{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":2251,"total_is_capped":false,"direct_labels_cover":9,"predictions_cover":2251,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"158b6d6b4639","filters":{"topic":"Radiomics and Machine Learning in Medical Imaging"}},"results":[{"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02495140181129539,"gpt":0.3432160363981265,"spread":0.3182646345868311,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006705901,0.0001863732,0.0003306412,0.0001610134,0.0004632187,0.00006701433,0.0006169752,0.0001495162,0.000009779053],"category_scores_gemma":[0.001661471,0.0001745238,0.0001102284,0.0003720216,0.0002730252,0.0001280311,0.0002261299,0.00195769,0.00001054097],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001435619,"about_ca_system_score_gemma":0.00011062,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006283552,"about_ca_topic_score_gemma":0.000005709138,"domain_scores_codex":[0.9986647,0.0002232239,0.0002950884,0.000286677,0.000239966,0.0002903698],"domain_scores_gemma":[0.9978002,0.0005626525,0.0001768056,0.001077,0.0002018788,0.0001814909],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002731324,0.002153068,0.09494112,0.0004584994,0.0009361558,0.00003231618,0.007790627,0.001743303,0.3869395,0.3652923,0.07060973,0.0688303],"study_design_scores_gemma":[0.001054767,0.00003721691,0.001294382,0.0001422935,0.0001947841,0.0001854449,0.0004980013,0.9591377,0.0004710791,0.0004358171,0.03628872,0.000259792],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2100409,0.03683174,0.639318,0.03506905,0.0008149348,0.001367009,0.00004419327,0.0006140746,0.07590017],"genre_scores_gemma":[0.703513,0.0002223971,0.2939696,0.001954595,0.00008036535,0.00001044421,0.0001561985,0.00003831763,0.00005508104],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9573944,"threshold_uncertainty_score":0.8505299,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.2566280228861588,"gpt":0.5461063273453626,"spread":0.2894783044592038,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.002239794,0.000395377,0.002467009,0.0003414713,0.0001301439,0.00006442105,0.000305732,0.0003534732,0.00007729683],"category_scores_gemma":[0.0006672479,0.0003108387,0.0008260156,0.0002048713,0.0002046119,0.00007201108,0.00006764879,0.0027648,0.00001987885],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002893152,"about_ca_system_score_gemma":0.00169631,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004157049,"about_ca_topic_score_gemma":0.0000927782,"domain_scores_codex":[0.9962692,0.0001917048,0.002122232,0.000665656,0.0002552876,0.0004958675],"domain_scores_gemma":[0.9968987,0.00126037,0.0009281912,0.0003495982,0.0001803598,0.0003827708],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0000369748,0.0001262949,0.0002254923,0.007104387,0.0002022741,0.00003117471,0.00009240042,0.000007553057,9.269897e-8,0.0004277589,0.0008643884,0.9908812],"study_design_scores_gemma":[0.000285608,0.0001343166,0.00005872602,0.01765666,0.001686895,0.0002980568,0.0001283534,0.001298565,6.747353e-8,0.001205076,0.9769455,0.0003021371],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000008380654,0.9880539,0.003042627,0.00431373,0.00255212,0.001644317,0.00005628794,0.00002194239,0.0003067156],"genre_scores_gemma":[0.00002345734,0.9920671,0.0005671325,0.0009100846,0.005313571,0.0006508358,0.00001987088,0.0001062138,0.0003417114],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9905791,"threshold_uncertainty_score":0.9999344,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01289525745999718,"gpt":0.355635835647866,"spread":0.3427405781878688,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","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":[0.0009309822,0.00003791621,0.00005388907,0.0002404596,0.0001525627,0.00002215489,0.0004811985,0.002416166,0.00001034455],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009320196,"about_ca_system_score_gemma":0.000159159,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001611205,"about_ca_topic_score_gemma":0.00002847774,"domain_scores_codex":[0.9988829,0.0002007354,0.0001566099,0.00009450985,0.000543966,0.0001212125],"domain_scores_gemma":[0.9983391,0.0005156055,0.00005638499,0.0009355106,0.00005057231,0.0001028846],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001329998,0.0008315836,0.04002739,0.00002336275,0.0002560079,0.00005721162,0.001436334,0.0000804704,0.002485523,0.1557404,0.2502589,0.5486698],"study_design_scores_gemma":[0.0004700451,0.00004440815,0.00780687,0.000009158167,0.00003363989,0.0002355703,0.0004071413,0.01736996,0.00003011753,0.0003496414,0.97319,0.00005342435],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.07596477,0.03738828,0.001149642,0.8407227,0.001310721,0.0007846337,0.00001095011,0.00028236,0.04238589],"genre_scores_gemma":[0.9868758,0.001220956,0.003444534,0.007368573,0.00007644531,0.0001163223,0.0001335644,0.00001315703,0.0007506417],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.910911,"threshold_uncertainty_score":0.9998853,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.2445465864156629,"gpt":0.6209623229717565,"spread":0.3764157365560936,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.008369708,0.0008030243,0.0114178,0.0002588693,0.000129571,0.00001879128,0.0005137935,0.002129639,0.0002102806],"category_scores_gemma":[0.02959383,0.0004088861,0.003813182,0.0003518662,0.0006241163,0.00005953904,0.0002481542,0.004537026,0.0002200138],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006859557,"about_ca_system_score_gemma":0.001696361,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002942688,"about_ca_topic_score_gemma":0.000004385566,"domain_scores_codex":[0.9923472,0.001520794,0.003806443,0.001279487,0.0003042673,0.0007417558],"domain_scores_gemma":[0.9875434,0.008342369,0.002332409,0.0008551607,0.0003902563,0.0005363784],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003709356,0.0001248904,0.00004827855,0.02413983,0.0009189213,0.00007135363,0.000005707619,3.573748e-9,1.946759e-7,0.0001348258,0.1709301,0.8035887],"study_design_scores_gemma":[0.001463924,0.0002101269,0.00001089706,0.07425171,0.005444,0.0002175613,0.000003080337,0.0000223732,2.642351e-8,0.0001330064,0.9178383,0.0004049345],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[1.838104e-7,0.9738525,0.0003359407,0.01302323,0.007319489,0.003943298,0.00004303211,0.00008882987,0.001393523],"genre_scores_gemma":[2.768716e-7,0.9741305,0.004985691,0.01033801,0.005781935,0.001376718,0.00009384094,0.0001497366,0.003143349],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.8031838,"threshold_uncertainty_score":0.9998363,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1197117159693125,"gpt":0.3639329413583748,"spread":0.2442212253890623,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005311962,0.0001132993,0.0004503956,0.00005103745,0.00003335487,0.000002673929,0.00008712162,0.00006001251,0.000002288801],"category_scores_gemma":[0.0005283944,0.00005680467,0.00003420439,0.0001014314,0.0006559648,0.00002588311,0.00006133505,0.0003192587,1.878055e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001691191,"about_ca_system_score_gemma":0.00005661328,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008207909,"about_ca_topic_score_gemma":0.00005420927,"domain_scores_codex":[0.9992523,0.00007325179,0.0002702046,0.0001736854,0.00009620569,0.000134394],"domain_scores_gemma":[0.9991584,0.0004329451,0.0001288245,0.0001746217,0.00005603884,0.00004914891],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001679097,0.0006446012,0.3842377,0.001167333,0.0008468919,0.00002391641,0.03296002,0.01649992,0.1477058,0.02611376,0.03416837,0.3539525],"study_design_scores_gemma":[0.005549113,0.0004387579,0.02562305,0.0005768728,0.0003720228,0.00005912532,0.002499823,0.9207383,0.001009013,0.04167357,0.001351005,0.0001093625],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8294577,0.03488452,0.112979,0.02085543,0.0004284872,0.001030044,0.0001481988,0.00001694059,0.0001997032],"genre_scores_gemma":[0.9959145,0.001455642,0.001666261,0.0005984379,0.0002621971,0.00001367819,0.00005240866,0.000009742699,0.00002711866],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9042383,"threshold_uncertainty_score":0.241693,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01137390998662466,"gpt":0.3068003099155884,"spread":0.2954263999289637,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001104962,0.000555778,0.002844013,0.0003629761,0.00008185377,0.00004374073,0.0003681084,0.0004230711,0.0001339578],"category_scores_gemma":[0.002641668,0.0004354071,0.0005802789,0.0006360153,0.0002331726,0.0001011375,0.0002632893,0.001862652,0.00001096228],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002638864,"about_ca_system_score_gemma":0.0007856439,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006695197,"about_ca_topic_score_gemma":0.00003532134,"domain_scores_codex":[0.9965008,0.0003179964,0.001242976,0.0006005644,0.0008680169,0.0004696093],"domain_scores_gemma":[0.9976418,0.0003153901,0.0006851858,0.0005577896,0.0001043587,0.0006954491],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001280294,0.00006882881,0.000112774,0.0640107,0.0002180103,0.0003931567,0.00003382871,5.615312e-7,0.00001355475,0.0002437188,0.002735087,0.932157],"study_design_scores_gemma":[0.001028059,0.0002860083,0.0001410495,0.1629575,0.004247904,0.006048081,0.00002677529,0.03665087,0.00002420053,0.00009665437,0.7877461,0.0007467165],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000006649717,0.9520087,0.03895105,0.006760924,0.0001174288,0.001783175,0.00001543885,0.0002133311,0.0001432623],"genre_scores_gemma":[0.00008860459,0.9707069,0.02299123,0.005180388,0.0002330952,0.0002895814,0.0002501493,0.000117112,0.0001429756],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9314103,"threshold_uncertainty_score":0.9998097,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.0170700159655151,"gpt":0.3163460536078446,"spread":0.2992760376423295,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008058053,0.0001988623,0.000604814,0.0002407159,0.00004975296,0.00001981845,0.0001089045,0.0001356812,0.00008039721],"category_scores_gemma":[0.0001789462,0.0001601143,0.00007661416,0.0002378465,