":0.000100026875,"teacher_disagreement_score":0.9627801,"about_ca_system_score_codex":0.000035608078,"about_ca_system_score_gemma":0.00006892932,"threshold_uncertainty_score":0.55102324},"labels":[],"label_agreement":null},{"id":"W4413139295","doi":"10.1109/tbme.2025.3599011","title":"Lung-DDPM: Semantic Layout-Guided Diffusion Models for Thoracic CT Image Synthesis","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Biomedical Engineering","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut universitaire de cardiologie et de pneumologie de Québec; Université Laval","funders":"Institut de Valorisation des Données","keywords":"Dice; Computer science; Artificial intelligence; Segmentation; Sørensen–Dice coefficient; Lung cancer screening; Image quality; Medical imaging; Image segmentation; Pattern recognition (psychology); Lung cancer; Computer vision; Image (mathematics); Statistics; Mathematics","score_opus":0.011482231942291974,"score_gpt":0.29675292585916146,"score_spread":0.2852706939168695,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413139295","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033822052,0.00011211975,0.9592554,0.004493385,0.0010681787,0.0004938724,0.000024851011,0.0003672828,0.00036286272],"genre_scores_gemma":[0.9779815,0.0001343146,0.020007394,0.0004935421,0.00013762513,0.00020007978,0.000013600902,0.0000629568,0.00096898316],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99828887,0.000026385012,0.0004397103,0.00041313595,0.00037880297,0.00045309594],"domain_scores_gemma":[0.99875265,0.00048660254,0.000042070304,0.0003349208,0.00006379505,0.00031995238],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039586652,0.0002738628,0.0004703513,0.00057819334,0.0001718592,0.000040491384,0.00016562335,0.00012588286,0.00007674801],"category_scores_gemma":[0.00019821717,0.00023835567,0.0002826617,0.00051709864,0.000109776534,0.00009884271,0.000003689387,0.00061556464,0.000011301731],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00065171,0.002421121,0.000056816352,0.0061354013,0.0015537204,0.00041997415,0.0004738897,0.19146192,0.24671312,0.0008987869,0.0117554385,0.5374581],"study_design_scores_gemma":[0.0010166524,0.000068823174,0.000048814054,0.00096628396,0.00037834892,0.00007225514,0.00002455566,0.97969085,0.013531229,0.00008679296,0.003903783,0.00021161264],"about_ca_topic_score_codex":0.000035754645,"about_ca_topic_score_gemma":6.4896375e-7,"teacher_disagreement_score":0.94415945,"about_ca_system_score_codex":0.0001554538,"about_ca_system_score_gemma":0.00010200655,"threshold_uncertainty_score":0.97198623},"labels":[],"label_agreement":null},{"id":"W4413139576","doi":"10.1038/s41598-025-15617-1","title":"Revisiting model scaling with a U-net benchmark for 3D medical image segmentation","year":2025,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"National Key Research and Development Program of China; National Science and Technology Major Project; Shanghai Jiao Tong University","keywords":"Benchmark (surveying); Computer science; Scaling; Artificial intelligence; Segmentation; Image (mathematics); Image segmentation; Net (polyhedron); Pattern recognition (psychology); Cartography; Mathematics; Geography","score_opus":0.008355165634917497,"score_gpt":0.3132938013573507,"score_spread":0.3049386357224332,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413139576","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27610967,0.00024529788,0.70468026,0.0060576024,0.001913023,0.0008502642,0.0000016518142,0.00012887998,0.010013336],"genre_scores_gemma":[0.56482655,0.000014048057,0.42360514,0.0017207447,0.0003459579,0.00011349075,0.0003495872,0.000040204257,0.008984293],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99780893,0.000025840523,0.00050373375,0.00061788963,0.0007340661,0.00030950722],"domain_scores_gemma":[0.9988615,0.00009453343,0.00019108466,0.00041424864,0.00023367447,0.00020494967],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030549234,0.00012845924,0.00026708105,0.00020154734,0.00035304233,0.00018704862,0.00007923544,0.00006738894,0.00008826211],"category_scores_gemma":[0.0016794291,0.00009750345,0.000083228384,0.00039217493,0.0002558205,0.0001181691,0.000049822705,0.00025708272,0.0000019750487],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00043268054,0.00045536447,0.04933888,0.0033501256,0.00044317424,0.0033074745,0.0019791403,0.006952478,0.11684457,0.0019384976,0.12713595,0.6878217],"study_design_scores_gemma":[0.0009885326,0.000033651086,0.0004279759,0.0014085055,0.00017592419,0.00052943005,0.00014164705,0.9769046,0.0027615747,0.002900545,0.013563872,0.00016374959],"about_ca_topic_score_codex":0.000012652741,"about_ca_topic_score_gemma":0.0000014376216,"teacher_disagreement_score":0.9699521,"about_ca_system_score_codex":0.000073261705,"about_ca_system_score_gemma":0.00060208346,"threshold_uncertainty_score":0.3976075},"labels":[],"label_agreement":null},{"id":"W4413148282","doi":"10.18280/ts.420403","title":"Addressing Boundary Ambiguity in Renal Tumor Segmentation: A Softmax-Refined Deep Learning Approach","year":2025,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Chengdu Science and Technology Program; Sichuan Province Science and Technology Support Program","keywords":"Softmax function; Ambiguity; Artificial intelligence; Segmentation; Deep learning; Computer science; Boundary (topology); Pattern recognition (psychology); Mathematics","score_opus":0.02444994104306319,"score_gpt":0.3120447784122475,"score_spread":0.2875948373691843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413148282","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.84966594,0.0011094635,0.12758103,0.0031908227,0.00022072108,0.000753602,0.0000022269778,0.00022073564,0.01725545],"genre_scores_gemma":[0.9802122,0.00002216688,0.015709357,0.0026931546,0.00022893041,0.000077677236,0.00011058834,0.00002637046,0.0009195437],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99808747,0.0001608565,0.00050981,0.00040710697,0.0004370136,0.00039775812],"domain_scores_gemma":[0.9994518,0.000091349495,0.00011814243,0.00014281928,0.00005709052,0.00013880798],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00091639924,0.00021128988,0.00038103518,0.0003116369,0.00025094728,0.0000831538,0.00013380237,0.000060877963,0.00036338507],"category_scores_gemma":[0.00018094703,0.00019487242,0.00010598021,0.00043318278,0.00014275515,0.000117497424,0.00006649535,0.00080651266,0.000008719505],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016353497,0.0022275927,0.20382498,0.0016839915,0.0005573127,0.00080546195,0.0047973166,0.020336954,0.09719756,0.0015427235,0.006296062,0.6590947],"study_design_scores_gemma":[0.018570317,0.0006296022,0.25166172,0.0018581392,0.00042459831,0.00022484023,0.002123508,0.6856464,0.0029871364,0.0006813007,0.03443164,0.0007608155],"about_ca_topic_score_codex":0.0000823756,"about_ca_topic_score_gemma":0.000010537042,"teacher_disagreement_score":0.6653094,"about_ca_system_score_codex":0.00021394217,"about_ca_system_score_gemma":0.00020297935,"threshold_uncertainty_score":0.7946667},"labels":[],"label_agreement":null},{"id":"W4413149186","doi":"10.1016/j.compmedimag.2025.102630","title":"Inference time correction based on confidence and uncertainty for improved deep-learning model performance and explainability in medical image classification","year":2025,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"ASTER","funders":"Qatar National Research Fund; Qatar Foundation","keywords":"Inference; Artificial intelligence; Computer science; Deep learning; Machine learning; Image (mathematics); Confidence interval; Medical imaging; Pattern recognition (psychology); Computer vision; Statistics; Mathematics","score_opus":0.008764051783965858,"score_gpt":0.3013993181054609,"score_spread":0.29263526632149506,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413149186","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33958393,0.00021256875,0.64131397,0.017863061,0.00023198283,0.0004586252,0.0000014183468,0.00010681138,0.00022760531],"genre_scores_gemma":[0.9884627,0.0008031987,0.0059598824,0.0045519583,0.000055286677,0.000053428837,0.00003521496,0.000015283478,0.00006306724],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982719,0.00013383885,0.00040619913,0.00053848716,0.00034797282,0.0003016448],"domain_scores_gemma":[0.9979594,0.0012521092,0.000089804904,0.0001824896,0.00013937945,0.00037685456],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018194905,0.0002058793,0.00042597135,0.00027877605,0.00021927482,0.00007296334,0.00010673096,0.00017050856,0.000009398172],"category_scores_gemma":[0.0044485764,0.00017927679,0.000044375513,0.00025165547,0.0007445078,0.00010373809,0.0000903635,0.0010121035,2.5283177e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00068759173,0.00020481135,0.038885046,0.00082678266,0.000025861767,0.000020898384,0.00029097547,0.0004045309,0.0015507366,0.0014728853,0.00028529376,0.9553446],"study_design_scores_gemma":[0.0035462189,0.00012999334,0.028023181,0.0011104797,0.000035204877,0.000034782774,0.000043459124,0.9656033,0.0000167339,0.0008293161,0.0004781883,0.00014916541],"about_ca_topic_score_codex":0.00004659212,"about_ca_topic_score_gemma":0.0000041221692,"teacher_disagreement_score":0.96519876,"about_ca_system_score_codex":0.000046361507,"about_ca_system_score_gemma":0.00029371513,"threshold_uncertainty_score":0.7310695},"labels":[],"label_agreement":null},{"id":"W4413203604","doi":"10.1016/j.bspc.2025.108492","title":"Radiomic feature selection for response prediction of cancer treatment using sparse rank revealing QR factorization and adaptive graph: locally advanced breast cancer and head &amp; neck cancer studies","year":2025,"lang":"en","type":"article","venue":"Biomedical Signal Processing and Control","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Toronto Metropolitan University; Health Sciences Centre; Sunnybrook Health Science Centre","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Terry Fox Foundation; Terry Fox Research Institute; University of Toronto; Lotte and John Hecht Memorial Foundation","keywords":"Breast cancer; Factorization; Graph; Computer science; Cancer; Rank (graph theory); Feature selection; Pattern recognition (psychology); Artificial intelligence; Mathematics; Medicine; Algorithm; Theoretical computer science; Combinatorics; Internal medicine","score_opus":0.021503268441776736,"score_gpt":0.34007093562447394,"score_spread":0.3185676671826972,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413203604","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.80706996,0.050241284,0.13552774,0.006073873,0.00018648745,0.00069817377,0.00015542135,0.000045530323,0.000001531023],"genre_scores_gemma":[0.9927289,0.0045493944,0.0017573672,0.0003402101,0.00027803206,0.00016501726,0.000015439813,0.000019722489,0.00014591943],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987342,0.00008333681,0.00032214046,0.00039867076,0.00021116313,0.00025052277],"domain_scores_gemma":[0.99910814,0.00020429438,0.00019181041,0.000053560034,0.0002708611,0.00017131638],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003421479,0.000221042,0.0005509973,0.00020277462,0.0003012329,0.000032746473,0.000029396377,0.0001491475,0.00000438964],"category_scores_gemma":[0.00012995308,0.00016338807,0.00005132666,0.00030741646,0.000347943,0.00010438855,0.0000140422035,0.00019888865,1.6397665e-8],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.012030638,0.00011852001,0.045195326,0.0010027993,0.00070686685,0.0000024941414,0.00076723786,0.00057717535,0.22107285,0.000010736972,0.000114693226,0.71840066],"study_design_scores_gemma":[0.038501825,0.0017594087,0.10916445,0.012833855,0.0035996176,0.00012483004,0.0007873909,0.8242921,0.002285251,0.0003958613,0.0057232575,0.000532144],"about_ca_topic_score_codex":0.0006519812,"about_ca_topic_score_gemma":0.00006658146,"teacher_disagreement_score":0.8237149,"about_ca_system_score_codex":0.0002571371,"about_ca_system_score_gemma":0.00046625012,"threshold_uncertainty_score":0.6662772},"labels":[],"label_agreement":null},{"id":"W4413225428","doi":"10.18280/isi.300602","title":"Feature Dimensionality Reduction for Lung Tumor Classification Using Transformer Deep Learning and YOLO Model","year":2025,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Dimensionality reduction; Artificial intelligence; Pattern recognition (psychology); Computer science; Feature (linguistics); Curse of dimensionality; Deep learning","score_opus":0.014638564819172703,"score_gpt":0.29802441488530856,"score_spread":0.28338585006613587,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413225428","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4257656,0.0003165008,0.5700929,0.0010931563,0.00018125218,0.0005529033,0.0000038289677,0.000095467076,0.0018983564],"genre_scores_gemma":[0.96766764,0.000058796653,0.031399377,0.00031189687,0.00006085274,0.00004934971,0.0001720484,0.000012036513,0.00026798056],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99909866,0.000034959063,0.00033824786,0.00015103015,0.00016899206,0.0002081102],"domain_scores_gemma":[0.99936503,0.00005128417,0.00016650709,0.00009857023,0.00024065413,0.0000779244],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005306235,0.00014082248,0.00022771269,0.00023111544,0.00045476382,0.000090039575,0.00004011264,0.00011085991,0.000004237441],"category_scores_gemma":[0.00044498444,0.00012864516,0.00007047297,0.00022118933,0.00012470793,0.00078259705,0.000012725224,0.0003183926,8.05258e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016742294,0.00015378991,0.020878999,0.009264353,0.00049616763,0.0000044614667,0.011855078,0.062005784,0.10250869,0.038263634,0.0028667338,0.7500281],"study_design_scores_gemma":[0.00092636974,0.000040594055,0.0037457014,0.00036715175,0.00014354187,0.000110017376,0.00095968,0.98910683,0.00059333764,0.0014116046,0.0024762445,0.000118926575],"about_ca_topic_score_codex":0.000016643236,"about_ca_topic_score_gemma":6.037019e-7,"teacher_disagreement_score":0.927101,"about_ca_system_score_codex":0.0002770452,"about_ca_system_score_gemma":0.00012263827,"threshold_uncertainty_score":0.52459973},"labels":[],"label_agreement":null},{"id":"W4413288733","doi":"10.1038/s41746-025-01941-3","title":"Incorporating large language models as clinical decision support in oncology: the Woollie model","year":2025,"lang":"en","type":"editorial","venue":"npj Digital Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Clinical decision making; Medicine; Oncology; Internal medicine; Computer science; Medical physics; Intensive care medicine","score_opus":0.019810511979871853,"score_gpt":0.40243749621926206,"score_spread":0.38262698423939023,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413288733","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005139059,0.0021649166,0.024050547,0.018502882,0.6138919,0.0018446333,0.00027351076,0.00033696857,0.33379558],"genre_scores_gemma":[0.1472938,0.0017309617,0.0035226177,0.010434292,0.8044274,0.00013997422,0.00434614,0.0002552222,0.02784958],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99428856,0.00016354598,0.0019690113,0.0009812679,0.0018677996,0.00072983507],"domain_scores_gemma":[0.99158967,0.0060128774,0.00061766355,0.0010020552,0.00029862623,0.00047911596],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.0045746774,0.0005948678,0.001962242,0.000468613,0.0001385884,0.00008823471,0.00072821777,0.0013858376,0.00011260258],"category_scores_gemma":[0.03270349,0.00036748187,0.0003177295,0.0005688851,0.00059377874,0.0002571681,0.0004972302,0.005813658,0.00006210693],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044881384,0.00031182243,0.0002432439,0.00015340667,0.00009670187,0.00095235964,0.0006579154,0.00032262446,0.0000050426333,0.00043282355,0.83469,0.16168529],"study_design_scores_gemma":[0.0077955737,0.001218218,0.000031273394,0.0031917933,0.00032368815,0.0000543912,0.0007806669,0.17670925,9.036036e-7,0.00959631,0.7999312,0.00036670416],"about_ca_topic_score_codex":0.000118390395,"about_ca_topic_score_gemma":0.000044974717,"teacher_disagreement_score":0.30594602,"about_ca_system_score_codex":0.00041388016,"about_ca_system_score_gemma":0.0030255248,"threshold_uncertainty_score":0.9999106},"labels":[],"label_agreement":null},{"id":"W4413308818","doi":"10.1093/jbmr/zjaf113","title":"Fracture risk scores using output from an opportunistic screen of low bone density from conventional X-ray","year":2025,"lang":"en","type":"article","venue":"Journal of Bone and Mineral Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Health Sciences Centre; McGill University; Sunnybrook Health Science Centre; McGill University Health Centre; North York General Hospital; BitCan (Canada); McMaster University; University of Toronto","funders":"Canadian Institutes of Health Research; Eli Lilly Canada; Arthritis Society; Dairy Farmers of Canada; Servier Canada","keywords":"Fracture (geology); Bone density; Medicine; X-ray; Dentistry; Orthodontics; Osteoporosis; Internal medicine; Materials science; Physics; Composite material; Optics","score_opus":0.05057651233710688,"score_gpt":0.39501786188868215,"score_spread":0.3444413495515753,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413308818","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9870845,0.0019185684,0.0077933106,0.0027737303,0.0001298528,0.00010259857,0.000050487793,0.0000041791195,0.00014274557],"genre_scores_gemma":[0.99002683,0.0005622981,0.0077577373,0.0003937432,0.00053627003,4.616463e-7,0.000058667738,0.000012318074,0.0006516759],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9978913,0.00026910254,0.00058455864,0.0001905741,0.0008200029,0.000244445],"domain_scores_gemma":[0.99807644,0.00049587147,0.00029688462,0.00018631038,0.0005948719,0.00034959853],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019950592,0.00011302278,0.0005823546,0.0004222655,0.00013800405,0.000049241364,0.00009474412,0.00011030163,0.0001182942],"category_scores_gemma":[0.0020377906,0.00008520289,0.00013262592,0.00017853899,0.00030732816,0.00012702234,0.00008608055,0.0012968881,9.649523e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0040786294,0.0010926845,0.5167919,0.00031253064,0.0011957644,0.0027594292,0.0011372968,0.00041412053,0.3799617,0.0005817233,0.021176018,0.07049824],"study_design_scores_gemma":[0.007840536,0.0010492045,0.8985885,0.0033126792,0.0006966921,0.0002692318,0.0010356673,0.06667476,0.0012398362,0.009266341,0.009777701,0.00024887954],"about_ca_topic_score_codex":0.0034158523,"about_ca_topic_score_gemma":0.000042353222,"teacher_disagreement_score":0.3817966,"about_ca_system_score_codex":0.00005367688,"about_ca_system_score_gemma":0.0005796294,"threshold_uncertainty_score":0.56344056},"labels":[],"label_agreement":null},{"id":"W4413318157","doi":"10.1055/a-2580-8101","title":"KOPF HALS – Automatisierte ASPECTS-Berechnung mittels KI – klinischer Nutzen trotz sinkender Relevanz zur Therapieentscheidung?","year":2025,"lang":"de","type":"article","venue":"RöFo - Fortschritte auf dem Gebiet der Röntgenstrahlen und der bildgebenden Verfahren","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Medicine; Gynecology","score_opus":0.013343943361375543,"score_gpt":0.31678851337953645,"score_spread":0.3034445700181609,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413318157","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22878587,0.5741247,0.03271575,0.04235924,0.021886325,0.01074428,0.00066546455,0.0037644836,0.08495387],"genre_scores_gemma":[0.92643464,0.011914637,0.015046844,0.015792582,0.0054248115,0.00037880713,0.0009754127,0.0010598096,0.022972478],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98254275,0.001267796,0.0042949268,0.0041291844,0.0032794639,0.00448588],"domain_scores_gemma":[0.99012214,0.0015179298,0.0015452373,0.0038748411,0.0008464592,0.0020933775],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"category_scores_codex":[0.0036111716,0.003068691,0.004013496,0.0016154686,0.0015140093,0.0013328999,0.0024452258,0.0026431188,0.0026316417],"category_scores_gemma":[0.0014080757,0.0029550414,0.0020125986,0.0025109618,0.0013327405,0.0011150216,0.0011149273,0.0059994264,0.0026762704],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002253783,0.0049554654,0.094957136,0.005166223,0.071863614,0.0057409694,0.005400492,0.0011248231,0.016941395,0.021637097,0.36192906,0.40802994],"study_design_scores_gemma":[0.021102417,0.0011551838,0.043273326,0.006211083,0.024426213,0.000589654,0.00079453853,0.038569055,0.010567378,0.011644822,0.83632594,0.005340396],"about_ca_topic_score_codex":0.001221797,"about_ca_topic_score_gemma":0.00009624055,"teacher_disagreement_score":0.69764876,"about_ca_system_score_codex":0.0008558366,"about_ca_system_score_gemma":0.0029357288,"threshold_uncertainty_score":0.9997859},"labels":[],"label_agreement":null},{"id":"W4413324439","doi":"10.1016/j.cpet.2025.07.006","title":"Objective Task-Based Evaluation of Quantitative Medical Imaging Methods","year":2025,"lang":"en","type":"review","venue":"PET Clinics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Medicine; Task (project management); Medical physics; Systems engineering","score_opus":0.08863096550514929,"score_gpt":0.577972175259264,"score_spread":0.48934120975411477,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413324439","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000004177037,0.9417537,0.051272947,0.0005529076,0.0010726649,0.0010498657,0.000029567787,0.0000587637,0.004205446],"genre_scores_gemma":[0.000013657369,0.9297327,0.06879057,0.0006232096,0.00020388006,0.00010866479,0.0003201332,0.000058583097,0.00014864405],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9931366,0.0027862298,0.0015986268,0.0006262892,0.0015492905,0.00030297486],"domain_scores_gemma":[0.988504,0.008797234,0.0010055098,0.00060646824,0.00083381176,0.0002529855],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.016164552,0.000398986,0.0028476196,0.0005259675,0.00006606505,0.000017734352,0.00033287928,0.000263297,0.00032906994],"category_scores_gemma":[0.06384675,0.00031307034,0.00092779566,0.00068687886,0.00032516895,0.00003754732,0.000120142526,0.001846449,0.000017361761],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019219817,0.00014596521,0.000049381757,0.01532814,0.00032518563,0.000044616972,0.00005426597,0.000012644704,2.2116451e-7,0.00033699133,0.0006150614,0.9830683],"study_design_scores_gemma":[0.0018702403,0.0001222063,0.00002745952,0.060281143,0.010684209,0.00009475673,0.00007375051,0.25327066,9.972671e-7,0.0006569839,0.67259073,0.00032688814],"about_ca_topic_score_codex":0.000029248704,"about_ca_topic_score_gemma":0.0000021406988,"teacher_disagreement_score":0.9827414,"about_ca_system_score_codex":0.00025526527,"about_ca_system_score_gemma":0.0077570057,"threshold_uncertainty_score":0.9999321},"labels":[],"label_agreement":null},{"id":"W4413353079","doi":"10.2214/ajr.25.33364","title":"Physician-in-the-Loop Active Learning in Radiology Artificial Intelligence Workflows: Opportunities, Challenges, and Future Directions","year":2025,"lang":"en","type":"review","venue":"American Journal of Roentgenology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Children's Hospital; Simon Fraser University; University of British Columbia","funders":"","keywords":"Medicine; Workflow; Loop (graph theory); Radiology; Medical physics; Artificial intelligence; Medical education; Management","score_opus":0.053389953118471827,"score_gpt":0.34831596239682266,"score_spread":0.29492600927835083,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413353079","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00036973465,0.9889546,0.00015672378,0.008930363,0.0005487506,0.0002573577,0.000001896373,0.000010778811,0.0007697658],"genre_scores_gemma":[0.00026853874,0.9977236,0.00035491688,0.0005917216,0.00094077614,0.000020768863,0.000012297332,0.00002654519,0.000060857663],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99684227,0.001293393,0.00097301765,0.00030500948,0.00018230842,0.00040401422],"domain_scores_gemma":[0.9977035,0.0009531534,0.0009496385,0.00020117112,0.00007794647,0.00011458145],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0009008974,0.00031093223,0.0022672524,0.0010373164,0.000067807196,0.000012939223,0.0003005623,0.00018181863,0.000012465851],"category_scores_gemma":[0.00043217078,0.00022096986,0.00027605248,0.0005913012,0.0006096092,0.000049618462,0.000060528266,0.003283259,0.0000016264366],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000067232024,0.000113619295,0.000011450856,0.00071739615,0.00021267192,0.0007361724,0.001297538,0.000008876524,3.944872e-7,0.0007637876,0.00003401308,0.9960368],"study_design_scores_gemma":[0.00016797357,0.00096735905,0.0000923981,0.0049300394,0.00055349723,0.0037128348,0.009602635,0.000039370512,1.2352538e-7,0.00031124952,0.979463,0.0001595638],"about_ca_topic_score_codex":0.000033161312,"about_ca_topic_score_gemma":0.000024845738,"teacher_disagreement_score":0.99587727,"about_ca_system_score_codex":0.00018382826,"about_ca_system_score_gemma":0.00062688085,"threshold_uncertainty_score":0.9990162},"labels":[],"label_agreement":null},{"id":"W4413365399","doi":"10.1007/s12672-025-03321-5","title":"Oncogene-driven lung cancer in the era of radiogenomics: current evidence and future developments","year":2025,"lang":"en","type":"article","venue":"Discover Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Trinity College","funders":"","keywords":"Radiogenomics; KRAS; Precision medicine; ROS1; Lung cancer; Personalized medicine; Medicine; Oncogene; Radiomics; Molecular diagnostics; Cancer; Bioinformatics; Pathology; Biology; Internal medicine; Adenocarcinoma; Radiology; Colorectal cancer","score_opus":0.014583336343756683,"score_gpt":0.3796400258933808,"score_spread":0.3650566895496241,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413365399","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94985557,0.025416763,0.00040031003,0.022077171,0.00079890375,0.00036595727,0.000005163774,0.0000064546402,0.0010736828],"genre_scores_gemma":[0.98106086,0.015331983,0.0008154206,0.0024076828,0.00025049073,0.0000490975,0.0000067262026,0.000007665786,0.0000700649],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9991576,0.000108755594,0.00025090267,0.0001938703,0.000121777055,0.00016706453],"domain_scores_gemma":[0.99951077,0.00019808696,0.000079163656,0.00014109598,0.000030133217,0.000040750787],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035116833,0.00009485432,0.00028771377,0.00008094287,0.000041399184,0.0000094978295,0.00014156985,0.00006256316,0.000028319926],"category_scores_gemma":[0.00011110696,0.000062865445,0.00003909815,0.00019113215,0.00012256367,0.000049898168,0.00006789993,0.0004616999,6.63384e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011811009,0.0001310655,0.579046,0.0002307044,0.00008062944,0.00003201192,0.0025996584,0.00008504397,0.0014456364,0.0012155502,0.002013482,0.4130021],"study_design_scores_gemma":[0.0024702894,0.0001309734,0.80424935,0.0012203694,0.00023136038,0.0000461844,0.0006394727,0.007105541,0.00018972307,0.0001681084,0.18340723,0.0001414168],"about_ca_topic_score_codex":0.00015032716,"about_ca_topic_score_gemma":0.00008524416,"teacher_disagreement_score":0.4128607,"about_ca_system_score_codex":0.00020599381,"about_ca_system_score_gemma":0.00072881236,"threshold_uncertainty_score":0.25635785},"labels":[],"label_agreement":null},{"id":"W4413371775","doi":"10.3390/cancers17162706","title":"A Priori Prediction of Breast Cancer Response to Neoadjuvant Chemotherapy Using CT Radiomics","year":2025,"lang":"en","type":"article","venue":"Cancers","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Toronto Metropolitan University; Health Sciences Centre; Sunnybrook Health Science Centre","funders":"Natural Sciences and Engineering Research Council of Canada; Terry Fox Research Institute; University of Toronto; Terry Fox Foundation","keywords":"Medicine; Radiomics; Breast cancer; Complete response; Neoadjuvant therapy; Radiology; Cancer; Chemotherapy; Internal medicine","score_opus":0.01111965939185374,"score_gpt":0.31784485005225993,"score_spread":0.3067251906604062,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413371775","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98543465,0.00054445956,0.0050820233,0.0074795405,0.000744196,0.00032768247,0.00004294768,0.000046255624,0.00029826118],"genre_scores_gemma":[0.99175566,0.00032824467,0.0030612147,0.00375682,0.00022913348,0.000020154808,0.000004240423,0.000027098995,0.0008174313],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9990912,0.00004226351,0.000254993,0.0002265012,0.000177774,0.00020724168],"domain_scores_gemma":[0.9994223,0.000041657462,0.000077423014,0.00022859333,0.00008890141,0.0001411032],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035685065,0.00011568471,0.00029487026,0.00020829261,0.000055135042,0.000010186978,0.000088104796,0.000037445694,0.00006867247],"category_scores_gemma":[0.00013291428,0.00010562112,0.00007918659,0.00042727316,0.00008844088,0.000037342394,0.000021711912,0.00021022838,9.609698e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0073568025,0.00004978798,0.05617454,0.00032882392,0.00039972115,0.000049256534,0.0012714482,0.020200174,0.59380716,0.00008307993,0.009456881,0.31082234],"study_design_scores_gemma":[0.01026255,0.0003486515,0.4714449,0.0037136339,0.00046307835,0.0003239502,0.00050384254,0.37752235,0.017704317,0.00007054993,0.11726504,0.00037712636],"about_ca_topic_score_codex":0.0017712726,"about_ca_topic_score_gemma":0.00000638592,"teacher_disagreement_score":0.57610285,"about_ca_system_score_codex":0.001639576,"about_ca_system_score_gemma":0.0015091846,"threshold_uncertainty_score":0.4307104},"labels":[],"label_agreement":null},{"id":"W4413377061","doi":"10.1101/2025.08.12.25333156","title":"SuReCAN: a suite of user-friendly Galaxy machine learning workflows to predict survival and treatment response of cancer patients","year":2025,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Government of Ontario","keywords":"Suite; Workflow; Galaxy; Computer science; User Friendly; Human–computer interaction; Astrophysics; Operating system; Physics; Database; Geography","score_opus":0.013064466832558155,"score_gpt":0.3029655370758174,"score_spread":0.2899010702432593,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413377061","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99469566,0.0013108429,0.00032150073,0.0012968415,0.00078348827,0.0009417692,0.00020858055,0.000056193738,0.00038512656],"genre_scores_gemma":[0.9926352,0.0010976569,0.0020478975,0.00007250871,0.00012603679,0.00010619506,0.0001099929,0.00005013402,0.0037544153],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9971228,0.00050346163,0.0007699679,0.00064438616,0.00059863663,0.0003607204],"domain_scores_gemma":[0.99786526,0.00058089284,0.0004038821,0.0005296519,0.00028493867,0.00033540293],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012432772,0.00040973694,0.0012537808,0.00045800747,0.00006218116,0.000018386148,0.00022367609,0.0002273152,0.000086225446],"category_scores_gemma":[0.0021266427,0.0003337999,0.00021847199,0.00031769092,0.00015013076,0.000024006753,0.000452337,0.00085260003,0.000001205125],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00277943,0.00026674516,0.9753838,0.0006606086,0.00045239815,0.000023417391,0.00084833795,0.0012783005,0.0014675441,0.000013137088,0.00016299737,0.016663266],"study_design_scores_gemma":[0.0033499394,0.0014404799,0.9671944,0.002836747,0.0005979023,0.0000027537667,0.00004725062,0.005714907,0.0014443507,0.000010420697,0.017077724,0.00028311813],"about_ca_topic_score_codex":0.0026651851,"about_ca_topic_score_gemma":0.00020594025,"teacher_disagreement_score":0.016914727,"about_ca_system_score_codex":0.00020059825,"about_ca_system_score_gemma":0.0004986125,"threshold_uncertainty_score":0.9999114},"labels":[],"label_agreement":null},{"id":"W4413438811","doi":"10.62051/gjgj3p83","title":"Research and Model Development for Gastric Cancer Risk Prediction","year":2025,"lang":"en","type":"article","venue":"Transactions on Computer Science and Intelligent Systems Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"SGS (Canada)","funders":"","keywords":"Cancer; Risk model; Medicine; Computer science; Internal medicine; Risk analysis (engineering)","score_opus":0.09615967985680633,"score_gpt":0.42970108788982725,"score_spread":0.3335414080330209,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413438811","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08766309,0.0005595972,0.9089363,0.0012620842,0.0003391445,0.0009093741,0.000006670045,0.000030526975,0.000293218],"genre_scores_gemma":[0.98511213,0.0018279057,0.009796931,0.00008263651,0.00010401665,0.00034525723,0.0000017064316,0.000010616269,0.0027188116],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99753374,0.00010585327,0.00027384094,0.0005169962,0.0010711445,0.0004984148],"domain_scores_gemma":[0.9979865,0.00037758754,0.00002339484,0.00021378939,0.001152712,0.00024603604],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0066333045,0.00009429151,0.00017429663,0.00140779,0.0014923821,0.00023777375,0.00017803076,0.000058426867,0.000004599369],"category_scores_gemma":[0.000103118145,0.00007475274,0.000022122938,0.0013535741,0.00075085333,0.00011872518,0.000027685188,0.00079591403,0.0000036357105],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019452092,0.00028563364,0.0016411333,0.0005319919,0.00008252903,0.000002603179,0.001225739,0.02981883,0.0011285619,0.0016385299,0.0026152409,0.9608347],"study_design_scores_gemma":[0.00035989535,0.00038730793,0.0011364324,0.00048700505,0.000010730646,0.00001319207,0.00023855014,0.98786086,0.0014899948,0.00018261837,0.007778022,0.00005537068],"about_ca_topic_score_codex":0.00025716893,"about_ca_topic_score_gemma":0.0000071994577,"teacher_disagreement_score":0.9607793,"about_ca_system_score_codex":0.00034998255,"about_ca_system_score_gemma":0.0009502922,"threshold_uncertainty_score":0.99980754},"labels":[],"label_agreement":null},{"id":"W4413506097","doi":"10.3390/cancers17172738","title":"Hybrid Feature Selection for Predicting Chemotherapy Response in Locally Advanced Breast Cancer Using Clinical and CT Radiomics Features: Integration of Matrix Rank and Genetic Algorithm","year":2025,"lang":"en","type":"article","venue":"Cancers","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Toronto Metropolitan University; Health Sciences Centre; Sunnybrook Health Science Centre","funders":"Natural Sciences and Engineering Research Council of Canada; Terry Fox Research Institute","keywords":"Radiomics; Breast cancer; Feature selection; Rank (graph theory); Selection (genetic algorithm); Medicine; Feature (linguistics); Oncology; Cancer; Computer science; Pattern recognition (psychology); Artificial intelligence; Radiology; Internal medicine; Mathematics","score_opus":0.008039674792051272,"score_gpt":0.34402163942283104,"score_spread":0.3359819646307798,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413506097","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92661124,0.0030557886,0.06742404,0.002050458,0.0002776693,0.0005307752,0.00002335325,0.000020306337,0.000006359122],"genre_scores_gemma":[0.9163012,0.0032550932,0.07899165,0.0009270348,0.00024063519,0.00004072324,0.000010657092,0.00003250784,0.00020050917],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99905807,0.000081307866,0.0002997389,0.00029166203,0.00009744483,0.00017177357],"domain_scores_gemma":[0.9994053,0.00021267612,0.00012062375,0.00009065941,0.00009267393,0.000078026074],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004931147,0.00012957894,0.0003548468,0.00016440163,0.00006311787,0.000017260809,0.00004166648,0.00006976996,0.0000025107572],"category_scores_gemma":[0.0002958542,0.000117013464,0.00005323034,0.00019730868,0.00016118026,0.000054048614,0.000012940242,0.0003856406,1.35097435e-8],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0076940036,0.000021710104,0.08283532,0.00028648775,0.00012623679,0.000011022021,0.00025246205,0.0071832896,0.023622157,0.000013086375,0.0004996854,0.8774545],"study_design_scores_gemma":[0.006783111,0.00019160636,0.14551921,0.0011308668,0.00011991849,0.00026165016,0.00015520879,0.8436346,0.0014205092,0.00007162123,0.000598542,0.00011316486],"about_ca_topic_score_codex":0.00036669977,"about_ca_topic_score_gemma":0.000028100678,"teacher_disagreement_score":0.8773414,"about_ca_system_score_codex":0.0004299734,"about_ca_system_score_gemma":0.00068934966,"threshold_uncertainty_score":0.47716704},"labels":[],"label_agreement":null},{"id":"W4413535946","doi":"10.4108/airo.9795","title":"An Explainable AI Based Deep Ensemble Transformer Framework for Gastrointestinal Disease Prediction from Endoscopic Images","year":2025,"lang":"en","type":"article","venue":"EAI Endorsed Transactions on AI and Robotics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wycliffe College","funders":"","keywords":"Artificial intelligence; Computer science; Gastrointestinal disease; Transformer; Medicine; Disease; Internal medicine; Engineering","score_opus":0.00797303578652087,"score_gpt":0.2904283652456261,"score_spread":0.28245532945910523,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413535946","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028607624,0.00016266176,0.982294,0.013299355,0.00039213963,0.00057340914,0.0001165258,0.00015796837,0.00014315831],"genre_scores_gemma":[0.79457295,0.00008540119,0.20055142,0.003875661,0.00014404953,0.00009676089,0.00017671689,0.000036513076,0.000460514],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987002,0.000056218538,0.00029356228,0.00040571613,0.00019750594,0.00034682226],"domain_scores_gemma":[0.9988805,0.00033031683,0.0000411174,0.00028984304,0.00009399796,0.00036422317],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013130465,0.00023161624,0.0003034571,0.00022067383,0.0004089693,0.000076262884,0.00008074414,0.000090907706,0.00010291202],"category_scores_gemma":[0.00011826813,0.00020892579,0.00014472147,0.00018509405,0.00011884677,0.0001481577,0.0000011970828,0.00070670195,0.0000027293045],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0050113504,0.00430517,0.03395327,0.0016313172,0.0005636898,0.00022619253,0.0006007879,0.73555344,0.021136193,0.0073109646,0.0018812862,0.18782635],"study_design_scores_gemma":[0.006157114,0.0010545162,0.01070097,0.0013646843,0.0010614562,0.000021468577,0.0002065587,0.9671916,0.004258962,0.0058417213,0.0018706587,0.00027033294],"about_ca_topic_score_codex":0.00004981106,"about_ca_topic_score_gemma":0.0000073438077,"teacher_disagreement_score":0.7917122,"about_ca_system_score_codex":0.00006119023,"about_ca_system_score_gemma":0.00018666245,"threshold_uncertainty_score":0.8519746},"labels":[],"label_agreement":null},{"id":"W4413630510","doi":"10.1109/jbhi.2025.3602674","title":"Radiomics-Driven Diffusion Model and Monte Carlo Compression Sampling for Reliable Medical Image Synthesis","year":2025,"lang":"en","type":"article","venue":"IEEE Journal of Biomedical and Health Informatics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Monte Carlo method; Computer science; Medical imaging; Sampling (signal processing); Artificial intelligence; Radiomics; Diffusion; Computer vision; Statistics; Mathematics","score_opus":0.028994004530462622,"score_gpt":0.3617778476237319,"score_spread":0.33278384309326925,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413630510","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46738395,0.0020249733,0.46517983,0.063952215,0.0007636277,0.00045153615,0.000018059278,0.000029174622,0.0001966423],"genre_scores_gemma":[0.5581367,0.021927487,0.4002381,0.018618377,0.00080880657,0.000016996531,0.000012193087,0.000039118648,0.00020223045],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975608,0.000027117354,0.0013987155,0.00009866167,0.00058580097,0.00032892489],"domain_scores_gemma":[0.99797016,0.0003767691,0.00051726715,0.00011705941,0.0001586893,0.0008600402],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002060737,0.00015456353,0.0007032061,0.00033223035,0.00025240085,0.000044035114,0.00013511046,0.00018857911,0.000007353306],"category_scores_gemma":[0.00090313295,0.00010511876,0.00009661379,0.00013202285,0.00028662288,0.00014750734,0.00007016255,0.000708352,3.7614504e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012520159,0.0007289943,0.0058022137,0.01574432,0.00035483774,0.000057988844,0.0050133825,0.0012945401,0.00203721,0.0009382856,0.109590374,0.85718584],"study_design_scores_gemma":[0.0029789566,0.00034553895,0.0009521354,0.0035538436,0.000103824685,0.00036200517,0.00030833317,0.9732595,0.000037218953,0.0003968784,0.017604861,0.00009691184],"about_ca_topic_score_codex":0.000028287188,"about_ca_topic_score_gemma":0.000001254472,"teacher_disagreement_score":0.97196496,"about_ca_system_score_codex":0.00009373922,"about_ca_system_score_gemma":0.0007244438,"threshold_uncertainty_score":0.42866185},"labels":[],"label_agreement":null},{"id":"W4413801790","doi":"10.1016/j.artmed.2025.103245","title":"Privacy-preserving federated transfer learning for enhanced liver lesion segmentation in PET–CT imaging","year":2025,"lang":"en","type":"article","venue":"Artificial Intelligence in Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Natural Science Foundation of Zhejiang Province; Science and Technology Program of Suzhou","keywords":"Computer science; Transfer of learning; Segmentation; Artificial intelligence; Computer vision; Medical imaging; Pattern recognition (psychology); Medical physics; Medicine","score_opus":0.03924530443730946,"score_gpt":0.37190883860463947,"score_spread":0.33266353416733,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413801790","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6021866,0.00049712526,0.3836471,0.01015804,0.00040953557,0.0008825988,4.0322055e-7,0.000073543226,0.0021450357],"genre_scores_gemma":[0.99495053,0.00046615035,0.0025936596,0.001308227,0.00016854482,0.000091290545,0.000049733128,0.000025536106,0.00034635264],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99764913,0.00015168112,0.0008906617,0.00050592667,0.00033824865,0.00046435642],"domain_scores_gemma":[0.9988647,0.0006095371,0.00006992578,0.00019640423,0.00015396037,0.000105445506],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015692438,0.00022927998,0.00050812913,0.00065067346,0.00016543985,0.000040056693,0.00019210331,0.00003564808,0.00019218426],"category_scores_gemma":[0.0031789115,0.0002038212,0.00007301967,0.0008583592,0.00017937153,0.00016459527,0.00005502488,0.0008410561,0.000010089981],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00069666025,0.00025915165,0.015927296,0.0005165727,0.00003418832,0.00045810733,0.0030701866,0.006194953,0.28124818,0.002540402,0.00029437186,0.6887599],"study_design_scores_gemma":[0.0012036,0.00026394703,0.0046513714,0.0035768028,0.0000847158,0.000056587076,0.005975305,0.8590282,0.117584,0.0061066775,0.0011880887,0.00028067778],"about_ca_topic_score_codex":0.0011239266,"about_ca_topic_score_gemma":0.0002546392,"teacher_disagreement_score":0.8528333,"about_ca_system_score_codex":0.00021282084,"about_ca_system_score_gemma":0.00013845753,"threshold_uncertainty_score":0.8311587},"labels":[],"label_agreement":null},{"id":"W4413820826","doi":"10.2196/75665","title":"Deep Learning Radiomics Model Based on Computed Tomography Image for Predicting the Classification of Osteoporotic Vertebral Fractures: Algorithm Development and Validation","year":2025,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Bijzonder Onderzoeksfonds UGent; Jiangsu Commission of Health","keywords":"Artificial intelligence; Deep learning; Machine learning; Feature selection; Lasso (programming language); Receiver operating characteristic; Computer science; Magnetic resonance imaging; Feature (linguistics); Medical imaging; Cross-validation; Medicine; Pattern recognition (psychology); Algorithm; Radiology","score_opus":0.0093598410298103,"score_gpt":0.2941317626622125,"score_spread":0.2847719216324022,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413820826","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13411614,0.00004043604,0.86308044,0.0013813326,0.0001045562,0.00071520853,0.0000018696026,0.000064924185,0.00049507903],"genre_scores_gemma":[0.7941724,0.000018538334,0.20282105,0.002517708,0.00006810287,0.00010414907,0.00025204424,0.00001850615,0.000027502449],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982701,0.00005017042,0.0007439575,0.0001298159,0.0005787067,0.00022722753],"domain_scores_gemma":[0.9986275,0.0005781818,0.00028186964,0.0001922152,0.0001554681,0.00016480833],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010185128,0.00016367681,0.000309872,0.00025577325,0.0002302478,0.000045139295,0.00015884728,0.00016854689,0.000008066487],"category_scores_gemma":[0.0008963369,0.00011362214,0.000084274754,0.00028135095,0.0002104101,0.00010065071,0.00004712938,0.0006626158,6.696289e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020104181,0.0002896519,0.0057593007,0.0017028308,0.00020459012,0.0000029717776,0.007121036,0.027162522,0.00018269737,0.0012734415,0.0009382206,0.9551617],"study_design_scores_gemma":[0.0020868487,0.0001255435,0.005919546,0.0005344957,0.0000780369,0.0000071705463,0.0009197333,0.9889334,0.0004317822,0.000089827015,0.000778068,0.00009558505],"about_ca_topic_score_codex":0.0000021074422,"about_ca_topic_score_gemma":3.9157342e-7,"teacher_disagreement_score":0.96177083,"about_ca_system_score_codex":0.000062834835,"about_ca_system_score_gemma":0.0002914217,"threshold_uncertainty_score":0.46333766},"labels":[],"label_agreement":null},{"id":"W4413856517","doi":"10.1093/noajnl/vdaf166.041","title":"43 NATURAL LANGUAGE PROCESSING MODEL-BASED SOLUTION FOR LABELING BRAIN METASTASIS IN RADIOLOGY REPORTS","year":2025,"lang":"en","type":"article","venue":"Neuro-Oncology Advances","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Brain metastasis; Computer science; Natural language processing; Metastasis; Artificial intelligence; Medicine; Internal medicine; Cancer","score_opus":0.010429191859290202,"score_gpt":0.35632803259831647,"score_spread":0.34589884073902627,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413856517","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43340015,0.047608454,0.44644493,0.066052735,0.0024245002,0.0016078114,0.000006891646,0.00033220783,0.0021223216],"genre_scores_gemma":[0.93184435,0.00006550554,0.05517938,0.012477288,0.00011605107,0.000109433306,0.000041023708,0.000020366206,0.00014657238],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99852276,0.00012611323,0.00042897862,0.00044527298,0.000107270214,0.0003696129],"domain_scores_gemma":[0.998787,0.0007178802,0.00018359584,0.00017497526,0.00007384025,0.000062698084],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007448172,0.00015710242,0.00047344732,0.00028351825,0.00012847142,0.000011512047,0.00008706933,0.00012408056,0.0000048988654],"category_scores_gemma":[0.0033364524,0.00013849763,0.00008637431,0.00027530806,0.00017202576,0.00011661805,0.00003125673,0.00058321113,5.1022744e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00059200305,0.00023922145,0.008165368,0.0005600196,0.000032956545,0.0006423295,0.00044350923,0.026268553,0.19833496,0.00017216188,0.001423205,0.7631257],"study_design_scores_gemma":[0.0025069402,0.0002882156,0.0003152754,0.00014499914,0.00011015237,0.00025337542,0.00014669383,0.9692843,0.0034911688,0.00082883873,0.022487555,0.0001424854],"about_ca_topic_score_codex":0.000009395582,"about_ca_topic_score_gemma":0.000034940804,"teacher_disagreement_score":0.94301575,"about_ca_system_score_codex":0.00013841773,"about_ca_system_score_gemma":0.00041484178,"threshold_uncertainty_score":0.56477696},"labels":[],"label_agreement":null},{"id":"W4413878685","doi":"10.1038/s41598-025-15604-6","title":"Explainable self-supervised learning for medical image diagnosis based on DINO V2 model and semantic search","year":2025,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Science and Technology Development Fund","keywords":"Interpretability; Computer science; Artificial intelligence; Machine learning; Medical imaging; Semantic gap; Workflow; Deep learning; Supervised learning; Feature (linguistics); Image (mathematics); Information retrieval; Image retrieval; Artificial neural