{"meta":{"query_hash":"8ecfb07cf6d9","filters":{"venue":"npj Digital Medicine"},"cohort_total":214,"direct_labels_cover":0,"predictions_cover":214,"exported":214,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/8ecfb07cf6d9","api":"https://metacan.xera.ac/api/v1/cohort?venue=npj+Digital+Medicine"},"results":[{"id":"W2804721547","doi":"10.1038/s41746-017-0014-0","title":"Lab-on-chip technology for chronic disease diagnosis","year":2018,"lang":"en","type":"review","venue":"npj Digital Medicine","topic":"Microfluidic and Capillary Electrophoresis Applications","field":"Engineering","cited_by":167,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Seven Oaks General Hospital; University of Manitoba","funders":"Canadian Institutes of Health Research; Natural Sciences and Engineering Research Council of Canada; Mitacs; Chinese Academy of Sciences; University of Manitoba","keywords":"Bottleneck; Intensive care medicine; Medicine; Risk analysis (engineering); Emerging technologies; Health care; Kidney disease; Computer science; Data science; Artificial intelligence; Embedded system","score_opus":0.02184455016158873,"score_gpt":0.28305930699198895,"score_spread":0.26121475683040024,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2804721547","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000011838252,0.99410385,0.00036871302,0.00025202273,0.00028157255,0.001242424,0.00041534004,0.000429545,0.0028946688],"genre_scores_gemma":[0.00017127313,0.9942122,0.000005601452,0.000048561407,0.0014727239,0.0027772705,0.0007333986,0.00014116829,0.0004377703],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99848986,0.0000074486793,0.00048153094,0.0004263106,0.00016254577,0.00043231796],"domain_scores_gemma":[0.99875355,0.00021810035,0.00008336574,0.000683523,0.000051957737,0.00020949125],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00006272344,0.00046961222,0.0010489495,0.0003324947,0.00007149451,0.000025753983,0.0004334891,0.0002834771,0.00014756017],"category_scores_gemma":[0.00017042324,0.00035270743,0.00023448202,0.00052593945,0.00022816613,0.000048270253,0.000042814154,0.00026033167,0.0004010434],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000021820783,0.0000215615,8.9525247e-7,0.0053568343,0.00011003133,0.0000040203568,0.0000034913446,1.1431379e-7,0.0000030812025,0.0017544499,0.36858693,0.6241564],"study_design_scores_gemma":[0.00019368266,0.00030441862,7.354078e-7,0.006381599,0.00041121157,0.000009467931,0.000003002407,0.000005500072,0.000017335062,0.00080760283,0.99155277,0.00031269947],"about_ca_topic_score_codex":4.0716762e-7,"about_ca_topic_score_gemma":3.396661e-7,"teacher_disagreement_score":0.6238437,"about_ca_system_score_codex":0.00026142315,"about_ca_system_score_gemma":0.00012522936,"threshold_uncertainty_score":0.9998925},"labels":[],"label_agreement":null},{"id":"W2889893184","doi":"10.1038/s41746-018-0053-1","title":"Agile research to complement agile development: a proposal for an mHealth research lifecycle","year":2018,"lang":"en","type":"review","venue":"npj Digital Medicine","topic":"Mobile Health and mHealth Applications","field":"Health Professions","cited_by":121,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; Université Laval; University of Ottawa","funders":"Canadian Institutes of Health Research; Health Canada; Public Health Agency; Public Health Agency of Canada; Sanofi","keywords":"mHealth; Agile software development; Process management; New product development; Product lifecycle; Computer science; Scrum; Knowledge management; Systems engineering; Risk analysis (engineering); Engineering; Health care; Medicine; Business; Software development; Software engineering; Software; Marketing","score_opus":0.6834930904629046,"score_gpt":0.6912984246389174,"score_spread":0.0078053341760128125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2889893184","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000038355127,0.854365,0.00039716807,0.010178076,0.0016857866,0.07487766,0.0011827435,0.00035847904,0.056916725],"genre_scores_gemma":[0.00008571417,0.82540184,0.0037882978,0.0016218799,0.008294997,0.14163749,0.0053193886,0.00032889022,0.013521504],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9853738,0.0024459239,0.0036129777,0.0018525567,0.002447891,0.004266827],"domain_scores_gemma":[0.98382384,0.0061501986,0.00067415024,0.0019008237,0.003467463,0.003983502],"candidate_categories":["metaepi_narrow","sts","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.020354303,0.00067699474,0.0025687183,0.0017905844,0.0050729397,0.00006624606,0.0015438873,0.0007969714,0.0008454703],"category_scores_gemma":[0.0047487495,0.00050645944,0.00015206597,0.0026637006,0.0006535968,0.0002413521,0.0008212186,0.0034552221,0.006045809],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000059254715,0.00019517864,0.000008855838,0.036933813,0.000019695402,0.0000015563058,0.0011966282,1.5522168e-8,1.7287584e-7,0.0054834546,0.41450658,0.5415948],"study_design_scores_gemma":[0.0009910567,0.0027674178,0.000021837515,0.029407239,0.000045447614,0.000005978364,0.0014512722,0.0000044591166,2.408162e-7,0.0017841494,0.9631712,0.00034971134],"about_ca_topic_score_codex":0.00045873574,"about_ca_topic_score_gemma":0.0012286489,"teacher_disagreement_score":0.54866457,"about_ca_system_score_codex":0.0024565484,"about_ca_system_score_gemma":0.024699818,"threshold_uncertainty_score":0.9997387},"labels":[],"label_agreement":null},{"id":"W2890069845","doi":"10.1038/s41746-018-0055-z","title":"Tracking health seeking behavior during an Ebola outbreak via mobile phones and SMS","year":2018,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"COVID-19 epidemiological studies","field":"Mathematics","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University; University of Waterloo","funders":"International Growth Centre; National Science Foundation","keywords":"Data collection; Outbreak; Health care; Population; Public health; Environmental health; Government (linguistics); Medicine; Matching (statistics); Population health; Public health surveillance; Survey data collection; Health facility; Tracking (education); Business; Medical emergency; Psychology; Statistics; Nursing; Economic growth; Economics","score_opus":0.18357386309470444,"score_gpt":0.4430421985880072,"score_spread":0.2594683354933027,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2890069845","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9942425,0.00050791795,0.002069931,0.0011090538,0.00022650616,0.00049123965,0.000012961907,0.0002630525,0.0010768604],"genre_scores_gemma":[0.9975965,0.00004512095,0.0006067485,0.00072563277,0.000777864,0.00006343796,0.000007592661,0.00003281533,0.0001442987],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99816644,0.00006217729,0.000575143,0.00044640878,0.00028432603,0.0004655112],"domain_scores_gemma":[0.998239,0.0008864595,0.00021973667,0.0003048871,0.00009208415,0.0002578663],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006240935,0.00025492645,0.00066582335,0.000078537545,0.00030492188,0.00004077971,0.00015395693,0.00008201567,0.00006872767],"category_scores_gemma":[0.0019694169,0.00017670708,0.000046415567,0.00015561293,0.0004723586,0.00030250638,0.00018166396,0.00018198446,0.000015204109],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023300078,0.00122024,0.2924385,0.0014269986,0.00018579345,0.00016347987,0.028467195,0.0000022525373,0.017289652,0.002077905,0.0022093512,0.6542856],"study_design_scores_gemma":[0.00652968,0.010867459,0.86669147,0.0026405605,0.0003333353,0.00052703195,0.011468655,0.0008474784,0.0022941928,0.08139797,0.014458816,0.0019433645],"about_ca_topic_score_codex":0.00016232501,"about_ca_topic_score_gemma":0.000114471804,"teacher_disagreement_score":0.65234226,"about_ca_system_score_codex":0.00010479194,"about_ca_system_score_gemma":0.000018911016,"threshold_uncertainty_score":0.7205906},"labels":[],"label_agreement":null},{"id":"W2890680583","doi":"10.1038/s41746-018-0059-8","title":"Beyond “implementation”: digital health innovation and service design","year":2018,"lang":"en","type":"review","venue":"npj Digital Medicine","topic":"Service and Product Innovation","field":"Business, Management and Accounting","cited_by":212,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Michael's Hospital; Women's College Hospital; University of Toronto","funders":"","keywords":"Value proposition; Digital health; Knowledge management; Service (business); Health technology; Process management; Health care; Work (physics); Service design; Computer science; Business; Engineering; Service provider; Marketing","score_opus":0.10612907177689702,"score_gpt":0.3603471578954226,"score_spread":0.2542180861185256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2890680583","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007522284,0.95874405,0.00074506743,0.01818882,0.0012110169,0.00211496,0.00007297387,0.00026737165,0.018580543],"genre_scores_gemma":[0.00046010863,0.8762067,0.00021704887,0.07923118,0.020088172,0.00019567345,0.022581931,0.00026328728,0.00075588946],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99743026,0.000012467794,0.0011803474,0.00057159323,0.00044915438,0.00035618973],"domain_scores_gemma":[0.99761766,0.00010709049,0.0011780233,0.0003582286,0.00071686105,0.000022162167],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006704244,0.00047394584,0.0009822509,0.0009377221,0.00019132058,0.00073194515,0.00027390986,0.00013959121,0.0002002039],"category_scores_gemma":[0.00024037823,0.00036995416,0.00004572926,0.003782595,0.00008288102,0.0031962253,0.00018498908,0.00021051895,0.00048289137],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006359749,0.000024150366,0.000018405844,0.011502924,0.00005590519,0.0000017347508,0.000059966278,4.772518e-8,1.2625314e-7,0.013948792,0.03420429,0.9401773],"study_design_scores_gemma":[0.0003957539,0.00007795416,0.000025396688,0.0039301547,0.00013168686,0.000015062705,0.00024251873,0.000008170223,1.2271539e-7,0.011180568,0.98366404,0.00032857977],"about_ca_topic_score_codex":0.00009994235,"about_ca_topic_score_gemma":0.000015369646,"teacher_disagreement_score":0.94945973,"about_ca_system_score_codex":0.000072712864,"about_ca_system_score_gemma":0.00016175545,"threshold_uncertainty_score":0.99987525},"labels":[],"label_agreement":null},{"id":"W2892370045","doi":"10.1038/s41746-018-0058-9","title":"Health intelligence: how artificial intelligence transforms population and personalized health","year":2018,"lang":"en","type":"editorial","venue":"npj Digital Medicine","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":256,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre","funders":"","keywords":"Health care; Data science; Analytics; Clinical decision support system; Big data; Computer science; Geocoding; Artificial intelligence; Visualization; Decision support system; Knowledge management; Data mining","score_opus":0.1329808311194993,"score_gpt":0.48456641142171236,"score_spread":0.3515855803022131,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2892370045","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001054178,0.0065296986,0.018148482,0.100873806,0.86329764,0.0057674297,0.0015908132,0.0006644626,0.0020734863],"genre_scores_gemma":[0.10811333,0.0068928814,0.0003456841,0.0031140293,0.87134975,0.00036597127,0.0054323906,0.00032697042,0.004058978],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9888033,0.0009036997,0.003691889,0.001764216,0.0025675048,0.0022693868],"domain_scores_gemma":[0.98989,0.004039849,0.0022100064,0.0009749044,0.0013561886,0.0015290616],"candidate_categories":["metaepi_narrow","sts","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.003978147,0.0011123929,0.002670653,0.0006996354,0.0021548045,0.00014237675,0.0007763221,0.0019576673,0.0007114182],"category_scores_gemma":[0.008265161,0.00089978246,0.00021177367,0.0009280708,0.0014918946,0.000747588,0.00022348431,0.0042765853,0.0004535842],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003082905,0.00007179316,0.00044769834,0.0028106642,0.00005004919,0.000008136706,0.01589292,9.667515e-7,8.965529e-7,0.0045552338,0.64704376,0.32880962],"study_design_scores_gemma":[0.00021226023,0.0038956683,0.000106082654,0.009399138,0.00005074129,0.000008931494,0.034831822,0.00067625934,0.0000072647144,0.045039304,0.90476394,0.0010085945],"about_ca_topic_score_codex":0.011119345,"about_ca_topic_score_gemma":0.008543573,"teacher_disagreement_score":0.32780102,"about_ca_system_score_codex":0.001935732,"about_ca_system_score_gemma":0.0035301382,"threshold_uncertainty_score":0.9993453},"labels":[],"label_agreement":null},{"id":"W2901612843","doi":"10.1038/s41746-019-0112-2","title":"Development and validation of a deep learning algorithm for improving Gleason scoring of prostate cancer","year":2019,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Prostate Cancer Diagnosis and Treatment","field":"Medicine","cited_by":500,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University Health Network","funders":"","keywords":"Prostate cancer; Medicine; Genitourinary system; Prostate; Scoring system; Reproducibility; Medical physics; Radiology; Cancer; Artificial intelligence; Algorithm; Computer science; Internal medicine; Statistics; Mathematics","score_opus":0.014864084460874949,"score_gpt":0.2718944423352889,"score_spread":0.257030357874414,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2901612843","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99452454,0.0027333188,0.0009332804,0.00018030632,0.00012266474,0.00093323074,0.000017154802,0.000017935568,0.00053754676],"genre_scores_gemma":[0.99567914,0.0001971946,0.0035686537,0.000025462505,0.000061246465,0.000121413024,0.0000842263,0.000019087312,0.00024355065],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990979,0.000004428631,0.00031975913,0.00020626023,0.00021238335,0.00015930363],"domain_scores_gemma":[0.9993889,0.0000766676,0.00020198345,0.00009110216,0.00016157095,0.0000798118],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012204004,0.0001199905,0.00035925527,0.00008118587,0.000023298633,0.0000074639397,0.000026253394,0.00003259189,0.000020500347],"category_scores_gemma":[0.00008455699,0.000088769186,0.00002971588,0.000097785814,0.00005158899,0.00013281405,0.000027131364,0.00005859755,0.0000010249039],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010237414,0.00006469036,0.11861265,0.00079338544,0.00007955764,0.0000021268884,0.001540702,0.000010073807,0.0047530658,0.000025515532,0.000006589158,0.87400925],"study_design_scores_gemma":[0.027080433,0.009913775,0.14505617,0.009365529,0.00071736757,0.000043398497,0.0059099244,0.009454699,0.7757813,0.00016819416,0.015885541,0.00062369695],"about_ca_topic_score_codex":0.000049220514,"about_ca_topic_score_gemma":0.0000022911422,"teacher_disagreement_score":0.87338555,"about_ca_system_score_codex":0.00009676451,"about_ca_system_score_gemma":0.00007923675,"threshold_uncertainty_score":0.36199024},"labels":[],"label_agreement":null},{"id":"W2918817626","doi":"10.1038/s41746-019-0087-z","title":"A computer vision system for deep learning-based detection of patient mobilization activities in the ICU","year":2019,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Intensive Care Unit Cognitive Disorders","field":"Medicine","cited_by":122,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canada Excellence Research Chairs, Government of Canada; Intermountain Healthcare","keywords":"Artificial intelligence; Computer science; Mobilization; Deep learning; Computer vision; Human–computer interaction; Physical medicine and rehabilitation; Medicine; Geography","score_opus":0.0064850073948668095,"score_gpt":0.2412217533211034,"score_spread":0.23473674592623658,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2918817626","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95092833,0.00007002272,0.04496801,0.00035990137,0.00036497976,0.0014753105,0.0000054876164,0.000037984206,0.0017899851],"genre_scores_gemma":[0.9984336,0.0000016777616,0.000030382786,0.0012349813,0.00007214926,0.000054245604,0.00012643966,0.000019227127,0.000027296046],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.99902976,0.000053158386,0.00027455218,0.00018188321,0.00031732142,0.00014335604],"domain_scores_gemma":[0.99789166,0.00051926874,0.00013767181,0.00014296011,0.0012779629,0.000030453537],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000154155,0.00012593315,0.0002947992,0.0002313358,0.000027495722,0.000010497416,0.000048484915,0.00006362687,0.000008329564],"category_scores_gemma":[0.0010488915,0.000080323,0.00007136603,0.00024720927,0.00009972122,0.00010891394,0.0000116580095,0.00013679918,0.0000049380055],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008337345,0.0011513804,0.05042138,0.0063975113,0.00023328747,0.000063492174,0.016908683,0.004434118,0.056413043,0.0004987296,0.0006944328,0.8544466],"study_design_scores_gemma":[0.03276602,0.08188103,0.056914773,0.015863426,0.0005096442,0.00025444027,0.39977023,0.33923045,0.05889905,0.00016424072,0.012817989,0.0009287039],"about_ca_topic_score_codex":0.000010871158,"about_ca_topic_score_gemma":0.000005984172,"teacher_disagreement_score":0.8535179,"about_ca_system_score_codex":0.000089917194,"about_ca_system_score_gemma":0.000025982396,"threshold_uncertainty_score":0.32754767},"labels":[],"label_agreement":null},{"id":"W2940900531","doi":"10.1038/s41746-019-0106-0","title":"Physician perspectives on integration of artificial intelligence into diagnostic pathology","year":2019,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":305,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; Princess Margaret Cancer Centre; University of Toronto","funders":"Brain Tumour Research; Brain Tumour Foundation of Canada; Conquer Cancer Foundation","keywords":"Workflow; Cohort; Workload; Enthusiasm; Psychology; Health care; Medicine; Medical laboratory; Medical education; Pathology; Family medicine; Computer science; Social psychology","score_opus":0.01716213315268671,"score_gpt":0.27697750791596953,"score_spread":0.2598153747632828,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2940900531","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3368481,0.00016674954,0.64587003,0.0018835218,0.001309603,0.00029723422,0.0000023020038,0.00011348778,0.013508986],"genre_scores_gemma":[0.9985616,0.000021934115,0.0008952439,0.00019947885,0.00024742444,0.00001168365,0.000003297074,0.000008144014,0.000051160565],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988869,0.000029923107,0.00026634327,0.00036774206,0.00030241278,0.00014670451],"domain_scores_gemma":[0.9987557,0.00050876685,0.00013643509,0.00041829856,0.0001350793,0.000045724366],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013547328,0.0001267516,0.00021249217,0.00015956114,0.000029202645,0.00003009811,0.00036529705,0.00005272294,0.000020956264],"category_scores_gemma":[0.00065196236,0.00010025305,0.000039781487,0.00042005721,0.00018513853,0.00049047766,0.00007294423,0.00015214559,0.00016418874],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026751663,0.000098396195,0.00010856902,0.000015752375,0.00000859732,0.0000070205474,0.008315265,0.00010016551,0.009038318,0.13489424,0.000075308824,0.8473116],"study_design_scores_gemma":[0.0010009824,0.022858677,0.0144679295,0.0020167031,0.000052650248,0.0000800666,0.037573442,0.068836115,0.20906764,0.6405617,0.0021822818,0.0013018115],"about_ca_topic_score_codex":0.000019753548,"about_ca_topic_score_gemma":0.0000062613776,"teacher_disagreement_score":0.8460098,"about_ca_system_score_codex":0.000104764506,"about_ca_system_score_gemma":0.00003221187,"threshold_uncertainty_score":0.40882006},"labels":[],"label_agreement":null},{"id":"W2945614313","doi":"10.1038/s41746-019-0125-x","title":"A systematic review of feasibility studies promoting the use of mobile technologies in clinical research","year":2019,"lang":"en","type":"review","venue":"npj Digital Medicine","topic":"Mobile Health and mHealth Applications","field":"Health Professions","cited_by":65,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Microsemi (Canada)","funders":"U.S. Food and Drug Administration; U.S. Department of Health and Human Services","keywords":"Computer science; Standardization; Terminology; Wearable computer; Electronic data capture; Systematic review; Mobile phone; Mobile device; Mobile technology; Data science; Clinical trial; Multimedia; World Wide Web; Embedded system; MEDLINE; Telecommunications; Medicine","score_opus":0.7680999171888864,"score_gpt":0.6899029819995458,"score_spread":0.07819693518934057,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2945614313","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000029356048,0.9420842,0.0000019553709,0.0011599195,0.0002974601,0.05581698,0.00010797533,0.00006433205,0.00043785028],"genre_scores_gemma":[0.0001215716,0.9660794,0.000028978231,0.00017778047,0.000099178265,0.033044174,0.000058587822,0.000037728933,0.00035261453],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9847093,0.0040364857,0.008930394,0.0006524126,0.00090904674,0.0007623357],"domain_scores_gemma":[0.95330626,0.03864734,0.0039973347,0.0024782177,0.0014222739,0.00014856516],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.021682564,0.00035062066,0.0073586134,0.00040833183,0.00020117956,0.0000039914817,0.0008677713,0.00057249196,0.00001927425],"category_scores_gemma":[0.10485655,0.00016649174,0.0003367498,0.001976375,0.0012009381,0.00011840118,0.000609378,0.0029579375,0.00009060304],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000048670304,0.00010583081,0.00018201777,0.8106721,0.000056270466,8.766069e-7,0.0002184966,1.0706563e-8,7.486833e-9,0.00037584922,0.0031936576,0.18518998],"study_design_scores_gemma":[0.0001796822,0.00030261368,0.000007365425,0.6557252,0.0002853568,0.0000024000349,0.0016076375,0.0000010890197,8.434165e-9,0.00012445686,0.34170198,0.00006224408],"about_ca_topic_score_codex":0.000046195244,"about_ca_topic_score_gemma":0.000025611358,"teacher_disagreement_score":0.33850834,"about_ca_system_score_codex":0.00039567507,"about_ca_system_score_gemma":0.0023080108,"threshold_uncertainty_score":0.99934226},"labels":[],"label_agreement":null},{"id":"W2948510341","doi":"10.1038/s41746-019-0116-y","title":"Smartphone-based migraine behavioral therapy: a single-arm study with assessment of mental health predictors","year":2019,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Migraine and Headache Studies","field":"Medicine","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Center for Complementary and Integrative Health; National Center for Advancing Translational Sciences; National Institute of Neurological Disorders and Stroke; U.S. Department of Health and Human Services; National Institutes of Health; Clinical and Translational Science Institute, New York University; American Brain Foundation; York University","keywords":"Migraine; Mental health; Behavioral therapy; Psychology; Psychiatry; Clinical psychology; Medicine","score_opus":0.03831925813497347,"score_gpt":0.34514958596201356,"score_spread":0.3068303278270401,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2948510341","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9826364,0.0006226733,0.000034227687,0.0055467677,0.00008827699,0.0023750921,0.000060960734,0.000096499694,0.008539095],"genre_scores_gemma":[0.9965485,0.000032154378,0.0001925742,0.0008601243,0.00015922327,0.000047413723,0.00024514575,0.00004926994,0.0018656012],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.997434,0.00004418049,0.00063370395,0.00043681596,0.0010335431,0.00041773138],"domain_scores_gemma":[0.9987115,0.000089099405,0.0002665157,0.0004916198,0.00016222529,0.00027902995],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031597467,0.00035295595,0.0010618594,0.00023804231,0.00007171201,0.000014043498,0.000117448675,0.000053855838,0.00034071627],"category_scores_gemma":[0.000031940388,0.00021711184,0.00012456022,0.0004054857,0.00027175038,0.00012313094,0.00004410248,0.0002514073,0.0000074350482],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001224329,0.011032875,0.9653433,0.0002068493,0.00037273977,0.000028409902,0.005306365,0.000001608259,0.0017718418,0.000021971702,0.010238807,0.004450935],"study_design_scores_gemma":[0.032081947,0.21046561,0.7182285,0.0014627246,0.00022001672,0.00005537262,0.018838752,0.000086061365,0.0003432544,0.000008609116,0.017815687,0.00039345716],"about_ca_topic_score_codex":0.00033405106,"about_ca_topic_score_gemma":0.0001557923,"teacher_disagreement_score":0.24711475,"about_ca_system_score_codex":0.0001723978,"about_ca_system_score_gemma":0.0003536499,"threshold_uncertainty_score":0.88535637},"labels":[],"label_agreement":null},{"id":"W2954565918","doi":"10.1038/s41746-019-0134-9","title":"Real-world heart rate norms in the Health eHeart study","year":2019,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Heart Rate Variability and Autonomic Control","field":"Medicine","cited_by":205,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Heart, Lung, and Blood Institute; Fonds de Recherche du Québec-Société et Culture; National Institutes of Health; National Institute of Biomedical Imaging and Bioengineering; U.S. Department of Health and Human Services","keywords":"Photoplethysmogram; Percentile; Medicine; Intraclass correlation; Demographics; Body mass index; Heart rate; Cohort; Cardiology; Internal medicine; Cardiovascular health; Physical therapy; Demography; Blood pressure; Disease; Statistics","score_opus":0.02434942508142618,"score_gpt":0.3197553516243565,"score_spread":0.2954059265429303,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2954565918","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89245576,0.00006594559,0.0000044914477,0.073382005,0.00031739683,0.0023778218,0.0000075138996,0.000067917994,0.031321142],"genre_scores_gemma":[0.9861788,0.000013611608,0.000012884302,0.008724076,0.00036669915,0.00004558248,0.00003233957,0.000022240283,0.0046037426],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9977765,0.00019090831,0.0007035556,0.00043522764,0.00041271266,0.0004811041],"domain_scores_gemma":[0.9983192,0.00057161937,0.000082924125,0.0007516252,0.00005606474,0.00021856319],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002372964,0.00022306251,0.0008072194,0.00021917892,0.000061692335,0.000043104836,0.00015377038,0.000050063456,0.00040914302],"category_scores_gemma":[0.00029076368,0.00012635108,0.000079946585,0.0006200823,0.00011440747,0.00020552542,0.000042045573,0.00047202536,0.0005516974],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00057555723,0.0032080822,0.9342058,0.0003290375,0.0001270511,0.00015003374,0.014203407,0.000015749449,0.0033090867,0.0016111871,0.0135365985,0.028728414],"study_design_scores_gemma":[0.0054121283,0.0040308186,0.85465425,0.00025743365,0.000023194387,0.00003490967,0.0041469126,0.00021080105,0.000011933454,0.00022515346,0.13084656,0.00014593176],"about_ca_topic_score_codex":0.001519508,"about_ca_topic_score_gemma":0.00058402057,"teacher_disagreement_score":0.11730996,"about_ca_system_score_codex":0.00017278042,"about_ca_system_score_gemma":0.00034970362,"threshold_uncertainty_score":0.7091138},"labels":[],"label_agreement":null},{"id":"W2955961229","doi":"10.1038/s41746-019-0136-7","title":"The use of photoplethysmography for assessing hypertension","year":2019,"lang":"en","type":"review","venue":"npj Digital Medicine","topic":"Non-Invasive Vital Sign Monitoring","field":"Engineering","cited_by":598,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Children's & Women's Health Centre of British Columbia; University of British Columbia","funders":"BC Children's Hospital; Children's Hospital Foundation","keywords":"Photoplethysmogram; Wearable computer; Wearable technology; Pulse oximetry; Computer science; Blood pressure; Oxygen saturation; Continuous monitoring; Pulse (music); Medicine; Biomedical engineering; Embedded system; Telecommunications; Wireless; Engineering; Internal medicine","score_opus":0.17560596526643585,"score_gpt":0.3235047375433279,"score_spread":0.14789877227689208,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2955961229","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00006645214,0.99441767,0.0010857009,0.000009450752,0.0023314538,0.0010871001,0.00006211744,0.00012492698,0.0008151441],"genre_scores_gemma":[0.0012018548,0.99745995,0.00022433235,0.000009653465,0.00065084064,0.000093899245,0.00010828392,0.0001514173,0.00009977342],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983443,0.000020464444,0.00069116737,0.00026265418,0.00032983845,0.000351562],"domain_scores_gemma":[0.9961938,0.0028896525,0.000209125,0.0004904749,0.00012795292,0.000088956505],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00015212473,0.00042962248,0.0014416303,0.00021812407,0.00006543891,0.0001291801,0.0003033286,0.0002117414,0.0000025984832],"category_scores_gemma":[0.00062887877,0.00024997123,0.0004317071,0.0004260084,0.00015130285,0.0004077856,0.00005973739,0.00029552839,0.000011507648],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000021756493,0.00000855369,0.000013612017,0.0115833655,0.00016767466,0.0000050597278,0.00001126237,0.000008659539,0.00017394006,0.000038932132,0.0019952464,0.98599154],"study_design_scores_gemma":[0.0002068951,0.00007952267,0.0000037489658,0.020707227,0.0003857956,0.000022426268,0.000021596283,0.000024838699,0.00004270715,0.000056149624,0.97819716,0.00025195203],"about_ca_topic_score_codex":0.000004031078,"about_ca_topic_score_gemma":4.232644e-7,"teacher_disagreement_score":0.9857396,"about_ca_system_score_codex":0.00007062828,"about_ca_system_score_gemma":0.00004589758,"threshold_uncertainty_score":0.99999523},"labels":[],"label_agreement":null},{"id":"W2971313112","doi":"10.1038/s41746-019-0163-4","title":"Developing a digital intervention for cancer survivors: an evidence-, theory- and person-based approach","year":2019,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Cancer survivorship and care","field":"Medicine","cited_by":61,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Programme Grants for Applied Research; National Institute for Health Research Southampton Biomedical Research Centre; National Institute for Health and Care Research","keywords":"Intervention (counseling); Psychological intervention; Intervention mapping; Focus group; Psychology; Theory of planned behavior; Theory of change; Cancer survivor; Medicine; Applied psychology; Medical education; Nursing; Cancer; Computer science; Health promotion; Public health; Sociology","score_opus":0.05973935156910082,"score_gpt":0.3326194398178664,"score_spread":0.2728800882487656,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2971313112","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9591169,0.003055929,0.028020196,0.0020212699,0.0006866668,0.0012772663,0.000092311835,0.00013373749,0.005595763],"genre_scores_gemma":[0.99620867,0.000031138177,0.00012500452,0.0007133889,0.00044708236,0.00015344533,0.00027517034,0.000046266658,0.0019998087],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9984848,0.00003565273,0.00029034866,0.0004998441,0.00037458361,0.00031479],"domain_scores_gemma":[0.9987145,0.00043682466,0.00010760632,0.00029576733,0.0002218743,0.00022340103],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00049164484,0.00024950938,0.00046628242,0.00015444674,0.000052853717,0.00011729997,0.000118823744,0.00010418729,0.0001219203],"category_scores_gemma":[0.00052892126,0.0001868828,0.000119237244,0.00023077767,0.00016768437,0.00074026984,0.000029106426,0.00014724767,0.000008582876],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.006265241,0.00043873015,0.25538018,0.0054552723,0.00035753066,0.00001933515,0.010536804,0.000016993798,0.00069580233,0.010387598,0.0005757885,0.70987076],"study_design_scores_gemma":[0.0828086,0.046281077,0.23210643,0.0777075,0.0029771167,0.0007024686,0.30503973,0.026944462,0.0040303636,0.017043168,0.19683562,0.0075234496],"about_ca_topic_score_codex":0.00043176787,"about_ca_topic_score_gemma":0.0002514008,"teacher_disagreement_score":0.7023473,"about_ca_system_score_codex":0.00017275759,"about_ca_system_score_gemma":0.00016360474,"threshold_uncertainty_score":0.762086},"labels":[],"label_agreement":null},{"id":"W2977779327","doi":"10.1038/s41746-019-0180-3","title":"How the weather affects the pain of citizen scientists using a smartphone app","year":2019,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Behavioral Health and Interventions","field":"Psychology","cited_by":96,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Engineering and Physical Sciences Research Council; Alan Turing Institute; Arthritis Australia; National Oceanic and Atmospheric Administration; Sight Research UK; Medical Research Council; Royal Society; Natural Environment Research Council; Versus Arthritis","keywords":"Smartphone app; Citizen science; Smartphone application; Mobile apps; Psychology; Computer science; Internet privacy; World Wide Web; Multimedia; Biology","score_opus":0.05508504235935677,"score_gpt":0.3545409939157637,"score_spread":0.2994559515564069,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2977779327","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95760363,0.0008522819,0.00045382202,0.0069721937,0.0016586618,0.0005615924,0.000023635248,0.000030798157,0.031843375],"genre_scores_gemma":[0.9821673,0.0000014843343,0.000012533717,0.00082697306,0.00019507123,0.000018885012,0.000010323218,0.000015584603,0.016751818],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9989503,0.0001324875,0.00019114139,0.00018752165,0.00025712527,0.0002814321],"domain_scores_gemma":[0.9990132,0.00023945652,0.00013160115,0.0004625327,0.00007307387,0.00008013184],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007578595,0.00011022304,0.00019315336,0.00006252945,0.00008375166,0.000037533002,0.000265606,0.00005735639,0.0009444665],"category_scores_gemma":[0.00016252897,0.00005279495,0.000088261535,0.0003052564,0.0003832403,0.00010245525,0.000044885914,0.00016590673,0.00011472378],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029427692,0.00078352465,0.08304558,0.00025059996,0.00015289312,0.000039009978,0.0077224937,0.0000017899304,0.008076847,0.017511692,0.19149685,0.6906244],"study_design_scores_gemma":[0.011377623,0.00882614,0.61119527,0.0030862407,0.0003854174,0.00038493,0.030919196,0.0006446719,0.0007586446,0.0036945285,0.32775798,0.0009693504],"about_ca_topic_score_codex":0.00011848986,"about_ca_topic_score_gemma":0.00001821728,"teacher_disagreement_score":0.68965507,"about_ca_system_score_codex":0.00002399318,"about_ca_system_score_gemma":0.000024156056,"threshold_uncertainty_score":0.9999688},"labels":[],"label_agreement":null},{"id":"W2989808997","doi":"10.1038/s41746-019-0191-0","title":"Artificial intelligence for precision medicine in neurodevelopmental disorders","year":2019,"lang":"en","type":"review","venue":"npj Digital Medicine","topic":"Genomics and Rare Diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":243,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"SickKids Foundation; Hospital for Sick Children","funders":"Mohammed Bin Rashid University of Medicine and Health Sciences; Al Jalila Foundation","keywords":"Precision medicine; Autism spectrum disorder; Autism; Intellectual disability; Psychological intervention; Neuropsychology; Neurodevelopmental disorder; Intervention (counseling); Disease; Artificial intelligence; Computer science; Psychology; Medicine; Cognition; Machine learning; Neuroscience; Psychiatry; Pathology","score_opus":0.0551165369490018,"score_gpt":0.34860490407117445,"score_spread":0.29348836712217263,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2989808997","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00029904608,0.9943127,0.00059913937,0.00014583823,0.00094738224,0.0013721674,0.00015774071,0.000009910172,0.002156059],"genre_scores_gemma":[0.005926392,0.9894307,0.000043396543,0.0001041154,0.0006894394,0.00011326872,0.003117511,0.000067491994,0.00050768134],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99797225,0.000027468579,0.0008281266,0.0006616318,0.00019804764,0.00031244944],"domain_scores_gemma":[0.99911094,0.00012449651,0.00022081357,0.0003717056,0.00004737743,0.00012469427],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000187447,0.00040797557,0.0009984445,0.00018798234,0.00003488177,0.000019910292,0.00037949905,0.00025090273,0.00003562308],"category_scores_gemma":[0.0006616033,0.00028340396,0.00020454382,0.00018497063,0.00018486154,0.0000060444204,0.0001524452,0.00013927725,0.000028293785],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044693094,0.00006037119,0.00001419747,0.0018680163,0.00003472395,0.000004526286,0.000025833233,0.0000022071877,0.000018207156,0.000084210056,0.0015831314,0.99625987],"study_design_scores_gemma":[0.00017103387,0.00074503775,0.00002045318,0.0038108197,0.00012006987,0.00002120451,0.000082661834,0.0000099323,0.0000068047875,0.0007373851,0.99395156,0.00032301652],"about_ca_topic_score_codex":0.000008447612,"about_ca_topic_score_gemma":0.000022751645,"teacher_disagreement_score":0.9959369,"about_ca_system_score_codex":0.000035703746,"about_ca_system_score_gemma":0.00020845458,"threshold_uncertainty_score":0.9999618},"labels":[],"label_agreement":null},{"id":"W2990990887","doi":"10.1038/s41746-019-0196-8","title":"Publisher Correction: Development and validation of a deep learning algorithm for improving Gleason scoring of prostate cancer","year":2019,"lang":"en","type":"erratum","venue":"npj Digital Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University Health Network","funders":"","keywords":"Prostate cancer; Algorithm; Computer science; Artificial intelligence; Machine learning; Cancer; Medicine; Internal medicine","score_opus":0.010074030973793646,"score_gpt":0.27254625596355025,"score_spread":0.2624722249897566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2990990887","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12561248,0.08656862,0.2374015,0.01000405,0.32910427,0.016270844,0.0001411247,0.0009363868,0.19396073],"genre_scores_gemma":[0.3232026,0.0023818382,0.022746952,0.0005737788,0.009671469,0.00053847954,0.00646706,0.0006449039,0.6337729],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99768585,0.000023228156,0.0007983137,0.0004903406,0.00066508545,0.00033719247],"domain_scores_gemma":[0.99808365,0.00020828999,0.0008001736,0.00020710909,0.00051164255,0.00018911628],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005554267,0.0003341236,0.0010353765,0.0003596524,0.000073266456,0.00005352842,0.000114719456,0.00026131407,0.00003584367],"category_scores_gemma":[0.0020353796,0.00026893336,0.00009178784,0.0002556713,0.00020993267,0.00028865488,0.00008925072,0.0009905,9.716035e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008689236,0.00004933899,0.0060420237,0.0029949227,0.00017089643,0.000005837737,0.001176825,0.000025869407,0.00014876387,0.0000050494127,0.05076277,0.9385308],"study_design_scores_gemma":[0.009214288,0.0030155638,0.0060305423,0.020311983,0.0011240053,0.00018864611,0.0023499883,0.12336182,0.0010324462,0.000090466165,0.83233696,0.00094330206],"about_ca_topic_score_codex":0.00015535337,"about_ca_topic_score_gemma":0.0000030653441,"teacher_disagreement_score":0.9375875,"about_ca_system_score_codex":0.00016378722,"about_ca_system_score_gemma":0.00043194942,"threshold_uncertainty_score":0.9999763},"labels":[],"label_agreement":null},{"id":"W2991289251","doi":"10.1038/s41746-020-0238-2","title":"Pan-cancer