0.0002200202,0.00006005233,0.00001696615,0.0006495564,0.000002132365],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007088712,"about_ca_system_score_gemma":0.0004659311,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001066906,"about_ca_topic_score_gemma":0.00002580577,"domain_scores_codex":[0.9985113,0.0002189681,0.0003145238,0.0003685027,0.000219689,0.0003669873],"domain_scores_gemma":[0.9990454,0.0001969937,0.00009108772,0.0002244747,0.0000363127,0.0004057267],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.004214347,0.001233127,0.6805259,0.0004506744,0.0005853885,0.006520309,0.004240428,0.001519457,0.01209109,0.001974699,0.04048109,0.2461635],"study_design_scores_gemma":[0.03998844,0.003754691,0.09967846,0.0002954782,0.0003776147,0.002543953,0.0005250508,0.3835826,0.0008575064,0.0005681909,0.4671346,0.0006933644],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.932064,0.04163034,0.007455545,0.01615029,0.0006214603,0.0005844265,0.00000787711,0.0001007661,0.00138531],"genre_scores_gemma":[0.9852641,0.0006321819,0.008368181,0.005135798,0.000317174,0.00002763652,0.00002962608,0.00003986122,0.0001854238],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5808474,"threshold_uncertainty_score":0.6529272,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.0569063703711607,"gpt":0.2794875699005049,"spread":0.2225811995293442,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004660977,0.0001187938,0.0002877231,0.0002416482,0.0001109194,0.00004789278,0.00007841417,0.00009124251,0.00004542295],"category_scores_gemma":[0.0009428448,0.0001119648,0.00005062032,0.0004437028,0.00004638958,0.00009218352,0.00001835909,0.0003454419,0.00003924095],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001346879,"about_ca_system_score_gemma":0.00004079243,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002347264,"about_ca_topic_score_gemma":5.814726e-7,"domain_scores_codex":[0.9988562,0.00007421587,0.0002203393,0.000234295,0.0004175261,0.0001974563],"domain_scores_gemma":[0.9992562,0.0001027605,0.0001392856,0.0002709976,0.00009564604,0.0001351193],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005035181,0.001186831,0.05903313,0.0009995732,0.000368596,0.000008543232,0.0003552262,0.002052025,0.9037522,0.0002867026,0.001478113,0.03042872],"study_design_scores_gemma":[0.0009286535,0.00007803387,0.009885264,0.0003731802,0.0004658441,0.00002663197,0.00003819381,0.9751226,0.01276,0.00005590884,0.0001374313,0.0001282042],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9025783,0.0001856955,0.09411187,0.002084063,0.00009202259,0.0003162678,0.000001264325,0.0001392391,0.000491299],"genre_scores_gemma":[0.7771683,0.000057429,0.2209896,0.0006534694,0.0003749999,0.00000954713,0.0000916548,0.00003928326,0.0006156295],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9730706,"threshold_uncertainty_score":0.4565794,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1037579113986433,"gpt":0.4339280365929593,"spread":0.330170125194316,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003334709,0.0005751516,0.00227669,0.0002623149,0.0006411668,0.00009913933,0.0004637994,0.0002732984,0.001149923],"category_scores_gemma":[0.01993551,0.0003019882,0.000584203,0.0003350115,0.0005615414,0.00009845938,0.0002809275,0.002404811,0.000003074607],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001115296,"about_ca_system_score_gemma":0.0003046417,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002118673,"about_ca_topic_score_gemma":0.000001982397,"domain_scores_codex":[0.9966528,0.000291466,0.001014982,0.0007546689,0.0007451072,0.0005409374],"domain_scores_gemma":[0.9844901,0.01407577,0.0004473854,0.0003995963,0.00009075358,0.0004963703],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00006559939,0.00004911851,0.00002069104,0.003961235,0.0002909222,0.00002892279,0.00008144583,4.583312e-7,9.189181e-8,0.001841357,0.03404057,0.9596196],"study_design_scores_gemma":[0.001767496,0.0004877794,0.000003681505,0.003334088,0.001834351,0.001380518,0.0004025262,0.004588564,2.768323e-8,0.0005076544,0.9854048,0.0002885217],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[2.188141e-7,0.8506236,0.02131817,0.1236454,0.00123593,0.002004801,0.0000898205,0.0001311352,0.000950943],"genre_scores_gemma":[0.00001542303,0.9840838,0.003109542,0.002742042,0.004282169,0.001007613,0.002757158,0.00013874,0.001863565],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.959331,"threshold_uncertainty_score":0.9999432,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.0355448319793312,"gpt":0.4180000261170838,"spread":0.3824551941377526,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.001314125,0.0005303234,0.003037513,0.00008467665,0.0001601318,0.00004841785,0.0002807901,0.0004917299,0.00007926852],"category_scores_gemma":[0.005644344,0.0004092286,0.0006816892,0.0003245593,0.0003927562,0.00004058529,0.0002117535,0.002923203,0.00002005592],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001024535,"about_ca_system_score_gemma":0.000457246,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006072138,"about_ca_topic_score_gemma":1.290201e-7,"domain_scores_codex":[0.9972717,0.0003216332,0.0007330046,0.0006958275,0.0005040207,0.0004738095],"domain_scores_gemma":[0.99661,0.001692839,0.0003163678,0.0002869391,0.0000575277,0.00103629],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001415558,0.00005007934,0.000007508946,0.01526543,0.0003246362,0.00006507595,0.00007287441,4.000324e-7,3.95054e-7,0.0006150854,0.0003277727,0.9832566],"study_design_scores_gemma":[0.0009511053,0.0001960285,5.946951e-7,0.005068477,0.001946884,0.0003627864,0.000004979065,0.03131346,0.000001081954,0.0008413038,0.958968,0.0003452831],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[1.020992e-7,0.6135073,0.3843843,0.0008283174,0.0002549888,0.0005504936,0.000004742065,0.00009694989,0.0003728149],"genre_scores_gemma":[0.000002186726,0.9534328,0.04223717,0.001181141,0.002259247,0.000101637,0.0003711193,0.0001811799,0.0002335012],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9829113,"threshold_uncertainty_score":0.999836,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01897411251840962,"gpt":0.3615030147370685,"spread":0.3425289022186588,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001761378,0.0001042716,0.0003285141,0.0001310681,0.000318285,0.0002784627,0.0001052346,0.00005282681,0.00002309753],"category_scores_gemma":[0.000619273,0.00008459455,0.00007655028,0.00007062378,0.0003881195,0.0001813379,0.00005696035,0.0002449784,2.136259e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005474182,"about_ca_system_score_gemma":0.000532482,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006725205,"about_ca_topic_score_gemma":0.0003088738,"domain_scores_codex":[0.9986078,0.0000208846,0.0004165082,0.0004340578,0.0002920094,0.0002287061],"domain_scores_gemma":[0.9985666,0.00003824101,0.000541723,0.0006056271,0.0001293394,0.0001185115],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00002606618,0.0001064322,0.9491409,0.0002973861,0.00004826322,0.0002426959,0.0004482009,0.0004701382,0.03198849,0.0008370972,0.005648636,0.01074568],"study_design_scores_gemma":[0.00207516,0.0001344623,0.8945228,0.0007502651,0.0001461232,0.0002958439,0.0004758667,0.05303358,0.001998401,0.01788308,0.02844293,0.000241485],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9928355,0.0001803957,0.001413023,0.002033962,0.001950533,0.0003995019,0.000005066491,0.00001505121,0.001166988],"genre_scores_gemma":[0.9880162,0.00005280798,0.01113386,0.00003015485,0.00009569901,0.00003427557,0.00001386432,0.00001396472,0.0006091357],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05461811,"threshold_uncertainty_score":0.3449666,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.00762688133724588,"gpt":0.2962035355455158,"spread":0.2885766542082699,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00197853,0.000439263,0.0008708394,0.0006442023,0.0001469531,0.0002632003,0.0006771563,0.0004418535,0.00008116783],"category_scores_gemma":[0.0004828759,0.0003694035,0.0001821354,0.000399082,0.001129688,0.0001571324,0.0009136457,0.002220038,0.00004794839],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003418039,"about_ca_system_score_gemma":0.0008546401,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005003502,"about_ca_topic_score_gemma":0.000009393189,"domain_scores_codex":[0.9961548,0.0001038746,0.0006620598,0.001171429,0.001299087,0.0006087563],"domain_scores_gemma":[0.9978811,0.0006766481,0.0002902423,0.0005761737,0.0001865358,0.0003893534],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002321242,0.00009525676,0.001553543,0.0004719191,0.00004055993,0.0003395456,0.0003190046,0.0005758296,0.0001558232,0.00006778177,0.002424519,0.993933],"study_design_scores_gemma":[0.001737857,0.0003428956,0.007357907,0.004323348,0.0000515188,0.001221329,3.681021e-7,0.9803883,0.0000530815,0.0008850679,0.003207456,0.0004308713],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005746935,0.000794697,0.9866669,0.00256737,0.002521816,0.0004642176,0.000003260215,0.0001100043,0.001124833],"genre_scores_gemma":[0.1973457,0.000266468,0.7694582,0.01984345,0.007368558,0.000007788326,0.0003320354,0.0002484159,0.005129466],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9935021,"threshold_uncertainty_score":0.9998758,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"St. Thomas Hospital","funders":"","keywords":"Medicine; Nuclear medicine; Lung cancer; Pathology; Tongue; Angiogenesis; Radiology; Internal medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.0118872542745247,"gpt":0.2819139874022782,"spread":0.2700267331277535,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000387813,0.0001779313,0.0004414264,0.00007695911,0.0001173861,0.000004808259,0.0001147389,0.0001319893,0.0001298251],"category_scores_gemma":[0.0002203133,0.0001369585,0.0001471028,0.00006627723,0.0001540831,0.00002949234,0.00004491133,0.0004197326,0.00002484571],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002405287,"about_ca_system_score_gemma":0.0000515202,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004346104,"about_ca_topic_score_gemma":0.000002317506,"domain_scores_codex":[0.998802,0.00005514386,0.0002243037,0.0002700652,0.00006846833,0.0005800163],"domain_scores_gemma":[0.9991213,0.0002650909,0.0001166683,0.0002230871,0.00002808698,0.0002457311],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001339372,0.0000945757,0.9176915,0.0002217417,0.00006300092,0.00008186918,0.0005918378,0.0002655735,0.01101553,0.0001508639,0.05779629,0.01189324],"study_design_scores_gemma":[0.01082983,0.001397032,0.2810656,0.0002776366,0.001960436,0.008837386,0.0002289852,0.191119,0.003534715,0.0003153672,0.4991668,0.001267146],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9768129,0.01172506,0.005277193,0.002244595,0.001715165,0.0005304141,0.000008139094,0.00007406036,0.001612483],"genre_scores_gemma":[0.9864647,0.0004979109,0.004955969,0.003244596,0.0005466836,0.0001243514,0.00006280649,0.00003701005,0.004066018],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6366259,"threshold_uncertainty_score":0.5585005,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.0252816267536549,"gpt":0.3903279829484029,"spread":0.365046356194748,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.01131474,0.0004900739,0.002132737,0.001524899,0.0003147899,0.0003282562,0.0005582689,0.000240489,0.0002997827],"category_scores_gemma":[0.01147999,0.0003332779,0.0003442572,0.0008108309,0.001136621,0.0003955679,0.000285544,0.004972932,0.00001016682],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00017428,"about_ca_system_score_gemma":0.001452488,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008469367,"about_ca_topic_score_gemma":0.000002692334,"domain_scores_codex":[0.9929221,0.0006143641,0.001891256,0.0006554601,0.003274841,0.0006419731],"domain_scores_gemma":[0.9955042,0.001783676,0.001303345,0.0001382964,0.0001481435,0.001122344],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000009444876,0.00005545928,0.03492324,0.001847922,0.00005104475,0.0008006059,0.0002836724,0.0000256068,6.00146e-7,0.0000631856,0.0002730338,0.9616662],"study_design_scores_gemma":[0.0009884165,0.00006358982,0.0003108509,0.0124126,0.0003215268,0.00919052,0.0007006667,0.3055764,2.00919e-7,0.00003786663,0.6701357,0.0002615867],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0002078582,0.9796531,0.00241042,0.01596984,0.001024648,0.0002302237,7.479571e-7,0.00004107734,0.0004620825],"genre_scores_gemma":[0.004093684,0.9933242,0.0004621392,0.0009378344,0.0009894966,0.000004285554,0.00001505263,0.00005260649,0.0001207447],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9614046,"threshold_uncertainty_score":0.9999119,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02241397381995801,"gpt":0.320448033344801,"spread":0.298034059524843,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001164478,0.0001619323,0.0002934727,0.0001568338,0.0002121853,0.0002457449,0.0000518892,0.00009715742,0.00001501943],"category_scores_gemma":[0.0006855482,0.000125652,0.0000549814,0.0002007142,0.0003708044,0.00009834269,0.00005405897,0.0002984556,9.166113e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007268207,"about_ca_system_score_gemma":0.0001986565,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003573778,"about_ca_topic_score_gemma":0.00001806342,"domain_scores_codex":[0.9983315,0.00002629732,0.0002594792,0.0006821086,0.0003740267,0.0003265947],"domain_scores_gemma":[0.9988199,0.00006875674,0.0001486672,0.0003557063,0.0001561009,0.0004508873],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001546796,0.00007263793,0.144217,0.0004372303,0.00008467914,0.0004458239,0.001781797,0.0002401463,0.01428351,0.00006326271,0.8137046,0.02451469],"study_design_scores_gemma":[0.002352854,0.0001262077,0.021383,0.0006471415,0.0002358027,0.002751935,0.0001875844,0.02376208,0.0004256614,0.00173039,0.946,0.0003973735],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9713524,0.01530855,0.001248554,0.005718663,0.005030727,0.0009172647,0.000003536863,0.0000696197,0.0003506822],"genre_scores_gemma":[0.9749154,0.0001345502,0.0134849,0.00049823,0.0005639866,0.00007043405,0.0001219541,0.00004579623,0.01016469],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1322954,"threshold_uncertainty_score":0.512394,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01796075419887752,"gpt":0.2944722943734753,"spread":0.2765115401745978,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00107,0.0001684381,0.0006670928,0.0002252132,0.00009790262,0.00001376238,0.0001003283,0.00006043533,0.0003546042],"category_scores_gemma":[0.0006632241,0.0001019498,0.0001236785,0.0004275717,0.0002769957,0.000126731,0.00005364973,0.001081746,9.323214e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006623021,"about_ca_system_score_gemma":0.00004627836,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001418706,"about_ca_topic_score_gemma":0.00001993134,"domain_scores_codex":[0.9979662,0.0001782685,0.0008322483,0.0001953471,0.0006438575,0.0001841381],"domain_scores_gemma":[0.9986011,0.0001051036,0.000730789,0.0001767105,0.0002277858,0.0001585397],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002337783,0.0001614202,0.9572381,0.0001524576,0.0008625922,0.00006344206,0.003220755,0.002117568,0.02694843,0.00004676662,0.003664094,0.005290539],"study_design_scores_gemma":[0.001925891,0.0003617245,0.7590293,0.000534952,0.000775941,0.0002804566,0.0005607472,0.2212185,0.00002104423,0.00001698036,0.01520144,0.00007306048],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9827589,0.0004576602,0.001054039,0.01531935,0.0001340841,0.0002009954,0.00001126689,0.000009224334,0.00005441342],"genre_scores_gemma":[0.9867983,0.0001687992,0.001903012,0.01053638,0.0004899687,0.000002538761,0.00006182927,0.00002335463,0.00001579853],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2191009,"threshold_uncertainty_score":0.4699707,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01370251181660053,"gpt":0.3628712415156012,"spread":0.3491687296990006,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0009645834,0.0003848933,0.005617998,0.0009795241,0.00004299902,0.000008670427,0.00061421,0.0001261879,0.00007286276],"category_scores_gemma":[0.001065686,0.0002576256,0.00188195,0.001894996,0.0008545536,0.00003633102,0.00007122393,0.003264548,0.000006603086],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003317694,"about_ca_system_score_gemma":0.0005066482,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006769642,"about_ca_topic_score_gemma":2.154731e-7,"domain_scores_codex":[0.9964604,0.0007255728,0.001796395,0.0003828835,0.000313824,0.0003209139],"domain_scores_gemma":[0.9938828,0.0006667563,0.004161642,0.0006599376,0.0003159658,0.0003128923],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001088009,0.00007106289,0.0004597024,0.01212803,0.0007254254,0.0002602496,0.000007854493,0.000002332912,0.00001103344,0.00002974185,0.0006555821,0.9856381],"study_design_scores_gemma":[0.0001616166,0.0005646494,0.0001639649,0.008353046,0.01703235,0.01433004,0.000005972657,0.00005839123,9.28321e-8,0.00001322938,0.9591597,0.0001569028],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00003649931,0.9941412,0.002386822,0.002511562,0.0002184075,0.0004384675,0.0000110023,0.00001668703,0.000239387],"genre_scores_gemma":[0.0002405749,0.9922284,0.001857191,0.005000163,0.0005360325,0.00002410198,0.00003825386,0.00005352173,0.00002169502],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9854812,"threshold_uncertainty_score":0.9999876,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02125261402716713,"gpt":0.3330902779849891,"spread":0.311837663957822,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003603516,0.00008997045,0.0002080846,0.00004040375,0.0005907727,0.0002194145,0.00006134804,0.00004680222,0.00007289528],"category_scores_gemma":[0.006700546,0.000051734,0.00008459834,0.000178165,0.0004366435,0.0000431769,0.00008265253,0.000200347,0.00000459085],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002264369,"about_ca_system_score_gemma":0.0002970011,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000241449,"about_ca_topic_score_gemma":0.000009166133,"domain_scores_codex":[0.9982991,0.00007438801,0.0003808502,0.0005173823,0.0004503972,0.0002779121],"domain_scores_gemma":[0.9985877,0.0004601181,0.0001261944,0.0003482124,0.0002326029,0.0002451536],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001858284,0.0003974193,0.2793679,0.0004070558,0.0003329366,0.02038391,0.001630416,0.00001335689,0.06594708,0.01508009,0.1572514,0.4590026],"study_design_scores_gemma":[0.0008398608,0.0000709236,0.006851943,0.0004237101,0.00006752805,0.01400367,0.001475463,0.06344434,0.002809569,0.01240376,0.8973918,0.000217457],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9492971,0.006202879,0.01031057,0.02398127,0.007742172,0.0004451998,0.000002775509,0.00006303885,0.001954938],"genre_scores_gemma":[0.9935531,0.0001386674,0.003698273,0.0003656613,0.0001760203,0.00002493491,0.00004666211,0.00001388405,0.001982766],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7401404,"threshold_uncertainty_score":0.8021664,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1720944463343659,"gpt":0.574027760237618,"spread":0.4019333139032522,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.007573877,0.0006139469,0.01032887,0.0003610957,0.00004861462,0.00001832437,0.0005549536,0.004880527,0.0003026053],"category_scores_gemma":[0.02993352,0.0004312876,0.001907948,0.001110496,0.0003483665,0.00004982791,0.0002011662,0.0160539,0.001106494],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001076628,"about_ca_system_score_gemma":0.003303877,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007599236,"about_ca_topic_score_gemma":0.0000162852,"domain_scores_codex":[0.9886686,0.003803394,0.005458813,0.001182349,0.0003300534,0.0005567492],"domain_scores_gemma":[0.991677,0.004909494,0.002059899,0.000606927,0.00008026417,0.0006663653],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00005972353,0.0004943273,0.00002260378,0.006339166,0.0001112885,0.0009249211,0.00002386607,2.320233e-7,7.886317e-8,0.001177218,0.006383556,0.984463],"study_design_scores_gemma":[0.0002662828,0.001361972,0.00001366127,0.00868973,0.00153086,0.0004056141,0.000004959101,0.0003300166,5.185244e-8,0.0003569238,0.9867149,0.0003250318],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[5.392799e-7,0.978197,0.0005