network; Database","score_opus":0.011720068886704557,"score_gpt":0.3061803413620892,"score_spread":0.29446027247538464,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413878685","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9090651,0.00026012806,0.064225085,0.015417844,0.0019824991,0.0012457734,0.0000012655288,0.00031660643,0.0074856505],"genre_scores_gemma":[0.9793442,0.000035388042,0.013065148,0.000990678,0.00008167663,0.00016135098,0.000060853425,0.000033025262,0.0062276954],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99710506,0.00007976033,0.00047755553,0.0008848198,0.0009479504,0.000504878],"domain_scores_gemma":[0.9983514,0.00041253312,0.00008936731,0.00053992885,0.00021931852,0.00038746526],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0041645314,0.00018599343,0.00037652988,0.00041169638,0.00063674216,0.0002595266,0.000118730975,0.00012158971,0.00011840013],"category_scores_gemma":[0.0036388668,0.00015504475,0.00013230628,0.0004541444,0.00030568757,0.00009777233,0.00010070134,0.0005631399,0.000004744916],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00061321363,0.003234393,0.524334,0.007840855,0.00048105395,0.0078772,0.0032630335,0.040398035,0.02846826,0.0024321561,0.22126198,0.15979582],"study_design_scores_gemma":[0.0010505712,0.00009556141,0.0009997531,0.00054350693,0.000095586736,0.00008295152,0.00009476798,0.9800064,0.0014067644,0.0008478758,0.014633844,0.00014239637],"about_ca_topic_score_codex":0.000029859868,"about_ca_topic_score_gemma":0.0000019557194,"teacher_disagreement_score":0.9396084,"about_ca_system_score_codex":0.00008702999,"about_ca_system_score_gemma":0.0006938313,"threshold_uncertainty_score":0.6322541},"labels":[],"label_agreement":null},{"id":"W4413926110","doi":"10.1109/tuffc.2025.3605285","title":"Grounding DINO-US-SAM: Text-Prompted Multiorgan Segmentation in Ultrasound With LoRA-Tuned Vision–Language Models","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Ultrasonics Ferroelectrics and Frequency Control","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Segmentation; Computer science; Computer vision; Artificial intelligence; Image segmentation","score_opus":0.00609714589514114,"score_gpt":0.26396040278681704,"score_spread":0.2578632568916759,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413926110","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38752624,0.0006152744,0.6091316,0.00095517567,0.0001867074,0.000755058,0.000017574486,0.00010348907,0.0007089082],"genre_scores_gemma":[0.9940426,0.0006648814,0.003473287,0.0013156461,0.000036276753,0.00010019232,0.000028764,0.00005057484,0.00028778397],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99779546,0.0001255768,0.00052196666,0.0005999105,0.00040921528,0.0005478624],"domain_scores_gemma":[0.9985867,0.00063450984,0.00012483668,0.00031273547,0.00012941612,0.00021180048],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00047364866,0.00035954468,0.0005522906,0.00071431266,0.00032041458,0.00013234606,0.00013604813,0.00019561945,0.000043599804],"category_scores_gemma":[0.00009903844,0.00030838465,0.00010951137,0.001171502,0.00013378263,0.00028440045,9.218253e-7,0.0011119061,0.0000033902031],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0027140237,0.0026484274,0.019362774,0.0005441136,0.0011407868,0.00036927278,0.0032771686,0.04079392,0.639462,0.004321483,0.00010051737,0.28526554],"study_design_scores_gemma":[0.03025804,0.002398427,0.018140942,0.0011963142,0.0011889418,0.00041863165,0.00088034035,0.92500556,0.016979113,0.0022856193,0.00009242542,0.001155658],"about_ca_topic_score_codex":0.0005517211,"about_ca_topic_score_gemma":0.00021282717,"teacher_disagreement_score":0.8842116,"about_ca_system_score_codex":0.00036190142,"about_ca_system_score_gemma":0.00023411185,"threshold_uncertainty_score":0.9999368},"labels":[],"label_agreement":null},{"id":"W4413942875","doi":"10.3390/diagnostics15172231","title":"[18F]FDG PET/CT Radiomics in Untreated Breast Carcinoma: A Review of the Current State and Future Directions","year":2025,"lang":"en","type":"review","venue":"Diagnostics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Radiomics; Breast carcinoma; Medicine; Nuclear medicine; Radiology; Breast cancer; Medical physics; Internal medicine; Cancer","score_opus":0.010503470354942692,"score_gpt":0.3193499888281132,"score_spread":0.3088465184731705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413942875","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00009902027,0.99534,0.0000057397747,0.00156702,0.0010322202,0.0013058846,0.00028996324,0.000019125715,0.00034104026],"genre_scores_gemma":[0.000019709463,0.9988614,0.000083198305,0.0002855108,0.0002649031,0.00007854434,0.00020509408,0.000039346,0.00016232546],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99802166,0.00028058147,0.000810855,0.0003639014,0.00025311433,0.00026986626],"domain_scores_gemma":[0.9978178,0.0010460331,0.00037171372,0.00051377516,0.00011075613,0.00013992327],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000400615,0.0003749195,0.0018504282,0.0002392759,0.000068462614,0.000017156712,0.00021011596,0.000024146126,0.000020868074],"category_scores_gemma":[0.001992164,0.0002373177,0.00036445924,0.0009328909,0.00015742074,0.000020679508,0.00014738203,0.0013999488,0.000003521349],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000020474188,0.00009517813,0.0014573694,0.13977395,0.0000583549,0.00020686148,0.000015475653,2.589488e-7,7.826792e-9,0.00003450539,0.0040584253,0.8542976],"study_design_scores_gemma":[0.00031315573,0.000015070292,0.0017507363,0.22416848,0.001725183,0.0014773683,0.0000032575747,0.000048629532,6.8891076e-8,0.000015196487,0.7703383,0.00014453998],"about_ca_topic_score_codex":0.00008946452,"about_ca_topic_score_gemma":0.000015592701,"teacher_disagreement_score":0.85415304,"about_ca_system_score_codex":0.00016308141,"about_ca_system_score_gemma":0.0008031955,"threshold_uncertainty_score":0.96775347},"labels":[],"label_agreement":null},{"id":"W4413998229","doi":"10.1002/mp.18078","title":"Feature level quantitative ultrasound and CT information fusion to predict the outcome of head &amp; neck cancer radiotherapy treatment: Enhanced principal component analysis","year":2025,"lang":"en","type":"article","venue":"Medical Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Toronto Metropolitan University; Health Sciences Centre; Sunnybrook Health Science Centre","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Terry Fox Research Institute","keywords":"Principal component analysis; Artificial intelligence; Radiation therapy; Support vector machine; Pattern recognition (psychology); Feature (linguistics); Medical imaging; Computer science; Medicine; Radiology","score_opus":0.027402639540685784,"score_gpt":0.3691947812038415,"score_spread":0.34179214166315575,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413998229","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7829067,0.00037646896,0.20419233,0.011628604,0.00016160196,0.00039099864,0.000034361237,0.000026029134,0.0002829323],"genre_scores_gemma":[0.9930254,0.00052389846,0.002478244,0.0031515653,0.00011849384,0.000040484527,0.00012890775,0.000009331584,0.0005236303],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9986668,0.00006772413,0.00032717007,0.00018503754,0.00055805343,0.00019520572],"domain_scores_gemma":[0.9989571,0.00036853016,0.00012829083,0.00025771206,0.00009178727,0.00019658754],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003110547,0.00016737831,0.00053066004,0.000119700344,0.000115266106,0.000022859784,0.00012367069,0.00005846781,0.00005340389],"category_scores_gemma":[0.00052126247,0.00010075642,0.00015116156,0.0006670952,0.00023828859,0.00007461524,0.000039067494,0.00034020666,0.0000021211874],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008827542,0.00071499334,0.5143305,0.00052617415,0.0044496427,0.000010865617,0.012163487,0.0035705785,0.007861763,0.0023303935,0.004917971,0.44824088],"study_design_scores_gemma":[0.009483206,0.0008749106,0.81989646,0.0010060179,0.002920862,0.000019947223,0.00047082815,0.06914327,0.004777542,0.0003738725,0.09057519,0.00045786944],"about_ca_topic_score_codex":0.00059914804,"about_ca_topic_score_gemma":0.00010958473,"teacher_disagreement_score":0.447783,"about_ca_system_score_codex":0.00013938721,"about_ca_system_score_gemma":0.00014327021,"threshold_uncertainty_score":0.41087276},"labels":[],"label_agreement":null},{"id":"W4414000490","doi":"10.18280/jesa.580708","title":"Development of a Comprehensive Lung Scan Dataset for Machine Learning-Based Lung Cancer Detection","year":2025,"lang":"en","type":"article","venue":"Journal Européen des Systèmes Automatisés","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Lung cancer; Artificial intelligence; Computed tomography; Computer science; Medical physics; Machine learning; Medicine; Radiology; Oncology","score_opus":0.017029281771292943,"score_gpt":0.32427314290305526,"score_spread":0.30724386113176233,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414000490","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49968976,0.006892476,0.48976204,0.0013606289,0.000852124,0.00091007835,0.00016489577,0.00015004264,0.00021796035],"genre_scores_gemma":[0.9483748,0.00017842998,0.049398102,0.0007469792,0.00019273457,0.00006432886,0.00030826777,0.00006348067,0.00067287456],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981246,0.0001588791,0.0007711929,0.00024303824,0.00036696318,0.0003353173],"domain_scores_gemma":[0.9986234,0.00019855394,0.00047447972,0.00018326179,0.00033392172,0.00018643837],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00060766557,0.00022372992,0.0005444389,0.0004006079,0.00046880773,0.00007258125,0.00017235079,0.000073705734,0.000084536034],"category_scores_gemma":[0.0004594468,0.00018499713,0.00014642131,0.0003375635,0.00011443797,0.00009216183,0.000058625155,0.0006151145,0.0000018426937],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005889195,0.0002520391,0.03334147,0.005965129,0.0012381499,0.000090371264,0.0007473792,0.013439034,0.041749112,0.00006167388,0.015138884,0.8873878],"study_design_scores_gemma":[0.0028803295,0.00012943923,0.13654408,0.0022680382,0.00040584712,0.00018262322,0.00008160521,0.811229,0.0035591894,0.000032916832,0.042508677,0.0001782292],"about_ca_topic_score_codex":0.000085402564,"about_ca_topic_score_gemma":0.000035434896,"teacher_disagreement_score":0.8872096,"about_ca_system_score_codex":0.0004419261,"about_ca_system_score_gemma":0.00064349634,"threshold_uncertainty_score":0.7543964},"labels":[],"label_agreement":null},{"id":"W4414004847","doi":"10.18103/mra.v12i12.6175","title":"The Invaluable Role of CEUS in HCC Imaging: Diagnosis, Management Planning, Guidance of Ablative Therapy, and Secondary Surveillance","year":2024,"lang":"en","type":"article","venue":"Medical Research Archives","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Ablative case; Medicine; Radiology; Medical physics; Radiation therapy","score_opus":0.026608112314831105,"score_gpt":0.38571302624453585,"score_spread":0.3591049139297047,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414004847","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6858472,0.23196903,0.00040011996,0.017772999,0.0001503323,0.0008164374,0.00001237549,0.000041918098,0.06298959],"genre_scores_gemma":[0.9595377,0.03893709,0.00065244304,0.00011840506,0.00008051688,0.00008366431,0.0000065304203,0.000020508789,0.0005631486],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99718195,0.00052024424,0.00039484157,0.00031064742,0.0011517374,0.00044056482],"domain_scores_gemma":[0.99414164,0.0052694096,0.000044998516,0.00025439312,0.00004390406,0.00024564477],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0041871853,0.000111597445,0.00030603725,0.00030555326,0.00009931611,0.000035196852,0.0003044597,0.000034464236,0.00011815953],"category_scores_gemma":[0.0029484818,0.000069730435,0.000056467332,0.00037289044,0.0015993767,0.000048927803,0.0002826323,0.001112977,0.000002216826],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022026464,0.000109776935,0.19746514,0.0005858845,0.00011368683,0.00030266977,0.0027019407,0.000009482637,0.00083827577,0.0050541046,0.002831957,0.78976685],"study_design_scores_gemma":[0.0020754314,0.00044005446,0.63356084,0.0052047335,0.000011064829,0.00005277007,0.0024203581,0.08761827,0.0013588566,0.023670506,0.24342434,0.00016280478],"about_ca_topic_score_codex":0.0002183989,"about_ca_topic_score_gemma":0.000020739197,"teacher_disagreement_score":0.789604,"about_ca_system_score_codex":0.000021766838,"about_ca_system_score_gemma":0.0003439551,"threshold_uncertainty_score":0.589297},"labels":[],"label_agreement":null},{"id":"W4414008101","doi":"10.1109/access.2025.3606838","title":"MLXOps4Medic: A Service Framework for Machine Learning and Explainability Operations in Medical Imaging AI Development","year":2025,"lang":"en","type":"article","venue":"IEEE Access","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Service (business); Artificial intelligence","score_opus":0.014651901827657401,"score_gpt":0.38647544437227,"score_spread":0.3718235425446126,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414008101","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48802266,0.00075008615,0.4303328,0.07904162,0.00050570257,0.0006853367,0.000001944445,0.00010718016,0.0005526531],"genre_scores_gemma":[0.9670997,0.00008599354,0.014722146,0.017554421,0.00015066136,0.00018493566,0.000027041677,0.000021692013,0.0001534025],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984535,0.000077914505,0.00043056323,0.00039727852,0.00031394995,0.00032678037],"domain_scores_gemma":[0.9989373,0.0004987927,0.000039234394,0.00016720452,0.0001429885,0.00021445988],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011227791,0.0001642991,0.0003421527,0.00022610747,0.00024236909,0.00011043813,0.00022076743,0.00011912362,0.00008838194],"category_scores_gemma":[0.0032373592,0.00014315655,0.00003636158,0.00045133405,0.000092480186,0.0001752275,0.00014266168,0.0009976601,0.0000019404629],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015926539,0.00025031442,0.7175504,0.0010043508,0.0000763031,0.00009324662,0.0014939327,0.00044206553,0.000206277,0.0033796788,0.00060751406,0.27473664],"study_design_scores_gemma":[0.0047917156,0.000052913245,0.09292886,0.0024222636,0.00009456194,0.000097891585,0.00041944222,0.8521783,0.00071288884,0.0073210495,0.03858853,0.00039162076],"about_ca_topic_score_codex":0.00047391356,"about_ca_topic_score_gemma":0.00032712432,"teacher_disagreement_score":0.8517362,"about_ca_system_score_codex":0.000115532566,"about_ca_system_score_gemma":0.0005222585,"threshold_uncertainty_score":0.58377546},"labels":[],"label_agreement":null},{"id":"W4414015774","doi":"10.11159/mhci25.001","title":"Improving Medical Imaging Efficiency with AI Algorithms Running on Dedicated AI Chips","year":2025,"lang":"en","type":"article","venue":"Proceedings of the World Congress on Electrical Engineering and Computer Systems and Science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Medical imaging; Artificial intelligence; Algorithm","score_opus":0.0028650087725615634,"score_gpt":0.22765682270549384,"score_spread":0.22479181393293227,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414015774","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92548466,0.0017982244,0.05223945,0.014726798,0.0027481066,0.0009126333,9.3570014e-7,0.0003501512,0.0017390256],"genre_scores_gemma":[0.9978236,0.000015955315,0.00048570285,0.0012263332,0.00015652807,0.000011482656,1.6573031e-7,0.000012563475,0.00026767782],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980919,0.0000057440398,0.0002908713,0.00046319384,0.0007469723,0.00040132742],"domain_scores_gemma":[0.9992319,0.00011248264,0.00010246817,0.0001189494,0.00018180274,0.00025245146],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00082925026,0.00019696273,0.0003519271,0.00048617128,0.00027925443,0.00020501747,0.0003480768,0.000042231102,7.345489e-7],"category_scores_gemma":[0.00027103408,0.0001186995,0.00003797002,0.0013393441,0.0003625747,0.00010424718,0.00014923555,0.0007934664,1.6735632e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00055885024,0.0007696102,0.18476886,0.0031794165,0.0003377211,0.00011957122,0.0005631825,0.01167652,0.023689333,0.22984311,0.005250202,0.53924364],"study_design_scores_gemma":[0.0007267354,0.00016686223,0.0067075114,0.0019506608,0.00002998614,0.00013226122,0.000008738888,0.9885622,0.00087902613,0.000012690313,0.00069251936,0.0001307722],"about_ca_topic_score_codex":0.000034514473,"about_ca_topic_score_gemma":2.022746e-7,"teacher_disagreement_score":0.97688574,"about_ca_system_score_codex":0.00005505019,"about_ca_system_score_gemma":0.0001410903,"threshold_uncertainty_score":0.48404253},"labels":[],"label_agreement":null},{"id":"W4414041568","doi":"10.1055/s-0045-1810854","title":"Malignant transformation from IPMN to invasive IPMN and PDAC is characterized by distinct shifts in body composition – an AI-based body composition analysis","year":2025,"lang":"en","type":"article","venue":"Zeitschrift für Gastroenterologie","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Composition (language); Malignant transformation; Transformation (genetics); Cancer","score_opus":0.00876399707389375,"score_gpt":0.2966913380346458,"score_spread":0.28792734096075207,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414041568","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8569305,0.000058085447,0.12609988,0.015679805,0.00010130108,0.00069801457,0.00022664525,0.00009561103,0.00011018355],"genre_scores_gemma":[0.978792,0.000042008804,0.0017399838,0.0151953595,0.00006065905,0.000096283526,0.004042367,0.000021325595,0.0000099976405],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9976539,0.00029158028,0.00064397254,0.0006071868,0.00032198033,0.00048138844],"domain_scores_gemma":[0.9990021,0.00012226473,0.00015096106,0.0003400318,0.000092447204,0.00029219943],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00042758707,0.00031857134,0.0007447062,0.000624518,0.00013910022,0.000118974116,0.00018095046,0.00014155684,0.00007786456],"category_scores_gemma":[0.00005868794,0.00028984746,0.00015894421,0.00047647147,0.00010706789,0.00028084015,0.00005575418,0.00050241646,0.000008109618],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0035019035,0.0008676391,0.4958692,0.00018561895,0.00056533824,0.000088541135,0.0006952582,0.0002189097,0.49252775,0.00006357667,0.00070408016,0.004712183],"study_design_scores_gemma":[0.007130136,0.0013060739,0.898753,0.0005495771,0.0011704168,0.0000073524157,0.00012981395,0.07145913,0.017859856,0.00003545036,0.0013362434,0.0002629903],"about_ca_topic_score_codex":0.00032711343,"about_ca_topic_score_gemma":0.000056404664,"teacher_disagreement_score":0.4746679,"about_ca_system_score_codex":0.000052992502,"about_ca_system_score_gemma":0.00005768566,"threshold_uncertainty_score":0.99995536},"labels":[],"label_agreement":null},{"id":"W4414048012","doi":"10.1016/j.ibreh.2025.100045","title":"Preventive, personalized, and precision medicine and biomarkers for breast cancer diagnosis: Artificial intelligence framework","year":2025,"lang":"en","type":"article","venue":"Innovative Practice in Breast Health","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; University of Toronto","funders":"","keywords":"Precision medicine; Breast cancer; Personalized medicine; Profiling (computer programming); Lobular carcinoma; Applications of artificial intelligence; Mammography; Invasive lobular carcinoma","score_opus":0.03186222235680831,"score_gpt":0.434178418866193,"score_spread":0.4023161965093847,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414048012","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05213305,0.010808455,0.09753644,0.8363612,0.0005587289,0.0018951395,0.00012389444,0.000052421554,0.0005306247],"genre_scores_gemma":[0.913708,0.01278664,0.041244864,0.030857444,0.00045905088,0.0007604841,0.000031457963,0.000046486708,0.00010562792],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9978876,0.0002787987,0.0006685994,0.000527347,0.0002725947,0.00036506166],"domain_scores_gemma":[0.99501854,0.0037844619,0.00035428634,0.0001679939,0.0005087738,0.00016594508],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026736357,0.00021366133,0.0005168125,0.00044155293,0.00019225467,0.00004086406,0.00008454597,0.00011879988,0.000078927726],"category_scores_gemma":[0.0062245294,0.00017638643,0.000026560283,0.001370659,0.00050435454,0.0002550004,0.00007927675,0.00078518287,7.671512e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019352769,0.00027459834,0.04714271,0.0005681061,0.00016781948,0.000012603291,0.0025936284,0.0000024922495,0.00006482032,0.02802907,0.0024777928,0.91673106],"study_design_scores_gemma":[0.0060556103,0.0014126608,0.74905163,0.034308475,0.00048659346,0.0021575615,0.026636073,0.017511223,0.00011068884,0.09000957,0.071345195,0.0009147355],"about_ca_topic_score_codex":0.0013809229,"about_ca_topic_score_gemma":0.00002589482,"teacher_disagreement_score":0.91581637,"about_ca_system_score_codex":0.00020972692,"about_ca_system_score_gemma":0.0005109852,"threshold_uncertainty_score":0.7451793},"labels":[],"label_agreement":null},{"id":"W4414142624","doi":"10.12809/hkjr2417805","title":"Can Machine Learning of Magnetic Resonance Imaging Textural Features Differentiate Intra- and Extra-Axial Brain Tumours? A Feasibility Study","year":2025,"lang":"en","type":"article","venue":"Hong Kong Journal of Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; University of Ottawa","funders":"","keywords":"Magnetic resonance imaging; Functional magnetic resonance imaging; Deep learning; Pattern recognition (psychology); Medical imaging","score_opus":0.00813194633211477,"score_gpt":0.2836992049049977,"score_spread":0.27556725857288294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414142624","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9682643,0.021883823,0.00072226446,0.008249335,0.00044677372,0.00027100072,0.0000032929015,0.0000193503,0.00013988417],"genre_scores_gemma":[0.9978425,0.00026389209,0.00081893924,0.00042114346,0.00020671923,0.0000020621999,0.0000043342184,0.000020101521,0.00042033492],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9977558,0.00061019306,0.0007289484,0.00029992987,0.00025567357,0.00034945342],"domain_scores_gemma":[0.99856746,0.00048853335,0.00039615986,0.00020456723,0.00016341957,0.00017988592],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013601639,0.00022943658,0.00089363253,0.00036404686,0.00012884071,0.000031366642,0.00020599188,0.00007874654,0.00003911368],"category_scores_gemma":[0.002088645,0.00017423606,0.00015355699,0.00022723278,0.0004092958,0.000066499386,0.00008643785,0.0014945769,2.3047068e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005987056,0.00021158876,0.93438154,0.00009172824,0.00007775559,0.000379097,0.0008491906,0.00003744058,0.009315296,0.00012338883,0.00073612627,0.05319816],"study_design_scores_gemma":[0.004844348,0.0011348815,0.98444605,0.000350543,0.0002603735,0.0034610205,0.0005448174,0.0040513165,0.00015054531,0.00040237248,0.00022457239,0.00012917086],"about_ca_topic_score_codex":0.00013825977,"about_ca_topic_score_gemma":0.00003276643,"teacher_disagreement_score":0.053068988,"about_ca_system_score_codex":0.00008443385,"about_ca_system_score_gemma":0.0001526698,"threshold_uncertainty_score":0.71051407},"labels":[],"label_agreement":null},{"id":"W4414156949","doi":"10.3390/s25175603","title":"DG-TTA: Out-of-Domain Medical Image Segmentation Through Augmentation, Descriptor-Driven Domain Generalization, and Test-Time Adaptation","year":2025,"lang":"en","type":"article","venue":"Sensors","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Discovery Air (Canada)","funders":"European Research Area Network on Cardiovascular Diseases; Bundesministerium für Bildung und Forschung","keywords":"Segmentation; Domain adaptation; Image segmentation; Consistency (knowledge bases); Bridging (networking); Pattern recognition (psychology); Scale-space segmentation; Adaptation (eye)","score_opus":0.011041446613985425,"score_gpt":0.3001524031973003,"score_spread":0.28911095658331487,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414156949","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8958649,0.00014271232,0.09018777,0.010865408,0.0003717949,0.00045199573,0.000009991893,0.00008517664,0.0020202447],"genre_scores_gemma":[0.67774546,0.00050915004,0.31014627,0.006379551,0.00042187094,0.0000430778,0.0004997077,0.000071189184,0.004183688],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99840444,0.0001412337,0.00047457663,0.00029467896,0.0004884412,0.00019659723],"domain_scores_gemma":[0.999141,0.00025312806,0.00014919773,0.0001688866,0.00016095761,0.00012684634],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042292842,0.0001584094,0.00029629437,0.00013770335,0.00012347738,0.00003182886,0.0000731971,0.0001077879,0.00018280908],"category_scores_gemma":[0.001126259,0.00014576272,0.000056825764,0.00025243132,0.00023895511,0.00013307777,0.00003778476,0.00020276032,0.000015251605],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000564534,0.0007880891,0.086177796,0.0013133205,0.00062489114,0.00024215228,0.03444957,0.002356447,0.76423454,0.019205077,0.044106293,0.045937307],"study_design_scores_gemma":[0.034573782,0.0013954749,0.10719187,0.003178254,0.0014868858,0.00031192208,0.021065308,0.69545984,0.06942142,0.023875412,0.0402513,0.0017885435],"about_ca_topic_score_codex":0.000090783185,"about_ca_topic_score_gemma":0.000011438272,"teacher_disagreement_score":0.69481313,"about_ca_system_score_codex":0.00009015411,"about_ca_system_score_gemma":0.00015446561,"threshold_uncertainty_score":0.59440315},"labels":[],"label_agreement":null},{"id":"W4414223005","doi":"10.1016/j.jvs.2025.06.037","title":"Reply","year":2025,"lang":"en","type":"letter","venue":"Journal of Vascular Surgery","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Michael's Hospital; University Health Network; Toronto Rehabilitation Institute; University of Toronto","funders":"","keywords":"Vascular surgery; Multidisciplinary approach; Amputation; Vascular disease; Clinical Practice; MEDLINE","score_opus":0.013052023760796408,"score_gpt":0.27129107208162495,"score_spread":0.25823904832082856,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414223005","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013913623,0.0055266465,0.001319086,0.9864287,0.0033632526,0.000094284165,0.0000018049193,0.000023947305,0.0018509408],"genre_scores_gemma":[0.00023164542,0.0023534112,0.0013882271,0.97982174,0.011478592,0.000001603691,0.000038829596,0.00005263008,0.004633322],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973522,0.00018556349,0.000977424,0.0002038081,0.00096987386,0.0003111508],"domain_scores_gemma":[0.99744743,0.00085202657,0.0007332108,0.00045692254,0.00037339827,0.00013700189],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0020723788,0.00023761191,0.0013537846,0.0008361166,0.000045701097,0.000043675278,0.00017770544,0.00039729502,0.0001785804],"category_scores_gemma":[0.0030836791,0.00018017786,0.0018590719,0.00024756262,0.00007160464,0.00006028669,0.0000412684,0.0047377255,0.000012714982],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020117666,0.000031023737,0.0019276859,0.00058072613,0.0009106919,0.01004653,0.000013187219,0.000003934953,0.000023473267,0.0000014488458,0.974573,0.011868178],"study_design_scores_gemma":[0.00036638856,0.000038280516,0.0007587724,0.002357873,0.00078974536,0.0019122334,0.00000439064,0.000064761654,0.00001983307,0.00006297571,0.99348086,0.00014386793],"about_ca_topic_score_codex":0.000019621779,"about_ca_topic_score_gemma":4.0399662e-8,"teacher_disagreement_score":0.018907875,"about_ca_system_score_codex":0.00011417321,"about_ca_system_score_gemma":0.0009855694,"threshold_uncertainty_score":0.99755836},"labels":[],"label_agreement":null},{"id":"W4414245527","doi":"10.4103/sijm.sijm_29_25","title":"Imaging Modalities: Cornerstones of Precision Medicine’s Future","year":2025,"lang":"en","type":"article","venue":"Sarvodaya International Journal of Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Interior Health","funders":"","keywords":"Interoperability; Operationalization; Modalities; Deep learning; Medical imaging; Software deployment; Health care; Digital health; Convolutional neural network","score_opus":0.009022143989473054,"score_gpt":0.3365589416251068,"score_spread":0.32753679763563376,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414245527","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21118625,0.021124855,0.047939725,0.63236827,0.024406854,0.0004456754,0.000010431972,0.000065330816,0.062452596],"genre_scores_gemma":[0.98323464,0.0020265125,0.002082548,0.0057987226,0.0048962436,0.000001822969,0.000018985982,0.000021964037,0.0019185703],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99696666,0.00008596812,0.0012244751,0.00018382803,0.001351861,0.000187224],"domain_scores_gemma":[0.99702764,0.0003815778,0.0007234992,0.00022153788,0.0014655645,0.000180179],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016134534,0.0001934305,0.00074106845,0.0010348991,0.000041957726,0.000009364901,0.000497598,0.00007542372,0.0006247075],"category_scores_gemma":[0.002638335,0.00012518906,0.00017110122,0.00032386227,0.0006364745,0.00014505694,0.00007615006,0.0006467694,0.0000023826249],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0030213683,0.00043035168,0.08442581,0.00049092533,0.0017463093,0.0010544076,0.004655374,0.00022277053,0.037548803,0.03362106,0.25533557,0.57744724],"study_design_scores_gemma":[0.042224027,0.0022278028,0.114181034,0.028786773,0.0017446878,0.005812519,0.017041188,0.014801046,0.0028793486,0.032751158,0.73701954,0.0005309044],"about_ca_topic_score_codex":0.00010436281,"about_ca_topic_score_gemma":0.0000014361832,"teacher_disagreement_score":0.77204835,"about_ca_system_score_codex":0.00015253127,"about_ca_system_score_gemma":0.00025514606,"threshold_uncertainty_score":0.68401086},"labels":[],"label_agreement":null},{"id":"W4414282987","doi":"10.3390/targets3030029","title":"Contrast-Enhanced Mammography as a Functional Biomarker in Breast Cancer: Correlation of Enhancement Patterns with Ki-67 and Histological Grade","year":2025,"lang":"en","type":"article","venue":"Targets","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mount Sinai Hospital","funders":"","keywords":"Mammography; Breast cancer; Histology; Correlation; Lesion; Biomarker; Imaging biomarker; Breast tumor","score_opus":0.0074345339576226445,"score_gpt":0.2668992532431752,"score_spread":0.25946471928555254,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414282987","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9612843,0.00090071565,0.0314472,0.0049447967,0.0001801683,0.00024288493,0.00000760669,0.000019666408,0.00097271235],"genre_scores_gemma":[0.9982615,0.00022920752,0.0004232785,0.00074239646,0.00001921822,0.00004060613,0.000030323039,0.0000064869405,0.00024695936],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99920803,0.000033472683,0.00021204649,0.0002131305,0.00017504254,0.00015829355],"domain_scores_gemma":[0.9996621,0.000058094643,0.000078335026,0.00008302503,0.000050687086,0.00006776847],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013881784,0.00010454475,0.00024306889,0.00016771619,0.00003398635,0.0000054720804,0.000030912277,0.000054249853,0.00024341288],"category_scores_gemma":[0.00003057905,0.00007745604,0.000034428595,0.00017835927,0.00012479689,0.00003310916,0.000017821132,0.0002013759,0.0000010614085],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009271566,0.00025412798,0.9441311,0.00014026107,0.00013095989,0.000024928946,0.00015704156,0.000056021996,0.028669396,0.00042337057,0.00064008805,0.024445556],"study_design_scores_gemma":[0.002604406,0.00011204512,0.99092805,0.00039302433,0.00006994855,0.000033329597,0.000047992085,0.0041844696,0.00088399183,0.00015543484,0.00050799665,0.00007929652],"about_ca_topic_score_codex":0.0005813834,"about_ca_topic_score_gemma":0.00005073922,"teacher_disagreement_score":0.046796974,"about_ca_system_score_codex":0.000055482087,"about_ca_system_score_gemma":0.000067555724,"threshold_uncertainty_score":0.31585658},"labels":[],"label_agreement":null},{"id":"W4414310538","doi":"10.3390/biomedicines13092285","title":"Artificial Intelligence in the Diagnosis and Treatment of Brain Gliomas","year":2025,"lang":"en","type":"review","venue":"Biomedicines","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Interpretability; Radiogenomics; Radiomics; Deep learning; Neuroimaging; Glioma; Immunotherapy; Molecular imaging; Bench to bedside","score_opus":0.07106096587037072,"score_gpt":0.41183179199847886,"score_spread":0.34077082612810816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414310538","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00011288043,0.9925468,0.0001037614,0.0057808585,0.000244918,0.00086701487,0.000010314731,0.000013777927,0.00031967834],"genre_scores_gemma":[0.00014521924,0.99856627,0.00022368465,0.00027564357,0.00039983698,0.00018003967,0.0000577279,0.00001476107,0.00013678959],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984946,0.00015070578,0.00065282156,0.00028719803,0.00023086416,0.00018380853],"domain_scores_gemma":[0.9977893,0.0016476057,0.00016642318,0.00030134484,0.000025251307,0.00007004609],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047593284,0.0002612798,0.0013916346,0.00061495375,0.000033334156,0.000011675318,0.00014442847,0.00014479051,0.000023716484],"category_scores_gemma":[0.000844942,0.00012924064,0.00018793941,0.0008840826,0.00033350632,0.000012696719,0.0000295199,0.00019690144,0.0000026621951],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007504321,0.00018753063,0.00016852388,0.0074672927,0.00007507184,0.00010898525,0.00030452598,3.9132534e-8,0.0000010880043,0.00031908028,0.00078267086,0.9905777],"study_design_scores_gemma":[0.00013070795,0.0004745273,0.00009340929,0.020817958,0.0008408518,0.000120508,0.00014452064,0.00005428785,0.0000032578967,0.00017664411,0.97704005,0.00010330496],"about_ca_topic_score_codex":0.00017037953,"about_ca_topic_score_gemma":0.0000119365495,"teacher_disagreement_score":0.9904744,"about_ca_system_score_codex":0.000055768563,"about_ca_system_score_gemma":0.00019467059,"threshold_uncertainty_score":0.527028},"labels":[],"label_agreement":null},{"id":"W4414343118","doi":"10.1007/978-3-032-05162-2","title":"Medical Image Computing and Computer Assisted Intervention – MICCAI 2025","year":2025,"lang":"en","type":"book","venue":"Lecture notes in computer science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Erasmus Universitair Medisch Centrum Rotterdam; University of North Carolina at Greensboro; University of Colorado Denver; University of Texas MD Anderson Cancer Center; University of California, Los Angeles; Helmholtz Artificial Intelligence Cooperation Unit; Stony Brook University; ShanghaiTech University; Johns Hopkins University; Harbin Institute of Technology; Universität Innsbruck; University of Science and Technology of China; Shenzhen University; Universidade do Minho; Julius-Maximilians-Universität Würzburg; National University of Singapore; Zayed University; Rheinische Friedrich-Wilhelms-Universität Bonn; Peking University; Monash University; Universitat Rovira i Virgili; Indian Institute of Technology Delhi; Uniwersytet Warszawski; Hokkaido University; Institute of Computing Technology, Chinese Academy of Sciences; Nanjing University of Science and Technology; Korea University Anam Hospital; Cleveland Clinic; Shanghai Jiao Tong University; Siemens Healthineers; Università degli Studi di Messina; Zhejiang University; Kungliga Tekniska Högskolan; Tongji University; Hebrew University of Jerusalem; Huazhong University of Science and Technology; Eidgenössische Technische Hochschule Zürich; McMaster University; Technische Universiteit Eindhoven; RIKEN; Concordia University; Chalmers Tekniska Högskola; National Institutes of Health; Anhui University; Indian Institute of Technology Jodhpur; Technische Universität München; Kyung Hee University; University of Exeter; Chinese Academy of Sciences; Shandong University; Nanyang Technological University; University of Electronic Science and Technology of China; Université de Lausanne; Boston College; University of Westminster; University of Leeds; University of Oxford; Medizinische Universität Innsbruck; Imperial College London; King's College London; Northwestern University; Rensselaer Polytechnic Institute; University of North Carolina at Chapel Hill; Politecnico di Torino; University of Twente; Beihang University; Intuitive Surgical; University of Cape Town; Massachusetts General Hospital; University College London; University of Notre Dame; Polytechnique Montréal; Heriot-Watt University; Norges Teknisk-Naturvitenskapelige Universitet; Karolinska Institutet; Yale University; Weill Cornell Medical College; University of Pennsylvania; Xiamen University; Univerza v Ljubljani; Universitätsspital Basel; Vanderbilt University; Fudan University; Tencent; Université de Sfax; University of Bern; Daegu Gyeongbuk Institute of Science and Technology; Korea University; Northwestern Polytechnical University; Children's National Hospital; Harvard University; Deutsches Krebsforschungszentrum; Beijing Institute of Technology; Agency for Science, Technology and Research; East China Normal University; Gachon University; Université de Strasbourg; Universidad de Zaragoza; Robarts Research Institute; Eberhard Karls Universität Tübingen; Memorial Sloan-Kettering Cancer Center; Universidade de Coimbra; University of Texas at Arlington; Yonsei University; Rowan University; Nanjing University; Oulun Yliopisto; Pohang University of Science and Technology; Nile University; South China University of Technology","keywords":"Intervention (counseling); Image (mathematics); Image processing; Computer Applications; Medical imaging","score_opus":0.008348370353227082,"score_gpt":0.30890641167883337,"score_spread":0.30055804132560626,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414343118","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014811184,0.00085592276,0.98889685,0.0039121294,0.002042389,0.0003726508,0.0000027009842,0.000119224744,0.0023169974],"genre_scores_gemma":[0.10637149,0.00026991928,0.85922945,0.0229222,0.005195549,0.000012128968,0.00021831416,0.00012211764,0.0056588044],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964209,0.00010930317,0.0006811538,0.0011327974,0.0010969879,0.00055886054],"domain_scores_gemma":[0.99792176,0.0007906756,0.00022626901,0.00050340756,0.00020549496,0.000352365],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0018555885,0.00042048056,0.00082476175,0.00081208046,0.000204822,0.00026266454,0.0006681581,0.00042146732,0.00007071479],"category_scores_gemma":[0.0008131901,0.0003632181,0.00017793725,0.0005929152,0.001230396,0.00011765339,0.0010459697,0.0021975967,0.000010074861],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019264311,0.00009041122,0.0007696126,0.00058849785,0.00004287085,0.00040201558,0.0002353473,0.00048791998,0.000053060412,0.000113580165,0.002066852,0.99513054],"study_design_scores_gemma":[0.0014288172,0.00019920472,0.0045394576,0.006668538,0.00006535531,0.0005211535,3.847318e-7,0.9808368,0.000052443094,0.0018515625,0.0034895549,0.00034674132],"about_ca_topic_score_codex":0.000046548652,"about_ca_topic_score_gemma":0.000015258507,"teacher_disagreement_score":0.9947838,"about_ca_system_score_codex":0.00036824567,"about_ca_system_score_gemma":0.001197784,"threshold_uncertainty_score":0.999882},"labels":[],"label_agreement":null},{"id":"W4414347583","doi":"10.1093/noajnl/vdaf206","title":"Saturation Transfer Imaging Radiomics using Machine Learning Improves Differentiation of Tumour Progression from Radiation Necrosis in Brain Metastases","year":2025,"lang":"en","type":"article","venue":"Neuro-Oncology Advances","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Sunnybrook Hospital; Sunnybrook Health Science Centre; St. Michael's Hospital","funders":"Canadian Institutes of Health Research; Lotte and John Hecht Memorial Foundation","keywords":"Radiomics; Magnetization transfer; Radiosurgery; Classifier (UML); Transfer of learning; Magnetic resonance imaging; Pattern recognition (psychology)","score_opus":0.008482336203272559,"score_gpt":0.3185820326368007,"score_spread":0.31009969643352814,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414347583","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96372527,0.0040963474,0.026350826,0.004685961,0.00055040757,0.00043230495,0.0000098767605,0.0000613984,0.00008761161],"genre_scores_gemma":[0.99209297,0.00053380046,0.00611391,0.0009254074,0.00009546799,0.000020038424,0.00018170521,0.00002281104,0.0000139206095],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99820834,0.00039965697,0.00056138454,0.00038585617,0.00020033511,0.00024443332],"domain_scores_gemma":[0.99877924,0.0007547412,0.00020795332,0.0001313916,0.00006402665,0.00006264873],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004074292,0.00019442661,0.0005136596,0.00039418388,0.0001240609,0.000024678488,0.00009615811,0.00009525885,0.000017510381],"category_scores_gemma":[0.0012210569,0.00017326068,0.00009591132,0.00038189426,0.00013413638,0.00032692484,0.0000344727,0.00063135516,4.841827e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029680383,0.00011450964,0.1384125,0.000082601175,0.000022844302,0.000015789094,0.00022984839,0.0013782183,0.6764646,0.00007638639,0.000014653749,0.18289122],"study_design_scores_gemma":[0.006113338,0.0003639208,0.14826931,0.00043496653,0.00036703658,0.000028232751,0.00023934721,0.64870024,0.18767951,0.0008763274,0.0066712447,0.00025651322],"about_ca_topic_score_codex":0.00018717324,"about_ca_topic_score_gemma":0.000049463575,"teacher_disagreement_score":0.647322,"about_ca_system_score_codex":0.00015417725,"about_ca_system_score_gemma":0.00014442921,"threshold_uncertainty_score":0.70653653},"labels":[],"label_agreement":null},{"id":"W4414349817","doi":"10.1158/1538-7445.ovarian25-a018","title":"Abstract A018: Identifying and integrating global ovarian cancer patient priorities to guide artificial intelligence (AI) research in ovarian cancer","year":2025,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Ovarian Cancer Canada","funders":"","keywords":"Ovarian cancer; Context (archaeology); Disease; Cancer; Implementation research; Qualitative research; Alliance; MEDLINE","score_opus":0.12218855035724274,"score_gpt":0.5186538183863431,"score_spread":0.3964652680291003,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414349817","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9176396,0.0077454904,0.0024371378,0.061290093,0.0012255055,0.0016532444,0.000053283176,0.00006268182,0.007892973],"genre_scores_gemma":[0.9937175,0.0014510779,0.0011775438,0.0013292155,0.00059865444,0.0007513749,0.0000059974577,0.000036205165,0.0009324167],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99520636,0.00038016337,0.00075238623,0.0008790753,0.001420102,0.0013618978],"domain_scores_gemma":[0.99762535,0.00047480015,0.00006190685,0.0004438517,0.00090995093,0.00048412822],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0045455066,0.00023961229,0.00046878384,0.0009225023,0.00053962856,0.00039858095,0.0004170988,0.00017474353,0.00046492662],"category_scores_gemma":[0.0020521595,0.00021845012,0.000066459696,0.002589126,0.0005522876,0.00018052904,0.0005478931,0.0027122553,0.000016253245],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00058390276,0.00012794764,0.069738254,0.0008786768,0.00011625777,0.0003171132,0.003985683,0.00047447067,0.025095202,0.011267373,0.010801126,0.876614],"study_design_scores_gemma":[0.0045109056,0.0012785883,0.51725054,0.05845055,0.00021919087,0.00010459846,0.051697023,0.033775833,0.064985275,0.07200287,0.19326867,0.002455984],"about_ca_topic_score_codex":0.095987946,"about_ca_topic_score_gemma":0.015588798,"teacher_disagreement_score":0.874158,"about_ca_system_score_codex":0.002720105,"about_ca_system_score_gemma":0.0028970335,"threshold_uncertainty_score":0.99958855},"labels":[],"label_agreement":null},{"id":"W4414350018","doi":"10.1007/978-3-032-04971-1_10","title":"ConStyX: Content Style Augmentation for Generalizable Medical Image Segmentation","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Image segmentation; Segmentation; Image (mathematics); Image processing; Pattern recognition (psychology); Scale-space segmentation","score_opus":0.02058843324833159,"score_gpt":0.31118274765494897,"score_spread":0.29059431440661737,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414350018","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00028335987,0.00033848657,0.9888678,0.005444936,0.0012401147,0.00081644516,0.000009980714,0.000058138045,0.0029406918],"genre_scores_gemma":[0.012889459,0.0002650146,0.9595217,0.01940921,0.0012245696,0.000066011824,0.00030043034,0.00006008019,0.0062635094],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976562,0.000020551433,0.0004520101,0.0006708972,0.0008547958,0.00034553514],"domain_scores_gemma":[0.99868655,0.00039538974,0.00016793137,0.00030347786,0.00024260182,0.00020403112],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009032243,0.00026490833,0.00045226017,0.00041267904,0.00015925936,0.000115390976,0.00032298063,0.00021715296,0.00016475229],"category_scores_gemma":[0.00057443365,0.00022716793,0.00011820524,0.00015139898,0.00062388,0.00011188556,0.000149176,0.00058853877,0.000007155922],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007106055,0.00005818756,0.00028614857,0.00035989942,0.000055932232,0.000093198825,0.00030116056,0.0017250456,0.0033377402,0.004447386,0.0013776948,0.98788655],"study_design_scores_gemma":[0.002808809,0.00029215505,0.00010204782,0.0015806847,0.00010222171,0.00010789351,0.0000016757712,0.97652906,0.0031822806,0.009545042,0.005385212,0.00036292739],"about_ca_topic_score_codex":0.00004833286,"about_ca_topic_score_gemma":0.000016065223,"teacher_disagreement_score":0.9875236,"about_ca_system_score_codex":0.00032034473,"about_ca_system_score_gemma":0.00082514354,"threshold_uncertainty_score":0.92636395},"labels":[],"label_agreement":null},{"id":"W4414370752","doi":"10.1101/2025.09.17.25335756","title":"Tract-based Quantitative MRI for Resolving the Clinico-Radiological Paradox in Multiple Sclerosis","year":2025,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Tamkeen; Multiple Sclerosis Society; York University; New York University Abu Dhabi","keywords":"Multiple sclerosis; Diffusion MRI; Fractional anisotropy; Lesion; White matter; Magnetic resonance imaging; Expanded Disability Status Scale; Neuroradiology","score_opus":0.11671715558699153,"score_gpt":0.3739828500924988,"score_spread":0.2572656945055073,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414370752","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9206853,0.0020514638,0.04465041,0.028057773,0.0012394659,0.0022255762,0.000074288284,0.00013954345,0.0008762126],"genre_scores_gemma":[0.96365625,0.00044715236,0.031382978,0.0033330068,0.00030227212,0.00038652666,0.00013285664,0.000038856993,0.00032008742],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971886,0.00041546812,0.0008160007,0.0007796277,0.00032091205,0.0004793614],"domain_scores_gemma":[0.9932257,0.0055136834,0.0002961463,0.00069910055,0.00011656278,0.00014880631],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0030830575,0.0003493708,0.00093753426,0.00023939941,0.00015518989,0.00005228593,0.00050470367,0.0004146717,0.000036276946],"category_scores_gemma":[0.010334435,0.00022913134,0.00045094083,0.0002347726,0.0003381584,0.000024461535,0.00021037523,0.0024668628,0.000008861209],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014875816,0.0009443126,0.9487256,0.0014064402,0.0002637232,0.0001252984,0.0015188442,0.01935756,0.001370694,0.0015592411,0.005740907,0.017499842],"study_design_scores_gemma":[0.0038513253,0.00032883658,0.36219084,0.0026738069,0.00025504708,0.000006992273,0.0002224924,0.6132355,0.00020925351,0.0011470049,0.015513958,0.00036496605],"about_ca_topic_score_codex":0.00015471171,"about_ca_topic_score_gemma":0.000030304514,"teacher_disagreement_score":0.5938779,"about_ca_system_score_codex":0.0001229651,"about_ca_system_score_gemma":0.00038522406,"threshold_uncertainty_score":0.9998345},"labels":[],"label_agreement":null},{"id":"W4414393464","doi":"10.1038/s44303-025-00104-z","title":"Radiomics in preclinical imaging research: methods, challenges and opportunities","year":2025,"lang":"en","type":"review","venue":"npj Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Capital District Health Authority; Izaak Walton Killam Health Centre; Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada; Beatrice Hunter Cancer Research Institute; Cancer Research Institute","keywords":"Radiomics; Context (archaeology); Medical imaging; Disease; Precision medicine","score_opus":0.4077714123931623,"score_gpt":0.5648616776765055,"score_spread":0.15709026528334324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414393464","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000019960428,0.9679376,0.0006129031,0.008729277,0.00050114735,0.00087067374,0.000006316755,0.00011919986,0.021220915],"genre_scores_gemma":[0.00000895189,0.98029965,0.017151073,0.00065638416,0.00048540102,0.00012383597,0.000057429676,0.00011675149,0.001100507],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99401695,0.0022025981,0.0012469951,0.0010929701,0.00052798085,0.0009125319],"domain_scores_gemma":[0.9933018,0.005104304,0.0002582135,0.0007726226,0.00015661081,0.0004064335],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.010503641,0.00056383805,0.0027872156,0.0018704748,0.00016447845,0.00014140067,0.00041576813,0.00023721151,0.00003192429],"category_scores_gemma":[0.005586349,0.00048821888,0.00038127758,0.0004023851,0.0007137199,0.00016746818,0.00060000946,0.0040314626,0.00000817062],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010367256,0.00006044372,0.00007842897,0.025159027,0.00007915699,0.0005871314,0.00027117223,1.4141622e-7,7.469052e-7,0.0015484196,0.0010975166,0.9711074],"study_design_scores_gemma":[0.0006372446,0.000019235138,0.000048186605,0.05500185,0.00049063435,0.0007232387,0.00041620276,0.002127226,3.4142988e-7,0.0009783854,0.93919903,0.00035842555],"about_ca_topic_score_codex":0.000049649658,"about_ca_topic_score_gemma":0.0000023494654,"teacher_disagreement_score":0.970749,"about_ca_system_score_codex":0.0002915007,"about_ca_system_score_gemma":0.0011722853,"threshold_uncertainty_score":0.99975693},"labels":[],"label_agreement":null},{"id":"W4414399915","doi":"10.1016/s0167-8140(25)04664-x","title":"AUTOMATED CBCT-BASED TUMOUR VOLUME TRACKING IS PROGNOSTIC IN VIRALLY-MEDIATED HEAD &amp; NECK CANCER","year":2025,"lang":"en","type":"article","venue":"Radiotherapy and Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre","funders":"","keywords":"Head and neck cancer; Cone beam computed tomography; Radiation therapy; Chemoradiotherapy; Head and neck; Cancer; Chemotherapy; Image-guided radiation therapy","score_opus":0.015070154498835907,"score_gpt":0.35460983863627027,"score_spread":0.33953968413743435,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414399915","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9509724,0.0056768693,0.0023587362,0.039214574,0.00038514924,0.000505847,0.0000064638753,0.00027534846,0.00060465635],"genre_scores_gemma":[0.9622272,0.0013466607,0.006543423,0.028388426,0.00019820934,0.00009425311,0.000042562144,0.000040274947,0.0011189603],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9985675,0.00014782211,0.00038146184,0.00036945246,0.0001357453,0.00039799965],"domain_scores_gemma":[0.99926186,0.0002863464,0.00009504851,0.00015894305,0.000053459902,0.00014431635],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000373745,0.00019633748,0.00058779656,0.0003095867,0.00008745694,0.000028060902,0.00009954398,0.0002286775,0.00030250807],"category_scores_gemma":[0.0002805856,0.00017292684,0.00006910585,0.0004293546,0.00018073949,0.000048847203,0.000014272699,0.00057707966,0.0000075248095],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007263056,0.0005490594,0.79688364,0.0003206688,0.00018235369,0.00025485523,0.0012427724,0.00047720157,0.036359668,0.00008930936,0.01822089,0.14469327],"study_design_scores_gemma":[0.007912962,0.0004636136,0.39853173,0.0005185125,0.000074830816,0.00005139917,0.00003132372,0.33520567,0.00017905221,0.000048187776,0.2567842,0.0001985355],"about_ca_topic_score_codex":0.0006554263,"about_ca_topic_score_gemma":0.00038571513,"teacher_disagreement_score":0.39835194,"about_ca_system_score_codex":0.00049514056,"about_ca_system_score_gemma":0.0006002687,"threshold_uncertainty_score":0.7051752},"labels":[],"label_agreement":null},{"id":"W4414413354","doi":"10.1002/mp.70026","title":"Radiation therapy response prediction for head and neck cancer using multimodal imaging and multiview dynamic graph autoencoder feature selection","year":2025,"lang":"en","type":"article","venue":"Medical Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Toronto Metropolitan University; Health Sciences Centre; Sunnybrook Health Science Centre","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Autoencoder; Head and neck cancer; Medical imaging; Feature (linguistics); Radiation therapy; Feature selection; Pattern recognition (psychology); Image-guided radiation therapy; Radiation treatment planning","score_opus":0.009356078743038993,"score_gpt":0.33861827461444866,"score_spread":0.32926219587140965,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414413354","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.71028495,0.0045414115,0.27138478,0.012754511,0.00037369528,0.0005453985,0.000011143447,0.00008883128,0.000015263637],"genre_scores_gemma":[0.9882674,0.002837908,0.0052636666,0.0029255943,0.0003838646,0.000069424925,0.000044241373,0.000034286033,0.000173592],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988807,0.00009091675,0.00019198259,0.0003303572,0.00027627603,0.00022976122],"domain_scores_gemma":[0.99935126,0.00023026076,0.00007025137,0.00009715201,0.00008400131,0.00016705394],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00052294234,0.00015901041,0.00027893417,0.000100849604,0.00022069634,0.000033249667,0.000041832194,0.0001166197,0.000008008877],"category_scores_gemma":[0.0005076031,0.0001363854,0.00006303419,0.000255447,0.00019638658,0.00011376267,0.000023757946,0.0004685907,1.62938e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008729568,0.00012333844,0.09671615,0.0002386212,0.00011164556,0.0000049251216,0.00035762234,0.0002349685,0.007056227,0.00005236811,0.00085893885,0.89337224],"study_design_scores_gemma":[0.003964899,0.000086584485,0.13672286,0.000551937,0.00010070358,0.000024804873,0.000020378542,0.85476935,0.0002641001,0.0007502912,0.0026429482,0.0001011691],"about_ca_topic_score_codex":0.00015365274,"about_ca_topic_score_gemma":0.0000072574776,"teacher_disagreement_score":0.8932711,"about_ca_system_score_codex":0.000121335295,"about_ca_system_score_gemma":0.00024133535,"threshold_uncertainty_score":0.5561635},"labels":[],"label_agreement":null},{"id":"W4414419288","doi":"10.3390/bioengineering12101008","title":"Evaluation of UNeXt for Automatic Bone Surface Segmentation on Ultrasound Imaging in Image-Guided Pediatric Surgery","year":2025,"lang":"en","type":"article","venue":"Bioengineering","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Segmentation; Pelvis; Ultrasound; Thorax (insect anatomy); Image segmentation; 3D ultrasound; Dice","score_opus":0.02222821343949334,"score_gpt":0.3289550872747537,"score_spread":0.30672687383526037,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414419288","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9715345,0.0007843525,0.025799612,0.0006534817,0.00037240193,0.00055146514,0.0000027061076,0.00006791897,0.00023360067],"genre_scores_gemma":[0.9892528,0.00006591482,0.010389469,0.00008329452,0.000084672945,0.0000332019,0.000033510398,0.00002028292,0.000036853202],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99879813,0.000048296824,0.0004144076,0.00018140096,0.0003669832,0.00019080237],"domain_scores_gemma":[0.9989871,0.00057697983,0.00008941297,0.0001458144,0.00015767857,0.00004301974],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022626861,0.00011708059,0.00026935898,0.0004194728,0.000026563193,0.000017050714,0.000040374656,0.00003461892,0.000016351469],"category_scores_gemma":[0.0023993119,0.000117028896,0.00008029725,0.00041226536,0.000018738232,0.00007081352,0.000010011199,0.00012390202,0.0000017033364],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007515511,0.00036333266,0.22096846,0.0035520743,0.0001323343,0.00001927566,0.0005266873,0.13512897,0.5080548,0.0003033926,0.0063050254,0.124570504],"study_design_scores_gemma":[0.0017064932,0.000021183805,0.075720325,0.00043021483,0.0002760938,0.000009885393,0.000086354805,0.9124267,0.009056624,0.000100657766,0.00004723775,0.00011822207],"about_ca_topic_score_codex":0.00003303526,"about_ca_topic_score_gemma":7.6378655e-7,"teacher_disagreement_score":0.77729774,"about_ca_system_score_codex":0.00021446933,"about_ca_system_score_gemma":0.00016355244,"threshold_uncertainty_score":0.47722998},"labels":[],"label_agreement":null},{"id":"W4414465220","doi":"10.1158/2326-6074.cimm25-a001","title":"Abstract A001: nELISA high-throughput protein profiling applied to the RADIOHEAD cohort: insights from the largest plasma proteomics study of patients receiving checkpoint inhibitor therapy","year":2025,"lang":"en","type":"article","venue":"Cancer Immunology Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Proteomics; Pembrolizumab; Biomarker discovery; Immunotherapy; Antibody; Antibody microarray; Biomarker; Limiting; Chemokine","score_opus":0.030574614917593085,"score_gpt":0.35456210833617924,"score_spread":0.3239874934185861,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414465220","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98029363,0.001621545,0.0000743179,0.008822811,0.00053662405,0.008101659,0.000014068941,0.000043755314,0.00049158535],"genre_scores_gemma":[0.9955753,0.0003792566,0.00043884057,0.00041641222,0.0003674392,0.0025164937,0.00003843986,0.000043738386,0.0002240618],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99691904,0.00049523154,0.0006437281,0.0006245499,0.0007299363,0.0005875458],"domain_scores_gemma":[0.99767375,0.0006287915,0.0001771124,0.00095117965,0.00048140757,0.00008773168],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0017315216,0.00024554622,0.000553082,0.00021279194,0.0005955526,0.00006888888,0.0007398448,0.00018333239,0.000055393833],"category_scores_gemma":[0.0011225473,0.0001406218,0.000071949,0.00083549664,0.0004968654,0.00005920793,0.00038482493,0.0023582599,0.000017239787],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0058198543,0.0025163754,0.31521684,0.00017468623,0.002119192,0.000023955407,0.01141506,0.00035333604,0.55279994,0.0006598052,0.0029159754,0.105984986],"study_design_scores_gemma":[0.0067900894,0.000746234,0.8692913,0.0005624351,0.000053775722,9.1478023e-7,0.002388232,0.00030642777,0.11407826,0.00027809857,0.0053194696,0.00018476957],"about_ca_topic_score_codex":0.004462553,"about_ca_topic_score_gemma":0.00022159703,"teacher_disagreement_score":0.55407447,"about_ca_system_score_codex":0.00034368414,"about_ca_system_score_gemma":0.0006116847,"threshold_uncertainty_score":0.9999433},"labels":[],"label_agreement":null},{"id":"W4414472106","doi":"10.3390/curroncol32100533","title":"Deep Learning-Based 30-Day Mortality Prediction in Critically Ill Bone and Bone Marrow Metastasis Patients: A Multicenter Retrospective Cohort Study","year":2025,"lang":"en","type":"article","venue":"Current Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Xinjiang Medical University","keywords":"Critically ill; Retrospective cohort study; Logistic regression; Univariate analysis; Cohort; Cohort study; Intensive care unit; Intensive care","score_opus":0.019910614245286465,"score_gpt":0.3657455581241438,"score_spread":0.3458349438788573,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414472106","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98765534,0.0008307896,0.0064768936,0.0016309707,0.0010366337,0.0014100686,0.000009327067,0.0000823686,0.00086758926],"genre_scores_gemma":[0.9984212,0.000087700995,0.000244332,0.000812388,0.00008446259,0.00017117707,0.0000895489,0.000019354615,0.000069866204],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9974457,0.0006205642,0.0006170509,0.0005921066,0.00035749108,0.00036706857],"domain_scores_gemma":[0.99862796,0.0002706117,0.0001301421,0.00023567495,0.0005520067,0.00018357455],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001572982,0.00021607337,0.0007626246,0.00032143525,0.000109512155,0.000023403969,0.00006501536,0.00011890397,0.00016748268],"category_scores_gemma":[0.006340679,0.00019513548,0.00008477914,0.00029208796,0.00025049516,0.00006595618,0.00009650943,0.0011537088,0.000007736477],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012617432,0.0034326783,0.950929,0.00013009987,0.00013854877,0.00007007553,0.00037215557,0.00006252461,0.000028714576,0.00003099472,0.0003955514,0.04428352],"study_design_scores_gemma":[0.0069564465,0.0009802623,0.8846199,0.00014393618,0.0005142851,0.0000022453744,0.0002928574,0.10059717,0.0000052059595,0.00004081661,0.005731291,0.00011558032],"about_ca_topic_score_codex":0.000072829425,"about_ca_topic_score_gemma":0.00007105614,"teacher_disagreement_score":0.10053465,"about_ca_system_score_codex":0.00058361073,"about_ca_system_score_gemma":0.00011777757,"threshold_uncertainty_score":0.7957394},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W4414555061","doi":"10.3390/arm93050039","title":"NSCLC EGFR Mutation Prediction via Random Forest Model: A Clinical–CT–Radiomics Integration Approach","year":2025,"lang":"en","type":"article","venue":"Advances in respiratory medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec en Outaouais","funders":"Université Hassan II de Casablanca","keywords":"Random forest; Epidermal growth factor receptor; Feature selection; Genotyping; Lung cancer; Mutation; Precision and recall; Feature (linguistics); Cohort","score_opus":0.02387018802319279,"score_gpt":0.374591916578327,"score_spread":0.3507217285551342,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414555061","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09017014,0.009699563,0.8732037,0.00233267,0.0013677055,0.0010975399,0.0000034560512,0.00018986838,0.021935347],"genre_scores_gemma":[0.9811387,0.0020372213,0.0083728125,0.0068991305,0.0007888864,0.00015973463,0.000145063,0.000045428784,0.00041299046],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99698025,0.0002604853,0.0013165198,0.00061805936,0.00047824119,0.00034647228],"domain_scores_gemma":[0.9983913,0.00048589322,0.00028628457,0.0004709207,0.00016663116,0.0001990255],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026171478,0.00028560776,0.0007998681,0.000590517,0.00011946905,0.00001474882,0.00019446843,0.0001412654,0.000016583617],"category_scores_gemma":[0.0030746046,0.00022267218,0.0001286477,0.00076573965,0.000530903,0.00037274495,0.000041211435,0.0010770488,0.000004392932],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001771779,0.0005616754,0.11915149,0.00057050557,0.00012365251,0.00016090844,0.0005389699,0.060043033,0.0015113167,0.006563622,0.004180695,0.8048224],"study_design_scores_gemma":[0.014826466,0.00049740466,0.011127561,0.0012252016,0.00021275373,0.000051869334,0.00029876063,0.93692553,0.00008952783,0.0047979094,0.029754188,0.00019283243],"about_ca_topic_score_codex":0.000032587282,"about_ca_topic_score_gemma":0.000033628563,"teacher_disagreement_score":0.8909686,"about_ca_system_score_codex":0.00024243885,"about_ca_system_score_gemma":0.00022508216,"threshold_uncertainty_score":0.9080308},"labels":[],"label_agreement":null},{"id":"W4414557357","doi":"10.1016/j.ijrobp.2025.06.1104","title":"Daily Online Adaptive Recontouring for Prostate Cancer Using 1.5 Tesla Magnetic Resonance Image Guidance (MRgRT) Improves Patient Reported Urinary Symptoms, A Prospective, International, Observational Cohort Study (NCT04075305)","year":2025,"lang":"en","type":"article","venue":"International Journal of Radiation Oncology*Biology*Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; University of Toronto; Sunnybrook Health Science Centre","funders":"","keywords":"Prostate cancer; Confidence interval; Prostate; Propensity score matching; Prospective cohort study; Magnetic resonance imaging; Cohort study; Radiation therapy","score_opus":0.022565612669245724,"score_gpt":0.3602077173538028,"score_spread":0.3376421046845571,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414557357","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.972992,0.0027211613,0.01335449,0.004841913,0.0039085043,0.001622444,0.00014575668,0.000059797178,0.00035393375],"genre_scores_gemma":[0.9636187,0.0007245864,0.030761858,0.0017976253,0.002159747,0.00020979466,0.00015673431,0.000055984536,0.00051498855],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9970727,0.0001957226,0.0013744185,0.00053733133,0.0004952936,0.0003245177],"domain_scores_gemma":[0.9948514,0.00046941478,0.0016810935,0.00022973244,0.0026399223,0.00012845409],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009526202,0.00030491813,0.0006945164,0.000313188,0.0001633075,0.000065779306,0.00044477283,0.00016463474,0.000028245775],"category_scores_gemma":[0.0017443137,0.00028424402,0.00024765593,0.00028878258,0.00027027266,0.00042195016,0.00014400932,0.0007533139,0.0000012056037],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014561397,0.0014263465,0.82874805,0.000019539752,0.0011177581,0.00009995478,0.00042624958,0.0007655012,0.005991091,0.00073040073,0.0012561176,0.15796283],"study_design_scores_gemma":[0.010207555,0.0029621245,0.866851,0.00051347335,0.00048239907,0.00022971974,0.000304068,0.09460629,0.0004824111,0.0038489217,0.019204581,0.00030748456],"about_ca_topic_score_codex":0.00010019176,"about_ca_topic_score_gemma":0.000006740692,"teacher_disagreement_score":0.15765534,"about_ca_system_score_codex":0.0017632575,"about_ca_system_score_gemma":0.0013890127,"threshold_uncertainty_score":0.99996096},"labels":[],"label_agreement":null},{"id":"W4414557714","doi":"10.1016/j.ijrobp.2025.06.2512","title":"Artificial Intelligence and Radiomic-Based Predictors of Response to Neoadjuvant SABR in Early-Stage Breast Cancer: Insights from the SPORT-DS Trial","year":2025,"lang":"en","type":"article","venue":"International Journal of Radiation Oncology*Biology*Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Intégré Universitaire de Santé et de Services Sociaux du Centre-Sud-de-l'Île-de-Montréal; Hôpital Maisonneuve-Rosemont; McGill University Health Centre; McGill University","funders":"Varian Medical Systems","keywords":"SABR volatility model; Correlation; Feature (linguistics); Breast cancer; Intraclass correlation; Clinical trial","score_opus":0.01666151961282412,"score_gpt":0.34171826836297836,"score_spread":0.3250567487501542,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414557714","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96446896,0.00037257248,0.01565357,0.016535744,0.0025141328,0.00032623205,0.00007368876,0.000011931183,0.000043200318],"genre_scores_gemma":[0.99550396,0.0002473793,0.00095982454,0.0017934015,0.0014295158,0.000012008944,0.000023044,0.000013466786,0.00001741136],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99812466,0.00028719736,0.0009436397,0.00021782551,0.00026714755,0.0001595272],"domain_scores_gemma":[0.99766386,0.0010989365,0.00064724096,0.00014884317,0.00032322307,0.00011788125],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00096251926,0.00015113126,0.00051032065,0.0002918634,0.000050039594,0.000023643228,0.00034854995,0.00015902238,0.000023755712],"category_scores_gemma":[0.0008553786,0.00011280485,0.00013338904,0.0002880321,0.0003224573,0.00009774929,0.000059138863,0.0006407342,0.0000017660134],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.06005209,0.00052256125,0.68698096,0.000009976994,0.00047932361,0.00007789537,0.0013487297,0.0071246247,0.0072638206,0.00848335,0.00026448976,0.22739218],"study_design_scores_gemma":[0.029243981,0.0025066186,0.8805299,0.0007421975,0.00033666054,0.000057818244,0.00040855832,0.04771641,0.0063725035,0.015194187,0.016577503,0.00031368158],"about_ca_topic_score_codex":0.00033929804,"about_ca_topic_score_gemma":0.000022584882,"teacher_disagreement_score":0.2270785,"about_ca_system_score_codex":0.00043389638,"about_ca_system_score_gemma":0.0009908363,"threshold_uncertainty_score":0.46000484},"labels":[],"label_agreement":null},{"id":"W4414557795","doi":"10.1016/j.ijrobp.2025.06.1087","title":"Development and Validation of a Digital Pathology-Based, Multimodal Artificial Intelligence (MMAI) Biomarker in Patients with Head and Neck Cancer","year":2025,"lang":"en","type":"article","venue":"International Journal of Radiation Oncology*Biology*Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre; Centre Hospitalier de l’Université de Montréal","funders":"National Center for Advancing Translational Sciences; Radiological Society of North America","keywords":"Head and neck cancer; Biomarker; Proportional hazards model; Missing data; Hazard ratio; Prognostic model; Radiation therapy; Cancer","score_opus":0.01756672883736538,"score_gpt":0.3380143504488788,"score_spread":0.3204476216115134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414557795","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96595484,0.00015163433,0.03135233,0.0019506043,0.00037373113,0.00013977008,0.000013131941,0.0000065170802,0.0000574396],"genre_scores_gemma":[0.9891307,0.00006220888,0.010304495,0.00034662618,0.00008679121,0.000005925971,0.000050368093,0.00000818077,0.0000047368517],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99897313,0.000058056776,0.00053896185,0.0001581163,0.00015702234,0.00011473749],"domain_scores_gemma":[0.9989336,0.00017751075,0.00043110526,0.000053072697,0.00034553552,0.000059144928],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030251002,0.000108567874,0.00029759816,0.00023436637,0.000030737086,0.000018841161,0.0000914503,0.000102248545,0.000006933932],"category_scores_gemma":[0.0002857606,0.000088666246,0.000035682147,0.00013615614,0.00024891554,0.00013538936,0.000035788144,0.00027165367,5.28981e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00051499275,0.00024141853,0.61211014,0.000012091589,0.000098225486,0.0000088247025,0.00019181395,0.00038666552,0.00037617632,0.0009369673,0.000009158261,0.38511357],"study_design_scores_gemma":[0.006388995,0.0007948371,0.9585517,0.00048577628,0.00009320928,0.000030174186,0.000090318645,0.023788368,0.0035487397,0.0042177215,0.001843853,0.00016628635],"about_ca_topic_score_codex":0.000010746979,"about_ca_topic_score_gemma":0.000003280919,"teacher_disagreement_score":0.38494727,"about_ca_system_score_codex":0.00021693607,"about_ca_system_score_gemma":0.00043613202,"threshold_uncertainty_score":0.36157045},"labels":[],"label_agreement":null},{"id":"W4414573665","doi":"10.1016/j.ijrobp.2025.06.2960","title":"Utility of Screening for Oligometastatic Disease: A Systematic Review","year":2025,"lang":"en","type":"article","venue":"International Journal of Radiation Oncology*Biology*Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Disease; Asymptomatic; Modalities; Cancer; Systematic review; Clinical endpoint; Brain metastasis; MEDLINE","score_opus":0.02312724890370339,"score_gpt":0.38398115624550416,"score_spread":0.3608539073418008,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414573665","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019562263,0.034416255,0.9200117,0.021511829,0.0021833056,0.0014967838,0.0000945964,0.000039116345,0.0006841437],"genre_scores_gemma":[0.96511066,0.0059210346,0.021310506,0.0066180695,0.00067186926,0.000045065193,0.00012443606,0.000024185527,0.00017419373],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980591,0.00024284715,0.0011416068,0.0001564447,0.00025048168,0.00014950336],"domain_scores_gemma":[0.996562,0.0009512805,0.0012586042,0.00016866162,0.00093704683,0.00012242247],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014453329,0.0001330376,0.00090149755,0.00018078492,0.000042954394,0.000011172995,0.00030979965,0.00007279015,0.000032118754],"category_scores_gemma":[0.0053388607,0.00010734648,0.00037968942,0.00019288441,0.00018063122,0.00010308546,0.00004181812,0.0003346486,0.0000020055197],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022671332,0.0022469424,0.36015534,0.16346109,0.009691304,0.00011528887,0.0005151456,0.00072002836,0.0024250222,0.11355569,0.019997349,0.32484967],"study_design_scores_gemma":[0.04056977,0.0033183051,0.08537199,0.31195113,0.0187636,0.00066403387,0.0003801455,0.36080462,0.001835206,0.11183661,0.06338369,0.0011208823],"about_ca_topic_score_codex":0.0000034305615,"about_ca_topic_score_gemma":2.1653217e-7,"teacher_disagreement_score":0.94554836,"about_ca_system_score_codex":0.00012723426,"about_ca_system_score_gemma":0.00057645777,"threshold_uncertainty_score":0.63915},"labels":[],"label_agreement":null},{"id":"W4414574379","doi":"10.1016/j.ijrobp.2025.06.3451","title":"Investigation of Survival and Non-Cancer Death following Lung Stereotactic Body Radiation Therapy Using Machine Learning-Based Auto-Segmentation","year":2025,"lang":"en","type":"article","venue":"International Journal of Radiation Oncology*Biology*Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University Health Network; Princess Margaret Cancer Centre","funders":"","keywords":"Proportional hazards model; Lung; Cohort; Comorbidity; Radiation therapy; Radiation treatment planning; Survival analysis; Cyberknife","score_opus":0.022060606905099762,"score_gpt":0.36363566912687983,"score_spread":0.3415750622217801,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414574379","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91215575,0.0014018891,0.08156403,0.0025812478,0.0019354172,0.0002455749,0.000008333437,0.000022957469,0.00008477685],"genre_scores_gemma":[0.9940348,0.0009699875,0.0033965327,0.0008321943,0.0006088912,0.000007732662,0.00009876786,0.000023769888,0.000027316491],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982443,0.0003245363,0.000745369,0.0002094378,0.00031086183,0.00016550825],"domain_scores_gemma":[0.99775076,0.00048739216,0.0011467971,0.00009095418,0.00042572294,0.00009839183],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009395077,0.00017844982,0.0005000125,0.0003445417,0.00010545259,0.000034845787,0.0001581396,0.00016223388,0.000022044529],"category_scores_gemma":[0.00046290306,0.00016430848,0.00018261692,0.00022830431,0.00012449632,0.00027260778,0.000030145586,0.0005724212,6.3512823e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030471286,0.00008865825,0.8891985,0.000030012963,0.00067069504,0.000010092223,0.00029880897,0.0030985887,0.056882594,0.0005636077,0.00003067567,0.048823074],"study_design_scores_gemma":[0.012030525,0.00067407504,0.29199353,0.00032778212,0.00044173465,0.000029360739,0.00005956197,0.67767334,0.013615695,0.0016342347,0.0013326973,0.0001874868],"about_ca_topic_score_codex":0.000115164046,"about_ca_topic_score_gemma":0.0000016532807,"teacher_disagreement_score":0.67457473,"about_ca_system_score_codex":0.000595977,"about_ca_system_score_gemma":0.0007437593,"threshold_uncertainty_score":0.67003053},"labels":[],"label_agreement":null},{"id":"W4414574871","doi":"10.1016/j.ijrobp.2025.07.1286","title":"Adaptive vs. Non-Adaptive Radiation Dose Escalation in Locally Advanced Non-Small Cell Lung Cancer (LA-NSCLC): Indirect Comparison of NRG-RTOG 0617 and 1106 Individual Patient Data","year":2025,"lang":"en","type":"article","venue":"International Journal of Radiation Oncology*Biology*Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre","funders":"","keywords":"Confidence interval; Hazard ratio; Radiation therapy; Odds ratio; Lung cancer; Proportional hazards model; Statistical significance; Logistic regression","score_opus":0.018281080500143345,"score_gpt":0.3523416704792677,"score_spread":0.33406058997912436,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414574871","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.905975,0.0019448621,0.08719966,0.0017681952,0.0015226783,0.0005778138,0.00010999988,0.00001742959,0.000884373],"genre_scores_gemma":[0.9896678,0.00089614827,0.008040607,0.00062247604,0.00043699928,0.000018543798,0.00027830416,0.000022813376,0.000016317057],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997625,0.000317842,0.001102071,0.00036225934,0.00036086087,0.00023199456],"domain_scores_gemma":[0.9968454,0.000797264,0.0015118333,0.00020048444,0.0005237606,0.00012122297],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00093844405,0.0002302977,0.0007553759,0.0004499615,0.00006460448,0.000028248356,0.000439138,0.00026920225,0.00001256148],"category_scores_gemma":[0.00048527584,0.00021812381,0.000103951155,0.00031187176,0.00025565093,0.0003471576,0.00019367236,0.0009786165,0.0000012091978],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011744496,0.00053653336,0.49800962,0.000031687992,0.0004764259,0.00001774541,0.0020384532,0.009282589,0.0015105013,0.00055098895,0.00067404466,0.48569697],"study_design_scores_gemma":[0.016048612,0.0016700369,0.41863322,0.0007971451,0.0004838443,0.000030237536,0.0006121848,0.55469596,0.0029999472,0.0011734694,0.0025706394,0.0002846729],"about_ca_topic_score_codex":0.000115880546,"about_ca_topic_score_gemma":0.000023437893,"teacher_disagreement_score":0.5454134,"about_ca_system_score_codex":0.00062088703,"about_ca_system_score_gemma":0.0011260841,"threshold_uncertainty_score":0.88948303},"labels":[],"label_agreement":null},{"id":"W4414574909","doi":"10.1016/j.ijrobp.2025.06.3682","title":"Radiomic Analysis for Prediction of Progression Free Survival and Early Polymetastatic Progression in Lung Oligometastases Patients on SABR-5 Trial","year":2025,"lang":"en","type":"article","venue":"International Journal of Radiation Oncology*Biology*Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Positive Living North; Surrey Memorial Hospital; University of British Columbia; Kelowna General Hospital","funders":"Canadian Institutes of Health Research","keywords":"Radiomics; Progression-free survival; SABR volatility model; Concordance; Proportional hazards model; Recursive partitioning; Lung cancer; Concordance correlation coefficient; Hazard ratio","score_opus":0.015518171330716007,"score_gpt":0.3657500075304407,"score_spread":0.35023183619972464,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414574909","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97160435,0.0004907547,0.023685632,0.0015012708,0.0017970577,0.00065877207,0.0001283423,0.000015064101,0.000118764045],"genre_scores_gemma":[0.99417657,0.0002410398,0.0046624416,0.00015894655,0.00051561964,0.000029239487,0.00018653349,0.000014744623,0.000014846019],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99796563,0.00028245983,0.00097615697,0.00023323664,0.0003647264,0.00017776409],"domain_scores_gemma":[0.9974921,0.00077841873,0.0010500088,0.00014099183,0.00044739753,0.00009112906],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010999661,0.0001597096,0.0006950925,0.000838666,0.000052501917,0.000021430391,0.0002264186,0.00015013099,0.0000069149514],"category_scores_gemma":[0.0016794084,0.00012925375,0.0002534737,0.0004338425,0.00019368947,0.00014978087,0.000054799904,0.000393496,2.7084755e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.010022951,0.0009379263,0.81376654,0.00003854846,0.0014092588,0.000005918016,0.00015545943,0.0003695972,0.0007483624,0.003214038,0.00021246153,0.16911897],"study_design_scores_gemma":[0.12589778,0.007072552,0.81777537,0.0006516135,0.0020376851,0.000011759781,0.00007397241,0.03743772,0.0017121813,0.005606748,0.0015325595,0.00019005773],"about_ca_topic_score_codex":0.000016815558,"about_ca_topic_score_gemma":0.0000017309678,"teacher_disagreement_score":0.1689289,"about_ca_system_score_codex":0.00033229732,"about_ca_system_score_gemma":0.00028942645,"threshold_uncertainty_score":0.5270815},"labels":[],"label_agreement":null},{"id":"W4414576575","doi":"10.1002/dneu.23001","title":"Early Prediction and Risk Analysis Using Hybrid Deep Learning Techniques in Multimodal Biomedical Image","year":2025,"lang":"en","type":"article","venue":"Developmental Neurobiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Interpretability; Deep learning; Medical imaging; Feature extraction; Feature (linguistics); Pattern recognition (psychology); Smoothing; Process (computing)","score_opus":0.005056878578627496,"score_gpt":0.2672826414032313,"score_spread":0.2622257628246038,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414576575","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97945064,0.000063135885,0.019455625,0.00022417257,0.00011922657,0.00019066222,0.000006299541,0.00010729946,0.00038290786],"genre_scores_gemma":[0.9603761,0.00022073698,0.03886578,0.00030123178,0.000033785025,0.000011802237,0.00010697146,0.000013255038,0.000070351474],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9986677,0.00018334616,0.0003688775,0.0004082252,0.0000910079,0.00028083587],"domain_scores_gemma":[0.9995885,0.000120820325,0.0000810223,0.00008324563,0.000028740915,0.00009768819],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040084746,0.00015511701,0.00038162872,0.00081650895,0.00012716568,0.000020484771,0.000070385584,0.000102329934,0.000030930834],"category_scores_gemma":[0.00041083942,0.00014111908,0.00006437515,0.00063691096,0.00026953142,0.00005820235,0.0001293547,0.00072671816,0.000002756752],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006993214,0.00006928283,0.91173226,0.000024700586,0.00023261785,0.00009861221,0.00016471535,0.000019117826,0.056645583,0.000009377082,0.000024055356,0.030909736],"study_design_scores_gemma":[0.0010806358,0.00013775362,0.9265649,0.000065092456,0.0003226381,0.00018559565,0.000080162274,0.066764176,0.0032877347,0.000047517042,0.0013262314,0.00013758705],"about_ca_topic_score_codex":0.0003146317,"about_ca_topic_score_gemma":0.000009644874,"teacher_disagreement_score":0.06674506,"about_ca_system_score_codex":0.00010613301,"about_ca_system_score_gemma":0.00006670901,"threshold_uncertainty_score":0.5754669},"labels":[],"label_agreement":null},{"id":"W4414585727","doi":"10.1158/1538-7445.pancreatic25-b086","title":"Abstract B086: External validation of a multimodal machine learning system to predict outcomes in advanced pancreatic cancer in the PASS-01 trial","year":2025,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Ontario Institute for Cancer Research; Université de Montréal; University of British Columbia; University Health Network","funders":"","keywords":"Percentile; Receiver operating characteristic; Cohort; Pancreatic cancer; Hazard ratio; Generalizability theory; Compass; Clinical trial","score_opus":0.03635725401411739,"score_gpt":0.4335930376683845,"score_spread":0.3972357836542671,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414585727","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9910611,0.001187244,0.00028959097,0.004815224,0.0002933339,0.0015617206,0.000012702837,0.000024498146,0.0007545728],"genre_scores_gemma":[0.9977982,0.00035297763,0.0002313597,0.00016066065,0.00017529476,0.0007787701,0.000007883362,0.000019895288,0.00047495315],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.997365,0.00045390902,0.0005370482,0.00033713106,0.00085625594,0.00045065215],"domain_scores_gemma":[0.9986089,0.00077757274,0.000090881105,0.00028600753,0.00013361688,0.00010301394],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003117548,0.00014200088,0.0004982563,0.0005701944,0.00009052914,0.00003831941,0.00030198862,0.000078097306,0.00010219241],"category_scores_gemma":[0.0017078507,0.00009727347,0.00007999679,0.0008592982,0.000093656316,0.000070442686,0.00008040103,0.0013892284,0.000003989727],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.013823551,0.00032391428,0.84009796,0.0011588932,0.0001075875,0.00012371883,0.0022116576,0.022695297,0.037440166,0.00018248937,0.00019358621,0.08164118],"study_design_scores_gemma":[0.043143287,0.00055521773,0.8975934,0.0069265077,0.000057361052,0.000006294432,0.0015626776,0.044999957,0.0033415286,0.000059635284,0.0015497315,0.00020442736],"about_ca_topic_score_codex":0.011391603,"about_ca_topic_score_gemma":0.00037837823,"teacher_disagreement_score":0.08143675,"about_ca_system_score_codex":0.00058885175,"about_ca_system_score_gemma":0.00045283602,"threshold_uncertainty_score":0.99519163},"labels":[],"label_agreement":null},{"id":"W4414630376","doi":"10.1055/a-2710-7613","title":"Correction: Computer-assisted optical diagnosis of colorectal polyps up to 10 mm","year":2025,"lang":"en","type":"erratum","venue":"Endoscopy","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier de l’Université de Montréal; McGill University Health Centre; Université de Montréal; Montreal General Hospital","funders":"","keywords":"Colorectal Polyp; Colonoscopy; Colonic disease; MEDLINE; Endoscopy; Peutz–Jeghers syndrome","score_opus":0.010141083719556996,"score_gpt":0.30289214187815966,"score_spread":0.29275105815860264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414630376","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024793258,0.003527124,0.019512713,0.021311449,0.49241528,0.0028013503,0.00016306392,0.00082449423,0.43465126],"genre_scores_gemma":[0.017822552,0.0008000959,0.035099644,0.004053148,0.008384032,0.00029669655,0.0012974074,0.00018258826,0.9320638],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99762434,0.00009514184,0.00062221556,0.0006102485,0.00059950794,0.00044857076],"domain_scores_gemma":[0.9981358,0.0005689511,0.00020201727,0.0004614778,0.00020667586,0.00042507032],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002710722,0.00040006408,0.0011692718,0.00045321594,0.0001019121,0.000044471548,0.0002972328,0.00048949016,0.0012849662],"category_scores_gemma":[0.0014741962,0.00037074872,0.00031912487,0.0005629764,0.00017191863,0.00003040624,0.0002059062,0.0018946881,0.000103236765],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028786022,0.0001864891,0.002160756,0.00035985408,0.00024411955,0.000103880346,0.00015264719,0.000014618024,0.00012064437,0.000050305425,0.966971,0.029347839],"study_design_scores_gemma":[0.0017337122,0.0013953258,0.010201217,0.0039226436,0.0005265507,0.000072737166,0.000049849164,0.0094044665,0.0018610297,0.000008949798,0.9704533,0.00037019385],"about_ca_topic_score_codex":0.000199331,"about_ca_topic_score_gemma":0.000013139819,"teacher_disagreement_score":0.49741256,"about_ca_system_score_codex":0.00021759802,"about_ca_system_score_gemma":0.00069306267,"threshold_uncertainty_score":0.9998745},"labels":[],"label_agreement":null},{"id":"W4414732254","doi":"10.1007/978-3-031-94302-7_28","title":"AI-Driven Radiotherapy Solutions for Rare and Complex Cancers Using Multi-omics Approaches","year":2025,"lang":"en","type":"book-chapter","venue":"Artificial Intelligence in Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Precision medicine; Personalization; Radiation therapy; Modality (human–computer interaction); Radiomics; Personalized medicine; Cancer treatment; Cancer","score_opus":0.2235316522206108,"score_gpt":0.4161496160141744,"score_spread":0.19261796379356358,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414732254","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00080831884,0.0036359893,0.9515855,0.019293373,0.0018801792,0.0029144415,0.000101924765,0.00010822054,0.019672075],"genre_scores_gemma":[0.09751213,0.012710194,0.7683205,0.029638037,0.0046809637,0.00052761956,0.0011222932,0.00058460754,0.08490366],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981962,0.000045907258,0.00065385917,0.0005315949,0.00012218954,0.00045027238],"domain_scores_gemma":[0.99885577,0.00047217857,0.00019988703,0.00023219943,0.000101513106,0.0001384518],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004341771,0.00029388635,0.0008203876,0.00037763471,0.00019543218,0.000029299435,0.00015887024,0.00050153036,0.0000959454],"category_scores_gemma":[0.00024874718,0.00029956526,0.0001523534,0.00007300845,0.0006436962,0.000039072598,0.000084979845,0.0008989489,0.0000030452604],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045633357,0.00015685294,0.00025021075,0.00035572523,0.0002763155,0.000088420464,0.0011307208,0.010563124,0.0010750701,0.22926618,0.0015443658,0.7548367],"study_design_scores_gemma":[0.00028906125,0.00027545952,0.000021603775,0.00031742957,0.00015378589,0.000063250125,0.00022977419,0.87344927,0.00003796643,0.012492883,0.11241538,0.00025414574],"about_ca_topic_score_codex":0.0004068422,"about_ca_topic_score_gemma":0.00067803945,"teacher_disagreement_score":0.86288613,"about_ca_system_score_codex":0.0010540986,"about_ca_system_score_gemma":0.00092938956,"threshold_uncertainty_score":0.99994564},"labels":[],"label_agreement":null},{"id":"W4414768645","doi":"10.3390/cancers17193218","title":"Pre-Treatment PET Radiomics for Prediction of Disease-Free Survival in Cervical Cancer","year":2025,"lang":"en","type":"article","venue":"Cancers","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria; University of British Columbia; Spinal Cord Injury BC","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Radiomics; Cervical cancer; Lymph node; Feature selection; Generalizability theory; Cancer; Nomogram; Feature (linguistics)","score_opus":0.012834719229200564,"score_gpt":0.3101670330023721,"score_spread":0.29733231377317154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414768645","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9807287,0.0019561818,0.005509474,0.007286994,0.0015793995,0.0010123985,0.00038002114,0.000054675817,0.0014921646],"genre_scores_gemma":[0.9957267,0.0009703774,0.0008461742,0.00045323718,0.00024940053,0.0002593142,0.000080141035,0.000018618557,0.0013960202],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9992147,0.000022469343,0.00023067617,0.00021315992,0.00013293079,0.00018604564],"domain_scores_gemma":[0.99943566,0.00009802075,0.0000519269,0.00024540952,0.00004836745,0.00012061183],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014002733,0.00010312244,0.00028282768,0.00011370307,0.000030257877,0.00000577923,0.00009179912,0.000033822907,0.000033148186],"category_scores_gemma":[0.00021859618,0.00008826497,0.000095093616,0.00017309094,0.00008402311,0.00002752729,0.000022157281,0.00011150481,2.1669538e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0032635187,0.00017971074,0.90342855,0.0012720954,0.00040090675,0.000033122793,0.0004892137,0.022117134,0.0017582476,0.0024536408,0.010712091,0.05389177],"study_design_scores_gemma":[0.01410521,0.0004568868,0.59821224,0.0011250159,0.0005769266,0.0000039898196,0.00017025556,0.3380452,0.0007404715,0.0013240628,0.045057476,0.00018229739],"about_ca_topic_score_codex":0.001327956,"about_ca_topic_score_gemma":0.00018307354,"teacher_disagreement_score":0.31592807,"about_ca_system_score_codex":0.0016064313,"about_ca_system_score_gemma":0.0011041,"threshold_uncertainty_score":0.42007622},"labels":[],"label_agreement":null},{"id":"W4414779438","doi":"10.1002/lary.70169","title":"Roadmap for Representative Artificial Intelligence Models for Thyroid Cancer","year":2025,"lang":"en","type":"article","venue":"The Laryngoscope","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Hospital; Sunnybrook Health Science Centre; Ottawa Hospital; University of Calgary; Toronto East General Hospital; SickKids Foundation; University of Toronto; Hospital for Sick Children; University of Ottawa","funders":"","keywords":"Thyroid cancer; Training set; Radiomics; Cancer; Applications of artificial intelligence","score_opus":0.046037188371574445,"score_gpt":0.3948823551259376,"score_spread":0.34884516675436317,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414779438","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02691466,0.0019461084,0.8974772,0.066236176,0.00065986335,0.001885996,0.000028551422,0.000075985525,0.004775446],"genre_scores_gemma":[0.95020413,0.00049896666,0.019834816,0.013522595,0.0009769595,0.0013576702,0.000054276963,0.00005538863,0.013495217],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99907583,0.00003657427,0.00024384476,0.00025877208,0.00012330504,0.00026169163],"domain_scores_gemma":[0.9990607,0.0004370843,0.0000625837,0.00025839472,0.00011989678,0.000061373925],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00052182877,0.000115138784,0.00024624527,0.000058378868,0.00020514958,0.000033591477,0.00018287332,0.000048791808,0.000036509216],"category_scores_gemma":[0.00046768738,0.00007504951,0.000120208395,0.00017376394,0.00013180026,0.000058565474,0.000054351895,0.00022110663,0.0000044082694],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0033869455,0.00038888547,0.0007300482,0.00078050204,0.00086613663,0.00001136796,0.0046866997,0.017784813,0.028098643,0.36660567,0.16859715,0.40806314],"study_design_scores_gemma":[0.0006730646,0.00021476044,0.000176905,0.00028871698,0.00029074476,0.000004820749,0.0005485007,0.7676893,0.018732825,0.18574393,0.025485683,0.0001507542],"about_ca_topic_score_codex":0.0002146571,"about_ca_topic_score_gemma":0.000019186651,"teacher_disagreement_score":0.9232895,"about_ca_system_score_codex":0.00004664267,"about_ca_system_score_gemma":0.00015346159,"threshold_uncertainty_score":0.30604303},"labels":[],"label_agreement":null},{"id":"W4414959082","doi":"10.3390/diagnostics15192536","title":"Performance of ChatGPT-4o in Determining Radiology–Pathology Concordance and Management Recommendations Following Image-Guided Breast Biopsies","year":2025,"lang":"en","type":"article","venue":"Diagnostics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Sunnybrook Health Science Centre","funders":"","keywords":"Concordance; Gold standard (test); Biopsy; Conservative management; Breast imaging; Multidisciplinary approach; Retrospective cohort study","score_opus":0.009463016648554454,"score_gpt":0.30880864729878066,"score_spread":0.2993456306502262,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414959082","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9914974,0.000517486,0.00096374366,0.003849213,0.0003810932,0.00021834894,0.0000050271187,0.000024492967,0.002543168],"genre_scores_gemma":[0.97925156,0.005264362,0.0143579375,0.00089666434,0.00003121595,0.00002944981,0.000025027643,0.000010802199,0.00013298541],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9991364,0.00004834016,0.0003385755,0.00020399336,0.00007097671,0.00020173029],"domain_scores_gemma":[0.9992122,0.00045814697,0.000078617384,0.00016775058,0.00003585636,0.00004742038],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036591743,0.00010796717,0.00031727855,0.00024295163,0.00005938249,0.00000956934,0.0000793388,0.000055384815,0.0000076245105],"category_scores_gemma":[0.0007275824,0.00010492616,0.000038359798,0.00022776221,0.00016553732,0.000052435033,0.000093076305,0.00021799967,0.0000015505664],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020549545,0.000058386737,0.9185423,0.00027457552,0.00005226633,0.00024388,0.00019585533,0.000026808153,0.0008433249,0.00055273646,0.0011009461,0.07808836],"study_design_scores_gemma":[0.0025596984,0.0001282422,0.95866627,0.0018776079,0.00016733097,0.000413781,0.00036211236,0.03355299,0.0004064238,0.00008660736,0.0016281395,0.00015079285],"about_ca_topic_score_codex":0.000024814628,"about_ca_topic_score_gemma":0.000004385837,"teacher_disagreement_score":0.077937566,"about_ca_system_score_codex":0.000047297694,"about_ca_system_score_gemma":0.000032342123,"threshold_uncertainty_score":0.42787647},"labels":[],"label_agreement":null},{"id":"W4414994015","doi":"10.1038/s41598-025-19345-4","title":"Preoperative prediction of lymph node metastasis risk in papillary thyroid carcinoma based on multiple model comparisons","year":2025,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Logistic regression; Thyroid carcinoma; Lymph node; Lymph node metastasis; Dissection (medical); Calibration; Carcinoma; Generalization; Confidence interval; Thyroid cancer","score_opus":0.015915828406923897,"score_gpt":0.27676773850999375,"score_spread":0.26085191010306985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414994015","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96855456,0.0002511857,0.024590928,0.0006043107,0.0013617125,0.00046524432,0.000026676511,0.000049562143,0.0040958086],"genre_scores_gemma":[0.9932801,0.000008517672,0.005530712,0.00017592516,0.00001993813,0.000029171735,0.00011816209,0.00001284296,0.0008246038],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978644,0.00012476389,0.0006474068,0.00061257364,0.0005099274,0.00024087926],"domain_scores_gemma":[0.99859273,0.00016146273,0.00025691252,0.00071757677,0.00016001322,0.00011128173],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001753867,0.00015002607,0.0003939411,0.0004967599,0.00018081261,0.000044367236,0.00008222211,0.00006889966,0.000020995738],"category_scores_gemma":[0.0017028198,0.0001235247,0.00012587491,0.000636911,0.00025830397,0.00006824331,0.00004663431,0.00032448245,0.0000016450743],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007118022,0.00029741976,0.8135644,0.0000872486,0.00003220085,0.00010535862,0.0002445165,0.16934592,0.007938338,0.000021981397,0.007396682,0.0008947556],"study_design_scores_gemma":[0.0008728588,0.000037794758,0.18717323,0.00022438273,0.00009640539,0.000015118707,0.000087714354,0.80414474,0.0066059623,0.00020104338,0.00047618843,0.00006455546],"about_ca_topic_score_codex":0.00025535733,"about_ca_topic_score_gemma":0.000013054499,"teacher_disagreement_score":0.6347988,"about_ca_system_score_codex":0.00012811276,"about_ca_system_score_gemma":0.0004980607,"threshold_uncertainty_score":0.5037191},"labels":[],"label_agreement":null},{"id":"W4415027654","doi":"10.1016/j.modpat.2025.100893","title":"Corrigendum