diagnostic consensus through searching archival histopathology images using artificial intelligence","year":2020,"lang":"en","type":"preprint","venue":"npj Digital Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Toronto General Hospital; Jacobs (Canada); Toronto Western Hospital; MaRS; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs; Government of Ontario; Ontario Research Foundation; Dell EMC","keywords":"Digital pathology; Telepathology; Computer science; Histopathology; Dermatopathology; Medical diagnosis; Artificial intelligence; Pathology; Medicine","score_opus":0.1344635809798248,"score_gpt":0.36839954069882636,"score_spread":0.23393595971900155,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2991289251","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019527905,0.0014268106,0.9525582,0.01491321,0.0059805056,0.00059577415,0.00008334645,0.00044485505,0.0044693705],"genre_scores_gemma":[0.9714648,0.0002911713,0.02490913,0.0007270247,0.0024240036,0.00007180581,0.000022700702,0.00005474429,0.000034617446],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9961301,0.00018098995,0.00084539375,0.0014184751,0.0008047051,0.00062034745],"domain_scores_gemma":[0.9964906,0.001699185,0.00046114225,0.00094844523,0.00018225069,0.00021836034],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003211328,0.00051652023,0.0007824957,0.00020789854,0.00018155128,0.00028662037,0.0014545199,0.00019381453,0.000026075966],"category_scores_gemma":[0.0026547168,0.00048083437,0.00015006866,0.0004360826,0.00095631456,0.00035981473,0.0023259963,0.0015645733,0.000055974302],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009628956,0.000109842294,0.00031253122,0.00053531444,0.00008932517,0.0012278347,0.0054953857,0.004975955,0.0057859337,0.029214464,0.0012661325,0.950891],"study_design_scores_gemma":[0.00026134835,0.0007272248,0.0016900301,0.0022043504,0.00013489557,0.00046416503,0.0002730593,0.08862531,0.006779724,0.8959275,0.0017711993,0.0011412255],"about_ca_topic_score_codex":0.000460829,"about_ca_topic_score_gemma":0.000012659977,"teacher_disagreement_score":0.9519369,"about_ca_system_score_codex":0.0004846593,"about_ca_system_score_gemma":0.00055864383,"threshold_uncertainty_score":0.9997643},"labels":[],"label_agreement":null},{"id":"W3003190198","doi":"10.1038/s41746-020-0219-5","title":"Individual-patient prediction of meningioma malignancy and survival using the Surveillance, Epidemiology, and End Results database","year":2020,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Meningioma and schwannoma management","field":"Medicine","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Montreal Children's Hospital; Montreal Neurological Institute and Hospital","funders":"National Institute of Biomedical Imaging and Bioengineering; Fonds de Recherche du Québec - Santé; Natural Sciences and Engineering Research Council of Canada; Fondation des Etoiles; Canada First Research Excellence Fund; Canada Research Chairs; National Institutes of Health; U.S. Department of Health and Human Services; Government of Canada; McGill University","keywords":"Generalizability theory; Logistic regression; Surveillance, Epidemiology, and End Results; Meningioma; Medicine; Malignancy; Random forest; Epidemiology; Machine learning; Artificial intelligence; Computer science; Radiology; Internal medicine; Cancer registry; Statistics","score_opus":0.10844842141037171,"score_gpt":0.30490896413714386,"score_spread":0.19646054272677216,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3003190198","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98201656,0.0016134413,0.000552458,0.0073012686,0.00019420173,0.00049710844,0.00044118482,0.000044082382,0.0073396913],"genre_scores_gemma":[0.9985068,0.00006609119,0.000453662,0.00033858122,0.00023956355,0.0000064182996,0.00033730228,0.000014122595,0.000037456124],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9981584,0.00011644681,0.00070813566,0.0003986713,0.00036791156,0.00025043328],"domain_scores_gemma":[0.9985625,0.0005502502,0.00027238275,0.00028089437,0.000075601725,0.00025834044],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00094850094,0.00019018057,0.00055175653,0.00009480856,0.00008119402,0.0000135461305,0.0000825163,0.000060454382,0.000015652611],"category_scores_gemma":[0.0022706643,0.00011780277,0.00003608906,0.00026574044,0.00045877523,0.00015508354,0.00020998204,0.00015136886,0.0000010434012],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0047492376,0.00034878103,0.8348512,0.001927909,0.0015542121,0.001596844,0.014690778,0.00004546308,0.017853178,0.007845768,0.02318191,0.091354735],"study_design_scores_gemma":[0.0168713,0.010203012,0.9185583,0.0021020523,0.0009946938,0.0017650137,0.0076662092,0.01148128,0.0009708379,0.00069208996,0.028062582,0.0006326488],"about_ca_topic_score_codex":0.000047856196,"about_ca_topic_score_gemma":0.0000012748695,"teacher_disagreement_score":0.090722084,"about_ca_system_score_codex":0.000014256513,"about_ca_system_score_gemma":0.00002650364,"threshold_uncertainty_score":0.48038575},"labels":[],"label_agreement":null},{"id":"W3004612364","doi":"10.1038/s41746-020-0221-y","title":"An overview of clinical decision support systems: benefits, risks, and strategies for success","year":2020,"lang":"en","type":"review","venue":"npj Digital Medicine","topic":"Electronic Health Records Systems","field":"Health Professions","cited_by":2827,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Health Services; University of Alberta Hospital; University of Alberta","funders":"Canadian Institutes of Health Research","keywords":"Risk analysis (engineering); Decision support system; Management science; Computer science; Business; Engineering; Artificial intelligence","score_opus":0.5559688032830784,"score_gpt":0.6346517270370996,"score_spread":0.0786829237540212,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3004612364","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00008308034,0.9841765,0.00046560174,0.00016349714,0.0034197564,0.006854425,0.0012050621,0.00013186049,0.0035002294],"genre_scores_gemma":[0.00093293464,0.9930804,0.000115005525,0.0001929837,0.003678038,0.00083771185,0.0008211712,0.00016126611,0.00018053716],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9891679,0.0011499373,0.0068674246,0.0010587287,0.0007732692,0.0009826861],"domain_scores_gemma":[0.9847859,0.009453042,0.003330615,0.00092690275,0.00051610207,0.0009874362],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.004748542,0.00072024635,0.0075644325,0.0002632363,0.00025239776,0.0000472902,0.0007050307,0.0012758139,0.00008910321],"category_scores_gemma":[0.0029422252,0.00047751894,0.00038091803,0.0004941755,0.00023635042,0.0005354966,0.0001686307,0.0016152657,0.00007067406],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000060140763,0.000053451626,0.00034754025,0.16641447,0.00011486838,0.000008439082,0.00015727323,1.668962e-7,1.1426281e-8,0.010052052,0.0059376303,0.81685394],"study_design_scores_gemma":[0.0012811343,0.0026993353,0.00008615719,0.1113641,0.00049869705,0.000030853695,0.0009518751,0.00003933934,3.151831e-9,0.00040023786,0.8823409,0.00030735953],"about_ca_topic_score_codex":0.000528792,"about_ca_topic_score_gemma":0.00015087113,"teacher_disagreement_score":0.8764033,"about_ca_system_score_codex":0.00023809617,"about_ca_system_score_gemma":0.006305241,"threshold_uncertainty_score":0.99976766},"labels":[],"label_agreement":null},{"id":"W3005283278","doi":"10.1038/s41746-020-0222-x","title":"Lymelight: forecasting Lyme disease risk using web search data","year":2020,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"U.S. National Library of Medicine; Canadian Institutes of Health Research; National Institutes of Health","keywords":"Lyme disease; Disease; Computer science; Machine learning; Psychological intervention; Web application; LYME; Medicine; Classifier (UML); Artificial intelligence; World Wide Web; Borrelia burgdorferi; Pathology; Psychiatry; Immunology","score_opus":0.1929112390497841,"score_gpt":0.33943124847063755,"score_spread":0.14652000942085344,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3005283278","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95700777,0.0029450816,0.0017431963,0.01208102,0.0004049869,0.0010442253,0.0077872984,0.00065712404,0.016329298],"genre_scores_gemma":[0.99141836,0.00009160877,0.00045999963,0.0020227314,0.001953696,0.000005523676,0.0037865108,0.000084505045,0.0001770461],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996693,0.00006859487,0.0005883495,0.0009785495,0.0010737444,0.0005977194],"domain_scores_gemma":[0.99609476,0.00025013604,0.00017097825,0.0014997975,0.00017854445,0.0018057802],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003596085,0.000350223,0.0006717752,0.00013175288,0.00013258484,0.00007299543,0.000638276,0.000066412766,0.00044451052],"category_scores_gemma":[0.005847251,0.00027577157,0.00009314691,0.0006864513,0.00037150335,0.00073406973,0.00078835106,0.0003721873,0.00024668605],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003709904,0.00064343424,0.72209597,0.0018676695,0.0007649344,0.0063701603,0.0010995923,0.00017146378,0.0037041989,0.00018116471,0.07723943,0.1821521],"study_design_scores_gemma":[0.015512795,0.0015254762,0.0928149,0.0030617125,0.0016793968,0.00033810813,0.0013572313,0.7016114,0.00018178139,0.0002372304,0.18022655,0.0014534154],"about_ca_topic_score_codex":0.000043908207,"about_ca_topic_score_gemma":0.000003804777,"teacher_disagreement_score":0.7014399,"about_ca_system_score_codex":0.00008549392,"about_ca_system_score_gemma":0.00047852474,"threshold_uncertainty_score":0.9999694},"labels":[],"label_agreement":null},{"id":"W3007464329","doi":"10.1038/s41746-020-0232-8","title":"Impact of a deep learning assistant on the histopathologic classification of liver cancer","year":2020,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":309,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Artificial intelligence; Medicine; H&E stain; Workflow; Test (biology); Machine learning; Set (abstract data type); Diagnostic accuracy; Test set; Medical physics; Computer science; Pathology; Radiology; Staining","score_opus":0.05833074722149878,"score_gpt":0.2945620820779027,"score_spread":0.2362313348564039,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3007464329","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7919111,0.000933737,0.1823411,0.0077970442,0.00028816305,0.00029814275,0.000007685279,0.00013275263,0.016290227],"genre_scores_gemma":[0.9995698,0.00003984721,0.000094239964,0.00015544081,0.00008939498,0.000010552817,0.0000012072089,0.000005412144,0.000034151984],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99914443,0.00004157204,0.00021628906,0.0001947681,0.00030149703,0.000101452075],"domain_scores_gemma":[0.9992081,0.0001730836,0.00024882876,0.00021772178,0.00010011789,0.000052159343],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013473775,0.00008618803,0.00016516176,0.0000436768,0.00003341892,0.000012643899,0.0003297108,0.000033230368,0.00006217748],"category_scores_gemma":[0.0004129692,0.00004857645,0.000057028272,0.00037954003,0.00014332551,0.0001805533,0.000054083852,0.00015367933,0.000006690914],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019377627,0.000108780216,0.026043534,0.00009058497,0.000062662686,0.000018671048,0.0072676204,0.0014648297,0.07094273,0.00832,0.0018970049,0.8835898],"study_design_scores_gemma":[0.0007666305,0.0063654827,0.82071525,0.00026278407,0.00003392936,0.000015585401,0.00032262856,0.164651,0.0029736608,0.0007836193,0.002882026,0.00022740226],"about_ca_topic_score_codex":0.00004730945,"about_ca_topic_score_gemma":0.0000027968426,"teacher_disagreement_score":0.8833624,"about_ca_system_score_codex":0.00014145144,"about_ca_system_score_gemma":0.00004497809,"threshold_uncertainty_score":0.19808902},"labels":[],"label_agreement":null},{"id":"W3012501605","doi":"10.1038/s41746-020-00323-1","title":"The future of digital health with federated learning","year":2020,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":2532,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute on Governance","funders":"Centre For Medical Engineering, King’s College London; Engineering and Physical Sciences Research Council; Bundesministerium für Bildung und Forschung; National Institute of Neurological Disorders and Stroke; Deutscher Akademischer Austauschdienst; UK Research and Innovation; Wellcome Trust; NIH Clinical Center; National Cancer Institute; National Institutes of Health; U.S. Department of Health and Human Services","keywords":"Federated learning; Key (lock); Digital health; Health care; Confidentiality; Health data; Information privacy","score_opus":0.015072068181797984,"score_gpt":0.272940096182485,"score_spread":0.25786802800068703,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3012501605","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.043412156,0.005350376,0.12354758,0.79460335,0.00076906226,0.0008060043,0.000013888451,0.0009929307,0.030504659],"genre_scores_gemma":[0.9972872,0.000040555617,0.00031405364,0.0016449317,0.000439672,0.000004123127,0.000018090155,0.00001683543,0.00023451002],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983437,0.00006436786,0.00036678588,0.00032877395,0.0005628614,0.00033350257],"domain_scores_gemma":[0.9987107,0.00029910757,0.00026116235,0.00026666358,0.00015561307,0.00030676843],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019321174,0.00016559052,0.00029486392,0.000035615998,0.00029013457,0.00025259523,0.0005884753,0.000039001025,0.000006646641],"category_scores_gemma":[0.00046801005,0.00009013141,0.00003086614,0.00062895345,0.00015444368,0.0005027075,0.00015710747,0.0005050623,0.000017869836],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009160518,0.00002874869,0.031183338,0.00020013771,0.000038707574,0.000036212205,0.0048674634,0.0003139139,0.000012172915,0.015659103,0.004907242,0.94266135],"study_design_scores_gemma":[0.0038069035,0.017776817,0.022594856,0.0008891152,0.000013335444,0.00026200173,0.0074935798,0.0957307,0.00005520835,0.0017473083,0.84880954,0.0008206516],"about_ca_topic_score_codex":0.000020348634,"about_ca_topic_score_gemma":0.000007742528,"teacher_disagreement_score":0.95387506,"about_ca_system_score_codex":0.000030046749,"about_ca_system_score_gemma":0.0002003986,"threshold_uncertainty_score":0.36754522},"labels":[],"label_agreement":null},{"id":"W3013443134","doi":"10.1038/s41746-020-0254-2","title":"Machine intelligence in healthcare—perspectives on trustworthiness, explainability, usability, and transparency","year":2020,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":325,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Center for Advancing Translational Sciences; Agency for Healthcare Research and Quality; National Institutes of Health; University of Toronto; National Institute of Biomedical Imaging and Bioengineering; Vanderbilt University; York University; Vanderbilt University Medical Center; Johns Hopkins University; Massachusetts Institute of Technology","keywords":"Transparency (behavior); Workflow; Health care; Usability; Context (archaeology); Quality (philosophy); Data science; Knowledge management; Medicine; Computer science; Political science; Human–computer interaction; Computer security","score_opus":0.12282443027379096,"score_gpt":0.40369610721632404,"score_spread":0.28087167694253307,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3013443134","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7244193,0.002872659,0.0009897845,0.26568875,0.00026345163,0.0010266812,0.000017759196,0.00011774588,0.0046039093],"genre_scores_gemma":[0.99473387,0.00082768436,0.0000843001,0.003736783,0.00047230592,0.000039904975,0.00004094817,0.000023263754,0.000040924326],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9977157,0.000058201083,0.00079568743,0.0006647903,0.00040280272,0.00036281138],"domain_scores_gemma":[0.99849385,0.00038979217,0.000086587366,0.0003080527,0.00018454835,0.0005371567],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032311652,0.0002513314,0.0005392819,0.00015206948,0.00007492411,0.000024664716,0.00012224457,0.0001271034,0.0001634154],"category_scores_gemma":[0.0024287738,0.0001974224,0.00005247921,0.0006633122,0.00046535872,0.0002535465,0.000032840107,0.0005221777,0.000032421733],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010947392,0.00057379523,0.42227268,0.000872123,0.000018099965,0.00006776685,0.035488006,0.000020407795,0.000057845507,0.011264625,0.00022216332,0.52804774],"study_design_scores_gemma":[0.0024555451,0.04047217,0.56579953,0.0053154603,0.00024131381,0.0004239176,0.19440518,0.01437344,0.0041047526,0.15379795,0.016135616,0.002475136],"about_ca_topic_score_codex":0.0012366466,"about_ca_topic_score_gemma":0.00016163511,"teacher_disagreement_score":0.5255726,"about_ca_system_score_codex":0.00017141494,"about_ca_system_score_gemma":0.00016603114,"threshold_uncertainty_score":0.8050652},"labels":[],"label_agreement":null},{"id":"W3013567425","doi":"10.1038/s41746-020-0252-4","title":"Channel management in virtual care","year":2020,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Telemedicine and Telehealth Implementation","field":"Medicine","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Women's College Hospital; University of Toronto; University Health Network; McGill University","funders":"","keywords":"Workflow; Phone; Modalities; Channel (broadcasting); Focus (optics); Modality (human–computer interaction); Computer science; Asynchronous communication; Adaptation (eye); Multimedia; Human–computer interaction; Telecommunications; Psychology","score_opus":0.039392545532516664,"score_gpt":0.33043797577499867,"score_spread":0.29104543024248203,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3013567425","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.67043436,0.0014892707,0.0025780818,0.1209713,0.00070805615,0.0028125974,0.000048787188,0.00042657962,0.20053096],"genre_scores_gemma":[0.9845157,0.00008340049,0.0000672765,0.013950895,0.0007217525,0.00003744166,0.00031909146,0.000025215808,0.00027921764],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984216,0.000011272687,0.0004640257,0.00031352072,0.00046065493,0.00032892378],"domain_scores_gemma":[0.9992822,0.000037102498,0.000068934445,0.000165081,0.000061225765,0.00038548026],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007235705,0.00017275062,0.00036485158,0.00017716947,0.000029103028,0.00000918445,0.00008366351,0.00004801011,0.00024630566],"category_scores_gemma":[0.00014037118,0.00013623634,0.000036364265,0.00048144843,0.00007346483,0.000149861,0.000050620132,0.00019085078,0.000102064376],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001070732,0.00022186321,0.029539745,0.0015759787,0.00014865442,0.0017591218,0.025001274,0.000019587778,0.00022847956,0.0025669374,0.053871352,0.88399625],"study_design_scores_gemma":[0.04820356,0.018701922,0.24581312,0.0016345643,0.00039970025,0.00019326119,0.16101618,0.0009362794,0.0005267154,0.0005613102,0.52118206,0.0008313309],"about_ca_topic_score_codex":0.00002408523,"about_ca_topic_score_gemma":0.0000068880313,"teacher_disagreement_score":0.88316494,"about_ca_system_score_codex":0.000087343156,"about_ca_system_score_gemma":0.00003920084,"threshold_uncertainty_score":0.5555557},"labels":[],"label_agreement":null},{"id":"W3016012157","doi":"10.1038/s41746-020-0262-2","title":"The need for a system view to regulate artificial intelligence/machine learning-based software as medical device","year":2020,"lang":"en","type":"review","venue":"npj Digital Medicine","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":341,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Novo Nordisk Fonden; Novo Nordisk","keywords":"Computer science; Software; Artificial intelligence; Software engineering; Operating system","score_opus":0.2289590153630134,"score_gpt":0.46604409642802025,"score_spread":0.23708508106500684,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3016012157","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000010459525,0.9465471,0.014657415,0.030529652,0.0021326994,0.0050269864,0.00005691426,0.00042367494,0.00061512814],"genre_scores_gemma":[0.0031792005,0.98161745,0.0003001447,0.0036988591,0.0068202284,0.0015248077,0.0015839267,0.000287209,0.0009881475],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99396753,0.00020604469,0.002619731,0.00094455795,0.0014366567,0.0008254745],"domain_scores_gemma":[0.9921457,0.004264708,0.0006544695,0.0007423423,0.0006918233,0.0015009117],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0015450624,0.00077645585,0.0027791604,0.0003185019,0.00052406074,0.00015099598,0.0006845879,0.0006586315,0.0001668279],"category_scores_gemma":[0.023007369,0.0004597513,0.00061830884,0.0013871836,0.00036800717,0.0000981965,0.00011581541,0.0013121412,0.0011039105],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002368861,0.000068741305,0.0000054557945,0.018917438,0.00014221856,0.00007650281,0.00028965258,0.000004770907,1.2086618e-7,0.0010878838,0.0015932501,0.9775771],"study_design_scores_gemma":[0.00005611075,0.002137044,3.687568e-7,0.046380278,0.0008607553,0.00025037598,0.0011108381,0.0012608937,0.000009853001,0.00041737017,0.9471462,0.00036994668],"about_ca_topic_score_codex":0.0002137331,"about_ca_topic_score_gemma":0.00008392788,"teacher_disagreement_score":0.9772071,"about_ca_system_score_codex":0.000593478,"about_ca_system_score_gemma":0.003104467,"threshold_uncertainty_score":0.9997854},"labels":[],"label_agreement":null},{"id":"W3018185338","doi":"10.1038/s41746-020-0266-y","title":"PENet—a scalable deep-learning model for automated diagnosis of pulmonary embolism using volumetric CT imaging","year":2020,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Venous Thromboembolism Diagnosis and Management","field":"Medicine","cited_by":182,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"National Center for Advancing Translational Sciences; U.S. National Library of Medicine; National Institutes of Health; National Heart, Lung, and Blood Institute; Georgia Clinical and Translational Science Alliance","keywords":"Pulmonary embolism; Medical diagnosis; Artificial intelligence; Deep learning; Convolutional neural network; Triage; Gold standard (test); Medicine; Computer science; Generalizability theory; Population; Radiology; Medical imaging; Machine learning; Emergency medicine; Surgery","score_opus":0.03486099507753343,"score_gpt":0.2905976254379858,"score_spread":0.25573663036045235,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3018185338","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91967374,0.006004379,0.043837763,0.010109917,0.00044424765,0.0028323792,0.000065080756,0.0011798722,0.015852602],"genre_scores_gemma":[0.9951548,0.00034109084,0.0019542708,0.0016414985,0.00037464435,0.00009473622,0.00013769242,0.00009175324,0.00020953245],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976577,0.000022086595,0.0006930273,0.0005266241,0.0005702364,0.0005303028],"domain_scores_gemma":[0.998572,0.0002187219,0.00027714806,0.00027103993,0.00025245783,0.00040866467],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002304621,0.0003228443,0.0011136577,0.0003581624,0.00012694315,0.00004135454,0.00019712868,0.000052618827,0.00011636543],"category_scores_gemma":[0.0012355614,0.00028090697,0.00018838108,0.000875586,0.00016358176,0.00036450895,0.00016318785,0.00020299059,0.000015635416],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006761956,0.0032048242,0.27004918,0.0064945687,0.0013585795,0.000791671,0.0042117722,0.07042405,0.011217808,0.0012225853,0.042489603,0.58785915],"study_design_scores_gemma":[0.0019576252,0.0004232349,0.013407533,0.0005932402,0.0005875727,0.0000415924,0.0005981013,0.9777294,0.00029403332,0.000108866916,0.004005703,0.00025314014],"about_ca_topic_score_codex":0.00008509537,"about_ca_topic_score_gemma":8.852826e-7,"teacher_disagreement_score":0.9073053,"about_ca_system_score_codex":0.000099721554,"about_ca_system_score_gemma":0.0000759808,"threshold_uncertainty_score":0.9999643},"labels":[],"label_agreement":null},{"id":"W3026135140","doi":"10.1038/s41746-020-0284-9","title":"Evaluation of an augmented reality platform for austere surgical telementoring: a randomized controlled crossover study in cricothyroidotomies","year":2020,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Surgical Simulation and Training","field":"Medicine","cited_by":54,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Calgary Laboratory Services; Canadian Armed Forces; University of Calgary","funders":"Office of the Secretary of Defense; U.S. Department of Defense; National Science Foundation","keywords":"Crossover; Augmented reality; Crossover study; Randomized controlled trial; Medicine; Computer science; Human–computer interaction; Surgery; Artificial intelligence; Pathology; Alternative medicine","score_opus":0.15577219057625263,"score_gpt":0.41868010340090045,"score_spread":0.2629079128246478,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3026135140","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97853315,0.00011599856,0.0001392509,0.0011148339,0.000098176184,0.006905554,0.00001442926,0.000054633045,0.013024001],"genre_scores_gemma":[0.99896127,0.0000029532387,0.000022026945,0.00017923555,0.0002701718,0.00034068833,0.000121866244,0.000016771442,0.000084994586],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.996821,0.00018290704,0.00117271,0.00032167006,0.001277001,0.00022474532],"domain_scores_gemma":[0.99739695,0.001386891,0.00027013614,0.00016909084,0.0005263955,0.00025051297],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0041062534,0.00019564296,0.0017403672,0.0001252162,0.000033318673,0.000026456162,0.00007094787,0.00006950719,0.00033990992],"category_scores_gemma":[0.0072285403,0.00012412548,0.00019332975,0.00028081544,0.00014166329,0.00024744123,0.000024810006,0.00012855395,0.000001944041],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.9177668,0.0021561005,0.014878805,0.00014686119,0.0009417145,0.00007055612,0.0076125646,0.00040350328,0.00011779176,0.00056624017,0.00007527944,0.055263784],"study_design_scores_gemma":[0.9231941,0.0021425793,0.006305787,0.00011909276,0.0007581797,0.000004081163,0.0031885535,0.062917896,0.000038529357,0.00035101906,0.0008660322,0.00011413032],"about_ca_topic_score_codex":0.00003398007,"about_ca_topic_score_gemma":0.000012248502,"teacher_disagreement_score":0.06251439,"about_ca_system_score_codex":0.00010007835,"about_ca_system_score_gemma":0.00010278091,"threshold_uncertainty_score":0.865376},"labels":[],"label_agreement":null},{"id":"W3026182705","doi":"10.1038/s41746-020-0283-x","title":"Homeostasis as a proportional–integral control system","year":2020,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Heart Rate Variability and Autonomic Control","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Canada; University of Ontario Institute of Technology","keywords":"Homeostasis; Outlier; Universality (dynamical systems); Control theory (sociology); Mathematics; Control (management); Computer science; Medicine; Statistics; Endocrinology; Artificial intelligence; Physics","score_opus":0.01942029188832669,"score_gpt":0.25098114998120646,"score_spread":0.23156085809287977,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3026182705","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5515124,0.0010762007,0.005169162,0.3074026,0.00068506045,0.0030471827,0.00023812897,0.0011032583,0.12976597],"genre_scores_gemma":[0.9909164,0.00000587577,0.000056768113,0.00711982,0.0010882813,0.00004356022,0.00008433669,0.000028014669,0.0006569672],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981314,0.00003281089,0.00061338005,0.00042539518,0.00045704094,0.00033998003],"domain_scores_gemma":[0.99860334,0.0001702829,0.000107149266,0.00027209977,0.00017812451,0.00066901883],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002394475,0.00023819464,0.0007461452,0.00007611114,0.000062867744,0.000037319307,0.00010502092,0.00010993432,0.0006537241],"category_scores_gemma":[0.0013620479,0.00016502915,0.00015231299,0.00026521573,0.00021810103,0.00019416178,0.000027224407,0.00030064496,0.00089280476],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0068782764,0.001976251,0.045648772,0.005525991,0.002892491,0.004682765,0.0077244616,0.000070714486,0.080195494,0.103511296,0.055867884,0.6850256],"study_design_scores_gemma":[0.03289505,0.009590102,0.023870552,0.0019629062,0.0009797708,0.0013386843,0.006450394,0.016044527,0.0013656735,0.0007239141,0.9038203,0.0009581532],"about_ca_topic_score_codex":0.00004520369,"about_ca_topic_score_gemma":9.0126065e-7,"teacher_disagreement_score":0.84795237,"about_ca_system_score_codex":0.00014564148,"about_ca_system_score_gemma":0.00034394366,"threshold_uncertainty_score":0.99988514},"labels":[],"label_agreement":null},{"id":"W3030474364","doi":"10.1038/s41746-020-0286-7","title":"A data-driven framework for selecting and validating digital health metrics: use-case in neurological sensorimotor impairments","year":2020,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Stroke Rehabilitation and Recovery","field":"Medicine","cited_by":57,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"Staatssekretariat für Bildung, Forschung und Innovation; Canadian Institutes of Health Research; European Commission; James S. McDonnell Foundation","keywords":"Computer science; Set (abstract data type); Machine learning; Reliability (semiconductor); Artificial intelligence; Selection (genetic algorithm); Discriminant validity; Data mining; Physical medicine and rehabilitation; Psychometrics; Medicine; Mathematics; Statistics","score_opus":0.12472322854214851,"score_gpt":0.37231419761965534,"score_spread":0.24759096907750683,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3030474364","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97965646,0.00023182917,0.0059446185,0.012136797,0.00019952568,0.0011482851,0.00033762396,0.00011832363,0.00022650968],"genre_scores_gemma":[0.9853965,0.000028807877,0.00945917,0.0041790665,0.0005849571,0.000014082076,0.00027351239,0.000032782886,0.00003109271],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9980676,0.000041239156,0.00059965294,0.0005951932,0.0003158407,0.0003804373],"domain_scores_gemma":[0.99594426,0.0030427275,0.00017450516,0.00026492143,0.000082131024,0.00049143046],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0002660295,0.00021134278,0.0006109891,0.00020228086,0.00007010044,0.00011402449,0.000100561585,0.000113645736,0.000017763157],"category_scores_gemma":[0.022912512,0.00015646293,0.00006221613,0.00061063585,0.0001177225,0.0006016908,0.00014026338,0.0003875703,0.000006101354],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00078052515,0.00034090938,0.8886189,0.0008396608,0.0001152893,0.0009815475,0.0019959786,0.000015117937,0.0000976929,0.00020095296,0.002791327,0.1032221],"study_design_scores_gemma":[0.050331213,0.0836691,0.49681124,0.0060245264,0.00062697113,0.019701121,0.025183203,0.19050254,0.000058891146,0.0034582056,0.12097879,0.0026541844],"about_ca_topic_score_codex":0.0000124870985,"about_ca_topic_score_gemma":0.0000013762268,"teacher_disagreement_score":0.39180765,"about_ca_system_score_codex":0.000045760586,"about_ca_system_score_gemma":0.0000869204,"threshold_uncertainty_score":0.9853179},"labels":[],"label_agreement":null},{"id":"W3032158497","doi":"10.1038/s41746-020-0287-6","title":"A machine learning approach predicts future risk to suicidal ideation from social media data","year":2020,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Suicide and Self-Harm Studies","field":"Psychology","cited_by":212,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; Royal Ottawa Mental Health Centre; Dalhousie University; University of Ottawa","funders":"Mach-Gaensslen Foundation of Canada","keywords":"Suicidal ideation; Loneliness; Machine learning; Psychology; Artificial intelligence; Random forest; Suicide prevention; Poison control; Social media; Artificial neural network; Depression (economics); Computer science; Clinical psychology; Medicine; Psychiatry; Medical emergency; World Wide Web","score_opus":0.07242908903235011,"score_gpt":0.3112115631894398,"score_spread":0.2387824741570897,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3032158497","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7800382,0.0075581167,0.00837463,0.044445645,0.003493021,0.0011280362,0.0043848427,0.001094269,0.14948325],"genre_scores_gemma":[0.98330015,0.00006273794,0.00018380687,0.0021142282,0.0095717525,0.000026114922,0.0045187715,0.00004577957,0.00017664355],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9978486,0.00010596742,0.0004091916,0.00073842984,0.00052469724,0.00037317004],"domain_scores_gemma":[0.9986863,0.000413597,0.00015614548,0.00038473852,0.000069589456,0.00028963923],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022174136,0.00027966584,0.000509162,0.000082743405,0.00018618978,0.000046869358,0.0005511911,0.0001499195,0.0006239665],"category_scores_gemma":[0.0016259853,0.00021913569,0.000050676776,0.00041095976,0.00011316814,0.00026533892,0.00035216552,0.0005636815,0.00036401494],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001915196,0.00035919747,0.29403713,0.00006531585,0.0013794182,0.00018763158,0.21243887,0.000036544527,0.00026239888,0.0014584386,0.2880511,0.19980876],"study_design_scores_gemma":[0.011382438,0.0018372788,0.64362127,0.000039175025,0.00092270167,0.00002625824,0.07659898,0.0042621642,0.000019897594,0.0013448627,0.25865117,0.0012938255],"about_ca_topic_score_codex":0.0005512101,"about_ca_topic_score_gemma":0.00008424863,"teacher_disagreement_score":0.34958413,"about_ca_system_score_codex":0.000024996647,"about_ca_system_score_gemma":0.000020488695,"threshold_uncertainty_score":0.8936094},"labels":[],"label_agreement":null},{"id":"W3035816197","doi":"10.1038/s41746-020-0294-7","title":"What do medical students actually need to know about artificial intelligence?","year":2020,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":233,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Canada Research Chairs; Public Health Ontario; University of Toronto; University of New Brunswick","funders":"National Institute of Biomedical Imaging and Bioengineering; University of Toronto; U.S. Department of Health and Human Services","keywords":"Need to know; Psychology; Computer science; Artificial intelligence; Medical education; Medicine; Computer security","score_opus":0.13537486617891314,"score_gpt":0.4444024851899593,"score_spread":0.30902761901104614,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3035816197","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.63341445,0.0018425012,0.004664733,0.3504534,0.003636373,0.0012943423,0.000008779316,0.00027053605,0.004414863],"genre_scores_gemma":[0.9622739,0.0009958963,0.000100651094,0.031510636,0.004541335,0.00004790035,0.00008304736,0.000047571946,0.0003990665],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9953166,0.00004127954,0.001146916,0.0006366812,0.0022668003,0.00059169036],"domain_scores_gemma":[0.9964932,0.00038510328,0.00012720902,0.00040147558,0.00042812186,0.0021648507],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00057360413,0.0003234681,0.0006350224,0.00020947776,0.00012035365,0.0003133381,0.0005813622,0.0002606674,0.002694686],"category_scores_gemma":[0.0064368728,0.00025421547,0.0001110323,0.0009181583,0.00028353147,0.0006016166,0.00018453338,0.0005565412,0.0024004178],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005859868,0.00035196438,0.0052175918,0.00012326922,0.00005924143,0.00015044387,0.017340928,0.000005820008,0.00036455027,0.0010982084,0.0198963,0.9548057],"study_design_scores_gemma":[0.00096918264,0.024822535,0.008371684,0.017544352,0.0006297685,0.00058483286,0.3554856,0.0028384717,0.027120937,0.018857474,0.54016495,0.0026101945],"about_ca_topic_score_codex":0.0000599987,"about_ca_topic_score_gemma":0.000024825513,"teacher_disagreement_score":0.9521955,"about_ca_system_score_codex":0.0001352046,"about_ca_system_score_gemma":0.00045199215,"threshold_uncertainty_score":0.999991},"labels":[],"label_agreement":null},{"id":"W3042022921","doi":"10.1038/s41746-020-0306-7","title":"Germany’s digital health reforms in the COVID-19 era: lessons and opportunities for other countries","year":2020,"lang":"en","type":"review","venue":"npj Digital Medicine","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":195,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Novo Nordisk Fonden; Novo Nordisk; Ewing Marion Kauffman Foundation","keywords":"Coronavirus disease 2019 (COVID-19); 2019-20 coronavirus outbreak; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Political science; Virology; Economic growth; Development economics; Medicine; Economics; Outbreak","score_opus":0.545709545380491,"score_gpt":0.5253593496480097,"score_spread":0.020350195732481313,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3042022921","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000019465839,0.79523885,0.00014654409,0.19813353,0.0002971288,0.0020718025,0.00043358974,0.000053604846,0.0036054803],"genre_scores_gemma":[0.0016941472,0.9679655,0.000008939492,0.026656779,0.0013756023,0.00034339732,0.0008863952,0.000060408755,0.0010088703],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975094,0.00004971387,0.0011565376,0.00043402752,0.00041232014,0.00043795176],"domain_scores_gemma":[0.99726933,0.0013174351,0.00039982446,0.0003552639,0.00010128897,0.0005568602],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00069275376,0.00039769794,0.0016339596,0.00024993235,0.00017375691,0.00013673832,0.00020501822,0.00021846591,0.000038710044],"category_scores_gemma":[0.00157697,0.0002148145,0.0001544934,0.0002592285,0.0004903957,0.00029742983,0.00003990392,0.0004885845,0.000023343711],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000457954,0.00004950439,0.00003036624,0.017757177,0.000044345084,0.000040996063,0.0037580025,2.6250538e-8,6.878747e-9,0.0033837834,0.020979797,0.9539102],"study_design_scores_gemma":[0.00012772877,0.0008331148,0.0000049936352,0.006381646,0.00012754675,0.00038835936,0.00712504,0.000003317413,5.847407e-8,0.0012825617,0.9835462,0.00017945311],"about_ca_topic_score_codex":0.0002567931,"about_ca_topic_score_gemma":0.00007268819,"teacher_disagreement_score":0.9625664,"about_ca_system_score_codex":0.0004212085,"about_ca_system_score_gemma":0.0028381022,"threshold_uncertainty_score":0.87598807},"labels":[],"label_agreement":null},{"id":"W3082170769","doi":"10.1038/s41746-020-00321-3","title":"Virtual care models for cancer survivorship","year":2020,"lang":"en","type":"review","venue":"npj Digital Medicine","topic":"Cancer survivorship and care","field":"Medicine","cited_by":54,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; McMaster University; Trillium Health Centre; Niagara Health System; Regional Municipality of Niagara; Niagara College; Hamilton Health Sciences; University Health Network; University of Toronto; Public