101008,0.009845248,0.003071768,0.002586323,0.000005873778,0.00006389765,0.005719251],"genre_scores_gemma":[0.000003538642,0.9783366,0.007939078,0.0088059,0.004314022,0.0001915654,0.000222475,0.00008007106,0.0001067779],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.984138,"threshold_uncertainty_score":0.9998139,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1317209994531531,"gpt":0.5501465579063007,"spread":0.4184255584531477,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.01843094,0.0008688839,0.0134125,0.000551164,0.00009032139,0.00003512432,0.0005976621,0.007532115,0.0002117658],"category_scores_gemma":[0.0350837,0.000548896,0.002320226,0.0006166855,0.000229012,0.0001418858,0.0002552753,0.01427542,0.0005720609],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001890931,"about_ca_system_score_gemma":0.002493347,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003885888,"about_ca_topic_score_gemma":0.00002061413,"domain_scores_codex":[0.986084,0.004223312,0.006921728,0.00116208,0.0006830237,0.0009257977],"domain_scores_gemma":[0.9806278,0.01362514,0.003714861,0.0009755458,0.0001512276,0.0009054305],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00007664805,0.0008324715,0.01330233,0.007846587,0.000245497,0.0002133069,0.00002588396,4.885273e-7,5.930992e-8,0.00006365402,0.00618862,0.9712045],"study_design_scores_gemma":[0.003083894,0.001059536,0.0009970727,0.01232457,0.003494933,0.0004349205,0.000005900073,0.0001446406,7.139799e-9,0.000007314676,0.9780357,0.0004115295],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00003322916,0.9651482,0.0001058244,0.0005049234,0.02710715,0.004314504,0.00002027202,0.0000951619,0.002670721],"genre_scores_gemma":[0.00004411971,0.9835861,0.003882127,0.001249001,0.009877093,0.0003450299,0.0004754431,0.0001267184,0.0004143255],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9718471,"threshold_uncertainty_score":0.9996963,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.05869387304731272,"gpt":0.3462172372383782,"spread":0.2875233641910655,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001420628,0.0002292712,0.0007565885,0.0001060552,0.0001643066,0.0001162303,0.00021529,0.00002865951,0.0002050424],"category_scores_gemma":[0.0009367942,0.0001161779,0.0003312728,0.0001323688,0.0002701978,0.00007848246,0.00004721131,0.000811192,0.00001037496],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002700333,"about_ca_system_score_gemma":0.0002972714,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007465061,"about_ca_topic_score_gemma":0.000001709701,"domain_scores_codex":[0.9977061,0.000727528,0.0006782851,0.0002458243,0.0004894435,0.0001528086],"domain_scores_gemma":[0.9978621,0.0005512132,0.0008705794,0.0002462193,0.000178735,0.0002911403],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00008264116,0.00001369294,0.00005741397,0.0001691543,0.0002473563,0.0001867851,0.0006172766,9.687158e-7,0.000001440553,0.0001504748,0.009310725,0.9891621],"study_design_scores_gemma":[0.0005949429,0.00005123229,0.00110415,0.0387699,0.0007598386,0.00007710238,0.0002681348,0.000005460375,1.984049e-8,0.00007756668,0.9581641,0.000127531],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000024684,0.9887686,0.00406142,0.003787645,0.0007828773,0.0002087302,0.0000430011,0.0000120083,0.002311069],"genre_scores_gemma":[0.0003955052,0.9929895,0.0009496615,0.0001807033,0.004794102,0.000004150248,0.00001260764,0.00007824313,0.0005955435],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9890345,"threshold_uncertainty_score":0.4737596,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.013589213883682,"gpt":0.3453327389953813,"spread":0.3317435251116993,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001951471,0.0001234727,0.0003484713,0.0004209989,0.0002312122,0.00002123314,0.0005924577,0.0001882687,0.0002287396],"category_scores_gemma":[0.0004197843,0.00009403636,0.0001549037,0.001441326,0.001462397,0.00005801176,0.0001950733,0.001307554,0.000004154205],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005204658,"about_ca_system_score_gemma":0.00009537689,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001533807,"about_ca_topic_score_gemma":0.0004260061,"domain_scores_codex":[0.9989167,0.0001014469,0.0002737207,0.0001924385,0.0003532042,0.0001624939],"domain_scores_gemma":[0.9973832,0.0002319245,0.0001259219,0.001474664,0.0006365927,0.0001476512],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001574379,0.005199467,0.3592491,0.001026744,0.02293464,0.0001246649,0.06710467,0.0000465247,0.1183411,0.07568961,0.3192023,0.02950674],"study_design_scores_gemma":[0.003765616,0.001031859,0.06303222,0.0008407474,0.006672798,0.0001370477,0.004084778,0.04277809,0.002012784,0.0001563284,0.8749477,0.0005400165],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.3016647,0.0110025,0.1329489,0.4631781,0.0005793759,0.001636502,0.0004329199,0.0007871509,0.08776993],"genre_scores_gemma":[0.9228439,0.0001116863,0.07021758,0.005962081,0.0000746783,0.0000143717,0.0007206883,0.00001881003,0.00003617159],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6211793,"threshold_uncertainty_score":0.5680745,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01641777494677072,"gpt":0.3384855564519291,"spread":0.3220677815051584,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004876105,0.00006885831,0.0002150244,0.00003834772,0.0001227951,0.00001717114,0.0001957559,0.00004661703,0.0001326372],"category_scores_gemma":[0.001188491,0.00003953957,0.00005348839,0.00004033987,0.0001914534,0.00002861352,0.00006250126,0.0002831017,0.000005289981],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002931637,"about_ca_system_score_gemma":0.00006502701,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007233203,"about_ca_topic_score_gemma":0.00002164662,"domain_scores_codex":[0.9993625,0.00003621424,0.0001716556,0.0001289138,0.0001447676,0.0001559249],"domain_scores_gemma":[0.9994035,0.0001150852,0.000111785,0.0002911063,0.00002532332,0.00005314401],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00004790467,0.00002906653,0.9622284,0.00003276445,0.00003750624,0.00001666257,0.0003077342,0.00004925166,0.002111966,0.001694328,0.002276388,0.03116801],"study_design_scores_gemma":[0.001126584,0.0000386314,0.9683527,0.0002494676,0.00004289821,0.0000125718,0.00006439033,0.02297775,0.002266103,0.00006031305,0.004727561,0.00008103107],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9814972,0.004238372,0.0001739237,0.009373268,0.0002342127,0.0001102719,0.000002275285,0.00001506837,0.004355371],"genre_scores_gemma":[0.997114,0.0006613945,0.0009316219,0.0009939342,0.0001659113,0.00001076502,0.000002209996,0.000008776481,0.0001113632],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03108698,"threshold_uncertainty_score":0.1612377,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.07907597815907866,"gpt":0.5092562311739407,"spread":0.4301802530148621,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.008336406,0.0006543772,0.003988189,0.0003921105,0.0005325318,0.00002781365,0.000406938,0.0007811625,0.00001627095],"category_scores_gemma":[0.05526782,0.0003223278,0.0007765262,0.0007248374,0.0002600291,0.0000484524,0.0002006067,0.003430161,0.000001243421],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003138226,"about_ca_system_score_gemma":0.0008175445,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002199308,"about_ca_topic_score_gemma":0.000006573379,"domain_scores_codex":[0.9938525,0.0001822247,0.003761016,0.0007336306,0.0007536492,0.0007169875],"domain_scores_gemma":[0.9926697,0.002575503,0.002970837,0.0009301843,0.0006443617,0.0002094091],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003191302,0.00004267563,0.000001429672,0.02819377,0.0009585471,0.0002135133,0.0002806968,0.000008094994,0.000004304574,0.00111989,0.08593412,0.883211],"study_design_scores_gemma":[0.001364914,0.0001152713,1.421015e-7,0.05952769,0.004856208,0.0003680569,0.0005592989,0.008272637,0.000001103647,0.0004460262,0.9242456,0.0002430421],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000003773108,0.9779376,0.009191836,0.006553353,0.002724319,0.002066682,0.00002986816,0.0001331327,0.001359412],"genre_scores_gemma":[0.00001014823,0.9781941,0.007612108,0.003651921,0.004384447,0.0001234748,0.0004588628,0.0001071825,0.005457785],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.882968,"threshold_uncertainty_score":0.9999229,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.0701277189664954,"gpt":0.462730770855044,"spread":0.3926030518885487,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005236773,0.0001909452,0.000877264,0.000212256,0.0002647412,0.00001210422,0.0003328324,0.00008638862,0.00004332369],"category_scores_gemma":[0.01100104,0.00009794466,0.000309864,0.0002433175,0.0003181738,0.0001534023,0.00006712019,0.0004373016,1.172506e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001735145,"about_ca_system_score_gemma":0.0002914858,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004771269,"about_ca_topic_score_gemma":0.0001347034,"domain_scores_codex":[0.9973792,0.0002816897,0.001203702,0.0002773407,0.0005292505,0.0003288289],"domain_scores_gemma":[0.9906096,0.006528929,0.001769519,0.0002521636,0.0007192499,0.0001205081],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.01075431,0.0007794281,0.007867189,0.0004468019,0.0003701003,0.000005760471,0.0120693,0.0006550071,0.00419343,0.0004409512,0.04001137,0.9224064],"study_design_scores_gemma":[0.09928455,0.03525828,0.02998498,0.03757437,0.006519222,0.0002055382,0.01344107,0.1220199,0.007259224,0.06093432,0.5862554,0.001263099],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5852872,0.004045705,0.2277207,0.1740111,0.002372443,0.005049673,0.001176486,0.00002215586,0.0003145791],"genre_scores_gemma":[0.9671516,0.009433816,0.01708546,0.004428205,0.001111459,0.0006598118,0.00001156622,0.00005360753,0.00006442503],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9211432,"threshold_uncertainty_score":0.9973297,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"Cancer Research UK","keywords":"Medicine; General hospital; Library science; Radiology; Family