to “Magnetic Resonance Imaging (MRI)–Adapted Prostate Cancer Risk Tool Incorporating Cribriform and Intraductal Carcinoma” (Modern Pathology 2025 Dec;38(12):100852)","year":2025,"lang":"en","type":"article","venue":"Modern Pathology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University Health Network; Sunnybrook Health Science Centre","funders":"","keywords":"Cribriform; Prostate cancer; Magnetic resonance imaging; Anatomical pathology; Biopsy","score_opus":0.009522474384345479,"score_gpt":0.2667779797980237,"score_spread":0.2572555054136782,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415027654","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9283371,0.013566926,0.046406835,0.0075927405,0.0013924821,0.000977821,0.00009160461,0.00019931854,0.0014351775],"genre_scores_gemma":[0.9799132,0.00060548325,0.011681376,0.0044671823,0.000248408,0.0002081914,0.000057627487,0.00008105038,0.002737491],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965637,0.0002726175,0.00076027814,0.0011967239,0.00029303716,0.00091367296],"domain_scores_gemma":[0.99848056,0.00012307819,0.0002425947,0.00065478624,0.00019809126,0.00030091772],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00082303816,0.00046956178,0.0008647345,0.00043080005,0.00037792348,0.00006711932,0.0002673992,0.00022384418,0.000052702362],"category_scores_gemma":[0.0008398164,0.00044500674,0.00010696086,0.00035308767,0.00047778315,0.00013587391,0.00039360212,0.0011053956,0.000010072783],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036470627,0.000089202964,0.46045393,0.00012799009,0.000024114703,0.00202037,0.0030715032,0.00021490363,0.022059033,0.00040273857,0.0025833263,0.5085882],"study_design_scores_gemma":[0.004638761,0.0005732655,0.47660634,0.0004646997,0.0003453745,0.0019125206,0.00032867678,0.49172541,0.00085508253,0.011627738,0.010142308,0.00077982293],"about_ca_topic_score_codex":0.0005067394,"about_ca_topic_score_gemma":0.00019266846,"teacher_disagreement_score":0.5078084,"about_ca_system_score_codex":0.00020051641,"about_ca_system_score_gemma":0.00042172582,"threshold_uncertainty_score":0.99980015},"labels":[],"label_agreement":null},{"id":"W4415150354","doi":"10.3390/jimaging11100360","title":"Lung Nodule Malignancy Classification Integrating Deep and Radiomic Features in a Three-Way Attention-Based Fusion Module","year":2025,"lang":"en","type":"article","venue":"Journal of Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; Health Sciences Centre; University of Toronto; Sunnybrook Health Science Centre; Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto","keywords":"Pattern recognition (psychology); Deep learning; Convolutional neural network; Encoder; Feature extraction; Malignancy; Adenocarcinoma; Atypical adenomatous hyperplasia","score_opus":0.005775253117694657,"score_gpt":0.28217825058266466,"score_spread":0.27640299746497,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415150354","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8525332,0.003916678,0.13015562,0.012045989,0.00033186103,0.00014911547,3.9467693e-7,0.000017109638,0.0008499777],"genre_scores_gemma":[0.983785,0.00008233066,0.015102611,0.0007757403,0.00013022513,0.00000289781,0.0000040997547,0.0000151224285,0.00010200309],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99882203,0.000065862165,0.0005154814,0.00017225873,0.00023615961,0.00018821219],"domain_scores_gemma":[0.99920547,0.00013096785,0.00029035695,0.00013287288,0.00014880333,0.00009155144],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000848058,0.0001287064,0.00032660319,0.0005615731,0.0001125845,0.000054066186,0.000097098404,0.000045823286,0.000014990837],"category_scores_gemma":[0.0006010373,0.00010240384,0.00010228985,0.00029187332,0.00008174805,0.0001590333,0.000027399414,0.00069585704,5.7135634e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011056056,0.000090410125,0.83518577,0.00019094312,0.000035709007,0.00017354579,0.0001823153,0.00022265186,0.07349033,0.00044993346,0.00055849575,0.08930935],"study_design_scores_gemma":[0.0018557092,0.000024901192,0.5461323,0.0015787977,0.000071873656,0.00025924304,0.00019803252,0.4490355,0.00033710178,0.00034227577,0.000094405485,0.00006984799],"about_ca_topic_score_codex":0.000056050565,"about_ca_topic_score_gemma":0.000013322148,"teacher_disagreement_score":0.44881284,"about_ca_system_score_codex":0.00016762984,"about_ca_system_score_gemma":0.00013972244,"threshold_uncertainty_score":0.41759077},"labels":[],"label_agreement":null},{"id":"W4415170028","doi":"10.6000/1929-6029.2025.14.58","title":"AI-Powered CNN Model for Automated Lung Cancer Diagnosis in Medical Imaging","year":2025,"lang":"en","type":"article","venue":"International Journal of Statistics in Medical Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Preprocessor; Convolutional neural network; Normalization (sociology); Medical imaging; Pixel; Grayscale; Deep learning; Pattern recognition (psychology)","score_opus":0.03140246757287672,"score_gpt":0.5195471447686191,"score_spread":0.48814467719574234,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415170028","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033792082,0.0033235957,0.6573518,0.3010284,0.0024458938,0.00060078705,0.00012531891,0.000042461554,0.0012896896],"genre_scores_gemma":[0.96412563,0.00701445,0.01929053,0.008346504,0.000614868,0.00017088508,0.000041686784,0.000036732345,0.0003586923],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99352926,0.00023130835,0.0011512382,0.00025430578,0.0043331548,0.00050072203],"domain_scores_gemma":[0.993937,0.0035952271,0.00015085912,0.0001269709,0.0016947668,0.0004951796],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0074113626,0.00013673372,0.00046495805,0.0014402746,0.000054547196,0.000069538226,0.00080661225,0.00017440457,0.0009294004],"category_scores_gemma":[0.044143938,0.000115147726,0.00008965038,0.00047761228,0.0004002905,0.0001013666,0.00020553774,0.002684153,0.0000019244303],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011920023,0.0010254753,0.2537217,0.0004143343,0.00036527147,0.007550401,0.0006262484,0.0020252683,0.00009324364,0.020677032,0.2770916,0.43521738],"study_design_scores_gemma":[0.00492141,0.000045118693,0.011285595,0.0037726467,0.000023795183,0.00010289978,0.00007172102,0.96559304,0.000019838737,0.009207931,0.004874491,0.00008149792],"about_ca_topic_score_codex":0.0003628981,"about_ca_topic_score_gemma":0.00014716675,"teacher_disagreement_score":0.9635678,"about_ca_system_score_codex":0.00083704054,"about_ca_system_score_gemma":0.0039385045,"threshold_uncertainty_score":0.9999839},"labels":[],"label_agreement":null},{"id":"W4415213801","doi":"10.20944/preprints202510.1139.v1","title":"Precision Oncology: Current Landscape, Emerging Trends, Challenges, and Future Perspectives","year":2025,"lang":"en","type":"preprint","venue":"Preprints.org","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research","keywords":"Precision medicine; Precision oncology; Cancer Medicine; Cancer; Personalized medicine; Clinical Oncology; CRISPR; Cancer treatment; Disease","score_opus":0.06921511048518905,"score_gpt":0.40450536505616397,"score_spread":0.33529025457097494,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415213801","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5179502,0.23092256,0.0001998429,0.06427069,0.004800415,0.0010542069,0.00003221977,0.00055335293,0.1802165],"genre_scores_gemma":[0.71723354,0.27274492,0.0013694827,0.0002898087,0.0037758064,0.0001647657,0.0001527166,0.000072162205,0.004196815],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9969874,0.00023499524,0.0005228808,0.0013989396,0.00044015562,0.00041560753],"domain_scores_gemma":[0.998083,0.00014977291,0.0002830168,0.0009797505,0.00017821605,0.00032624992],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.001084721,0.00046267625,0.0009332823,0.0005501636,0.00013488851,0.000020160694,0.00034244184,0.0004817633,0.0006083256],"category_scores_gemma":[0.0005020318,0.00040963767,0.00025933096,0.00016125932,0.00014516729,0.000057190533,0.001755084,0.0032795004,0.000046601835],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019918321,0.0004424877,0.069229946,0.0010158871,0.00033920136,0.000059418733,0.011438032,0.000038688915,0.00014146589,0.0013513918,0.0009234923,0.9148208],"study_design_scores_gemma":[0.0016139629,0.00007282043,0.41760454,0.001497887,0.00041417146,0.00007149872,0.0026809082,0.0022716983,0.00008011601,0.0009593839,0.5723031,0.00042988683],"about_ca_topic_score_codex":0.00003159913,"about_ca_topic_score_gemma":0.000006485406,"teacher_disagreement_score":0.9143909,"about_ca_system_score_codex":0.00022375549,"about_ca_system_score_gemma":0.00032898464,"threshold_uncertainty_score":0.99983555},"labels":[],"label_agreement":null},{"id":"W4415214707","doi":"10.1016/j.neucom.2025.131713","title":"Enhanced 3D tumor synthesis and segmentation framework using multiscale diffusion and hybrid SAM-Swin models across diverse anatomical datasets","year":2025,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Key Research and Development Program of Zhejiang Province; Natural Science Foundation of Zhejiang Province; National Natural Science Foundation of China","keywords":"Segmentation; Synthetic data; Pattern recognition (psychology); Context (archaeology); Ground truth; Generalization; Diffusion MRI; Image segmentation","score_opus":0.014836748653580721,"score_gpt":0.3251164410061931,"score_spread":0.3102796923526124,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415214707","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.80177236,0.00009742567,0.19739729,0.00026143403,0.00013708087,0.00021800307,0.00001859565,0.00005518893,0.00004263071],"genre_scores_gemma":[0.95447123,0.000030020106,0.04428752,0.0010643679,0.00008977338,0.000003768997,0.000022300057,0.000018951909,0.000012095354],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987326,0.00008784734,0.0002607709,0.00045143312,0.00017910404,0.00028822038],"domain_scores_gemma":[0.9990784,0.0004931778,0.00009136449,0.00017272033,0.00002401233,0.00014032972],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002675099,0.00016443335,0.00029428705,0.000083270614,0.0003513722,0.000082580686,0.000071678915,0.000048333095,0.000009265026],"category_scores_gemma":[0.00048851647,0.00015468025,0.000034143,0.00012949164,0.00012200489,0.00011239649,0.00032283962,0.0004461725,0.0000012601308],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029176456,0.00030215282,0.036893636,0.00084761635,0.00011617764,0.0004997155,0.0019877374,0.0048805834,0.3134724,0.00013174799,0.00046183058,0.64011467],"study_design_scores_gemma":[0.0009314143,0.000022431268,0.010629324,0.00070386083,0.000089911104,0.00011629046,0.0002226507,0.97864026,0.008267671,0.00015747483,0.00008324755,0.00013547721],"about_ca_topic_score_codex":0.000071148694,"about_ca_topic_score_gemma":8.472921e-7,"teacher_disagreement_score":0.97375965,"about_ca_system_score_codex":0.00004044218,"about_ca_system_score_gemma":0.0000231512,"threshold_uncertainty_score":0.63076776},"labels":[],"label_agreement":null},{"id":"W4415269171","doi":"10.2196/84396","title":"Multimodal Prediction of Renal Tumor Malignancy From Radiology Reports and Structured Electronic Health Records: Retrospective Cohort Study","year":2025,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Malignancy; Retrospective cohort study; Abnormality; Electronic health record; Text mining; Renal tumor","score_opus":0.004460516947575159,"score_gpt":0.28971599633208417,"score_spread":0.285255479384509,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415269171","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99088633,0.00032727123,0.0049926597,0.000923873,0.00046317143,0.001421467,0.00001972844,0.00009110501,0.00087439385],"genre_scores_gemma":[0.99565727,0.00020439753,0.0021073625,0.0015614416,0.00016244085,0.00006961647,0.00013684218,0.000014417569,0.000086220265],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99709564,0.00012437004,0.0013851236,0.00025478884,0.00074523553,0.00039482137],"domain_scores_gemma":[0.9984973,0.00013002247,0.00054466724,0.00038432967,0.00012414026,0.0003195033],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013537934,0.00020058079,0.00086793664,0.00020905159,0.000102894344,0.00001537228,0.00011385518,0.00016620355,0.00013672652],"category_scores_gemma":[0.0011392885,0.0001588492,0.00007433578,0.0002816601,0.00025941583,0.000100284815,0.00009992203,0.0011075425,0.000001015309],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013649231,0.00023734222,0.97724384,0.0002085938,0.00038097086,0.000076646116,0.003011807,0.0000064999003,0.000060947434,0.00017839097,0.003991313,0.014467149],"study_design_scores_gemma":[0.002870354,0.0011296433,0.9529674,0.0005448613,0.00013906704,0.00042901174,0.0013385027,0.038307257,0.000038907314,0.0010312782,0.0010918161,0.000111903944],"about_ca_topic_score_codex":0.00038979127,"about_ca_topic_score_gemma":0.000027163305,"teacher_disagreement_score":0.038300756,"about_ca_system_score_codex":0.0002735959,"about_ca_system_score_gemma":0.0008423064,"threshold_uncertainty_score":0.64776826},"labels":[],"label_agreement":null},{"id":"W4415322336","doi":"10.61882/ijbd.18.3.10","title":"Intraoperative Assessment of Breast Lymph Nodes using Cancer Diagnostic Probe in Impedimetric Mode","year":2025,"lang":"fa","type":"article","venue":"Journal of Breast Diseases","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Breast cancer; Lymph; Cancer; Axilla","score_opus":0.008161808985664647,"score_gpt":0.36099874737445536,"score_spread":0.3528369383887907,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415322336","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96382564,0.02193134,0.0074087065,0.0046688025,0.0012238531,0.00038413875,0.00036086116,0.0000103270095,0.00018632713],"genre_scores_gemma":[0.9940858,0.0031131492,0.0014178782,0.000438486,0.0008052631,0.000010598162,0.000010442179,0.000038152586,0.000080261976],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99649465,0.00037388547,0.001471921,0.00031909285,0.00082942983,0.00051104947],"domain_scores_gemma":[0.99645114,0.0011488341,0.00094707723,0.00025036783,0.000714747,0.0004878371],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006321395,0.00036997302,0.0012549958,0.0013168836,0.00010709662,0.00008263301,0.0003348186,0.00012622395,0.00026133476],"category_scores_gemma":[0.0017152264,0.00029761912,0.0003588983,0.0013971905,0.00032370497,0.0003336099,0.00013412027,0.00083799864,0.0000010275376],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040804624,0.0018713676,0.91461754,0.0011792344,0.0007506115,0.0004948429,0.00029114346,0.01693238,0.0026936873,0.00019178679,0.0002839735,0.060285404],"study_design_scores_gemma":[0.0040504704,0.00010079336,0.84689003,0.010346814,0.0017837211,0.00071957853,0.00058498036,0.13503504,0.00005968966,0.00019883185,0.000022002248,0.00020802082],"about_ca_topic_score_codex":0.002363108,"about_ca_topic_score_gemma":0.000014326652,"teacher_disagreement_score":0.11810266,"about_ca_system_score_codex":0.0010601897,"about_ca_system_score_gemma":0.004303906,"threshold_uncertainty_score":0.9999476},"labels":[],"label_agreement":null},{"id":"W4415325631","doi":"10.1101/2025.10.17.25337471","title":"Artificial Intelligence-assisted reader evaluation in acute CT head interpretation (AI-REACT): a multireader multicase study","year":2025,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"University of Oxford","keywords":"Diagnostic accuracy; Confidence interval; Head trauma; Computed tomography; Emergency department; Neuroimaging; Triage; Head (geology)","score_opus":0.07239348744651863,"score_gpt":0.4276278960154223,"score_spread":0.35523440856890365,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415325631","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9730049,0.00020887687,0.014610871,0.006510058,0.0014613234,0.0033564812,0.000016449574,0.0001512704,0.00067976676],"genre_scores_gemma":[0.99482834,0.000039446284,0.0028394514,0.0008920872,0.00021600335,0.0005202843,0.00030894557,0.00004936411,0.00030609124],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9953818,0.0007827688,0.0012984825,0.001080045,0.0010095281,0.00044738245],"domain_scores_gemma":[0.99785125,0.000371522,0.00031632523,0.00086589216,0.00037709717,0.000217912],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.002957411,0.00048940186,0.0009463554,0.0008620355,0.00008635596,0.00011099538,0.00031932534,0.00024210331,0.00015808908],"category_scores_gemma":[0.0033212986,0.00044164658,0.00024066142,0.0005102541,0.00014501551,0.00009301975,0.0003392619,0.0026746623,0.00004326928],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008665482,0.0029751768,0.16539784,0.0004654962,0.00076835876,0.0011464787,0.010395452,0.0036127542,0.0012130336,0.000053191063,0.00015193516,0.8129537],"study_design_scores_gemma":[0.0010284423,0.00020248875,0.15500419,0.001667323,0.0013103574,0.00006726399,0.0013155661,0.8377181,0.00048190355,0.00068245304,0.00014154498,0.00038034178],"about_ca_topic_score_codex":0.0012110281,"about_ca_topic_score_gemma":0.0004192665,"teacher_disagreement_score":0.8341054,"about_ca_system_score_codex":0.00049524056,"about_ca_system_score_gemma":0.0006056558,"threshold_uncertainty_score":0.99980354},"labels":[],"label_agreement":null},{"id":"W4415402222","doi":"10.3390/cancers17203394","title":"A Priori Prediction of Neoadjuvant Chemotherapy Response in Breast Cancer Using Deep Features from Pre-Treatment MRI and CT","year":2025,"lang":"en","type":"article","venue":"Cancers","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Toronto Metropolitan University; Health Sciences Centre; Sunnybrook Health Science Centre","funders":"Natural Sciences and Engineering Research Council of Canada; Terry Fox Research Institute; University of Toronto; Terry Fox Foundation","keywords":"Radiomics; Breast cancer; Feature (linguistics); Breast MRI; Pattern recognition (psychology); Feature selection; Deep learning; Neoadjuvant therapy","score_opus":0.006882309839001007,"score_gpt":0.302846860440009,"score_spread":0.295964550601008,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415402222","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9913945,0.004117961,0.0004962366,0.003331435,0.0002450264,0.00026846997,0.000042186635,0.000020893596,0.0000832733],"genre_scores_gemma":[0.9959319,0.0020144554,0.0010733943,0.00062614854,0.0001000672,0.000021882508,0.000008149749,0.000013650296,0.00021034981],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9993054,0.000049681832,0.00017409404,0.00021890162,0.000108896646,0.00014297402],"domain_scores_gemma":[0.99963677,0.00006114332,0.000062817846,0.00014384434,0.000027606604,0.0000678121],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013231397,0.00011062693,0.00026613133,0.00012277889,0.000033411834,0.00000947069,0.000038059236,0.000040661682,0.000032865384],"category_scores_gemma":[0.00003526803,0.000089449066,0.00003884015,0.0001655023,0.00009399469,0.000034536482,0.0000130174185,0.00015207111,8.886326e-8],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008623365,0.000076229146,0.58064854,0.00014330851,0.00038373788,0.000070052825,0.0033349094,0.010954424,0.080850996,0.000016396556,0.000680841,0.3142172],"study_design_scores_gemma":[0.0037922778,0.00011215977,0.8893881,0.0008607965,0.00011129953,0.000028369093,0.000189356,0.101363584,0.0018449388,0.000036848513,0.0022048645,0.00006741608],"about_ca_topic_score_codex":0.017639706,"about_ca_topic_score_gemma":0.00013863639,"teacher_disagreement_score":0.3141498,"about_ca_system_score_codex":0.001319472,"about_ca_system_score_gemma":0.00061847083,"threshold_uncertainty_score":0.9889019},"labels":[],"label_agreement":null},{"id":"W4415402809","doi":"10.2196/73162","title":"Survival Prediction for Postoperative Patients With Kidney Cancer Based on Computed Tomography Radiomics: Retrospective Cohort Study","year":2025,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Retrospective cohort study; Nomogram; Kidney cancer; Computed tomography; Radiomics; Cancer; Kidney disease; Survival analysis","score_opus":0.0051517246297633846,"score_gpt":0.28640158593681947,"score_spread":0.2812498613070561,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415402809","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94166434,0.000012611292,0.040210526,0.005437926,0.0012494323,0.0061788755,0.00016195887,0.00025377155,0.0048305914],"genre_scores_gemma":[0.98250335,0.00000725909,0.002699654,0.013223466,0.0001840643,0.0006930082,0.0005202477,0.000033186177,0.00013576173],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9973968,0.00007324267,0.00065654353,0.00025325903,0.001275441,0.0003447143],"domain_scores_gemma":[0.9982893,0.00018636632,0.00018487466,0.0003351863,0.0005076838,0.00049658475],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000722189,0.0002711375,0.0006291598,0.00037238747,0.00020910942,0.00005270771,0.00018756944,0.00017059079,0.00008755466],"category_scores_gemma":[0.0007344719,0.00019001089,0.00011472964,0.00061606924,0.00017585789,0.00012531958,0.000043762313,0.00078240654,0.0000029097466],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000783564,0.0011344735,0.9768033,0.00019458203,0.0004330279,0.000004925926,0.0010720819,0.000152569,0.0000017296593,0.0001680036,0.014699554,0.004552181],"study_design_scores_gemma":[0.011287027,0.0018740776,0.6976161,0.0007474866,0.0002094178,0.0000012899662,0.00041011415,0.28385407,0.00001259545,0.0000149937205,0.003812606,0.0001602105],"about_ca_topic_score_codex":0.00003560918,"about_ca_topic_score_gemma":0.000006276249,"teacher_disagreement_score":0.2837015,"about_ca_system_score_codex":0.0003096953,"about_ca_system_score_gemma":0.00064363657,"threshold_uncertainty_score":0.7748419},"labels":[],"label_agreement":null},{"id":"W4415446324","doi":"10.1016/j.jacc.2025.09.571","title":"TCT-449 Automated SYNTAX Score Prediction Using Deep Learning Outperforms Expert Readers in Coronary Angiography Assessment","year":2025,"lang":"en","type":"article","venue":"Journal of the American College of Cardiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Montreal Heart Institute","funders":"","keywords":"Deep learning; Syntax; Coronary angiography; Angiography; Text mining","score_opus":0.011518485072911857,"score_gpt":0.3129570029223823,"score_spread":0.30143851784947046,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415446324","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9892426,0.00088707265,0.005852589,0.0025194124,0.000684426,0.00019041763,0.0000043513046,0.000028992887,0.00059011125],"genre_scores_gemma":[0.9939296,0.00037744682,0.0049384967,0.0005179694,0.00017519672,0.0000032711341,0.0000020095215,0.00001621627,0.000039796516],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99823236,0.0004029239,0.0006566917,0.00015582208,0.00030515285,0.00024705156],"domain_scores_gemma":[0.9987087,0.00019767169,0.00064458797,0.00020416956,0.0001627575,0.0000820928],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00088005856,0.00014466351,0.00089845987,0.0006097298,0.000096942334,0.0000052536384,0.00021241796,0.000070143185,0.0000042710976],"category_scores_gemma":[0.0003797895,0.00009702495,0.000519887,0.0008986004,0.00052539416,0.000066582536,0.00007982919,0.0008394977,1.3687388e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004440981,0.00004646187,0.94754505,0.000042395517,0.0007510381,0.00034353219,0.00013766818,0.036276568,0.0074905166,0.000029935645,0.0012939877,0.0055987253],"study_design_scores_gemma":[0.0017792872,0.0008111248,0.8714232,0.0007016305,0.00034789764,0.0033809869,0.003771247,0.11591467,0.00010814632,0.000059586906,0.0016009983,0.00010123671],"about_ca_topic_score_codex":0.000047447575,"about_ca_topic_score_gemma":0.0000016766155,"teacher_disagreement_score":0.0796381,"about_ca_system_score_codex":0.00025308435,"about_ca_system_score_gemma":0.00034776083,"threshold_uncertainty_score":0.3956563},"labels":[],"label_agreement":null},{"id":"W4415446918","doi":"10.1016/j.jacc.2025.09.562","title":"TCT-441 DeepCORO-CLIP: Development and Validation of a Foundation Model for Multi-view Coronary Artery Analysis Through Video-Text Contrastive Learning","year":2025,"lang":"en","type":"article","venue":"Journal of the American College of Cardiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Montreal Heart Institute","funders":"","keywords":"Foundation (evidence); Coronary artery disease; MEDLINE; Disease; Contrastive analysis","score_opus":0.02148838481458054,"score_gpt":0.3230228192599511,"score_spread":0.30153443444537054,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415446918","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.56284714,0.00027836955,0.4356516,0.0008893185,0.00008475246,0.00016643167,0.000004276871,0.0000026012399,0.00007552887],"genre_scores_gemma":[0.9568551,0.00026634237,0.042313624,0.0003096811,0.000049204657,0.0000075286557,0.000005636227,0.000008538251,0.00018431622],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99862915,0.00023775452,0.00067328446,0.00013724588,0.00018610818,0.00013643163],"domain_scores_gemma":[0.998014,0.0004551867,0.00097458955,0.00012552364,0.00038538253,0.000045360204],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00087170076,0.000111637455,0.0010531537,0.00022133875,0.00009011841,0.0000041108683,0.00011423214,0.000041656273,0.0000022246932],"category_scores_gemma":[0.00091964507,0.000078524215,0.0003149486,0.00042024208,0.00035701634,0.000060616927,0.00005092163,0.0002693584,1.1461699e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0046321508,0.00024962606,0.5490833,0.000567439,0.019021962,0.00009499503,0.002060678,0.28536046,0.01881176,0.0014762694,0.0012984455,0.117342904],"study_design_scores_gemma":[0.0070242854,0.0011897834,0.29270202,0.0006380975,0.007455225,0.0009925992,0.0023125592,0.6778645,0.0026493836,0.00087406824,0.0060442113,0.00025326328],"about_ca_topic_score_codex":0.000005389895,"about_ca_topic_score_gemma":0.000002209823,"teacher_disagreement_score":0.394008,"about_ca_system_score_codex":0.00009099905,"about_ca_system_score_gemma":0.00035317588,"threshold_uncertainty_score":0.32021245},"labels":[],"label_agreement":null},{"id":"W4415449897","doi":"10.1210/jendso/bvaf149.2342","title":"SUN-326 The additive value of real-time elastography to thyroid ultrasound in detecting malignancy in nodules over 20 mm in diameter","year":2025,"lang":"en","type":"article","venue":"Journal of the Endocrine Society","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Petro-Canada","funders":"","keywords":"Thyroid nodules; Nodule (geology); Thyroid; Malignancy; Elastography; Grading (engineering); Ultrasound","score_opus":0.004147621643434331,"score_gpt":0.2726947115520179,"score_spread":0.26854708990858356,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415449897","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99107,0.00038243126,0.00020072838,0.0069381148,0.00023760405,0.00024964978,0.000005661043,0.0000051642573,0.00091066776],"genre_scores_gemma":[0.9938794,0.00058475137,0.0034067007,0.0016070227,0.00015815893,0.000006690049,0.0000010212207,0.00001831692,0.00033793403],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99828845,0.00022992826,0.00068090454,0.00015397037,0.00034583482,0.00030088774],"domain_scores_gemma":[0.99815184,0.0011792571,0.00030101588,0.00022793154,0.000077740166,0.00006220366],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012404945,0.00014689307,0.00045530705,0.00021219441,0.000052491294,0.000016853237,0.0002965826,0.00004459424,0.00003092175],"category_scores_gemma":[0.0017903072,0.00008582872,0.00044509233,0.00096050516,0.00012675584,0.0000745413,0.0001063818,0.0011216836,7.1339485e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029305933,0.0004104988,0.79884243,0.00014271091,0.0003204576,0.00009659123,0.0060847746,0.003355625,0.16937776,0.00020507042,0.014437117,0.0064339275],"study_design_scores_gemma":[0.0043711616,0.000246068,0.9734966,0.0026187375,0.00013006272,0.00020128534,0.002416013,0.0026984124,0.008905396,0.0011846655,0.0035610297,0.00017057314],"about_ca_topic_score_codex":0.00040056714,"about_ca_topic_score_gemma":0.00007463419,"teacher_disagreement_score":0.17465419,"about_ca_system_score_codex":0.00015730366,"about_ca_system_score_gemma":0.000119349505,"threshold_uncertainty_score":0.48732194},"labels":[],"label_agreement":null},{"id":"W4415453393","doi":"10.1210/jendso/bvaf149.2494","title":"SUN-292 Examining Predictive Elements Influencing Metastasis to Right Para Esophageal Lymph Nodes in Papillary Thyroid Carcinoma: A Systematic Review and Meta-Analysis","year":2025,"lang":"en","type":"review","venue":"Journal of the Endocrine Society","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Metastasis; Echogenicity; Funnel plot; Lymph node metastasis; Lymph node; Thyroid; Lymph; Meta-analysis","score_opus":0.038652245627838235,"score_gpt":0.35604254725283735,"score_spread":0.3173903016249991,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415453393","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00016470309,0.9962832,0.00022968334,0.0013278878,0.000099508616,0.0017706829,0.00004450262,0.000012641765,0.000067240224],"genre_scores_gemma":[0.0009008741,0.9916798,0.0031985478,0.0032048444,0.00011523835,0.00013535946,0.000012480297,0.000045962588,0.00070688355],"study_design_codex":"systematic_review","study_design_gemma":"meta_analysis","domain_scores_codex":[0.9939663,0.0012598145,0.0028861582,0.00046693432,0.00095044903,0.0004703889],"domain_scores_gemma":[0.9954944,0.0009943555,0.002244527,0.0007056155,0.00026621734,0.00029485958],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0037613774,0.00063957996,0.009822499,0.00045676564,0.00015987302,0.00006831817,0.0006384858,0.00010874061,0.000055509925],"category_scores_gemma":[0.0023154481,0.00032826685,0.005352524,0.0019120157,0.000091017486,0.00012834699,0.00044550732,0.0015091822,0.0000014788504],"study_design_candidate":"meta_analysis","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008940934,0.000118735756,0.00065758405,0.78941524,0.2057641,0.0003550525,0.00045827884,0.000049653063,0.0000011866282,0.000010582512,0.0012906237,0.0018700375],"study_design_scores_gemma":[0.0007269684,0.00008136729,0.00022704697,0.071941435,0.9219939,0.00094871456,0.00018084151,0.00013033563,0.0000011477031,0.000010778308,0.0035058476,0.00025160224],"about_ca_topic_score_codex":0.00005214804,"about_ca_topic_score_gemma":0.000001753889,"teacher_disagreement_score":0.7174738,"about_ca_system_score_codex":0.00052717904,"about_ca_system_score_gemma":0.0005933274,"threshold_uncertainty_score":0.9999169},"labels":[],"label_agreement":null},{"id":"W4415507482","doi":"10.1016/j.cpet.2025.09.009","title":"Large Language Models Are Reshaping Patient Data Management and Clinical Practice in Nuclear Medicine","year":2025,"lang":"en","type":"article","venue":"PET Clinics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency","funders":"","keywords":"Clinical Practice; Field (mathematics); Adaptation (eye); Domain (mathematical analysis); Medical practice; Key (lock); Data management; Alternative medicine","score_opus":0.04204382532221992,"score_gpt":0.4298031957762698,"score_spread":0.3877593704540499,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415507482","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7071838,0.014497351,0.007910743,0.15084547,0.0018989507,0.0015751536,0.00005528054,0.00029276943,0.11574051],"genre_scores_gemma":[0.8020449,0.016776813,0.058057867,0.119822055,0.0006201647,0.000013316978,0.00022393494,0.0000890965,0.0023518025],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99796146,0.00017892953,0.00076465314,0.00052357756,0.00029167382,0.00027972885],"domain_scores_gemma":[0.997854,0.00092852995,0.0002052742,0.0008080942,0.000053829524,0.00015029406],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003175899,0.00012992515,0.0004338987,0.00015201695,0.00006717071,0.00002133309,0.00023738656,0.00007171114,0.000055932844],"category_scores_gemma":[0.0066684177,0.00010916778,0.000033158052,0.00021683199,0.00013514725,0.00015115726,0.00065320637,0.00084825914,0.000011012631],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012577829,0.0025674428,0.074177325,0.0014866866,0.00093907985,0.008432662,0.0057147783,0.00015514303,0.0000141815735,0.0192973,0.343801,0.54215664],"study_design_scores_gemma":[0.0051880064,0.00023945907,0.013347672,0.0015408557,0.00046532456,0.00007451517,0.011533852,0.5261048,1.5466861e-7,0.0007682848,0.44057378,0.00016328125],"about_ca_topic_score_codex":0.000067789166,"about_ca_topic_score_gemma":0.000027658838,"teacher_disagreement_score":0.5419933,"about_ca_system_score_codex":0.00003402609,"about_ca_system_score_gemma":0.000041096995,"threshold_uncertainty_score":0.79832006},"labels":[],"label_agreement":null},{"id":"W4415520146","doi":"10.1016/j.jtho.2025.09.1122","title":"PT1.04.04 Biomarker-Based Eligibility for Lung Cancer Screening - Validation of Protein-Based INTEGRAL-Risk Model in the LC3 Consortium","year":2025,"lang":"en","type":"article","venue":"Journal of Thoracic Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lunenfeld-Tanenbaum Research Institute","funders":"","keywords":"Lung cancer screening; Lung cancer; MEDLINE; Cancer","score_opus":0.032491435333927156,"score_gpt":0.46536927765584163,"score_spread":0.43287784232191445,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415520146","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6591815,0.0005580889,0.3194482,0.019798698,0.0001919823,0.00061164994,0.000010207641,0.00000762719,0.00019205816],"genre_scores_gemma":[0.9514067,0.000029453853,0.04691115,0.0014242014,0.00008878244,0.0000567827,0.000008803102,0.000013158774,0.000060933136],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978009,0.000535259,0.0009342756,0.00018758571,0.0003038454,0.00023817075],"domain_scores_gemma":[0.99736243,0.0009758201,0.00092005625,0.00023428885,0.00042550845,0.0000818649],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0049578035,0.00014461177,0.00062928157,0.00043077298,0.00007873771,0.000016402095,0.00024811813,0.00015899079,0.000020470181],"category_scores_gemma":[0.00290171,0.00009447509,0.00024969957,0.00038259255,0.0001994171,0.0000629192,0.000020737862,0.00084424677,1.07676335e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.015133525,0.0017374569,0.20790674,0.0023295777,0.0005719247,0.00012887619,0.0007850903,0.18060401,0.04026064,0.00028921946,0.0047564837,0.54549646],"study_design_scores_gemma":[0.0030078855,0.0006075936,0.010459044,0.0012945053,0.0006190127,0.000022044873,0.00019724878,0.97162545,0.009998579,0.00081977405,0.0012533937,0.00009549116],"about_ca_topic_score_codex":0.00018389887,"about_ca_topic_score_gemma":0.00002855454,"teacher_disagreement_score":0.7910214,"about_ca_system_score_codex":0.00031215054,"about_ca_system_score_gemma":0.0015987189,"threshold_uncertainty_score":0.38525823},"labels":[],"label_agreement":null},{"id":"W4415520171","doi":"10.1016/j.jtho.2025.09.112","title":"MA03.01 Ultrasensitive MRD Improves Detection in Resectable Stage I NSCLC","year":2025,"lang":"en","type":"article","venue":"Journal of Thoracic Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; St Joseph's Health Centre; Toronto East General Hospital; Princess Margaret Cancer Centre","funders":"","keywords":"Stage (stratigraphy); Neoplasm staging; MEDLINE; Carcinoma","score_opus":0.011144662150878143,"score_gpt":0.40401976473193674,"score_spread":0.3928751025810586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415520171","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9707856,0.00040309096,0.007864434,0.0077255885,0.0010705321,0.0001614576,9.3812645e-7,0.000014537341,0.011973814],"genre_scores_gemma":[0.9920499,0.00014962666,0.0033348727,0.0014027507,0.00029130286,0.0000024601304,0.0000014075796,0.000011972913,0.002755715],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99861884,0.0002443515,0.00054873695,0.00014554724,0.00019503637,0.00024751527],"domain_scores_gemma":[0.9988527,0.00035733468,0.0003234512,0.00012418408,0.00021899705,0.0001233025],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015783616,0.00010627337,0.0005059802,0.0005341977,0.00005318212,0.000016012344,0.000092960465,0.00015715137,0.00004934905],"category_scores_gemma":[0.0014993806,0.00008530408,0.00010303075,0.0004473246,0.000098730736,0.00010203514,0.00003262902,0.0012255975,0.000004118727],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0030619747,0.00033390915,0.003512103,0.00015495674,0.0001397829,0.0017487754,0.0004109521,0.00013432663,0.29349416,0.00008381811,0.0011600786,0.69576514],"study_design_scores_gemma":[0.015708407,0.0120853735,0.3666528,0.003911721,0.0014833388,0.008373222,0.010361047,0.022302354,0.26981205,0.0056207096,0.28287387,0.0008151374],"about_ca_topic_score_codex":0.00011274934,"about_ca_topic_score_gemma":0.00008496252,"teacher_disagreement_score":0.69495004,"about_ca_system_score_codex":0.0004394171,"about_ca_system_score_gemma":0.0005567354,"threshold_uncertainty_score":0.5324679},"labels":[],"label_agreement":null},{"id":"W4415520360","doi":"10.1016/j.jtho.2025.09.135","title":"MA05.06 Integrating Circulating Protein Biomarkers in Nodule Malignancy Prediction Model Based on Five International Lung Cancer Screening Cohorts","year":2025,"lang":"en","type":"article","venue":"Journal of Thoracic Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lunenfeld-Tanenbaum Research Institute","funders":"","keywords":"Malignancy; Lung cancer screening; Lung cancer; Nodule (geology); Cancer; Lung; Biomarker","score_opus":0.011904925806043175,"score_gpt":0.3964103218691319,"score_spread":0.3845053960630887,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415520360","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.769272,0.00033128005,0.20598876,0.017304506,0.0009152264,0.0004426519,0.000007440725,0.000027084294,0.005711026],"genre_scores_gemma":[0.948642,0.000022397136,0.049326893,0.00131635,0.00027157803,0.000026477222,0.000012569473,0.000018612553,0.00036309907],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99817574,0.00018964766,0.0007938664,0.000223874,0.00037889992,0.00023797748],"domain_scores_gemma":[0.99877524,0.0001863968,0.0005604375,0.00012269306,0.0002483679,0.00010687935],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015870656,0.0001530193,0.00047204737,0.0007302133,0.00007981742,0.00002770832,0.0001630117,0.0001600544,0.000049725462],"category_scores_gemma":[0.0012027622,0.000129083,0.00014234848,0.00030948393,0.00006525614,0.0001303675,0.00004326507,0.0010576915,4.816877e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019721582,0.0004533079,0.27982315,0.0003446624,0.0005862208,0.00084774353,0.0005645317,0.25362137,0.022627262,0.00018233267,0.0027371403,0.43624014],"study_design_scores_gemma":[0.0014114047,0.00020570647,0.017426835,0.004835374,0.00014891585,0.00010532955,0.00022181546,0.97454214,0.00039906192,0.00014670382,0.0004722306,0.00008447345],"about_ca_topic_score_codex":0.00008766372,"about_ca_topic_score_gemma":0.000015083522,"teacher_disagreement_score":0.7209208,"about_ca_system_score_codex":0.000848361,"about_ca_system_score_gemma":0.00067502214,"threshold_uncertainty_score":0.5263852},"labels":[],"label_agreement":null},{"id":"W4415534402","doi":"10.1016/j.cpet.2025.09.003","title":"Toward Integrated Clinical-Computational Nuclear Medicine","year":2025,"lang":"en","type":"review","venue":"PET Clinics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Institutes of Health; Siemens Healthineers","keywords":"Workflow; Automation; Field (mathematics); Precision medicine; Key (lock); Personalized medicine","score_opus":0.09530598775363894,"score_gpt":0.475079336003645,"score_spread":0.3797733482500061,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415534402","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000050608596,0.982513,0.0013633728,0.0038728116,0.0023224326,0.0007119846,0.000034923723,0.0002569459,0.008919473],"genre_scores_gemma":[0.0000029415064,0.97906196,0.008971322,0.0048998385,0.0015113212,0.000019449151,0.0010894679,0.0001068612,0.0043368232],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9951686,0.00046547104,0.0026063442,0.00084273756,0.0005346984,0.00038214293],"domain_scores_gemma":[0.9942804,0.0035909603,0.00078425184,0.000655664,0.00026715617,0.000421579],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0024998465,0.0005475343,0.00402907,0.0004012231,0.00009634722,0.000034857978,0.00046023141,0.0004630684,0.00082742545],"category_scores_gemma":[0.011427628,0.00038007562,0.00096948683,0.00066066714,0.0004825761,0.00003514832,0.00018928284,0.0033690154,0.00035859842],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000191606,0.00013012503,0.000037965467,0.014576647,0.0004275045,0.0002981138,0.000028716882,0.0000037498032,4.197957e-9,0.0006255214,0.06898436,0.9148681],"study_design_scores_gemma":[0.0010840513,0.00028440822,0.00001755742,0.035421915,0.0029583308,0.00036777105,0.000028395345,0.004067302,6.5543454e-10,0.00041338618,0.95507866,0.00027820806],"about_ca_topic_score_codex":0.000024985571,"about_ca_topic_score_gemma":6.1309066e-7,"teacher_disagreement_score":0.91458994,"about_ca_system_score_codex":0.00012899042,"about_ca_system_score_gemma":0.0015335047,"threshold_uncertainty_score":0.9998651},"labels":[],"label_agreement":null},{"id":"W4415567131","doi":"10.3389/fnagi.2025.1679788","title":"Multimodal radiomics of cerebellar subregions for machine learning-driven Alzheimer’s disease diagnosis","year":2025,"lang":"en","type":"article","venue":"Frontiers in Aging Neuroscience","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research; National Institutes of Health; Northern California Institute for Research and Education; BioClinica; Alzheimer's Disease Neuroimaging Initiative; Bristol-Myers Squibb; Eli Lilly and Company; Biogen; Eisai; Alzheimer's Association; Foundation for the National Institutes of Health","keywords":"Radiomics; Disease; Neuroimaging; Magnetic resonance imaging; Cerebellum; Biomarker","score_opus":0.017368757387368074,"score_gpt":0.2968238335483256,"score_spread":0.2794550761609575,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415567131","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43987596,0.007607029,0.51778406,0.026055451,0.005680676,0.0021173682,0.00006096564,0.0002493887,0.0005690791],"genre_scores_gemma":[0.973743,0.000818152,0.023136778,0.0016848025,0.000052791544,0.000073608484,0.000017819122,0.00002722346,0.00044581175],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99838233,0.00008110101,0.00035969226,0.00051434105,0.00025921917,0.0004033209],"domain_scores_gemma":[0.99907833,0.00019850426,0.00012801151,0.0003165484,0.00005920545,0.0002193695],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038125398,0.00017943207,0.00040460564,0.00048893807,0.00018195751,0.000030042216,0.00033192433,0.00005086384,0.0000031257655],"category_scores_gemma":[0.0019635984,0.00017303716,0.00015134098,0.00069815066,0.00045490495,0.00009539936,0.000099167686,0.00045948807,3.869721e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000103176695,0.00017726827,0.97279173,0.00014486322,0.000016832106,0.000035303736,0.00014657155,0.008196716,0.0011382119,0.00026399075,0.0040638056,0.012921527],"study_design_scores_gemma":[0.0016955199,0.00009288384,0.12886406,0.00032223345,0.00015939868,0.000006393669,0.000046327845,0.8439409,0.0006993749,0.0003259496,0.023683583,0.00016335977],"about_ca_topic_score_codex":0.00007158136,"about_ca_topic_score_gemma":0.000002066543,"teacher_disagreement_score":0.8439277,"about_ca_system_score_codex":0.00006768992,"about_ca_system_score_gemma":0.00020553585,"threshold_uncertainty_score":0.70562506},"labels":[],"label_agreement":null},{"id":"W4415618108","doi":"10.1148/radiol.253205","title":"Subregional Radiomics Analysis for the Prediction of Progression-free Survival of Primary Spinal Tumors","year":2025,"lang":"en","type":"editorial","venue":"Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Sunnybrook Health Science Centre","funders":"","keywords":"Radiomics; Survival analysis; Overall survival; MEDLINE; Prognostic model; Primary (astronomy); Primary tumor","score_opus":0.01287661239849972,"score_gpt":0.3084124042035821,"score_spread":0.2955357918050824,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415618108","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006907007,0.010110013,0.08198226,0.005049401,0.89025956,0.0023603858,0.0020285975,0.00011419466,0.0011885513],"genre_scores_gemma":[0.034942906,0.004010836,0.012369251,0.00032009726,0.93608445,0.00035841457,0.009471513,0.00014216392,0.002300372],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972959,0.00020121798,0.00094157306,0.00048771768,0.0007354103,0.0003381666],"domain_scores_gemma":[0.99432456,0.0034979952,0.0007708614,0.00082227285,0.00048202503,0.00010229948],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015787358,0.00029712284,0.0017768302,0.0005599975,0.000099766425,0.0000074306304,0.0006148903,0.0007110415,0.000020805664],"category_scores_gemma":[0.0055511235,0.00020215123,0.0007774978,0.0005349133,0.00062140374,0.00002495116,0.00014488316,0.0011189573,2.615594e-7],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002319028,0.00018009063,0.026007248,0.0016871558,0.0051407204,0.000016493777,0.000057444315,0.00023778071,0.00020124028,0.00093067315,0.95606405,0.0071580913],"study_design_scores_gemma":[0.009565701,0.003058328,0.083573475,0.0016936931,0.018429408,0.000105279665,0.00007051345,0.030688759,0.00007112575,0.0011923497,0.85108376,0.0004676002],"about_ca_topic_score_codex":0.00008484181,"about_ca_topic_score_gemma":0.0000034905972,"teacher_disagreement_score":0.10498026,"about_ca_system_score_codex":0.00017638209,"about_ca_system_score_gemma":0.0013795197,"threshold_uncertainty_score":0.8243488},"labels":[],"label_agreement":null},{"id":"W4415898701","doi":"10.1136/jitc-2025-sitc2025.0078","title":"78 Exploratory radiomics analysis in unresectable hepatocellular carcinoma treated with durvalumab alone or combined with tremelimumab or bevacizumab","year":2025,"lang":"","type":"article","venue":"Regular and Young Investigator Award Abstracts","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"AstraZeneca (Canada)","funders":"","keywords":"Durvalumab; Tremelimumab; Bevacizumab; Radiomics; Hepatocellular carcinoma; Nivolumab; Exploratory analysis","score_opus":0.015160175798743708,"score_gpt":0.25031871104562703,"score_spread":0.23515853524688332,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415898701","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98862815,0.0044193347,0.00057994784,0.0033350727,0.00031197738,0.0018335808,0.000048195743,0.00018809408,0.00065563316],"genre_scores_gemma":[0.9898199,0.001259023,0.0019338101,0.001078833,0.00019195779,0.000108469605,0.0002996103,0.00019955647,0.005108861],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9921302,0.00070102036,0.002021897,0.002019808,0.0013833913,0.0017436816],"domain_scores_gemma":[0.9946727,0.0005004993,0.00077335397,0.0015589489,0.0004316972,0.0020627666],"candidate_categories":["metaepi_narrow"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.0020028297,0.001425631,0.0032528993,0.0021463458,0.0006153787,0.00045597856,0.0005662038,0.0006763996,0.0001474966],"category_scores_gemma":[0.0015603094,0.0009807748,0.00032444796,0.005790945,0.0018043054,0.0005831122,0.00018528414,0.0019917393,0.000011947511],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.024370648,0.0012749052,0.93649185,0.0023751745,0.007231806,0.013623709,0.00243241,0.004127275,0.0045011514,0.00025881588,0.0015188644,0.0017933901],"study_design_scores_gemma":[0.07492948,0.00848369,0.52040786,0.008555257,0.024548858,0.0015746794,0.005911015,0.32252783,0.02410229,0.00022397084,0.005167169,0.0035679452],"about_ca_topic_score_codex":0.0031858103,"about_ca_topic_score_gemma":0.0020009717,"teacher_disagreement_score":0.41608402,"about_ca_system_score_codex":0.0008982941,"about_ca_system_score_gemma":0.0048912386,"threshold_uncertainty_score":0.9998494},"labels":[],"label_agreement":null},{"id":"W4415942489","doi":"10.1016/j.annonc.2025.08.2535","title":"1911P