Health Ontario; Memorial University of Newfoundland","funders":"Canadian Institutes of Health Research","keywords":"Survivorship curve; Repurposing; Health care; Cancer survivorship; Nursing; Medicine; Knowledge management; Cancer; Computer science; Engineering; Political science","score_opus":0.09030298459789432,"score_gpt":0.3649372564946814,"score_spread":0.2746342718967871,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3082170769","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000040342484,0.97174376,0.0006778494,0.00087642256,0.002457395,0.002488065,0.0017395326,0.00023389951,0.019779054],"genre_scores_gemma":[0.0014792535,0.9850432,0.00001603436,0.0007309337,0.0050566094,0.001040238,0.003068603,0.0002630191,0.0033020629],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9965994,0.000047500558,0.0009671263,0.0009840499,0.0007858248,0.00061612745],"domain_scores_gemma":[0.9974074,0.00047531613,0.00034131965,0.0006583348,0.00040228304,0.0007153975],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00013496201,0.00089595007,0.0040381975,0.00026496657,0.000079409234,0.000059804057,0.00038333485,0.00055178977,0.00020313014],"category_scores_gemma":[0.00034915016,0.0006346246,0.0009802884,0.00065219484,0.00022796649,0.00021422237,0.00011642585,0.0007020073,0.000058685924],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001119183,0.00002683688,0.000006180926,0.032312106,0.00035281645,0.00006823351,0.0015148184,9.980337e-7,1.1067261e-7,0.000810969,0.0053861197,0.9594089],"study_design_scores_gemma":[0.0011036142,0.0011339356,6.789111e-7,0.034006048,0.002628998,0.000064739594,0.0014541864,0.000023366598,5.318824e-7,0.00014190911,0.95890015,0.00054183835],"about_ca_topic_score_codex":0.00055233657,"about_ca_topic_score_gemma":0.00063054176,"teacher_disagreement_score":0.9588671,"about_ca_system_score_codex":0.0005388789,"about_ca_system_score_gemma":0.0011278186,"threshold_uncertainty_score":0.9996105},"labels":[],"label_agreement":null},{"id":"W3082454838","doi":"10.1038/s41746-020-00326-y","title":"Digital advantage in the COVID-19 response: perspective from Canada’s largest integrated digitalized healthcare system","year":2020,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"COVID-19 Digital Contact Tracing","field":"Computer Science","cited_by":83,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Alberta Hospital; University of Alberta","funders":"Alberta Machine Intelligence Institute; University of Alberta; Government of Alberta; Canadian Institute for Advanced Research; Alberta Health Services","keywords":"Telehealth; Health care; Population; Business; Telemedicine; Medicine","score_opus":0.034724081375774075,"score_gpt":0.29888715042899006,"score_spread":0.26416306905321596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3082454838","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14792022,0.0021326037,0.06642838,0.72971976,0.0011395774,0.0025565866,0.0032294244,0.0016969986,0.045176454],"genre_scores_gemma":[0.97108346,0.0000040628042,0.000053879066,0.028243931,0.00021471202,0.000038580692,0.00019610421,0.000039186154,0.00012610294],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9955186,0.0002656995,0.00087021576,0.0011718475,0.0014192754,0.0007543367],"domain_scores_gemma":[0.99411523,0.0033730846,0.00026071383,0.0009792891,0.00026413164,0.0010075178],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00048566633,0.0005444618,0.00075978885,0.00021264993,0.00018852238,0.001109891,0.0022067637,0.000119381504,0.000012550912],"category_scores_gemma":[0.009385268,0.00038439056,0.000118941105,0.0016933825,0.00019040043,0.0028208017,0.00041224796,0.0006359935,0.000040060397],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.015035512,0.0014342911,0.14149159,0.0028729893,0.0010183862,0.055947386,0.19294922,0.00057478365,0.0016407184,0.38963977,0.10616921,0.09122614],"study_design_scores_gemma":[0.017685132,0.00453112,0.029669607,0.0024673457,0.00009027151,0.00084728905,0.21272655,0.011593973,0.00019457772,0.004768982,0.7117999,0.0036252495],"about_ca_topic_score_codex":0.16854535,"about_ca_topic_score_gemma":0.08226578,"teacher_disagreement_score":0.8231632,"about_ca_system_score_codex":0.0027732824,"about_ca_system_score_gemma":0.0041791713,"threshold_uncertainty_score":0.99992704},"labels":[],"label_agreement":null},{"id":"W3090477134","doi":"10.1038/s41746-020-00342-y","title":"Social license for the use of big data in the COVID-19 era","year":2020,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"COVID-19 Digital Contact Tracing","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Women's College Hospital; University of Toronto","funders":"Wellcome Trust","keywords":"License; Coronavirus disease 2019 (COVID-19); Social distance; Big data; Corporate governance; Public relations; Political science; 2019-20 coronavirus outbreak; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Business; Medicine; Law; Computer science","score_opus":0.4289164045512512,"score_gpt":0.3784350431428148,"score_spread":0.0504813614084364,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3090477134","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0072938628,0.00025575605,0.480692,0.5087071,0.00037238825,0.0010810102,0.00021809478,0.00013888981,0.0012408863],"genre_scores_gemma":[0.95002455,0.000006453517,0.00021355684,0.04911171,0.00054863817,0.000017743003,0.000038321217,0.000010541595,0.000028521146],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99836594,0.000047050595,0.0003842255,0.00041747154,0.0005240285,0.00026127175],"domain_scores_gemma":[0.9938548,0.0048824637,0.00013389684,0.0009293698,0.00006422587,0.0001351966],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004946683,0.00015401264,0.00025442406,0.00006358063,0.000115909745,0.00028771846,0.002540427,0.0000430625,0.0000029794269],"category_scores_gemma":[0.0075025344,0.00008508445,0.000056925088,0.00072405173,0.00019209979,0.0013180878,0.0006363529,0.00019764509,0.000005962256],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045084886,0.0003231246,0.003948188,0.000691743,0.00015422243,0.00019449633,0.057549,0.00026120775,0.0004954693,0.086521834,0.22035423,0.6290556],"study_design_scores_gemma":[0.002243214,0.00056218397,0.0032916034,0.000068994384,0.0000378282,0.000022416456,0.0007694931,0.029830638,0.000024456285,0.0020333817,0.9608582,0.0002575593],"about_ca_topic_score_codex":0.00014838486,"about_ca_topic_score_gemma":0.00008688855,"teacher_disagreement_score":0.94273067,"about_ca_system_score_codex":0.000044195127,"about_ca_system_score_gemma":0.0002835934,"threshold_uncertainty_score":0.8981776},"labels":[],"label_agreement":null},{"id":"W3111503343","doi":"10.1038/s41746-021-00507-3","title":"Overcoming barriers to data sharing with medical image generation: a comprehensive evaluation","year":2021,"lang":"en","type":"preprint","venue":"npj Digital Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Institute for Advanced Research","funders":"GlaxoSmithKline","keywords":"Overfitting; Synthetic data; Computer science; Benchmark (surveying); Medical imaging; Artificial intelligence; Image synthesis; Generative model; Machine learning; Aggregate (composite); Data mining; Image (mathematics); Pattern recognition (psychology); Data science; Generative grammar; Artificial neural network","score_opus":0.11388781899955881,"score_gpt":0.3576403586010562,"score_spread":0.2437525396014974,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3111503343","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.048620325,0.0006114906,0.93044126,0.010899607,0.0032002712,0.0009455317,0.000035237546,0.00025533192,0.0049909423],"genre_scores_gemma":[0.9670559,0.00004774244,0.026333492,0.0027616676,0.0025450056,0.00015586238,0.0009887598,0.000049690185,0.0000618442],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9943208,0.00008881567,0.0005504138,0.0018917733,0.0028048567,0.00034333195],"domain_scores_gemma":[0.99490416,0.00017857445,0.00023952874,0.0031790668,0.0007867898,0.00071185286],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009745936,0.000374587,0.000523007,0.0002180778,0.00015402069,0.0008195219,0.0029852062,0.00022872462,0.0004069384],"category_scores_gemma":[0.0028490268,0.0003194575,0.000043018972,0.0005415936,0.0001559867,0.0015758588,0.006413485,0.0007251471,0.00001736368],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012081386,0.00011788186,0.0011049485,0.00056833297,0.0007366937,0.00091758743,0.010463165,0.0074746255,0.0033363816,0.0008721277,0.051364955,0.9229225],"study_design_scores_gemma":[0.0012376062,0.0002997212,0.00058761897,0.002475723,0.00010129309,0.00022654903,0.0005049418,0.988213,0.0005454804,0.0004954643,0.00473346,0.0005791559],"about_ca_topic_score_codex":0.00014276413,"about_ca_topic_score_gemma":0.00015237203,"teacher_disagreement_score":0.98073834,"about_ca_system_score_codex":0.00047974742,"about_ca_system_score_gemma":0.0016053336,"threshold_uncertainty_score":0.99992573},"labels":[],"label_agreement":null},{"id":"W3119391019","doi":"10.1038/s41746-020-00378-0","title":"Clinical outcomes of digital sensor alerting systems in remote monitoring: a systematic review and meta-analysis","year":2021,"lang":"en","type":"review","venue":"npj Digital Medicine","topic":"Healthcare Technology and Patient Monitoring","field":"Medicine","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kensington Health","funders":"NIHR Imperial Biomedical Research Centre; Patient Safety Translational Research Centre; National Institute for Health and Care Research","keywords":"Meta-analysis; Medicine; Hazard ratio; Emergency department; Medical emergency; Emergency medicine; Digital health; Systematic review; MEDLINE; Health care; Confidence interval; Internal medicine; Nursing","score_opus":0.3243054856668229,"score_gpt":0.4888321124695749,"score_spread":0.16452662680275204,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3119391019","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00012309724,0.9952519,0.000019060177,0.0004414951,0.00033587744,0.003278859,0.000090997404,0.000093517825,0.00036520755],"genre_scores_gemma":[0.005250443,0.9933274,0.00007046191,0.00006503763,0.00016484453,0.00011548211,0.000166655,0.00006423907,0.0007754649],"study_design_codex":"systematic_review","study_design_gemma":"meta_analysis","domain_scores_codex":[0.99199903,0.0004274924,0.005519555,0.0008528804,0.0007476748,0.00045334696],"domain_scores_gemma":[0.9932889,0.0027456384,0.0019950867,0.0012916228,0.00033512284,0.00034366702],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad"],"consensus_categories":[],"category_scores_codex":[0.0018798066,0.0007393119,0.024948193,0.00087905285,0.00003631301,0.000037877762,0.00025969278,0.0007138037,0.000013407899],"category_scores_gemma":[0.011103404,0.0004365179,0.002504485,0.0018706624,0.0002593373,0.0001688419,0.0001723487,0.0011543705,0.000010809303],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000028177276,0.00008058527,0.008255794,0.87795687,0.080845825,0.0003046214,0.000033727687,8.3394255e-8,9.40348e-9,0.000013658062,0.000015120333,0.032490913],"study_design_scores_gemma":[0.00028944094,0.00025838337,0.0000900137,0.36238426,0.6300196,0.00026438377,0.00020556508,0.0000027578155,4.3675232e-8,0.000002555664,0.00620709,0.00027586974],"about_ca_topic_score_codex":0.000058005426,"about_ca_topic_score_gemma":0.0000014320007,"teacher_disagreement_score":0.5491738,"about_ca_system_score_codex":0.00012520998,"about_ca_system_score_gemma":0.00020734788,"threshold_uncertainty_score":0.99980867},"labels":[],"label_agreement":null},{"id":"W3125542913","doi":"10.1038/s41746-020-00369-1","title":"Deep COVID DeteCT: an international experience on COVID-19 lung detection and prognosis using chest CT","year":2021,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":51,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Sociedade Beneficente Israelita Brasileira Albert Einstein","keywords":"Coronavirus disease 2019 (COVID-19); Pneumonia; Medicine; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Receiver operating characteristic; Convolutional neural network; 2019-20 coronavirus outbreak; Computed tomography; Radiology; Disease; Artificial intelligence; Computer science; Internal medicine; Pathology; Infectious disease (medical specialty)","score_opus":0.05638066611232208,"score_gpt":0.37125490061331634,"score_spread":0.3148742345009943,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3125542913","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9717988,0.00037648395,0.007201139,0.018362915,0.0007190317,0.00048272734,0.000014123576,0.00020076803,0.0008440357],"genre_scores_gemma":[0.9743079,0.000098005825,0.00040455352,0.024297968,0.00063090265,0.00006417409,0.00006426622,0.000045165427,0.00008709142],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976857,0.000052161144,0.0004246801,0.000765796,0.0007348026,0.00033687416],"domain_scores_gemma":[0.9978852,0.0005177833,0.0001448263,0.0004211976,0.00021481786,0.0008161236],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00022904252,0.00029179905,0.00041209508,0.00029851784,0.00019274277,0.00013184105,0.00014747358,0.00008990616,0.00038168678],"category_scores_gemma":[0.00667303,0.00026169658,0.000067811976,0.00049693964,0.0003547191,0.0005561044,0.00010925752,0.00027611764,0.00001190587],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017350102,0.0021679173,0.46341664,0.0017100308,0.0005149269,0.0067560016,0.012556328,0.00090766506,0.122812055,0.00031458848,0.0015084221,0.38560042],"study_design_scores_gemma":[0.02644487,0.007509116,0.24669543,0.0045751855,0.0012208537,0.012850378,0.009395664,0.12646402,0.119000755,0.0008084971,0.44238707,0.0026481661],"about_ca_topic_score_codex":0.00022954283,"about_ca_topic_score_gemma":0.00013734406,"teacher_disagreement_score":0.44087866,"about_ca_system_score_codex":0.0008103473,"about_ca_system_score_gemma":0.000369737,"threshold_uncertainty_score":0.99998355},"labels":[],"label_agreement":null},{"id":"W3127218785","doi":"10.1038/s41746-021-00394-8","title":"Predicting adverse outcomes due to diabetes complications with machine learning using administrative health data","year":2021,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":121,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Vector Institute; Lunenfeld-Tanenbaum Research Institute; Trillium Health Centre; Public Health Ontario; University of Toronto","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Mitacs; Canada Research Chairs; Government of Canada","keywords":"Medicine; Health care; Decision tree; Population; Adverse effect; Diabetes mellitus; Machine learning; Hypoglycemia; Diabetes management; Emergency medicine; Artificial intelligence; Intensive care medicine; Computer science; Type 2 diabetes; Environmental health; Internal medicine","score_opus":0.11333986118734035,"score_gpt":0.38665419269461526,"score_spread":0.2733143315072749,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3127218785","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4610583,0.00094948924,0.37923568,0.147423,0.0006516331,0.0011412926,0.00032077,0.0010958312,0.008124013],"genre_scores_gemma":[0.9646378,0.0000038123387,0.031587265,0.0030029432,0.00012367974,0.000013216791,0.00039976908,0.000027255288,0.00020426701],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99737227,0.00017698636,0.00051021104,0.0008486055,0.00058640586,0.00050553854],"domain_scores_gemma":[0.99695224,0.0006742954,0.00027978132,0.0013743568,0.00024507832,0.000474242],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046774943,0.00025184028,0.0005006684,0.00013530235,0.0004085381,0.00012686329,0.0010219689,0.000041705884,0.000021116619],"category_scores_gemma":[0.0021228446,0.00019621367,0.0000280643,0.000869349,0.000100386016,0.0008075115,0.0008625872,0.00051816774,0.000018504275],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000069442517,0.000085307336,0.96588093,0.000118665695,0.00006135493,0.00010425893,0.002299196,0.001654602,0.0000451891,0.0023899938,0.0001992644,0.027154274],"study_design_scores_gemma":[0.0014937056,0.0019274286,0.48342142,0.0015772464,0.000033128745,0.0003437879,0.0018076752,0.49464965,0.000048033777,0.0003309296,0.013710364,0.0006566406],"about_ca_topic_score_codex":0.000301729,"about_ca_topic_score_gemma":0.00024154609,"teacher_disagreement_score":0.5035795,"about_ca_system_score_codex":0.0001142719,"about_ca_system_score_gemma":0.0005347597,"threshold_uncertainty_score":0.80013615},"labels":[],"label_agreement":null},{"id":"W3130937151","doi":"10.1038/s41746-021-00385-9","title":"Do as AI say: susceptibility in deployment of clinical decision-aids","year":2021,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":447,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; University of Toronto; St. Michael's Hospital","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Canada; Canadian Institute for Advanced Research; Vector Institute; Microsoft Research","keywords":"Advice (programming); Medical diagnosis; Decision aids; Software deployment; Task (project management); Quality (philosophy); Work (physics); Psychology; Medicine; Medical education; Computer science; Medical physics; Pathology; Engineering; Alternative medicine","score_opus":0.20546653871318685,"score_gpt":0.527046304125125,"score_spread":0.3215797654119381,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3130937151","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9772666,0.0006927217,0.00028566137,0.009860774,0.0010821866,0.0002875529,0.000004545521,0.00002717037,0.010492805],"genre_scores_gemma":[0.9955879,0.00023680094,0.00031415958,0.002633744,0.0006570057,0.000010274084,0.00004516705,0.000015572612,0.00049938256],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9971855,0.00006702465,0.0015312815,0.00041809626,0.0005446801,0.0002533943],"domain_scores_gemma":[0.9972445,0.0012034817,0.00014194731,0.00055259664,0.0005376634,0.00031980584],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0010430487,0.00013528635,0.00063643086,0.00012802421,0.00002548267,0.000012869081,0.000089838955,0.0001649767,0.0010155509],"category_scores_gemma":[0.011922375,0.000103809296,0.000117144846,0.0005291419,0.0002609165,0.00014716104,0.00005318708,0.00036539545,0.0001263351],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002742773,0.00053709757,0.46324342,0.000068637404,0.000015343405,0.000073477924,0.00053729204,0.0000016278909,0.00017271953,0.0005112204,0.001886866,0.532678],"study_design_scores_gemma":[0.0023488959,0.009886109,0.78652185,0.0053649857,0.00019893386,0.0003541145,0.021817924,0.0002786978,0.019725978,0.09359109,0.059361663,0.0005497835],"about_ca_topic_score_codex":0.00041429058,"about_ca_topic_score_gemma":0.00021150206,"teacher_disagreement_score":0.5321282,"about_ca_system_score_codex":0.00009863031,"about_ca_system_score_gemma":0.00074299227,"threshold_uncertainty_score":0.99989766},"labels":[],"label_agreement":null},{"id":"W3131964007","doi":"10.1038/s41746-021-00399-3","title":"CovidCTNet: an open-source deep learning approach to diagnose covid-19 using small cohort of CT images","year":2021,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":103,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; Princess Margaret Cancer Centre; Ontario Institute for Cancer Research; University of Toronto","funders":"National Institute for Medical Research Development; Tehran University of Medical Sciences and Health Services; University of Rochester","keywords":"Coronavirus disease 2019 (COVID-19); Cohort; Artificial intelligence; Deep learning; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); 2019-20 coronavirus outbreak; Open source; Computer science; Medicine; Medical physics; Virology; Internal medicine; Software; Infectious disease (medical specialty)","score_opus":0.06967825296814312,"score_gpt":0.35803284044559835,"score_spread":0.28835458747745524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3131964007","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9246894,0.0015352769,0.03586953,0.021667847,0.00034226113,0.0022076843,0.00005233901,0.0004211726,0.013214447],"genre_scores_gemma":[0.9577176,0.00009750041,0.0043862034,0.03518306,0.0004978559,0.00008618559,0.00048002822,0.00015245685,0.0013991023],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99616456,0.00020523959,0.00089229265,0.0011691678,0.00091400533,0.00065471564],"domain_scores_gemma":[0.99529505,0.0013085672,0.00030997928,0.0010811738,0.00047677895,0.0015284391],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009806149,0.0004815309,0.0013389231,0.00040780485,0.00020856876,0.00018983588,0.0005919762,0.00012558789,0.00031085912],"category_scores_gemma":[0.014925235,0.00043568207,0.0001285945,0.0012821127,0.00043682603,0.0004731609,0.0007040277,0.0005265025,0.00002404922],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013209282,0.0075745992,0.741933,0.0036479651,0.0010818186,0.004353199,0.009935057,0.03169114,0.049722,0.0005817782,0.027070107,0.12108839],"study_design_scores_gemma":[0.020773683,0.0066948505,0.07166399,0.004194941,0.0021026921,0.0040180637,0.009877268,0.015089774,0.015343778,0.0003499055,0.8475972,0.002293896],"about_ca_topic_score_codex":0.0015870079,"about_ca_topic_score_gemma":0.00006262927,"teacher_disagreement_score":0.8205271,"about_ca_system_score_codex":0.0005553728,"about_ca_system_score_gemma":0.00095214916,"threshold_uncertainty_score":0.9998095},"labels":[],"label_agreement":null},{"id":"W3134221810","doi":"10.1038/s41746-021-00410-x","title":"Assessing the quality of mobile applications in chronic disease management: a scoping review","year":2021,"lang":"en","type":"review","venue":"npj Digital Medicine","topic":"Mobile Health and mHealth Applications","field":"Health Professions","cited_by":87,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Université Laval; University of Victoria; The Quebec Population Health Research Network; Douglas College; University of Toronto; Women's College Hospital; The Scarborough Hospital","funders":"Canadian Institutes of Health Research","keywords":"Usability; Quality (philosophy); Quality management; Computer science; Medicine; Process management; Operations management; Engineering","score_opus":0.22574716160441624,"score_gpt":0.6114914662054894,"score_spread":0.38574430460107323,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3134221810","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[9.4165983e-7,0.9522959,0.00035725857,0.00067640946,0.00017708195,0.030828023,0.00011937741,0.0000566488,0.015488369],"genre_scores_gemma":[0.000033132666,0.9018618,0.000029914356,0.0008256998,0.00044601882,0.09491891,0.0013493269,0.00005278223,0.00048242294],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99317294,0.000964562,0.0039303536,0.00067929947,0.0005549026,0.00069792697],"domain_scores_gemma":[0.9925219,0.0031605917,0.002030477,0.0016102582,0.00020534948,0.00047142385],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0025038673,0.0004131802,0.0029042556,0.00021673966,0.00046111477,0.000016051255,0.00058276334,0.00021012139,0.00037391088],"category_scores_gemma":[0.0007650303,0.00025759175,0.00028418397,0.0017009386,0.00023459144,0.0001865405,0.00028183995,0.0010964209,0.00009517163],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[5.6432066e-7,0.000039784292,0.000024544688,0.46003342,0.000014020877,0.0000015116187,0.000019060215,1.7410406e-7,7.16475e-9,0.003860343,0.000773831,0.5352327],"study_design_scores_gemma":[0.0001769264,0.0000114604,0.000056629175,0.44883746,0.00021207974,5.515054e-7,0.0001622291,5.757437e-7,1.649277e-9,0.00007929348,0.5503657,0.000097123484],"about_ca_topic_score_codex":0.00005124261,"about_ca_topic_score_gemma":0.000046838086,"teacher_disagreement_score":0.54959184,"about_ca_system_score_codex":0.0007228786,"about_ca_system_score_gemma":0.004884791,"threshold_uncertainty_score":0.9999876},"labels":[],"label_agreement":null},{"id":"W3134471948","doi":"10.1038/s41746-021-00407-6","title":"Digital public health surveillance: a systematic scoping review","year":2021,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":96,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Health Services; University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; Cumming School of Medicine, University of Calgary; O'Brien Institute for Public Health, University of Calgary; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Public health; The Internet; Digital health; Public health surveillance; Systematic review; Underpinning; Medicine; Data science; Internet privacy; Public relations; Medical education; Computer science; MEDLINE; World Wide Web; Political science; Health care; Engineering; Pathology","score_opus":0.05479254040524195,"score_gpt":0.3476133980444081,"score_spread":0.29282085763916615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3134471948","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0068324865,0.7007277,0.0018605852,0.098180756,0.001504493,0.007987582,0.0012032378,0.001519656,0.1801835],"genre_scores_gemma":[0.9553893,0.016878322,0.00009750975,0.017739335,0.00070372166,0.00018165617,0.004669248,0.00011982762,0.0042210775],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9957569,0.00016207495,0.0014302827,0.00071599596,0.0011913979,0.0007433074],"domain_scores_gemma":[0.996125,0.0004612721,0.00045037124,0.0013076194,0.000604862,0.0010509097],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00097411877,0.0003938715,0.0022196393,0.00014813186,0.000093357245,0.000180057,0.00024432916,0.00006976683,0.00047180557],"category_scores_gemma":[0.01219849,0.00030014245,0.00022456149,0.0010864002,0.00023526445,0.000688118,0.0001839196,0.00026228736,0.00045945842],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049292048,0.0006503633,0.027105313,0.8697345,0.00045789458,0.0014857339,0.00019214308,4.095516e-7,0.000033388427,0.0003520502,0.0548902,0.04504871],"study_design_scores_gemma":[0.003221168,0.0006248074,0.0071903504,0.96690017,0.00010387818,0.0019634482,0.00041880482,0.000034448876,0.0000064074607,0.000057273683,0.018919623,0.0005596128],"about_ca_topic_score_codex":0.0000038570665,"about_ca_topic_score_gemma":0.000012571026,"teacher_disagreement_score":0.94855684,"about_ca_system_score_codex":0.00023766588,"about_ca_system_score_gemma":0.0014290297,"threshold_uncertainty_score":0.99994504},"labels":[],"label_agreement":null},{"id":"W3136582211","doi":"10.1038/s41746-021-00414-7","title":"Crowdsourcing digital health measures to predict Parkinson’s disease severity: the Parkinson’s Disease Digital Biomarker DREAM Challenge","year":2021,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Parkinson's Disease Mechanisms and Treatments","field":"Medicine","cited_by":64,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Max Planck ETH Center for Learning Systems; Academy of Finland; University of New South Wales; National Institutes of Health; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; European Commission; Cohen Veterans Bioscience; National Center for Advancing Translational Sciences; Agence Nationale de la Recherche; Georgia Clinical and Translational Science Alliance; University of Rochester; Michael J. Fox Foundation for Parkinson's Research; Robert Wood Johnson Foundation; American Parkinson Disease Association; National Institute of General Medical Sciences; Translational Cancer Research Network; Alfred Kordelinin Säätiö; Canadian Institutes of Health Research; National Science Foundation","keywords":"Dyskinesia; Crowdsourcing; Parkinson's disease; Disease; Physical medicine and rehabilitation; Biomarker; Medicine; Motor symptoms; Benchmark (surveying); Computer science; Internal medicine; World Wide Web","score_opus":0.03138687479558548,"score_gpt":0.27933386622573164,"score_spread":0.24794699143014615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3136582211","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.80418575,0.02795116,0.0025066664,0.120667,0.0021087131,0.004756867,0.0070986617,0.0013404588,0.02938471],"genre_scores_gemma":[0.9878031,0.00061417936,0.000048489303,0.0049738344,0.0010536499,0.00029194402,0.0018078898,0.00018739184,0.0032195367],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9934627,0.00010821137,0.0010541688,0.0016904199,0.0022494406,0.0014350502],"domain_scores_gemma":[0.99240494,0.00030334905,0.0003014964,0.0017189101,0.0004162335,0.004855045],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00035924968,0.0010006919,0.0012368374,0.00032595027,0.00053058227,0.0007334063,0.0004709923,0.00014286289,0.0002502715],"category_scores_gemma":[0.0023310024,0.00069179083,0.00056081865,0.0009145238,0.00041454204,0.0011228146,0.00045439013,0.0004455501,0.00032314245],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005504798,0.0061220084,0.28587198,0.0010125418,0.0019863418,0.011189745,0.0019455076,0.000021159572,0.00007801668,0.00052983966,0.04604009,0.63969797],"study_design_scores_gemma":[0.0040471163,0.0007207707,0.34824497,0.0014580466,0.00042558872,0.00016870494,0.0008532258,0.00023616136,0.000020769183,0.0010865075,0.64213437,0.0006037924],"about_ca_topic_score_codex":0.000036692425,"about_ca_topic_score_gemma":0.000018782479,"teacher_disagreement_score":0.6390942,"about_ca_system_score_codex":0.0005661154,"about_ca_system_score_gemma":0.0013316048,"threshold_uncertainty_score":0.9995533},"labels":[],"label_agreement":null},{"id":"W3138676254","doi":"10.1038/s41746-021-00423-6","title":"The potential of artificial intelligence to improve patient safety: a scoping review","year":2021,"lang":"en","type":"review","venue":"npj Digital Medicine","topic":"Clinical Reasoning and Diagnostic Skills","field":"Medicine","cited_by":288,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research","keywords":"Context (archaeology); Patient safety; Harm; Leverage (statistics); Health care; Computer science; Artificial intelligence; MEDLINE; Adverse effect; Medicine; Risk analysis (engineering); Intensive care medicine; Machine learning; Data science; Psychology","score_opus":0.06301976923425544,"score_gpt":0.4160997882411918,"score_spread":0.35308001900693636,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3138676254","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000002694599,0.99086636,0.00079341215,0.0021674442,0.0012316284,0.00290023,0.00007163677,0.0000336575,0.0019329364],"genre_scores_gemma":[0.000046931327,0.9973849,0.00010266372,0.00097018573,0.00082786253,0.00014234883,0.00028079568,0.000052726533,0.00019157573],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.9953353,0.000104759194,0.002630238,0.00062064803,0.00088580186,0.00042328003],"domain_scores_gemma":[0.9859941,0.011391816,0.0007243085,0.00096202386,0.00042880338,0.00049895304],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00072823477,0.000452082,0.0035818429,0.000104240135,0.00008167254,0.00003848979,0.00028517775,0.00021105078,0.00018197233],"category_scores_gemma":[0.13148585,0.00024367338,0.000723413,0.00074355234,0.00032613717,0.000039635634,0.00025927622,0.00053593784,0.00011788901],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029993535,0.00011212324,2.759915e-7,0.028112013,0.00012698995,0.00011950139,0.000015902293,2.1007072e-7,3.073374e-7,0.00028988943,0.0011750151,0.9700178],"study_design_scores_gemma":[0.00006487929,0.00096486777,5.0719103e-7,0.735522,0.0012982191,0.00012553357,0.00005077211,0.0000018697907,0.00000264709,0.000078590325,0.2617266,0.00016354288],"about_ca_topic_score_codex":0.000012012706,"about_ca_topic_score_gemma":0.0000028674094,"teacher_disagreement_score":0.96985424,"about_ca_system_score_codex":0.000098456556,"about_ca_system_score_gemma":0.0009740477,"threshold_uncertainty_score":0.99367124},"labels":[],"label_agreement":null},{"id":"W3155378790","doi":"10.1038/s41746-021-00441-4","title":"Machine learning prediction of blood alcohol concentration: a digital signature of smart-breathalyzer behavior","year":2021,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Substance Abuse Treatment and Outcomes","field":"Medicine","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute on Alcohol Abuse and Alcoholism; National Institutes of Health; Canada Research Chairs","keywords":"Cohort; Poison control; Simulation; Medicine; Computer science; Statistics; Artificial intelligence; Machine learning; Mathematics; Environmental health","score_opus":0.02179084628332751,"score_gpt":0.262459402135735,"score_spread":0.24066855585240748,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3155378790","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97735566,0.004550871,0.000029715835,0.0003973348,0.00021572277,0.00035471743,0.00009491578,0.0000887563,0.016912308],"genre_scores_gemma":[0.99491066,0.00017777996,0.000052575648,0.00006909375,0.000198981,0.000017224254,0.0011181395,0.00002872583,0.0034267933],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9983501,0.000016600401,0.0005558908,0.00029114558,0.000566374,0.0002199316],"domain_scores_gemma":[0.99885863,0.00015207217,0.00021167906,0.00028217986,0.0003439663,0.00015145824],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006564943,0.0002283599,0.0006247048,0.00008570981,0.000035989175,0.000016822267,0.0000637792,0.0001335775,0.00043410758],"category_scores_gemma":[0.0004127679,0.00016916337,0.0001605254,0.00039457408,0.00021247895,0.0003642792,0.000028238823,0.00023633036,0.000007420096],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002773712,0.000806704,0.96331406,0.0000934696,0.0004332654,0.0005337676,0.0012289458,0.0000034345796,0.021206694,0.00019955057,0.00020827867,0.01169449],"study_design_scores_gemma":[0.06752863,0.011616601,0.62655276,0.0047836457,0.009337461,0.0030823865,0.008146251,0.00042893225,0.25863263,0.00037727636,0.008570684,0.0009427465],"about_ca_topic_score_codex":0.0000048753363,"about_ca_topic_score_gemma":0.000003033387,"teacher_disagreement_score":0.33676127,"about_ca_system_score_codex":0.00003247433,"about_ca_system_score_gemma":0.000103199796,"threshold_uncertainty_score":0.68982816},"labels":[],"label_agreement":null},{"id":"W3156463266","doi":"10.1038/s41746-021-00440-5","title":"U-Sleep: resilient high-frequency sleep staging","year":2021,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"EEG and Brain-Computer Interfaces","field":"Neuroscience","cited_by":332,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Center for Advancing Translational Sciences; National Heart, Lung, and Blood Institute; Nvidia; Copenhagen Graduate School for Nanoscience and Nanotechnology; National Institutes of Health; Case Western Reserve University; Johns Hopkins University; Fundação para a Ciência e a Tecnologia; University of California, Davis; University of Minnesota; York University; University of Washington; American Sleep Medicine Foundation","keywords":"Polysomnography; Sleep (system call); Sleep Stages; Sleep medicine; Slow-wave sleep; Electroencephalography; Workflow; Convolutional neural network; Sleep study; Deep learning; Medicine; Artificial intelligence; Computer science; Sleep disorder; Insomnia; Psychiatry","score_opus":0.022672438987406767,"score_gpt":0.2678749680301528,"score_spread":0.24520252904274606,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3156463266","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8993155,0.00033032335,0.0017969289,0.008492294,0.00175763,0.00013363773,0.000030794286,0.00022383536,0.08791906],"genre_scores_gemma":[0.99363846,0.000017379461,0.00018966124,0.0030634825,0.00048236366,0.0000062836334,0.000015668265,0.000023980656,0.0025626968],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9980027,0.00005456949,0.0003597446,0.0006108078,0.00056215026,0.00041004384],"domain_scores_gemma":[0.9987834,0.00039149448,0.00008762568,0.00046106306,0.00008352554,0.00019286892],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010807588,0.00020905564,0.00028434425,0.000100319514,0.00010628396,0.00013640246,0.00036133677,0.000052703326,0.00034085975],"category_scores_gemma":[0.0012258013,0.00016185522,0.00005569067,0.000430558,0.00023904155,0.00044565607,0.00018372433,0.00023176632,0.00018786408],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000047197358,0.00037980315,0.0044597713,0.00012597119,0.00003536849,0.002420661,0.0018828985,0.00012955989,0.81446916,0.030287003,0.011398395,0.13436423],"study_design_scores_gemma":[0.0027813597,0.0009089571,0.005880961,0.0006561144,0.00004373907,0.00048362845,0.0008852396,0.0013606715,0.9262537,0.01676805,0.043142278,0.0008353016],"about_ca_topic_score_codex":0.000017087366,"about_ca_topic_score_gemma":0.000003503423,"teacher_disagreement_score":0.13352893,"about_ca_system_score_codex":0.00005213922,"about_ca_system_score_gemma":0.000034617613,"threshold_uncertainty_score":0.66002643},"labels":[],"label_agreement":null},{"id":"W3162006328","doi":"10.1038/s41746-021-00447-y","title":"Differential effects of the blood pressure state on pulse rate variability and heart rate variability in critically ill patients","year":2021,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Non-Invasive Vital Sign Monitoring","field":"Engineering","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Heart rate variability; Photoplethysmogram; Blood pressure; Cardiology; Medicine; Heart rate; Pulse (music); Internal medicine; Pulse pressure; Autonomic nervous system; Correlation; Mathematics; Computer science","score_opus":0.004388897247319036,"score_gpt":0.2037181567368407,"score_spread":0.19932925948952168,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3162006328","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99662393,0.000050109495,0.00037137125,0.00017367245,0.00093907455,0.00044166564,0.00005930344,0.000051677587,0.0012891836],"genre_scores_gemma":[0.9996478,0.000010278724,0.00002893755,0.00011203918,0.00010612317,0.00002179284,0.000011756477,0.000028136523,0.00003314147],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99834824,0.0002931905,0.0004069129,0.00035215885,0.00028833214,0.0003111425],"domain_scores_gemma":[0.99715316,0.0018885836,0.00003561087,0.00043818503,0.0003452221,0.00013925071],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0003324776,0.00023564938,0.00041593538,0.000044938457,0.000032496206,0.000035148452,0.0001314348,0.00008240453,0.000029046472],"category_scores_gemma":[0.011037011,0.00016990484,0.000051982865,0.00025841934,0.00019242716,0.00019168123,0.00013268473,0.0003099566,0.0000019038807],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014332117,0.0011630594,0.476774,0.0031394933,0.00027589177,0.000064281936,0.00063822843,0.00038979124,0.5091825,0.00038340513,0.00008658109,0.0077594416],"study_design_scores_gemma":[0.0023589118,0.0003015934,0.80053234,0.00069823646,0.00012329157,0.0000027061585,0.000014762121,0.00022204254,0.19232674,0.0031288653,0.000076686236,0.0002138216],"about_ca_topic_score_codex":0.000012494387,"about_ca_topic_score_gemma":0.0000032314138,"teacher_disagreement_score":0.32375833,"about_ca_system_score_codex":0.000034429744,"about_ca_system_score_gemma":0.000027210674,"threshold_uncertainty_score":0.9972935},"labels":[],"label_agreement":null},{"id":"W3167386324","doi":"10.1038/s41746-021-00459-8","title":"Leveraging artificial intelligence for pandemic preparedness and response: a scoping