medicine; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.07186118850790842,"gpt":0.4365936879278374,"spread":0.364732499419929,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.01249267,0.0007999318,0.002639022,0.0004203855,0.0006876405,0.0002412152,0.001041271,0.003844087,0.000076075],"category_scores_gemma":[0.0486067,0.0005666174,0.0004636439,0.0003855197,0.002360888,0.0001173042,0.0002998096,0.008867634,0.00007535272],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005495137,"about_ca_system_score_gemma":0.001983654,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006690903,"about_ca_topic_score_gemma":0.00002394397,"domain_scores_codex":[0.9903615,0.003116566,0.001586744,0.002068511,0.001257071,0.001609645],"domain_scores_gemma":[0.9643269,0.03223108,0.0006411527,0.001494622,0.0008494291,0.0004567801],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001041303,0.0000696592,0.00009371317,0.0002730646,0.0004032659,0.0000746455,0.0003419837,0.00002344216,0.000382667,0.00181472,0.972885,0.02259652],"study_design_scores_gemma":[0.001119637,0.001815033,0.0000703701,0.0008591818,0.0004816361,0.0002172457,0.0004428391,0.001192432,0.00001837111,0.004354651,0.9889256,0.0005030198],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"editorial","genre_gemma":"editorial","genre_scores_codex":[0.0009472191,0.009343187,0.004276549,0.01750145,0.9646634,0.002233265,0.0002052824,0.0001265384,0.0007030719],"genre_scores_gemma":[0.0004257521,0.007041877,0.004010077,0.001728017,0.9831874,0.0002484638,0.002123386,0.0001920303,0.001042956],"genre_candidate":"editorial","genre_consensus":"editorial","teacher_disagreement_score":0.03611404,"threshold_uncertainty_score":0.9996786,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01276414941444599,"gpt":0.321780288592158,"spread":0.309016139177712,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006686129,0.0001068978,0.0003466404,0.00006866561,0.0001724698,0.00000780664,0.00009257536,0.0001310928,0.0001334323],"category_scores_gemma":[0.0001624462,0.00006568729,0.00006113059,0.00008396259,0.0006295299,0.00002416852,0.00001235796,0.0002255862,7.306131e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001177101,"about_ca_system_score_gemma":0.0002418462,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001346648,"about_ca_topic_score_gemma":0.000009046217,"domain_scores_codex":[0.9992242,0.0000741108,0.0002406727,0.000167519,0.00009516523,0.00019826],"domain_scores_gemma":[0.9991735,0.0004410347,0.00008715074,0.0001471791,0.00007988387,0.00007121592],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.002120214,0.0002137753,0.00578023,0.0002653415,0.0004719651,0.000008725527,0.01528759,0.00001125315,0.08167502,0.007159328,0.02382097,0.8631856],"study_design_scores_gemma":[0.003970989,0.001663019,0.004509893,0.00004943522,0.00005912434,0.0001819592,0.0003998184,0.006499417,0.006030632,0.0006854701,0.9758326,0.0001176902],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9420696,0.006645915,0.0251763,0.02144662,0.0008461648,0.0008199692,0.000003763148,0.00005187033,0.002939734],"genre_scores_gemma":[0.9566757,0.000446168,0.03471285,0.005651655,0.001059497,0.00004247903,0.000009179936,0.0000286836,0.001373779],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9520116,"threshold_uncertainty_score":0.267865,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.152109339428697,"gpt":0.4691862588096908,"spread":0.3170769193809938,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03976215,0.0003609471,0.004391814,0.001327875,0.0002070687,0.000073334,0.0005746174,0.0005884022,0.0001259795],"category_scores_gemma":[0.4460105,0.0002754735,0.0008250656,0.00069374,0.0001382495,0.00009448436,0.00005197186,0.004046754,0.000009895908],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004940921,"about_ca_system_score_gemma":0.005078908,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00194758,"about_ca_topic_score_gemma":0.001208652,"domain_scores_codex":[0.9902382,0.005175937,0.002169436,0.0004110699,0.001133685,0.0008716546],"domain_scores_gemma":[0.964917,0.03079964,0.002491015,0.000332901,0.0007803949,0.0006790169],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","study_design_scores_codex":[0.000007519538,0.00001623017,0.0009317398,0.6241889,0.0002809056,0.0002212006,0.00005956295,0.000003233255,1.806876e-7,0.00007880402,0.003472317,0.3707394],"study_design_scores_gemma":[0.0009643555,0.0001416504,0.00007755063,0.6242118,0.001998827,0.002527195,0.0000550373,0.004190386,6.14052e-8,0.0003134672,0.3652108,0.0003088505],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000001762261,0.9888203,0.002940688,0.004940175,0.000507429,0.002493427,0.00005465559,0.00002422861,0.0002173901],"genre_scores_gemma":[0.00002455619,0.9906147,0.007184095,0.0007974238,0.0003140599,0.0001482382,0.0001416176,0.00006623227,0.0007090827],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.4062483,"threshold_uncertainty_score":0.9999697,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1075127998060665,"gpt":0.3980224307440145,"spread":0.290509630937948,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009450258,0.00005699241,0.0002397619,0.00001870775,0.0006903283,0.00003884675,0.0002110194,0.00004357284,0.000007237186],"category_scores_gemma":[0.0005776716,0.00002991407,0.00002750759,0.00002846249,0.0005848614,0.00003330339,0.00006282112,0.0002562542,0.000002455798],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008883668,"about_ca_system_score_gemma":0.00008958207,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001623072,"about_ca_topic_score_gemma":0.00009306016,"domain_scores_codex":[0.9993519,0.0001182516,0.0001488323,0.00009992558,0.0001132456,0.0001678916],"domain_scores_gemma":[0.99895,0.0003363049,0.0002185986,0.0004165744,0.00003241486,0.00004609321],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.0008335382,0.0001940122,0.2413366,0.0001734164,0.0002374001,0.00006617209,0.006297978,0.00001768853,0.01757106,0.5205835,0.02576925,0.1869195],"study_design_scores_gemma":[0.002902955,0.0004000122,0.9016418,0.0001678012,0.0001969469,0.0002613093,0.007933341,0.0210456,0.0003767317,0.02579669,0.0391599,0.0001168428],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7148263,0.0006945445,0.001738046,0.2373168,0.0003340839,0.0002663116,0.000003237742,0.00003045864,0.0447902],"genre_scores_gemma":[0.9980209,0.0005439545,0.0005035645,0.0003091188,0.000242642,0.00001341602,0.000003792068,0.000008043946,0.0003545779],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6603053,"threshold_uncertainty_score":0.5309517,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.008464244655051951,"gpt":0.294619389023894,"spread":0.286155144368842,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002152824,0.000468023,0.0008507902,0.0006385671,0.000221619,0.0002622512,0.0005819218,0.0004305204,0.00009151366],"category_scores_gemma":[0.001116048,0.0004074828,0.0001361876,0.0008143832,0.001464024,0.0001380992,0.0005348498,0.002203008,0.00001555811],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003893967,"about_ca_system_score_gemma":0.001265924,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003258752,"about_ca_topic_score_gemma":0.00001053169,"domain_scores_codex":[0.9960375,0.0001454855,0.0007231853,0.001171456,0.001255325,0.0006669893],"domain_scores_gemma":[0.9979771,0.0003973127,0.0002890508,0.0005181339,0.0003067168,0.0005116628],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001612005,0.0001394189,0.0009059968,0.0004066404,0.00003779008,0.000624834,0.0002862371,0.0003022528,0.00009340385,0.0001217641,0.002585175,0.9944804],"study_design_scores_gemma":[0.001945914,0.0003871769,0.002615079,0.004113395,0.00006417119,0.002332351,5.739622e-7,0.980617,0.00009804056,0.001878379,0.005424517,0.0005234123],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003073061,0.001060564,0.9897184,0.001542161,0.002276974,0.0004220556,0.00000230071,0.0001087077,0.001795726],"genre_scores_gemma":[0.04965037,0.0002315519,0.9297026,0.0148684,0.003217545,0.000008738166,0.0001365877,0.0001606637,0.00202359],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.993957,"threshold_uncertainty_score":0.9998377,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01606163956372151,"gpt":0.3234553194129652,"spread":0.3073936798492437,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0009188878,0.0002189238,0.0006668064,0.0003818878,0.00002785504,0.00001326611,0.0000931492,0.00043339,0.0007295064],"category_scores_gemma":[0.0007443066,0.0001865805,0.00009238013,0.00008542866,0.00007106974,0.00003381682,0.00005669337,0.002329746,0.0002267745],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001056337,"about_ca_system_score_gemma":0.001546498,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001343605,"about_ca_topic_score_gemma":0.00002785554,"domain_scores_codex":[0.9985915,0.00008830115,0.0003902173,0.0003190705,0.0003507944,0.0002600497],"domain_scores_gemma":[0.9992001,0.0001384151,0.0001645751,0.0001828478,0.0000697247,0.0002443068],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000148978,0.0001254423,0.006042189,0.0002085832,0.00009825953,0.0008837256,0.000409553,0.0003344195,0.00003443716,0.003877931,0.3409317,0.6469048],"study_design_scores_gemma":[0.002036955,0.0003273441,0.0002593013,0.0001638257,0.000071372,0.0001570981,0.00001164452,0.03125056,0.000001611863,0.001442766,0.9641091,0.0001684137],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.0000931079,0.002884981,0.0002771741,0.00427067,0.0003447527,0.0002797599,0.000001691753,0.0001391352,0.9917088],"genre_scores_gemma":[0.001048849,0.0009156853,0.001377239,0.001916973,0.0006978185,0.000009616102,0.0006741121,0.00007142536,0.9932883],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.6467364,"threshold_uncertainty_score":0.9999719,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01683635680560899,"gpt":0.3190334353009178,"spread":0.3021970784953088,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001826328,0.0001680577,0.0004513555,0.000465319,0.000988499,0.0005762182,0.000232467,0.00007977305,0.0001200164],"category_scores_gemma":[0.0005785862,0.0001398989,0.0004365484,0.0003990652,0.0003144299,0.00008930449,0.00005599873,0.0002020663,0.000002546157],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009628225,"about_ca_system