Evaluation of an AI-based imaging endpoint as a surrogate endpoint for overall survival (OS) in a phase III advanced non-small cell lung cancer (aNSCLC) randomized controlled trial (RCT)","year":2025,"lang":"en","type":"article","venue":"Annals of Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Glycemic Index Laboratories; University of Calgary; Princess Margaret Cancer Centre; Occupational Cancer Research Centre","funders":"","keywords":"Surrogate endpoint; Clinical endpoint; Randomized controlled trial; Overall survival; Lung cancer; Survival rate; Progression-free survival; Survival analysis","score_opus":0.030202384002716482,"score_gpt":0.4442721274187099,"score_spread":0.41406974341599345,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415942489","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96658427,0.0012307285,0.008820979,0.009968247,0.0009780582,0.00913151,0.000029184674,0.000025207633,0.0032318197],"genre_scores_gemma":[0.99260896,0.00020494637,0.0017803658,0.0030797692,0.0001638993,0.0018158827,0.00013812444,0.000030605544,0.00017746376],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.995662,0.0013182464,0.0016210887,0.00046291458,0.00047775285,0.0004580139],"domain_scores_gemma":[0.9953562,0.002330634,0.0009054529,0.00032130384,0.0009277253,0.000158706],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01168477,0.00027784676,0.0029770145,0.0005275634,0.000052867035,0.000012447764,0.0001823995,0.00015163433,0.00016661298],"category_scores_gemma":[0.0043209926,0.00023185999,0.0006381029,0.00021358485,0.0002054484,0.000097432385,0.000037974856,0.00042420294,4.325815e-7],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.9307599,0.0020265025,0.00020076723,0.00032151013,0.00035256732,0.000023657609,0.0005401165,0.0058404086,0.011323092,0.0002422729,0.0002855538,0.048083644],"study_design_scores_gemma":[0.5872821,0.0010676421,0.00008308325,0.00022357906,0.00072976795,9.681355e-7,0.000076981465,0.404139,0.005167317,0.00055258156,0.00057439937,0.000102558726],"about_ca_topic_score_codex":0.0009775967,"about_ca_topic_score_gemma":0.00016591803,"teacher_disagreement_score":0.39829862,"about_ca_system_score_codex":0.00018548705,"about_ca_system_score_gemma":0.0028759441,"threshold_uncertainty_score":0.9454976},"labels":[],"label_agreement":null},{"id":"W4416140781","doi":"10.1093/neuonc/noaf201.0924","title":"INNV-35. Artificial intelligence in Neuro-Oncology: Mapping the field","year":2025,"lang":"en","type":"article","venue":"Neuro-Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Google (Canada)","funders":"","keywords":"Metadata; Field (mathematics); Deep learning; Python (programming language); Precision medicine; Key (lock); Generative grammar","score_opus":0.03112628055538892,"score_gpt":0.35447840790261126,"score_spread":0.32335212734722235,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416140781","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3174873,0.00058968825,0.027941236,0.57450193,0.0058632307,0.0013309479,0.00000218736,0.00023752918,0.07204596],"genre_scores_gemma":[0.8603871,0.00036412114,0.0016894734,0.13662313,0.00064002734,0.00008604738,0.000006760795,0.000031914697,0.00017142892],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99757797,0.00047897827,0.00068963657,0.0005079585,0.00021259024,0.00053287786],"domain_scores_gemma":[0.9946386,0.0045556347,0.0001544909,0.00044741418,0.00006666298,0.0001371935],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009889208,0.00021682713,0.000570149,0.00038433526,0.00016939103,0.00003243677,0.00040735558,0.00030194444,0.00016983124],"category_scores_gemma":[0.0065160724,0.00016615124,0.00012334775,0.00080565794,0.00031338024,0.000053813612,0.0002593252,0.0022360578,0.00006164705],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003141637,0.000325231,0.0077928593,0.000057819394,0.00003706913,0.0011134659,0.0009464833,0.0001932274,0.09291055,0.0073613906,0.019399736,0.869548],"study_design_scores_gemma":[0.00078555115,0.0010557865,0.0032484164,0.00011549192,0.00008001549,0.00031329808,0.0008036642,0.033756513,0.004864965,0.005147774,0.9496429,0.00018564447],"about_ca_topic_score_codex":0.00013012458,"about_ca_topic_score_gemma":0.00008205383,"teacher_disagreement_score":0.93024313,"about_ca_system_score_codex":0.0002375888,"about_ca_system_score_gemma":0.0006583217,"threshold_uncertainty_score":0.97146827},"labels":[],"label_agreement":null},{"id":"W4416192201","doi":"10.3390/cancers17223638","title":"Integrating Multi-Omics and Medical Imaging in Artificial Intelligence-Based Cancer Research: An Umbrella Review of Fusion Strategies and Applications","year":2025,"lang":"en","type":"review","venue":"Cancers","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Interpretability; Modalities; Context (archaeology); Precision medicine; Generalizability theory; Medical imaging; Data integration; Cancer","score_opus":0.13321043786245654,"score_gpt":0.49417044641895014,"score_spread":0.3609600085564936,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416192201","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000020679952,0.99062127,0.0070418934,0.000722428,0.000103029524,0.0011922581,0.00001825213,0.00002037381,0.00025984403],"genre_scores_gemma":[0.00009249414,0.99708825,0.001677344,0.00044448298,0.0001859737,0.00037285156,0.00008910636,0.000030290144,0.000019196097],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.9975667,0.00032903932,0.0008496028,0.00051781075,0.00044163485,0.00029523953],"domain_scores_gemma":[0.99842864,0.0006110466,0.0002340107,0.00029621331,0.00017695135,0.0002531226],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002157822,0.00025166266,0.0012490235,0.00045539648,0.00009920542,0.00005039188,0.00021250175,0.00017742938,0.0000534449],"category_scores_gemma":[0.0012655233,0.00020008207,0.00010194463,0.0007218331,0.00063139456,0.000066510445,0.000103521605,0.0014807939,5.35622e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000066891716,0.000018372553,0.000028879973,0.11597919,0.000015038752,0.000012844217,0.000060883085,0.000010446575,0.000004252453,0.0008656532,0.000055413224,0.8829423],"study_design_scores_gemma":[0.00026167484,0.000053725995,0.000008135347,0.6689915,0.00044267834,0.000032770757,0.0010336512,0.036470473,0.000005632532,0.00029595388,0.29210225,0.00030156772],"about_ca_topic_score_codex":0.0017031617,"about_ca_topic_score_gemma":0.0002841017,"teacher_disagreement_score":0.8826408,"about_ca_system_score_codex":0.000601876,"about_ca_system_score_gemma":0.0073120147,"threshold_uncertainty_score":0.99831563},"labels":[],"label_agreement":null},{"id":"W4416225917","doi":"10.1186/s12880-025-02014-3","title":"Predicting mild cognitive impairment in patients with Parkinson’s disease by integrating striatal MRI radiomics with clinical features","year":2025,"lang":"en","type":"article","venue":"BMC Medical Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Radiomics; Generalizability theory; Disease; Cognitive impairment; Predictive value; Magnetic resonance imaging; Neuroimaging; Cognition","score_opus":0.00645340450959763,"score_gpt":0.30297135936234443,"score_spread":0.2965179548527468,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416225917","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96278834,0.00071968324,0.02982913,0.004310901,0.00033388284,0.0010396284,0.00003024249,0.00015152126,0.0007966925],"genre_scores_gemma":[0.9890832,0.00009738395,0.0056426777,0.0042180885,0.00028993268,0.00006776527,0.00032424266,0.00005962733,0.0002170819],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99609536,0.00032897267,0.00086351397,0.000830447,0.0011940054,0.00068768114],"domain_scores_gemma":[0.9969876,0.0013270495,0.0002394934,0.00032194782,0.00016722712,0.0009566993],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0015330177,0.00039503328,0.00072552345,0.00026643433,0.00017228814,0.0000939171,0.00025840593,0.00012871614,0.00005929085],"category_scores_gemma":[0.0044316184,0.0002695405,0.00013631758,0.00049815193,0.00057042524,0.00017816422,0.00015544036,0.0018892258,0.0000031631214],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0026132583,0.0007142512,0.9637244,0.00022444528,0.00012444386,0.00014440864,0.00015668936,0.00001531534,0.0000012349639,0.00003449709,0.0050446233,0.027202439],"study_design_scores_gemma":[0.01853485,0.000263682,0.92205536,0.0069384146,0.0003161178,0.000017067257,0.00076221087,0.049939115,0.0000110473,0.00002199627,0.0008301396,0.00030997928],"about_ca_topic_score_codex":0.00018743628,"about_ca_topic_score_gemma":0.00008125221,"teacher_disagreement_score":0.0499238,"about_ca_system_score_codex":0.00020786113,"about_ca_system_score_gemma":0.0012703789,"threshold_uncertainty_score":0.9999757},"labels":[],"label_agreement":null},{"id":"W4416260673","doi":"10.1007/978-3-032-09336-3_5","title":"Predicting Microsatellite Instability from Whole Slide Images Using Texture Features","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"North Island College","funders":"","keywords":"Texture (cosmology); Microsatellite instability; Pattern recognition (psychology); Tile; Identification (biology); Microsatellite; Contrast (vision)","score_opus":0.010532180485038933,"score_gpt":0.2771961267223021,"score_spread":0.26666394623726314,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416260673","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01399288,0.004605673,0.97132987,0.0027279682,0.0018351349,0.0005841859,0.00007769155,0.00016800138,0.004678626],"genre_scores_gemma":[0.3543508,0.00023140793,0.62955946,0.009436754,0.003057191,0.000006064016,0.00019862106,0.00012696072,0.0030327253],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967701,0.000043135904,0.0005394261,0.0013354776,0.00074408087,0.00056780805],"domain_scores_gemma":[0.9978148,0.00063256477,0.00024058566,0.00088019716,0.0002081034,0.0002237486],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0007601314,0.0005147212,0.00079108845,0.00051559415,0.0002865084,0.0002737282,0.00068855326,0.00043586708,0.000044483797],"category_scores_gemma":[0.00077097403,0.0004326808,0.0001929605,0.0003492557,0.0010285645,0.00016459222,0.00058518583,0.0025423174,0.0000059344056],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000063859174,0.000059349582,0.014125334,0.00029075512,0.00007780449,0.0003373548,0.00091647025,0.008484566,0.022543406,0.00013936903,0.00017443883,0.9527873],"study_design_scores_gemma":[0.0028820946,0.0003570214,0.028485563,0.01472689,0.0005333972,0.000562481,0.0000037661753,0.83942014,0.020472873,0.06947826,0.02085175,0.0022257771],"about_ca_topic_score_codex":0.0004476874,"about_ca_topic_score_gemma":0.000050497598,"teacher_disagreement_score":0.9505615,"about_ca_system_score_codex":0.00040426396,"about_ca_system_score_gemma":0.00075346814,"threshold_uncertainty_score":0.9998125},"labels":[],"label_agreement":null},{"id":"W4416393342","doi":"10.3390/jimaging11110417","title":"Explainable Radiomics-Based Model for Automatic Image Quality Assessment in Breast Cancer DCE MRI Data","year":2025,"lang":"en","type":"article","venue":"Journal of Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"European Commission","keywords":"Support vector machine; Breast cancer; Image quality; Classifier (UML); Pattern recognition (psychology); Feature extraction; Magnetic resonance imaging; Quality assessment; Breast imaging","score_opus":0.03178610046728949,"score_gpt":0.4154949641104987,"score_spread":0.3837088636432092,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416393342","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05856374,0.0006981572,0.8488529,0.090631135,0.0003923212,0.00032497247,0.000043451244,0.000026709198,0.00046664666],"genre_scores_gemma":[0.7670235,0.00014570077,0.22757426,0.0047205826,0.00022468637,0.000017555676,0.000026842383,0.00003406877,0.00023283256],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981401,0.00009110549,0.00085543003,0.00024592402,0.0003394423,0.00032798783],"domain_scores_gemma":[0.99844164,0.0002930035,0.00042243922,0.00044447219,0.0002573328,0.00014111727],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031127688,0.00015681855,0.0005727415,0.00040077715,0.00008818423,0.000086749875,0.00040169933,0.000035315283,0.000030108193],"category_scores_gemma":[0.00048979284,0.00013156123,0.00012879133,0.00024223661,0.00008014223,0.00040611773,0.0000938254,0.0006831216,3.6798914e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012225972,0.0017883616,0.4330904,0.005283768,0.00068506785,0.0006630468,0.0010235549,0.12751468,0.05077989,0.0015143825,0.116667315,0.25976694],"study_design_scores_gemma":[0.004366834,0.000014807906,0.021429155,0.0012298268,0.00015918343,0.00011074098,0.00022260327,0.9709675,0.000089378496,0.00061791745,0.000679095,0.00011298892],"about_ca_topic_score_codex":0.00015894088,"about_ca_topic_score_gemma":0.000009688253,"teacher_disagreement_score":0.8434528,"about_ca_system_score_codex":0.0005024464,"about_ca_system_score_gemma":0.0015884944,"threshold_uncertainty_score":0.5364911},"labels":[],"label_agreement":null},{"id":"W4416598955","doi":"10.1186/s12967-025-07409-y","title":"Radiology-based artificial intelligence for predicting targeted therapy response in pan-cancer: a comprehensive review","year":2025,"lang":"en","type":"article","venue":"Journal of Translational Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"National Science and Technology Major Project; Zhejiang University; National Natural Science Foundation of China","keywords":"Selection (genetic algorithm); Targeted therapy; Applications of artificial intelligence; MEDLINE; Precision medicine","score_opus":0.050586647950795656,"score_gpt":0.3966035611420007,"score_spread":0.34601691319120503,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416598955","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20761366,0.19732057,0.17311104,0.41954276,0.0011031964,0.0011914605,0.000011747746,0.000023468529,0.000082123915],"genre_scores_gemma":[0.94723505,0.018407393,0.013906063,0.019483851,0.0008348219,0.00004418366,0.000029285447,0.000022771352,0.00003660907],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99795294,0.00022229589,0.0011102753,0.00016297476,0.00036247753,0.00018903514],"domain_scores_gemma":[0.99696136,0.002053737,0.0003325786,0.000105810526,0.0004474201,0.000099085984],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021806215,0.00014551244,0.0007101614,0.00046360854,0.000057244568,0.000004487503,0.00012963377,0.000077404366,0.00010480466],"category_scores_gemma":[0.0020515781,0.00010306994,0.00016995348,0.00046463506,0.0001908283,0.000050939743,0.0000037681523,0.0005791029,3.995081e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.050009284,0.0006673071,0.042721204,0.0041284566,0.0007721387,0.00023212684,0.0013668896,0.00910949,0.07897231,0.0016875289,0.0094087515,0.80092454],"study_design_scores_gemma":[0.028178195,0.009076527,0.38946614,0.10073427,0.0016594616,0.00079254503,0.0007683836,0.2868033,0.0042988793,0.02348169,0.15402745,0.00071315997],"about_ca_topic_score_codex":0.000013359807,"about_ca_topic_score_gemma":0.0000015096196,"teacher_disagreement_score":0.80021137,"about_ca_system_score_codex":0.000069028734,"about_ca_system_score_gemma":0.0006071151,"threshold_uncertainty_score":0.420307},"labels":[],"label_agreement":null},{"id":"W4416738724","doi":"10.3390/curroncol32110602","title":"Machine Learning-Based Prognostic Modelling Using MRI Radiomic Data in Cervical Cancer Treated with Definitive Chemoradiotherapy and Brachytherapy","year":2025,"lang":"en","type":"article","venue":"Current Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Radiomics; Brachytherapy; Cervical cancer; Chemoradiotherapy; Reliability (semiconductor); Radiation therapy","score_opus":0.0795269983788093,"score_gpt":0.4050665405462953,"score_spread":0.32553954216748604,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416738724","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.865509,0.018864205,0.110575624,0.0038625752,0.00022529626,0.0006775339,0.00001873005,0.000083801766,0.00018328826],"genre_scores_gemma":[0.98769933,0.0036287378,0.007207907,0.0009045138,0.00014939226,0.00005275649,0.00026645642,0.000048309623,0.000042595868],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983237,0.00021300436,0.00033462376,0.0005978477,0.00015406418,0.00037680616],"domain_scores_gemma":[0.9989926,0.00036879446,0.00012561952,0.00029983092,0.00007206567,0.00014105342],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042540918,0.00024642993,0.0006771934,0.00031828537,0.00010472097,0.000026549287,0.00016904544,0.00013023484,0.000046618632],"category_scores_gemma":[0.00012276266,0.0001962343,0.0000352944,0.00044437393,0.00026174015,0.000070691945,0.00005711644,0.0010234282,8.289008e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010916304,0.0005189643,0.8701054,0.00026637423,0.00012240646,0.00010826333,0.00020851991,0.0321534,0.00027073527,0.0000763028,0.00004607415,0.09503192],"study_design_scores_gemma":[0.008042252,0.0003845812,0.010994824,0.000716826,0.00020436553,0.00006716812,0.000031349653,0.9672008,0.000047389516,0.000043174674,0.012086816,0.00018045418],"about_ca_topic_score_codex":0.0005335764,"about_ca_topic_score_gemma":0.00008994399,"teacher_disagreement_score":0.9350474,"about_ca_system_score_codex":0.00033552802,"about_ca_system_score_gemma":0.00062558113,"threshold_uncertainty_score":0.80022025},"labels":[],"label_agreement":null},{"id":"W4416778686","doi":"10.3390/cancers17233810","title":"Radiomics Analysis of QUS Spectral Parametric Images for Predicting the Risk of Breast Cancer Recurrence","year":2025,"lang":"en","type":"article","venue":"Cancers","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Health Sciences Centre; Sunnybrook Health Science Centre","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Radiomics; Breast cancer; Thresholding; Parametric statistics; Multivariate statistics; Receiver operating characteristic; Ground truth; Pattern recognition (psychology); Multivariate analysis","score_opus":0.00881520133795241,"score_gpt":0.31426930289885774,"score_spread":0.30545410156090536,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416778686","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9774018,0.0040961765,0.014869383,0.001759727,0.00048820215,0.00037578872,0.00034056266,0.00002029046,0.0006480652],"genre_scores_gemma":[0.99576783,0.0023215609,0.0014291283,0.00017733534,0.000101962774,0.00003345985,0.000012437689,0.000008772924,0.00014752858],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990857,0.000042910313,0.00032000002,0.00019630141,0.00016556008,0.00018947915],"domain_scores_gemma":[0.99878085,0.0004902202,0.0002752173,0.00025058503,0.00014715406,0.000055976292],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00050523493,0.000097109245,0.00043604706,0.0003728437,0.00007031632,0.000008249845,0.0001592703,0.00004121845,0.000030084533],"category_scores_gemma":[0.0008433067,0.00006696094,0.00025942037,0.0018548963,0.00024360101,0.000027316999,0.000021613037,0.0002624481,8.07883e-8],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027780834,0.000023919398,0.8504554,0.0003088439,0.0034177136,0.0000012862664,0.00039584018,0.05972846,0.001087456,0.00026910027,0.0042530107,0.07978118],"study_design_scores_gemma":[0.0010686583,0.00006352498,0.48221627,0.00029868082,0.0065051364,0.0000044301482,0.0003539918,0.50695413,0.0015846264,0.00013534828,0.0007272293,0.000087940425],"about_ca_topic_score_codex":0.0038928317,"about_ca_topic_score_gemma":0.00004160617,"teacher_disagreement_score":0.4472257,"about_ca_system_score_codex":0.00036025257,"about_ca_system_score_gemma":0.00056937046,"threshold_uncertainty_score":0.5884823},"labels":[],"label_agreement":null},{"id":"W4416780730","doi":"10.1016/j.esmorw.2025.100514","title":"318P AI-driven dynamic prediction of prognosis in mNSCLC using CT scans and multimodal real-world data","year":2025,"lang":"en","type":"article","venue":"ESMO Real World Data and Digital Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Health Science Centre","funders":"","keywords":"Computed tomography; Medical imaging; Radiation therapy; Feature (linguistics)","score_opus":0.03792552906213953,"score_gpt":0.3827712362419128,"score_spread":0.34484570717977325,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416780730","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9807497,0.00013522794,0.0008607575,0.0043562856,0.00024480378,0.0004715128,0.001293516,0.000056762714,0.011831389],"genre_scores_gemma":[0.99260724,0.00055117265,0.0029209463,0.00026047943,0.000074700714,0.000006162457,0.0031210652,0.000018127026,0.00044009282],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9983472,0.00006892799,0.00049831864,0.0006365532,0.0001632088,0.00028576385],"domain_scores_gemma":[0.9986358,0.0003316603,0.00016503847,0.0006755762,0.000040082374,0.00015181013],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004331711,0.00017296089,0.0005903449,0.00050479686,0.00006989878,0.000060381542,0.00032538126,0.000044087134,0.0000061296364],"category_scores_gemma":[0.00038151417,0.00015428806,0.000022469458,0.0006323691,0.00058503455,0.00051765767,0.00094847707,0.0004482378,8.0042264e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020564086,0.0002461446,0.7846299,0.00012241559,0.00008429529,0.000121995276,0.00005097171,0.00003027893,0.00014442761,0.00033294858,0.0013386841,0.21269232],"study_design_scores_gemma":[0.0019388981,0.00018843292,0.53067833,0.00034679874,0.00017242544,0.000067456276,0.00009892817,0.44912535,0.0000073682572,0.00012443142,0.017143693,0.00010789269],"about_ca_topic_score_codex":0.0049149645,"about_ca_topic_score_gemma":0.009710628,"teacher_disagreement_score":0.44909507,"about_ca_system_score_codex":0.00013036664,"about_ca_system_score_gemma":0.00031904035,"threshold_uncertainty_score":0.74299884},"labels":[],"label_agreement":null},{"id":"W4416781138","doi":"10.1016/j.esmorw.2025.100601","title":"405P Optimizing prognostic models for early breast cancer (EBC) recurrence using real-world data (RWD) and machine learning (ML)","year":2025,"lang":"en","type":"article","venue":"ESMO Real World Data and Digital Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mount Sinai Hospital","funders":"","keywords":"Prognostic model; Risk assessment; Predictive modelling; Breast cancer; Cancer","score_opus":0.08166011315931654,"score_gpt":0.3898118497130605,"score_spread":0.30815173655374395,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416781138","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7970581,0.005622114,0.084590234,0.033283293,0.0019371882,0.0038526892,0.008656838,0.0006645381,0.064335026],"genre_scores_gemma":[0.9716856,0.0027918674,0.018143082,0.0007598529,0.00039604146,0.00003384345,0.0035317147,0.000059185717,0.0025987956],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997662,0.00007900293,0.0005013808,0.0010220698,0.00019974496,0.00053580885],"domain_scores_gemma":[0.9976242,0.00092606473,0.00024818146,0.00079890224,0.000096206626,0.00030643196],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00069641584,0.00029436633,0.0007512112,0.00035643906,0.00029954273,0.00025253763,0.0005048147,0.0000703925,0.000009565642],"category_scores_gemma":[0.0005146036,0.00025717268,0.00003924337,0.0005230072,0.00053199945,0.0009406756,0.0014306956,0.0007378385,0.0000011104655],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00080899044,0.00018331195,0.3912877,0.00028926946,0.00025772813,0.00010721134,0.00013299599,0.00045702182,0.00004965545,0.0020631081,0.0021162387,0.60224676],"study_design_scores_gemma":[0.0026331937,0.00031532889,0.058551632,0.0008428799,0.0005956253,0.00017953975,0.00009253316,0.8869141,0.0000037049965,0.0008619717,0.04864723,0.00036230343],"about_ca_topic_score_codex":0.0058585047,"about_ca_topic_score_gemma":0.0026038964,"teacher_disagreement_score":0.886457,"about_ca_system_score_codex":0.00012980684,"about_ca_system_score_gemma":0.0004306934,"threshold_uncertainty_score":0.9999881},"labels":[],"label_agreement":null},{"id":"W4416815050","doi":"10.1155/bmri/1246604","title":"Vocal Cord Dysfunction in Nonlaryngeal Head and Neck Cancer After Chemoradiation Therapy: Predictive Modeling Using CT Radiomics and Machine Learning","year":2025,"lang":"en","type":"article","venue":"BioMed Research International","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Université Laval; University of British Columbia Hospital","funders":"Iran University of Medical Sciences","keywords":"Radiomics; Head and neck cancer; Radiation therapy; Head and neck; Predictive value of tests; Cancer","score_opus":0.052955003111724276,"score_gpt":0.39399323325153096,"score_spread":0.34103823013980666,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416815050","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98268867,0.0028730894,0.008050916,0.0052087987,0.00050273567,0.0003204394,0.000011539434,0.000027150381,0.00031669054],"genre_scores_gemma":[0.9949676,0.0026166642,0.0012939752,0.00027998126,0.0003513989,0.000053308868,0.000063911146,0.000019266396,0.00035394228],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984781,0.0001316719,0.000256388,0.00035971156,0.00048695385,0.00028716287],"domain_scores_gemma":[0.9994327,0.00012116875,0.00004155866,0.00008620986,0.0001890723,0.00012930208],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009897469,0.00012555574,0.00020583624,0.0008314901,0.0001316113,0.00008530204,0.000078985744,0.00006927611,0.00004547006],"category_scores_gemma":[0.00042112137,0.0001127099,0.00003256632,0.00038337667,0.00018548884,0.00015526646,0.00011074827,0.0008769503,8.372771e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0046781707,0.00022512824,0.71302044,0.00015062682,0.00028116335,0.00013863716,0.00056146574,0.0049197404,0.0141309,0.00017105433,0.00019232208,0.26153034],"study_design_scores_gemma":[0.0032483996,0.00015105552,0.0719111,0.00033214755,0.00001237612,0.000047484835,0.000078757505,0.920858,0.00015964019,0.00018674223,0.0029341711,0.000080092716],"about_ca_topic_score_codex":0.0017943375,"about_ca_topic_score_gemma":0.00005328393,"teacher_disagreement_score":0.9159383,"about_ca_system_score_codex":0.0004308312,"about_ca_system_score_gemma":0.00020847553,"threshold_uncertainty_score":0.45961764},"labels":[],"label_agreement":null},{"id":"W4416830923","doi":"10.2196/80182","title":"Performance of ChatGPT-4o, Claude 3 Opus, and DeepSeek-R1 in BI-RADS Category 4 Classification and Malignancy Prediction From Mammography Reports: Retrospective Diagnostic Study","year":2025,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mammography; Retrospective cohort study; Malignancy; Screening mammography; MEDLINE; BI-RADS","score_opus":0.00649036711079671,"score_gpt":0.2758797265391429,"score_spread":0.2693893594283462,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416830923","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99587905,0.0006823005,0.00056662597,0.00064761227,0.00025302463,0.0009242522,0.0000072309663,0.000059697664,0.0009801928],"genre_scores_gemma":[0.99708486,0.0015589936,0.0006164889,0.00044020652,0.000073360796,0.00011969179,0.000062126164,0.000013338103,0.000030917316],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99760747,0.00006345594,0.0011635788,0.00023661503,0.0006847082,0.0002441822],"domain_scores_gemma":[0.9987105,0.0002672453,0.00033772635,0.00034261547,0.00010381207,0.00023806303],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009409804,0.00019453191,0.00051788683,0.00044299467,0.0000813976,0.000028937086,0.00010183739,0.00021887591,0.000025723708],"category_scores_gemma":[0.0014163841,0.00016271819,0.000045112116,0.00054408284,0.00034481537,0.0002379183,0.000107515036,0.00077041646,0.0000011119531],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000059639606,0.0003764319,0.96982265,0.00048189107,0.000074851414,0.000044426404,0.004283803,0.000003411705,0.000080296195,0.00014186322,0.00034485193,0.024285877],"study_design_scores_gemma":[0.0018623447,0.0004347891,0.9242726,0.0012820475,0.00011258949,0.000050447277,0.0028118172,0.06845665,0.000035864636,0.0002570254,0.0003112668,0.00011253366],"about_ca_topic_score_codex":0.00017215832,"about_ca_topic_score_gemma":0.000017296828,"teacher_disagreement_score":0.06845324,"about_ca_system_score_codex":0.0000841817,"about_ca_system_score_gemma":0.00016518345,"threshold_uncertainty_score":0.66354555},"labels":[],"label_agreement":null},{"id":"W4416903810","doi":"10.2196/78644","title":"Predictive Performance of Radiomics-Based Machine Learning for Colorectal Cancer Recurrence Risk: Systematic Review and Meta-Analysis","year":2025,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Colorectal cancer; Risk stratification; Radiomics; Predictive value; Predictive modelling; Prospective cohort study; Personalized medicine; Logistic regression","score_opus":0.015387820310240797,"score_gpt":0.33267114540255827,"score_spread":0.3172833250923175,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416903810","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4658564,0.24737437,0.24464327,0.01708971,0.00054323947,0.020920154,0.0006077429,0.0005339706,0.0024311403],"genre_scores_gemma":[0.95879585,0.021982465,0.008912667,0.0072877915,0.00004556127,0.0021235636,0.00023201267,0.000034921955,0.0005851512],"study_design_codex":"systematic_review","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99733704,0.00015723793,0.0013842284,0.00018246208,0.0006552946,0.00028370987],"domain_scores_gemma":[0.9975847,0.0008109076,0.0007816768,0.00026834814,0.0002838353,0.0002705137],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022237028,0.0002518777,0.0025199081,0.00034678075,0.0001393106,0.000020330941,0.00022902159,0.00015521608,0.00016392105],"category_scores_gemma":[0.0031186752,0.00016715385,0.00060767244,0.00085414905,0.00029534334,0.00010864016,0.00007229014,0.0008374729,0.0000013687404],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003621588,0.00026585304,0.024314174,0.870336,0.09718688,0.0000046803652,0.0015050389,0.0018559734,0.000010042667,0.00019498647,0.0017046765,0.002259513],"study_design_scores_gemma":[0.0009096673,0.00025617133,0.00048420925,0.0057164603,0.24783495,0.000010870909,0.00007041899,0.7443494,0.00006271773,0.000007958827,0.00017527712,0.00012186521],"about_ca_topic_score_codex":0.000042787753,"about_ca_topic_score_gemma":0.000006080018,"teacher_disagreement_score":0.86461955,"about_ca_system_score_codex":0.00007438286,"about_ca_system_score_gemma":0.0003598793,"threshold_uncertainty_score":0.68163365},"labels":[],"label_agreement":null},{"id":"W4416945183","doi":"10.1038/s41598-025-26365-7","title":"Foundation model based prediction of lung cancer survival using temporal changes in dual time point CT scans","year":2025,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia, Okanagan Campus; Kelowna General Hospital; University of British Columbia; Artificial Intelligence in Medicine (Canada)","funders":"National Cancer Institute; National Institutes of Health; National Instruments Corporation","keywords":"Feature (linguistics); Lung cancer; Time point; Radiation therapy; Computed tomography; Pattern recognition (psychology); Point (geometry); Survival analysis","score_opus":0.02363825058324953,"score_gpt":0.32875212623205474,"score_spread":0.3051138756488052,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416945183","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9782349,0.000084839005,0.015570182,0.0015005935,0.0032142391,0.00035060666,0.0000053103804,0.00004169384,0.000997627],"genre_scores_gemma":[0.9958421,0.0000031757356,0.0017156688,0.000084712694,0.000066120876,0.000013042534,0.0001302484,0.000011424728,0.0021335054],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984887,0.00004627698,0.00043199185,0.00040317955,0.00043431262,0.00019551099],"domain_scores_gemma":[0.999231,0.000025164267,0.00021417103,0.00031383178,0.00014761617,0.00006824188],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019522455,0.000097139186,0.00024856665,0.00043216575,0.00010589901,0.000048574813,0.00003312891,0.00003724079,0.00010104352],"category_scores_gemma":[0.00030353156,0.00008871357,0.00004951064,0.00061893597,0.00016723301,0.00009316702,0.000031837233,0.00018014107,4.541925e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007808871,0.00025840773,0.6443316,0.00046044783,0.00007094547,0.00043135724,0.00039557336,0.11354658,0.22547339,0.00006354417,0.0058261347,0.0090639265],"study_design_scores_gemma":[0.0004188317,0.000012301111,0.0072887065,0.00053879275,0.000068504756,0.000038461912,0.000022298607,0.9867916,0.003955562,0.00023900208,0.0005671441,0.00005877379],"about_ca_topic_score_codex":0.00068077276,"about_ca_topic_score_gemma":0.00010357587,"teacher_disagreement_score":0.87324506,"about_ca_system_score_codex":0.00020856822,"about_ca_system_score_gemma":0.00080996397,"threshold_uncertainty_score":0.36176345},"labels":[],"label_agreement":null},{"id":"W4416963203","doi":"10.1109/embc58623.2025.11251774","title":"CT Heterogeneity and Dose Distribution Patterns in Block and Ring Regions Improved the Prediction of Radiation Pneumonitis","year":2025,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"National Natural Science Foundation of China","keywords":"Dose-volume histogram; Radiomics; Histogram; Random forest; Voxel; Radiation therapy; Dosimetry; Block (permutation group theory); Lung cancer","score_opus":0.008130201671046429,"score_gpt":0.2685827765859175,"score_spread":0.26045257491487106,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416963203","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99092984,0.00025385528,0.004366957,0.0040165787,0.00006169669,0.00019850388,0.000012011499,0.000017863047,0.00014270897],"genre_scores_gemma":[0.99902654,0.00065841567,0.000040777915,0.00016080723,0.000024240315,0.000009105177,0.000028656397,0.0000032812306,0.00004818368],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9995337,0.000036736386,0.00016402344,0.00012167368,0.00006042595,0.0000834502],"domain_scores_gemma":[0.99974287,0.000067885936,0.000040736802,0.00009673318,0.000016520267,0.000035269895],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019679665,0.000054460117,0.000110593035,0.000049303093,0.000056133984,0.0000128166175,0.000021933916,0.000022979559,0.0000014195472],"category_scores_gemma":[0.00015603214,0.000038222108,0.000018723327,0.0000955532,0.000057530928,0.000037507933,0.0000296908,0.00015984746,6.311738e-8],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023592236,0.00003987033,0.89484686,0.00010357093,0.000028790986,0.0000053575995,0.000096208,0.000025357638,0.007164996,0.0004655414,0.00006223371,0.097137645],"study_design_scores_gemma":[0.0009670543,0.000041708772,0.8838155,0.000119141274,0.00004215665,0.000047487265,0.000072923256,0.1124291,0.0019422735,0.00007828029,0.0004180947,0.000026256768],"about_ca_topic_score_codex":0.0005059966,"about_ca_topic_score_gemma":0.000055864228,"teacher_disagreement_score":0.112403736,"about_ca_system_score_codex":0.000029892472,"about_ca_system_score_gemma":0.00001779261,"threshold_uncertainty_score":0.15586524},"labels":[],"label_agreement":null},{"id":"W4416963387","doi":"10.1109/embc58623.2025.11254089","title":"Structural Guidance in Stacked Generative Diffusion Model: Synthesizing Head and Neck CT from MRI in Radiotherapy Planning","year":2025,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Generative model; Probabilistic logic; Similarity (geometry); Diffusion MRI; Consistency (knowledge bases); Medical imaging; Fiducial marker; Image registration; Head and neck","score_opus":0.014322451705424979,"score_gpt":0.32342733665792855,"score_spread":0.3091048849525036,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416963387","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97022295,0.002563092,0.021490268,0.004522414,0.00008390772,0.00021090083,0.0000018887266,0.000037189195,0.00086740626],"genre_scores_gemma":[0.94837517,0.0002454283,0.048692424,0.002285433,0.000057729823,0.000008546332,0.000011105784,0.000016107439,0.00030803643],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989446,0.00006697189,0.00029555397,0.00032557594,0.00013738657,0.00022995188],"domain_scores_gemma":[0.9995593,0.00016020286,0.00004233897,0.00015123573,0.000014441639,0.0000724998],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020327223,0.00015166165,0.00036374936,0.00019437166,0.0000565879,0.00003357737,0.0000718103,0.00004642914,0.000027049853],"category_scores_gemma":[0.00013885414,0.00012022612,0.0000287391,0.00015614014,0.00006115866,0.00007951809,0.000040837345,0.00040364277,2.6887295e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025653242,0.00004947615,0.89862204,0.000060080645,0.000047792455,0.00014949116,0.0028406512,0.03092529,0.038102277,0.0012347215,0.0004994217,0.027212255],"study_design_scores_gemma":[0.0022006948,0.000024849023,0.18037644,0.00066369865,0.000007706848,0.000005084738,0.00014635653,0.81465983,0.00049551774,0.0010933306,0.0002284102,0.00009809477],"about_ca_topic_score_codex":0.001158757,"about_ca_topic_score_gemma":0.00008803578,"teacher_disagreement_score":0.7837345,"about_ca_system_score_codex":0.000121405894,"about_ca_system_score_gemma":0.0000649862,"threshold_uncertainty_score":0.49026787},"labels":[],"label_agreement":null},{"id":"W4417000301","doi":"10.1002/ird3.70046","title":"Artificial Intelligence in CT Imaging: A Systematic Review of Diagnostic Accuracy, Clinical Decision–Support Impact, and Integration Pathways","year":2025,"lang":"en","type":"article","venue":"iRadiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Workflow; Interpretability; Turnaround time; Diagnostic accuracy; MEDLINE; Systematic review; Medical imaging","score_opus":0.03226271468110218,"score_gpt":0.411535278014166,"score_spread":0.3792725633330638,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417000301","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.71609175,0.10119141,0.16613393,0.009441894,0.001469106,0.003832626,0.0000140621805,0.00010427803,0.0017209171],"genre_scores_gemma":[0.9804978,0.014524448,0.0020767276,0.0027615295,0.000054867014,0.000043881933,0.000019650472,0.000009567232,0.000011555234],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.99766564,0.0003417585,0.0013882363,0.0002839837,0.00012382069,0.00019653082],"domain_scores_gemma":[0.99251527,0.006726046,0.00025848794,0.00031096055,0.00008646515,0.00010276426],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0025376494,0.00014102159,0.0010502092,0.00022034724,0.000024228073,0.000011272479,0.0001333989,0.00004590395,0.000049061233],"category_scores_gemma":[0.068334125,0.00009785192,0.00012766436,0.00028218795,0.0002377642,0.00004681273,0.00006055958,0.00047572266,0.000009125674],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031218937,0.00066064124,0.14467084,0.14557356,0.00022004337,0.0009497915,0.00032193973,0.000020391957,0.0008322141,0.012258578,0.003565486,0.69061434],"study_design_scores_gemma":[0.0018232361,0.0025720014,0.13354367,0.69257784,0.0020090742,0.004326071,0.00051063154,0.11194409,0.00032192993,0.049162403,0.00051551807,0.0006935288],"about_ca_topic_score_codex":0.000043672255,"about_ca_topic_score_gemma":0.0000060081666,"teacher_disagreement_score":0.6899208,"about_ca_system_score_codex":0.000057281934,"about_ca_system_score_gemma":0.000225118,"threshold_uncertainty_score":0.9395137},"labels":[],"label_agreement":null},{"id":"W4417137807","doi":"10.1016/j.resuscitation.2025.110916","title":"Expanding qEEG feature analysis: A step towards better prognostication","year":2025,"lang":"en","type":"editorial","venue":"Resuscitation","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"SickKids Foundation; Hospital for Sick Children","funders":"","keywords":"Feature (linguistics); Pattern recognition (psychology); MEDLINE; Feature extraction","score_opus":0.00772614510684154,"score_gpt":0.3232688210635964,"score_spread":0.31554267595675484,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417137807","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018000389,0.0014656986,0.076011136,0.019515725,0.88666433,0.0014273578,0.00013718224,0.0003926312,0.012585882],"genre_scores_gemma":[0.009134222,0.0004466853,0.031548455,0.00081192056,0.9279729,0.0002131103,0.016282681,0.00009002163,0.013500014],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975187,0.00012996598,0.00040025965,0.0005815749,0.0010746638,0.00029481703],"domain_scores_gemma":[0.99800575,0.00066436495,0.00029105254,0.00041033945,0.0004863216,0.00014214432],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006536385,0.00027888964,0.0006341539,0.0008963615,0.00012988322,0.00013829333,0.00016289347,0.0006905621,0.00003086906],"category_scores_gemma":[0.006723199,0.00024486755,0.00030136606,0.0011383189,0.00006201137,0.00009186456,0.0000489287,0.0014545817,0.000015097435],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000095153475,0.000044076933,0.00052065344,0.0005475925,0.00097584625,0.000023965744,0.00020190135,0.00003566256,0.00010014414,0.000044611195,0.961419,0.03599138],"study_design_scores_gemma":[0.0012760762,0.00010171035,0.004986132,0.001191838,0.005778908,0.0000014301831,0.00007808433,0.011452097,0.000027781132,0.0001628597,0.9746515,0.00029158618],"about_ca_topic_score_codex":0.000097495904,"about_ca_topic_score_gemma":0.0000106119405,"teacher_disagreement_score":0.044462677,"about_ca_system_score_codex":0.00028088514,"about_ca_system_score_gemma":0.00053099386,"threshold_uncertainty_score":0.99854094},"labels":[],"label_agreement":null},{"id":"W4417294489","doi":"10.1016/j.ultrasmedbio.2025.11.151","title":"QUANTITATIVE ULTRASOUND RADIOMICS GUIDED ADAPTIVE NEOADJUVANT CHEMOTHERAPY IN BREAST CANCER: A RANDOMIZED STUDY","year":2025,"lang":"en","type":"article","venue":"Ultrasound in Medicine & Biology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University; York University; University of Toronto; Sunnybrook Health Science Centre","funders":"","keywords":"Chemotherapy; Radiomics; Breast cancer; Randomized controlled trial; Anthracycline; Ultrasound; Clinical trial","score_opus":0.0182548004355375,"score_gpt":0.36507913817694126,"score_spread":0.34682433774140375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417294489","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9590896,0.0043164175,0.0043028197,0.023633376,0.0010702638,0.0027849183,0.000019909841,0.000080857826,0.0047018407],"genre_scores_gemma":[0.984218,0.0058131237,0.0017861035,0.0071197175,0.00028526547,0.00029331018,0.0000740587,0.000044606066,0.0003658289],"study_design_codex":"observational","study_design_gemma":"randomized_trial","domain_scores_codex":[0.9956826,0.0010488392,0.0014182535,0.0008517336,0.0002869699,0.0007115885],"domain_scores_gemma":[0.9932322,0.0056195543,0.00029868458,0.00047695724,0.00018602014,0.00018657498],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0036756287,0.0004894974,0.0025145544,0.0010206861,0.0000921102,0.000016667336,0.00034616797,0.00023081762,0.00037847244],"category_scores_gemma":[0.0056835585,0.00034934474,0.00017432086,0.001269908,0.0014078631,0.00007692572,0.00004372884,0.0013730491,0.000006946185],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.075156875,0.0019989247,0.81870097,0.00013911315,0.0012178654,0.00025422478,0.0122284405,0.00028495214,0.042105302,0.011817356,0.0070700464,0.029025936],"study_design_scores_gemma":[0.6014298,0.002499015,0.34991062,0.0024414158,0.00074537826,0.0007018758,0.011527931,0.01175037,0.00016691221,0.012680893,0.0052408315,0.0009049705],"about_ca_topic_score_codex":0.007909618,"about_ca_topic_score_gemma":0.00044077105,"teacher_disagreement_score":0.5262729,"about_ca_system_score_codex":0.0004651905,"about_ca_system_score_gemma":0.00041638454,"threshold_uncertainty_score":0.9998959},"labels":[],"label_agreement":null},{"id":"W4417465895","doi":"10.2196/72424","title":"A Machine Learning Approach to Predicting Mortality Risk in Chemotherapy-Treated Lung Cancer: Machine Learning Model Development and Validation","year":2025,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Risk assessment; Predictive modelling; Model risk; Risk model; Lung disease","score_opus":0.01275479045094815,"score_gpt":0.31636441651505237,"score_spread":0.30360962606410424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417465895","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9095147,0.00044553127,0.08287402,0.00086658326,0.00006415358,0.0008332736,0.000004985725,0.0002157014,0.0051810164],"genre_scores_gemma":[0.9676955,0.0008944839,0.0281059,0.0020260925,0.00007221536,0.00023596291,0.00022773114,0.00004099875,0.0007011218],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971873,0.00012394854,0.0010702153,0.00028466652,0.0008442725,0.00048957136],"domain_scores_gemma":[0.9988253,0.00013801751,0.00027174246,0.00020362718,0.0000859822,0.00047530304],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001884883,0.0003076833,0.00059872447,0.0004257785,0.00027119086,0.000071855524,0.00018498048,0.00024639248,0.000039917162],"category_scores_gemma":[0.0011355955,0.00025859653,0.00006290191,0.00065758644,0.00009899705,0.00017285433,0.00019381968,0.0021340812,0.000002657698],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010612753,0.00019464696,0.84155124,0.0010042158,0.00019173262,0.000008317374,0.011631792,0.031675115,0.00003042409,0.00012490427,0.00015958384,0.11332189],"study_design_scores_gemma":[0.0027133403,0.00004780627,0.021856194,0.00086571404,0.00008975388,0.000017021255,0.0004319544,0.9705208,0.00012944602,0.000025353502,0.003084504,0.00021811076],"about_ca_topic_score_codex":0.000517178,"about_ca_topic_score_gemma":0.000029195708,"teacher_disagreement_score":0.9388457,"about_ca_system_score_codex":0.00027421853,"about_ca_system_score_gemma":0.0003948524,"threshold_uncertainty_score":0.99998665},"labels":[],"label_agreement":null},{"id":"W4417470337","doi":"10.1109/nss/mic/rtsd57106.2025.11287292","title":"RADIUMA: A Shareable Executable Workflow Generator for Medical Image Analysis","year":2025,"lang":"","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Teck (Canada)","funders":"","keywords":"Executable; Workflow; Preprocessor; DICOM; Image processing; Graphical user interface; Scripting language; Generator (circuit theory); Image segmentation","score_opus":0.007553560678817632,"score_gpt":0.3132109866954959,"score_spread":0.3056574260166783,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417470337","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006748476,0.010780854,0.878263,0.04869134,0.0026411286,0.0015545135,0.00007056486,0.0002604306,0.050989687],"genre_scores_gemma":[0.3463774,0.004998342,0.21903288,0.048345376,0.0056277104,0.00078818883,0.001060971,0.00028999173,0.37347913],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9941961,0.00020522633,0.0014947759,0.0013795216,0.0011952617,0.0015291269],"domain_scores_gemma":[0.99573237,0.0011382275,0.00023330882,0.0010997583,0.00047212624,0.0013242125],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0030273239,0.0006525937,0.0019909341,0.001250872,0.0006103101,0.0003977813,0.0007867883,0.000621476,0.020598572],"category_scores_gemma":[0.00605578,0.00056114304,0.0012428183,0.0038856203,0.00046654337,0.0002228199,0.0003232639,0.0013306866,0.00011869443],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00085592415,0.0016450966,0.0276619,0.0019548284,0.01940279,0.0004648623,0.00036021258,0.0010149657,0.0033120606,0.013733926,0.7562283,0.17336513],"study_design_scores_gemma":[0.0053601237,0.00016216871,0.00084023544,0.00067205675,0.009252905,0.00001875842,0.00016631008,0.7857013,0.00093731587,0.00072782673,0.1956926,0.0004684272],"about_ca_topic_score_codex":0.00049454335,"about_ca_topic_score_gemma":0.000047775964,"teacher_disagreement_score":0.7846863,"about_ca_system_score_codex":0.00033347422,"about_ca_system_score_gemma":0.0018849146,"threshold_uncertainty_score":0.999684},"labels":[],"label_agreement":null},{"id":"W4417470437","doi":"10.1109/nss/mic/rtsd57106.2025.11286591","title":"Radiological and Biological Dictionary of Radiomics Features: Addressing Understandable AI Issues in Personalized Breast Cancer; Dictionary Version BM1.0","year":2025,"lang":"","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Radiomics; Pattern recognition (psychology); Feature selection; Gray (unit); Correlation; Gray level; Entropy (arrow of time); Decision