review to identify key use cases","year":2021,"lang":"en","type":"review","venue":"npj Digital Medicine","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":123,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research","keywords":"Grey literature; Preparedness; Operationalization; Triage; Pandemic; Public health; Psychological intervention; Preprint; Delphi method; Computer science; Medicine; Coronavirus disease 2019 (COVID-19); Artificial intelligence; Data science; MEDLINE; Medical emergency; Infectious disease (medical specialty); Disease; Nursing; Political science","score_opus":0.30572327218425255,"score_gpt":0.5010962774777272,"score_spread":0.19537300529347468,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3167386324","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00048933295,0.99062705,0.0010248949,0.00034916977,0.00050746213,0.0058875335,0.00086605555,0.0001811845,0.00006731776],"genre_scores_gemma":[0.00039513462,0.99456996,0.00021793516,0.0009962048,0.00055442285,0.0006726468,0.0021246318,0.0001249405,0.00034415064],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.995432,0.00025893265,0.0018127732,0.0012721352,0.0006582374,0.00056591455],"domain_scores_gemma":[0.9924488,0.004821296,0.00048827322,0.0011142822,0.00044428837,0.0006830547],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013442963,0.0007016451,0.004127028,0.00036552083,0.00010313637,0.00019039732,0.00030029766,0.000195296,0.00011033554],"category_scores_gemma":[0.04150988,0.00055394566,0.0004069979,0.00086502417,0.0002398483,0.0003726825,0.0003495096,0.00036028362,0.000048485836],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002479815,0.00005573273,0.000027322154,0.15213959,0.0001732454,0.0006452629,0.00020089268,1.1131323e-7,0.0000031837724,0.000018645369,0.0036511705,0.84283686],"study_design_scores_gemma":[0.00014221473,0.00025485147,0.000014079247,0.5810097,0.0011225324,0.0011418819,0.00010934785,0.0000017153118,7.7642545e-7,0.000013097131,0.41584897,0.0003408209],"about_ca_topic_score_codex":0.000015972575,"about_ca_topic_score_gemma":0.00001680748,"teacher_disagreement_score":0.84249604,"about_ca_system_score_codex":0.00034964242,"about_ca_system_score_gemma":0.0015371346,"threshold_uncertainty_score":0.9996912},"labels":[],"label_agreement":null},{"id":"W3176980366","doi":"10.1038/s41746-021-00470-z","title":"Using a Digital Neuro Signature to measure longitudinal individual-level change in Alzheimer’s disease: the Altoida large cohort study","year":2021,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","cited_by":64,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Adidas (Canada)","funders":"EIT Health; National Heart, Lung, and Blood Institute; Innosuisse - Schweizerische Agentur für Innovationsförderung; National Institutes of Health; Alzheimer's Association","keywords":"Neuropsychology; Neuropsychological assessment; Cognition; Dementia; Alzheimer's disease; Disease; Psychology; Neuropsychological test; Biomarker; Physical medicine and rehabilitation; Medicine; Clinical psychology; Audiology; Psychiatry; Internal medicine","score_opus":0.16059343850153088,"score_gpt":0.3796462796968277,"score_spread":0.2190528411952968,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3176980366","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9804884,0.0029252958,0.00017567886,0.0073563103,0.00027440416,0.0035194973,0.00033967904,0.000058859903,0.004861869],"genre_scores_gemma":[0.99513066,0.00001939008,0.000012042869,0.0030975011,0.00064082706,0.00024527535,0.0003402961,0.00005150443,0.000462492],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99561507,0.000117883326,0.00047925892,0.00077769207,0.0022102643,0.0007998382],"domain_scores_gemma":[0.99791265,0.00024726716,0.00008026144,0.0005837596,0.0004948179,0.00068124256],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007013254,0.00037879578,0.0005899749,0.0002989341,0.00015507775,0.00023641308,0.00028370417,0.00008195934,0.00041487924],"category_scores_gemma":[0.0019048102,0.00025159022,0.000120212,0.001318845,0.0001530736,0.00055245846,0.00044235593,0.00064395077,0.00006547547],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003784119,0.001691856,0.97283316,0.000035237204,0.00040702615,0.003601046,0.0008739851,7.9704336e-7,0.00011092011,0.000033048214,0.0010845037,0.018950004],"study_design_scores_gemma":[0.004164163,0.0010402085,0.9883092,0.00049203145,0.0005895735,0.00012880129,0.00175122,0.00006306043,0.000050275718,0.000049650847,0.0031188473,0.00024299222],"about_ca_topic_score_codex":0.00004229299,"about_ca_topic_score_gemma":0.00007518614,"teacher_disagreement_score":0.018707013,"about_ca_system_score_codex":0.000090413276,"about_ca_system_score_gemma":0.0003042699,"threshold_uncertainty_score":0.9999936},"labels":[],"label_agreement":null},{"id":"W3200084086","doi":"10.1038/s41746-021-00503-7","title":"Non-invasive diagnosis of deep vein thrombosis from ultrasound imaging with machine learning","year":2021,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Venous Thromboembolism Diagnosis and Management","field":"Medicine","cited_by":84,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Health Services","funders":"","keywords":"Medicine; Deep vein; Pulmonary embolism; Radiology; Referral; Gold standard (test); Ultrasound; Thrombosis; Clinical prediction rule; Prospective cohort study; Emergency medicine; Surgery; Internal medicine","score_opus":0.010937463365106403,"score_gpt":0.24591223267824108,"score_spread":0.23497476931313468,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3200084086","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95063156,0.0030893523,0.000722722,0.004257383,0.00023849211,0.00046422114,0.000052278403,0.00010625429,0.04043776],"genre_scores_gemma":[0.9952042,0.0016519252,0.0004897612,0.0012721771,0.0003431601,0.00006545798,0.00062834966,0.00006830256,0.0002766607],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99779856,0.000029781655,0.0005127421,0.0005575077,0.00069595757,0.0004054423],"domain_scores_gemma":[0.9979879,0.00070329837,0.00023121623,0.0004978871,0.00031156675,0.00026812017],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00013321395,0.00033907368,0.0011287853,0.00015898698,0.000097357086,0.0000503809,0.00014585903,0.0000658069,0.001373449],"category_scores_gemma":[0.00095124665,0.00025177674,0.00013131773,0.00049331074,0.0003029396,0.0002743732,0.00011666595,0.00030671142,0.00004278534],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009343423,0.0012531815,0.95777905,0.0003628341,0.0010392996,0.00068764226,0.0025880444,0.00006217138,0.010041519,0.00021855172,0.003692448,0.022181809],"study_design_scores_gemma":[0.008630298,0.0026317183,0.91209483,0.004795048,0.0023248526,0.00017258235,0.009471037,0.000386815,0.04326709,0.0006055445,0.014863355,0.00075683784],"about_ca_topic_score_codex":0.000631664,"about_ca_topic_score_gemma":0.00018914281,"teacher_disagreement_score":0.045684244,"about_ca_system_score_codex":0.00008826503,"about_ca_system_score_gemma":0.00010317025,"threshold_uncertainty_score":0.99999344},"labels":[],"label_agreement":null},{"id":"W3201556772","doi":"10.1038/s41746-021-00508-2","title":"Digital intervention increases influenza vaccination rates for people with diabetes in a decentralized randomized trial","year":2021,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Influenza Virus Research Studies","field":"Medicine","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba; University of British Columbia","funders":"Sanofi Pasteur; Sanofi","keywords":"Medicine; Vaccination; Randomized controlled trial; Diabetes mellitus; Influenza vaccine; Glycemic; Intervention (counseling); Logistic regression; Internal medicine; Immunology","score_opus":0.03819408838658505,"score_gpt":0.3796648798871834,"score_spread":0.34147079150059834,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3201556772","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9875985,0.002754309,0.0002999262,0.0013453239,0.00013902821,0.0036102803,0.00007566106,0.00009233524,0.0040846844],"genre_scores_gemma":[0.9967737,0.0001204344,0.0001261769,0.00046695175,0.00027367074,0.00096575404,0.0005613888,0.00004316772,0.00066871446],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.99736834,0.000112254624,0.0008755044,0.00044333262,0.0006598528,0.000540697],"domain_scores_gemma":[0.9965141,0.0020532333,0.00020699116,0.00027681212,0.0007384965,0.00021035892],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0006997666,0.00031049488,0.0014504394,0.000343029,0.000075403,0.00015477714,0.000101677906,0.00009652498,0.00018153316],"category_scores_gemma":[0.02144595,0.00020633728,0.00025244357,0.0006719995,0.00020719224,0.000767519,0.00009034724,0.00020545683,0.0000132639425],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.88421184,0.0013578457,0.079777166,0.00072659866,0.0006994148,0.00008230915,0.0005393969,0.00000646901,0.00027639777,0.0004119897,0.00088111457,0.031029481],"study_design_scores_gemma":[0.975291,0.0023269698,0.014098616,0.0013487664,0.00023645956,0.000018665756,0.0008221845,0.0004624199,0.00096132205,0.0008711144,0.0033194306,0.00024303113],"about_ca_topic_score_codex":0.000048302536,"about_ca_topic_score_gemma":0.00014694652,"teacher_disagreement_score":0.091079205,"about_ca_system_score_codex":0.00017861492,"about_ca_system_score_gemma":0.00019039004,"threshold_uncertainty_score":0.9867968},"labels":[],"label_agreement":null},{"id":"W3207121065","doi":"10.1038/s41746-021-00531-3","title":"Temporal convolutional networks predict dynamic oxygen uptake response from wearable sensors across exercise intensities","year":2021,"lang":"lv","type":"preprint","venue":"npj Digital Medicine","topic":"Cardiovascular and exercise physiology","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Research Institute for Aging; University of Waterloo; Toronto Rehabilitation Institute","funders":"Canadian Institutes of Health Research; Natural Sciences and Engineering Research Council of Canada; Government of Canada","keywords":"Cardiorespiratory fitness; VO2 max; Hyperparameter; Computer science; Artificial intelligence; Medicine; Physical therapy; Heart rate; Internal medicine","score_opus":0.014744738630396607,"score_gpt":0.26462911086045127,"score_spread":0.24988437223005466,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3207121065","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92548406,0.05608264,0.0019505535,0.0022237427,0.008389723,0.0017521183,0.002259001,0.00039027297,0.0014679104],"genre_scores_gemma":[0.96249455,0.009015384,0.00015414311,0.00066443253,0.004013898,0.00017861836,0.015486437,0.0002818041,0.0077107083],"study_design_codex":"randomized_trial","study_design_gemma":"observational","domain_scores_codex":[0.99005884,0.0005742465,0.0024274203,0.0027705133,0.0020752503,0.0020937396],"domain_scores_gemma":[0.9923558,0.0012184875,0.00071644236,0.0029140194,0.0014943708,0.001300876],"candidate_categories":["metaepi_narrow","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow","research_integrity"],"category_scores_codex":[0.0019710776,0.0018039481,0.005603176,0.0003722557,0.00042929183,0.00034367238,0.0007938951,0.0018594513,0.0012309403],"category_scores_gemma":[0.0024506107,0.0016246722,0.0019981929,0.0007083824,0.0027376174,0.0005173721,0.0018970122,0.003253961,0.00041790362],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.42263812,0.0052041584,0.009019056,0.0068484046,0.044870853,0.03973235,0.063163176,0.081569046,0.018270493,0.00009040854,0.09767782,0.21091612],"study_design_scores_gemma":[0.027678296,0.0031893905,0.67708606,0.058620997,0.008481869,0.0026460113,0.086827874,0.10882737,0.00033445685,0.0012218568,0.020269731,0.004816099],"about_ca_topic_score_codex":0.0022587297,"about_ca_topic_score_gemma":0.00009028522,"teacher_disagreement_score":0.668067,"about_ca_system_score_codex":0.0009726572,"about_ca_system_score_gemma":0.0013108442,"threshold_uncertainty_score":0.99997634},"labels":[],"label_agreement":null},{"id":"W3214205311","doi":"10.1038/s41746-021-00528-y","title":"Telephone, video, equity and access in virtual care","year":2021,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Telemedicine and Telehealth Implementation","field":"Medicine","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Women's College Hospital; University of Toronto","funders":"","keywords":"Equity (law); Health care; Telehealth; Videoconferencing; Business; Pandemic; Service delivery framework; Internet privacy; Service (business); Telemedicine; Coronavirus disease 2019 (COVID-19); Public relations; Telecommunications; Computer science; Medicine; Political science; Marketing; Economic growth; Economics","score_opus":0.05289607843928619,"score_gpt":0.4112261043490273,"score_spread":0.3583300259097411,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3214205311","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9419096,0.0020912862,0.00022352551,0.014338367,0.0003539044,0.0004407667,0.00002834777,0.00007757282,0.040536612],"genre_scores_gemma":[0.99224114,0.00025837426,0.00006636871,0.0060451967,0.00052124483,0.000023268813,0.00040498612,0.00002269028,0.0004167288],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9981736,0.000024342724,0.00051661365,0.00037844753,0.00053328485,0.0003737139],"domain_scores_gemma":[0.99897665,0.00015541876,0.000085351196,0.0002571513,0.00019312938,0.0003323217],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017811425,0.00018323098,0.00046830717,0.00020351434,0.000050048286,0.000046712044,0.00009395401,0.0000798035,0.0003723044],"category_scores_gemma":[0.00080789503,0.00014762342,0.000030020803,0.0005339005,0.00014854073,0.00039930968,0.00029832352,0.0002521361,0.000013831716],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020205823,0.0001233068,0.28427818,0.0005201546,0.00003157795,0.0008016715,0.0023706884,7.594888e-7,0.0012098073,0.00062987185,0.008742472,0.70108944],"study_design_scores_gemma":[0.014828054,0.002439748,0.8757475,0.0010930826,0.00012057964,0.0007212388,0.017153466,0.000041125848,0.0023752972,0.0011012531,0.08405574,0.0003229151],"about_ca_topic_score_codex":0.00017833796,"about_ca_topic_score_gemma":0.00028692948,"teacher_disagreement_score":0.70076656,"about_ca_system_score_codex":0.0001209703,"about_ca_system_score_gemma":0.000266139,"threshold_uncertainty_score":0.6019908},"labels":[],"label_agreement":null},{"id":"W4210804144","doi":"10.1038/s41746-021-00555-9","title":"PhenoPad: Building AI enabled note-taking interfaces for patient encounters","year":2022,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Electronic Health Records Systems","field":"Health Professions","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; Hospital for Sick Children; Toronto Rehabilitation Institute; University of Toronto; University Health Network","funders":"Hospital for Sick Children; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Handwriting; Computer science; Modalities; Human–computer interaction; Interface (matter); Variety (cybernetics); Clinical trial; User interface; Health care; Data science; Artificial intelligence; Medicine","score_opus":0.04653920708181176,"score_gpt":0.43270383728708367,"score_spread":0.3861646302052719,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210804144","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85677505,0.0023054094,0.023367438,0.021602107,0.01611976,0.007894506,0.00029252438,0.00067183,0.07097137],"genre_scores_gemma":[0.9885601,0.000009776331,0.00013795504,0.006825721,0.0010157366,0.0015219051,0.000069071495,0.00007396235,0.0017857742],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.996173,0.00029986523,0.0011754679,0.0004919828,0.00065907964,0.0012005691],"domain_scores_gemma":[0.9968375,0.0015869465,0.0007463396,0.00037498222,0.00019328474,0.00026094413],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001329883,0.00026273387,0.00058496784,0.00023933838,0.0012639579,0.000018417739,0.0003609402,0.000101012054,0.0008895833],"category_scores_gemma":[0.0014741184,0.00021943389,0.00006394368,0.00036551812,0.00007298033,0.00029150202,0.00028068386,0.0010818285,0.00004742627],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0024042882,0.00062205084,0.019234892,0.0060986397,0.00032407625,0.00008634109,0.10053896,0.0004942686,0.019048277,0.01794474,0.35628197,0.4769215],"study_design_scores_gemma":[0.0033200467,0.0037445116,0.00013133735,0.0012549356,0.000035198496,0.000022609504,0.020147108,0.001872384,0.00015481477,0.0021856017,0.9667634,0.00036805237],"about_ca_topic_score_codex":0.0004378139,"about_ca_topic_score_gemma":0.00006804199,"teacher_disagreement_score":0.61048144,"about_ca_system_score_codex":0.0016613842,"about_ca_system_score_gemma":0.0006732294,"threshold_uncertainty_score":0.9740313},"labels":[],"label_agreement":null},{"id":"W4220861269","doi":"10.1038/s41746-022-00567-z","title":"Smartphone applications for informal caregivers of chronically ill patients: a scoping review","year":2022,"lang":"en","type":"review","venue":"npj Digital Medicine","topic":"Mobile Health and mHealth Applications","field":"Health Professions","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; Princess Margaret Cancer Centre; Public Health Ontario; University of Toronto","funders":"Canadian Institutes of Health Research; Fundação de Amparo à Pesquisa do Estado de São Paulo; Government of Canada","keywords":"Dementia; Mood; Medicine; Family caregivers; Usability; Personalization; Quality of life (healthcare); Anxiety; Caregiver burden; Disease; Gerontology; Physical therapy; Psychiatry; Nursing; World Wide Web; Computer science","score_opus":0.10149263976804553,"score_gpt":0.4864160122637142,"score_spread":0.3849233724956687,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220861269","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.3222953e-7,0.93308496,0.00058922137,0.0007661141,0.0004846112,0.045030672,0.0014655803,0.000097133496,0.018481575],"genre_scores_gemma":[6.9450317e-7,0.8625908,0.00010663192,0.003758463,0.00051325903,0.12528677,0.007014345,0.000075399344,0.00065365434],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9942266,0.00017888311,0.0035741474,0.0005799073,0.00058335415,0.0008571572],"domain_scores_gemma":[0.9918151,0.0030769233,0.0026463089,0.0010093626,0.00085421605,0.0005980984],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00093188655,0.00046761066,0.0030183834,0.0002801048,0.0007317054,0.000004319649,0.0006287955,0.00033544123,0.0014618721],"category_scores_gemma":[0.002726726,0.00036751034,0.00039317054,0.00091885356,0.00021346686,0.00017552414,0.00026841485,0.0010173632,0.0001352883],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000074155378,0.000050788683,0.0000043467,0.3787465,0.000021337411,1.14744225e-7,0.000046914945,3.4817695e-8,1.7767815e-9,0.00058990775,0.02343218,0.59710044],"study_design_scores_gemma":[0.0008598532,0.00031571276,0.00000297441,0.25390816,0.0003530332,0.0000014267995,0.000080141304,3.5021196e-7,2.3992113e-9,0.000023297029,0.74428004,0.00017500101],"about_ca_topic_score_codex":0.000052033647,"about_ca_topic_score_gemma":0.000026108997,"teacher_disagreement_score":0.72084785,"about_ca_system_score_codex":0.00056106003,"about_ca_system_score_gemma":0.0052435305,"threshold_uncertainty_score":0.9998777},"labels":[],"label_agreement":null},{"id":"W4220928686","doi":"10.1038/s41746-022-00576-y","title":"Machine learning of language use on Twitter reveals weak and non-specific predictions","year":2022,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Mental Health via Writing","field":"Psychology","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Trinity College","funders":"Science Foundation Ireland; Horizon 2020 Framework Programme; Trinity College Dublin; MQ: Transforming Mental Health; Wellcome Trust","keywords":"Mental health; Depression (economics); Psychology; Anxiety; Set (abstract data type); Alcohol abuse; Clinical psychology; Psychiatry; Computer science","score_opus":0.04423126047728148,"score_gpt":0.3403301616868572,"score_spread":0.2960989012095757,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220928686","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8971629,0.00067296636,0.00007781072,0.0009614443,0.00049696176,0.00029480632,0.00008243063,0.000059754508,0.1001909],"genre_scores_gemma":[0.98733217,0.0000197574,0.000028160297,0.0006311115,0.00023176121,0.000051042625,0.00012336407,0.000028404253,0.0115542235],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99871665,0.000088561326,0.00037006158,0.00027154104,0.0003102899,0.00024289984],"domain_scores_gemma":[0.9991022,0.0003754485,0.00014602255,0.00023552414,0.000019297851,0.0001215438],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00029827975,0.00012250087,0.00024471738,0.0001674931,0.00015799401,0.00001186282,0.00009469263,0.000034857825,0.0024881752],"category_scores_gemma":[0.000098201686,0.00010860503,0.000026292746,0.00020496816,0.00011034102,0.00009624504,0.00009683359,0.00043800275,0.000052153933],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018251375,0.0015590946,0.5465875,0.0005444686,0.00026612708,0.0006388582,0.07748514,0.00009974405,0.011723374,0.012832742,0.1090172,0.23742056],"study_design_scores_gemma":[0.010680885,0.0118347835,0.5882633,0.0010588025,0.00007897806,0.0007569344,0.08573446,0.00059021567,0.00014688438,0.00044258236,0.2997031,0.0007091061],"about_ca_topic_score_codex":0.00014595536,"about_ca_topic_score_gemma":0.0000017101908,"teacher_disagreement_score":0.23671146,"about_ca_system_score_codex":0.00006270862,"about_ca_system_score_gemma":0.000006351165,"threshold_uncertainty_score":0.9984237},"labels":[],"label_agreement":null},{"id":"W4221133714","doi":"10.1038/s41746-022-00579-9","title":"Better Understanding of the Metamorphosis of Pregnancy (BUMP): protocol for a digital feasibility study in women from preconception to postpartum","year":2022,"lang":"en","type":"review","venue":"npj Digital Medicine","topic":"Maternal Mental Health During Pregnancy and Postpartum","field":"Medicine","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"SickKids Foundation; Vector Institute; Canadian Institute for Advanced Research","funders":"","keywords":"Pregnancy; Cohort; Protocol (science); Cohort study; Medicine; Alternative medicine","score_opus":0.22077143473717087,"score_gpt":0.42111780504315705,"score_spread":0.20034637030598618,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4221133714","genre_codex":"protocol","genre_gemma":"protocol","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"protocol","genre_consensus":"protocol","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026756944,0.23163079,0.000053602653,0.0005889086,0.0010467062,0.7347325,0.0031405264,0.000079642494,0.0019703996],"genre_scores_gemma":[0.13561665,0.0687214,0.00006754726,0.00036601123,0.0004992817,0.7928141,0.0005021561,0.00027340793,0.0011394954],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.99606204,0.0001639673,0.0018624316,0.00066734676,0.0007774439,0.00046674357],"domain_scores_gemma":[0.997304,0.00065011514,0.000925041,0.0008273426,0.000059874466,0.00023360098],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004500417,0.00049270137,0.002520419,0.00028641106,0.00006769905,0.000024991281,0.00042509014,0.00014566955,0.0003855416],"category_scores_gemma":[0.00052769686,0.0003051397,0.00036886643,0.00057569105,0.00016637584,0.000226582,0.00030238504,0.00043890704,0.0000036520446],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0056419605,0.0057992316,0.056046363,0.3400935,0.0009265032,0.000052903128,0.009314895,8.296455e-7,0.0000037143059,0.00005902687,0.00027461097,0.58178645],"study_design_scores_gemma":[0.013327573,0.019296043,0.014146783,0.7351793,0.0011705208,0.000049387494,0.0038318012,0.0000028481397,0.000032151318,0.0015294785,0.21060836,0.00082572264],"about_ca_topic_score_codex":0.00005915537,"about_ca_topic_score_gemma":0.000012849381,"teacher_disagreement_score":0.58096075,"about_ca_system_score_codex":0.0011759829,"about_ca_system_score_gemma":0.00029859474,"threshold_uncertainty_score":0.9999401},"labels":[],"label_agreement":null},{"id":"W4223430324","doi":"10.1038/s41746-022-00592-y","title":"Machine learning for medical imaging: methodological failures and recommendations for the future","year":2022,"lang":"en","type":"review","venue":"npj Digital Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":593,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute; Institut National de la Recherche Scientifique","funders":"Novo Nordisk Fonden; Agence Nationale de la Recherche","keywords":"Medical imaging; Psychology; Computer science; Data science; Engineering ethics; Artificial intelligence; Medical physics; Medicine; Engineering","score_opus":0.10375791139864335,"score_gpt":0.4339280365929593,"score_spread":0.330170125194316,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4223430324","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.1881414e-7,0.8506236,0.021318167,0.12364536,0.0012359296,0.0020048006,0.0000898205,0.00013113522,0.00095094304],"genre_scores_gemma":[0.000015423031,0.9840838,0.003109542,0.0027420423,0.0042821686,0.001007613,0.0027571577,0.00013873995,0.0018635647],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99665284,0.000291466,0.0010149821,0.0007546689,0.0007451072,0.00054093736],"domain_scores_gemma":[0.9844901,0.014075771,0.00044738542,0.00039959635,0.00009075358,0.0004963703],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003334709,0.00057515164,0.0022766902,0.00026231495,0.0006411668,0.00009913933,0.00046379937,0.00027329836,0.0011499228],"category_scores_gemma":[0.019935507,0.00030198824,0.000584203,0.00033501154,0.00056154135,0.00009845938,0.00028092752,0.0024048113,0.0000030746066],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000065599386,0.000049118506,0.000020691035,0.0039612353,0.0002909222,0.000028922788,0.00008144583,4.5833124e-7,9.1891806e-8,0.0018413573,0.034040574,0.9596196],"study_design_scores_gemma":[0.0017674961,0.0004877794,0.0000036815047,0.0033340878,0.0018343508,0.001380518,0.0004025262,0.004588564,2.7683228e-8,0.0005076544,0.9854048,0.00028852167],"about_ca_topic_score_codex":0.000021186732,"about_ca_topic_score_gemma":0.0000019823967,"teacher_disagreement_score":0.95933104,"about_ca_system_score_codex":0.00011152957,"about_ca_system_score_gemma":0.0003046417,"threshold_uncertainty_score":0.9999432},"labels":[],"label_agreement":null},{"id":"W4223442957","doi":"10.1038/s41746-022-00577-x","title":"A high-generalizability machine learning framework for predicting the progression of Alzheimer’s disease using limited data","year":2022,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":47,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Program on Open Innovation Platform with Enterprises, Research Institute and Academia; National Institute on Aging; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; Eisai; Japan Science and Technology Agency; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Northern California Institute for Research and Education; Pfizer; Biogen; BioClinica; Fujifilm Corporation; F. Hoffmann-La Roche; University of Southern California; Eli Lilly and Company; U.S. Department of Defense; Meso Scale Diagnostics; Alzheimer's Disease Neuroimaging Initiative; Novartis Pharmaceuticals Corporation; Bristol-Myers Squibb; Alzheimer's Association; Foundation for the National Institutes of Health","keywords":"Generalizability theory; Artificial intelligence; Machine learning; Computer science; Disease; Alzheimer's disease; Psychology; Medicine; Developmental psychology; Internal medicine","score_opus":0.36847750045530964,"score_gpt":0.5231412404781808,"score_spread":0.15466374002287114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4223442957","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95050657,0.005365179,0.011885113,0.020635657,0.0032202136,0.005472827,0.0023785087,0.00029928648,0.00023662583],"genre_scores_gemma":[0.994866,0.000023424012,0.0016547276,0.00076349,0.0009819943,0.0003426578,0.0012650389,0.000054538938,0.00004813574],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99627143,0.00075747434,0.0011485501,0.0005351268,0.0007368228,0.0005505921],"domain_scores_gemma":[0.9942154,0.003348669,0.0007506984,0.0011307552,0.00029857014,0.00025585847],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.002317414,0.00020420733,0.00042583628,0.00009670571,0.0022035986,0.000010790869,0.0007293312,0.00010062957,0.0004131785],"category_scores_gemma":[0.012074461,0.00013568527,0.00006089606,0.00051663304,0.00030669084,0.00025325496,0.0012093075,0.0012898505,0.0000038430467],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016006867,0.00036350402,0.8941557,0.0011042869,0.00014192401,0.000015716407,0.010826549,0.0039397134,0.000291321,0.010954104,0.0023260037,0.074280486],"study_design_scores_gemma":[0.0012765769,0.0022436269,0.012695209,0.0034357938,0.00066078856,0.000007991145,0.036486335,0.8643778,0.00013859657,0.03458834,0.04347412,0.00061485247],"about_ca_topic_score_codex":0.0012935217,"about_ca_topic_score_gemma":0.00004512991,"teacher_disagreement_score":0.8814605,"about_ca_system_score_codex":0.00011403676,"about_ca_system_score_gemma":0.0004161566,"threshold_uncertainty_score":0.9990954},"labels":[],"label_agreement":null},{"id":"W4224212258","doi":"10.1038/s41746-022-00595-9","title":"Machine learning and health need better values","year":2022,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute","funders":"","keywords":"Operationalization; Sociotechnical system; Harm; Introspection; Field (mathematics); Health care; Process (computing); Set (abstract data type); Value (mathematics); Computer science; Product (mathematics); Engineering ethics; Knowledge management; Data science; Psychology; Engineering; Political science; Social psychology; Epistemology; Machine learning","score_opus":0.13916775649927204,"score_gpt":0.4248653433613452,"score_spread":0.28569758686207314,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4224212258","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.74796367,0.0062034074,0.00020751772,0.22820215,0.00088649226,0.0005722718,0.000012834983,0.00017868802,0.015773004],"genre_scores_gemma":[0.9877678,0.00019397738,0.00007121873,0.008292343,0.0005769923,0.00002780814,0.00018146171,0.000020463152,0.0028679399],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99876374,0.000043334905,0.0003576812,0.00022733481,0.00035059077,0.00025729445],"domain_scores_gemma":[0.99936414,0.00011551501,0.000095643096,0.00012485065,0.00005456107,0.0002452994],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044680675,0.00011243446,0.0002714563,0.0001462758,0.00033286487,0.000016482056,0.00004713868,0.0000263625,0.0007062214],"category_scores_gemma":[0.00025380086,0.00009228014,0.000027983648,0.00024065314,0.000112922,0.000097572796,0.000062322666,0.0004180739,0.000022832059],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000112921945,0.00012591406,0.26892298,0.0001378531,0.000027591585,0.000025039888,0.0056099067,0.0000067073765,0.00014471712,0.00036990605,0.011862134,0.7126543],"study_design_scores_gemma":[0.0010185619,0.014089014,0.047201373,0.0005231976,0.000104641455,0.0011518532,0.045125905,0.0039589806,0.0004096812,0.012452032,0.87341344,0.00055134256],"about_ca_topic_score_codex":0.0006903787,"about_ca_topic_score_gemma":0.000007295893,"teacher_disagreement_score":0.8615513,"about_ca_system_score_codex":0.0001348769,"about_ca_system_score_gemma":0.000120754354,"threshold_uncertainty_score":0.7732629},"labels":[],"label_agreement":null},{"id":"W4224995026","doi":"10.1038/s41746-022-00596-8","title":"Continuous monitoring of surgical bimanual expertise using deep neural networks in virtual reality simulation","year":2022,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Surgical Simulation and Training","field":"Medicine","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Montreal Neurological Institute and Hospital","funders":"Montreal Neurological Institute and Hospital; Brain Tumour Research; King Fahad Medical City; Association of Surgeons of Great Britain and Ireland; Mitacs; Brain Tumour Foundation of Canada; Royal College of Physicians and Surgeons of Canada; McGill University","keywords":"Coaching; Psychomotor learning; Virtual reality; Computer science; Neurosurgery; Medical physics; Artificial intelligence; Physical medicine and rehabilitation; Machine learning; Psychology; Medicine; Cognition; Surgery","score_opus":0.06123148524459355,"score_gpt":0.3497350418061716,"score_spread":0.28850355656157806,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4224995026","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9933581,0.00035818317,0.002738982,0.00024408042,0.00041833278,0.00027378733,0.000003809453,0.000060779017,0.002543955],"genre_scores_gemma":[0.99930376,0.0000053155118,0.000018522896,0.000071347655,0.00046763866,0.00000915414,0.00005926507,0.000021429378,0.000043543005],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982215,0.00008473275,0.0006297701,0.00026343917,0.0005226951,0.0002778701],"domain_scores_gemma":[0.998877,0.0005577206,0.00014426453,0.00017382446,0.00007673619,0.0001704855],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034378353,0.00015591226,0.00050308486,0.0001788389,0.000077830904,0.000011146099,0.000073364215,0.0000639191,0.00024582964],"category_scores_gemma":[0.000271555,0.00013422062,0.00008261023,0.0005042864,0.00013450108,0.00016457326,0.00008583941,0.00033878605,6.2814837e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011062904,0.00021167075,0.15289615,0.000013530634,0.000023919765,0.00034843315,0.0009280526,0.6571369,0.00006543684,0.00008948484,0.000002853219,0.18717727],"study_design_scores_gemma":[0.0082676625,0.000696476,0.023747968,0.00009241115,0.000029135812,0.000079449375,0.0022310049,0.96367055,0.000013156266,0.000026779726,0.00101569,0.00012972506],"about_ca_topic_score_codex":0.00005709788,"about_ca_topic_score_gemma":8.7275663e-7,"teacher_disagreement_score":0.30653363,"about_ca_system_score_codex":0.00015558426,"about_ca_system_score_gemma":0.000021276128,"threshold_uncertainty_score":0.54733586},"labels":[],"label_agreement":null},{"id":"W4225927996","doi":"10.1038/s41746-021-00552-y","title":"Machine learning in vascular surgery: a systematic review and critical appraisal","year":2022,"lang":"en","type":"review","venue":"npj Digital Medicine","topic":"Renal and Vascular Pathologies","field":"Medicine","cited_by":123,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada Research Chairs; Public Health Ontario; Artificial Intelligence in Medicine (Canada); University of Toronto; St. Michael's Hospital","funders":"","keywords":"Medicine; Critical appraisal; Vascular surgery; MEDLINE; Systematic review; Data extraction; Receiver operating characteristic; Abdominal aortic aneurysm; Randomized controlled trial; Stenosis; Surgery; Internal medicine; Aneurysm; Cardiac surgery; Alternative medicine; Pathology","score_opus":0.07156965216405017,"score_gpt":0.3682808810693053,"score_spread":0.29671122890525514,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225927996","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000027076396,0.99532473,0.0000151347485,0.00052363885,0.00023579899,0.00187559,0.000024666777,0.00012498852,0.0018727583],"genre_scores_gemma":[0.000060583618,0.9979145,0.000015162281,0.00028516783,0.0001551287,0.00055793754,0.00064049475,0.00008343159,0.00028761834],"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","domain_scores_codex":[0.99602014,0.00055481616,0.0015569755,0.0006589457,0.0007690311,0.000440075],"domain_scores_gemma":[0.993736,0.005073216,0.00030545463,0.00056796684,0.00005130055,0.00026600677],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0019294008,0.00061348575,0.00788931,0.0005049207,0.00006971474,0.000036121182,0.00018085816,0.00019952287,0.00031122979],"category_scores_gemma":[0.03963022,0.00036794526,0.0007708331,0.0007816129,0.00028992177,0.00013024975,0.00023670688,0.0012937634,0.000040467043],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000038512735,0.000067171095,0.000031052256,0.8766689,0.0002290685,0.0009411619,0.000031573283,2.1517593e-8,2.7006594e-8,0.00007292028,0.00026529047,0.121689014],"study_design_scores_gemma":[0.00022655084,0.00022711746,0.0000069104444,0.49301773,0.0054818755,0.002125687,0.00004622883,0.0000033707502,5.2489866e-9,0.000011300045,0.49862832,0.00022489548],"about_ca_topic_score_codex":0.000013965993,"about_ca_topic_score_gemma":7.578889e-7,"teacher_disagreement_score":0.49836302,"about_ca_system_score_codex":0.00010772236,"about_ca_system_score_gemma":0.00018752331,"threshold_uncertainty_score":0.9998773},"labels":[],"label_agreement":null},{"id":"W4282942659","doi":"10.1038/s41746-022-00613-w","title":"Prostate cancer therapy personalization via multi-modal deep learning on randomized phase III clinical trials","year":2022,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":197,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre; Nova Scotia Cancer Centre; Centre Hospitalier de l’Université de Montréal; Horizon Health Network; Occupational Cancer Research Centre; Saint John Regional Hospital","funders":"National Cancer Institute; NRG Oncology","keywords":"Randomized controlled trial; Modal; Prostate cancer; Personalization; Clinical trial; Medicine; Cancer; Medical physics; Computer science; Artificial intelligence; Oncology; Internal medicine; World Wide Web","score_opus":0.07307830830311975,"score_gpt":0.45086439510705606,"score_spread":0.3777860868039363,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4282942659","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87714016,0.009041826,0.058115672,0.037079718,0.0039775595,0.005920546,0.00004172785,0.00058460067,0.008098181],"genre_scores_gemma":[0.986001,0.0016161911,0.00018121226,0.0054274383,0.001407445,0.00036261752,0.00045564625,0.00007827608,0.0044701523],"study_design_codex":"design_other","study_design_gemma":"randomized_trial","domain_scores_codex":[0.9951386,0.0013555256,0.001521282,0.0005624607,0.0010201674,0.00040197367],"domain_scores_gemma":[0.99621147,0.002337102,0.00065946823,0.00024650324,0.00013649336,0.00040895335],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008494128,0.0003178568,0.001978607,0.00024160292,0.00033349564,0.000046819267,0.00016270594,0.00008591483,0.0018308826],"category_scores_gemma":[0.011366142,0.00021214424,0.00043192328,0.00034717994,0.0004892675,0.00012755068,0.000069399954,0.0014598325,0.000013981703],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.12756567,0.0013572031,0.0044531673,0.00005779624,0.0006106232,0.00019017591,0.003243143,0.00072962436,0.0014798698,0.0001783422,0.0022468888,0.8578875],"study_design_scores_gemma":[0.65937835,0.0034880848,0.0004979505,0.00027964954,0.0003427302,0.00010438996,0.0008818447,0.26376012,0.00003540176,0.00015497812,0.07076724,0.0003092963],"about_ca_topic_score_codex":0.00009935773,"about_ca_topic_score_gemma":8.6440366e-7,"teacher_disagreement_score":0.8575782,"about_ca_system_score_codex":0.000144651,"about_ca_system_score_gemma":0.00014436354,"threshold_uncertainty_score":0.99908155},"labels":[],"label_agreement":null},{"id":"W4285012884","doi":"10.1038/s41746-022-00637-2","title":"The