_score_gemma":0.0004842303,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002205206,"about_ca_topic_score_gemma":0.00003623172,"domain_scores_codex":[0.9978816,0.00001597691,0.0004545981,0.0008300446,0.0004000731,0.0004176975],"domain_scores_gemma":[0.9973819,0.0000500881,0.0006063131,0.001391603,0.0002687285,0.0003013427],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002763526,0.0001425216,0.9579125,0.0002859924,0.0003264614,0.0002944096,0.0001513318,0.001111703,0.01442695,0.000006679339,0.02002202,0.005291822],"study_design_scores_gemma":[0.001928932,0.00007732679,0.1289915,0.0002922095,0.004482311,0.00005670454,0.00003612032,0.7388674,0.04654443,0.0002388742,0.07800521,0.0004790128],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9581801,0.0003044317,0.02947401,0.00336574,0.00530533,0.001082002,0.000006660791,0.00006812902,0.002213645],"genre_scores_gemma":[0.9792932,0.000008846494,0.01118766,0.0002250181,0.0002559935,0.0001901669,0.000097931,0.00003035746,0.008710871],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.828921,"threshold_uncertainty_score":0.7602836,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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)","retraction":null,"screen_n_in":null,"score":{"opus":0.2044532537495304,"gpt":0.4761892435788327,"spread":0.2717359898293022,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.008619542,0.0004328747,0.0009479658,0.001246203,0.0005768002,0.0005651902,0.0005079747,0.0002153878,0.00005995066],"category_scores_gemma":[0.01181555,0.0003479626,0.0004288628,0.001607663,0.0006368198,0.0004069675,0.0002645487,0.002180843,0.00004199052],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008029742,"about_ca_system_score_gemma":0.0004506043,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003013608,"about_ca_topic_score_gemma":0.000002637358,"domain_scores_codex":[0.9947859,0.0008363351,0.001022821,0.001240433,0.001060565,0.001053926],"domain_scores_gemma":[0.9919667,0.006336384,0.0001294351,0.0007029065,0.0004022237,0.0004624028],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0007037583,0.0003415963,0.01119621,0.002294079,0.0004813357,0.0008097054,0.004351325,0.00009292826,0.319403,0.03462314,0.04868111,0.5770218],"study_design_scores_gemma":[0.004608246,0.0003776506,0.001306397,0.00157034,0.0003081421,0.0005786963,0.0006822543,0.3729048,0.02858558,0.03238804,0.5555844,0.001105379],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5114394,0.02354412,0.4467962,0.01065178,0.00244241,0.001664953,0.00001855414,0.0007354398,0.002707092],"genre_scores_gemma":[0.8737165,0.0009714761,0.1201658,0.001779773,0.001695028,0.0001886228,0.0001266511,0.0001771542,0.001178958],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5759165,"threshold_uncertainty_score":0.9998972,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Robarts Clinical Trials; Sunnybrook Hospital; Queen's University","funders":"","keywords":"Computer science; Intervention (counseling); Medicine; Nursing","retraction":null,"screen_n_in":null,"score":{"opus":0.011788956385331,"gpt":0.2917829354307164,"spread":0.2799939790453854,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001944962,0.0004551426,0.0008263336,0.0006767006,0.0001955182,0.0001801274,0.0007395483,0.0004308609,0.0001863931],"category_scores_gemma":[0.0003869535,0.0003877044,0.0001764758,0.0002982747,0.001618995,0.0001526338,0.000924592,0.002106072,0.00003713903],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002743704,"about_ca_system_score_gemma":0.0007245329,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001183949,"about_ca_topic_score_gemma":0.00002332567,"domain_scores_codex":[0.9963409,0.00010504,0.0007006068,0.001152732,0.001074051,0.0006266249],"domain_scores_gemma":[0.9980056,0.0004351979,0.000310005,0.0005486101,0.0001934137,0.0005071887],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002410869,0.000131614,0.001051374,0.0003544985,0.00003565999,0.0005189636,0.000549893,0.00006671566,0.00009493483,0.0001009267,0.0008082029,0.9962631],"study_design_scores_gemma":[0.00194147,0.0005681323,0.009743091,0.004473743,0.00008208948,0.0021507,6.469559e-7,0.9740052,0.000149016,0.003736857,0.002552445,0.00059657],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005114376,0.0008777425,0.9887007,0.001278611,0.001875322,0.0003635616,0.000002186137,0.000138644,0.001648826],"genre_scores_gemma":[0.1997485,0.0002437036,0.7852788,0.008547442,0.004523069,0.000008748731,0.0001256366,0.0001687232,0.001355381],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9956666,"threshold_uncertainty_score":0.9998575,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01829434343786143,"gpt":0.334440177149113,"spread":0.3161458337112516,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008977373,0.00009059903,0.0002724378,0.0001422705,0.0001969962,0.00004616374,0.00004663278,0.00003534147,0.0003624847],"category_scores_gemma":[0.001086579,0.00008375874,0.0000958329,0.0004042031,0.0003054104,0.00007130016,0.00004664263,0.0002988151,0.00000164687],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001202797,"about_ca_system_score_gemma":0.0004056227,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009776297,"about_ca_topic_score_gemma":0.000006511461,"domain_scores_codex":[0.998391,0.0000773585,0.0004486419,0.0004921097,0.0003707555,0.0002201558],"domain_scores_gemma":[0.9987489,0.00004034462,0.0003611516,0.0004103697,0.000325609,0.0001136409],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000006466436,0.00006761876,0.3375939,0.0001783974,0.00004927183,0.001748544,0.0002574994,0.001520453,0.6358998,0.00006303495,0.002521124,0.02009386],"study_design_scores_gemma":[0.0008697722,0.00004436214,0.1231002,0.0007561995,0.0006451641,0.01167265,0.0005864266,0.6461361,0.1078622,0.0008876281,0.1070022,0.0004371501],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9793729,0.003532905,0.009046453,0.001011855,0.00430127,0.0001202732,2.88558e-7,0.00004763491,0.002566406],"genre_scores_gemma":[0.9910766,0.00004289223,0.004186785,0.00005728687,0.00009650017,0.000005636424,0.00004350308,0.00001743809,0.004473303],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6446157,"threshold_uncertainty_score":0.3968953,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01635311578946379,"gpt":0.2895553287678998,"spread":0.273202212978436,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.003068934,0.001264413,0.01305979,0.0008162734,0.0001162442,0.00002822023,0.0005522407,0.0004395127,0.0001539892],"category_scores_gemma":[0.003957863,0.0008347894,0.003627547,0.002213062,0.0006526273,0.00007731425,0.0001224914,0.004257249,0.00004387096],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006096766,"about_ca_system_score_gemma":0.0009071719,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001533219,"about_ca_topic_score_gemma":7.443239e-7,"domain_scores_codex":[0.9927493,0.001406088,0.001474336,0.001554784,0.001967524,0.0008479704],"domain_scores_gemma":[0.9964828,0.0004135646,0.0005046697,0.001571181,0.0001867643,0.0008409936],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003592454,0.00005425782,0.001522331,0.1093308,0.004749879,0.002924281,0.00003271773,0.00001085148,5.048176e-8,0.000001540138,0.04357252,0.8377649],"study_design_scores_gemma":[0.00209615,0.0004226903,0.00002614277,0.1955334,0.02310752,0.0003144502,0.00002028567,0.0006725849,1.588678e-7,0.000001981069,0.777202,0.0006026541],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[1.123482e-7,0.9784982,0.01123346,0.004202639,0.001398662,0.003121978,0.00002379764,0.0002316144,0.001289504],"genre_scores_gemma":[0.000001166748,0.977912,0.01662846,0.001541803,0.001375383,0.0009639385,0.001085818,0.000357679,0.0001337426],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.8371622,"threshold_uncertainty_score":0.9994103,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.06673218546828867,"gpt":0.3641202994435485,"spread":0.2973881139752598,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004631351,0.0001455097,0.0004480319,0.0007097723,0.0003589398,0.00001129774,0.0004817271,0.0001881279,0.0003688638],"category_scores_gemma":[0.001212709,0.0001561007,0.0001088844,0.001015425,0.001619888,0.0002630974,0.0003685898,0.001395353,0.00001216983],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004698464,"about_ca_system_score_gemma":0.0003471225,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004003164,"about_ca_topic_score_gemma":0.001111676,"domain_scores_codex":[0.9963472,0.000692836,0.0002646011,0.0004204123,0.00189651,0.0003783852],"domain_scores_gemma":[0.9978568,0.000698037,0.0002916027,0.000367907,0.0005724879,0.000213174],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003139547,0.003442811,0.09597633,0.004741004,0.00105348,0.01230514,0.1018097,0.001688894,0.05342663,0.002769163,0.03035956,0.6892878],"study_design_scores_gemma":[0.01049251,0.001498261,0.1977971,0.001443984,0.0003172856,0.000199445,0.2926798,0.4711973,0.0001556171,0.0001797221,0.02360632,0.0004325695],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9904842,0.0003088118,0.0009267642,0.005239587,0.00003668233,0.0006432902,0.00005420433,0.000037873,0.002268594],"genre_scores_gemma":[0.9958972,0.001736482,0.001548438,0.00002076413,0.00002465269,2.105704e-7,0.0004789032,0.00001351924,0.00027988],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6888552,"threshold_uncertainty_score":0.6365603,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02121364223199364,"gpt":0.2897854946914529,"spread":0.2685718524594593,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000562795,0.0001502704,0.0004055745,0.0001613544,0.00002566789,0.00001246606,0.0001633884,0.0001005396,0.00009883293],"category_scores_gemma":[0.001065466,0.0001154046,0.00007684279,0.0002324196,0.00009777751,0.00005666915,0.00003850003,0.0005471883,0.00001114024],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000210768,"about_ca_system_score_gemma":0.0004224023,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001086427,"about_ca_topic_score_gemma":0.000002054099,"domain_scores_codex":[0.9986455,0.0001508498,0.0003405322,0.0002621368,0.0003370397,0.000263908],"domain_scores_gemma":[0.9990135,0.0003002504,0.0001778674,0.0001997