tree","score_opus":0.02079701608576301,"score_gpt":0.3363373890492375,"score_spread":0.3155403729634745,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417470437","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7291338,0.15289022,0.0066451007,0.10061068,0.0024919491,0.0012217851,0.00026760105,0.00019329939,0.0065455986],"genre_scores_gemma":[0.9232452,0.06788217,0.0015227199,0.0034213066,0.0004560172,0.00002313195,0.000114936745,0.000029889072,0.0033046245],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99650294,0.00051341404,0.0009086035,0.000927279,0.00047653896,0.0006712412],"domain_scores_gemma":[0.99820006,0.00079353334,0.00022613304,0.00030061862,0.00016233063,0.00031731167],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0011015502,0.00049174693,0.0012923357,0.00060942303,0.00040890303,0.000067782494,0.00025178166,0.0006749778,0.0014072433],"category_scores_gemma":[0.0005281275,0.00037756588,0.00023760386,0.0008411968,0.0018956985,0.00021867745,0.00027109418,0.0016839321,0.0000029077414],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.009330844,0.0015556869,0.84920466,0.0015184426,0.0010827893,0.00039994475,0.002378273,0.0012961534,0.011159033,0.018060977,0.050831098,0.053182088],"study_design_scores_gemma":[0.02040922,0.0009010523,0.75501865,0.008790332,0.0007612901,0.0012328723,0.011864264,0.16641411,0.00027279995,0.004509889,0.028818956,0.0010065455],"about_ca_topic_score_codex":0.001351118,"about_ca_topic_score_gemma":0.000014200626,"teacher_disagreement_score":0.19411144,"about_ca_system_score_codex":0.000631268,"about_ca_system_score_gemma":0.0005715156,"threshold_uncertainty_score":0.9998676},"labels":[],"label_agreement":null},{"id":"W4417470816","doi":"10.1109/nss/mic/rtsd57106.2025.11287912","title":"Dual Representation Learning in CNNs: Generalised Glycolytic Patterns and Organ-specific Activations","year":2025,"lang":"","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Discriminative model; Pattern recognition (psychology); Convolutional neural network; Representation (politics); Feature (linguistics); Deep learning; Glycolysis","score_opus":0.016652696869040983,"score_gpt":0.3133475990511696,"score_spread":0.29669490218212863,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417470816","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9392185,0.0011426731,0.029549,0.020109972,0.0007876403,0.00067685836,0.0000025943289,0.00010503138,0.008407701],"genre_scores_gemma":[0.9770064,0.0035186666,0.0010525142,0.001592595,0.00038236112,0.000031706273,0.00007060945,0.00003979381,0.016305348],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9972761,0.00031452338,0.00078597496,0.0007453461,0.0003650225,0.0005130218],"domain_scores_gemma":[0.99857366,0.0005876374,0.00016525206,0.00035397627,0.000110451314,0.00020899698],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00066256133,0.00030435852,0.0005448296,0.00071075873,0.00029193383,0.00019818869,0.00011395344,0.00019630812,0.001044596],"category_scores_gemma":[0.0012390933,0.0002993424,0.00007990998,0.0010345345,0.00014566057,0.0002438814,0.00015801273,0.0014214249,0.00002177734],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022895665,0.00034963374,0.800807,0.0003700147,0.00021062171,0.00022158632,0.0032002935,0.0022323828,0.026108706,0.006179624,0.00418095,0.15591024],"study_design_scores_gemma":[0.008530962,0.00020101255,0.7534519,0.0016826415,0.00021153592,0.000059952763,0.0053031445,0.20999078,0.0026605746,0.00056098227,0.016854433,0.00049210584],"about_ca_topic_score_codex":0.0009849614,"about_ca_topic_score_gemma":0.00005260803,"teacher_disagreement_score":0.2077584,"about_ca_system_score_codex":0.00023547096,"about_ca_system_score_gemma":0.00023869419,"threshold_uncertainty_score":0.9999459},"labels":[],"label_agreement":null},{"id":"W4417470962","doi":"10.1109/nss/mic/rtsd57106.2025.11287502","title":"Advanced Prediction of Glioblastoma IDH Mutation Using Semi-Supervised Pseudolabeling and Combined MRI Sequences Across Multiple Centers","year":2025,"lang":"","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Teck (Canada)","funders":"","keywords":"Isocitrate dehydrogenase; Glioblastoma; Mutation; Magnetic resonance imaging; IDH1; Biomarker","score_opus":0.011300171049580159,"score_gpt":0.3030021740332421,"score_spread":0.29170200298366195,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417470962","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9182697,0.0016515884,0.075895496,0.001378455,0.0015560226,0.000820838,0.00003926139,0.00010825928,0.000280362],"genre_scores_gemma":[0.9871121,0.00090775784,0.010912469,0.0005486818,0.00011652842,0.000011752522,0.00004414475,0.000039923216,0.00030662384],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967506,0.00019737004,0.0011830681,0.0007162265,0.0005101712,0.0006425944],"domain_scores_gemma":[0.9981536,0.0004928428,0.00038508215,0.0003472538,0.0003498175,0.00027135274],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00096059404,0.00040441015,0.00079161336,0.00031751383,0.00045745855,0.0001013562,0.00018337255,0.00023976625,0.000060784816],"category_scores_gemma":[0.0012815159,0.0003872003,0.00014801633,0.0007698384,0.00057980133,0.00042250266,0.00016889481,0.0006741648,0.0000017645729],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002526606,0.00050289906,0.26288232,0.002644222,0.00073973206,0.00007710339,0.0065417225,0.034200896,0.6116916,0.00024133691,0.00015712169,0.077794425],"study_design_scores_gemma":[0.010546728,0.0006754525,0.009652651,0.0035604136,0.0003737215,0.0000563255,0.006377703,0.9471968,0.021074427,0.00012548905,0.00012811758,0.0002321835],"about_ca_topic_score_codex":0.0004965229,"about_ca_topic_score_gemma":0.000031042022,"teacher_disagreement_score":0.9129959,"about_ca_system_score_codex":0.00021089833,"about_ca_system_score_gemma":0.0002488001,"threshold_uncertainty_score":0.99985796},"labels":[],"label_agreement":null},{"id":"W4417472315","doi":"10.1109/nss/mic/rtsd57106.2025.11286706","title":"Semi-Supervised Learning for Improved Radiomics-Based Outcome Prediction from Lymphoma [${ }^{18}\\mathrm{F}]\\text{FDG}$ PET Images","year":2025,"lang":"","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Teck (Canada)","funders":"","keywords":"Feature selection; Radiomics; Pattern recognition (psychology); Logistic regression; Feature extraction; Feature (linguistics); Lymphoma; Dimensionality reduction","score_opus":0.012900573753866336,"score_gpt":0.29856779882528484,"score_spread":0.2856672250714185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417472315","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21260916,0.005732371,0.72461975,0.029025517,0.009085366,0.0047575384,0.00055073027,0.0014005665,0.012219023],"genre_scores_gemma":[0.9132565,0.00096710824,0.03880911,0.010987507,0.0023639768,0.00036560927,0.0017992177,0.00035577553,0.031095175],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99215657,0.00050322386,0.0026664576,0.0021329261,0.00073661475,0.001804226],"domain_scores_gemma":[0.9936958,0.0028445716,0.00065149623,0.0013281928,0.0005883367,0.00089162425],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.0023938024,0.0013352915,0.0023734453,0.0009607715,0.0011625893,0.0005661322,0.0008620272,0.0006350527,0.0022461817],"category_scores_gemma":[0.005692011,0.0012553957,0.0012424835,0.00096073875,0.00061843003,0.00043197357,0.00029297758,0.0018200466,0.00009395331],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0068534543,0.0026027719,0.15626556,0.0038225525,0.003645141,0.0002545473,0.0009815728,0.0069235004,0.1654985,0.00094410876,0.06268668,0.58952165],"study_design_scores_gemma":[0.026622558,0.0009213276,0.017230047,0.0012752512,0.0021534886,0.00003131042,0.00084373466,0.88939536,0.003847531,0.00052166765,0.05626068,0.0008970735],"about_ca_topic_score_codex":0.0011062957,"about_ca_topic_score_gemma":0.000017122531,"teacher_disagreement_score":0.88247186,"about_ca_system_score_codex":0.0010551853,"about_ca_system_score_gemma":0.0014539609,"threshold_uncertainty_score":0.9999398},"labels":[],"label_agreement":null},{"id":"W4417472698","doi":"10.1109/nss/mic/rtsd57106.2025.11287351","title":"Multi-Center Semi-Supervised Prediction of Lung Cancer Survival Outcomes Via Pseudolabeling of CT Images","year":2025,"lang":"","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Teck (Canada)","funders":"","keywords":"Lung cancer; Feature selection; Logistic regression; Feature extraction; Pattern recognition (psychology); Feature (linguistics); Dimensionality reduction; Data set","score_opus":0.018536185083279172,"score_gpt":0.3364256894333033,"score_spread":0.31788950435002417,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417472698","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7992572,0.009279953,0.17074367,0.007378979,0.0076323412,0.0012944054,0.00024381178,0.00014175907,0.004027863],"genre_scores_gemma":[0.98449355,0.002956558,0.005418593,0.000789918,0.0002100592,0.00002474171,0.000045384993,0.00005657999,0.006004601],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99615633,0.0002565319,0.0016574967,0.0006306044,0.0007050769,0.0005939709],"domain_scores_gemma":[0.9977671,0.0004686883,0.00043338526,0.0006061946,0.00048726576,0.00023737276],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012128723,0.000462317,0.001478807,0.0004750582,0.00013395016,0.000028193082,0.0003511481,0.00015491851,0.0009695558],"category_scores_gemma":[0.0010099765,0.00038172636,0.00043965236,0.00058621523,0.00038705746,0.00018240752,0.00023300937,0.0009149594,0.000003334108],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013814287,0.0010964557,0.90480065,0.00274401,0.0013796339,0.000014856055,0.00041393624,0.00047802486,0.069085754,0.00005132542,0.0017190406,0.01807816],"study_design_scores_gemma":[0.013492624,0.00010473606,0.24246101,0.0033725202,0.001334716,0.000007729205,0.00042552236,0.72695017,0.011141589,0.0000139681515,0.00045145358,0.00024394797],"about_ca_topic_score_codex":0.0028613098,"about_ca_topic_score_gemma":0.000027486123,"teacher_disagreement_score":0.72647214,"about_ca_system_score_codex":0.0001816477,"about_ca_system_score_gemma":0.0003957753,"threshold_uncertainty_score":0.9999437},"labels":[],"label_agreement":null},{"id":"W4417472771","doi":"10.1109/nss/mic/rtsd57106.2025.11287878","title":"Optimization of Gross Tumor Volume Dilation for Improved Radiomic Prediction of HPV Status in Head and Neck Cancer","year":2025,"lang":"","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Douglas Mental Health University Institute","funders":"Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung","keywords":"Head and neck cancer; Dilation (metric space); Feature (linguistics); Feature selection; Redundancy (engineering); Resampling; Support vector machine; Clinical Practice","score_opus":0.00828985533631035,"score_gpt":0.2938679914543984,"score_spread":0.2855781361180881,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417472771","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5564852,0.0035471185,0.43405506,0.002131058,0.0010442621,0.0018204651,0.00015981036,0.000026748694,0.0007302971],"genre_scores_gemma":[0.97959936,0.0027013645,0.015713405,0.0002936623,0.00013960789,0.00007438564,0.00012963655,0.000029488216,0.0013190833],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979555,0.000070392125,0.001042634,0.00039741804,0.00016807871,0.0003659881],"domain_scores_gemma":[0.99884665,0.00016954764,0.0003996084,0.00020753042,0.00025112243,0.00012554949],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00061065116,0.000206111,0.00066571106,0.00043152168,0.00006708349,0.00002063907,0.000073527684,0.00013793386,0.0002058614],"category_scores_gemma":[0.00080211693,0.00020012581,0.00008794007,0.00049756037,0.00022624066,0.00017976062,0.00004664321,0.0002856352,1.281204e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0023705675,0.0005300293,0.61478794,0.004401722,0.0003111973,0.0000014188395,0.0012915162,0.16451904,0.029198784,0.0011039334,0.0009423492,0.1805415],"study_design_scores_gemma":[0.0072085597,0.00038737006,0.2081112,0.0006970169,0.00021887022,0.0000014874256,0.0001443141,0.78129876,0.0011728622,0.00009554651,0.0005734851,0.00009050774],"about_ca_topic_score_codex":0.0030365724,"about_ca_topic_score_gemma":0.0000919533,"teacher_disagreement_score":0.61677974,"about_ca_system_score_codex":0.0002387446,"about_ca_system_score_gemma":0.00045277443,"threshold_uncertainty_score":0.81608933},"labels":[],"label_agreement":null},{"id":"W4417473093","doi":"10.1109/sipaim67325.2025.11283389","title":"Multimodal Radiomic Profiling Can Distinguish AT1- and AT2- Cell of Origin Lung Adenocarcinoma Models","year":2025,"lang":"","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"National Cancer Institute","keywords":"Adenocarcinoma; Cell; Cell of origin; Lung; Radiomics; Cell type; Phenotype; Precision medicine; Transcriptome","score_opus":0.010614040268008943,"score_gpt":0.2850144647262009,"score_spread":0.27440042445819196,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417473093","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8958502,0.027112585,0.03550915,0.0023677119,0.0014111992,0.0012858167,0.000032564843,0.00011384481,0.036316928],"genre_scores_gemma":[0.97271776,0.0014648088,0.014291205,0.0005797589,0.00039727974,0.000020261094,0.000030163663,0.000072829374,0.010425922],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99619496,0.00019623264,0.0012100086,0.0010003024,0.0005091339,0.0008893658],"domain_scores_gemma":[0.9978114,0.00043292332,0.00035807214,0.0006486418,0.00023284189,0.00051612884],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000903039,0.00056907424,0.0012333574,0.00047598672,0.00028040574,0.00009112421,0.00035887255,0.00029642074,0.00020183995],"category_scores_gemma":[0.0007863766,0.0005248324,0.0002335113,0.0005835051,0.00059055403,0.00012000268,0.00030942218,0.0013096526,0.000003589003],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004887186,0.0009773858,0.8632599,0.011366256,0.0009881817,0.00035749373,0.005300653,0.0059491172,0.040760726,0.016134268,0.004444365,0.049972925],"study_design_scores_gemma":[0.0050050896,0.00015170673,0.010813892,0.0013133184,0.00088033284,0.00004112531,0.0006610471,0.97543865,0.0045459215,0.00037989972,0.0003350121,0.00043400488],"about_ca_topic_score_codex":0.0030797068,"about_ca_topic_score_gemma":0.000013645772,"teacher_disagreement_score":0.9694895,"about_ca_system_score_codex":0.00026826188,"about_ca_system_score_gemma":0.0005136142,"threshold_uncertainty_score":0.99972034},"labels":[],"label_agreement":null},{"id":"W4417476627","doi":"10.1016/j.radonc.2025.111350","title":"The Actual Performance of ML/AI Models in Predicting Radiation-Induced Toxicity in Head and Neck Cancer: A Systematic Review and Meta-Analysis.","year":2025,"lang":"en","type":"review","venue":"Radiotherapy and Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre","funders":"Rijksuniversiteit Groningen","keywords":"Comparability; Reliability (semiconductor); Receiver operating characteristic; Predictive modelling; Head and neck; Systematic review; Meta-analysis; Head and neck cancer","score_opus":0.04526372028538901,"score_gpt":0.4009531191821383,"score_spread":0.3556893988967493,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417476627","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020834808,0.99367076,0.000061345476,0.002123863,0.00003897564,0.0019514523,0.000009643129,0.000008493803,0.00005197906],"genre_scores_gemma":[0.000993854,0.99663144,0.00021479087,0.0016194029,0.000032294352,0.0003742689,0.000008445883,0.00001643381,0.000109080465],"study_design_codex":"systematic_review","study_design_gemma":"meta_analysis","domain_scores_codex":[0.997399,0.0007047573,0.0011405327,0.0003719563,0.00014925432,0.00023454451],"domain_scores_gemma":[0.9977192,0.0013490869,0.0005408556,0.0002674614,0.000035098765,0.000088288376],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020197402,0.00028913422,0.0062580165,0.00034941043,0.000080061356,0.000019144729,0.00012317157,0.00024013841,0.000011537733],"category_scores_gemma":[0.00033198428,0.00016541131,0.000327135,0.0006063958,0.0001235495,0.00006550512,0.000034952453,0.00074548664,4.7701562e-8],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038997063,0.0000735601,0.00067013566,0.69380176,0.024261635,0.000013307291,0.00058832683,0.0000677225,8.337848e-7,0.00013054383,0.00003711093,0.28031603],"study_design_scores_gemma":[0.0036193165,0.001234756,0.0005310652,0.16778672,0.688749,0.00035204622,0.00007400745,0.09862159,7.123392e-7,0.000062921536,0.038294863,0.000672973],"about_ca_topic_score_codex":0.00023153893,"about_ca_topic_score_gemma":0.00026221143,"teacher_disagreement_score":0.6644874,"about_ca_system_score_codex":0.00027038762,"about_ca_system_score_gemma":0.00044654263,"threshold_uncertainty_score":0.67452776},"labels":[],"label_agreement":null},{"id":"W574622532","doi":"10.1007/978-3-319-13692-9_7","title":"Metastatic Liver Tumor Segmentation Using Texture-Based Omni-Directional Deformable Surface Models","year":2014,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":33,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Artificial intelligence; Computer science; Voxel; Segmentation; Pattern recognition (psychology); Image segmentation; Support vector machine; Computer vision","score_opus":0.024964991671873275,"score_gpt":0.2812976091360035,"score_spread":0.2563326174641302,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W574622532","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003888608,0.00041499414,0.99306947,0.00037097183,0.0007177699,0.000385708,0.000004229104,0.00007377746,0.0010744717],"genre_scores_gemma":[0.2874077,0.000018650533,0.706868,0.0046682484,0.00043983755,0.0000034507464,0.00003635477,0.0000614379,0.0004963674],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975027,0.000039441467,0.00039942964,0.0007048026,0.0009275404,0.00042610322],"domain_scores_gemma":[0.9986788,0.00030730583,0.00024794132,0.00037186526,0.00019567324,0.00019840585],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00092823576,0.0003595532,0.000523846,0.00041367838,0.00022251501,0.00013046092,0.00030490628,0.00010882016,0.00008905726],"category_scores_gemma":[0.00011197261,0.00030043343,0.00012875842,0.00024290849,0.0004823484,0.0001818402,0.000112656824,0.0009224814,0.0000143916395],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024732484,0.000021560043,0.000105131076,0.00013841738,0.000020592262,0.000081039434,0.00013608288,0.9231304,0.0011306243,0.0003060463,0.000018461837,0.074886896],"study_design_scores_gemma":[0.0006706848,0.0001129282,0.000033778004,0.0006581118,0.000081435086,0.00028054154,2.8924197e-7,0.989957,0.0010476379,0.006474148,0.0003870586,0.0002964152],"about_ca_topic_score_codex":0.00013086604,"about_ca_topic_score_gemma":0.00001090035,"teacher_disagreement_score":0.2862015,"about_ca_system_score_codex":0.00044430012,"about_ca_system_score_gemma":0.0006659424,"threshold_uncertainty_score":0.9999448},"labels":[],"label_agreement":null},{"id":"W608785522","doi":"","title":"Tikhonov regularized gamma variate fits to radiochelated-DTPA bolus dilution curves with minimum plasma-clearance relative error","year":2010,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"SickKids Foundation; Hospital for Sick Children; University of Toronto; Memorial University of Newfoundland","funders":"","keywords":"Tikhonov regularization; Bolus (digestion); Mathematics; Exponential function; Nuclear medicine; Dilution; Statistics; Chemistry; Physics; Mathematical analysis; Thermodynamics; Medicine","score_opus":0.007801952875587653,"score_gpt":0.2673291266842326,"score_spread":0.25952717380864493,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W608785522","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92204994,0.00017543309,0.020266099,0.037001174,0.0006785518,0.00097339257,0.000005745686,0.00033916038,0.018510489],"genre_scores_gemma":[0.9172308,0.000059346043,0.05498447,0.004442396,0.00031321374,0.000042854103,0.00004860156,0.0000782291,0.022800116],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9980462,0.0000804115,0.00038150567,0.00054534123,0.00046634872,0.00048016358],"domain_scores_gemma":[0.99852115,0.00014459086,0.00014208921,0.0004943018,0.00021199655,0.0004858762],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00063089596,0.0002826129,0.00049729337,0.00015679782,0.0001599185,0.000038366925,0.0001793809,0.00018415933,0.00044158974],"category_scores_gemma":[0.0011727395,0.00020727064,0.000086731496,0.00051114196,0.00018635423,0.00018666807,0.00005949063,0.0012597251,0.00019424965],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0112642655,0.0014667886,0.023704452,0.0014068177,0.0019141977,0.0011960713,0.0058075567,0.00095907954,0.7380452,0.02719615,0.118374154,0.068665236],"study_design_scores_gemma":[0.035176273,0.003907612,0.39161652,0.00682034,0.0017282397,0.0032614002,0.0003691059,0.3431459,0.022911116,0.0016000947,0.18648423,0.0029791493],"about_ca_topic_score_codex":0.00013273393,"about_ca_topic_score_gemma":0.000026023035,"teacher_disagreement_score":0.7151341,"about_ca_system_score_codex":0.000055979683,"about_ca_system_score_gemma":0.000175855,"threshold_uncertainty_score":0.84522516},"labels":[],"label_agreement":null},{"id":"W623581242","doi":"","title":"Localisation du ganglion sentinelle au moyen de nanoparticules fluorescentes émettant dans le proche infrarouge : Application au cancer du sein","year":2012,"lang":"fr","type":"preprint","venue":"Publications Et Travaux Academiques de Lorraine (Universite de Lorraine)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre d'expertise et de recherche en infrastructures urbaines","funders":"","keywords":"Molecular biology; Chemistry; Physics; Biology","score_opus":0.016733298490313287,"score_gpt":0.27940108460075563,"score_spread":0.26266778611044234,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W623581242","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25346637,0.0017984462,0.58871526,0.14528604,0.0003572155,0.0016830212,0.00017438232,0.00057079527,0.007948501],"genre_scores_gemma":[0.95600593,0.0040933737,0.020902675,0.0039942325,0.0040388294,0.00073844264,0.0033222192,0.0002489164,0.0066553643],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9931452,0.00133098,0.0011579011,0.0013826385,0.0007839878,0.0021992659],"domain_scores_gemma":[0.9947372,0.00064129767,0.0010889649,0.0010844853,0.0008373034,0.0016107699],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.0053253057,0.0009886642,0.0010201677,0.00097336626,0.0010676994,0.00025870174,0.0013433777,0.0015233342,0.00029490798],"category_scores_gemma":[0.0023046094,0.001129078,0.00048690473,0.0015322947,0.0010013499,0.0012794397,0.0007147037,0.0037988643,0.00007728499],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003328213,0.0021644707,0.31703043,0.0023913814,0.0012727276,0.00009812881,0.13064839,0.028801376,0.097005494,0.35851958,0.020502666,0.041232534],"study_design_scores_gemma":[0.0021882085,0.00008256536,0.18224066,0.0009638683,0.0012888876,0.00048601633,0.005942828,0.6101097,0.0030152453,0.0017301748,0.19083081,0.0011210594],"about_ca_topic_score_codex":0.013366603,"about_ca_topic_score_gemma":0.0005505793,"teacher_disagreement_score":0.70253956,"about_ca_system_score_codex":0.006876412,"about_ca_system_score_gemma":0.004696606,"threshold_uncertainty_score":0.9997729},"labels":[],"label_agreement":null},{"id":"W632029899","doi":"10.71781/3321","title":"Imagerie multimodale (radiographie numérique, tomodensitométrie, résonance magnétique à 1,5 Tesla) pour l'évaluation des lésions d'ostéoarthrose","year":2007,"lang":"en","type":"dissertation","venue":"Papyrus : Institutional Repository (Université de Montréal)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Nuclear medicine; Medicine; Physics","score_opus":0.0071469863154847305,"score_gpt":0.2369027210360738,"score_spread":0.22975573472058905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W632029899","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92495966,0.017030073,0.0039423183,0.0006870309,0.0010439906,0.00079856446,0.000043135868,0.00030560518,0.05118962],"genre_scores_gemma":[0.8454267,0.0042906324,0.02313491,0.00053697877,0.0007547671,0.000059496095,0.0018083777,0.00014656183,0.12384161],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99678165,0.00013767436,0.0005865511,0.00081721053,0.001020085,0.00065681053],"domain_scores_gemma":[0.99752676,0.00020253283,0.0004402004,0.00053034205,0.00067974004,0.00062039244],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.00054325897,0.0005713978,0.0006770044,0.00082035596,0.004123128,0.000069092894,0.00029054153,0.0006383874,0.00008903604],"category_scores_gemma":[0.000462081,0.0006193397,0.0005297734,0.0006880422,0.0004801629,0.00030768654,0.000083820414,0.0012348113,0.00005066317],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008939558,0.0027051806,0.17543635,0.0024498382,0.002262704,0.043015406,0.080062896,0.005329584,0.36013648,0.009280967,0.02571195,0.2846691],"study_design_scores_gemma":[0.011065662,0.0007532811,0.74822056,0.004536198,0.0018949675,0.010833628,0.03492636,0.04705512,0.050291263,0.0035737639,0.08394366,0.0029055302],"about_ca_topic_score_codex":0.008149465,"about_ca_topic_score_gemma":0.0019911595,"teacher_disagreement_score":0.57278425,"about_ca_system_score_codex":0.0028570094,"about_ca_system_score_gemma":0.0021746473,"threshold_uncertainty_score":0.9996258},"labels":[],"label_agreement":null},{"id":"W6726021","doi":"10.1200/jco.2009.27.15_suppl.7571","title":"Comparison of primary tumor maximal standardized uptake value (SUV<sub>max</sub>) on preoperative [18F]fluorodeoxyglucose positron emission tomography/computed tomography (PET/CT) and histological subtype in patients with non-small cell lung cancer (NSCLC)","year":2009,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University Health Centre","funders":"","keywords":"Medicine; Standardized uptake value; Histology; Positron emission tomography; Nuclear medicine; Pathological; Carcinoma; Adenocarcinoma; Fluorodeoxyglucose; Radiology; Cancer; Pathology; Internal medicine","score_opus":0.019999461109965175,"score_gpt":0.3577746419173138,"score_spread":0.3377751808073486,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6726021","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99446386,0.001636511,0.0005894117,0.0015899107,0.00044680212,0.0006165782,0.000007653446,0.000017197926,0.0006320478],"genre_scores_gemma":[0.98721915,0.00026103138,0.010304865,0.0019530763,0.00020908721,0.0000047013095,0.00001358859,0.000026008933,0.000008459703],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9953025,0.00066777685,0.0024479865,0.00045447168,0.00070405984,0.00042322034],"domain_scores_gemma":[0.9957046,0.0009795995,0.0020111105,0.00022013328,0.0005043696,0.0005802146],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0021565198,0.00033594738,0.0026296459,0.00043651427,0.000080587495,0.000019688809,0.00023922714,0.00011438208,0.000016520036],"category_scores_gemma":[0.00074770476,0.00022188506,0.00041002737,0.000401771,0.0003535355,0.00011370717,0.000062975596,0.0024155728,3.8634454e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.020898866,0.0054480913,0.9177656,0.000116629555,0.00023110391,0.0011295166,0.000162965,0.0003996944,0.0029898966,0.000016698445,0.0011624572,0.049678486],"study_design_scores_gemma":[0.020789351,0.025306951,0.94592756,0.00091209705,0.00049764145,0.00015347394,0.000035702826,0.004102256,0.0015928332,0.000038270002,0.00042394997,0.00021993561],"about_ca_topic_score_codex":0.000023949035,"about_ca_topic_score_gemma":0.000007455625,"teacher_disagreement_score":0.04945855,"about_ca_system_score_codex":0.0002802901,"about_ca_system_score_gemma":0.0011346288,"threshold_uncertainty_score":0.9998859},"labels":[],"label_agreement":null},{"id":"W6891643944","doi":"10.48336/qsdf-f110","title":"Machine learning-based prediction of molecular subtypes of breast cancer using DCE MRI","year":2023,"lang":"en","type":"article","venue":"Memorial University Research Repository (Memorial University)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Breast cancer; Radiomics; Feature (linguistics); Mammography; Outlier; Robustness (evolution); Hyperparameter; Pattern recognition (psychology)","score_opus":0.022243247983165976,"score_gpt":0.28223087123171225,"score_spread":0.2599876232485463,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6891643944","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9911407,0.00005598061,0.0011404094,0.0005519436,0.002093095,0.0004672934,0.00011269974,0.0001719352,0.004265944],"genre_scores_gemma":[0.9937496,0.00017695682,0.00035695714,0.0000069456323,0.0010676454,2.0770658e-7,0.00006411824,0.000035644025,0.0045419247],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967812,0.0007713347,0.00028034163,0.0005017344,0.0011618929,0.00050352915],"domain_scores_gemma":[0.99783033,0.00028035216,0.0002324512,0.0003949491,0.00091836054,0.00034355148],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010271602,0.00020070565,0.0005271751,0.0015783537,0.000498851,0.000020797197,0.0004562519,0.00022984766,0.00007452739],"category_scores_gemma":[0.0002829114,0.00022715073,0.00026787358,0.002678519,0.00069936435,0.0002171251,0.00029653357,0.000987393,0.000005621311],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.012076268,0.0005609741,0.103383,0.00076422846,0.00072374963,0.0048912214,0.00057829055,0.06319782,0.80924267,0.0015181691,0.001660134,0.0014034712],"study_design_scores_gemma":[0.033106424,0.0032129865,0.045523778,0.00209887,0.00210321,0.00027561956,0.004512155,0.62631845,0.1913944,0.00011432447,0.09018791,0.0011518865],"about_ca_topic_score_codex":0.004991468,"about_ca_topic_score_gemma":0.000019754429,"teacher_disagreement_score":0.6178483,"about_ca_system_score_codex":0.0005913603,"about_ca_system_score_gemma":0.0011855352,"threshold_uncertainty_score":0.9262938},"labels":[],"label_agreement":null},{"id":"W6902030058","doi":"10.6084/m9.figshare.16306024.v1","title":"Additional file 1 of Preselection of robust radiomic features does not improve outcome modelling in non-small cell lung cancer based on clinical routine FDG-PET imaging","year":2021,"lang":"en","type":"article","venue":"Figshare","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Cohort; Outcome (game theory); Lung cancer; Venn diagram; Robustness (evolution); Cohort study","score_opus":0.026077446125640218,"score_gpt":0.31330291900421386,"score_spread":0.28722547287857364,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6902030058","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007704172,0.00012721767,0.00020640194,0.0004983941,0.00015479774,0.00032978228,0.9897693,0.000032440526,0.0011775286],"genre_scores_gemma":[0.404443,0.000011399475,0.010223248,0.0011307616,0.0006113622,0.00038167884,0.5804719,0.000067112596,0.0026595655],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983185,0.00008402638,0.0006340027,0.00038920142,0.00031927993,0.00025497115],"domain_scores_gemma":[0.997135,0.001913808,0.0003306186,0.0002553844,0.00024631567,0.00011890148],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00015641087,0.00017411294,0.0004889081,0.00015651438,0.00004570965,0.000013893576,0.00012042512,0.00008922802,0.614914],"category_scores_gemma":[0.0043897624,0.00014355696,0.00021149564,0.00021619548,0.000025513726,0.000056284403,0.00005429993,0.0008162263,0.000011642418],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016060233,0.0002862757,0.0087697,0.0011133992,0.00003796723,0.0001596659,0.00004696433,0.066475615,0.000889973,5.916349e-7,0.920902,0.001157251],"study_design_scores_gemma":[0.0016105999,0.00006596918,0.025301628,0.00510691,0.00004520827,0.000017802784,0.000021720361,0.95984924,0.0029339392,0.0000026327414,0.004885597,0.00015872528],"about_ca_topic_score_codex":0.00010177574,"about_ca_topic_score_gemma":0.00001847696,"teacher_disagreement_score":0.9160164,"about_ca_system_score_codex":0.00009448273,"about_ca_system_score_gemma":0.00044847,"threshold_uncertainty_score":0.58540833},"labels":[],"label_agreement":null},{"id":"W6902144974","doi":"10.6084/m9.figshare.25045445.v1","title":"Additional file 1 of Development and validation of survival prognostic models for head and neck cancer patients using machine learning and dosiomics and CT radiomics features: a multicentric study","year":2024,"lang":"en","type":"article","venue":"Figshare","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Radiomics; Head and neck cancer; Computed tomography; Radiation therapy; Head and neck; Cancer","score_opus":0.02952345158394558,"score_gpt":0.3076036582086909,"score_spread":0.2780802066247453,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6902144974","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6056226,0.0013780366,0.00001651919,0.000018729908,0.000021004576,0.00065341685,0.39226064,0.000015467485,0.000013603405],"genre_scores_gemma":[0.7032157,0.00007039045,0.009868851,0.000029284203,0.000072246476,0.000273534,0.2863398,0.000044143082,0.000086022366],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99925715,0.000027973498,0.0002102115,0.00022636958,0.00016025144,0.00011802169],"domain_scores_gemma":[0.99877447,0.00090705114,0.000097012395,0.000037578506,0.00009715905,0.00008674272],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000067849534,0.00011637583,0.00023948403,0.00011625893,0.00008069266,0.000035250247,0.000021804077,0.000032695698,0.012726789],"category_scores_gemma":[0.0017292466,0.000100755286,0.000018151228,0.00010011707,0.00002002779,0.00008049891,0.000065150525,0.0001665194,2.5772485e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010597946,0.00168571,0.20449029,0.027672788,0.0016642209,0.00011324609,0.015176967,0.0029973171,0.00048619814,0.000021421054,0.3670082,0.37762383],"study_design_scores_gemma":[0.0031541656,0.00041023042,0.081458546,0.010346319,0.00019518253,0.00005020565,0.00019910028,0.8811793,0.00011940885,0.00001833248,0.022631578,0.00023764704],"about_ca_topic_score_codex":0.000030723095,"about_ca_topic_score_gemma":0.000006299562,"teacher_disagreement_score":0.878182,"about_ca_system_score_codex":0.000031144376,"about_ca_system_score_gemma":0.000119832825,"threshold_uncertainty_score":0.9881757},"labels":[],"label_agreement":null},{"id":"W6902300996","doi":"10.6084/m9.figshare.26563797","title":"Additional file 1 of Radiogenomic association of deep MR imaging features with genomic profiles and clinical characteristics in breast cancer","year":2024,"lang":"en","type":"article","venue":"Open MIND","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"CancerCare Manitoba; Western University; University of Manitoba","funders":"","keywords":"Python (programming language); Breast cancer; Lasso (programming language); Radiogenomics; Distributed File System; Set (abstract data type); Table (database); R package; Radiomics","score_opus":0.008976773018362964,"score_gpt":0.30939130667728615,"score_spread":0.3004145336589232,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6902300996","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86946386,0.00044722782,0.00002261079,0.003070048,0.00014056504,0.0004859522,0.12417571,0.0000036445858,0.0021904015],"genre_scores_gemma":[0.95104754,0.00028436416,0.025526762,0.00025830485,0.0006483532,0.00010562267,0.019113796,0.000057056983,0.0029582072],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9992378,0.00004014088,0.0002958752,0.00019092421,0.00012612938,0.00010916941],"domain_scores_gemma":[0.9990726,0.00059168244,0.00015710026,0.00007396528,0.000048099206,0.000056524474],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00029302377,0.00007519189,0.0002886559,0.000076234246,0.000017457398,0.000036435584,0.00007260286,0.000044159733,0.12997825],"category_scores_gemma":[0.0002574195,0.000059349626,0.00003444113,0.00008706074,0.000084841595,0.00006570765,0.00004894308,0.00026224073,0.000009243742],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023550731,0.00011674689,0.28999794,0.00014435042,0.00022583509,0.000079034486,0.00034442215,0.0000057103134,0.0016710543,0.000006396992,0.2257613,0.48141173],"study_design_scores_gemma":[0.00062231725,0.000043912103,0.92933655,0.0012402199,0.00010122804,0.00012245994,0.000072492454,0.011177989,0.00004481433,0.000007584045,0.057146315,0.00008413799],"about_ca_topic_score_codex":0.000075977594,"about_ca_topic_score_gemma":0.000022962186,"teacher_disagreement_score":0.6393386,"about_ca_system_score_codex":0.00008924982,"about_ca_system_score_gemma":0.0002525812,"threshold_uncertainty_score":0.87081707},"labels":[],"label_agreement":null},{"id":"W6902310589","doi":"10.6084/m9.figshare.28666094","title":"Additional file 1 of Radiomic-based approaches in the multi-metastatic setting: a quantitative review","year":2025,"lang":"en","type":"article","venue":"Open MIND","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Queen's University; University Health Network","funders":"","keywords":"Key (lock); Identification (biology); Feature (linguistics); Set (abstract data type); Focus (optics)","score_opus":0.09224151579043803,"score_gpt":0.3845544106113622,"score_spread":0.29231289482092415,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6902310589","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010795096,0.021704916,0.01481565,0.18724671,0.00041621726,0.01934545,0.36251208,0.000024468405,0.38313943],"genre_scores_gemma":[0.006262259,0.00009054419,0.9367895,0.00785766,0.000031388958,0.00080601685,0.043375805,0.000021502947,0.004765317],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990535,0.00019645822,0.00029713966,0.00018306987,0.00015370875,0.00011615112],"domain_scores_gemma":[0.99715984,0.0024555512,0.00012359659,0.00019507112,0.000034589633,0.000031340285],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00076290604,0.000085610984,0.00030646453,0.000085931366,0.000038339203,0.000021202322,0.00025127042,0.000019767007,0.26602128],"category_scores_gemma":[0.0048411633,0.000056437933,0.0000680708,0.00033492502,0.00011855491,0.00004074996,0.000041541523,0.00026148467,0.000052883333],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003075458,0.00023731063,0.00006411476,0.00037928825,0.000041441865,0.00002321745,0.00021212488,0.000019611865,0.000019492536,0.000045480207,0.92275506,0.076172076],"study_design_scores_gemma":[0.0014058747,0.00007997235,0.0023311093,0.010683508,0.00011428643,0.000018229302,0.00066215824,0.073308624,0.000037324593,0.000037907976,0.91123486,0.00008615372],"about_ca_topic_score_codex":0.000019354162,"about_ca_topic_score_gemma":0.000007660536,"teacher_disagreement_score":0.9219739,"about_ca_system_score_codex":0.000022442036,"about_ca_system_score_gemma":0.00033432044,"threshold_uncertainty_score":0.73464966},"labels":[],"label_agreement":null},{"id":"W6907963253","doi":"10.25384/sage.24905755","title":"sj-docx-1-caj-10.1177_08465371231218250 – Supplemental material for Limitations of GPT-3.5 and GPT-4 in Applying Fleischner Society Guidelines to Incidental Lung Nodules","year":2023,"lang":"en","type":"article","venue":"Sage Journals Data","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Lung; Lung disease; MEDLINE; Clinical Practice","score_opus":0.10493372042395245,"score_gpt":0.40500391639958794,"score_spread":0.3000701959756355,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6907963253","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94426465,0.0027062178,0.01220135,0.030109627,0.0008440017,0.0018076285,0.007830215,0.000108419845,0.00012789435],"genre_scores_gemma":[0.8127491,0.011842057,0.15315042,0.0038044117,0.0027624185,0.00024173394,0.013883629,0.00018158263,0.0013846682],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979536,0.00004960554,0.0008108998,0.00037775873,0.00041613643,0.00039203244],"domain_scores_gemma":[0.998762,0.00028460787,0.00019245266,0.0004190078,0.00012315728,0.00021878214],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002004142,0.00018074327,0.0004275108,0.00024496342,0.00016354743,0.000100878686,0.00034639388,0.00007447227,0.00113495],"category_scores_gemma":[0.0015310429,0.00015815716,0.00009632222,0.00036312183,0.00007825395,0.0002975897,0.00058867404,0.0002763646,0.000009679055],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002480192,0.0001625957,0.042238284,0.0003868782,0.00030180663,0.000091850714,0.0017520593,0.00026192624,0.13227047,0.000022709855,0.62591404,0.19634937],"study_design_scores_gemma":[0.016305426,0.0006378231,0.120876506,0.0062270155,0.0009399166,0.0007550065,0.014914929,0.35136554,0.006534132,0.00079226604,0.47944325,0.0012081793],"about_ca_topic_score_codex":0.00017669656,"about_ca_topic_score_gemma":0.000065467764,"teacher_disagreement_score":0.3511036,"about_ca_system_score_codex":0.000056565423,"about_ca_system_score_gemma":0.000101173675,"threshold_uncertainty_score":0.99977815},"labels":[],"label_agreement":null},{"id":"W6911633631","doi":"10.5281/zenodo.13695615","title":"PHARAOH: A Collaborative Crowdsourcing Platform for PHenotyping And Regional Analysis Of Histology: CCRCC Validation Cohort Grades 1 and 2","year":2024,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network","funders":"","keywords":"Crowdsourcing; Cohort; Cohort study; Statistical analysis","score_opus":0.02743407092939961,"score_gpt":0.2943660161061856,"score_spread":0.26693194517678603,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6911633631","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03568672,0.022884663,0.07874268,0.010617107,0.0006825938,0.0067114946,0.002333597,0.0028608833,0.8394803],"genre_scores_gemma":[0.50415504,0.0116705485,0.021016104,0.00197124,0.002481478,0.000003341306,0.040066034,0.02988005,0.3887562],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988239,0.00007987854,0.0002483953,0.00042632956,0.00023565392,0.0001858394],"domain_scores_gemma":[0.999189,0.00005063834,0.0002002508,0.00019201843,0.00023958535,0.00012850399],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000568491,0.00015898453,0.00043788817,0.0008635101,0.00032335662,0.00016376167,0.00014188868,0.0001190012,0.0015271261],"category_scores_gemma":[0.0006114668,0.00015246906,0.00006783513,0.00062796293,0.00029643113,0.000050660412,0.00021183016,0.00028834937,0.000045126977],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022171203,0.00009892757,0.0001520731,0.001743676,0.003823637,0.000025486697,0.0027204556,0.000026033269,0.0017986777,0.0063037453,0.90785104,0.07523455],"study_design_scores_gemma":[0.00066623476,0.00012326107,0.00038399702,0.00034683,0.0015113933,0.0000820463,0.00025084522,0.008290626,0.000026930718,0.00016370125,0.98800546,0.00014869407],"about_ca_topic_score_codex":0.000036335496,"about_ca_topic_score_gemma":7.1641836e-7,"teacher_disagreement_score":0.4684683,"about_ca_system_score_codex":0.00008283453,"about_ca_system_score_gemma":0.000008858838,"threshold_uncertainty_score":0.9993856},"labels":[],"label_agreement":null},{"id":"W6920485897","doi":"10.60692/3bf59-vzf56","title":"Radiomic Analysis of Tumour Heterogeneity Using MRI in Head and Neck Cancer Following Chemoradiotherapy: A Feasibility Study","year":2022,"lang":"en","type":"article","venue":"Greater South Information System","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Thomas Hospital","funders":"","keywords":"Wilcoxon signed-rank test; Head and neck cancer; Lymph node; Kurtosis; Effective diffusion coefficient; Confidence interval; Tumour heterogeneity; Stage (stratigraphy); Multiparametric MRI","score_opus":0.04090396642078167,"score_gpt":0.31689119352837025,"score_spread":0.2759872271075886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6920485897","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99730605,0.000034257584,0.0016709925,0.00006896562,0.00014991403,0.00066326343,0.000031275744,0.000037895024,0.00003737442],"genre_scores_gemma":[0.99939966,4.032147e-7,0.0003669119,0.00013551523,0.000021365799,0.000049100923,0.000011437723,0.000010170499,0.0000054234147],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9983916,0.00016266954,0.0006739226,0.00019362017,0.000392652,0.00018548376],"domain_scores_gemma":[0.9993146,0.000009147834,0.00028181134,0.00026382972,0.000040820254,0.00008978489],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010661363,0.00013793739,0.0006782096,0.0006875439,0.00012866675,0.000035597186,0.00008824336,0.000031138432,0.000021545757],"category_scores_gemma":[0.000021100472,0.00012304448,0.00015777402,0.0009016261,0.000023332077,0.00017200982,0.000069050555,0.00021204112,5.691635e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012209374,0.000019924368,0.9557723,0.0001574958,0.00049909373,0.000010048675,0.033202156,0.01000501,0.00008501729,0.0000010755994,0.0000017465358,0.00012407244],"study_design_scores_gemma":[0.00283821,0.00008586281,0.7198005,0.0000605526,0.00046430607,0.000022100716,0.008153952,0.26843742,0.00004354489,8.1688306e-8,0.000006773534,0.00008675222],"about_ca_topic_score_codex":0.0005351545,"about_ca_topic_score_gemma":0.0000052386904,"teacher_disagreement_score":0.25843242,"about_ca_system_score_codex":0.00048312487,"about_ca_system_score_gemma":0.00007316971,"threshold_uncertainty_score":0.5017608},"labels":[],"label_agreement":null},{"id":"W6920569833","doi":"10.6084/m9.figshare.16306024","title":"Additional file 1 of Preselection of robust radiomic features does not improve outcome modelling in non-small cell lung cancer based on clinical routine FDG-PET imaging","year":2021,"lang":"en","type":"article","venue":"Figshare","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Cohort; Outcome (game theory); Lung cancer; Venn diagram; Robustness (evolution); Cohort study","score_opus":0.026077446125640218,"score_gpt":0.31330291900421386,"score_spread":0.28722547287857364,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6920569833","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007704172,0.00012721767,0.00020640194,0.0004983941,0.00015479774,0.00032978228,0.9897693,0.000032440526,0.0011775286],"genre_scores_gemma":[0.404443,0.000011399475,0.010223248,0.0011307616,0.0006113622,0.00038167884,0.5804719,0.000067112596,0.0026595655],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983185,0.00008402638,0.0006340027,0.00038920142,0.00031927993,0.00025497115],"domain_scores_gemma":[0.997135,0.001913808,0.0003306186,0.0002553844,0.00024631567,0.00011890148],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00015641087,0.00017411294,0.0004889081,0.00015651438,0.00004570965,0.000013893576,0.00012042512,0.00008922802,0.614914],"category_scores_gemma":[0.0043897624,0.00014355696,0.00021149564,0.00021619548,0.000025513726,0.000056284403,0.00005429993,0.0008162263,0.000011642418],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016060233,0.0002862757,0.0087697,0.0011133992,0.00003796723,0.0001596659,0.00004696433,0.066475615,0.000889973,5.916349e-7,0.920902,0.001157251],"study_design_scores_gemma":[0.0016105999,0.00006596918,0.025301628,0.00510691,0.00004520827,0.000017802784,0.000021720361,0.95984924,0.0029339392,0.0000026327414,0.004885597,0.00015872528],"about_ca_topic_score_codex":0.00010177574,"about_ca_topic_score_gemma":0.00001847696,"teacher_disagreement_score":0.9160164,"about_ca_system_score_codex":0.00009448273,"about_ca_system_score_gemma":0.00044847,"threshold_uncertainty_score":0.58540833},"labels":[],"label_agreement":null},{"id":"W6920670071","doi":"10.6084/m9.figshare.26687759.v1","title":"Additional file 1 of Conditional generative adversarial network driven radiomic prediction of mutation status based on magnetic resonance imaging of breast cancer","year":2024,"lang":"en","type":"article","venue":"Figshare","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lawson Health Research Institute; University of Winnipeg; Western University","funders":"","keywords":"Autoencoder; Magnetic resonance imaging; Receiver operating characteristic; Pattern recognition (psychology); Deep learning; Breast