promise of machine learning applications in solid organ transplantation","year":2022,"lang":"en","type":"review","venue":"npj Digital Medicine","topic":"Renal Transplantation Outcomes and Treatments","field":"Medicine","cited_by":88,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Institutes of Health Research; Héma-Québec; Polytechnique Montréal; Centre Hospitalier de l’Université de Montréal; Université de Montréal; University of Ottawa; Vector Institute; Mila - Quebec Artificial Intelligence Institute; University of Toronto; Toronto General Hospital; University Health Network","funders":"","keywords":"Generalizability theory; MEDLINE; Medicine; Transplantation; Interpretability; Organ transplantation; Intensive care medicine; Computer science; Matching (statistics); Data extraction; Medical physics; Machine learning; Surgery; Pathology; Psychology","score_opus":0.04640388300708699,"score_gpt":0.3604793772593029,"score_spread":0.3140754942522159,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285012884","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000045358334,0.98872215,0.00009478513,0.00012252157,0.00007985267,0.0019078124,0.00016660508,0.00003933296,0.008821567],"genre_scores_gemma":[0.0025347625,0.9910305,0.000018080698,0.00001568019,0.00006458602,0.00038436393,0.004276565,0.000047384405,0.0016280442],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.998166,0.00006602979,0.00084707333,0.00027109132,0.00042980822,0.00021995277],"domain_scores_gemma":[0.998497,0.0007648424,0.00035118833,0.00025350507,0.00003530941,0.00009815269],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020371006,0.00029013678,0.0011812901,0.00023311596,0.00012977546,0.000013932817,0.00015626433,0.0000871238,0.00016653103],"category_scores_gemma":[0.00009441235,0.00015519849,0.0002125857,0.0005883301,0.00011771875,0.00006403238,0.000017292883,0.0004740242,0.000012486729],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008090708,0.00017810479,0.0011468485,0.017586032,0.00027273817,0.00009729949,0.00036421613,0.0000021749543,0.0000013226662,0.00029071415,0.000008264734,0.97997135],"study_design_scores_gemma":[0.001891654,0.00048376393,0.00030816178,0.0111447815,0.0013909829,0.00028119734,0.00014130458,0.000008039863,0.000003088392,0.00004867163,0.98415303,0.00014534533],"about_ca_topic_score_codex":0.000030058347,"about_ca_topic_score_gemma":0.000011788943,"teacher_disagreement_score":0.98414475,"about_ca_system_score_codex":0.00010612698,"about_ca_system_score_gemma":0.00015345601,"threshold_uncertainty_score":0.6328811},"labels":[],"label_agreement":null},{"id":"W4285795957","doi":"10.1038/s41746-022-00641-6","title":"A Delphi consensus statement for digital surgery","year":2022,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Delphi Technique in Research","field":"Social Sciences","cited_by":84,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; University of Toronto; St. Michael's Hospital","funders":"Bundesministerium für Wirtschaft und Energie; Bundesministerium für Gesundheit; Royal College of Surgeons of England; University of Bristol; National Institute for Health and Care Research; NIHR Imperial Biomedical Research Centre; University Hospitals Bristol NHS Foundation Trust; Research to Prevent Blindness","keywords":"Delphi method; Confidentiality; Digital health; Harm; Public relations; Medicine; Health care; Computer-assisted web interviewing; Political science; Business; Medical education; Computer science; Law; Marketing","score_opus":0.20876622618429713,"score_gpt":0.4603592201766032,"score_spread":0.25159299399230606,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285795957","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40722921,0.00072432787,0.00246487,0.1434367,0.0025213875,0.0047090985,0.0016553698,0.001218201,0.43604085],"genre_scores_gemma":[0.99293226,0.000017937144,0.0000731911,0.00035962125,0.0003449275,0.00042207766,0.00011516925,0.000025955289,0.005708837],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972026,0.00007847852,0.00044351185,0.00030140686,0.0013850494,0.00058896525],"domain_scores_gemma":[0.99670213,0.002492229,0.00012282828,0.0002354365,0.00019784718,0.0002495194],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020141623,0.00012750519,0.00026946983,0.0002285045,0.0005990945,0.00015379091,0.0003705495,0.000040334802,0.0006210455],"category_scores_gemma":[0.004392431,0.00011858211,0.000099438665,0.00052791735,0.0006833216,0.00023483635,0.00020350631,0.00019109595,0.00002310306],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002223813,0.00024277062,0.0033348459,0.00004475652,0.00005512379,0.00014719393,0.0044444627,0.000007837532,0.00007497764,0.014555386,0.82802296,0.14884734],"study_design_scores_gemma":[0.0004181909,0.0003405044,0.00011053404,0.00003333743,0.000007092936,0.000011128654,0.019257553,0.000034841985,0.00002039859,0.012665916,0.9669291,0.00017142278],"about_ca_topic_score_codex":0.00022868412,"about_ca_topic_score_gemma":0.000035330693,"teacher_disagreement_score":0.5857031,"about_ca_system_score_codex":0.0003500324,"about_ca_system_score_gemma":0.00046418246,"threshold_uncertainty_score":0.6800012},"labels":[],"label_agreement":null},{"id":"W4286485296","doi":"10.1038/s41746-022-00630-9","title":"Age estimation from sleep studies using deep learning predicts life expectancy","year":2022,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Obstructive Sleep Apnea Research","field":"Medicine","cited_by":35,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Center for Research Resources; National Heart, Lung, and Blood Institute; National Institute on Aging; National Center for Advancing Translational Sciences; Danmarks Tekniske Universitet; Johns Hopkins University; York University; National Institute of Arthritis and Musculoskeletal and Skin Diseases; Klarman Family Foundation; University of Washington; American Sleep Medicine Foundation; University of California, Davis; University of Minnesota; U.S. Department of Health and Human Services; National Institutes of Health; Case Western Reserve University","keywords":"Life expectancy; Estimation; Expectancy theory; Psychology; Econometrics; Artificial intelligence; Sleep (system call); Deep learning; Cognitive psychology; Computer science; Statistics; Gerontology; Demography; Mathematics; Medicine; Economics; Sociology; Social psychology","score_opus":0.0592865076667791,"score_gpt":0.3450982479370772,"score_spread":0.2858117402702981,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4286485296","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9817378,0.0056495285,0.0031163641,0.0010603968,0.000693037,0.00062358566,0.000026306112,0.00023863591,0.006854381],"genre_scores_gemma":[0.9972871,0.000026894511,0.0009653101,0.0002552487,0.0007375247,0.000074689626,0.00029960184,0.00006417836,0.00028947231],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99686813,0.00011429478,0.0005101478,0.0005159532,0.0015271236,0.00046435377],"domain_scores_gemma":[0.99843484,0.00046068564,0.00017687908,0.0003577929,0.00020996162,0.00035983755],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029245875,0.00026679836,0.00064106385,0.00032928406,0.0003923013,0.000036671707,0.00018261575,0.000056217337,0.00086101965],"category_scores_gemma":[0.004917978,0.0002293133,0.00008671729,0.00062497106,0.0003705427,0.00034891942,0.00039507207,0.0007520867,0.00003761465],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0030037912,0.0013455688,0.23096675,0.0008117145,0.0039109644,0.006374928,0.04790501,0.015168897,0.045318276,0.0009669019,0.0017192056,0.642508],"study_design_scores_gemma":[0.0314248,0.0116412025,0.15099135,0.0014413899,0.0017720262,0.0008895402,0.16084808,0.6183912,0.0019712013,0.007164378,0.011614065,0.0018507458],"about_ca_topic_score_codex":0.000050898972,"about_ca_topic_score_gemma":0.0000026348243,"teacher_disagreement_score":0.64065725,"about_ca_system_score_codex":0.00054599374,"about_ca_system_score_gemma":0.000050072205,"threshold_uncertainty_score":0.9427561},"labels":[],"label_agreement":null},{"id":"W4288684345","doi":"10.1038/s41746-022-00658-x","title":"Localization-adjusted diagnostic performance and assistance effect of a computer-aided detection system for pneumothorax and consolidation","year":2022,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Lung Cancer Diagnosis and Treatment","field":"Medicine","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"CAD; Medicine; Diagnostic accuracy; Artificial intelligence; Abnormality; Radiography; Radiology; Computer science","score_opus":0.008697279896513676,"score_gpt":0.24666832680741094,"score_spread":0.23797104691089727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4288684345","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99068564,0.000952458,0.006105171,0.00036870065,0.000286882,0.0012231838,0.00004864767,0.00005149177,0.00027779423],"genre_scores_gemma":[0.9991775,0.000102836166,0.000042130392,0.00007227002,0.000095839845,0.0003466191,0.00011369534,0.000016261138,0.00003281171],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9991229,0.000033586926,0.00026454657,0.00023523648,0.0002256697,0.000118035736],"domain_scores_gemma":[0.9987854,0.0007845311,0.00013823967,0.00012616199,0.0000801425,0.000085571424],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017967567,0.00013103274,0.00037585327,0.00009527112,0.0001263461,0.000013309522,0.000026205113,0.000028491722,0.0000062021822],"category_scores_gemma":[0.00018954652,0.00009925394,0.00002689778,0.00017215818,0.00009907265,0.0000971369,0.000032209013,0.000059365997,4.1554762e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0026463845,0.0003712662,0.56046045,0.011503058,0.00045571243,0.0000529086,0.0010505073,0.0006243403,0.0015761418,0.00035141016,0.00141688,0.41949093],"study_design_scores_gemma":[0.06814092,0.09995414,0.5187182,0.011972158,0.003907216,0.002060836,0.002178217,0.22695643,0.046799347,0.0000791952,0.018159218,0.0010741493],"about_ca_topic_score_codex":0.000020398375,"about_ca_topic_score_gemma":0.0000028992858,"teacher_disagreement_score":0.41841677,"about_ca_system_score_codex":0.00019090559,"about_ca_system_score_gemma":0.000024049923,"threshold_uncertainty_score":0.40474585},"labels":[],"label_agreement":null},{"id":"W4289781034","doi":"10.1038/s41746-022-00638-1","title":"Clinical use of artificial intelligence in endometriosis: a scoping review","year":2022,"lang":"en","type":"review","venue":"npj Digital Medicine","topic":"Endometriosis Research and Treatment","field":"Medicine","cited_by":90,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"B.C. Women's Hospital & Health Centre; University of British Columbia; Western University","funders":"","keywords":"Endometriosis; Logistic regression; Artificial intelligence; Machine learning; Medicine; Decision tree; Random forest; Psychological intervention; Predictive modelling; Decision support system; Disease; Medical physics; Computer science; Pathology","score_opus":0.43497645135183555,"score_gpt":0.5310461331984203,"score_spread":0.09606968184658476,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4289781034","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000050761046,0.991925,0.000048443788,0.00019201665,0.00027534654,0.005544981,0.00008545839,0.00003744053,0.0018862435],"genre_scores_gemma":[0.00005876495,0.99786156,0.00019508867,0.00023662606,0.00027765284,0.000666088,0.00048180443,0.00007003289,0.00015238856],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99287075,0.00043542616,0.0038490782,0.0007924134,0.0014875125,0.0005648065],"domain_scores_gemma":[0.9760736,0.02148867,0.0008658622,0.0009340409,0.00014248012,0.00049532735],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0019562128,0.0005493482,0.006409818,0.0019789163,0.000036866542,0.000027293116,0.00034890918,0.00021322057,0.0017166595],"category_scores_gemma":[0.104245566,0.0003639048,0.0010339529,0.0047853794,0.0004014699,0.00020576795,0.00031863197,0.0012501689,0.000084682506],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000054925233,0.0006962088,0.00006775614,0.13511409,0.00027475957,0.00051495107,0.000008580396,4.0762256e-8,3.2596567e-8,0.000055146418,0.0002980118,0.8629155],"study_design_scores_gemma":[0.00033392958,0.0016805684,0.0000044086714,0.473573,0.0007271079,0.00012915804,0.000013959141,0.0000012265155,3.3232152e-7,0.00001592403,0.52337164,0.00014872022],"about_ca_topic_score_codex":0.000037382993,"about_ca_topic_score_gemma":0.000010388686,"teacher_disagreement_score":0.8627668,"about_ca_system_score_codex":0.00037219402,"about_ca_system_score_gemma":0.0011054978,"threshold_uncertainty_score":0.99988127},"labels":[],"label_agreement":null},{"id":"W4297338512","doi":"10.1038/s41746-022-00681-y","title":"Ageing and degeneration analysis using ageing-related dynamic attention on lateral cephalometric radiographs","year":2022,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Dental Radiography and Imaging","field":"Dentistry","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Fundamental Research Funds for the Central Universities; Natural Science Foundation of Shaanxi Province; National Natural Science Foundation of China","keywords":"Ageing; Salience (neuroscience); Craniofacial; Radiography; Age groups; Medicine; Artificial intelligence; Computer science; Surgery","score_opus":0.011633104939881513,"score_gpt":0.26291816009831054,"score_spread":0.251285055158429,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297338512","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9950776,0.0009970512,0.00046305114,0.00007030765,0.00078235666,0.00017103025,0.000049204755,0.000110713285,0.0022786672],"genre_scores_gemma":[0.99863356,0.00002458365,0.00003451737,0.000117226584,0.00006401683,0.000010254975,0.0005304139,0.000028346489,0.00055706187],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9981127,0.0000863639,0.0004432749,0.00045283025,0.0006138609,0.00029099593],"domain_scores_gemma":[0.9993323,0.000080285354,0.00019409135,0.00023583541,0.000036289148,0.00012116378],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027584063,0.00021560575,0.000350015,0.0029878195,0.00043916333,0.00016981343,0.00013832278,0.00004735114,0.00023309317],"category_scores_gemma":[0.00007110217,0.00020766939,0.0002345481,0.0058681904,0.00012584284,0.0005429737,0.00008916198,0.00029270962,0.000009343356],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024968147,0.0005588903,0.78457665,0.00011890777,0.0034637982,0.0042746663,0.0011825841,0.006547437,0.09144089,0.00059089257,0.00065964216,0.10633594],"study_design_scores_gemma":[0.0020660856,0.00040210152,0.94196165,0.00007949256,0.0011415038,0.00043037406,0.00069142674,0.052075826,0.00006839134,0.00046625847,0.0002141589,0.00040276512],"about_ca_topic_score_codex":0.000103512604,"about_ca_topic_score_gemma":0.000015160638,"teacher_disagreement_score":0.15738495,"about_ca_system_score_codex":0.00012955947,"about_ca_system_score_gemma":0.000007490975,"threshold_uncertainty_score":0.8468512},"labels":[],"label_agreement":null},{"id":"W4307386048","doi":"10.1038/s41746-022-00710-w","title":"Predicting radiocephalic arteriovenous fistula success with machine learning","year":2022,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Central Venous Catheters and Hemodialysis","field":"Health Professions","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; St. Michael's Hospital","funders":"National Heart, Lung, and Blood Institute; National Institutes of Health; Brigham and Women's Hospital; U.S. Department of Health and Human Services","keywords":"Medicine; Arteriovenous fistula; Receiver operating characteristic; Hemodialysis; Decision tree; Logistic regression; Random forest; Logistic model tree; Machine learning; Radiology; Computer science; Surgery; Internal medicine","score_opus":0.02276550189376183,"score_gpt":0.3052088456266984,"score_spread":0.2824433437329366,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4307386048","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9541449,0.00057189947,0.00023917608,0.0025616193,0.00050650566,0.0005749215,0.0001017225,0.00025473716,0.04104451],"genre_scores_gemma":[0.99267304,0.00003119914,0.000021077069,0.0009815593,0.00057963433,0.00013016383,0.00036711415,0.00005411421,0.0051620896],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977102,0.00018516494,0.0004775171,0.00036585837,0.0006114268,0.0006497759],"domain_scores_gemma":[0.9988467,0.00030604305,0.00027598446,0.0002728992,0.00006754018,0.00023081478],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00043871123,0.00021597324,0.00048249884,0.00014556054,0.0017431935,0.000019145838,0.00024173278,0.00005277264,0.002360194],"category_scores_gemma":[0.00015232588,0.00015885255,0.000069841415,0.0004139034,0.00011132762,0.0001749195,0.0001861,0.0010476528,0.000042199583],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005248235,0.0003626898,0.9445035,0.00022224909,0.00020507188,0.00028956603,0.024383353,0.00041923227,0.00034333297,0.00033061454,0.002637722,0.025777884],"study_design_scores_gemma":[0.015658397,0.011150407,0.10388889,0.0010106631,0.00059505407,0.0005303897,0.03962426,0.010063584,0.00002511628,0.00053201977,0.8154909,0.0014303485],"about_ca_topic_score_codex":0.0006405228,"about_ca_topic_score_gemma":0.000098468,"teacher_disagreement_score":0.84061456,"about_ca_system_score_codex":0.00027678776,"about_ca_system_score_gemma":0.00012500258,"threshold_uncertainty_score":0.9995564},"labels":[],"label_agreement":null},{"id":"W4307511335","doi":"10.1038/s41746-022-00707-5","title":"Computer vision in surgery: from potential to clinical value","year":2022,"lang":"en","type":"review","venue":"npj Digital Medicine","topic":"Surgical Simulation and Training","field":"Medicine","cited_by":198,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; Artificial Intelligence in Medicine (Canada)","funders":"Horizon 2020 Framework Programme; Agence Nationale de la Recherche; European Commission","keywords":"Value (mathematics); Medicine; Optometry; General surgery; Medical physics; Artificial intelligence; Computer science; Machine learning","score_opus":0.16533228863459287,"score_gpt":0.44733049255360113,"score_spread":0.28199820391900826,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4307511335","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008945617,0.9807891,0.00034463572,0.0009460849,0.004199041,0.0012874652,0.00010320085,0.00016967047,0.011266212],"genre_scores_gemma":[0.008746865,0.9808067,0.00013953692,0.0021719143,0.004498804,0.000043062468,0.0031757618,0.00010108966,0.00031627156],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9960968,0.00022414316,0.0017525465,0.00074639183,0.0008262731,0.00035386087],"domain_scores_gemma":[0.9947153,0.003998444,0.000260726,0.0004386217,0.000036802987,0.00055014767],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000884328,0.00041173445,0.0033188388,0.0004934052,0.000042567957,0.000038040656,0.00017649755,0.00029594445,0.0033093921],"category_scores_gemma":[0.0012793764,0.00028787908,0.0006894708,0.0007746422,0.000107137006,0.00009117104,0.00021949499,0.000925452,0.000283525],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000113209506,0.00019472111,0.0002912488,0.00053786027,0.00010242767,0.0010773008,0.000029496563,0.0000066004477,8.772092e-9,0.000023935765,0.0026603881,0.9949628],"study_design_scores_gemma":[0.0017927664,0.00058010983,0.0013773531,0.0124571435,0.00031010553,0.00006781139,0.000018465826,0.00019355278,5.531167e-9,0.000042928183,0.9829101,0.00024964914],"about_ca_topic_score_codex":0.000038395097,"about_ca_topic_score_gemma":0.000001460631,"teacher_disagreement_score":0.9947131,"about_ca_system_score_codex":0.00015033846,"about_ca_system_score_gemma":0.00022794193,"threshold_uncertainty_score":0.9999573},"labels":[],"label_agreement":null},{"id":"W4308194052","doi":"10.1038/s41746-022-00716-4","title":"Representational ethical model calibration","year":2022,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Ethics in Clinical Research","field":"Medicine","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Wellcome; Medical Research Council; University College London Hospitals NHS Foundation Trust; Engineering and Physical Sciences Research Council; National Institute for Health and Care Research; Wellcome Trust","keywords":"Biobank; Fidelity; Equity (law); Management science; Health care; Context (archaeology); Population; Data science; Computer science; Engineering ethics; Epistemology; Psychology; Sociology; Political science; Engineering","score_opus":0.5277191323212951,"score_gpt":0.5939597710879909,"score_spread":0.06624063876669584,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4308194052","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17116986,0.00022268367,0.011913769,0.45467192,0.00063611404,0.0009377219,0.00012172711,0.0002882365,0.36003795],"genre_scores_gemma":[0.9674134,0.000025562578,0.00047926776,0.011786412,0.00042702587,0.00007437052,0.0003195007,0.000025927542,0.01944849],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9960425,0.00006831139,0.0004925092,0.00040541883,0.0027386064,0.00025264238],"domain_scores_gemma":[0.9952769,0.003643978,0.00007370658,0.00044394116,0.00025143338,0.00030999817],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0018707123,0.000109632,0.00026549122,0.00013321436,0.00018897148,0.000024240222,0.0002042362,0.00021995006,0.0019460557],"category_scores_gemma":[0.017248562,0.000090187685,0.00007777681,0.00035472363,0.00046355915,0.00012643848,0.00032493946,0.0035913356,0.00003476273],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0024200047,0.0011044241,0.019714223,0.00038001817,0.00019598876,0.00061786437,0.0024172324,0.006376483,0.005881762,0.7849768,0.16214333,0.013771881],"study_design_scores_gemma":[0.0064029666,0.0034519192,0.0057370435,0.00023261261,0.00009080912,0.00038521737,0.0017552115,0.29675245,0.0002881893,0.6632446,0.021302482,0.00035647702],"about_ca_topic_score_codex":0.000017371627,"about_ca_topic_score_gemma":0.0000036797426,"teacher_disagreement_score":0.7962436,"about_ca_system_score_codex":0.00014170387,"about_ca_system_score_gemma":0.0005750476,"threshold_uncertainty_score":0.9989663},"labels":[],"label_agreement":null},{"id":"W4309563912","doi":"10.1038/s41746-022-00709-3","title":"Improving the repeatability of deep learning models with Monte Carlo dropout","year":2022,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":90,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"National Eye Institute; Natural Sciences and Engineering Research Council of Canada; Eunice Kennedy Shriver National Institute of Child Health and Human Development; Genentech; Mitacs; National Cancer Institute; National Institutes of Health; U.S. Department of Health and Human Services; Polytechnique Montréal; Research to Prevent Blindness; Foundation for the National Institutes of Health","keywords":"Dropout (neural networks); Monte Carlo method; Repeatability; Computer science; Deep learning; Artificial intelligence; Machine learning; Statistics; Mathematics","score_opus":0.011748409491715036,"score_gpt":0.24371177153516085,"score_spread":0.2319633620434458,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4309563912","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9575963,0.001251958,0.011498598,0.0069574183,0.0002215306,0.00055134937,0.000007589055,0.00013942985,0.021775829],"genre_scores_gemma":[0.9977105,0.000015783702,0.0003527315,0.0005813985,0.00019494862,0.000035698486,0.000026083959,0.000041436437,0.0010413895],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978965,0.00008769244,0.00043621432,0.00036256033,0.0009045686,0.00031244228],"domain_scores_gemma":[0.9986767,0.00028824768,0.00023627654,0.00049509865,0.00012414962,0.00017948127],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008788048,0.00018813567,0.000487541,0.000101257436,0.0002762426,0.000019895924,0.00023354785,0.00003074327,0.00014302786],"category_scores_gemma":[0.0011840365,0.00010709345,0.00008610076,0.00034646952,0.00052856153,0.0001662945,0.00020719058,0.0011050513,0.0000013695895],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0020817823,0.0005882133,0.18723878,0.00069150876,0.00045702312,0.00052981597,0.011793653,0.058051027,0.0035439867,0.002434112,0.0007920764,0.731798],"study_design_scores_gemma":[0.0053853556,0.0050682095,0.0076485234,0.0003073425,0.00039138464,0.0011414308,0.012403209,0.95352226,0.0000967554,0.0007209414,0.0129491165,0.0003654497],"about_ca_topic_score_codex":0.00037367787,"about_ca_topic_score_gemma":0.000003763721,"teacher_disagreement_score":0.8954713,"about_ca_system_score_codex":0.00011155392,"about_ca_system_score_gemma":0.000088298184,"threshold_uncertainty_score":0.4800959},"labels":[],"label_agreement":null},{"id":"W4317815057","doi":"10.1038/s41746-023-00753-7","title":"Making machine learning matter to clinicians: model actionability in medical decision-making","year":2023,"lang":"en","type":"review","venue":"npj Digital Medicine","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":57,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Hospital for Sick Children","funders":"Hospital for Sick Children","keywords":"Metric (unit); Computer science; Point (geometry); Medical decision making; Machine learning; Calibration; Artificial intelligence; Management science; Medicine; Engineering; Mathematics; Medical emergency","score_opus":0.45664069738851165,"score_gpt":0.5864048797666964,"score_spread":0.12976418237818477,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317815057","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009888948,0.96879065,0.005927772,0.009084447,0.0028272266,0.0031155301,0.000050447583,0.0003711322,0.008843876],"genre_scores_gemma":[0.022907235,0.9684916,0.00051570457,0.0034235634,0.0024573926,0.00031339773,0.0003274017,0.00021235127,0.0013513612],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.994324,0.00012518284,0.002600961,0.00095321337,0.0013258175,0.0006708085],"domain_scores_gemma":[0.994469,0.0037843161,0.00040397857,0.00062521046,0.00022364256,0.0004938928],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0018501513,0.0005349376,0.0023394497,0.0010209348,0.0001225831,0.000052288477,0.0003623883,0.0007291446,0.0011359378],"category_scores_gemma":[0.018514121,0.00040141377,0.00028630014,0.0014875192,0.00016975382,0.00020359184,0.00020770862,0.0020035943,0.002182254],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000073940944,0.000107868414,0.0014493763,0.00615261,0.000042223066,0.00011481944,0.00048335356,0.000059369395,4.8003248e-8,0.000029910421,0.002016744,0.9894697],"study_design_scores_gemma":[0.00013349432,0.00052690605,0.00019786658,0.22892016,0.00033777778,0.0002866757,0.00075189536,0.0059497724,1.4184094e-7,0.003550593,0.75877404,0.000570678],"about_ca_topic_score_codex":0.00012789117,"about_ca_topic_score_gemma":0.00020259792,"teacher_disagreement_score":0.98889905,"about_ca_system_score_codex":0.0007599433,"about_ca_system_score_gemma":0.0012112883,"threshold_uncertainty_score":0.9998438},"labels":[],"label_agreement":null},{"id":"W4319039932","doi":"10.1038/s41746-023-00757-3","title":"Multi-modality data-driven analysis of diagnosis and treatment of psoriatic arthritis","year":2023,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Rheumatoid Arthritis Research and Therapies","field":"Medicine","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"SKiN Health","funders":"National Health and Medical Research Council; National Natural Science Foundation of China","keywords":"Psoriatic arthritis; Psoriasis; Medicine; Methotrexate; Leverage (statistics); Internal medicine; Oncology; Machine learning; Artificial intelligence; Computer science; Dermatology","score_opus":0.07885102612230678,"score_gpt":0.3556399481009212,"score_spread":0.27678892197861443,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319039932","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.988956,0.007389368,0.000056671935,0.0020456505,0.000053243934,0.0003812907,0.0007060036,0.00005085481,0.00036091465],"genre_scores_gemma":[0.9255521,0.07315249,0.00012782111,0.00001672072,0.00004638815,0.000035085737,0.0009558055,0.000012704101,0.000100864614],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9985124,0.000032131837,0.00047494358,0.00030310906,0.00044938986,0.00022803045],"domain_scores_gemma":[0.9985695,0.0003795204,0.00011575186,0.00061001175,0.00011625115,0.00020898465],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017815748,0.00014485118,0.0009118148,0.00050767715,0.000031559335,0.000011458415,0.00011215108,0.000045550347,0.0001463068],"category_scores_gemma":[0.00070685684,0.000102375845,0.00009551556,0.0010694333,0.00043540177,0.0001757787,0.000081116275,0.000048297858,0.000009669848],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017837014,0.00072904275,0.28460574,0.000113590846,0.003396251,0.00012623711,0.0014773816,0.000012616928,0.0007989352,0.00010953254,0.0006723024,0.70778],"study_design_scores_gemma":[0.011894089,0.004564439,0.95444685,0.0010069134,0.00056633406,0.00002656641,0.00143061,0.01566733,0.0007209058,0.00022790581,0.009242201,0.00020586132],"about_ca_topic_score_codex":0.0003465211,"about_ca_topic_score_gemma":0.00019916298,"teacher_disagreement_score":0.7075741,"about_ca_system_score_codex":0.000024079198,"about_ca_system_score_gemma":0.00004722072,"threshold_uncertainty_score":0.41747656},"labels":[],"label_agreement":null},{"id":"W4319298080","doi":"10.1038/s41746-023-00765-3","title":"Towards artificial intelligence-based learning health system for population-level mortality prediction using electrocardiograms","year":2023,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Canadian VIGOUR Centre; University of Alberta","funders":"Canadian Institutes of Health Research; Alberta Innovates; University of Alberta; Alberta Health Services","keywords":"Artificial intelligence; Computer science; Machine learning","score_opus":0.1443796521940316,"score_gpt":0.38076821585427556,"score_spread":0.23638856366024397,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319298080","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.054308344,0.000078075755,0.93893635,0.0029499864,0.0012979215,0.0007212156,0.000035544894,0.0014127848,0.00025977832],"genre_scores_gemma":[0.99317694,0.0000039183446,0.005425272,0.00015696522,0.0007274634,0.000058778216,0.00039066025,0.00003082484,0.000029155726],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970985,0.00014562333,0.0007760491,0.00059184374,0.00077137846,0.00061661843],"domain_scores_gemma":[0.9985534,0.00023856474,0.00031061325,0.00043509607,0.0002129318,0.00024941005],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001461232,0.00022590107,0.0004447725,0.00037211357,0.00043484604,0.00016511616,0.00040741908,0.00010139637,0.0000026016073],"category_scores_gemma":[0.000843357,0.00020389278,0.00012033517,0.0015118098,0.000055271892,0.0003963361,0.00008257419,0.0003417721,0.000014175306],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004288563,0.00004367916,0.0647291,0.0011184883,0.00006592309,0.000016013051,0.0008226091,0.087896556,0.000061243605,0.032273084,0.00024054413,0.8126899],"study_design_scores_gemma":[0.00017557775,0.0007700559,0.029609837,0.00040930675,0.000013127623,0.000017063474,0.00024073222,0.9653598,0.00005237849,0.0025654288,0.00061098736,0.00017568527],"about_ca_topic_score_codex":0.001383323,"about_ca_topic_score_gemma":0.000028586934,"teacher_disagreement_score":0.93886864,"about_ca_system_score_codex":0.00038091847,"about_ca_system_score_gemma":0.000298082,"threshold_uncertainty_score":0.83145064},"labels":[],"label_agreement":null},{"id":"W4321226584","doi":"10.1038/s41746-023-00749-3","title":"Long-term participant retention and engagement patterns in an app and wearable-based multinational remote digital depression study","year":2023,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Digital Mental Health Interventions","field":"Psychology","cited_by":56,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Krembil Foundation; University of Toronto","funders":"Economic and Social Research Council; Engineering and Physical Sciences Research Council; Scottish Government; Chief Scientist Office, Scottish Government Health and Social Care Directorate; NIHR BioResource; GIESKES-STRIJBIS FONDS; Institut Català de la Salut; Innovative Medicines Initiative; King's Health Partners; ZonMw; National Institute for Health Research Applied Research Collaboration South London; South London and Maudsley NHS Foundation Trust; NIHR Maudsley Biomedical Research Centre; Health and Social Care Research and Development Division; Public Health Agency; European Commission; King's College London; Medical Research Council; Department of Health and Social Care; NHS Blood and Transplant; National Institute for Health and Care Research; UK Research and Innovation; Wellcome Trust; University College London; British Heart Foundation; European Federation of Pharmaceutical Industries and Associations; King's College Hospital NHS Foundation Trust; Alzheimer's Society","keywords":"mHealth; Data collection; Generalizability theory; Wearable technology; Depression (economics); Wearable computer; Psychology; Digital health; Medicine; Computer science; Health care; Psychiatry; Developmental psychology","score_opus":0.1332883568546411,"score_gpt":0.42810007266058714,"score_spread":0.294811715805946,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321226584","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99565345,0.00013740217,0.00025990233,0.0006833929,0.00045488734,0.0009831288,0.00010048368,0.0001664015,0.0015609378],"genre_scores_gemma":[0.9984933,0.0000039922365,0.0000105681565,0.00009687266,0.0000843914,0.00009883128,0.00034830748,0.00003222685,0.0008314844],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99785787,0.00011002354,0.0006269668,0.0005790143,0.00040526252,0.00042085547],"domain_scores_gemma":[0.9990246,0.00023096947,0.00013461344,0.00029151826,0.000051183088,0.00026706504],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005347556,0.00021409635,0.00027905242,0.00035596677,0.000111096444,0.00015778441,0.00012082977,0.000069918395,0.000102995145],"category_scores_gemma":[0.00019688146,0.00018487297,0.000033283464,0.0003032987,0.00013747791,0.0007208054,0.0001374388,0.00021004851,0.00007608392],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001854784,0.0009996278,0.69797784,0.00010185859,0.000027177106,0.00018043419,0.0012719445,0.0000038127553,0.000023423516,0.000060969025,0.00006954461,0.2990979],"study_design_scores_gemma":[0.004076076,0.0021536264,0.98908573,0.0008573566,0.00002558699,0.000016886212,0.0023999095,0.00083186326,0.000012699577,0.00031054244,0.000059513175,0.00017018893],"about_ca_topic_score_codex":0.00006958883,"about_ca_topic_score_gemma":0.00012409738,"teacher_disagreement_score":0.29892772,"about_ca_system_score_codex":0.00005911921,"about_ca_system_score_gemma":0.000014893249,"threshold_uncertainty_score":0.7538901},"labels":[],"label_agreement":null},{"id":"W4321498667","doi":"10.1038/s41746-023-00769-z","title":"Author Correction: Prostate cancer therapy personalization via multi-modal deep learning on randomized phase III clinical trials","year":2023,"lang":"en","type":"erratum","venue":"npj Digital Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre; Nova Scotia Cancer Centre; Centre Hospitalier de l’Université de Montréal; Horizon Health Network; Occupational Cancer Research Centre; Saint John Regional Hospital","funders":"","keywords":"Personalization; Prostate cancer; Randomized controlled trial; Modal; Phase (matter); Medicine; Medical physics; Cancer; Computer science; Internal medicine; World Wide Web; Physics; Materials science","score_opus":0.08889351755534235,"score_gpt":0.4632223718861051,"score_spread":0.37432885433076274,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321498667","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010089265,0.043982107,0.12719311,0.115760244,0.5994443,0.024862764,0.0002514868,0.005067731,0.07334895],"genre_scores_gemma":[0.03456843,0.022617644,0.00014650702,0.0042906106,0.03089746,0.0007484232,0.0075560617,0.0005394789,0.8986354],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99157506,0.0016199299,0.0031438977,0.0012505014,0.0016741878,0.0007364012],"domain_scores_gemma":[0.9915565,0.0047232816,0.0019057436,0.00050102227,0.0005004427,0.0008130041],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.010798087,0.000906355,0.0053902906,0.00066467206,0.00030678554,0.0001546057,0.00027284437,0.00093756476,0.0009078507],"category_scores_gemma":[0.049853683,0.0005963828,0.0011047777,0.0007040446,0.0010084745,0.00018110318,0.00007292652,0.0051973187,0.00012138686],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.05247386,0.00051324535,0.00022619106,0.00021537665,0.001097744,0.00023232866,0.0012270412,0.00006889094,0.000037235368,0.000013251289,0.48428127,0.45961356],"study_design_scores_gemma":[0.31803933,0.0022183731,0.00017358808,0.0041035954,0.00095693854,0.00008023717,0.00033379567,0.22397217,0.0000039882966,0.000053457326,0.44956118,0.00050331897],"about_ca_topic_score_codex":0.00025753985,"about_ca_topic_score_gemma":0.000009572211,"teacher_disagreement_score":0.82528645,"about_ca_system_score_codex":0.0002731861,"about_ca_system_score_gemma":0.00056887383,"threshold_uncertainty_score":0.99964875},"labels":[],"label_agreement":null},{"id":"W4322719140","doi":"10.1038/s41746-023-00780-4","title":"Health data justice: building new norms for health data governance","year":2023,"lang":"en","type":"review","venue":"npj Digital Medicine","topic":"Ethics in Clinical Research","field":"Medicine","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Canadian Institutes of Health Research; Government of Canada","keywords":"Economic Justice; Corporate governance; Public health; Government (linguistics); Public relations; Context (archaeology); Perspective (graphical); Data governance; Health care; Health equity; Political science; Sociology; Public administration; Business; Medicine; Data quality; Nursing; Computer science; Law; Geography","score_opus":0.9200269161078761,"score_gpt":0.7469333018938071,"score_spread":0.173093614214069,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4322719140","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[8.658829e-8,0.88955003,0.0030358147,0.08952254,0.0019003971,0.003925464,0.010188212,0.00025633594,0.0016211201],"genre_scores_gemma":[0.000002048378,0.9349659,0.0032695867,0.004227752,0.008307131,0.00006119737,0.029343883,0.00032683215,0.01949569],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9883056,0.00014169041,0.0036644232,0.0028532366,0.0033921343,0.0016429124],"domain_scores_gemma":[0.94537854,0.036614683,0.0024731604,0.0120563,0.00046545712,0.0030118297],"candidate_categories":["metaresearch","metaepi_narrow","open_science","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.013339689,0.00082116865,0.006042429,0.0002761097,0.000269412,0.00013773124,0.0055083116,0.00083251984,0.00007865075],"category_scores_gemma":[0.1649821,0.0005623974,0.0002793172,0.0013973388,0.0006007884,0.0006096528,0.004830164,0.004859486,0.00033855287],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003448603,0.000065014254,0.0000014931755,0.12200538,0.0001898759,0.0000343042,0.000027089936,4.4998966e-8,1.2378892e-8,0.0027655428,0.31414855,0.5607282],"study_design_scores_gemma":[0.0014010165,0.0014257287,0.0000083657915,0.16888365,0.0007077351,0.000105040475,0.00005177404,0.00008706337,1.07856195e-8,0.002267192,0.8247506,0.0003118165],"about_ca_topic_score_codex":0.00066097727,"about_ca_topic_score_gemma":0.00050118024,"teacher_disagreement_score":0.5604164,"about_ca_system_score_codex":0.0009222927,"about_ca_system_score_gemma":0.02011748,"threshold_uncertainty_score":0.9998724},"labels":[],"label_agreement":null},{"id":"W4323316076","doi":"10.1038/s41746-023-00784-0","title":"U-Sleep’s