947,0.00008721874,0.0002213009],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001053246,0.001858852,0.7735867,0.0003318756,0.00001336577,0.002352284,0.0006275863,0.00143168,0.2024077,0.00004445154,0.00635655,0.009935668],"study_design_scores_gemma":[0.03846369,0.01068244,0.749384,0.0004464977,0.0005268058,0.0007268794,0.0003864356,0.09005867,0.09854249,0.00101425,0.008854536,0.000913261],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9939413,0.0004784837,0.0002992481,0.001706497,0.000193128,0.0004409162,0.000002870853,0.00004241158,0.002895117],"genre_scores_gemma":[0.9947992,0.000005205791,0.004178732,0.0006622727,0.000145825,0.00002358968,0.0000356589,0.00001895972,0.0001305738],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1038652,"threshold_uncertainty_score":0.4706061,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.06928972278475067,"gpt":0.4398918690935059,"spread":0.3706021463087552,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002998249,0.0004223236,0.002173743,0.0002177621,0.0003121224,0.00009216955,0.0001880781,0.0004693138,0.00001756827],"category_scores_gemma":[0.005226847,0.0002488997,0.0006340257,0.0002736564,0.001127991,0.00005883719,0.0001091351,0.001016551,0.00001269846],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002513818,"about_ca_system_score_gemma":0.001128157,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001651938,"about_ca_topic_score_gemma":8.785457e-7,"domain_scores_codex":[0.9964172,0.0006746572,0.001235796,0.001028194,0.0002307646,0.0004133476],"domain_scores_gemma":[0.9959691,0.002589911,0.0004357552,0.0005752043,0.0002214265,0.0002086466],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003411933,0.00003046588,0.000005685198,0.005228534,0.001517287,0.00004547655,0.00009834803,8.013175e-7,0.00002841021,0.002356406,0.05685754,0.9334899],"study_design_scores_gemma":[0.001588227,0.0002863666,0.00001581832,0.002499338,0.002224707,0.0005528851,0.00002186566,0.001339597,0.000003366369,0.001182778,0.9900302,0.000254804],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0000552565,0.9390193,0.0550849,0.001319207,0.002130736,0.001657644,0.0001840818,0.00009233449,0.0004565958],"genre_scores_gemma":[0.00005606059,0.9918259,0.005217696,0.0002983804,0.001144341,0.0002239873,0.0007048654,0.00009662148,0.0004321264],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.933235,"threshold_uncertainty_score":0.9999963,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1001407464111719,"gpt":0.4829447736101836,"spread":0.3828040271990117,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004846701,0.0007153359,0.002696137,0.001286846,0.0002306493,0.0001367554,0.0009297198,0.0008400144,0.00049621],"category_scores_gemma":[0.01658091,0.0006418227,0.0007108774,0.001559478,0.0006416354,0.0001059918,0.0002694045,0.001898285,0.001448208],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004918005,"about_ca_system_score_gemma":0.00123228,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001769772,"about_ca_topic_score_gemma":0.00007053543,"domain_scores_codex":[0.9930041,0.0004260108,0.003207052,0.001488981,0.000671034,0.001202804],"domain_scores_gemma":[0.9952793,0.002570184,0.0004805596,0.0007426724,0.0002548869,0.0006723619],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0000996504,0.0001196044,0.00002384989,0.002878004,0.00009559378,0.00043271,0.0001645118,0.0003123898,0.000008816275,0.0136402,0.001080465,0.9811442],"study_design_scores_gemma":[0.00007127442,0.0002802895,0.00000876888,0.01408557,0.000512269,0.001240173,0.0001864769,0.07954095,0.0001406157,0.01505991,0.8878598,0.001013961],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00006206585,0.4996155,0.4889828,0.003971616,0.00309086,0.003376429,0.00005025457,0.0003470738,0.0005033814],"genre_scores_gemma":[0.0002411064,0.984997,0.00778197,0.001139873,0.003210947,0.001082319,0.0003986454,0.0002648926,0.0008832719],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9801303,"threshold_uncertainty_score":0.9996033,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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)","retraction":null,"screen_n_in":null,"score":{"opus":0.009524723942521691,"gpt":0.3205935885383795,"spread":0.3110688645958578,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008039452,0.000132149,0.0004403995,0.000177154,0.00008979,0.00005205758,0.0001043451,0.00001469418,0.001645344],"category_scores_gemma":[0.001772995,0.00008838154,0.0001673589,0.0009172283,0.0002092461,0.0000732952,0.00008859398,0.0006014485,0.0000219097],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004746037,"about_ca_system_score_gemma":0.0001318005,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003158035,"about_ca_topic_score_gemma":0.0002822911,"domain_scores_codex":[0.998179,0.000165132,0.0003570565,0.0003475502,0.0006884378,0.0002628715],"domain_scores_gemma":[0.9990677,0.0001981572,0.00006453217,0.0002894274,0.00007002192,0.0003101988],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000153823,0.001914787,0.614062,0.0005927432,0.003778685,0.1041826,0.002801018,0.00006824236,0.005461352,0.0006970323,0.00682184,0.2594659],"study_design_scores_gemma":[0.008366926,0.0002466285,0.4561817,0.0005669863,0.004851155,0.004988658,0.004218274,0.4961246,0.001195922,0.0005351261,0.02209826,0.0006257548],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9315662,0.001685682,0.00222063,0.06232565,0.00007063656,0.0001114646,0.000001940773,0.00003198054,0.001985792],"genre_scores_gemma":[0.9880181,0.0009808907,0.003254615,0.006613506,0.0001948908,0.00002076658,0.00007440078,0.00001798357,0.0008248326],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4960563,"threshold_uncertainty_score":0.9992673,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.06691848413472225,"gpt":0.3756019168080468,"spread":0.3086834326733246,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003598278,0.0002103695,0.0008000594,0.0004701363,0.0001517624,0.00003925449,0.00006850566,0.0005030729,0.000002705658],"category_scores_gemma":[0.0001528831,0.0001551166,0.0000604777,0.0001074547,0.0002883932,0.00004507122,0.00007627699,0.000915075,4.47564e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001350757,"about_ca_system_score_gemma":0.0004110381,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":8.298039e-7,"about_ca_topic_score_gemma":6.737619e-7,"domain_scores_codex":[0.9987387,0.00003790132,0.0006211558,0.000303121,0.0001031477,0.0001959608],"domain_scores_gemma":[0.9993473,0.0002095656,0.0002352187,0.00005197302,0.00005258657,0.0001033683],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003819166,0.000007643456,0.00004099041,0.001114164,0.00008907502,0.00001477787,0.00006231303,0.0002998471,0.000006048497,0.00244829,0.00002368838,0.995855],"study_design_scores_gemma":[0.0005872758,0.0002433306,0.0003463575,0.002056888,0.0002993153,0.01278819,0.00004136666,0.844804,0.0000027913,0.03302353,0.1055605,0.0002464002],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.01054652,0.8988759,0.08715827,0.002493083,0.00030223,0.0005725614,0.00001878817,0.00002466411,0.000007989639],"genre_scores_gemma":[0.003317243,0.9207709,0.07556703,0.0001177,0.00009437449,0.00001190528,0.00008633175,0.00001905978,0.00001541456],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9956086,"threshold_uncertainty_score":0.6325471,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01797630220835295,"gpt":0.3243917913262709,"spread":0.3064154891179179,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001550087,0.0001190322,0.0002814415,0.0002567947,0.0001150881,0.000096237,0.00006036269,0.00007315354,0.0007719782],"category_scores_gemma":[0.0005546977,0.0001012239,0.00008603614,0.0004560649,0.00009949032,0.0001227668,0.00004708046,0.000593093,0.000123715],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001418063,"about_ca_system_score_gemma":0.000123947,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002646379,"about_ca_topic_score_gemma":0.0000846452,"domain_scores_codex":[0.9979284,0.00004045271,0.0005440052,0.0006063731,0.0005423067,0.0003384434],"domain_scores_gemma":[0.9990757,0.00002705445,0.0001741169,0.000475883,0.00008137424,0.0001659343],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001173735,0.00004408515,0.9739534,0.00006891937,0.000009917097,0.0001803378,0.0003242197,0.004134229,0.007760718,0.00001035094,0.001523412,0.01197867],"study_design_scores_gemma":[0.000841281,0.00005368742,0.5391226,0.0003486987,0.00003601928,0.0005927635,0.00008673031,0.0476508,0.0001970431,0.0003782958,0.4105077,0.0001843343],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.984638,0.0003343718,0.0004047113,0.001008269,0.007976825,0.0003221056,2.426565e-7,0.0001167827,0.005198657],"genre_scores_gemma":[0.9646564,0.00001571609,0.0008934097,0.000199895,0.0001450358,0.00001773837,0.00005528873,0.00002246663,0.03399402],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4348308,"threshold_uncertainty_score":0.845262,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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)","retraction":null,"screen_n_in":null,"score":{"opus":0.01544506840489141,"gpt":0.3421089100691341,"spread":0.3266638416642427,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009322825,0.000201333,0.0006619751,0.0001936098,0.00008473873,0.00001590715,0.0001084313,0.00003375533,0.0004240317],"category_scores_gemma":[0.0001923718,0.0001731337,0.0000900304,0.000125182,0.0002378813,0.00006435672,0.00001182943,0.0003708814,7.872483e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004777165,"about_ca_system_score_gemma":0.0002838027,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001433452,"about_ca_topic_score_gemma":0.00001201145,"domain_scores_codex":[0.9986005,0.0002045219,0.0003713473,0.0003345918,0.00009894749,0.0003900898],"domain_scores_gemma":[0.999027,0.0003973185,0.0001405077,0.0001975564,0.00004778903,0.0001898529],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.1092718,0.002367893,0.4436555,0.0009743404,0.0009872514,0.009978279,0.01015356,0.000009032617,0.1980793,0.002174288,0.01068,0.2116688],"study_design_scores_gemma":[0.04005816,0.008662869,0.5491047,0.0003887634,0.0002342948,0.004082956,0.0002516041,0.1431931