MRI","score_opus":0.00896290874280175,"score_gpt":0.25372481692260845,"score_spread":0.2447619081798067,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6920670071","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00013086192,0.0005962108,0.00007215357,0.00018513226,0.000121775935,0.000183564,0.9980588,0.000027995326,0.0006235275],"genre_scores_gemma":[0.099379934,0.00000611775,0.0016937068,0.0001677071,0.0006631795,0.00024615525,0.89766204,0.000022194363,0.00015894006],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989606,0.000047000984,0.00028538716,0.00019751105,0.00035888248,0.00015062679],"domain_scores_gemma":[0.99865776,0.00083392207,0.00014522523,0.000096652206,0.00019686986,0.00006958615],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000037832342,0.00010386001,0.0002075406,0.00012151946,0.000034177072,0.000007660909,0.000048860173,0.000046241817,0.89931554],"category_scores_gemma":[0.0007212032,0.000097863835,0.000096515876,0.00022116472,0.000051544943,0.00006908878,0.000014767684,0.00021075128,0.000026964555],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000112041715,0.00004072827,0.00018108117,0.00024778707,0.000024288143,0.000018652107,0.00004992197,0.01143012,0.00019360283,0.000018921419,0.97698766,0.010695187],"study_design_scores_gemma":[0.00085500866,0.00015408668,0.1003984,0.011894202,0.00004789142,0.000028163464,0.000014649016,0.74818283,0.00013441038,0.00004001859,0.13817282,0.000077497505],"about_ca_topic_score_codex":0.000019900037,"about_ca_topic_score_gemma":0.0000015569973,"teacher_disagreement_score":0.89928854,"about_ca_system_score_codex":0.00009285194,"about_ca_system_score_gemma":0.0005030534,"threshold_uncertainty_score":0.39907715},"labels":[],"label_agreement":null},{"id":"W6920821472","doi":"10.6084/m9.figshare.26687759","title":"Additional file 1 of Conditional generative adversarial network driven radiomic prediction of mutation status based on magnetic resonance imaging of breast cancer","year":2024,"lang":"en","type":"article","venue":"Figshare","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lawson Health Research Institute; University of Winnipeg; Western University","funders":"","keywords":"Autoencoder; Magnetic resonance imaging; Receiver operating characteristic; Pattern recognition (psychology); Deep learning; Breast MRI","score_opus":0.00896290874280175,"score_gpt":0.25372481692260845,"score_spread":0.2447619081798067,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6920821472","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00013086192,0.0005962108,0.00007215357,0.00018513226,0.000121775935,0.000183564,0.9980588,0.000027995326,0.0006235275],"genre_scores_gemma":[0.099379934,0.00000611775,0.0016937068,0.0001677071,0.0006631795,0.00024615525,0.89766204,0.000022194363,0.00015894006],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989606,0.000047000984,0.00028538716,0.00019751105,0.00035888248,0.00015062679],"domain_scores_gemma":[0.99865776,0.00083392207,0.00014522523,0.000096652206,0.00019686986,0.00006958615],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000037832342,0.00010386001,0.0002075406,0.00012151946,0.000034177072,0.000007660909,0.000048860173,0.000046241817,0.89931554],"category_scores_gemma":[0.0007212032,0.000097863835,0.000096515876,0.00022116472,0.000051544943,0.00006908878,0.000014767684,0.00021075128,0.000026964555],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000112041715,0.00004072827,0.00018108117,0.00024778707,0.000024288143,0.000018652107,0.00004992197,0.01143012,0.00019360283,0.000018921419,0.97698766,0.010695187],"study_design_scores_gemma":[0.00085500866,0.00015408668,0.1003984,0.011894202,0.00004789142,0.000028163464,0.000014649016,0.74818283,0.00013441038,0.00004001859,0.13817282,0.000077497505],"about_ca_topic_score_codex":0.000019900037,"about_ca_topic_score_gemma":0.0000015569973,"teacher_disagreement_score":0.89928854,"about_ca_system_score_codex":0.00009285194,"about_ca_system_score_gemma":0.0005030534,"threshold_uncertainty_score":0.39907715},"labels":[],"label_agreement":null},{"id":"W6920944228","doi":"10.6084/m9.figshare.25045445","title":"Additional file 1 of Development and validation of survival prognostic models for head and neck cancer patients using machine learning and dosiomics and CT radiomics features: a multicentric study","year":2024,"lang":"en","type":"article","venue":"Figshare","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Radiomics; Head and neck cancer; Computed tomography; Radiation therapy; Head and neck; Cancer","score_opus":0.02952345158394558,"score_gpt":0.3076036582086909,"score_spread":0.2780802066247453,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6920944228","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6056226,0.0013780366,0.00001651919,0.000018729908,0.000021004576,0.00065341685,0.39226064,0.000015467485,0.000013603405],"genre_scores_gemma":[0.7032157,0.00007039045,0.009868851,0.000029284203,0.000072246476,0.000273534,0.2863398,0.000044143082,0.000086022366],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99925715,0.000027973498,0.0002102115,0.00022636958,0.00016025144,0.00011802169],"domain_scores_gemma":[0.99877447,0.00090705114,0.000097012395,0.000037578506,0.00009715905,0.00008674272],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000067849534,0.00011637583,0.00023948403,0.00011625893,0.00008069266,0.000035250247,0.000021804077,0.000032695698,0.012726789],"category_scores_gemma":[0.0017292466,0.000100755286,0.000018151228,0.00010011707,0.00002002779,0.00008049891,0.000065150525,0.0001665194,2.5772485e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010597946,0.00168571,0.20449029,0.027672788,0.0016642209,0.00011324609,0.015176967,0.0029973171,0.00048619814,0.000021421054,0.3670082,0.37762383],"study_design_scores_gemma":[0.0031541656,0.00041023042,0.081458546,0.010346319,0.00019518253,0.00005020565,0.00019910028,0.8811793,0.00011940885,0.00001833248,0.022631578,0.00023764704],"about_ca_topic_score_codex":0.000030723095,"about_ca_topic_score_gemma":0.000006299562,"teacher_disagreement_score":0.878182,"about_ca_system_score_codex":0.000031144376,"about_ca_system_score_gemma":0.000119832825,"threshold_uncertainty_score":0.9881757},"labels":[],"label_agreement":null},{"id":"W6921088666","doi":"10.6084/m9.figshare.28666094.v1","title":"Additional file 1 of Radiomic-based approaches in the multi-metastatic setting: a quantitative review","year":2025,"lang":"en","type":"article","venue":"Figshare","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Queen's University; University Health Network","funders":"","keywords":"Key (lock); Identification (biology); Feature (linguistics); Set (abstract data type); Focus (optics)","score_opus":0.09475280858225413,"score_gpt":0.3563143518001161,"score_spread":0.26156154321786196,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6921088666","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000005210105,0.002372995,0.000033586926,0.0030047386,0.000008548332,0.00047704575,0.990946,0.000016167818,0.0031357333],"genre_scores_gemma":[0.0006420078,0.000008699449,0.019738968,0.0060552172,0.00001744218,0.0009450893,0.9722602,0.000009661364,0.00032272347],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99916065,0.00013539544,0.00024885713,0.00015472075,0.0001753938,0.00012496233],"domain_scores_gemma":[0.99647766,0.0031383191,0.00011812577,0.00017849288,0.000055769025,0.000031614807],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00016301499,0.00009236899,0.00025537974,0.00010014244,0.000033608918,0.000008471337,0.00014176557,0.000024581108,0.8627849],"category_scores_gemma":[0.021676881,0.00006256377,0.000100681966,0.0003699894,0.000025061647,0.000025579853,0.000021683763,0.00031037375,0.00013149927],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000780981,0.00009891972,0.0000073396886,0.0025061704,0.00002195292,0.000018679531,0.00005286158,0.000016399972,0.000002059514,0.000019339186,0.99293476,0.0043137027],"study_design_scores_gemma":[0.00063357264,0.000042676016,0.0025111297,0.08785714,0.00003812609,0.000012869366,0.00013139866,0.07538889,0.000007881784,0.000019373167,0.833286,0.000070952454],"about_ca_topic_score_codex":0.0000034051104,"about_ca_topic_score_gemma":0.0000017565606,"teacher_disagreement_score":0.86265343,"about_ca_system_score_codex":0.000023737955,"about_ca_system_score_gemma":0.0002585536,"threshold_uncertainty_score":0.9865639},"labels":[],"label_agreement":null},{"id":"W6929636966","doi":"10.5063/q81bgh","title":"York University Tree Inventory","year":2019,"lang":"en","type":"dataset","venue":"UC Santa Barbara","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"York University","funders":"","keywords":"Census; Tree (set theory); Block (permutation group theory); Metropolitan area; Geographic coordinate system; Table (database); University campus","score_opus":0.018622407994803563,"score_gpt":0.2720323660076589,"score_spread":0.2534099580128553,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6929636966","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021210008,0.0016065012,0.000040350194,0.00094788097,0.0020427487,0.00050781533,0.98445433,0.00011051674,0.008168833],"genre_scores_gemma":[0.0003497477,0.0010366497,0.00018474161,0.001994717,0.00080210203,0.0000012532001,0.99051374,0.000040561124,0.0050764875],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99834913,0.00009478551,0.00023400517,0.00049967645,0.00044715006,0.0003752765],"domain_scores_gemma":[0.9985266,0.00008853364,0.00016054725,0.00086931855,0.000038993563,0.000316017],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00026802198,0.00031252307,0.0006285368,0.00029078097,0.000087645785,0.00002717166,0.00042340998,0.00037456732,0.001609391],"category_scores_gemma":[0.00018963928,0.00029373524,0.00023084124,0.00020718928,0.00015163439,0.000047162994,0.00017346299,0.0014582082,0.0014486925],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000822982,0.000082908475,0.0009479842,0.0003262034,0.00013092057,0.00047958404,0.000024408508,0.000002873419,0.000035827034,0.000013141331,0.9959897,0.0018841836],"study_design_scores_gemma":[0.0012241715,0.0001252228,0.0010667613,0.00039716708,0.0004568757,0.00010644984,0.0000595,0.00048716908,0.0000037942618,0.000008808581,0.9957775,0.0002865908],"about_ca_topic_score_codex":0.00040059607,"about_ca_topic_score_gemma":0.000019853811,"teacher_disagreement_score":0.0060593872,"about_ca_system_score_codex":0.0002051591,"about_ca_system_score_gemma":0.00034424578,"threshold_uncertainty_score":0.9999515},"labels":[],"label_agreement":null},{"id":"W6929814473","doi":"10.5281/zenodo.10123388","title":"Fig. 51 in A revision of Scipopus Enderlein including the subgenera Scipopus s. str., Phaeopterina Frey and Parascipopus subgen. nov. (Diptera, Micropezidae, Taeniapterinae)","year":2023,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Subgenus; Taxonomy (biology)","score_opus":0.03794480904730034,"score_gpt":0.2970628250269043,"score_spread":0.25911801597960393,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6929814473","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48687595,0.014370789,0.0028036071,0.01024691,0.0022350182,0.0068929303,0.000927277,0.0049605323,0.47068697],"genre_scores_gemma":[0.9103487,0.009428704,0.002194822,0.00051534513,0.0010342466,5.3885776e-7,0.0014068855,0.015147847,0.059922896],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9971175,0.00039447745,0.0005879934,0.0007347074,0.0006259027,0.0005393786],"domain_scores_gemma":[0.9984587,0.00005073897,0.00034581372,0.00073940004,0.00015638645,0.00024895545],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0014068738,0.00035618848,0.0006049573,0.0007938928,0.00069612986,0.0003153777,0.0008056161,0.000199828,0.0033619134],"category_scores_gemma":[0.0011472102,0.0002965421,0.000104850114,0.00082513946,0.00046714928,0.00010415675,0.0015043372,0.000893468,0.00058953103],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022372905,0.00014940649,0.00027932177,0.00075585995,0.00016407462,0.00023286021,0.0012167051,0.000013262989,0.0027464586,0.0003996176,0.2636859,0.73013276],"study_design_scores_gemma":[0.0011894844,0.00035678668,0.0007757965,0.001219449,0.00006347,0.00031479896,0.00013116689,0.0005771448,0.00012896296,0.000012542142,0.9949574,0.00027302676],"about_ca_topic_score_codex":0.0007383681,"about_ca_topic_score_gemma":0.000019586521,"teacher_disagreement_score":0.73127145,"about_ca_system_score_codex":0.00018346812,"about_ca_system_score_gemma":0.000015477368,"threshold_uncertainty_score":0.9999487},"labels":[],"label_agreement":null},{"id":"W6929973923","doi":"10.5281/zenodo.10013996","title":"gwastro/pycbc: v2.4.0 release of PyCBC","year":2023,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Semtech (Canada)","funders":"","keywords":"Container (type theory); Singularity; Shell (structure); Virtual machine","score_opus":0.022435785288877335,"score_gpt":0.27553983203975996,"score_spread":0.2531040467508826,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6929973923","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005048349,0.0003189069,0.0018961349,0.001530294,0.00031400865,0.0006155831,0.00023443346,0.0032312577,0.9913545],"genre_scores_gemma":[0.025827533,0.0017404503,0.0023303344,0.0005611085,0.0018149741,1.4161363e-7,0.004082932,0.05266703,0.9109755],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99809676,0.00018256242,0.00032973356,0.00045193074,0.00056418945,0.00037481321],"domain_scores_gemma":[0.9985755,0.000031525262,0.00024055596,0.00061703875,0.00022996093,0.00030538946],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00053800485,0.00021456317,0.00040538708,0.0005547783,0.000358774,0.000118039294,0.0005784722,0.00016710059,0.030124841],"category_scores_gemma":[0.001757502,0.00021103385,0.00012228316,0.0005232301,0.00027571493,0.000042303414,0.0006076775,0.00070950313,0.0076085683],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000047106154,0.000100531724,0.00000865139,0.00032435945,0.0001275242,0.0000821067,0.00014611425,0.000007634636,0.00059300323,0.00069391547,0.8927901,0.10507895],"study_design_scores_gemma":[0.000840709,0.00023197239,0.0002105715,0.0005632325,0.000080103215,0.00013070159,0.00008878849,0.00046497994,0.000051883693,0.00002996278,0.9971393,0.00016781501],"about_ca_topic_score_codex":0.00010996402,"about_ca_topic_score_gemma":6.032158e-7,"teacher_disagreement_score":0.10491113,"about_ca_system_score_codex":0.00010351215,"about_ca_system_score_gemma":0.00001084021,"threshold_uncertainty_score":0.9931641},"labels":[],"label_agreement":null},{"id":"W6930884367","doi":"10.5281/zenodo.154059","title":"ICGC-TCGA-PanCancer/CGP-Somatic-Docker: 2.0.0-cwl1","year":2016,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Institute for Cancer Research","funders":"","keywords":"Product (mathematics); Process (computing); Identification (biology); Work (physics)","score_opus":0.018382911230523352,"score_gpt":0.2821915503012922,"score_spread":0.2638086390707689,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6930884367","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00012972039,0.0005694579,0.005038228,0.0038303751,0.00038089327,0.0006917018,0.0001847357,0.0019122245,0.98726267],"genre_scores_gemma":[0.0036459037,0.0017216057,0.0019315202,0.001187972,0.0024282015,1.935078e-7,0.002473156,0.01802273,0.9685887],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975027,0.00024994157,0.00036019925,0.0006366469,0.0006720339,0.00057850464],"domain_scores_gemma":[0.9981901,0.000033658867,0.00026426016,0.00082167226,0.0002467656,0.00044355437],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0005580675,0.00032566272,0.000490462,0.0005111708,0.00074693805,0.0003320306,0.00081395794,0.00021646042,0.16116087],"category_scores_gemma":[0.0010226753,0.00027365825,0.0001361441,0.00031729753,0.0003115682,0.0000765866,0.0007185029,0.00072924787,0.033581305],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034606186,0.000076438235,0.0000072540915,0.000280637,0.0001362993,0.00006751055,0.00012419374,6.9897834e-7,0.0007591996,0.0009356303,0.82187957,0.175698],"study_design_scores_gemma":[0.0012892124,0.00016491051,0.00011745057,0.00080519693,0.000086446,0.00028489897,0.000042132633,0.00022298122,0.000049844948,0.00009875113,0.9965401,0.00029803748],"about_ca_topic_score_codex":0.0000473331,"about_ca_topic_score_gemma":3.1253188e-7,"teacher_disagreement_score":0.17539996,"about_ca_system_score_codex":0.00024213183,"about_ca_system_score_gemma":0.000016848557,"threshold_uncertainty_score":0.99997157},"labels":[],"label_agreement":null},{"id":"W6939512785","doi":"10.6084/m9.figshare.26607052.v1","title":"Additional file 1 of Radiomics using computed tomography to predict CD73 expression and prognosis of colorectal cancer liver metastases","year":2024,"lang":"en","type":"article","venue":"Figshare","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Polytechnique Montréal; Centre Hospitalier de l’Université de Montréal","funders":"","keywords":"Radiomics; Computed tomography; Colorectal cancer; Distribution (mathematics); Probabilistic logic; Cancer; Overall survival","score_opus":0.022346745987233407,"score_gpt":0.2847796792174718,"score_spread":0.2624329332302384,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6939512785","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011506314,0.0011039586,0.00001569757,0.000051330677,0.000035302222,0.0002484192,0.9869055,0.00004252076,0.00009096319],"genre_scores_gemma":[0.098396465,0.000015400563,0.028977498,0.0001840395,0.00025960672,0.0004416878,0.8716291,0.00004251409,0.00005365657],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992669,0.000025172421,0.00018362796,0.00019219633,0.00021218677,0.00011989892],"domain_scores_gemma":[0.99899715,0.0006455496,0.00006588858,0.00006443456,0.000100994876,0.00012598139],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00003077064,0.0000989869,0.00022960184,0.0001875145,0.00003158674,0.000016135902,0.000055479388,0.000048154146,0.7713386],"category_scores_gemma":[0.0009347692,0.000082115985,0.000086081774,0.00030173827,0.000028170407,0.000057344263,0.00007378743,0.00015378172,0.000009386027],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030870087,0.00003947499,0.00010897209,0.0008143643,0.0000857766,0.000028735594,0.00009337048,0.000084061394,0.003105936,9.929237e-7,0.98861575,0.0069917133],"study_design_scores_gemma":[0.00052699924,0.0003369574,0.0152519485,0.053297017,0.00017093774,0.00013419968,0.000044540036,0.26101628,0.012543221,0.000007292522,0.6564454,0.00022525218],"about_ca_topic_score_codex":0.000018918985,"about_ca_topic_score_gemma":0.0000011157025,"teacher_disagreement_score":0.77132916,"about_ca_system_score_codex":0.000021075097,"about_ca_system_score_gemma":0.00012827324,"threshold_uncertainty_score":0.33485925},"labels":[],"label_agreement":null},{"id":"W6949883381","doi":"10.5281/zenodo.5300659","title":"FIGURES 46–49 in Cybaeus (Araneae: Cybaeidae) in the Nearctic: the devius and tardatus species groups of the Californian clade","year":2021,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal British Columbia Museum","funders":"","keywords":"Clade; Patella; Genus; Sauria; Phylogenetics","score_opus":0.022896572037168224,"score_gpt":0.2578814518664333,"score_spread":0.23498487982926508,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6949883381","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0154514285,0.004278817,0.00013398763,0.024100436,0.00023883428,0.0015509571,0.00017696293,0.00016464021,0.9539039],"genre_scores_gemma":[0.7877024,0.0076636537,0.0004952144,0.005546823,0.0016554568,6.963148e-7,0.0021944765,0.0077386806,0.1870026],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99766433,0.0008034936,0.0003108496,0.0003398243,0.00055283355,0.0003286808],"domain_scores_gemma":[0.9989148,0.00010022603,0.00016060036,0.0006444794,0.00009617865,0.00008373845],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000965633,0.00018803122,0.00030816533,0.00020697358,0.00045093344,0.00025288356,0.0008867071,0.0001226954,0.0067869485],"category_scores_gemma":[0.0018608015,0.00010664628,0.00007539552,0.0006669457,0.00058279606,0.000028316921,0.00068459637,0.0011967538,0.00014699447],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009420088,0.00024399601,0.0008655424,0.0008351072,0.00013741918,0.0001994444,0.0048213582,0.000038753624,0.0016320171,0.0025516446,0.95136756,0.037212953],"study_design_scores_gemma":[0.00065624045,0.000061032275,0.014594338,0.0005550245,0.000036734775,0.0002616925,0.0008365613,0.0003140849,0.000023225562,0.00006110068,0.9824902,0.00010976771],"about_ca_topic_score_codex":0.00031677863,"about_ca_topic_score_gemma":0.000028103785,"teacher_disagreement_score":0.77225095,"about_ca_system_score_codex":0.0000774585,"about_ca_system_score_gemma":0.000016560321,"threshold_uncertainty_score":0.99412096},"labels":[],"label_agreement":null},{"id":"W6958083466","doi":"10.60692/j9re2-eyd46","title":"Radiomic Analysis of Tumour Heterogeneity Using MRI in Head and Neck Cancer Following Chemoradiotherapy: A Feasibility Study","year":2022,"lang":"en","type":"article","venue":"Greater South Information System","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Thomas Hospital","funders":"","keywords":"Wilcoxon signed-rank test; Head and neck cancer; Lymph node; Kurtosis; Effective diffusion coefficient; Confidence interval; Tumour heterogeneity; Stage (stratigraphy); Multiparametric MRI","score_opus":0.04090396642078167,"score_gpt":0.31689119352837025,"score_spread":0.2759872271075886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6958083466","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99730605,0.000034257584,0.0016709925,0.00006896562,0.00014991403,0.00066326343,0.000031275744,0.000037895024,0.00003737442],"genre_scores_gemma":[0.99939966,4.032147e-7,0.0003669119,0.00013551523,0.000021365799,0.000049100923,0.000011437723,0.000010170499,0.0000054234147],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9983916,0.00016266954,0.0006739226,0.00019362017,0.000392652,0.00018548376],"domain_scores_gemma":[0.9993146,0.000009147834,0.00028181134,0.00026382972,0.000040820254,0.00008978489],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010661363,0.00013793739,0.0006782096,0.0006875439,0.00012866675,0.000035597186,0.00008824336,0.000031138432,0.000021545757],"category_scores_gemma":[0.000021100472,0.00012304448,0.00015777402,0.0009016261,0.000023332077,0.00017200982,0.000069050555,0.00021204112,5.691635e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012209374,0.000019924368,0.9557723,0.0001574958,0.00049909373,0.000010048675,0.033202156,0.01000501,0.00008501729,0.0000010755994,0.0000017465358,0.00012407244],"study_design_scores_gemma":[0.00283821,0.00008586281,0.7198005,0.0000605526,0.00046430607,0.000022100716,0.008153952,0.26843742,0.00004354489,8.1688306e-8,0.000006773534,0.00008675222],"about_ca_topic_score_codex":0.0005351545,"about_ca_topic_score_gemma":0.0000052386904,"teacher_disagreement_score":0.25843242,"about_ca_system_score_codex":0.00048312487,"about_ca_system_score_gemma":0.00007316971,"threshold_uncertainty_score":0.5017608},"labels":[],"label_agreement":null},{"id":"W6958375940","doi":"10.6084/m9.figshare.26563797.v1","title":"Additional file 1 of Radiogenomic association of deep MR imaging features with genomic profiles and clinical characteristics in breast cancer","year":2024,"lang":"en","type":"article","venue":"Figshare","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"CancerCare Manitoba; Western University; University of Manitoba","funders":"","keywords":"Python (programming language); Breast cancer; Lasso (programming language); Radiogenomics; Distributed File System; Set (abstract data type); Table (database); R package; Radiomics","score_opus":0.008163429113300277,"score_gpt":0.2796420629166919,"score_spread":0.27147863380339166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6958375940","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010548328,0.00042702488,7.0818686e-7,0.00061210565,0.000031360985,0.00012808663,0.988002,0.000017809742,0.00023257766],"genre_scores_gemma":[0.18181333,0.000064039894,0.0010703271,0.00027799778,0.0005487699,0.00018302619,0.8155648,0.000040214116,0.00043748203],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9992869,0.000029588775,0.00025693292,0.00016621058,0.00014346947,0.0001169312],"domain_scores_gemma":[0.9988017,0.00084634847,0.00015235714,0.00006794302,0.00007402679,0.000057609745],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000076582706,0.00008108294,0.00024952472,0.00008815223,0.000015468988,0.000016295544,0.000043687458,0.00005384625,0.6750281],"category_scores_gemma":[0.0010784897,0.00006550838,0.000049092858,0.000095437994,0.000021506994,0.000044200333,0.000028003122,0.00030705388,0.00002168152],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037453054,0.000028670533,0.027728392,0.00045254536,0.000070783564,0.000035478388,0.000056542864,0.000002600335,0.00012346877,0.0000016031067,0.9462992,0.025163276],"study_design_scores_gemma":[0.00032643432,0.000027080045,0.9031097,0.006577759,0.000041126,0.00009646563,0.00001906335,0.012607554,0.000012009461,0.000004448912,0.07710245,0.00007589983],"about_ca_topic_score_codex":0.000016412521,"about_ca_topic_score_gemma":0.0000061633637,"teacher_disagreement_score":0.8753813,"about_ca_system_score_codex":0.00009368012,"about_ca_system_score_gemma":0.00019941828,"threshold_uncertainty_score":0.32526898},"labels":[],"label_agreement":null},{"id":"W6980543794","doi":"","title":"Characterizing turbidity and identifying sediment sources in Norway House Cree Nation drinking water using sediment fingerprinting","year":2017,"lang":"en","type":"dissertation","venue":"Mspace (University of Manitoba)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Turbidity; Sediment; Sedimentation; Hydrology (agriculture); Channel (broadcasting); Water quality; Erosion; Drainage basin","score_opus":0.024998415042448978,"score_gpt":0.2606524630712317,"score_spread":0.2356540480287827,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6980543794","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99712014,0.00019085943,0.0002582384,0.00078443566,0.0005344472,0.00031662316,0.0000015530264,0.000050842307,0.0007428374],"genre_scores_gemma":[0.99656886,0.00020933819,0.0020869677,0.00004031618,0.00019747869,5.1267494e-7,0.000089033565,0.000052854517,0.000754647],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.998466,0.00006715893,0.00021462489,0.00044828744,0.00046381133,0.00034011956],"domain_scores_gemma":[0.99900645,0.00004524818,0.0004576176,0.000274445,0.000101670164,0.000114564704],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006738357,0.00025431477,0.000536227,0.00047590848,0.0005030043,0.000097640965,0.00021174327,0.00022955489,0.000017543085],"category_scores_gemma":[0.00008907,0.00027864167,0.000118310025,0.00006655102,0.00008980626,0.00029556357,0.00014801868,0.0007332447,0.000008143407],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042939765,0.00023217069,0.4987283,0.0032621168,0.00042056985,0.000636888,0.0227043,0.0003149076,0.44869167,0.000038087368,0.00010098055,0.02444061],"study_design_scores_gemma":[0.002252634,0.00008456397,0.9363721,0.0052896705,0.0005383425,0.00004057082,0.023339925,0.017028658,0.011945777,0.000048060258,0.0025017676,0.0005579048],"about_ca_topic_score_codex":0.005549934,"about_ca_topic_score_gemma":0.018996917,"teacher_disagreement_score":0.4376438,"about_ca_system_score_codex":0.00026853118,"about_ca_system_score_gemma":0.000070520684,"threshold_uncertainty_score":0.99996656},"labels":[],"label_agreement":null},{"id":"W6995606420","doi":"","title":"The past, present, and future potential of publishing collectives","year":2021,"lang":"en","type":"other","venue":"Summit (Simon Fraser University)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Publishing; Key (lock); Focus (optics); Project commissioning; Section (typography)","score_opus":0.006684484066215567,"score_gpt":0.22112289278499417,"score_spread":0.2144384087187786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6995606420","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029880619,0.009635861,0.0005393578,0.020790681,0.0011099112,0.000498607,0.00004381858,0.00011907424,0.96427464],"genre_scores_gemma":[0.004527096,0.0054791095,0.0006426102,0.00018292428,0.0041249217,7.24405e-7,0.00011960232,0.00018097713,0.98474205],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99893767,0.00011534197,0.000121662386,0.00031323865,0.00029355017,0.00021854196],"domain_scores_gemma":[0.99918646,0.00008470527,0.00017786307,0.00030028855,0.000089260284,0.0001614412],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013796214,0.00018124499,0.00034929108,0.00033107054,0.00015535807,0.00009682966,0.00023110895,0.0002573169,0.00046550907],"category_scores_gemma":[0.000058908918,0.00014465104,0.00012305139,0.00045985816,0.00026746988,0.00007756178,0.0001808644,0.00066559494,0.0000011073602],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007385831,0.000045096596,0.038710356,0.0001926007,0.00034855807,0.00036685696,0.000012811814,0.0000022238303,0.000007063631,0.0003861997,0.9479376,0.011916749],"study_design_scores_gemma":[0.0011196806,0.000043491353,0.0012015732,0.00023403448,0.00022138799,1.4750141e-7,0.0054312404,0.00019276682,0.000012152905,0.000021715965,0.99139446,0.0001273519],"about_ca_topic_score_codex":0.0003508026,"about_ca_topic_score_gemma":0.0010909801,"teacher_disagreement_score":0.043456834,"about_ca_system_score_codex":0.000044607732,"about_ca_system_score_gemma":0.00014552228,"threshold_uncertainty_score":0.58986986},"labels":[],"label_agreement":null},{"id":"W6995650751","doi":"","title":"Optical Nonlinear-Phase-Noise Compensation for 9x32 Gbaud PolDM-16 QAM Transmission using a Code-Aided Expectation-Maximization Algorithm","year":2015,"lang":"en","type":"article","venue":"TSpace (University of Toronto)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Bell (Canada)","funders":"","keywords":"Phase noise; QAM; Optical communication; Transmission (telecommunications); Quadrature amplitude modulation; Phase (matter); Compensation (psychology); Phase modulation","score_opus":0.03176619570002433,"score_gpt":0.3227429698267857,"score_spread":0.2909767741267614,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6995650751","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17950213,0.00019450071,0.8145553,0.003280514,0.00012428884,0.0004347417,0.000012080216,0.0000675652,0.0018288863],"genre_scores_gemma":[0.56226826,0.000053070173,0.43673855,0.000077179284,0.0001247947,5.0643496e-7,0.00017906095,0.000022533557,0.00053606945],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990162,0.0000503377,0.00015403799,0.00024721108,0.00032956537,0.00020264064],"domain_scores_gemma":[0.9989938,0.000079011785,0.00015012828,0.00016649,0.00029579466,0.00031475897],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027314943,0.0001326624,0.00032526167,0.00006641906,0.00015039303,0.000013138156,0.00010439324,0.00011074952,0.00060883386],"category_scores_gemma":[0.00014554587,0.00014867935,0.00011726393,0.000081475584,0.000113186725,0.00030511097,0.000026112328,0.00012699164,0.0000029186904],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0024022239,0.0011523623,0.0008240451,0.0002966307,0.0002550678,0.000061566316,0.024917819,0.00339547,0.03667599,0.0006385972,0.002096607,0.92728364],"study_design_scores_gemma":[0.008313827,0.00050275266,0.0030599823,0.000149094,0.00026558954,0.00002583802,0.008255619,0.97575474,0.0005264405,0.000031736996,0.0029409337,0.00017345615],"about_ca_topic_score_codex":0.0075323638,"about_ca_topic_score_gemma":0.00025513078,"teacher_disagreement_score":0.97235924,"about_ca_system_score_codex":0.0004394633,"about_ca_system_score_gemma":0.00020917128,"threshold_uncertainty_score":0.99907655},"labels":[],"label_agreement":null},{"id":"W6996375707","doi":"","title":"Seed system security assessment: Zimbabwe","year":2009,"lang":"en","type":"report","venue":"CGSPace A Repository of Agricultural Research Outputs (Consultative Group for International Agricultural Research)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Office of U.S. Foreign Disaster Assistance; Consortium of International Agricultural Research Centers; Department for International Development; Catholic Relief Services; United States Agency for International Development","keywords":"Doors; Liberalization; Quarter (Canadian coin); Plastic bag; Clothing; Sowing","score_opus":0.05125257746646303,"score_gpt":0.4034176640157997,"score_spread":0.35216508654933665,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6996375707","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.58010197,0.0055845557,0.00024024732,0.029195305,0.0068315864,0.014051582,0.0014321237,0.00071428757,0.36184832],"genre_scores_gemma":[0.8944369,0.0013661097,0.0029888349,0.000050863426,0.0057731727,0.0008044184,0.0042738626,0.00012428185,0.090181544],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.98005635,0.0018638881,0.0019949034,0.0020056285,0.01200288,0.0020763576],"domain_scores_gemma":[0.950919,0.003960912,0.0011958862,0.0007062078,0.041975815,0.0012422337],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.010456937,0.0010126889,0.0020178757,0.0013691077,0.0015163117,0.00069060386,0.0018139848,0.0010132286,0.00004126],"category_scores_gemma":[0.018803839,0.000606168,0.001261845,0.0019404143,0.0017827498,0.00062261854,0.0008304099,0.006986932,0.000052159703],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018408041,0.0022547285,0.003631445,0.0066077914,0.004779195,0.00073562807,0.003609012,0.000057415724,0.2125158,0.014549591,0.7435754,0.005843208],"study_design_scores_gemma":[0.005959881,0.0042349645,0.69764584,0.0103075,0.0005030454,0.0024276718,0.019438181,0.0004887961,0.006572826,0.00043864007,0.25051126,0.0014713712],"about_ca_topic_score_codex":0.0021535158,"about_ca_topic_score_gemma":0.00010873188,"teacher_disagreement_score":0.69401443,"about_ca_system_score_codex":0.0072004935,"about_ca_system_score_gemma":0.0022560481,"threshold_uncertainty_score":0.9997836},"labels":[],"label_agreement":null},{"id":"W6996469575","doi":"","title":"Save an Endangered Turtle from a Canadian Wind Project","year":2015,"lang":"en","type":"other","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Endangered species; Turtle (robot); Wildlife conservation; Sea turtle","score_opus":0.020118876586141955,"score_gpt":0.3056369914225344,"score_spread":0.28551811483639244,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6996469575","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00036492108,0.0009411277,0.000040357765,0.0014224786,0.00048454068,0.00044777553,0.0001840847,0.00021887026,0.99589586],"genre_scores_gemma":[0.0015090002,0.000059550304,0.0068547754,0.0029606812,0.00231926,0.0000067924075,0.0019129365,0.00051873486,0.9838583],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99879694,0.000046613284,0.00014899169,0.00037846353,0.0002898747,0.00033910613],"domain_scores_gemma":[0.9986512,0.000016108661,0.00006714064,0.0004410685,0.000038513357,0.000785986],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00016319501,0.00023608391,0.00043693924,0.00038298956,0.000026583477,0.000033719494,0.00014445662,0.00030641817,0.010837576],"category_scores_gemma":[0.00017276696,0.00018228147,0.000056577363,0.00011603429,0.00007002482,0.000021096026,0.000021477226,0.0005549318,0.00030470933],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008848393,0.00002470922,0.00042468696,0.000021422304,0.00010550967,0.00021698601,0.00029934483,1.8457617e-7,0.000030756775,0.000022049964,0.98745435,0.011391176],"study_design_scores_gemma":[0.0007664351,0.000083513194,0.00028935453,0.00020812577,0.00011212966,0.00003500115,0.00011626804,0.0006361244,0.000004729335,0.000044822867,0.9974904,0.00021309151],"about_ca_topic_score_codex":0.80571747,"about_ca_topic_score_gemma":0.3989757,"teacher_disagreement_score":0.4067418,"about_ca_system_score_codex":0.00017673349,"about_ca_system_score_gemma":0.001542458,"threshold_uncertainty_score":0.99006665},"labels":[],"label_agreement":null},{"id":"W6996718856","doi":"","title":"Soutenir les couples porteurs de l’Ataxie récessive spastique de Charlevoix-Saguenay lors de la planification familiale : co-construction d’un outil d’aide à la décision avec les utilisateurs","year":2021,"lang":"fr","type":"other","venue":"Constellation (Université du Québec à Chicoutimi)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Ile de france; Child care; Health services; Primary health care","score_opus":0.010757134775755276,"score_gpt":0.2315587553025233,"score_spread":0.22080162052676802,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6996718856","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48031682,0.008392621,0.1869124,0.005935967,0.001078573,0.000930176,0.00014955482,0.00040191796,0.31588197],"genre_scores_gemma":[0.9390025,0.010337514,0.008200568,0.00043997815,0.0014256386,0.000009610103,0.0009886057,0.00036098168,0.03923457],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99533546,0.0013303305,0.00075357413,0.0010526151,0.0006332168,0.0008948007],"domain_scores_gemma":[0.99557906,0.0018317966,0.00096940703,0.0006190651,0.00028503913,0.000715632],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0015914636,0.00081414264,0.0010215692,0.00067586533,0.0008422101,0.00020097429,0.0004945474,0.0014121912,0.029824048],"category_scores_gemma":[0.0011642609,0.0009195897,0.00041914155,0.00042721324,0.00240751,0.00018015363,0.00014844637,0.0020186475,0.000052732266],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038417,0.0003618014,0.43402025,0.0008863019,0.0009139206,0.0016339971,0.017906256,0.009043738,0.008009888,0.004674561,0.015092628,0.5070725],"study_design_scores_gemma":[0.0059379907,0.00019251672,0.34399322,0.0045434968,0.0022624927,0.005338413,0.02989082,0.24893112,0.0015627246,0.000515215,0.3550365,0.0017955084],"about_ca_topic_score_codex":0.018924493,"about_ca_topic_score_gemma":0.002014192,"teacher_disagreement_score":0.505277,"about_ca_system_score_codex":0.0016248759,"about_ca_system_score_gemma":0.0038923107,"threshold_uncertainty_score":0.9998842},"labels":[],"label_agreement":null},{"id":"W6998571747","doi":"","title":"Assessing the Impact of Image Reconstruction and Acquisition Parameters on the Reproducibility of Radiomic Features","year":2025,"lang":"en","type":"dissertation","venue":"QSpace (Queen's University Library)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"University of Texas MD Anderson Cancer Center; Queen's University; National Institutes of Health; Memorial Sloan-Kettering Cancer Center","keywords":"Reproducibility; Feature (linguistics); Colorectal cancer; Hounsfield scale; Confidence interval; Cancer; Iterative reconstruction; Radiomics; Radiation treatment planning","score_opus":0.008082712426765185,"score_gpt":0.2658791877654226,"score_spread":0.2577964753386574,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6998571747","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97219956,0.00005965393,0.000046113713,0.020089991,0.0001867222,0.0004424292,0.000019846211,0.000042044303,0.006913645],"genre_scores_gemma":[0.9844639,0.00036375097,0.0018721195,0.00008685118,0.000053156928,8.0128643e-7,0.00022357969,0.00002238048,0.012913485],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9985034,0.00033817178,0.00021566365,0.0005669067,0.00022126248,0.00015461088],"domain_scores_gemma":[0.9980348,0.00050171185,0.00044476675,0.00086697267,0.00008220155,0.00006959422],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004131982,0.00021788235,0.0004638156,0.00028151943,0.00020733014,0.00004648078,0.000199515,0.00018517407,0.00008756977],"category_scores_gemma":[0.00058470835,0.00013825914,0.000283284,0.00037519867,0.00032591887,0.00039472972,0.000053223226,0.00079459825,4.6279192e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.01213984,0.0013232847,0.35671604,0.007431384,0.0060476917,0.00040535725,0.013149463,0.0009464781,0.020591715,0.0060155187,0.46577758,0.109455675],"study_design_scores_gemma":[0.0010161451,0.0003767677,0.970006,0.002164875,0.00070959784,0.000013870019,0.005995709,0.0004201953,0.017963994,0.0008331457,0.00022579118,0.0002739416],"about_ca_topic_score_codex":0.003348004,"about_ca_topic_score_gemma":0.000002822705,"teacher_disagreement_score":0.61328995,"about_ca_system_score_codex":0.000095671516,"about_ca_system_score_gemma":0.00040805436,"threshold_uncertainty_score":0.56380445},"labels":[],"label_agreement":null},{"id":"W7001258144","doi":"","title":"Issue 14 - Winter 2003 (1.52Mb)","year":2008,"lang":"en","type":"other","venue":"Lenus, The Irish Health Repository (Dr Steevens Hospital Library)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Hospital for Sick Children; North Dakota Soybean Council","keywords":"Natural (archaeology); Government (linguistics); Context (archaeology); Work (physics)","score_opus":0.008415892909545954,"score_gpt":0.2669992552460538,"score_spread":0.2585833623365078,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7001258144","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006587158,0.03431643,0.0001379817,0.06753172,0.010930898,0.0023631258,0.00006888361,0.001281749,0.8827105],"genre_scores_gemma":[0.0009014636,0.004382548,0.0020685168,0.016143002,0.008024534,0.00007634362,0.00021969421,0.001336674,0.96684724],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9955906,0.00038917756,0.0010269786,0.0010189594,0.0008909794,0.0010832822],"domain_scores_gemma":[0.99646854,0.00010761258,0.00093201466,0.0015943998,0.00007130395,0.0008261093],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00026537027,0.0007885034,0.0013624763,0.00032677708,0.00047236212,0.00013926592,0.00075980654,0.00062690297,0.0013795411],"category_scores_gemma":[0.00017589264,0.0005797339,0.0003768808,0.00055383024,0.00055643456,0.00022141237,0.0002778401,0.0025611073,0.0005417942],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049411916,0.00023405674,0.0041726846,0.0006412238,0.00026163796,0.0008428219,0.00046156658,0.000001588912,0.00000406659,0.000033682783,0.98836035,0.004936895],"study_design_scores_gemma":[0.0010042246,0.0007974264,0.0030787725,0.0019791294,0.00011038641,0.0007123355,0.00008451647,0.000102639126,0.00003223692,0.000011416736,0.9915293,0.0005576221],"about_ca_topic_score_codex":0.00069262803,"about_ca_topic_score_gemma":0.0000030758679,"teacher_disagreement_score":0.08413673,"about_ca_system_score_codex":0.00016143375,"about_ca_system_score_gemma":0.0011992555,"threshold_uncertainty_score":0.99974},"labels":[],"label_agreement":null},{"id":"W7019160495","doi":"","title":"Extraction et analyse des caractéristiques de l’image dans le cadre de la méthode radiomique appliqué à la prédiction de la radiothérapie","year":2022,"lang":"en","type":"article","venue":"theses.fr (ABES)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Région Bretagne; Canadian Institute for Advanced Research; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Digital pattern generator; Feature matching; Radiomics","score_opus":0.012740441907731537,"score_gpt":0.33316451994894125,"score_spread":0.3204240780412097,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7019160495","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.67179626,0.00049996667,0.2757097,0.0012326515,0.00006728852,0.00026801048,0.000014438515,0.00030433162,0.050107397],"genre_scores_gemma":[0.95299864,0.0009766498,0.04443903,0.00074278156,0.0002998092,0.00014863805,0.000050697396,0.00010080634,0.0002429344],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9953515,0.0030531792,0.0003387406,0.00039189841,0.00034825903,0.0005164562],"domain_scores_gemma":[0.9975982,0.0014732338,0.00018485573,0.00036731616,0.000048508864,0.00032792042],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0061939154,0.00026822856,0.00042920947,0.00024676745,0.00046840924,0.00013456562,0.00024375756,0.0002034455,0.00019276544],"category_scores_gemma":[0.0012589028,0.0002688228,0.00019665249,0.00033316793,0.00052275666,0.00020359133,0.00009264946,0.0018901645,0.000004338235],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00057399436,0.0012548905,0.09946238,0.00035464636,0.0005484294,0.002131784,0.02509872,0.007897562,0.7874276,0.031026633,0.0036347706,0.040588573],"study_design_scores_gemma":[0.008162883,0.00071190466,0.37065598,0.00056460575,0.0017115077,0.02611854,0.02220019,0.24703455,0.072932914,0.025317857,0.22303495,0.0015541164],"about_ca_topic_score_codex":0.010981701,"about_ca_topic_score_gemma":0.000043301465,"teacher_disagreement_score":0.7144947,"about_ca_system_score_codex":0.0010328075,"about_ca_system_score_gemma":0.0006656966,"threshold_uncertainty_score":0.9999764},"labels":[],"label_agreement":null},{"id":"W7025061563","doi":"","title":"Table ronde de Montréal, procès-verbaux / proceedings. Comment concilier le tourisme et la conservation des sites du&#13;\\npatrimoine mondial?","year":2017,"lang":"fr","type":"other","venue":"Papyrus : Institutional Repository (Université de Montréal)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Table (database); Context (archaeology); Tourism; Nature tourism","score_opus":0.006235340752074174,"score_gpt":0.2024359602255699,"score_spread":0.1962006194734957,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7025061563","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32093439,0.08165535,0.0044171805,0.028611518,0.0014190364,0.0018489959,0.0001408299,0.00042841354,0.5605443],"genre_scores_gemma":[0.36102125,0.010554908,0.005959743,0.0029954463,0.0016517945,0.00009345509,0.00035066693,0.0002602429,0.61711246],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9965214,0.00024720092,0.0005486507,0.0008655455,0.00087627966,0.00094093865],"domain_scores_gemma":[0.99708146,0.00025420415,0.00087336486,0.0005102951,0.00044317954,0.0008374758],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0010830713,0.0007499617,0.00092695956,0.00043580463,0.006219547,0.00026009564,0.0006450397,0.00074164214,0.00032173004],"category_scores_gemma":[0.00095424376,0.00079966785,0.00034064823,0.00028946958,0.0014610885,0.00057607406,0.00044940604,0.0013141172,0.00007617458],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018203693,0.0016063706,0.43618837,0.0025072722,0.002508076,0.011670366,0.045460314,0.00249772,0.039846156,0.05467394,0.37063038,0.030590666],"study_design_scores_gemma":[0.0043751616,0.00025554138,0.03662132,0.0019466463,0.00082667836,0.0023675424,0.0040992345,0.025414983,0.0011290055,0.00043998417,0.9217594,0.0007644807],"about_ca_topic_score_codex":0.15059783,"about_ca_topic_score_gemma":0.007912423,"teacher_disagreement_score":0.55112904,"about_ca_system_score_codex":0.0063294102,"about_ca_system_score_gemma":0.0042614196,"threshold_uncertainty_score":0.99944544},"labels":[],"label_agreement":null},{"id":"W7033677519","doi":"","title":"The Relationship Between Social Isolation and Cognitive Frailty Among Community-Dwelling Older Adults: The Mediating Role of Depressive Symptoms","year":2024,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Social isolation; Logistic regression; Depressive symptoms; Geriatric Depression Scale; Cognition; Dementia; Depression (economics); Association (psychology); Clinical Dementia Rating","score_opus":0.12885674156450544,"score_gpt":0.5164613556184641,"score_spread":0.38760461405395863,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7033677519","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97509664,0.02068412,0.001688716,0.0007691376,0.0001697147,0.0004915056,0.000025558556,0.000029420835,0.0010451913],"genre_scores_gemma":[0.9983495,0.0009220337,0.00005159873,0.00011790063,0.00041079315,0.000025513584,0.0000390549,0.000039475257,0.000044140976],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9975585,0.00076815754,0.0006907042,0.00020261067,0.00054681225,0.00023324322],"domain_scores_gemma":[0.9898064,0.009013434,0.0005960636,0.0002023022,0.0002530655,0.00012871457],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028079187,0.00018432159,0.00044395353,0.00024351991,0.0012268292,0.0006552832,0.00068512204,0.00011257416,0.00013568603],"category_scores_gemma":[0.003613493,0.00011618403,0.00012965118,0.0005190615,0.00049598404,0.0007102375,0.0004086947,0.001878498,0.0000013648212],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006430326,0.00003114223,0.9095083,0.00014481085,0.00029192428,0.00000442235,0.0058651273,0.000021036598,0.00079454965,0.00012244786,0.00036095022,0.082791],"study_design_scores_gemma":[0.0005465249,0.000011049871,0.9826375,0.0025140457,0.00040793698,0.000008112455,0.0022234432,0.0062510157,0.0006408932,0.0044596447,0.0001758451,0.0001239811],"about_ca_topic_score_codex":0.00080630777,"about_ca_topic_score_gemma":0.000020082392,"teacher_disagreement_score":0.082667015,"about_ca_system_score_codex":0.00004040114,"about_ca_system_score_gemma":0.00009761899,"threshold_uncertainty_score":0.9435903},"labels":[],"label_agreement":null},{"id":"W7039462501","doi":"","title":"Multifuntional house","year":2015,"lang":"cs","type":"dissertation","venue":"Brno University of Technology Digital Library (Brno University of Technology)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Work (physics); Telithromycin; Quarter (Canadian coin)","score_opus":0.005672259753494408,"score_gpt":0.20476393928268533,"score_spread":0.1990916795291909,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7039462501","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9552722,0.002424172,0.00071016577,0.010772838,0.0005694502,0.0009932114,0.0015552425,0.0028691462,0.0248336],"genre_scores_gemma":[0.92844576,0.0025882206,0.01985561,0.00006750241,0.00009060197,2.6605517e-7,0.002947319,0.00022441344,0.045780342],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9962842,0.000057992263,0.00066441396,0.0013066982,0.0008001972,0.0008865224],"domain_scores_gemma":[0.9959689,0.00012344989,0.0015181173,0.0013431702,0.00062184496,0.00042452876],"candidate_categories":["metaepi_narrow","sts","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.00019395862,0.0008238202,0.0019321884,0.0051988917,0.00046585882,0.000036841495,0.0029867936,0.003474735,0.00069753366],"category_scores_gemma":[0.0005235757,0.0011095145,0.0007112767,0.002935223,0.0048568733,0.0014236773,0.0016399678,0.002759594,0.00036708327],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0073784813,0.0059644757,0.37680483,0.0035621885,0.006547877,0.0080438,0.0021445625,0.00022895426,0.0072001885,0.04392093,0.12180855,0.4163952],"study_design_scores_gemma":[0.01817564,0.0035604476,0.017571144,0.00611608,0.0032135143,0.0005556187,0.08948306,0.0029516185,0.003756488,0.016440585,0.8351261,0.003049723],"about_ca_topic_score_codex":0.00019122344,"about_ca_topic_score_gemma":0.000026764828,"teacher_disagreement_score":0.7133175,"about_ca_system_score_codex":0.00026031342,"about_ca_system_score_gemma":0.0014314894,"threshold_uncertainty_score":0.9995411},"labels":[],"label_agreement":null},{"id":"W7044131410","doi":"","title":"The use of radiomics and natural language processing to detect pain in the simulation-CT images of patients undergoing radiotherapy for bone metastasis","year":2023,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"McGill University Health Centre; Natural Sciences and Engineering Research Council of Canada; Mitacs; McGill University","keywords":"Radiomics; Radiation therapy; Bone metastasis; Metastasis; Medical imaging","score_opus":0.017643165449757095,"score_gpt":0.3028046881646337,"score_spread":0.2851615227148766,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7044131410","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9956705,0.0022452858,0.000028297785,0.000110716355,0.00024983837,0.0014321548,0.00018119166,0.00004121574,0.00004079287],"genre_scores_gemma":[0.9921462,0.00043134263,0.00609067,0.00037178522,0.00003537366,0.00008541031,0.0003541246,0.00012904537,0.00035605562],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997388,0.00043012525,0.0008025247,0.0004332101,0.00057283987,0.00037329172],"domain_scores_gemma":[0.994683,0.0040376186,0.00055095943,0.00036347078,0.00026190112,0.00010303623],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002573201,0.0003420916,0.00067821826,0.00037391038,0.00043856047,0.00008080356,0.00025731733,0.00012378681,0.0000025626089],"category_scores_gemma":[0.010044157,0.00023136556,0.00021255076,0.00058388023,0.00007993772,0.00020687835,0.000035038673,0.00081109314,4.861333e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00065986114,0.00006920806,0.0004597234,0.0011412818,0.00020360203,0.000018773635,0.00020347536,0.0014704256,0.008176451,0.00014289748,0.000010098637,0.9874442],"study_design_scores_gemma":[0.0532014,0.009117484,0.22412613,0.027335837,0.0067662103,0.00019033022,0.026627846,0.4043575,0.09691239,0.008337792,0.13564946,0.007377622],"about_ca_topic_score_codex":0.00018470839,"about_ca_topic_score_gemma":0.0003883648,"teacher_disagreement_score":0.9800666,"about_ca_system_score_codex":0.00017571912,"about_ca_system_score_gemma":0.00006216128,"threshold_uncertainty_score":0.99829465},"labels":[],"label_agreement":null},{"id":"W7067469207","doi":"","title":"A network linear block coding approach to selective detect-and-forward multi-way relaying","year":2019,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Decoding methods; Relay; Linear network coding; Code word; Pairwise error probability; Block code; Binary number; Coding gain; Hamming code; Parity bit","score_opus":0.017696332834197765,"score_gpt":0.2733179850059611,"score_spread":0.25562165217176336,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7067469207","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8198074,0.0011407225,0.00013300955,0.00011314856,0.0024334844,0.003446166,0.00014394047,0.00069994864,0.17208216],"genre_scores_gemma":[0.92987686,0.000297198,0.046433944,0.0020203136,0.0003999931,0.00021484907,0.00047392867,0.0004852526,0.019797657],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99470115,0.0003401118,0.001031327,0.001703235,0.00097339036,0.0012507627],"domain_scores_gemma":[0.9968559,0.00040879403,0.0005553296,0.00075681246,0.0004637848,0.00095933955],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0017101127,0.0009857,0.0015798961,0.00056673837,0.0011407607,0.00010144972,0.0004462132,0.0010152556,0.000045173943],"category_scores_gemma":[0.0028980398,0.00096764776,0.00041170092,0.0009664229,0.000068294285,0.00025856827,0.00020774611,0.0048479857,0.00018521324],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005606522,0.0014746658,0.002817714,0.009560553,0.0050592,0.0007629984,0.00077157654,0.012492645,0.12345145,0.025547763,0.0008532379,0.8116017],"study_design_scores_gemma":[0.04466179,0.006531413,0.039771177,0.030822726,0.012816027,0.0041359835,0.0067061237,0.22331865,0.05775885,0.008338745,0.5458026,0.01933594],"about_ca_topic_score_codex":0.00019859937,"about_ca_topic_score_gemma":0.000040596533,"teacher_disagreement_score":0.7922657,"about_ca_system_score_codex":0.00070698594,"about_ca_system_score_gemma":0.0001152996,"threshold_uncertainty_score":0.9992774},"labels":[],"label_agreement":null},{"id":"W7084109037","doi":"10.5281/zenodo.17242616","title":"CANADA 🇨🇦, AUSTRALIA 🇦🇺,UK 🇬🇧 WORK VISAS AVAILABLE CALL OR WHATSAPP MR PETER OBENDE ON ☎(08143870581).","year":2025,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Work (physics)","score_opus":0.030863036772796826,"score_gpt":0.27534964821156666,"score_spread":0.24448661143876982,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7084109037","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00015847303,0.0001747325,0.00034075184,0.0024384214,0.0005293396,0.00068554166,0.00026696967,0.0006519504,0.99475384],"genre_scores_gemma":[0.005419456,0.0002381392,0.0004744832,0.0020487614,0.00064008596,1.17575645e-7,0.0019765238,0.0042844987,0.98491794],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972739,0.00023642958,0.00035484976,0.000728674,0.00077763473,0.00062848214],"domain_scores_gemma":[0.99825555,0.0000502578,0.00018153773,0.0007958368,0.00026272004,0.00045407715],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00044115054,0.00036503837,0.00047606067,0.00042821403,0.0006586246,0.00044341423,0.00080754474,0.00021781391,0.26888382],"category_scores_gemma":[0.0013353422,0.00031740425,0.000092326954,0.00057293725,0.00016938032,0.000042837997,0.00056349265,0.0012032872,0.014991962],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016976865,0.000085339336,0.00001686294,0.00027159092,0.00017586225,0.00027802738,0.000049821723,0.000011160221,0.0000750632,0.00031703364,0.98499846,0.013550987],"study_design_scores_gemma":[0.0009351569,0.0002138849,0.00015771406,0.00097215164,0.00009206853,0.000092833776,0.000023926053,0.00009639118,0.000034526623,0.000007452417,0.9970711,0.00030281488],"about_ca_topic_score_codex":0.031272434,"about_ca_topic_score_gemma":0.00069128745,"teacher_disagreement_score":0.25389186,"about_ca_system_score_codex":0.00051306654,"about_ca_system_score_gemma":0.00011347288,"threshold_uncertainty_score":0.9999278},"labels":[],"label_agreement":null},{"id":"W7095558034","doi":"","title":"Features Associated with Survival Systematic Analysis of Breast Cancer Morphology Uncovers Stromal Editor&amp;apos;s Summary","year":2014,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Stromal cell; Breast cancer; Cancer; Lymph node; Stroma; Set (abstract data type); Scoring system","score_opus":0.016261905316655157,"score_gpt":0.3109212302517489,"score_spread":0.2946593249350937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7095558034","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9879707,0.00014472991,0.0031113853,0.0021820916,0.0015119051,0.00030414332,0.000060588238,0.00010215213,0.0046123024],"genre_scores_gemma":[0.99559635,0.00001659715,0.00049742666,0.00048928056,0.00068653206,0.000013126793,0.00015137736,0.0000253281,0.0025239957],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.998294,0.00024558758,0.00035771984,0.00027000642,0.00054870156,0.00028401846],"domain_scores_gemma":[0.9984774,0.0005580458,0.00026780085,0.00032058547,0.00020006743,0.00017607251],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00078534544,0.00018047243,0.0010790597,0.0002934173,0.000050932915,0.000016447686,0.0001295374,0.000119449796,0.00028931376],"category_scores_gemma":[0.0007037446,0.00011516706,0.00018529328,0.00067434396,0.00015025082,0.00004423328,0.000032240023,0.00034516052,0.000003080418],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041379777,0.00035295245,0.93646014,0.0031501022,0.013335376,0.000038823335,0.00032339734,0.004141778,0.0044103065,0.00055625156,0.036329076,0.0004879755],"study_design_scores_gemma":[0.0030623125,0.00030855666,0.95986736,0.003246661,0.01322146,0.000073661795,0.00032971913,0.01909274,0.00006627938,0.00001572545,0.00036304083,0.00035248016],"about_ca_topic_score_codex":0.0022139165,"about_ca_topic_score_gemma":0.00074921065,"teacher_disagreement_score":0.035966035,"about_ca_system_score_codex":0.00010811855,"about_ca_system_score_gemma":0.00009588596,"threshold_uncertainty_score":0.46963763},"labels":[],"label_agreement":null},{"id":"W7099377087","doi":"","title":"Acquisitions et services bibliographiques","year":2014,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Interface (matter); User interface; Reproduction; Control (management); Subject (documents)","score_opus":0.00704127080091889,"score_gpt":0.3069617331105341,"score_spread":0.2999204623096152,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7099377087","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48420092,0.00019306706,0.05322338,0.04713447,0.00017637145,0.00014809956,0.0000011949274,0.0005168063,0.4144057],"genre_scores_gemma":[0.95749503,0.00014215296,0.012067129,0.029328218,0.00014746828,0.0000043723176,0.00001967407,0.000011379814,0.0007845728],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9995229,0.000032521835,0.00009337075,0.000113252885,0.00012357469,0.00011436145],"domain_scores_gemma":[0.999623,0.000055049655,0.000019952555,0.00014616137,0.000038227037,0.00011763579],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028011287,0.000058656453,0.00010897515,0.00051473174,0.000044157634,0.000031770087,0.000050316103,0.000029442668,0.0004071055],"category_scores_gemma":[0.000034899997,0.000042431133,0.00005713928,0.00053097826,0.000038271148,0.000060211274,0.00002072871,0.00014483005,0.000054263473],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000706729,0.00048492153,0.50977224,0.0005516288,0.00022988213,0.000041649364,0.0007734432,0.000061111954,0.020676045,0.29123867,0.08925706,0.086842686],"study_design_scores_gemma":[0.0018438533,0.0003750785,0.39509386,0.00030682745,0.00013136705,0.00018612732,0.00016739649,0.05826969,0.00080307084,0.016193807,0.5263418,0.00028715853],"about_ca_topic_score_codex":0.0001317118,"about_ca_topic_score_gemma":0.0000071414406,"teacher_disagreement_score":0.4732941,"about_ca_system_score_codex":0.0000033577608,"about_ca_system_score_gemma":0.00000805446,"threshold_uncertainty_score":0.44575197},"labels":[],"label_agreement":null},{"id":"W7115039004","doi":"","title":"Predictive models and biomarkers for early stage and oligometastatic non-small cell lung cancer patients treated with stereotactic body radiation therapy, using machine learning","year":2024,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Jewish General Hospital","keywords":"Stage (stratigraphy); Lung cancer; Radiation therapy; SABR volatility model; Cancer","score_opus":0.012375819386007665,"score_gpt":0.26830873874482325,"score_spread":0.25593291935881557,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7115039004","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99206096,0.0031081766,0.000019181098,0.00001426775,0.00030372918,0.0024846178,0.00073188875,0.00013807142,0.0011391165],"genre_scores_gemma":[0.99226063,0.0023758882,0.0009096794,0.00010321194,0.000046857844,0.00025626508,0.0015254673,0.00034163543,0.0021803821],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99695635,0.00020365707,0.0006289506,0.001081757,0.0005408281,0.00058848347],"domain_scores_gemma":[0.9981482,0.00027379105,0.0005687453,0.00024876185,0.00033597933,0.00042449016],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005540022,0.0007448946,0.0008929952,0.0006541229,0.0006501083,0.0001836711,0.00012809568,0.0003528188,0.000018004244],"category_scores_gemma":[0.00019439872,0.00062860484,0.0001528956,0.0004133385,0.00007745744,0.0005011221,0.000050101957,0.0015424548,0.0000012237248],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.026085762,0.0023313605,0.41042665,0.03617389,0.019507322,0.00071741274,0.0028977955,0.005450953,0.09699265,0.0009216589,0.000012981169,0.39848158],"study_design_scores_gemma":[0.019991262,0.0042635323,0.063788205,0.0057233567,0.007052562,0.000056032764,0.00056567707,0.8846106,0.009810446,0.0004984977,0.0015256748,0.002114155],"about_ca_topic_score_codex":0.002494659,"about_ca_topic_score_gemma":0.00012813052,"teacher_disagreement_score":0.8791596,"about_ca_system_score_codex":0.00050790614,"about_ca_system_score_gemma":0.00011410646,"threshold_uncertainty_score":0.9996165},"labels":[],"label_agreement":null},{"id":"W7115825032","doi":"","title":"AN INVESTIGATION OF AUTOMATED MODELS FOR TUMOR SEGMENTATION","year":2024,"lang":"en","type":"dissertation","venue":"MacSphere (McMaster University)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Hamilton Health Sciences","keywords":"Lung cancer; Segmentation; Focus (optics); Lesion; Pattern recognition (psychology); Melanoma; Image segmentation; Artificial neural network","score_opus":0.013340346967567057,"score_gpt":0.26537568483066276,"score_spread":0.25203533786309573,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7115825032","genre_codex":"empirical","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8394636,0.00039720768,0.008717269,0.00042379173,0.0013473479,0.0021647152,0.000104456674,0.0010864196,0.1462952],"genre_scores_gemma":[0.3372798,0.00006119719,0.029750273,0.00040050666,0.0003316765,0.000013421692,0.0065769283,0.0002151852,0.625371],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99894536,0.00004692303,0.00024701993,0.0003585277,0.00023257815,0.00016961525],"domain_scores_gemma":[0.99927706,0.00003843403,0.00020374675,0.00016717742,0.00016287647,0.00015073604],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00012257186,0.00020672467,0.00035090913,0.000298568,0.000059641603,0.000031672713,0.00013206677,0.00016295089,0.0020828298],"category_scores_gemma":[0.000017572835,0.00021509829,0.00013913657,0.00032466947,0.000047737845,0.00020841464,0.00001364201,0.00028923893,0.000007486047],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0037685502,0.0004161484,0.00299163,0.02052499,0.0017169775,0.0004962302,0.026809225,0.012357131,0.22592233,0.011973775,0.011884768,0.6811383],"study_design_scores_gemma":[0.0024191756,0.00057326857,0.001081821,0.001727529,0.0014673749,0.000017789796,0.009365518,0.9646219,0.0072607114,0.0014580007,0.009600518,0.00040641657],"about_ca_topic_score_codex":0.00012838903,"about_ca_topic_score_gemma":0.000053518244,"teacher_disagreement_score":0.9522647,"about_ca_system_score_codex":0.00013111357,"about_ca_system_score_gemma":0.00022197333,"threshold_uncertainty_score":0.9988294},"labels":[],"label_agreement":null},{"id":"W7116852604","doi":"10.1088/1361-6560/ae3047","title":"Deep learning-based prediction of dynamic blood dose estimates for head-and-neck cancer","year":2025,"lang":"en","type":"article","venue":"Physics in Medicine and Biology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Laurentian University; TRIUMF","funders":"","keywords":"Radiation therapy; Ground truth; Radiation treatment planning; Blood flow; Standard deviation; Histogram","score_opus":0.045519855117165525,"score_gpt":0.3944337208277837,"score_spread":0.3489138657106182,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7116852604","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9477099,0.007457336,0.03566041,0.008171005,0.00025357693,0.00039158508,0.0000071815502,0.00003737639,0.000311611],"genre_scores_gemma":[0.9954352,0.0011232028,0.002221385,0.00089776557,0.0001296654,0.00004792755,0.00008327417,0.000009609971,0.0000520056],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992717,0.000032539014,0.00024981252,0.00022819544,0.00004948724,0.00016825183],"domain_scores_gemma":[0.9993438,0.00037636963,0.00007835682,0.00008822149,0.00006118678,0.0000520727],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026129925,0.00011402625,0.0004266773,0.00012090234,0.000047957314,0.0000022710492,0.000040775794,0.00008147557,0.00000779291],"category_scores_gemma":[0.0005120839,0.00008283787,0.000030615385,0.00015994166,0.00035706535,0.000015949574,0.000023164828,0.00028539577,8.859815e-8],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038098847,0.00025382973,0.6575247,0.0011203185,0.00022531854,0.0000047813455,0.00040055224,0.000826173,0.037469182,0.0040283385,0.00014952425,0.29761627],"study_design_scores_gemma":[0.010674566,0.0017070592,0.14529572,0.0014900371,0.0005716553,0.000009107021,0.00013979312,0.8270084,0.00065437105,0.010527865,0.0018039312,0.000117466356],"about_ca_topic_score_codex":0.00021471709,"about_ca_topic_score_gemma":0.000018075141,"teacher_disagreement_score":0.82618225,"about_ca_system_score_codex":0.000017587248,"about_ca_system_score_gemma":0.00005381562,"threshold_uncertainty_score":0.33780304},"labels":[],"label_agreement":null},{"id":"W7117116225","doi":"10.1159/000550231","title":"Investigating Alzheimer’s Disease Progression Using a Radiomics Approach: The Hippocampal-Amygdala Border in FDG-Positron Emission Tomography Scans","year":2025,"lang":"en","type":"article","venue":"Neurodegenerative Diseases","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Eisai; Northern California Institute for Research and Education; Pfizer; Novartis Pharmaceuticals Corporation; University of Southern California; Biogen; Boğaziçi Üniversitesi; Eli Lilly and Company; Bristol-Myers Squibb; BioClinica; U.S. Department of Defense; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; Alzheimer's Association","keywords":"Radiomics; Workflow; Disease; Medical imaging; Computed tomography; Positron emission tomography","score_opus":0.02208247817272711,"score_gpt":0.3444605768812116,"score_spread":0.3223780987084845,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117116225","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.981578,0.008806256,0.0031382947,0.0043126955,0.0002916718,0.0011156162,0.00002501956,0.000115395436,0.00061706436],"genre_scores_gemma":[0.9922296,0.00010856944,0.003337804,0.0036911445,0.00023698367,0.00012345475,0.00013275632,0.000049997452,0.00008971714],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99749523,0.000477719,0.00044223233,0.00067414064,0.00045181173,0.00045883414],"domain_scores_gemma":[0.9985994,0.00017606291,0.00015359797,0.00048165245,0.00010653896,0.0004827328],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027573918,0.00035332027,0.00041501957,0.00034113927,0.000465407,0.000121354664,0.00024029303,0.00007443021,0.000013594506],"category_scores_gemma":[0.0008570281,0.00024152469,0.00021707709,0.0010184488,0.00042477867,0.00014422383,0.00014360255,0.0006371905,8.332969e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003869784,0.0009302483,0.925852,0.00029432858,0.00017272163,0.00009746243,0.0007253303,0.010594138,0.022894993,0.00083402783,0.0024041063,0.03481366],"study_design_scores_gemma":[0.0025147614,0.00011178883,0.34027216,0.001247936,0.0010621833,0.000018894947,0.00030312984,0.64949554,0.0028067252,0.0005851881,0.001157095,0.00042456837],"about_ca_topic_score_codex":0.000051535255,"about_ca_topic_score_gemma":0.0000017343211,"teacher_disagreement_score":0.6389014,"about_ca_system_score_codex":0.00007742141,"about_ca_system_score_gemma":0.0005210484,"threshold_uncertainty_score":0.98490906},"labels":[],"label_agreement":null},{"id":"W7117476274","doi":"10.21608/ijicis.2025.422365.1426","title":"Integrative Radio-Genomic Analysis of Lung Adenocarcinoma: Linking Imaging Features and Gene Expression Profiles for Tumor Classification","year":2025,"lang":"en","type":"article","venue":"International journal of intelligent computing and information sciences/International Journal of Intelligent Computing and Information Sciences","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre for Innovation Studies","funders":"","keywords":"Discriminative model; Transcriptome; Radiogenomics; Molecular imaging; Identification (biology); Radiomics; Gene; Adenocarcinoma","score_opus":0.015090775078392852,"score_gpt":0.34456958062843146,"score_spread":0.3294788055500386,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117476274","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46931404,0.0012348869,0.5247554,0.0026170823,0.0014648252,0.00019234639,0.000013037529,0.000011459113,0.00039691062],"genre_scores_gemma":[0.97392577,0.0010705786,0.023605838,0.0011109435,0.000244135,0.0000010585668,0.000027909264,0.000004422092,0.00000932226],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99578166,0.00009757397,0.0023794938,0.00018989878,0.0013201989,0.00023118164],"domain_scores_gemma":[0.99224144,0.00077580137,0.0031661086,0.00008711633,0.0035719771,0.00015753809],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00440023,0.00023466468,0.00057652354,0.0035120253,0.00035723587,0.0007759828,0.00073766196,0.00006728763,0.0000089079585],"category_scores_gemma":[0.0017308781,0.00017146788,0.000268921,0.0007727051,0.00062900066,0.0030685277,0.00022939738,0.00043386806,5.052918e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00101219,0.00021293153,0.31478062,0.00030069394,0.0025001545,0.000013366,0.020837413,0.059734013,0.0044797845,0.02107043,0.0015514836,0.57350695],"study_design_scores_gemma":[0.0011125742,0.00035559933,0.05960659,0.0016721361,0.00032871743,0.00096812233,0.008652164,0.9171097,0.007536835,0.0004501352,0.0020046295,0.000202782],"about_ca_topic_score_codex":0.000045106706,"about_ca_topic_score_gemma":9.253282e-7,"teacher_disagreement_score":0.8573757,"about_ca_system_score_codex":0.0002001925,"about_ca_system_score_gemma":0.00046552112,"threshold_uncertainty_score":0.748282},"labels":[],"label_agreement":null},{"id":"W7118052248","doi":"","title":"Towards Interpretable AI in Personalized Medicine: A Radiological-Biological Radiomics Dictionary Connecting Semantic Lung-RADS and imaging Radiomics Features; Dictionary LC 1.0","year":2025,"lang":"","type":"article","venue":"ArXiv.org","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Radiomics; Feature selection; Preprocessor; Margin (machine learning); Feature (linguistics); Pattern recognition (psychology); Semantics (computer science)","score_opus":0.01498240954740616,"score_gpt":0.3073746809023965,"score_spread":0.29239227135499035,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7118052248","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83767337,0.08508292,0.020525131,0.04599511,0.004223577,0.0013588443,0.000022139484,0.0003603716,0.004758517],"genre_scores_gemma":[0.9603575,0.019724064,0.0008256749,0.015802091,0.0016908097,0.00008699553,0.00018736202,0.000122043435,0.0012034486],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.991891,0.0012094512,0.0021398251,0.0022887653,0.00070008676,0.001770863],"domain_scores_gemma":[0.9957044,0.001772242,0.00056965573,0.00088602223,0.00027244588,0.00079522294],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0037146516,0.0012721973,0.0026514821,0.0012672909,0.0009827205,0.00015908449,0.0007906732,0.0008900633,0.00053775316],"category_scores_gemma":[0.0066152853,0.0010653234,0.00049763115,0.001830827,0.0026324503,0.00048090785,0.0007860453,0.005035721,0.000018043362],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017393898,0.0005214204,0.937307,0.000872366,0.00093345705,0.001338753,0.0037953665,0.0002678795,0.010393479,0.0040622973,0.009483661,0.029284922],"study_design_scores_gemma":[0.012453534,0.0005753465,0.68293417,0.005908551,0.0011166177,0.0030236295,0.004187997,0.27357587,0.00007739602,0.0017530617,0.013224929,0.0011689184],"about_ca_topic_score_codex":0.00059564435,"about_ca_topic_score_gemma":0.0000071309532,"teacher_disagreement_score":0.27330798,"about_ca_system_score_codex":0.0011510464,"about_ca_system_score_gemma":0.00062188314,"threshold_uncertainty_score":0.9991797},"labels":[],"label_agreement":null},{"id":"W7124133111","doi":"10.2196/preprints.78338","title":"Nomograms Based on X-Ray Radiomics for Predicting Pain Progression in Knee Osteoarthritis Using Data From the Foundation for the National Institutes of Health: Development and Validation Study (Preprint)","year":2025,"lang":"","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Osteoarthritis; Nomogram; Radiomics; Logistic regression; Receiver operating characteristic; Stage (stratigraphy); Clinical trial","score_opus":0.06937898031965231,"score_gpt":0.38178772343076234,"score_spread":0.31240874311111,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7124133111","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37775722,0.0007637673,0.60438514,0.008116793,0.0007142762,0.008170686,0.000041446387,0.000021159236,0.00002948998],"genre_scores_gemma":[0.9399885,0.000035861063,0.057231184,0.0013139602,0.00024286847,0.00037296215,0.00077697425,0.000022058357,0.000015629354],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99665505,0.00059718726,0.0012288245,0.00065796764,0.000560984,0.0003000036],"domain_scores_gemma":[0.99137914,0.0073273988,0.00052938727,0.0004630938,0.00024105365,0.000059926067],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.016301727,0.00023039883,0.0004278474,0.00019254842,0.0008188377,0.00015732241,0.0003558502,0.00008602183,0.000010611052],"category_scores_gemma":[0.009807334,0.000152085,0.00005037741,0.00034881802,0.00017489908,0.00018202908,0.00021234472,0.00035915282,2.1049509e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004642777,0.00057445146,0.15220237,0.00029087497,0.00013846174,3.4838612e-7,0.001877523,0.011992404,0.00011985764,0.0001277401,0.00011061163,0.8321011],"study_design_scores_gemma":[0.007106193,0.0006896316,0.040111646,0.0029270016,0.000118514385,5.6322233e-7,0.0027134323,0.94186383,0.00012337614,0.00014720396,0.004077917,0.00012066531],"about_ca_topic_score_codex":0.00050333,"about_ca_topic_score_gemma":0.0001813786,"teacher_disagreement_score":0.92987144,"about_ca_system_score_codex":0.00030623112,"about_ca_system_score_gemma":0.0014454885,"threshold_uncertainty_score":0.9985335},"labels":[],"label_agreement":null},{"id":"W7125587229","doi":"10.1109/ssitcon66133.2025.11341919","title":"R-Movignet: A Radiomics-MobileViT Framework with Gated Dilated Convolution for Liver Tumor Segmentation and Characterization","year":2025,"lang":"","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Segmentation; Convolution (computer science); Pattern recognition (psychology); Image segmentation; Feature (linguistics); Image processing","score_opus":0.006432809028758823,"score_gpt":0.2687969528942043,"score_spread":0.2623641438654455,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7125587229","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41155076,0.0010481488,0.58080536,0.0030500295,0.00060466595,0.0024607705,0.000030570176,0.00011884246,0.00033085508],"genre_scores_gemma":[0.964509,0.0016010482,0.022924384,0.005259131,0.00036653204,0.00015351057,0.0009152732,0.00007771854,0.0041933814],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976489,0.00013613216,0.00068229425,0.0007311219,0.00027960827,0.00052194216],"domain_scores_gemma":[0.9983425,0.00044092725,0.00034263908,0.00030010057,0.00031617942,0.00025764006],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005974049,0.00041463514,0.0006465175,0.00035539063,0.0003732682,0.00018786074,0.0001125602,0.00025583588,0.0003038255],"category_scores_gemma":[0.0005105358,0.00035131187,0.00008683936,0.00066849694,0.00033904988,0.00027191383,0.000053974512,0.00059957267,0.000009970653],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.010100616,0.001344728,0.07833365,0.006714544,0.0027525276,0.00016290939,0.0056174444,0.00043103442,0.43097186,0.033287123,0.0027486163,0.42753494],"study_design_scores_gemma":[0.011047091,0.0013215529,0.04820249,0.0041656336,0.0016967106,0.00010428584,0.0005635715,0.9158447,0.0071442635,0.00058364676,0.008694105,0.00063198415],"about_ca_topic_score_codex":0.00010680145,"about_ca_topic_score_gemma":0.0000043192817,"teacher_disagreement_score":0.9154136,"about_ca_system_score_codex":0.00025293394,"about_ca_system_score_gemma":0.00032284018,"threshold_uncertainty_score":0.9998939},"labels":[],"label_agreement":null},{"id":"W7126026672","doi":"10.1109/bibm66473.2025.11357126","title":"Graph Representation of CTA Images for Spatially Aware Classification","year":2025,"lang":"","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"CAD; Leverage (statistics); Convolutional neural network; Graph; Pooling; Pattern recognition (psychology); Representation (politics); Coronary artery disease","score_opus":0.023410909655512263,"score_gpt":0.3623326634140231,"score_spread":0.33892175375851086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7126026672","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023292765,0.0011619703,0.90504605,0.03110218,0.0016800658,0.001617719,0.000029401732,0.00007483404,0.035995033],"genre_scores_gemma":[0.97897875,0.0010430089,0.009186719,0.00086349045,0.0002636106,0.00006294899,0.00016171276,0.000026433398,0.009413328],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99791986,0.000111422814,0.0008604919,0.0004931491,0.0003186973,0.0002963912],"domain_scores_gemma":[0.9978602,0.000633612,0.0003504194,0.00052110455,0.000514894,0.000119793534],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00065879663,0.0002025281,0.0005340964,0.00040408937,0.00014536433,0.00004433508,0.00020588013,0.0001578817,0.00026196448],"category_scores_gemma":[0.0021804655,0.00018458316,0.00027147194,0.00064195663,0.0002806882,0.00011620251,0.00005692237,0.00031246064,0.0000057662837],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00067281874,0.0006053628,0.07841387,0.0026379456,0.0006525651,0.0000057021703,0.00047933133,0.00042862946,0.09058564,0.035430588,0.06710477,0.72298276],"study_design_scores_gemma":[0.00855886,0.0006525428,0.24293816,0.0020882252,0.0017840646,0.000008136952,0.0022244144,0.6545449,0.055983294,0.011895577,0.018865556,0.0004562859],"about_ca_topic_score_codex":0.0003633479,"about_ca_topic_score_gemma":0.0000069922626,"teacher_disagreement_score":0.955686,"about_ca_system_score_codex":0.00006170459,"about_ca_system_score_gemma":0.0002918591,"threshold_uncertainty_score":0.75270826},"labels":[],"label_agreement":null},{"id":"W7139526579","doi":"","title":"Signals in the Spread: Quantitative Imaging and Tumor Heterogeneity in Metastatic Cancer","year":2025,"lang":"","type":"dissertation","venue":"TSpace (University of Toronto)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Radiomics; Medical imaging; Benchmarking; Imaging biomarker; Feature (linguistics); Biomarker; Cancer; Sarcoma","score_opus":0.019951698048552464,"score_gpt":0.33202352022286147,"score_spread":0.312071822174309,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7139526579","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9577732,0.027976586,0.00064088195,0.004324251,0.00031710186,0.00094208145,0.00003462628,0.000012742331,0.007978521],"genre_scores_gemma":[0.9906913,0.006210056,0.0016216064,0.00030042333,0.000025650379,0.0000035787966,0.0000717372,0.000020149548,0.0010555218],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9975098,0.0006249572,0.00034993858,0.0006055439,0.00046701936,0.00044273798],"domain_scores_gemma":[0.9982319,0.0006973452,0.00047779764,0.00031946108,0.00014197042,0.00013150906],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012272057,0.00037670849,0.0010140914,0.00026551407,0.00019108807,0.000032698747,0.00044285008,0.00009441472,0.0019264373],"category_scores_gemma":[0.00035933228,0.00037607667,0.00017424306,0.00027489229,0.00028786346,0.00035480087,0.00010107675,0.000839459,0.0000023640034],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0043220567,0.0013504969,0.20523742,0.0082035605,0.0014601649,0.0027367887,0.46925196,0.0024354486,0.010201732,0.002303392,0.00087145146,0.29162553],"study_design_scores_gemma":[0.0033750786,0.00016935404,0.65004385,0.0038177464,0.0008403287,0.000012084604,0.2679796,0.07298478,0.00006919505,0.000061463405,0.0002807495,0.00036582092],"about_ca_topic_score_codex":0.5355494,"about_ca_topic_score_gemma":0.34859994,"teacher_disagreement_score":0.4448064,"about_ca_system_score_codex":0.00048148565,"about_ca_system_score_gemma":0.0004909004,"threshold_uncertainty_score":0.9998691},"labels":[],"label_agreement":null},{"id":"W7144209090","doi":"10.71465/ajbe1549","title":"Advancements in Artificial Intelligence for Diagnostic Imaging in Biomedical Engineering","year":2023,"lang":"","type":"article","venue":"American Journal of Biomedical Engineering","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Medical imaging; Applications of artificial intelligence; Diagnostic test; Field (mathematics); Clinical imaging; Clinical diagnosis; Diagnostic accuracy","score_opus":0.009289769892134514,"score_gpt":0.29695830649676225,"score_spread":0.2876685366046277,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7144209090","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45211688,0.002552478,0.5261295,0.012271072,0.0059850356,0.0007834232,0.000030411064,0.00012038173,0.000010848902],"genre_scores_gemma":[0.98172915,0.0019539935,0.013827473,0.00027512337,0.0019688797,0.00004689743,0.000038816917,0.00014888108,0.000010787129],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99309117,0.00009828191,0.0030864002,0.0006090612,0.0013695919,0.0017454805],"domain_scores_gemma":[0.9934093,0.0042184344,0.0006669037,0.00031303364,0.00015501071,0.001237322],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0040961453,0.0005947281,0.0016529565,0.003966418,0.000059350044,0.00007597278,0.0006738439,0.00017010575,0.0000700865],"category_scores_gemma":[0.01947312,0.0005874547,0.00038177485,0.0048086853,0.00064670615,0.00027668185,0.00019328756,0.002204744,0.00002592007],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003275538,0.00074543076,0.0056256554,0.00079069677,0.00019339015,0.0044084266,0.0015399042,0.07265586,0.014008331,0.0003317528,0.000310831,0.89906216],"study_design_scores_gemma":[0.00191753,0.0014364208,0.008660699,0.006170445,0.00013808918,0.0004048169,0.0016099772,0.96795934,0.00021968296,0.00018682648,0.010684709,0.00061144563],"about_ca_topic_score_codex":0.00008369396,"about_ca_topic_score_gemma":0.000001983509,"teacher_disagreement_score":0.89845073,"about_ca_system_score_codex":0.0006513578,"about_ca_system_score_gemma":0.0004913435,"threshold_uncertainty_score":0.9996577},"labels":[],"label_agreement":null},{"id":"W7148389675","doi":"10.2196/78005","title":"AI-Enhanced Predictive Analytics to Optimize Tele-oncology Implementation in Rural Settings: A Scoping Review (Preprint)","year":2025,"lang":"en","type":"article","venue":"JMIR Cancer","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Predictive analytics; Field (mathematics); Analytics; Big data; Data analysis; Data collection","score_opus":0.010563244280421909,"score_gpt":0.4356242913540954,"score_spread":0.4250610470736735,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7148389675","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43223178,0.032560617,0.11599858,0.37513462,0.0020069245,0.022084722,0.000036233327,0.0004599199,0.019486617],"genre_scores_gemma":[0.80568004,0.017075013,0.010438362,0.16094448,0.00047796013,0.0043033143,0.00006859258,0.000055623732,0.00095664576],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.99871075,0.00007249315,0.00046139173,0.00029125228,0.0001799077,0.00028417702],"domain_scores_gemma":[0.9993771,0.000088106135,0.0001095652,0.0001984251,0.000113590984,0.00011321524],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046484635,0.000129479,0.00046384148,0.00018153767,0.000045526966,0.000015839998,0.00009912426,0.000058847345,0.0004073099],"category_scores_gemma":[0.0002982628,0.000118440876,0.00007127117,0.00052965013,0.00003914189,0.000065191976,0.0000868184,0.00041589284,0.000009029285],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00062810816,0.00023455251,0.06541255,0.012636244,0.00030573932,0.00006409431,0.0030607018,0.0069940216,0.007556072,0.00016493764,0.06911862,0.83382434],"study_design_scores_gemma":[0.024855284,0.0018865408,0.123040855,0.66613144,0.0013473174,0.00007532394,0.0066165836,0.10098708,0.009291514,0.0006196253,0.06363197,0.0015164991],"about_ca_topic_score_codex":0.000218505,"about_ca_topic_score_gemma":0.00012217235,"teacher_disagreement_score":0.8323079,"about_ca_system_score_codex":0.0005894155,"about_ca_system_score_gemma":0.0006124714,"threshold_uncertainty_score":0.48298788},"labels":[],"label_agreement":null},{"id":"W75267038","doi":"","title":"A practical approach to PET/MRI: Common abdominal pathology in oncology","year":2013,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Medicine; Radiology; Medical physics; Positron emission tomography; Modalities; Magnetic resonance imaging; PET-CT; Nuclear medicine","score_opus":0.024360996372296797,"score_gpt":0.3676302822691176,"score_spread":0.3432692858968208,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W75267038","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6237951,0.00001986243,0.035641693,0.09538738,0.0001659558,0.00068714895,2.835082e-7,0.00006883503,0.24423377],"genre_scores_gemma":[0.75588775,0.000010958335,0.23046485,0.01201233,0.00013389999,0.00009565537,0.000008015961,0.00001720487,0.0013693357],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99874824,0.0001527914,0.00029157568,0.00028944283,0.00016101201,0.00035694524],"domain_scores_gemma":[0.9991349,0.00024153265,0.000041522704,0.00022161467,0.000043366068,0.00031709278],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00055777776,0.00011551838,0.0003993336,0.00016354749,0.00003054253,0.000017198963,0.00008578872,0.00008085419,0.0005406155],"category_scores_gemma":[0.00067728787,0.000087267144,0.00004712767,0.00016988552,0.000102614074,0.00006200773,0.000083255065,0.00073251897,0.00043091795],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00086078804,0.0061370595,0.13999213,0.00024718844,0.00011351672,0.0074312827,0.0030307763,0.00021675952,0.018737981,0.03213727,0.35788512,0.4332101],"study_design_scores_gemma":[0.01042611,0.0031529057,0.27926716,0.00013068592,0.0001484198,0.034103204,0.0032900455,0.40685114,0.0002870145,0.0022705446,0.25932428,0.0007484671],"about_ca_topic_score_codex":0.0004919995,"about_ca_topic_score_gemma":0.000019562938,"teacher_disagreement_score":0.43246165,"about_ca_system_score_codex":0.000104539344,"about_ca_system_score_gemma":0.000116939154,"threshold_uncertainty_score":0.59193605},"labels":[],"label_agreement":null},{"id":"W836659832","doi":"","title":"Panel on Imaging Technology","year":2012,"lang":"en","type":"article","venue":"Sound Ideas (University of Puget Sound)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Computer vision","score_opus":0.01605561452402715,"score_gpt":0.2559168862255465,"score_spread":0.23986127170151933,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W836659832","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9711661,0.00042505926,0.010048826,0.0048461873,0.00027883073,0.00012641649,0.0000033877832,0.00015249867,0.012952721],"genre_scores_gemma":[0.9943718,0.00003460189,0.00302997,0.00047770157,0.00015752908,2.0908445e-7,0.000013832111,0.000019855883,0.0018945364],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99896556,0.000034447927,0.00011741035,0.00021077799,0.00026888252,0.00040293968],"domain_scores_gemma":[0.9991946,0.000068851514,0.00011135289,0.0003238066,0.00007550655,0.00022587707],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032238945,0.00013703821,0.00029711038,0.00035993633,0.00021108866,0.000010194705,0.00019162748,0.000098986704,0.0002635664],"category_scores_gemma":[0.00020411806,0.00014942623,0.00012773192,0.00031191402,0.00040218703,0.00017034258,0.00010181139,0.00046190294,0.00017414957],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012917309,0.0003362682,0.47587606,0.000106384614,0.00014854211,0.000101749494,0.0015679129,0.00002319162,0.00045404685,0.51286274,0.0047717714,0.0036221442],"study_design_scores_gemma":[0.0021114396,0.00015535986,0.046862636,0.0001251317,0.00021443305,0.00024351805,0.0055663185,0.0014968975,0.000011786667,0.926719,0.016215974,0.00027748477],"about_ca_topic_score_codex":0.00009882245,"about_ca_topic_score_gemma":0.0000035937264,"teacher_disagreement_score":0.4290134,"about_ca_system_score_codex":0.00010335781,"about_ca_system_score_gemma":0.000044805667,"threshold_uncertainty_score":0.60934246},"labels":[],"label_agreement":null},{"id":"W907913464","doi":"","title":"Dependency of Rb-82 normal distribution on PET camera and processing","year":2013,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"SSS*; Nuclear medicine; Medicine; Myocardial perfusion imaging; Correction for attenuation; Gamma camera; Attenuation; Perfusion; Correlation; Radiology; Mathematics; Internal medicine; Positron emission tomography; Physics; Optics; Geometry","score_opus":0.005768747389841645,"score_gpt":0.26239173412507033,"score_spread":0.2566229867352287,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W907913464","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9803274,0.00009225479,0.006901872,0.002933215,0.000038107595,0.0001299433,0.0000014693852,0.00003046093,0.009545261],"genre_scores_gemma":[0.9967861,0.00002613265,0.0019128388,0.00044992418,0.00005954927,0.000004983795,0.000025278034,0.0000070592055,0.00072809844],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9994461,0.000011996815,0.00014187356,0.00011534293,0.00015856155,0.00012610441],"domain_scores_gemma":[0.9996893,0.000026954234,0.00004657754,0.00007803136,0.000057512545,0.00010161558],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011273904,0.000065350825,0.00013553315,0.000029744366,0.000043330056,0.000016539972,0.000029675359,0.00002283359,0.00026484168],"category_scores_gemma":[0.00015686837,0.000046426707,0.000021713575,0.00005761075,0.0000641006,0.00007607953,0.00001802972,0.00018646655,0.000014595722],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000078113444,0.00027128196,0.1936433,0.0005120423,0.00004207141,0.000049810016,0.00033520002,0.000025072757,0.01834001,0.0026033684,0.0052889385,0.7788108],"study_design_scores_gemma":[0.0036819396,0.00083822897,0.7937951,0.00071920897,0.00014328056,0.00071873615,0.0006633899,0.18593729,0.0072560865,0.001019963,0.0048565534,0.0003702287],"about_ca_topic_score_codex":0.00024871336,"about_ca_topic_score_gemma":0.0000010989434,"teacher_disagreement_score":0.77844054,"about_ca_system_score_codex":0.000014781014,"about_ca_system_score_gemma":0.00003172678,"threshold_uncertainty_score":0.28998306},"labels":[],"label_agreement":null},{"id":"W991726587","doi":"10.1118/1.4924238","title":"SU‐E‐J‐153: Reconstructing 4D Cone Beam CT Images for Clinical QA of Lung SABR Treatments","year":2015,"lang":"en","type":"article","venue":"Medical Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; BC Cancer Agency","funders":"","keywords":"SABR volatility model; Truebeam; Nuclear medicine; Cone beam computed tomography; Breathing; Image registration; Computer science; Cone beam ct; Medicine; Radiation therapy; Medical imaging; Radiation treatment planning; Radiology; Beam (structure); Physics; Computer vision; Mathematics; Computed tomography; Linear particle accelerator; Image (mathematics); Optics","score_opus":0.05411766469304394,"score_gpt":0.4042603526852522,"score_spread":0.35014268799220827,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W991726587","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91974175,0.00066469936,0.06976924,0.004426335,0.001611518,0.0007052672,0.000028674525,0.00012802507,0.00292446],"genre_scores_gemma":[0.9851082,0.00013937,0.010607162,0.0013797233,0.002171826,0.00002901508,0.00011529354,0.00006008853,0.00038932916],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99760807,0.00008749608,0.00077491684,0.00037658785,0.0007676025,0.00038531085],"domain_scores_gemma":[0.9975842,0.0008028209,0.00026912388,0.00033105156,0.0002040897,0.0008086632],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015856924,0.0002047082,0.00081461127,0.000044027107,0.00008105419,0.000022104046,0.00018996139,0.00011445493,0.00007338174],"category_scores_gemma":[0.005751968,0.00016466828,0.0002839913,0.00015938068,0.00092123577,0.00008062559,0.00008326515,0.0006427756,0.000010957878],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002739741,0.0010071563,0.38057023,0.00033814833,0.0005898508,0.00014370604,0.00020821123,0.000009406844,0.00024498408,0.0007586787,0.03484707,0.58100855],"study_design_scores_gemma":[0.21442254,0.014709842,0.0740084,0.010964517,0.011196043,0.0037211329,0.0025895645,0.2872317,0.073163964,0.061876893,0.2409044,0.005210975],"about_ca_topic_score_codex":0.00007986445,"about_ca_topic_score_gemma":4.509307e-7,"teacher_disagreement_score":0.5757976,"about_ca_system_score_codex":0.0000733683,"about_ca_system_score_gemma":0.00056947547,"threshold_uncertainty_score":0.68860584},"labels":[],"label_agreement":null},{"id":"W993201291","doi":"10.1118/1.4925587","title":"TU‐CD‐BRB‐02: BEST IN PHYSICS (JOINT IMAGING‐THERAPY): Identification of Molecular Phenotypes by Integrating Radiomics and Genomics","year":2015,"lang":"en","type":"article","venue":"Medical Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Montreal Clinical Research Institute; University Health Network","funders":"","keywords":"Radiomics; Concordance; Medicine; Phenotype; Computational biology; Oncology; Bioinformatics; Biology; Internal medicine; Gene; Genetics; Radiology","score_opus":0.013553956087921325,"score_gpt":0.28166735033201257,"score_spread":0.26811339424409125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W993201291","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8580275,0.0027363133,0.13451341,0.0032634127,0.0002806903,0.00036368656,0.000011038035,0.000058467256,0.00074548105],"genre_scores_gemma":[0.9957398,0.00052558916,0.0018441944,0.0012342894,0.00043079158,0.00001397496,0.00009509536,0.000059978178,0.000056255405],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99779785,0.00008868552,0.0006707269,0.00038555963,0.0007380102,0.00031915863],"domain_scores_gemma":[0.99874073,0.00009672893,0.000257878,0.00032506158,0.0001575615,0.00042202728],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010015075,0.0002346133,0.00055585144,0.00006705372,0.000042771422,0.000036606718,0.00018740962,0.00011025402,0.0000103866705],"category_scores_gemma":[0.0009797345,0.00021452113,0.00009286053,0.0003017034,0.0005240161,0.00012407568,0.000090254325,0.0007443622,0.000008637471],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000109671775,0.00086714857,0.015382888,0.00019686815,0.00010322857,0.00007985369,0.002562686,0.00015423314,0.18206121,0.0019598452,0.0018934445,0.7946289],"study_design_scores_gemma":[0.02091007,0.00091718824,0.004516747,0.0017791332,0.00043278837,0.00026072745,0.002189532,0.5442559,0.35803652,0.052966595,0.012039484,0.0016953317],"about_ca_topic_score_codex":0.0002125587,"about_ca_topic_score_gemma":0.0000020036116,"teacher_disagreement_score":0.7929336,"about_ca_system_score_codex":0.00014175981,"about_ca_system_score_gemma":0.00030415977,"threshold_uncertainty_score":0.8747918},"labels":[],"label_agreement":null}]}