resilience to AASM guidelines","year":2023,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Obstructive Sleep Apnea Research","field":"Medicine","cited_by":46,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Eurostars; National Center for Advancing Translational Sciences; National Center for Research Resources; National Institute of Nursing Research; National Heart, Lung, and Blood Institute; University of California, Davis; York University; American Sleep Medicine Foundation; University of Bern; European Commission; Johns Hopkins University; National Institutes of Health; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; University of Minnesota; National Science Foundation; University of Washington; Case Western Reserve University","keywords":"Computer science; Polysomnography; Sleep medicine; Context (archaeology); Exploit; Task (project management); Artificial intelligence; Sleep (system call); Machine learning; Data science; Medicine; Electroencephalography; Sleep disorder; Computer security; Insomnia","score_opus":0.07251396297277891,"score_gpt":0.3978284764700227,"score_spread":0.3253145134972438,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4323316076","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8127927,0.00020957268,0.0009590971,0.07058701,0.0008187756,0.0010360364,0.000036039357,0.00069957593,0.1128612],"genre_scores_gemma":[0.98654,0.00001793256,0.0004546378,0.0020190855,0.0010983859,0.00004830457,0.000070333066,0.000051270352,0.009700033],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99703336,0.000018386783,0.0005003202,0.0005304599,0.0012758073,0.0006416881],"domain_scores_gemma":[0.9977885,0.00022479784,0.00004882504,0.00062596786,0.0006268008,0.0006851314],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004398046,0.00022467619,0.00043392016,0.0005789602,0.00007848724,0.00003585377,0.00027855512,0.000082758095,0.00041673862],"category_scores_gemma":[0.007902393,0.00016406969,0.00007343514,0.0019843136,0.000304807,0.00021934863,0.00024153212,0.00024869,0.0038157234],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00056926627,0.00014176367,0.05446607,0.0002130376,0.00013793445,0.0013313787,0.0008652682,0.000057286707,0.048000395,0.0019767594,0.18718289,0.705058],"study_design_scores_gemma":[0.0087091895,0.005705952,0.4575825,0.001246687,0.00016514598,0.00064269576,0.0047527184,0.005940035,0.009733118,0.0031220096,0.5013741,0.0010258206],"about_ca_topic_score_codex":0.00003315775,"about_ca_topic_score_gemma":0.000005207738,"teacher_disagreement_score":0.7040321,"about_ca_system_score_codex":0.000113510236,"about_ca_system_score_gemma":0.000042492524,"threshold_uncertainty_score":0.9969599},"labels":[],"label_agreement":null},{"id":"W4323807075","doi":"10.1038/s41746-023-00774-2","title":"Machine learning for accurate estimation of fetal gestational age based on ultrasound images","year":2023,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Pregnancy and preeclampsia studies","field":"Medicine","cited_by":55,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hospital for Sick Children","funders":"Engineering and Physical Sciences Research Council; University of Oxford; National Institute for Health and Care Research; Bill and Melinda Gates Foundation","keywords":"Gestational age; Crown-rump length; Ultrasound; Medicine; Obstetrics; Pregnancy; Gestation; 3D ultrasound; Fetus; First trimester; Radiology; Biology","score_opus":0.03478213172163702,"score_gpt":0.3143024793343034,"score_spread":0.27952034761266636,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4323807075","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5992734,0.0032042668,0.0993559,0.032521352,0.0017439508,0.0054658637,0.0015852983,0.0019647651,0.25488526],"genre_scores_gemma":[0.9954669,0.00005751841,0.0005845192,0.00021406417,0.00012652896,0.000051480187,0.0017820344,0.000022168235,0.0016947706],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.998934,0.00001806434,0.00029411184,0.00020140572,0.00035731005,0.00019512486],"domain_scores_gemma":[0.9980759,0.0015050427,0.00011714302,0.00013746995,0.00009263838,0.00007179666],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022429982,0.0001527316,0.00033388834,0.00018287552,0.00008801929,0.000012384308,0.000057242247,0.000048240527,0.00005026084],"category_scores_gemma":[0.0031274457,0.00011341517,0.00007549275,0.0002817424,0.00018187195,0.00013873732,0.000016154741,0.00014232176,0.000024713487],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.010918476,0.001372947,0.18125665,0.009450643,0.0016616969,0.0009339494,0.008232138,0.07652487,0.052422803,0.01037168,0.056405894,0.59044826],"study_design_scores_gemma":[0.02751336,0.012144104,0.6168414,0.008208087,0.0007576099,0.00013101405,0.0013378067,0.293941,0.011161628,0.013438742,0.01353803,0.0009872514],"about_ca_topic_score_codex":0.0000069576186,"about_ca_topic_score_gemma":0.00000131978,"teacher_disagreement_score":0.58946097,"about_ca_system_score_codex":0.000023927405,"about_ca_system_score_gemma":0.00004088919,"threshold_uncertainty_score":0.46249363},"labels":[],"label_agreement":null},{"id":"W4360613735","doi":"10.1038/s41746-023-00772-4","title":"Complex modeling with detailed temporal predictors does not improve health records-based suicide risk prediction","year":2023,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Suicide and Self-Harm Studies","field":"Psychology","cited_by":46,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"U.S. Food and Drug Administration; Hamilton Health Sciences Foundation; National Institute of Mental Health; U.S. Department of Health and Human Services","keywords":"Random forest; Logistic regression; Predictive modelling; Machine learning; Ensemble learning; Computer science; Artificial intelligence; Receiver operating characteristic; Artificial neural network; Ensemble forecasting; Regression; Mental health; Statistics; Psychology; Mathematics; Psychiatry","score_opus":0.05809156678828752,"score_gpt":0.325537554484045,"score_spread":0.26744598769575745,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4360613735","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9767204,0.00022193724,0.006419543,0.004870865,0.0018510519,0.0009233521,0.0008542692,0.0011798731,0.0069587333],"genre_scores_gemma":[0.9957044,0.0000612701,0.00012434724,0.0010402284,0.0008237592,0.00014802479,0.00066942605,0.00007465674,0.0013538537],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9970415,0.000110454865,0.0007935129,0.0006990283,0.00060771406,0.00074776803],"domain_scores_gemma":[0.9983,0.00038968003,0.00032891374,0.000513659,0.00016663672,0.0003010969],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000616465,0.00038793014,0.0006933119,0.00035153108,0.0002996986,0.000042953212,0.00021896802,0.00011910596,0.000260865],"category_scores_gemma":[0.00028230099,0.000237818,0.00009633036,0.0006047403,0.00025563326,0.0002335122,0.00005818175,0.000384531,0.00015884156],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019826477,0.00023467156,0.95544887,0.0001395944,0.00065504765,0.00011063215,0.00457025,0.0008708829,0.00023564936,0.000162101,0.014618639,0.020971034],"study_design_scores_gemma":[0.026384465,0.017325524,0.72951907,0.0005979855,0.0006524327,0.000056582765,0.034622468,0.17971161,0.00021747343,0.0020961533,0.0070188157,0.0017974467],"about_ca_topic_score_codex":0.0019180812,"about_ca_topic_score_gemma":0.00075319107,"teacher_disagreement_score":0.22592981,"about_ca_system_score_codex":0.00011787091,"about_ca_system_score_gemma":0.00011055205,"threshold_uncertainty_score":0.9697937},"labels":[],"label_agreement":null},{"id":"W4362597259","doi":"10.1038/s41746-023-00803-0","title":"Predicting patient decompensation from continuous physiologic monitoring in the emergency department","year":2023,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Emergency and Acute Care Studies","field":"Medicine","cited_by":52,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario; University of Toronto","funders":"","keywords":"Vital signs; Medicine; Triage; Decompensation; Emergency department; Ventricular tachycardia; Tachycardia; Emergency medicine; Cardiology; Anesthesia","score_opus":0.031461340634896175,"score_gpt":0.3027716967926121,"score_spread":0.2713103561577159,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362597259","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9853008,0.0017872836,0.0000065023455,0.0019211974,0.0012646584,0.00043158678,0.000027235214,0.00013048961,0.009130279],"genre_scores_gemma":[0.997088,0.0014251851,0.000012910114,0.0001601231,0.00088230683,0.000084231986,0.00025445985,0.000012949826,0.000079830774],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9986215,0.000032434305,0.00042417433,0.00025585663,0.00039333772,0.00027266776],"domain_scores_gemma":[0.9993739,0.0001840839,0.000091652895,0.00021407711,0.000079474245,0.000056776385],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014980593,0.00016301358,0.0002969651,0.000087970955,0.00009359671,0.0000074233176,0.00009626304,0.00004568335,0.00006690598],"category_scores_gemma":[0.00063986145,0.00009464291,0.00006331658,0.00046789128,0.00005870845,0.00010770602,0.000060004433,0.00016527242,0.000055800145],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010074078,0.00015934998,0.9075201,0.000050122177,0.00015339915,0.00021030408,0.008648752,0.000018137547,0.0036290784,0.00006096219,0.01852722,0.060921837],"study_design_scores_gemma":[0.0011017014,0.0010419165,0.96922964,0.00054075976,0.000099334364,0.000008747009,0.02069515,0.0001390804,0.00041637404,0.0012518713,0.0053156726,0.000159769],"about_ca_topic_score_codex":0.00008045691,"about_ca_topic_score_gemma":0.000011854263,"teacher_disagreement_score":0.061709527,"about_ca_system_score_codex":0.00004139682,"about_ca_system_score_gemma":0.000011943298,"threshold_uncertainty_score":0.38594258},"labels":[],"label_agreement":null},{"id":"W4367055910","doi":"10.1038/s41746-023-00811-0","title":"Self-supervised learning for medical image classification: a systematic review and implementation guidelines","year":2023,"lang":"en","type":"review","venue":"npj Digital Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":412,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"U.S. National Library of Medicine; National Institute of Biomedical Imaging and Bioengineering; National Institute of Arthritis and Musculoskeletal and Skin Diseases; National Heart, Lung, and Blood Institute; National Institutes of Health","keywords":"Artificial intelligence; Computer science; Machine learning; Deep learning; Supervised learning; Medical imaging; Scopus; Data science; MEDLINE; Artificial neural network","score_opus":0.12664126699211417,"score_gpt":0.44221957864895156,"score_spread":0.31557831165683736,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367055910","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.6191307e-8,0.918204,0.07353895,0.00316268,0.00039112646,0.00391464,0.000011927407,0.00051324035,0.00026341612],"genre_scores_gemma":[8.849288e-7,0.9934216,0.003183914,0.00043551007,0.0004890722,0.0019504037,0.0001921918,0.000056282704,0.00027010273],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9961307,0.00015969883,0.0018879038,0.0006917369,0.00084136426,0.00028856867],"domain_scores_gemma":[0.9970051,0.00097008934,0.00082433695,0.00058284245,0.0004106158,0.00020703672],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0018140431,0.00039645657,0.0021884097,0.0002300912,0.00012641645,0.0001829233,0.000794368,0.00018164788,0.000023963556],"category_scores_gemma":[0.0036384726,0.00027397546,0.00020126632,0.0008512147,0.0000720553,0.00057203206,0.00023059893,0.00029425474,0.00007156216],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[2.2567201e-7,0.00000390721,1.11659126e-7,0.58902353,0.000083551415,0.0000034584293,0.000040834107,7.696121e-9,3.3796667e-8,0.00035063727,0.0033882835,0.40710542],"study_design_scores_gemma":[0.00035328322,0.00022438649,3.1838036e-7,0.50075465,0.0017769297,0.00020164147,0.000082950566,0.0036493014,6.752172e-8,0.00017943291,0.4924712,0.00030586694],"about_ca_topic_score_codex":0.000004127589,"about_ca_topic_score_gemma":0.0000028330692,"teacher_disagreement_score":0.4890829,"about_ca_system_score_codex":0.00019722295,"about_ca_system_score_gemma":0.00035865942,"threshold_uncertainty_score":0.9999713},"labels":[],"label_agreement":null},{"id":"W4367598055","doi":"10.1038/s41746-023-00806-x","title":"Time and event-specific deep learning for personalized risk assessment after cardiac perfusion imaging","year":2023,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Cardiac Imaging and Diagnostics","field":"Medicine","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Libin Cardiovascular Institute of Alberta; University of Calgary","funders":"National Heart, Lung, and Blood Institute; National Institutes of Health; National Center for Advancing Translational Sciences; U.S. Department of Health and Human Services","keywords":"Mace; Interquartile range; Medicine; Myocardial perfusion imaging; Internal medicine; Acute coronary syndrome; Cardiology; Receiver operating characteristic; Confidence interval; Risk assessment; Cardiovascular event; Revascularization; Artificial intelligence; Perfusion; Computer science; Percutaneous coronary intervention; Myocardial infarction","score_opus":0.008766639381066511,"score_gpt":0.28256599079930644,"score_spread":0.2737993514182399,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367598055","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95926416,0.015354343,0.0029698026,0.0061566653,0.001031713,0.0011863335,0.00016287078,0.00057597854,0.013298136],"genre_scores_gemma":[0.99291915,0.0011181284,0.00020265869,0.00024476668,0.0009983615,0.00009075487,0.0005343078,0.00006024016,0.0038316543],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9984088,0.000042077038,0.00028914877,0.0004047851,0.00046915747,0.00038604916],"domain_scores_gemma":[0.99848396,0.00077737926,0.00008430362,0.00021224836,0.00018325742,0.00025884825],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005259046,0.00022705227,0.00052784546,0.00022028277,0.00014761576,0.000078773075,0.000042258474,0.000054889486,0.0001377394],"category_scores_gemma":[0.0011508602,0.0001824478,0.00018149572,0.0002743611,0.0002627629,0.00016837327,0.00007872863,0.00028422623,0.00011669336],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004897343,0.000086644075,0.5515761,0.00018171068,0.00015238863,0.00023964583,0.0020681205,0.00003506146,0.0029164099,0.000066905086,0.031046437,0.41114086],"study_design_scores_gemma":[0.00691427,0.00064876064,0.67997736,0.0010244029,0.00060553756,0.00010267973,0.003039546,0.015614744,0.000054837015,0.0002563935,0.2913118,0.00044970997],"about_ca_topic_score_codex":0.000008590352,"about_ca_topic_score_gemma":1.8180602e-7,"teacher_disagreement_score":0.41069114,"about_ca_system_score_codex":0.00008390266,"about_ca_system_score_gemma":0.000040314055,"threshold_uncertainty_score":0.7440005},"labels":[],"label_agreement":null},{"id":"W4377289092","doi":"10.1038/s41746-023-00816-9","title":"Theory and rationale of interpretable all-in-one pattern discovery and disentanglement system","year":2023,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Interpretability; Computer science; Artificial intelligence; Inference; Masking (illustration); Machine learning; Cluster analysis; Association (psychology); Closing (real estate); Knowledge extraction; Class (philosophy); Data mining; Data science; Psychology","score_opus":0.03190714840485959,"score_gpt":0.2765683581320183,"score_spread":0.2446612097271587,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4377289092","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2434953,0.00035097904,0.7468653,0.0033899809,0.00018394578,0.0005570875,0.00011308724,0.000338559,0.004705773],"genre_scores_gemma":[0.9992707,0.000052421838,0.000257523,0.000115774936,0.00002165827,0.000027741416,0.000056623834,0.000004856653,0.00019269428],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9992027,0.000029643315,0.00023907278,0.00021521673,0.00020156708,0.000111756206],"domain_scores_gemma":[0.9993875,0.00021463745,0.00007443575,0.0002599549,0.000023383982,0.000040111754],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003523298,0.00007342065,0.00015510716,0.0001281717,0.000015594593,0.000060286635,0.00019272428,0.000019296782,0.0000024324327],"category_scores_gemma":[0.00009413492,0.000058292662,0.000008832162,0.00020077937,0.00010118719,0.00080315344,0.00022000924,0.00004169223,0.000003526638],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000046359426,0.00014496614,0.043966956,0.00075022987,0.00007269905,0.000041812964,0.003829717,0.0000031056695,0.01591366,0.6387327,0.003786905,0.29271093],"study_design_scores_gemma":[0.0073928125,0.00216328,0.6842173,0.008713538,0.00010082416,0.00017903473,0.011771989,0.068777606,0.030462634,0.1756845,0.008929668,0.0016068174],"about_ca_topic_score_codex":0.000008044671,"about_ca_topic_score_gemma":0.000002471014,"teacher_disagreement_score":0.7557754,"about_ca_system_score_codex":0.000029135146,"about_ca_system_score_gemma":0.0000114850955,"threshold_uncertainty_score":0.23771058},"labels":[],"label_agreement":null},{"id":"W4385257059","doi":"10.1038/s41746-023-00877-w","title":"The impact of transition to a digital hospital on medication errors (TIME study)","year":2023,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Electronic Health Records Systems","field":"Health Professions","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario; University of Toronto","funders":"","keywords":"Audit; Medicine; Chart; Dosing; Clinical audit; Emergency medicine; Medical emergency; Patient safety; Health care; Statistics; Internal medicine; Business","score_opus":0.03949860149094188,"score_gpt":0.45252819074744344,"score_spread":0.4130295892565016,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385257059","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9599214,0.000038817627,0.000085526655,0.015058323,0.00079913443,0.0031802156,0.000095958676,0.00026001225,0.020560607],"genre_scores_gemma":[0.9962717,0.000014563803,0.0000011975743,0.00019359916,0.00066358916,0.00031697066,0.00011956919,0.000047255042,0.0023715408],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.99666685,0.0002192176,0.0010708122,0.00035430808,0.0008593445,0.00082944427],"domain_scores_gemma":[0.9966544,0.0018388475,0.00032575984,0.00053928274,0.0002311811,0.00041055278],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0014210421,0.00023846759,0.0004938465,0.00028515654,0.00041461582,0.000018199307,0.0003241524,0.00013381988,0.00010465481],"category_scores_gemma":[0.002311843,0.00013529563,0.0001043999,0.0010721664,0.00012582708,0.00026588293,0.00005441153,0.00051350973,0.0021398333],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002076689,0.002207869,0.06300463,0.00069999235,0.0007977734,0.00008304062,0.13019286,0.00019342118,0.0007688776,0.0015104361,0.5367409,0.26172355],"study_design_scores_gemma":[0.015357154,0.0937397,0.7066129,0.0064903665,0.00014917215,0.00002122559,0.11640352,0.003612403,0.000035649773,0.0050706207,0.051088363,0.0014189396],"about_ca_topic_score_codex":0.00035144048,"about_ca_topic_score_gemma":0.00003690823,"teacher_disagreement_score":0.6436083,"about_ca_system_score_codex":0.0005287757,"about_ca_system_score_gemma":0.00054957176,"threshold_uncertainty_score":0.99863714},"labels":[],"label_agreement":null},{"id":"W4385754310","doi":"10.1038/s41746-023-00880-1","title":"CathAI: fully automated coronary angiography interpretation and stenosis estimation","year":2023,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Coronary Interventions and Diagnostics","field":"Medicine","cited_by":56,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université de Montréal; University of Ottawa; Montreal Heart Institute","funders":"National Institute of Biomedical Imaging and Bioengineering; Directorate for Computer and Information Science and Engineering; Ant Group; U.S. Department of Health and Human Services; National Institutes of Health; VMware; National Science Foundation; Amazon Web Services; Heart and Stroke Foundation of Canada; National Heart, Lung, and Blood Institute; Futurewei Technologies; Nvidia","keywords":"Medicine; Coronary artery disease; Stenosis; Coronary angiography; Angiography; Cardiology; Internal medicine; CAD; Gold standard (test); Radiology; Artificial intelligence; Computer science; Myocardial infarction","score_opus":0.015718293309684557,"score_gpt":0.29580300045551056,"score_spread":0.280084707145826,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385754310","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9872655,0.00062429154,0.0011159346,0.003555317,0.0003028302,0.0003894014,0.000051948882,0.0010291185,0.005665602],"genre_scores_gemma":[0.99787784,0.0000950705,0.00019170783,0.00028799943,0.00007886125,0.000031787575,0.00085492857,0.0000217959,0.0005600242],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9990022,0.000012676014,0.00031811206,0.0002255281,0.00025585058,0.00018559996],"domain_scores_gemma":[0.99924105,0.0002287144,0.00007115577,0.00018122687,0.00011521595,0.00016261372],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010535286,0.00014648392,0.00024421696,0.00043179956,0.000058525096,0.000031505977,0.00004728748,0.00006451232,0.00010428317],"category_scores_gemma":[0.00049992197,0.00011896609,0.00010852392,0.00064863334,0.00015718736,0.00024444572,0.000047559435,0.00008777121,0.00010883498],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00055165455,0.0004506228,0.2581916,0.00056677597,0.00043614628,0.0006258938,0.0020816657,0.00012931571,0.0007212287,0.0008608461,0.06408257,0.6713017],"study_design_scores_gemma":[0.0017883937,0.0020363727,0.9212783,0.0010362368,0.00024526802,0.00021563761,0.00081640563,0.07043637,0.000021460924,0.00065932644,0.0013166984,0.00014951901],"about_ca_topic_score_codex":0.00002323156,"about_ca_topic_score_gemma":0.0000032888383,"teacher_disagreement_score":0.6711522,"about_ca_system_score_codex":0.00003167127,"about_ca_system_score_gemma":0.00002334301,"threshold_uncertainty_score":0.48512965},"labels":[],"label_agreement":null},{"id":"W4385762225","doi":"10.1038/s41746-023-00884-x","title":"Blood glucose variance measured by continuous glucose monitors across the menstrual cycle","year":2023,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Regulation of Appetite and Obesity","field":"Neuroscience","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Canada","keywords":"Menstrual cycle; Luteal phase; Follicular phase; Medicine; Endocrinology; Internal medicine; Physiology; Menstruation; Estrogen; Hormone","score_opus":0.019206871181208222,"score_gpt":0.27059184429686606,"score_spread":0.25138497311565783,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385762225","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9872805,0.00020477519,0.00004939429,0.0038302662,0.00073142716,0.0003067681,0.00011527053,0.0003440424,0.007137574],"genre_scores_gemma":[0.995514,0.00013136036,0.0000057433163,0.00068566087,0.0004272636,0.000018663455,0.000026052265,0.000029655348,0.0031616369],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9977028,0.000069115034,0.00035653295,0.0004847101,0.0008551507,0.000531687],"domain_scores_gemma":[0.9986287,0.00047862218,0.00014323939,0.00048783785,0.00007290122,0.00018871287],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038440045,0.00022934643,0.00030182008,0.000048582522,0.0003886394,0.00016223839,0.0005003478,0.00008797511,0.000049302813],"category_scores_gemma":[0.0015176493,0.00014995266,0.00007124624,0.0008040891,0.0005963608,0.00041616522,0.00014382202,0.00021303385,0.00040929907],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015284556,0.00036099798,0.0046312353,0.00003993607,0.00004734812,0.000253125,0.0026819434,0.000069297275,0.9060661,0.0015589525,0.024887953,0.05925027],"study_design_scores_gemma":[0.0034603747,0.0006080827,0.02666838,0.00015657522,0.0000477828,0.00011340172,0.001209348,0.0006184995,0.8576508,0.0028270478,0.10616472,0.0004749541],"about_ca_topic_score_codex":0.000030366617,"about_ca_topic_score_gemma":0.000004428992,"teacher_disagreement_score":0.081276774,"about_ca_system_score_codex":0.0000234115,"about_ca_system_score_gemma":0.000028049997,"threshold_uncertainty_score":0.6114892},"labels":[],"label_agreement":null},{"id":"W4385981617","doi":"10.1038/s41746-023-00876-x","title":"Cost effectiveness review of text messaging, smartphone application, and website interventions targeting T2DM or hypertension","year":2023,"lang":"en","type":"review","venue":"npj Digital Medicine","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Medical Research Council; Horizon 2020 Framework Programme; National Health and Medical Research Council; European Commission; NYU Grossman School of Medicine; York University","keywords":"Psychological intervention; CINAHL; Medicine; Health economics; Cost effectiveness; MEDLINE; PsycINFO; Family medicine; Public health; Nursing; Political science; Risk analysis (engineering)","score_opus":0.6289997682366935,"score_gpt":0.5293901350280686,"score_spread":0.09960963320862481,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385981617","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00001707294,0.989084,0.0020173998,0.0024201882,0.0004570922,0.0031937417,0.0006630125,0.000086772896,0.002060716],"genre_scores_gemma":[0.00014957898,0.99544865,0.00010619986,0.0010373138,0.00033329087,0.0007747024,0.0010357264,0.00010091704,0.0010136223],"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","domain_scores_codex":[0.9912659,0.0004090405,0.006961124,0.0008486661,0.00016466815,0.00035058224],"domain_scores_gemma":[0.98993206,0.0040989732,0.0048920554,0.00066641223,0.0001826666,0.00022784458],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0149824405,0.00044518188,0.0053330353,0.0005811065,0.00012259076,0.000044596545,0.00034022404,0.00022896852,0.0002665608],"category_scores_gemma":[0.01595608,0.000387558,0.00042208796,0.00078098336,0.000213907,0.00036666027,0.00017404718,0.00031377558,0.0012820709],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000071597005,0.00010137431,0.0002661063,0.7695383,0.0003431177,0.000004823751,0.000093589464,5.081115e-7,9.284813e-8,0.003765935,0.04377984,0.18209916],"study_design_scores_gemma":[0.00037939253,0.00008767333,0.00022715081,0.2728497,0.00016219338,0.000029181509,0.000072457886,0.00002693718,3.902154e-8,0.00047838478,0.72541845,0.0002684199],"about_ca_topic_score_codex":0.000135534,"about_ca_topic_score_gemma":0.000013892822,"teacher_disagreement_score":0.6816386,"about_ca_system_score_codex":0.0003515224,"about_ca_system_score_gemma":0.00017941615,"threshold_uncertainty_score":0.9998576},"labels":[],"label_agreement":null},{"id":"W4386162831","doi":"10.1038/s41746-023-00906-8","title":"How AI can learn from the law: putting humans in the loop only on appeal","year":2023,"lang":"en","type":"review","venue":"npj Digital Medicine","topic":"Ethics and Social Impacts of AI","field":"Social Sciences","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Institutes of Health; University of Toronto; European Commission; Novo Nordisk Fonden; Connaught Fund; Pennsylvania State University; Novo Nordisk; National Institute of Biomedical Imaging and Bioengineering; University of Pennsylvania","keywords":"Appeal; Analogy; Process (computing); Computer science; Human intelligence; Artificial intelligence; Psychology; Law; Epistemology; Political science","score_opus":0.1940363635505531,"score_gpt":0.4431613134559878,"score_spread":0.2491249499054347,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386162831","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000084548425,0.5632845,0.0000013668098,0.23310214,0.0009324939,0.0010799284,0.00015038552,0.00011345539,0.20125116],"genre_scores_gemma":[0.010381174,0.96860605,0.000001359436,0.008132008,0.0054348023,0.000031963264,0.00020116614,0.00006387168,0.0071475706],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9966775,0.0005859943,0.0004347774,0.00038559828,0.0013430299,0.000573068],"domain_scores_gemma":[0.9945231,0.0045158654,0.00028884312,0.00040979558,0.00011257986,0.00014982773],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0025735488,0.00033405633,0.00097083155,0.00007609469,0.00087281957,0.0010639075,0.0012584924,0.00043786937,0.000021042604],"category_scores_gemma":[0.0051352703,0.00016448057,0.0002507557,0.0006844441,0.0012851484,0.00026472862,0.000099805504,0.0019084933,0.00007241662],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001633787,0.00003678055,0.000022807188,0.000344346,0.00007517005,0.00006367574,0.038892444,1.13541184e-7,1.7085908e-8,0.14391914,0.011462703,0.80518115],"study_design_scores_gemma":[0.000118260075,0.00010128365,0.000025837768,0.0076867803,0.00010075857,7.7129033e-7,0.020226123,1.8958994e-7,5.762862e-9,0.019347563,0.9522326,0.00015981008],"about_ca_topic_score_codex":0.024114877,"about_ca_topic_score_gemma":0.047074076,"teacher_disagreement_score":0.9407699,"about_ca_system_score_codex":0.00019005538,"about_ca_system_score_gemma":0.00080750673,"threshold_uncertainty_score":0.99997306},"labels":[],"label_agreement":null},{"id":"W4387330128","doi":"10.1038/s41746-023-00931-7","title":"Autonomous artificial intelligence increases real-world specialist clinic productivity in a cluster-randomized trial","year":2023,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":73,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"School of Medicine, New York University; York University; U.S. Department of Labor","keywords":"Randomized controlled trial; Productivity; Cluster (spacecraft); Cluster randomised controlled trial; Artificial intelligence; Computer science; Physical therapy; Psychology; Medicine; Economics; Internal medicine; Economic growth","score_opus":0.06661200835823462,"score_gpt":0.37132904477211537,"score_spread":0.30471703641388076,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387330128","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8349741,0.00014094297,0.02496048,0.06311417,0.007924453,0.0063994536,0.000028895218,0.002417438,0.06004007],"genre_scores_gemma":[0.99441856,0.000036270827,0.00057206786,0.0002976323,0.0025393243,0.0001713337,0.000048311107,0.00002702847,0.0018894426],"study_design_codex":"design_other","study_design_gemma":"randomized_trial","domain_scores_codex":[0.99569833,0.0006631599,0.0013748304,0.00093101757,0.00072581065,0.0006068438],"domain_scores_gemma":[0.9944468,0.0038989382,0.000367611,0.00091936294,0.000121105586,0.00024619617],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0040435367,0.0003047925,0.0010500567,0.0007898014,0.00012080781,0.00019457996,0.0009458699,0.000098267745,0.000098039774],"category_scores_gemma":[0.013738367,0.0002459878,0.00014261442,0.0026338408,0.00046077144,0.0006509526,0.0004654304,0.00059083157,0.00039119317],"study_design_candidate":"randomized_trial","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.21503796,0.0008953375,0.0048306603,0.00028712905,0.00006696355,0.00061477534,0.003718001,0.00051035604,0.000014967562,0.09415932,0.0048419037,0.6750226],"study_design_scores_gemma":[0.4868754,0.0038954313,0.016964866,0.0014461975,0.000077029275,0.000085442196,0.00058472255,0.19651507,0.000112453425,0.28008306,0.011450608,0.0019096872],"about_ca_topic_score_codex":0.0034093203,"about_ca_topic_score_gemma":0.0017163053,"teacher_disagreement_score":0.6731129,"about_ca_system_score_codex":0.00018039717,"about_ca_system_score_gemma":0.00031571073,"threshold_uncertainty_score":0.9999992},"labels":[],"label_agreement":null},{"id":"W4388001764","doi":"10.1038/s41746-023-00945-1","title":"Diagnostic accuracy of point-of-care ultrasound with artificial intelligence-assisted assessment of left ventricular ejection fraction","year":2023,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Ultrasound in Clinical Applications","field":"Medicine","cited_by":35,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"National Center for Advancing Translational Sciences; National Institute of Arthritis and Musculoskeletal and Skin Diseases","keywords":"Ejection fraction; Medicine; Intraclass correlation; Internal medicine; Cardiology; Predictive value; Predictive value of tests; Ultrasound; Nuclear medicine; Radiology; Heart failure","score_opus":0.04687346736303867,"score_gpt":0.376293923046781,"score_spread":0.32942045568374234,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388001764","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97653395,0.00010421,0.01646093,0.0008554033,0.00021019732,0.0008913562,0.00007322191,0.000093385774,0.004777321],"genre_scores_gemma":[0.9982582,0.00014418502,0.000700529,0.000035594367,0.00018806732,0.000036387977,0.0005691511,0.000024796263,0.000043135533],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9977789,0.000029930103,0.000994796,0.00029490958,0.00071078667,0.00019068841],"domain_scores_gemma":[0.99195737,0.006319817,0.0005699592,0.00042662653,0.00059973315,0.00012646982],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00026104783,0.00017010821,0.00060042716,0.00026698684,0.000041122174,0.000008944888,0.00011899897,0.00011600559,0.00023044793],"category_scores_gemma":[0.008483683,0.00012360698,0.00011768345,0.0010841273,0.0004291338,0.00018883181,0.000026991082,0.00025001945,0.000019670064],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007447598,0.0025778052,0.82908994,0.0020184696,0.00066158455,0.00006827605,0.00097113935,0.0003111102,0.054465763,0.0051091537,0.00088187895,0.10310012],"study_design_scores_gemma":[0.0011338282,0.00597951,0.9510968,0.0022392767,0.00071897113,0.00015056596,0.009402617,0.00025185014,0.023360228,0.0043724584,0.0010515699,0.00024233907],"about_ca_topic_score_codex":0.00004226716,"about_ca_topic_score_gemma":0.000007655722,"teacher_disagreement_score":0.12200685,"about_ca_system_score_codex":0.00009819708,"about_ca_system_score_gemma":0.00014787925,"threshold_uncertainty_score":0.9998683},"labels":[],"label_agreement":null},{"id":"W4388018182","doi":"10.1038/s41746-023-00950-4","title":"A randomized, clinical trial investigating the use of a digital intervention to reduce delirium-associated agitation","year":2023,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Intensive Care Unit Cognitive Disorders","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre for Advancing Health Outcomes; Fraser Health; Simon Fraser University; Royal Columbian Hospital","funders":"Mitacs","keywords":"Delirium; Intervention (counseling); Medicine; Randomized controlled trial; Protocol (science); Clinical trial; Population; Standard of care; Physical therapy; Emergency medicine; Psychiatry; Internal medicine; Alternative medicine; Environmental health","score_opus":0.16616085965205576,"score_gpt":0.4082018045922205,"score_spread":0.24204094494016473,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388018182","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96883684,0.00003316047,0.0011487204,0.023732701,0.0010184748,0.0026042613,0.00006530695,0.00016163543,0.0023988667],"genre_scores_gemma":[0.9856873,0.000014811963,0.000060561222,0.011749391,0.0003589704,0.00010761165,0.0008278465,0.000042118307,0.001151394],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.99697125,0.00029860815,0.0014018131,0.0003524918,0.0006693,0.000306509],"domain_scores_gemma":[0.9814616,0.00664761,0.00056060625,0.00035216028,0.010701368,0.00027669145],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0017352033,0.00022849243,0.0009648146,0.0003678177,0.000060657676,0.000081936225,0.00013110203,0.00012938348,0.00002446074],"category_scores_gemma":[0.52346903,0.00014625667,0.00046374372,0.0011978932,0.0008892623,0.00040942483,0.00010593392,0.0003456336,0.00008343669],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.52829206,0.0007577683,0.004194328,0.00019418975,0.0014492839,0.00009725016,0.004493747,0.0000270907,0.0005987518,0.00056254194,0.22302072,0.23631229],"study_design_scores_gemma":[0.9591702,0.005287147,0.0054354444,0.0038581486,0.0007623481,0.000029351697,0.017867073,0.0025448909,0.00016363831,0.0018935357,0.0026544197,0.00033375347],"about_ca_topic_score_codex":0.00004546404,"about_ca_topic_score_gemma":0.0000064835776,"teacher_disagreement_score":0.5217338,"about_ca_system_score_codex":0.00006485455,"about_ca_system_score_gemma":0.0001031963,"threshold_uncertainty_score":0.59641737},"labels":[],"label_agreement":null},{"id":"W4388703342","doi":"10.1038/s41746-023-00926-4","title":"Modeling personalized heart rate response to exercise and environmental factors with wearables data","year":2023,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Heart Rate Variability and Autonomic Control","field":"Medicine","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Broad Institute","keywords":"Wearable computer; Wearable technology; Computer science; Human–computer interaction; Medicine; Embedded system","score_opus":0.04396797527614487,"score_gpt":0.2782513144001016,"score_spread":0.2342833391239567,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388703342","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98647225,0.00020268766,0.00025215236,0.011947654,0.00006033694,0.00058067206,0.0002026938,0.0001339842,0.00014759354],"genre_scores_gemma":[0.9964295,0.00007061181,0.00008697466,0.0005650486,0.000094670046,0.00001570546,0.00053015415,0.000031278334,0.0021760662],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985391,0.000048859976,0.00027610277,0.0005246062,0.000279964,0.00033139068],"domain_scores_gemma":[0.9986244,0.00033129583,0.000022116712,0.00058469607,0.000016668402,0.0004208437],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007918154,0.00020758307,0.0004964632,0.00017129093,0.000091919435,0.000041629413,0.00011165845,0.00006185677,0.0001232244],"category_scores_gemma":[0.0005296198,0.00014028023,0.00002700721,0.00022924421,0.0001999202,0.00028910462,0.00015048319,0.00015577607,0.000080225494],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.031859037,0.0009348172,0.049174562,0.0006700857,0.000669493,0.00086588296,0.021421317,0.0021705767,0.80654025,0.000105955136,0.009619807,0.07596824],"study_design_scores_gemma":[0.03159659,0.0073341187,0.1703513,0.0057212776,0.00091543293,0.0003561651,0.03693615,0.4305966,0.0019434596,0.00030675557,0.31209368,0.0018484762],"about_ca_topic_score_codex":0.00004876111,"about_ca_topic_score_gemma":0.0000036635713,"teacher_disagreement_score":0.8045968,"about_ca_system_score_codex":0.00005522042,"about_ca_system_score_gemma":0.00010630807,"threshold_uncertainty_score":0.5720462},"labels":[],"label_agreement":null},{"id":"W4390037992","doi":"10.1038/s41746-023-00975-9","title":"Dissecting