,0.001306062,0.0002979666,0.2515916,0.0008279091],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9848066,0.002591656,0.005092878,0.005896238,0.0004805065,0.0007782446,0.00001396817,0.00005807615,0.0002818125],"genre_scores_gemma":[0.9129558,0.00710154,0.06347652,0.01426398,0.000630114,0.0003522241,0.00002253968,0.0001293869,0.00106785],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2409116,"threshold_uncertainty_score":0.7060187,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.07307830830311975,"gpt":0.4508643951070561,"spread":0.3777860868039363,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008494128,0.0003178568,0.001978607,0.0002416029,0.0003334956,0.00004681927,0.0001627059,0.00008591483,0.001830883],"category_scores_gemma":[0.01136614,0.0002121442,0.0004319233,0.0003471799,0.0004892675,0.0001275507,0.00006939995,0.001459833,0.0000139817],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000144651,"about_ca_system_score_gemma":0.0001443635,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009935773,"about_ca_topic_score_gemma":8.644037e-7,"domain_scores_codex":[0.9951386,0.001355526,0.001521282,0.0005624607,0.001020167,0.0004019737],"domain_scores_gemma":[0.9962115,0.002337102,0.0006594682,0.0002465032,0.0001364934,0.0004089533],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"randomized_trial","study_design_scores_codex":[0.1275657,0.001357203,0.004453167,0.00005779624,0.0006106232,0.0001901759,0.003243143,0.0007296244,0.00147987,0.0001783422,0.002246889,0.8578875],"study_design_scores_gemma":[0.6593783,0.003488085,0.0004979505,0.0002796495,0.0003427302,0.00010439,0.0008818447,0.2637601,0.00003540176,0.0001549781,0.07076724,0.0003092963],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8771402,0.009041826,0.05811567,0.03707972,0.00397756,0.005920546,0.00004172785,0.0005846007,0.008098181],"genre_scores_gemma":[0.986001,0.001616191,0.0001812123,0.005427438,0.001407445,0.0003626175,0.0004556463,0.00007827608,0.004470152],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8575782,"threshold_uncertainty_score":0.9990816,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.05472248690862956,"gpt":0.3610442799395229,"spread":0.3063217930308933,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006223807,0.00008782888,0.0004298528,0.00007679441,0.0001243996,0.00001238437,0.00006135833,0.00003493416,0.000004968061],"category_scores_gemma":[0.001298491,0.00006952021,0.0001107491,0.0001633341,0.0002809361,0.00005440311,0.00002741417,0.00008407989,2.302258e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001932319,"about_ca_system_score_gemma":0.00006887598,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002704212,"about_ca_topic_score_gemma":3.062035e-7,"domain_scores_codex":[0.9987394,0.00001289752,0.000543495,0.0003009311,0.000261001,0.000142226],"domain_scores_gemma":[0.9987811,0.00009355592,0.0004255577,0.00021274,0.0004037925,0.00008318301],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001176471,0.000496843,0.2363336,0.007256458,0.0004803887,0.00002197079,0.01505048,0.008363462,0.5512027,0.0001380089,0.1544155,0.02506402],"study_design_scores_gemma":[0.002343026,0.0004198469,0.009804677,0.000329807,0.0002774472,0.00003565555,0.0005982616,0.7741048,0.2061608,0.0001573816,0.005630334,0.0001379037],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9841421,0.0008131754,0.01110375,0.001253752,0.001721351,0.0008710859,0.000004075818,0.00002400618,0.0000666487],"genre_scores_gemma":[0.9898901,0.00001418028,0.009417435,0.00008929572,0.00007684694,0.00002522841,0.00008182212,0.00001377041,0.0003913415],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7657413,"threshold_uncertainty_score":0.2834952,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.09798999134276305,"gpt":0.4732502850888995,"spread":0.3752602937461365,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001577797,0.0003269793,0.00290911,0.0007876876,0.00002367495,0.0000131909,0.0001359692,0.0004952924,0.00001690299],"category_scores_gemma":[0.0003802832,0.0002869307,0.0002140491,0.0002237604,0.0001708481,0.00005417729,0.0001260242,0.00200889,0.000009169943],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009594223,"about_ca_system_score_gemma":0.000912531,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002992459,"about_ca_topic_score_gemma":0.00005458475,"domain_scores_codex":[0.9967161,0.0006551193,0.001264286,0.0006433131,0.0001731008,0.0005480878],"domain_scores_gemma":[0.9986504,0.0004210624,0.0004349118,0.0002594262,0.00002271241,0.0002114656],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004764814,0.0001273359,0.01004259,0.008291012,0.00008338704,0.0000863964,0.0002882008,0.00000105602,2.668545e-8,0.00005832488,0.002216759,0.9787573],"study_design_scores_gemma":[0.002940518,0.0005553032,0.0008775404,0.004120363,0.0003896907,0.00009273022,0.0004429708,0.0005044838,2.625624e-8,0.00006862425,0.9897823,0.0002254173],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0005456982,0.9929779,0.000293314,0.0005017825,0.004315858,0.00109731,0.000009184098,0.00002196195,0.0002370339],"genre_scores_gemma":[0.00003395877,0.9959149,0.00336436,0.0001012837,0.0003655676,0.00006625002,0.00007588224,0.00005163297,0.00002619082],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9875656,"threshold_uncertainty_score":0.9999583,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03217788701264307,"gpt":0.3455962183969238,"spread":0.3134183313842807,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003788785,0.0002029901,0.000391664,0.00007292017,0.000288287,0.00004546418,0.0003475776,0.00006861446,0.000117688],"category_scores_gemma":[0.001648709,0.00007740439,0.00005732041,0.0003966486,0.0006129771,0.00008846994,0.0001530688,0.000490535,0.000004233814],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000480051,"about_ca_system_score_gemma":0.0001315931,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002392891,"about_ca_topic_score_gemma":0.001239368,"domain_scores_codex":[0.9979004,0.0002600467,0.0004779563,0.000263672,0.0006176584,0.0004802532],"domain_scores_gemma":[0.9978132,0.0007963789,0.0001726278,0.0006362017,0.0001320265,0.0004495934],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001398629,0.0002138403,0.05800657,0.0008973978,0.0007032657,0.00001372348,0.03416641,0.00002280278,0.04933441,0.001773831,0.5393242,0.3141449],"study_design_scores_gemma":[0.002574987,0.0006810051,0.03138043,0.003139061,0.0004246168,0.00009372293,0.01603195,0.0002393066,0.00123314,0.0001215115,0.9438436,0.0002366538],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.3105895,0.01206837,0.0005199701,0.6725109,0.0005266404,0.00283739,0.000005104311,0.00003626346,0.0009059616],"genre_scores_gemma":[0.9508746,0.001775349,0.002857506,0.03793407,0.002266706,0.0007075118,0.00001472823,0.00007351996,0.003496015],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6402851,"threshold_uncertainty_score":0.3617352,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02466386476580567,"gpt":0.3268608859389012,"spread":0.3021970211730955,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001457129,0.0001742787,0.0003488159,0.0001762214,0.0002073623,0.00001297709,0.00005411903,0.00002119571,0.00009646875],"category_scores_gemma":[0.00005704291,0.0001448706,0.0001146923,0.000131797,0.0002194764,0.0000941062,7.538318e-7,0.0002507784,0.000001329543],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001214311,"about_ca_system_score_gemma":0.0002349722,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001745988,"about_ca_topic_score_gemma":0.000004197155,"domain_scores_codex":[0.9987354,0.00003918702,0.0003459843,0.0002754837,0.0003663023,0.0002376921],"domain_scores_gemma":[0.9992287,0.0001669577,0.0001230681,0.0001445397,0.00006493238,0.0002717726],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008999105,0.0007929967,0.03070689,0.0004013759,0.0002169058,0.0006470869,0.0009287798,0.001933189,0.04456281,0.00001304318,0.0002408146,0.9186562],"study_design_scores_gemma":[0.01162041,0.0005587104,0.03534946,0.001244129,0.000321307,0.001489545,0.00007570916,0.9156489,0.0280783,0.000008064168,0.005297896,0.0003076184],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6416012,0.0001463532,0.3532216,0.004272076,0.0003261841,0.0003178334,0.00002318819,0.00005428269,0.0000373147],"genre_scores_gemma":[0.9963363,0.0003397438,0.001431614,0.001337223,0.0001486551,0.00009613462,0.00006745176,0.000031942,0.0002108897],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9183486,"threshold_uncertainty_score":0.5907651,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01875206941140932,"gpt":0.3295022001419946,"spread":0.3107501307305853,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.000427836,0.0006942483,0.002961073,0.0007831957,0.0001505911,0.00008946025,0.0003954405,0.0003081139,0.0001109218],"category_scores_gemma":[0.001362374,0.0005392594,0.00057599,0.0008781602,0.0002598081,0.0001338423,0.0002421814,0.004298551,0.0002679154],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004801684,"about_ca_system_score_gemma":0.0004326033,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009474809,"about_ca_topic_score_gemma":0.000004477831,"domain_scores_codex":[0.9964503,0.0004743408,0.001080477,0.0009852598,0.0003853229,0.00062428],"domain_scores_gemma":[0.9982681,0.0004207801,0.0003938479,0.0004547909,0.00005779069,0.0004046539],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0000115075,0.00004165499,0.0004651099,0.004530748,0.0001477101,0.002330753,0.000912305,0.00001944265,0.000004427436,0.000117862,0.0002799533,0.9911385],"study_design_scores_gemma":[0.0006439958,0.00004408663,0.00002481742,0.0164805,0.0005928837,0.0009585823,0.00004221235,0.01704873,6.021216e-7,0.0002313822,0.9634386,0.0004936488],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00001051845,0.9897475,0.003214747,0.001042506,0.000582289,0.0006983789,1.984174e-7,0.0002432866,0.004460586],"genre_scores_gemma":[0.000196535,0.9899898,0.00714571,0.0009732075,0.0009850592,0.00008511807,0.0001062082,0.0001968336,0.0003215016],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9906449,"threshold_uncertainty_score":0.9997059,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}