the heterogeneity of “in the wild” stress from multimodal sensor data","year":2023,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Advanced Chemical Sensor Technologies","field":"Engineering","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Institute for Advanced Research; Vector Institute; Hospital for Sick Children; University of Toronto","funders":"Canadian Institutes of Health Research; Hospital for Sick Children; Canadian Institute for Advanced Research; Bill and Melinda Gates Foundation","keywords":"Stress (linguistics); Computer science; Computational biology; Biology; Philosophy; Linguistics","score_opus":0.04291571328632981,"score_gpt":0.28893846261862915,"score_spread":0.24602274933229934,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390037992","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9971965,0.0001841606,0.00017565978,0.00065761927,0.00013738111,0.00012433955,0.00027722167,0.00038009096,0.00086702197],"genre_scores_gemma":[0.9995244,0.000039797273,0.000062832274,0.000019901943,0.00013758555,0.0000059635954,0.0001799104,0.000017933848,0.000011674824],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99916565,0.000007193566,0.00022029327,0.00017671508,0.000223337,0.00020678785],"domain_scores_gemma":[0.9984021,0.0007672811,0.00003279064,0.000761118,0.000015799531,0.00002088573],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000065824606,0.000119937074,0.000174881,0.00003592797,0.000024630413,0.00001269146,0.00074138725,0.000055107703,0.0000046439864],"category_scores_gemma":[0.0011295595,0.00006257081,0.000019911744,0.00035172215,0.00018757491,0.00014082546,0.00017142676,0.0002322232,0.000008857699],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000087058965,0.00019318696,0.12590094,0.0003818758,0.00039438752,0.00044559294,0.0049806833,0.05311318,0.53842825,0.00040514566,0.005941401,0.26972833],"study_design_scores_gemma":[0.0034880324,0.00026548438,0.14626232,0.0013954246,0.0001339485,0.000051543615,0.04936009,0.26163077,0.51599,0.010969726,0.009262315,0.0011903235],"about_ca_topic_score_codex":0.000046930894,"about_ca_topic_score_gemma":0.000040568528,"teacher_disagreement_score":0.268538,"about_ca_system_score_codex":0.000016057962,"about_ca_system_score_gemma":9.186064e-7,"threshold_uncertainty_score":0.25515637},"labels":[],"label_agreement":null},{"id":"W4390745503","doi":"10.1038/s41746-023-00970-0","title":"Large language models to identify social determinants of health in electronic health records","year":2024,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Chronic Disease Management Strategies","field":"Medicine","cited_by":254,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"U.S. National Library of Medicine; European Commission; ViewRay; NRG Oncology; Radiological Society of North America; National Cancer Institute; National Institutes of Health; Conquer Cancer Foundation; U.S. Department of Health and Human Services","keywords":"Social determinants of health; Health care; Medicine; Political science; Law","score_opus":0.047660636487949916,"score_gpt":0.41487254738845186,"score_spread":0.3672119109005019,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390745503","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91578525,0.016282078,0.001977728,0.03495791,0.00062466617,0.0017051459,0.00018228315,0.00030078055,0.028184142],"genre_scores_gemma":[0.99612087,0.0002866632,0.000016686363,0.0017707573,0.000288714,0.000026282376,0.00014355908,0.000039768813,0.0013067236],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9977083,0.00004192713,0.0007099087,0.00038658068,0.00044291973,0.0007103635],"domain_scores_gemma":[0.9993598,0.00004934932,0.0001058092,0.00024807648,0.000031417625,0.00020557699],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007269428,0.00019761236,0.00070738996,0.0004507752,0.000040736242,0.000034986842,0.00013167837,0.00004707681,0.00015238987],"category_scores_gemma":[0.0000763886,0.00016661028,0.000084031715,0.00068648177,0.00007092037,0.00028684898,0.00008778335,0.00022732907,0.00003859103],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004762846,0.0010457562,0.0038198815,0.00946483,0.00026167653,0.00057829364,0.033009723,0.00002197065,0.00015578249,0.037466183,0.123099536,0.79060006],"study_design_scores_gemma":[0.04229123,0.03132416,0.3685255,0.058436606,0.000732964,0.00035367947,0.14806227,0.027421802,0.00026142638,0.09248691,0.22673707,0.0033663611],"about_ca_topic_score_codex":0.00045537646,"about_ca_topic_score_gemma":0.000558645,"teacher_disagreement_score":0.7872337,"about_ca_system_score_codex":0.00060794916,"about_ca_system_score_gemma":0.0008723428,"threshold_uncertainty_score":0.67941695},"labels":[],"label_agreement":null},{"id":"W4391142511","doi":"10.1038/s41746-024-01005-y","title":"An intriguing vision for transatlantic collaborative health data use and artificial intelligence development","year":2024,"lang":"en","type":"review","venue":"npj Digital Medicine","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Innovates; University of Alberta; Alberta Machine Intelligence Institute; Canadian Institutes of Health Research; Mitacs; University Hospital Foundation; Government of Canada; Canadian Institute for Advanced Research","keywords":"Data science; Artificial intelligence; Computer science; Psychology","score_opus":0.5831914706803393,"score_gpt":0.5764761877958379,"score_spread":0.006715282884501406,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391142511","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00013300657,0.98335093,0.008523043,0.003137089,0.0011565249,0.0032738675,0.00026768062,0.000113151116,0.000044715776],"genre_scores_gemma":[0.0025327408,0.9866745,0.0018988582,0.0003126357,0.0017434782,0.0001426613,0.0065008663,0.00009078104,0.00010346178],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9962296,0.000079360514,0.0017964002,0.0010225283,0.0004096407,0.00046248848],"domain_scores_gemma":[0.997241,0.000799528,0.00032914407,0.0007632687,0.00033002597,0.00053699384],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001023629,0.00048764973,0.0017588539,0.0004514972,0.00019468491,0.0002622963,0.00028917877,0.0002802448,0.000017654565],"category_scores_gemma":[0.0012277688,0.0003313511,0.000074860975,0.0007482032,0.00024974617,0.00065572903,0.00007461696,0.00049320585,0.000052344614],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000054681677,0.00012874726,0.0000029831847,0.020493506,0.00009261456,0.00001831199,0.0024198524,9.7131306e-8,5.676533e-7,0.00048383736,0.0020376677,0.9742671],"study_design_scores_gemma":[0.000027226668,0.0017229671,0.0000029223893,0.047734447,0.0006910318,0.00013107914,0.0018874948,0.0003766963,0.000008791786,0.0007587974,0.9463475,0.00031108156],"about_ca_topic_score_codex":0.00008489783,"about_ca_topic_score_gemma":0.00011477654,"teacher_disagreement_score":0.97395605,"about_ca_system_score_codex":0.00029641218,"about_ca_system_score_gemma":0.0026864402,"threshold_uncertainty_score":0.9999139},"labels":[],"label_agreement":null},{"id":"W4391508432","doi":"10.1038/s41746-024-00998-w","title":"Artificial intelligence-driven virtual rehabilitation for people living in the community: A scoping review","year":2024,"lang":"en","type":"review","venue":"npj Digital Medicine","topic":"Stroke Rehabilitation and Recovery","field":"Medicine","cited_by":92,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Toronto Rehabilitation Institute; University Health Network","funders":"","keywords":"Rehabilitation; Artificial intelligence; Computer science; MEDLINE; Machine learning; Data science; Medicine; Physical therapy","score_opus":0.112268736563046,"score_gpt":0.42556080548492986,"score_spread":0.3132920689218839,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391508432","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000060934868,0.9864754,0.00035490023,0.0033314566,0.0008281793,0.007319033,0.000048324542,0.00008046818,0.0015012984],"genre_scores_gemma":[0.00079647574,0.99566525,0.000141189,0.0006404482,0.00079342804,0.0012652051,0.00040157835,0.00007460797,0.00022179025],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.99643046,0.0004889729,0.0017681217,0.00042586704,0.00055151543,0.00033508797],"domain_scores_gemma":[0.9830218,0.015708767,0.00030972142,0.000689577,0.00015402696,0.00011610613],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0022650496,0.00046729425,0.0026309853,0.00057184714,0.000115783274,0.00007522337,0.00033936428,0.00024480556,0.00007687488],"category_scores_gemma":[0.017783249,0.00025698435,0.0008200942,0.001228843,0.00028524883,0.00016991288,0.00009629827,0.0011590869,0.00011954424],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011041765,0.0001365239,0.00001335807,0.27534968,0.000060333037,0.0000047553935,0.0022247015,2.683607e-7,9.010827e-8,0.00062047807,0.0018763276,0.7197024],"study_design_scores_gemma":[0.00007679977,0.001834265,0.000018548513,0.8417854,0.0013855214,0.000105669606,0.0038687768,0.000022342896,3.066577e-8,0.00047405122,0.15021513,0.00021349976],"about_ca_topic_score_codex":0.000019450836,"about_ca_topic_score_gemma":0.00007794097,"teacher_disagreement_score":0.7194889,"about_ca_system_score_codex":0.00024875414,"about_ca_system_score_gemma":0.0005124872,"threshold_uncertainty_score":0.99998826},"labels":[],"label_agreement":null},{"id":"W4391511766","doi":"10.1038/s41746-024-01020-z","title":"AI-derived epicardial fat measurements improve cardiovascular risk prediction from myocardial perfusion imaging","year":2024,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Cardiovascular Disease and Adiposity","field":"Medicine","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; University of Calgary","funders":"National Center for Advancing Translational Sciences; National Heart, Lung, and Blood Institute; National Institutes of Health","keywords":"Medicine; Context (archaeology); Myocardial infarction; Correlation; Perfusion; Correction for attenuation; Ejection fraction; Myocardial perfusion imaging; Cardiology; Confounding; Perfusion scanning; Nuclear medicine; Internal medicine; Radiology; Artificial intelligence; Positron emission tomography; Heart failure; Computer science; Mathematics","score_opus":0.012557672913267627,"score_gpt":0.2350708232695965,"score_spread":0.22251315035632888,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391511766","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8825673,0.07978015,0.008835297,0.00244519,0.007236746,0.0017256564,0.0010568792,0.0011633529,0.015189454],"genre_scores_gemma":[0.98976874,0.00071906927,0.00004873262,0.00048244218,0.007859216,0.000049152226,0.00084479223,0.00008970938,0.00013813915],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9960644,0.0001337416,0.0005381028,0.0009995694,0.0017763212,0.00048782],"domain_scores_gemma":[0.9981898,0.00009431544,0.000059749513,0.00095847447,0.00018203803,0.0005156099],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00051703927,0.0004507773,0.0010256184,0.00024126201,0.00017303563,0.00017487563,0.00013934617,0.00017421096,0.000096744785],"category_scores_gemma":[0.00041410848,0.000357512,0.0018118579,0.00037357942,0.00023573861,0.0005841357,0.0001362512,0.0006401646,0.00016148592],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009984392,0.00025226452,0.06254762,0.00035823573,0.016600251,0.0017008372,0.0010424558,0.00008917811,0.10311483,0.000024616373,0.011671933,0.8015993],"study_design_scores_gemma":[0.035095192,0.0021963085,0.5198078,0.007731142,0.06878893,0.0009781823,0.0016116494,0.010250631,0.037983917,0.0019477606,0.3107855,0.0028229652],"about_ca_topic_score_codex":0.00025769617,"about_ca_topic_score_gemma":0.0000010119011,"teacher_disagreement_score":0.7987764,"about_ca_system_score_codex":0.0001948317,"about_ca_system_score_gemma":0.00012225835,"threshold_uncertainty_score":0.9998877},"labels":[],"label_agreement":null},{"id":"W4392386827","doi":"10.1038/s41746-024-01066-z","title":"Integrating artificial intelligence into healthcare systems: more than just the algorithm","year":2024,"lang":"en","type":"editorial","venue":"npj Digital Medicine","topic":"Sepsis Diagnosis and Treatment","field":"Medicine","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"University of Toronto","keywords":"Software deployment; Interoperability; Health care; Adaptability; Computer science; Artificial intelligence; Medicine; Political science; Management; Software engineering","score_opus":0.08964970192950854,"score_gpt":0.3978191126073248,"score_spread":0.3081694106778162,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392386827","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00027311457,0.035576552,0.00092786027,0.033780895,0.92359143,0.0020184943,0.00060020474,0.00039289024,0.002838562],"genre_scores_gemma":[0.06782814,0.001384979,0.0001885871,0.00052303786,0.92403966,0.00054151047,0.0033456825,0.0002182669,0.0019301309],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9946429,0.00007595802,0.0013554284,0.0010749695,0.0022042713,0.00064648886],"domain_scores_gemma":[0.99551463,0.001942488,0.0003607249,0.0010086778,0.0007101093,0.00046335417],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00057182653,0.00087117526,0.0015137205,0.00034197822,0.00022527589,0.00036500185,0.000454061,0.00083750096,0.00008099791],"category_scores_gemma":[0.0029580556,0.00045726093,0.00034090722,0.0006814551,0.0005745557,0.00015346026,0.0002067095,0.0020862967,0.0003739973],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043979613,0.0001837774,0.00005786726,0.0012552438,0.0004492576,0.0005670616,0.002463784,0.0000012496245,0.0000026512564,0.000957297,0.7677908,0.22622705],"study_design_scores_gemma":[0.00043094595,0.002750657,0.00003119291,0.017864455,0.0013595908,0.0001380249,0.029507222,0.0012418177,0.00003839059,0.001670094,0.94440687,0.0005607718],"about_ca_topic_score_codex":0.0034437154,"about_ca_topic_score_gemma":0.0001801729,"teacher_disagreement_score":0.22566627,"about_ca_system_score_codex":0.00081882614,"about_ca_system_score_gemma":0.0007104406,"threshold_uncertainty_score":0.9997879},"labels":[],"label_agreement":null},{"id":"W4393335480","doi":"10.1038/s41746-024-01074-z","title":"Foundation metrics for evaluating effectiveness of healthcare conversations powered by generative AI","year":2024,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Topic Modeling","field":"Computer Science","cited_by":184,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Institute of Standards and Technology","keywords":"Health care; Computer science; Personalization; Set (abstract data type); Process (computing); Comprehension; Human–computer interaction; World Wide Web","score_opus":0.059876822644538336,"score_gpt":0.3823261757586979,"score_spread":0.32244935311415956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393335480","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011753276,0.00089532015,0.9804857,0.0049216943,0.00084933743,0.00047377488,0.000025447234,0.000091103895,0.00050437695],"genre_scores_gemma":[0.9928108,0.0000064536102,0.00667338,0.00019009563,0.00009345186,0.000044374265,0.000096913354,0.000008778631,0.00007578228],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988775,0.00006349319,0.00027465844,0.0003027073,0.00034230383,0.00013929394],"domain_scores_gemma":[0.99819523,0.0010755099,0.000063719934,0.00020838791,0.00039744034,0.00005969213],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007190111,0.00009546895,0.00018872143,0.00016569206,0.0000558382,0.00009499031,0.00019397397,0.000041211726,0.000005268011],"category_scores_gemma":[0.0010749295,0.00007897169,0.000035182522,0.0006558613,0.00004650534,0.00062938244,0.00004863327,0.00007975116,0.0000042581573],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034400055,0.000058120237,0.0004030335,0.0012889791,0.000117519994,0.0000036446374,0.003586556,0.00045234335,0.013157864,0.33878848,0.001405688,0.6407034],"study_design_scores_gemma":[0.0009983714,0.0010346113,0.00017786701,0.0006428447,0.000028297865,0.0000062043237,0.00018523063,0.9561091,0.0046109455,0.03350447,0.0025395672,0.0001625081],"about_ca_topic_score_codex":0.00004224028,"about_ca_topic_score_gemma":0.0000017195009,"teacher_disagreement_score":0.9810575,"about_ca_system_score_codex":0.00011676133,"about_ca_system_score_gemma":0.0001675937,"threshold_uncertainty_score":0.32203722},"labels":[],"label_agreement":null},{"id":"W4394911989","doi":"10.1038/s41746-024-01088-7","title":"Predicting non-muscle invasive bladder cancer outcomes using artificial intelligence: a systematic review using APPRAISE-AI","year":2024,"lang":"en","type":"review","venue":"npj Digital Medicine","topic":"Bladder and Urothelial Cancer Treatments","field":"Medicine","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"The Wilson Centre; Sinai Health System; Mount Sinai Hospital; Princess Margaret Cancer Centre; University of Toronto; University Health Network; Western University; Public Health Ontario","funders":"University of Toronto","keywords":"Medicine; MEDLINE; Systematic review; Bladder cancer; Scopus; Meta-analysis; Artificial intelligence; Medical physics; Machine learning; Internal medicine; Computer science; Cancer","score_opus":0.1434620547778596,"score_gpt":0.43946352798282284,"score_spread":0.2960014732049633,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394911989","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000031539003,0.98800135,0.00034018504,0.00045987018,0.0018945064,0.0071341987,0.00035707137,0.00019380951,0.0015874632],"genre_scores_gemma":[0.0008904678,0.9941218,0.0000806743,0.0013576087,0.0018008868,0.0006897151,0.00023548653,0.00030187756,0.0005215023],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.99380994,0.00012221899,0.0028623447,0.0011522851,0.0012785619,0.0007746211],"domain_scores_gemma":[0.99677145,0.000473343,0.00094274315,0.0009789456,0.00032769213,0.0005058143],"candidate_categories":["metaepi_narrow"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.00046969415,0.0013533849,0.0075203246,0.0005695682,0.00015350047,0.00016211357,0.00038616313,0.00044606868,0.00030862846],"category_scores_gemma":[0.0015487772,0.0008027632,0.0011700377,0.001369683,0.00030152095,0.0003442415,0.00022025901,0.00106769,0.00020515546],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009204778,0.00012839533,0.00002998826,0.8980127,0.0028696652,0.00040246785,0.00023355916,0.0000013353317,0.0000016728502,0.000038205293,0.00036740437,0.09790542],"study_design_scores_gemma":[0.0002303363,0.00032592393,0.0000014925964,0.92876136,0.059051357,0.0006334412,0.00025731703,0.0002149544,0.0000022225422,0.00014486225,0.009778092,0.0005986604],"about_ca_topic_score_codex":0.00029829127,"about_ca_topic_score_gemma":0.000021750946,"teacher_disagreement_score":0.09730676,"about_ca_system_score_codex":0.00095980935,"about_ca_system_score_gemma":0.00213226,"threshold_uncertainty_score":0.9999217},"labels":[],"label_agreement":null},{"id":"W4396894318","doi":"10.1038/s41746-024-01118-4","title":"Shortcut learning in medical AI hinders generalization: method for estimating AI model generalization without external data","year":2024,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":65,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; Vector Institute; University Health Network; Toronto General Hospital; University of Toronto; Ted Rogers Centre for Heart Research","funders":"University of Toronto; Natural Sciences and Engineering Research Council of Canada; University Health Network; Canadian Institute for Advanced Research","keywords":"Generalization; Computer science; Artificial intelligence; Machine learning; Mathematics","score_opus":0.06358721130492692,"score_gpt":0.4232754399995051,"score_spread":0.35968822869457817,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396894318","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007516966,0.00064121705,0.9713503,0.02494612,0.0009446021,0.00034794095,0.000010469735,0.00048514057,0.0005225294],"genre_scores_gemma":[0.40639663,0.000025160976,0.5853858,0.005390911,0.0014104355,0.000058241396,0.00056562386,0.0000691035,0.0006981218],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99666554,0.00016154457,0.00071185076,0.0009497579,0.0010658049,0.00044549498],"domain_scores_gemma":[0.9983618,0.0004074646,0.0001113694,0.0006964497,0.00015273684,0.00027017776],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018182523,0.00025997072,0.00037321664,0.00032699044,0.00014292187,0.0004042335,0.001289044,0.00016552248,0.000036884147],"category_scores_gemma":[0.002687702,0.00021975246,0.00004163275,0.00067343767,0.00007371791,0.0017346945,0.0005240092,0.00070460694,0.0000068091413],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012495642,0.000027064962,0.009062691,0.00042635173,0.000023186543,0.000075370794,0.001818788,0.510054,0.000055951343,0.036716506,0.0040301536,0.43769744],"study_design_scores_gemma":[0.0004596931,0.00012132811,0.000120561854,0.0008872121,0.000012848217,0.000109796936,0.00002285703,0.9887929,0.00000737044,0.006492275,0.0027598753,0.00021328828],"about_ca_topic_score_codex":0.00017094062,"about_ca_topic_score_gemma":0.0000594872,"teacher_disagreement_score":0.4787389,"about_ca_system_score_codex":0.00012260016,"about_ca_system_score_gemma":0.00049482135,"threshold_uncertainty_score":0.89612454},"labels":[],"label_agreement":null},{"id":"W4397032058","doi":"10.1038/s41746-024-01130-8","title":"Development and validation of machine learning algorithms based on electrocardiograms for cardiovascular diagnoses at the population level","year":2024,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"ECG Monitoring and Analysis","field":"Medicine","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Canadian VIGOUR Centre; University of Calgary; University of Alberta","funders":"Canadian Institutes of Health Research; Alberta Innovates; University of Alberta; Alberta Health Services","keywords":"Medicine; Internal medicine; Cardiology; Ventricular tachycardia; Algorithm; Atrial fibrillation; Medical diagnosis; Pulmonary embolism; Heart failure; Receiver operating characteristic; Population; Electrocardiography; Myocardial infarction; Radiology","score_opus":0.03396268307185496,"score_gpt":0.28266106438854605,"score_spread":0.2486983813166911,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4397032058","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94810414,0.010842644,0.03696189,0.002069755,0.00032830704,0.0006588476,0.000028549335,0.00015755079,0.00084833364],"genre_scores_gemma":[0.9974212,0.00008703446,0.0008471044,0.00003767521,0.00032971383,0.000043069995,0.00056792825,0.000022325477,0.0006439718],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99893165,0.000020501053,0.00024147276,0.00023267869,0.00043470343,0.00013900586],"domain_scores_gemma":[0.9993568,0.0003155654,0.000041843196,0.00015837116,0.00006657137,0.000060857954],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042419718,0.0001299112,0.00033129333,0.00015067832,0.00009871409,0.000025912794,0.00003297879,0.00004450263,0.000005807147],"category_scores_gemma":[0.00040124345,0.00007676186,0.00020864335,0.00025978687,0.000049052476,0.00005688628,0.000015251849,0.00011398669,0.0000023993045],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009869477,0.000047280297,0.03980835,0.00039739764,0.0010760805,0.000016676206,0.00027844208,0.0010754868,0.0005171778,0.000041902094,0.00015235916,0.95649016],"study_design_scores_gemma":[0.012360345,0.0070058145,0.17520341,0.009717451,0.009730793,0.00022727896,0.0013959124,0.27029938,0.107687846,0.00052401924,0.40447602,0.0013717383],"about_ca_topic_score_codex":0.00006181594,"about_ca_topic_score_gemma":0.0000024664432,"teacher_disagreement_score":0.9551184,"about_ca_system_score_codex":0.00008175189,"about_ca_system_score_gemma":0.000025937568,"threshold_uncertainty_score":0.3130258},"labels":[],"label_agreement":null},{"id":"W4398183239","doi":"10.1038/s41746-024-01127-3","title":"Generalization—a key challenge for responsible AI in patient-facing clinical applications","year":2024,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":103,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"GlaxoSmithKline foundation; Cystic Fibrosis Trust","keywords":"Generalization; Key (lock); Computer science; Artificial intelligence; Bioethics; Machine learning; Data science; Health care; Computer security; Political science; Epistemology","score_opus":0.23209419032222584,"score_gpt":0.5085691543340696,"score_spread":0.27647496401184374,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398183239","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6166777,0.013319824,0.07934923,0.2415406,0.0051591787,0.00669138,0.000100352125,0.00068744546,0.0364743],"genre_scores_gemma":[0.9936781,0.00038853998,0.0004282342,0.0021177381,0.0016524353,0.00038355606,0.00028282058,0.000030358678,0.0010382347],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983455,0.000026705675,0.0008018284,0.00036310017,0.00021352668,0.00024934663],"domain_scores_gemma":[0.99869186,0.0006032221,0.000051615658,0.00025350216,0.00021640517,0.00018338648],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004180981,0.00012351676,0.0002736076,0.00027754906,0.00006222273,0.0000380271,0.000062672756,0.0001339693,0.00007198113],"category_scores_gemma":[0.0009926913,0.0001002415,0.00007167167,0.0004958448,0.000111548165,0.00022197359,0.000017348111,0.00023056903,0.00010827376],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021712907,0.00030320534,0.006020563,0.00049196405,0.000033254157,0.000024831295,0.0031643573,0.000017319784,0.00035212873,0.020496538,0.016309917,0.95256877],"study_design_scores_gemma":[0.00035959607,0.0025003187,0.0018401366,0.0017022965,0.00009228316,0.000059034315,0.0030994203,0.007995756,0.0011038092,0.036779385,0.9441839,0.00028406407],"about_ca_topic_score_codex":0.000070301576,"about_ca_topic_score_gemma":0.000056013858,"teacher_disagreement_score":0.95228475,"about_ca_system_score_codex":0.000111270965,"about_ca_system_score_gemma":0.00037876202,"threshold_uncertainty_score":0.408773},"labels":[],"label_agreement":null},{"id":"W4398232573","doi":"10.1038/s41746-024-01134-4","title":"Evaluation of stenoses using AI video models applied to coronary angiography","year":2024,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Coronary Interventions and Diagnostics","field":"Medicine","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Polytechnique Montréal; Montreal Heart Institute","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; Institut de Valorisation des Données; Institut de Cardiologie de Montréal; Fondation Institut de Cardiologie de Montréal; Canadian Institute for Advanced Research","keywords":"Medicine; Stenosis; Coronary artery disease; Radiology; Gold standard (test); Coronary angiography; Cardiology; Coronary angiogram; Internal medicine; Angiography; Myocardial infarction","score_opus":0.08625673233747366,"score_gpt":0.36696833922921507,"score_spread":0.2807116068917414,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398232573","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9210078,0.008708511,0.017985784,0.0020792382,0.00066642015,0.0012177065,0.00010826572,0.00015444202,0.048071846],"genre_scores_gemma":[0.998744,0.000023670937,0.00028236333,0.00040799932,0.00023981852,0.000032137727,0.00010377854,0.000027683693,0.00013854257],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982058,0.000016594176,0.0004098464,0.000267747,0.0009260625,0.00017394255],"domain_scores_gemma":[0.9989238,0.00016253022,0.000042087446,0.00026046342,0.0004422179,0.00016890012],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042083533,0.00015325296,0.00031062646,0.00048350313,0.000027090826,0.000024393494,0.000067771245,0.000057677542,0.00032736312],"category_scores_gemma":[0.0002712244,0.00011988014,0.00019262599,0.00063875836,0.00010693474,0.00021531194,0.000048777576,0.00010206458,0.000024482713],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005054577,0.0009342071,0.004808175,0.00091161445,0.0011958188,0.00020489226,0.0016999426,0.006974136,0.009023158,0.0126332315,0.01790498,0.9432044],"study_design_scores_gemma":[0.020776166,0.019850776,0.14933957,0.03751588,0.022752922,0.0017975323,0.009242929,0.5651362,0.003860646,0.13654938,0.030996462,0.0021815526],"about_ca_topic_score_codex":0.000029860339,"about_ca_topic_score_gemma":0.0000038488583,"teacher_disagreement_score":0.9410228,"about_ca_system_score_codex":0.00009497768,"about_ca_system_score_gemma":0.00015303842,"threshold_uncertainty_score":0.488857},"labels":[],"label_agreement":null},{"id":"W4399850471","doi":"10.1038/s41746-024-01167-9","title":"Development of an effective predictive screening tool for prostate cancer using the ClarityDX machine learning platform","year":2024,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Prostate Cancer Diagnosis and Treatment","field":"Medicine","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University Health Network; Mount Sinai Hospital; University of Calgary; McGill University; University of Alberta; Prostate Cancer Canada","funders":"Alberta Innovates; University of Alberta; Prostate Cancer Canada; Alberta Cancer Foundation; Movember Foundation","keywords":"Prostate cancer; Medicine; Overdiagnosis; Prostate; Prostate biopsy; Cohort; Internal medicine; PCA3; Oncology; Cancer; Urology","score_opus":0.03643420052706463,"score_gpt":0.3258387579521162,"score_spread":0.28940455742505156,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399850471","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98210907,0.006211241,0.0068472675,0.0008218218,0.000311515,0.0028130116,0.00022990149,0.00012726069,0.00052890397],"genre_scores_gemma":[0.9960446,0.00013043243,0.0021686472,0.00012955288,0.0003264254,0.00064865296,0.00030439097,0.000050508308,0.00019682867],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985018,0.000015449192,0.00041538445,0.00037443868,0.00038379896,0.0003091744],"domain_scores_gemma":[0.9991011,0.00032011565,0.00011172171,0.00016741644,0.00017282274,0.00012680428],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035774012,0.0002470162,0.00043263094,0.00012209675,0.00017152456,0.000049155824,0.00007591772,0.00006722475,0.00002868926],"category_scores_gemma":[0.00015781554,0.00013948327,0.00008647632,0.00026351897,0.00016987008,0.00036169065,0.0000533184,0.00028015897,0.0000012360019],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013976475,0.00020735699,0.026924437,0.0009471367,0.0010921828,0.00006430326,0.010675643,0.00035853856,0.002296717,0.0001879181,0.00010736368,0.95574075],"study_design_scores_gemma":[0.03265102,0.028695123,0.22591019,0.040857922,0.005274884,0.0005299884,0.01324217,0.34702346,0.11294702,0.0018355653,0.1890471,0.0019855544],"about_ca_topic_score_codex":0.00008831798,"about_ca_topic_score_gemma":0.000023526383,"teacher_disagreement_score":0.9537552,"about_ca_system_score_codex":0.00032602734,"about_ca_system_score_gemma":0.00022705563,"threshold_uncertainty_score":0.5687962},"labels":[],"label_agreement":null},{"id":"W4399996641","doi":"10.1038/s41746-024-01162-0","title":"A scoping review assessing the usability of digital health technologies targeting people with multiple sclerosis","year":2024,"lang":"en","type":"review","venue":"npj Digital Medicine","topic":"Mobile Health and mHealth Applications","field":"Health Professions","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; McGill University; Montreal Neurological Institute and Hospital; University of Victoria; Université de Montréal","funders":"","keywords":"Usability; CINAHL; Computer science; mHealth; Digital health; Telehealth; MEDLINE; Web usability; World Wide Web; Telemedicine; Health care; Medicine; Human–computer interaction; Nursing; Psychological intervention","score_opus":0.1714885205261586,"score_gpt":0.5000118467964066,"score_spread":0.32852332627024805,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399996641","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000068003706,0.9666854,0.0002744544,0.010450889,0.00043843905,0.01909788,0.0003550915,0.0005621476,0.0021288889],"genre_scores_gemma":[0.0011829908,0.9837377,0.00013467425,0.0007088412,0.00028812466,0.013095194,0.000608951,0.00012033789,0.0001231591],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.99274826,0.00041095485,0.0039302595,0.00096319924,0.00075612136,0.0011911892],"domain_scores_gemma":[0.9904436,0.0048916014,0.0026451747,0.0013560907,0.00034498388,0.00031858875],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0027593563,0.0007038669,0.0041033695,0.00026956463,0.0009724407,0.00006216619,0.00073974335,0.00041118634,0.000055621],"category_scores_gemma":[0.006465917,0.00034791994,0.00029971017,0.0021909878,0.00061265175,0.00041156833,0.00044920348,0.002303785,0.00014836995],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000220662,0.000031756677,0.00021711408,0.4408522,0.000025971096,6.117055e-7,0.000107845706,4.4588653e-8,1.8595953e-8,0.00010780615,0.0057177385,0.5529367],"study_design_scores_gemma":[0.00017096252,0.00012585023,0.000016443148,0.54947966,0.00024548065,0.00000834274,0.0009253788,0.0000029458672,1.684753e-8,0.00007591789,0.44879124,0.00015775769],"about_ca_topic_score_codex":0.00014534971,"about_ca_topic_score_gemma":0.00009054311,"teacher_disagreement_score":0.5527789,"about_ca_system_score_codex":0.0005210928,"about_ca_system_score_gemma":0.005560975,"threshold_uncertainty_score":0.9999979},"labels":[],"label_agreement":null},{"id":"W4400098873","doi":"10.1038/s41746-024-01166-w","title":"A multi-center study on the adaptability of a shared foundation model for electronic health records","year":2024,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; SickKids Foundation; Hospital for Sick Children","funders":"","keywords":"Adaptability; Computer science; Modular design; Artificial intelligence; Machine learning; Foundation (evidence); Robustness (evolution); Scalability; Medical record; Usability; Task (project management); Medicine; Human–computer interaction; Engineering; Database","score_opus":0.09029825835760427,"score_gpt":0.3822316847891663,"score_spread":0.29193342643156206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400098873","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13179661,0.00024542576,0.8168802,0.047657814,0.00052380323,0.0022101959,0.000030872478,0.0002487969,0.00040622917],"genre_scores_gemma":[0.99776375,0.000005198349,0.0013098341,0.00044186163,0.000087569584,0.00012521973,0.000021455975,0.000014320462,0.00023080724],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983982,0.00009641002,0.00040348383,0.00043127022,0.00036394532,0.00030672294],"domain_scores_gemma":[0.99861574,0.00054072123,0.00010263961,0.0005534738,0.00011112472,0.00007632227],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010689787,0.00013398609,0.0002297406,0.00009533814,0.00008542657,0.00008378149,0.0004693692,0.00002735824,0.000009755677],"category_scores_gemma":[0.00071915664,0.00008118223,0.000054819797,0.00031857876,0.000047537404,0.0002908905,0.000089546455,0.00027706518,0.000008472314],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027943822,0.0028767039,0.021011416,0.0014276406,0.00018349118,0.00000623147,0.04723843,0.0017367043,0.000044848734,0.08482183,0.006118461,0.8342548],"study_design_scores_gemma":[0.00068892847,0.00258322,0.0060427254,0.0002128432,0.0000036649017,0.0000021918108,0.00022460762,0.9858892,9.757699e-7,0.0027407324,0.001543576,0.00006735232],"about_ca_topic_score_codex":0.00011649841,"about_ca_topic_score_gemma":0.00012047541,"teacher_disagreement_score":0.9841525,"about_ca_system_score_codex":0.0002043387,"about_ca_system_score_gemma":0.00033947488,"threshold_uncertainty_score":0.33105153},"labels":[],"label_agreement":null},{"id":"W4400316892","doi":"10.1038/s41746-024-01180-y","title":"The long but necessary road to responsible use of large language models in healthcare research","year":2024,"lang":"en","type":"editorial","venue":"npj Digital Medicine","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"University of Toronto","keywords":"Dissemination; Data extraction; Health care; Computer science; Data science; Risk analysis (engineering); Psychology; Cognitive psychology; Medicine; MEDLINE; Political science","score_opus":0.22443907727792461,"score_gpt":0.5133344245479209,"score_spread":0.28889534726999627,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400316892","genre_codex":"editorial","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13653348,0.023671832,0.00007532414,0.09227898,0.739196,0.0034237728,0.0008043403,0.00015555375,0.0038607374],"genre_scores_gemma":[0.5384659,0.0021341837,0.00003984503,0.0005406778,0.43435985,0.00020244274,0.0010165478,0.00013340077,0.023107102],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99466723,0.00025831378,0.0012511398,0.000672941,0.0022372287,0.000913172],"domain_scores_gemma":[0.99198294,0.004794929,0.00014941937,0.0009914124,0.001606495,0.00047483516],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0033179792,0.0003109232,0.00077814684,0.00098128,0.0001632795,0.00012170282,0.00036849725,0.0007173887,0.000028223401],"category_scores_gemma":[0.019297166,0.00020645522,0.000100967736,0.0015650939,0.00031262336,0.00032225478,0.00022155655,0.0025385283,0.0001470548],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011093944,0.00012202297,0.0003092278,0.001223034,0.000035289642,0.00024689466,0.005361625,0.0000070866727,0.000044261495,0.000563506,0.9398518,0.051125824],"study_design_scores_gemma":[0.0003374389,0.0035617363,0.00050858443,0.016060365,0.000090666814,0.000024735838,0.021373125,0.00065234816,0.00062159984,0.0070264884,0.94930124,0.00044166928],"about_ca_topic_score_codex":0.018489523,"about_ca_topic_score_gemma":0.005500429,"teacher_disagreement_score":0.40193248,"about_ca_system_score_codex":0.0005727623,"about_ca_system_score_gemma":0.0029405414,"threshold_uncertainty_score":0.99976265},"labels":[],"label_agreement":null},{"id":"W4400349581","doi":"10.1038/s41746-024-01172-y","title":"A systematic umbrella review and meta-meta-analysis of eHealth and mHealth interventions for improving lifestyle behaviours","year":2024,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Mobile Health and mHealth Applications","field":"Health Professions","cited_by":81,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Leibniz-Gemeinschaft; Veski; Freie Hansestadt Bremen","keywords":"eHealth; mHealth; Meta-analysis; Psychological intervention; Systematic review; Medicine; Psychology; MEDLINE; Computer science; Nursing; Political science; Health care","score_opus":0.22007413067781587,"score_gpt":0.512203863301477,"score_spread":0.29212973262366115,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400349581","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017359974,0.93243045,0.0065665375,0.040288165,0.00027026839,0.01568024,0.0018426673,0.00018265228,0.0010030521],"genre_scores_gemma":[0.8822835,0.04819512,0.0011699648,0.014779618,0.00025797967,0.04570197,0.0008672286,0.00013997198,0.00660461],"study_design_codex":"systematic_review","study_design_gemma":"meta_analysis","domain_scores_codex":[0.9957598,0.00031531474,0.0025074335,0.0005665154,0.0003017968,0.0005491623],"domain_scores_gemma":[0.9949501,0.002749997,0.0007890669,0.00053571194,0.0002978382,0.0006772809],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034962667,0.0002814928,0.0034668585,0.0005503169,0.00038266962,0.000018340164,0.00014165758,0.00013782705,0.00031529827],"category_scores_gemma":[0.0012799111,0.0001781051,0.00076604314,0.0010127698,0.00015682747,0.00017301197,0.00008088301,0.00040332446,0.000010076958],"study_design_candidate":"meta_analysis","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011377366,0.0000831706,0.00019985554,0.9472731,0.02877438,0.0000015408751,0.00051144115,4.501177e-7,0.0000023990867,0.014312055,0.00610176,0.0027285116],"study_design_scores_gemma":[0.00047260674,0.0005563385,0.0007323829,0.010018911,0.9809714,0.000012034494,0.0007013047,0.00040744693,3.174795e-7,0.0006690994,0.005272227,0.0001859607],"about_ca_topic_score_codex":0.00063691504,"about_ca_topic_score_gemma":0.00040145274,"teacher_disagreement_score":0.952197,"about_ca_system_score_codex":0.000086745094,"about_ca_system_score_gemma":0.00040892157,"threshold_uncertainty_score":0.7262915},"labels":[],"label_agreement":null},{"id":"W4401810043","doi":"10.1038/s41746-024-01206-5","title":"A portable and efficient dementia screening tool using eye tracking machine learning and virtual reality","year":2024,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Shenzhen Fundamental Research Program","keywords":"Dementia; Montreal Cognitive Assessment; Eye tracking; Cognition; Neuropsychology; Cognitive Assessment System; Cognitive impairment; Computer science; Artificial intelligence; Physical medicine and rehabilitation; Psychology; Medicine; Machine learning; Disease; Psychiatry; Pathology","score_opus":0.035353582365807434,"score_gpt":0.34994169133208314,"score_spread":0.3145881089662757,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401810043","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97695464,0.005779459,0.010247042,0.00091225567,0.00009999454,0.00039697182,0.000013756193,0.00013616975,0.0054597356],"genre_scores_gemma":[0.9979468,0.0001479043,0.00016301525,0.00012767267,0.00022149707,0.0000084931025,0.00008587091,0.000033913813,0.0012648326],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99808896,0.00004048336,0.00035742126,0.00047040006,0.00062096585,0.00042178016],"domain_scores_gemma":[0.99933374,0.00015493075,0.00004808684,0.00010846277,0.000101311096,0.00025345976],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00073059695,0.00021733847,0.00034666993,0.000252065,0.00017229338,0.00021717022,0.00004157742,0.00006108568,0.00023449647],"category_scores_gemma":[0.0004253983,0.00016533921,0.000047168982,0.00032205027,0.00026649598,0.00027441944,0.0001344087,0.00039630753,0.000006043876],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036145814,0.00018010811,0.5231267,0.0007326394,0.00056592113,0.0009996934,0.0010390239,0.000042750573,0.025851611,0.00047528767,0.00017738524,0.44644737],"study_design_scores_gemma":[0.010666682,0.0064174198,0.5680557,0.008912902,0.0022073009,0.0017378088,0.006105671,0.34593308,0.002536932,0.00029484998,0.046035897,0.0010957717],"about_ca_topic_score_codex":0.00007676212,"about_ca_topic_score_gemma":0.0000025009667,"teacher_disagreement_score":0.4453516,"about_ca_system_score_codex":0.00003863468,"about_ca_system_score_gemma":0.00005969389,"threshold_uncertainty_score":0.67423373},"labels":[],"label_agreement":null},{"id":"W4401855443","doi":"10.1038/s41746-024-01228-z","title":"Health equity through CMS collaboration with startups and digital health innovations","year":2024,"lang":"en","type":"editorial","venue":"npj Digital Medicine","topic":"Mobile Health and mHealth Applications","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Medicaid; Telehealth; Business; Equity (law); Health equity; Health care; Health technology; Digital health; Marketing; Public relations; Telemedicine; Economic growth; Political science; Economics","score_opus":0.04408853589757177,"score_gpt":0.47102326490736673,"score_spread":0.42693472900979496,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401855443","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00018347931,0.014669744,0.0031811025,0.24701643,0.63851964,0.016141653,0.01645979,0.00129142,0.06253675],"genre_scores_gemma":[0.01404305,0.011357607,0.00063596,0.016948447,0.8787533,0.009686243,0.05134391,0.00047815745,0.016753335],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9919125,0.00022092182,0.0028371366,0.0013939968,0.0018447638,0.0017907236],"domain_scores_gemma":[0.99205464,0.0023772118,0.0017628982,0.0009952937,0.0014410947,0.0013688613],"candidate_categories":["metaepi_narrow","sts","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0016146725,0.00080112636,0.0018346665,0.0004643526,0.0017965474,0.00021922671,0.00038284008,0.0009613218,0.000109149136],"category_scores_gemma":[0.0022909709,0.0006061577,0.000055341512,0.002181967,0.00054926507,0.001038947,0.00039196707,0.0035836236,0.0002646541],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012952166,0.00009660552,0.00012842732,0.006750604,0.000050896695,0.000005142642,0.002488534,5.808278e-7,2.2330593e-7,0.012325452,0.92667925,0.05134477],"study_design_scores_gemma":[0.0019984662,0.0021389925,0.000096043645,0.0051704952,0.000036453264,0.0000058148257,0.0029001585,0.0000133328285,6.259078e-8,0.005942965,0.9813072,0.00039003318],"about_ca_topic_score_codex":0.0011399148,"about_ca_topic_score_gemma":0.0016771798,"teacher_disagreement_score":0.24023366,"about_ca_system_score_codex":0.0019355969,"about_ca_system_score_gemma":0.021846198,"threshold_uncertainty_score":0.999639},"labels":[],"label_agreement":null},{"id":"W4402166628","doi":"10.1038/s41746-024-01225-2","title":"Development, deployment and scaling of operating room-ready artificial intelligence for real-time surgical decision support","year":2024,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Surgical Simulation and Training","field":"Medicine","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; Artificial Intelligence in Medicine (Canada); University of Toronto; University Health Network","funders":"University Health Network Foundation; Canadian Institute for Advanced Research","keywords":"Software deployment; Computer science; Scaling; Decision support system; Systems engineering; Artificial intelligence; Engineering; Operating system; Mathematics","score_opus":0.07551280644362011,"score_gpt":0.3691073329543519,"score_spread":0.29359452651073176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402166628","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9665359,0.00026667645,0.010649044,0.00056602457,0.0002569593,0.00051261403,0.000014199653,0.00016416033,0.02103439],"genre_scores_gemma":[0.99542606,0.000027540524,0.0037086292,0.00005900165,0.00027006544,0.000013800184,0.00013188504,0.00002560402,0.0003373983],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983815,0.000008401424,0.0007038979,0.0003111621,0.00037664996,0.0002183844],"domain_scores_gemma":[0.99851644,0.0010096501,0.000050283317,0.00010387835,0.00010739628,0.00021235023],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000512526,0.0001536431,0.00038727652,0.0001399313,0.000060642476,0.000049801747,0.000046653746,0.00007448735,0.0003214393],"category_scores_gemma":[0.0005123949,0.00010677398,0.00005127328,0.00021397881,0.00009940173,0.00013415067,0.00004014799,0.00010448835,0.000029065279],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002916576,0.00007531794,0.00054941385,0.00014505167,0.00005777982,0.00012946712,0.0008483675,0.000031660515,0.0012519765,0.0038535402,0.000078013865,0.99268776],"study_design_scores_gemma":[0.015832454,0.007913685,0.009754867,0.019789338,0.0009454737,0.001854092,0.0077653457,0.37330356,0.044293225,0.011624083,0.5047042,0.0022196888],"about_ca_topic_score_codex":0.000004451083,"about_ca_topic_score_gemma":0.0000010901658,"teacher_disagreement_score":0.9904681,"about_ca_system_score_codex":0.00003985123,"about_ca_system_score_gemma":0.000098051845,"threshold_uncertainty_score":0.43541166},"labels":[],"label_agreement":null},{"id":"W4402233200","doi":"10.1038/s41746-026-02642-1","title":"Predicting Clinically Significant Prostate Cancer with or Without Digital Rectal Exam and MRI Data Using Claritydx Prostate Models","year":2024,"lang":"en","type":"preprint","venue":"npj Digital Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Alberta Innovates; Prostate Cancer Canada; Alberta Cancer Foundation; Movember Foundation","keywords":"Prostate cancer; Prostate; Rectal examination; Medicine; Radiology; Oncology; Urology; Internal medicine; Cancer","score_opus":0.07383024008731685,"score_gpt":0.3753172845287043,"score_spread":0.3014870444413874,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402233200","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96624464,0.0031509353,0.0036555785,0.011015602,0.0014926065,0.0035663343,0.0017436426,0.0007328684,0.008397766],"genre_scores_gemma":[0.987027,0.001511263,0.0037255818,0.0007640245,0.0021649033,0.00010185327,0.0017623162,0.00032409423,0.002618998],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9934632,0.00007187092,0.0016555504,0.0023882452,0.0014869208,0.0009342143],"domain_scores_gemma":[0.99592257,0.00046877874,0.00067833107,0.0015751014,0.00035296398,0.0010022692],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0012965892,0.0009931249,0.001996445,0.00036655454,0.00017192785,0.0008542962,0.0006607985,0.00046429053,0.00003926104],"category_scores_gemma":[0.0018719994,0.0006106914,0.00011539844,0.00042734866,0.0014332016,0.0008134874,0.0029962035,0.0044537256,0.0000064918513],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.011592687,0.0009566609,0.5491542,0.015235998,0.0041336236,0.0072650653,0.010386713,0.0048907963,0.0006549842,0.00015181764,0.0061209025,0.3894565],"study_design_scores_gemma":[0.0059555937,0.0026242794,0.001404456,0.030290289,0.0022876712,0.0015147906,0.0013525101,0.9466511,0.0000129871905,0.0031681499,0.0035097583,0.0012284237],"about_ca_topic_score_codex":0.000604934,"about_ca_topic_score_gemma":0.000021125716,"teacher_disagreement_score":0.9417603,"about_ca_system_score_codex":0.00023116067,"about_ca_system_score_gemma":0.0017596049,"threshold_uncertainty_score":0.99963444},"labels":[],"label_agreement":null},{"id":"W4402453991","doi":"10.1038/s41746-024-01242-1","title":"Ethical debates amidst flawed healthcare artificial intelligence metrics","year":2024,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Institute on Minority Health and Health Disparities; National Institute of Biomedical Imaging and Bioengineering; Fogarty International Center; Gordon and Betty Moore Foundation; National Heart, Lung, and Blood Institute; Radiological Society of North America; National Cancer Institute; National Institutes of Health; National Science Foundation","keywords":"Health care; Engineering ethics; Psychology; Political science; Sociology; Artificial intelligence; Computer science; Engineering; Law","score_opus":0.25008066517707944,"score_gpt":0.4727379784701678,"score_spread":0.22265731329308835,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402453991","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2888414,0.018002043,0.034602243,0.6161785,0.011581572,0.0019931344,0.00006959337,0.0020161767,0.02671537],"genre_scores_gemma":[0.9905593,0.0004510373,0.00022255878,0.004611595,0.002955832,0.000040711842,0.00018407438,0.000053371357,0.00092156854],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9969593,0.000053755768,0.0010182294,0.0006033927,0.0007986496,0.0005666313],"domain_scores_gemma":[0.9973114,0.0011551952,0.00007359081,0.00040999922,0.000449642,0.00060014107],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007376173,0.00028719724,0.0004956929,0.00056687044,0.00015394618,0.00014630571,0.00016831707,0.00046442897,0.0005024642],"category_scores_gemma":[0.0036335427,0.00021778549,0.00013089339,0.0017861732,0.0004765055,0.00025763392,0.00004735833,0.0013378371,0.0010142347],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015631445,0.00012761651,0.0012405278,0.0007771477,0.000057405316,0.00020105981,0.0028467462,0.0000041258904,0.00038164255,0.05424939,0.007216171,0.9327419],"study_design_scores_gemma":[0.0002249524,0.012402946,0.0039657694,0.011721155,0.00080698007,0.0019354984,0.040314674,0.036352698,0.054560512,0.4901715,0.34537178,0.0021715418],"about_ca_topic_score_codex":0.0005351945,"about_ca_topic_score_gemma":0.00008610946,"teacher_disagreement_score":0.9305703,"about_ca_system_score_codex":0.00034557987,"about_ca_system_score_gemma":0.0005345308,"threshold_uncertainty_score":0.9997636},"labels":[],"label_agreement":null},{"id":"W4402582069","doi":"10.1038/s41746-024-01256-9","title":"The case for inclusive co-creation in digital health innovation","year":2024,"lang":"en","type":"editorial","venue":"npj Digital Medicine","topic":"Innovative Approaches in Technology and Social Development","field":"Business, Management and Accounting","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"University of Toronto","keywords":"Business; Co-creation; Knowledge management; Process management; Computer science; Marketing","score_opus":0.015882450004220353,"score_gpt":0.3250365110031917,"score_spread":0.30915406099897136,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402582069","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002553821,0.0007367313,0.0014021402,0.026324568,0.83065087,0.002950865,0.0003738635,0.00048712804,0.13452004],"genre_scores_gemma":[0.22011249,0.000049559738,0.000030916024,0.0011088719,0.7640675,0.00047265677,0.010288553,0.00010454056,0.003764911],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978275,0.0000051767006,0.0008766036,0.0004379684,0.00045917716,0.0003936196],"domain_scores_gemma":[0.9977843,0.00064445665,0.00055787433,0.0002168112,0.00078840915,0.000008140638],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012910711,0.0003302174,0.00045443414,0.0007556511,0.0004767518,0.00054897595,0.00031282936,0.000518967,0.0000061111264],"category_scores_gemma":[0.0066816877,0.00023180916,0.00004721581,0.0018430802,0.00043463355,0.0009186352,0.00028498174,0.00079871493,0.000057515797],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004693595,0.000027019363,0.00003394605,0.0003671826,0.00004389959,0.0000782294,0.00020462224,1.8265095e-7,2.8494253e-7,0.138811,0.754894,0.1054927],"study_design_scores_gemma":[0.00060362276,0.000055280605,0.000012027622,0.0003864412,0.0000147067285,0.000006206807,0.001572998,0.000058639383,9.471316e-7,0.1070641,0.89002,0.00020502125],"about_ca_topic_score_codex":0.00010134262,"about_ca_topic_score_gemma":0.00009342029,"teacher_disagreement_score":0.21755867,"about_ca_system_score_codex":0.00046142036,"about_ca_system_score_gemma":0.00031066756,"threshold_uncertainty_score":0.9452903},"labels":[],"label_agreement":null},{"id":"W4403064496","doi":"10.1038/s41746-024-01260-z","title":"Improving prognostic accuracy in lung transplantation using unique features of isolated human lung radiographs","year":2024,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Transplantation: Methods and Outcomes","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; Toronto General Hospital; Toronto Rehabilitation Institute; University of Toronto; University Health Network","funders":"University of Toronto; University Health Network Foundation; University Health Network","keywords":"Lung; Lung transplantation; Radiography; Medicine; Human lung; Transplantation; Radiology; Pathology; Internal medicine","score_opus":0.020561822596634978,"score_gpt":0.34804593960709107,"score_spread":0.3274841170104561,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403064496","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96086544,0.004372743,0.03063469,0.0005256749,0.00032486612,0.0008970463,0.00006440998,0.00018613166,0.0021290137],"genre_scores_gemma":[0.9971494,0.00022380307,0.0018931996,0.00008855134,0.00016103205,0.000013195028,0.00034195703,0.00004017503,0.000088677276],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99844754,0.000052078885,0.0005913264,0.0003168344,0.00032780835,0.00026441817],"domain_scores_gemma":[0.9989311,0.00061179156,0.000097129174,0.00016669453,0.000076885524,0.00011638514],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030229974,0.00022747798,0.00048307946,0.0006951161,0.000044869164,0.000041606494,0.00008439975,0.00012742999,0.000034669385],"category_scores_gemma":[0.00022917558,0.00017099257,0.00011350639,0.00087217166,0.00013341877,0.0004226072,0.000007904954,0.00034072902,5.649635e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011548222,0.00030746823,0.47154313,0.021173036,0.00057244784,0.0029896009,0.012950325,0.00010007894,0.39854223,0.0048903255,0.00029030224,0.08548625],"study_design_scores_gemma":[0.009631498,0.0018054572,0.91318727,0.02605445,0.0027690893,0.0023809425,0.0013443755,0.025053145,0.015524891,0.0012221469,0.00018545403,0.00084128155],"about_ca_topic_score_codex":0.0003871021,"about_ca_topic_score_gemma":0.000041402436,"teacher_disagreement_score":0.44164413,"about_ca_system_score_codex":0.000067747664,"about_ca_system_score_gemma":0.000098361495,"threshold_uncertainty_score":0.69728744},"labels":[],"label_agreement":null},{"id":"W4403122659","doi":"10.1038/s41746-024-01267-6","title":"Enabling data linkages for rare diseases in a resilient environment with the SERDIF framework","year":2024,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Trinity College","funders":"Trinity College Dublin; European Commission","keywords":"Usability; Linkage (software); Disease; Climate change; Data science; Environmental health; Medicine; Computer science; Risk analysis (engineering); Environmental resource management; Ecology; Biology; Pathology","score_opus":0.025218402084422484,"score_gpt":0.29574027527185065,"score_spread":0.27052187318742815,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403122659","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6067375,0.17577316,0.111643575,0.09681786,0.0011969409,0.0020304471,0.0018051245,0.0002618005,0.0037336152],"genre_scores_gemma":[0.99674994,0.00038962706,0.00053942204,0.00043068052,0.0005891361,0.000046242465,0.000632831,0.000017008528,0.00060513616],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991162,0.000014040214,0.00013260594,0.00038433928,0.00015951738,0.00019333113],"domain_scores_gemma":[0.99922055,0.00019471,0.000022284928,0.00048644084,0.000009148603,0.00006685553],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013518018,0.000119675504,0.00012996096,0.000030423793,0.000040635405,0.000042913674,0.00030990026,0.0000933159,0.000012296916],"category_scores_gemma":[0.00048518655,0.000060428756,0.000024484862,0.00008256939,0.00029413268,0.0000062078175,0.00018519332,0.00011785497,0.0000041509293],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00049249135,0.0002582469,0.006548372,0.00053552864,0.00033136946,0.0001902137,0.00096407527,0.000092871625,0.0038372043,0.000912963,0.11888741,0.86694926],"study_design_scores_gemma":[0.00050446956,0.0009654799,0.0019557623,0.0005910291,0.00005202955,0.000016657383,0.0013512411,0.00030071725,0.00037721256,0.0009192368,0.9928022,0.00016394777],"about_ca_topic_score_codex":0.0000037951015,"about_ca_topic_score_gemma":0.0000051181732,"teacher_disagreement_score":0.8739148,"about_ca_system_score_codex":0.0000101517,"about_ca_system_score_gemma":0.00003933834,"threshold_uncertainty_score":0.24642132},"labels":[],"label_agreement":null},{"id":"W4404476148","doi":"10.1038/s41746-024-01307-1","title":"Developing a Canadian artificial intelligence medical curriculum using a Delphi study","year":2024,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of British Columbia; University of British Columbia Hospital","funders":"Institute for Computing, Information and Cognitive Systems; Faculty of Medicine, University of British Columbia","keywords":"Curriculum; Delphi method; Medical education; Health care; Inclusion (mineral); Delphi; Set (abstract data type); Quality (philosophy); Knowledge management; Psychology; Computer science; Medicine; Artificial intelligence; Pedagogy; Political science","score_opus":0.314231560469973,"score_gpt":0.4896748324992941,"score_spread":0.17544327202932108,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404476148","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94894975,0.0011453179,0.011798087,0.030012252,0.003080901,0.00096944754,0.0000072569787,0.00022744996,0.003809507],"genre_scores_gemma":[0.9958862,0.000046517307,0.00026456895,0.0012569206,0.002323798,0.000033284698,0.000044744855,0.000040468847,0.00010346889],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.99705917,0.00003843056,0.0008962497,0.000519118,0.00088972476,0.0005973242],"domain_scores_gemma":[0.99811906,0.00023794794,0.00005013337,0.00028866593,0.00029724854,0.0010069737],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000721694,0.00024940836,0.00039576678,0.0006135348,0.00019090643,0.00012734307,0.00018441238,0.00018578926,0.00082943216],"category_scores_gemma":[0.0023063347,0.00019304182,0.00007096959,0.0012239212,0.00023225971,0.00030101312,0.000043783846,0.00052221084,0.000386932],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000045205128,0.0003532298,0.018798556,0.00031686353,0.00013451272,0.0019503155,0.010896309,0.000009864228,0.000052616237,0.014079321,0.0013703365,0.95199287],"study_design_scores_gemma":[0.00045861525,0.011104432,0.008138313,0.028214743,0.0015505452,0.008776537,0.45717448,0.25514403,0.0028053895,0.115778096,0.10716539,0.003689439],"about_ca_topic_score_codex":0.07590092,"about_ca_topic_score_gemma":0.03307601,"teacher_disagreement_score":0.9483034,"about_ca_system_score_codex":0.00073742575,"about_ca_system_score_gemma":0.003629045,"threshold_uncertainty_score":0.9845678},"labels":[],"label_agreement":null},{"id":"W4404696354","doi":"10.1038/s41746-024-01345-9","title":"Artificial Intelligence awarded two Nobel Prizes for innovations that will shape the future of medicine","year":2024,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Jumper; Artificial intelligence; Artificial neural network; Cognitive science; Engineering ethics; Engineering; Computer science; Psychology; Electrical engineering","score_opus":0.0652511274822534,"score_gpt":0.36656296636532837,"score_spread":0.301311838883075,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404696354","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005277086,0.0016115574,0.89888555,0.088302664,0.0026171228,0.00047108383,0.000032060325,0.00015355357,0.0026493135],"genre_scores_gemma":[0.9872254,0.00003260148,0.009376115,0.0009919073,0.0020944702,0.000049286857,0.000049221802,0.000019663099,0.0001612918],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99799144,0.0000522981,0.0005904767,0.00043347167,0.0006862087,0.00024608427],"domain_scores_gemma":[0.99673647,0.0022856288,0.00013552155,0.00045708657,0.00031047195,0.00007483868],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00092777883,0.0002081179,0.00031807067,0.00027405366,0.000107507934,0.0001222112,0.00090102764,0.000048983664,0.000045978148],"category_scores_gemma":[0.0007478418,0.00012070978,0.000079786216,0.0015386089,0.00053811463,0.00090917916,0.00020280776,0.00020428035,0.00001008974],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012156952,0.00002249433,0.00001411969,0.000051005005,0.000029987968,0.000003826185,0.0010449712,0.00031842978,0.00025320135,0.53611976,0.0019358833,0.46019414],"study_design_scores_gemma":[0.00022539841,0.00045462255,0.0004271946,0.0004718871,0.00003759836,0.000044318993,0.00074277306,0.3199525,0.0010070887,0.6253915,0.05104327,0.00020189269],"about_ca_topic_score_codex":0.000008901748,"about_ca_topic_score_gemma":0.0000064235232,"teacher_disagreement_score":0.9819484,"about_ca_system_score_codex":0.000043655727,"about_ca_system_score_gemma":0.00018164149,"threshold_uncertainty_score":0.49224022},"labels":[],"label_agreement":null},{"id":"W4405031321","doi":"10.1038/s41746-024-01361-9","title":"A scoping review on pediatric sepsis prediction technologies in healthcare","year":2024,"lang":"en","type":"review","venue":"npj Digital Medicine","topic":"Sepsis Diagnosis and Treatment","field":"Medicine","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; BC Children's Hospital; University of Waterloo","funders":"University of Waterloo","keywords":"Workflow; Logistic regression; Health care; Computer science; Medicine; Data science; Artificial intelligence; Machine learning","score_opus":0.19054823675272647,"score_gpt":0.455148064014945,"score_spread":0.26459982726221853,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405031321","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000006867714,0.9798178,4.716289e-7,0.011300594,0.0006245416,0.005007011,0.00013197474,0.0005767835,0.0025339723],"genre_scores_gemma":[0.00020347735,0.9957712,0.000011349698,0.0007448452,0.0006017036,0.0016293612,0.0007289169,0.0001067581,0.0002023489],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.99639416,0.00005303691,0.0014596962,0.0009348035,0.00069635955,0.00046193952],"domain_scores_gemma":[0.998284,0.00038620466,0.00032353756,0.0007536153,0.00007702101,0.00017565709],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002919691,0.0007418007,0.003726778,0.0012004595,0.00003678233,0.00003480131,0.0001814536,0.00047361403,0.000050292092],"category_scores_gemma":[0.0011891414,0.00043181115,0.00050343253,0.0019124199,0.00009675913,0.00010070397,0.00010781137,0.0009541812,0.00046339125],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000042143033,0.00014774127,0.00031564283,0.36334026,0.00009470727,0.00033877752,0.000009252553,1.3292033e-8,2.3008238e-9,0.000053784992,0.010600331,0.6250953],"study_design_scores_gemma":[0.00040986892,0.0011692895,0.000027959128,0.73919463,0.0032746822,0.00016121988,0.00002257511,3.9344658e-7,9.5160836e-8,0.00005911534,0.25548646,0.000193729],"about_ca_topic_score_codex":0.000018170911,"about_ca_topic_score_gemma":0.000007168546,"teacher_disagreement_score":0.62490153,"about_ca_system_score_codex":0.00068664964,"about_ca_system_score_gemma":0.0004919714,"threshold_uncertainty_score":0.9998134},"labels":[],"label_agreement":null},{"id":"W4405591076","doi":"10.1038/s41746-024-01363-7","title":"Optimising the paradigms of human AI collaborative clinical coding","year":2024,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"School of Medicine, Shanghai Jiao Tong University; Medical Research Foundation; Medical Research Council; National Science and Technology Major Project; Research Councils UK; National Natural Science Foundation of China; Shanghai Jiao Tong University; Tsinghua University; Department of Health and Social Care; National Institute for Health and Care Research; Canadian Institute of Steel Construction","keywords":"Coding (social sciences); Computer science; Annotation; Artificial intelligence; Machine learning; Statistics","score_opus":0.052127027441961106,"score_gpt":0.4289087960182908,"score_spread":0.37678176857632967,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405591076","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1744887,0.0092108855,0.34114984,0.26021415,0.0082193855,0.0015743683,0.00004940177,0.0014809541,0.20361233],"genre_scores_gemma":[0.9975146,0.00002601513,0.0007089489,0.0008274087,0.00047195144,0.0000056462504,0.0000060166994,0.000012237238,0.00042716952],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982362,0.00013151928,0.0005601015,0.0003529507,0.00047239877,0.00024685997],"domain_scores_gemma":[0.99789745,0.0012283826,0.00011187007,0.00047970444,0.00016320481,0.00011942053],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011187207,0.00013018031,0.00028679435,0.00010654562,0.00014111199,0.00021541669,0.00070419733,0.00006294097,0.000022884227],"category_scores_gemma":[0.00091368676,0.000076883785,0.000057881032,0.0008824961,0.00034206378,0.0004570253,0.00021421717,0.00051119865,0.000020825348],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012880019,0.000057819023,0.011076126,0.00029428143,0.00008886829,0.00014644234,0.0084225265,0.00019759405,0.00015504373,0.71458703,0.019795908,0.2451655],"study_design_scores_gemma":[0.0029124003,0.008613407,0.044561587,0.008723189,0.00013363085,0.0003613626,0.0031662327,0.5418813,0.00063391856,0.069843315,0.31784624,0.0013234116],"about_ca_topic_score_codex":0.000032056785,"about_ca_topic_score_gemma":0.0000040282303,"teacher_disagreement_score":0.82302594,"about_ca_system_score_codex":0.000034715533,"about_ca_system_score_gemma":0.00015073342,"threshold_uncertainty_score":0.31352296},"labels":[],"label_agreement":null},{"id":"W4405597099","doi":"10.1038/s41746-024-01366-4","title":"Probabilistic medical predictions of large language models","year":2024,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Topic Modeling","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"National Institutes of Health","keywords":"Probabilistic logic; Computer science; Artificial intelligence","score_opus":0.019218859412394984,"score_gpt":0.2821147625464776,"score_spread":0.2628959031340826,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405597099","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012907809,0.0013191059,0.94212043,0.003946608,0.00074064254,0.00013593477,0.000019469928,0.0003952871,0.03841471],"genre_scores_gemma":[0.9979385,0.000012719467,0.0009106128,0.00017194678,0.00029677484,0.0000115155235,0.000010153359,0.000009253104,0.0006385271],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984635,0.000014493577,0.00032027243,0.00030586528,0.0006841146,0.00021177206],"domain_scores_gemma":[0.9991649,0.00017977768,0.000028348572,0.00041580858,0.000050031187,0.00016117332],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030865526,0.000102147984,0.00018097172,0.00012223728,0.000026003507,0.00005010047,0.00050067296,0.0000667491,0.00008837994],"category_scores_gemma":[0.00043422423,0.00007358271,0.000044899312,0.00034699327,0.00009407267,0.00059695577,0.00018805836,0.00017437975,0.00002428624],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000032362302,0.00011946496,0.00004791218,0.00029796798,0.000046487443,0.00020891374,0.0055751516,0.0008564747,0.00008890382,0.8913528,0.004084505,0.09731824],"study_design_scores_gemma":[0.00023515946,0.000101863094,0.000031274332,0.000473412,0.000009871455,0.000060833623,0.0001250383,0.9677889,0.00002200688,0.02859833,0.0024772922,0.000076054734],"about_ca_topic_score_codex":0.000016213107,"about_ca_topic_score_gemma":0.000005166288,"teacher_disagreement_score":0.9850307,"about_ca_system_score_codex":0.000030534236,"about_ca_system_score_gemma":0.00013584012,"threshold_uncertainty_score":0.30006158},"labels":[],"label_agreement":null},{"id":"W4405695590","doi":"10.1038/s41746-024-01385-1","title":"An umbrella review on how digital health intervention co-design is conducted and described","year":2024,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Digital Mental Health Interventions","field":"Psychology","cited_by":62,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; Institute for Clinical Evaluative Sciences; SickKids Foundation; Hospital for Sick Children; University of Toronto","funders":"University of Toronto","keywords":"Intervention (counseling); Psychological intervention; Digital health; Research design; Health professionals; Co-design; Quality (philosophy); Medicine; Health care; Psychology; Medical education; Nursing; Computer science; Political science","score_opus":0.14209368746427375,"score_gpt":0.46352098447834517,"score_spread":0.3214272970140714,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405695590","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07840055,0.32170454,0.012904193,0.271464,0.013164193,0.009338738,0.004370354,0.0031758614,0.28547758],"genre_scores_gemma":[0.98219824,0.0005007443,0.00003177951,0.005463691,0.00025045325,0.00009992508,0.00066265767,0.00007649183,0.010716011],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99730587,0.00015371629,0.00079964224,0.00077552715,0.00043363852,0.00053162087],"domain_scores_gemma":[0.99838674,0.00027542282,0.00018900669,0.0005146448,0.00007626083,0.0005579246],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00057821703,0.00036687768,0.00059068366,0.00027819112,0.00008990036,0.0004438337,0.0002376302,0.00010584682,0.0008224443],"category_scores_gemma":[0.00020991151,0.00029512518,0.00015528733,0.00043288548,0.00032119677,0.0011989897,0.000042827254,0.00035599628,0.0008713328],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000119605,0.00067661214,0.00006263686,0.0033076208,0.00012869766,0.00010199921,0.0006449325,5.310749e-8,0.000017143626,0.008972793,0.30542007,0.68054783],"study_design_scores_gemma":[0.007815399,0.066242956,0.0038700874,0.17499697,0.00029397086,0.0020522366,0.00429258,0.00028385242,0.0003497495,0.025736991,0.7120918,0.0019733899],"about_ca_topic_score_codex":0.000036068526,"about_ca_topic_score_gemma":0.0000024449505,"teacher_disagreement_score":0.9037977,"about_ca_system_score_codex":0.00018386898,"about_ca_system_score_gemma":0.000058506328,"threshold_uncertainty_score":0.9999501},"labels":[],"label_agreement":null},{"id":"W4406037243","doi":"10.1038/s41746-024-01398-w","title":"Author Correction: Developing a Canadian artificial intelligence medical curriculum using a Delphi study","year":2025,"lang":"en","type":"erratum","venue":"npj Digital Medicine","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of British Columbia; University of British Columbia Hospital","funders":"","keywords":"Delphi; Delphi method; Curriculum; Computer science; Artificial intelligence; Medical education; Mathematics education; Psychology; Medicine; Pedagogy; Programming language","score_opus":0.2208876709590539,"score_gpt":0.46627068401900473,"score_spread":0.24538301305995083,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406037243","genre_codex":"editorial","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04043663,0.005808456,0.023541577,0.15601078,0.58451706,0.009701921,0.00013506485,0.0009420072,0.1789065],"genre_scores_gemma":[0.8288173,0.00034221727,0.0003334839,0.0057818675,0.03014404,0.00025238798,0.0018730186,0.00018475254,0.1322709],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9940387,0.00011430165,0.0020010492,0.0010616557,0.0017604725,0.0010238424],"domain_scores_gemma":[0.99573594,0.00036551975,0.00036788848,0.0007358144,0.0012667615,0.0015280772],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0010345739,0.00067990174,0.001309646,0.0014806483,0.0005078229,0.00014323875,0.0004736406,0.0012104112,0.0011950857],"category_scores_gemma":[0.010823562,0.000584923,0.00017697533,0.0020302928,0.00040415995,0.00023842162,0.00012558918,0.0025453889,0.00018850557],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000660347,0.00043268036,0.0027797022,0.00043075508,0.00019086631,0.0006285313,0.0032695348,0.0000044405597,7.6492734e-7,0.00040916548,0.6498511,0.34193647],"study_design_scores_gemma":[0.0001954185,0.0036932265,0.0010383866,0.027424008,0.001406966,0.0014431685,0.10374618,0.026358109,0.00006432949,0.0048786714,0.82782483,0.0019266837],"about_ca_topic_score_codex":0.18306135,"about_ca_topic_score_gemma":0.15342595,"teacher_disagreement_score":0.7883807,"about_ca_system_score_codex":0.0021347944,"about_ca_system_score_gemma":0.01872183,"threshold_uncertainty_score":0.9997558},"labels":[],"label_agreement":null},{"id":"W4407000772","doi":"10.1038/s41746-025-01474-9","title":"Telemedicine expands cardiovascular care in China – lessons for health equity in the United States","year":2025,"lang":"en","type":"editorial","venue":"npj Digital Medicine","topic":"Cardiovascular Health and Risk Factors","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Telemedicine; Equity (law); China; Health care; Business; Health equity; Economic growth; Medicine; Political science; Economics","score_opus":0.023122960907684138,"score_gpt":0.38212931064935307,"score_spread":0.35900634974166895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407000772","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0069878176,0.17351753,0.001248225,0.057692092,0.72864527,0.015225761,0.004674215,0.0003518367,0.011657239],"genre_scores_gemma":[0.16418578,0.047717445,0.00006553914,0.003915904,0.70221704,0.0012190774,0.0794302,0.00025335935,0.0009956171],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99275374,0.00030287582,0.0016075746,0.0011053391,0.0028689501,0.0013615417],"domain_scores_gemma":[0.99522424,0.0017872907,0.00030294593,0.0016547616,0.00051643595,0.00051432184],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0036167847,0.00083751767,0.0035329713,0.0016486106,0.00018323398,0.000057124777,0.0006183014,0.0009278419,0.000013255271],"category_scores_gemma":[0.0058861184,0.00051589846,0.0010325267,0.0020810496,0.00036668926,0.00011738587,0.00018815402,0.002482017,0.000003323876],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008155371,0.00018494595,0.00050942035,0.007743495,0.00064083026,0.0002679644,0.0061784126,0.00010413635,2.6216992e-7,0.00003725741,0.8883079,0.09520982],"study_design_scores_gemma":[0.013222151,0.0021081876,0.004637072,0.006482762,0.0006052177,0.000028175618,0.005980641,0.000037398535,0.0000012241178,0.0001163747,0.96640724,0.00037353358],"about_ca_topic_score_codex":0.008298679,"about_ca_topic_score_gemma":0.0014324688,"teacher_disagreement_score":0.15719797,"about_ca_system_score_codex":0.0015202067,"about_ca_system_score_gemma":0.003292413,"threshold_uncertainty_score":0.9998193},"labels":[],"label_agreement":null},{"id":"W4407009455","doi":"10.1038/s41746-025-01457-w","title":"Language models for data extraction and risk of bias assessment in complementary medicine","year":2025,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Complementary and Alternative Medicine Studies","field":"Medicine","cited_by":35,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Impact","funders":"Fundamental Research Funds for the Central Universities; China Academy of Chinese Medical Sciences; National Natural Science Foundation of China","keywords":"Computer science; Data extraction; Extraction (chemistry); Data science; Natural language processing; MEDLINE; Chemistry; Chromatography","score_opus":0.16032370427290943,"score_gpt":0.4542686677577073,"score_spread":0.29394496348479787,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407009455","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9241746,0.0044995407,0.027190853,0.012603698,0.0005746676,0.0017740029,0.00062539295,0.000048561797,0.028508686],"genre_scores_gemma":[0.9951743,0.001084248,0.0011986241,0.00038287012,0.0003401184,0.000034643534,0.0013180763,0.000012915798,0.0004542347],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99821454,0.000044486787,0.00071815273,0.0004284694,0.00036536326,0.00022896603],"domain_scores_gemma":[0.9979385,0.0011630161,0.00020798475,0.000488931,0.00011317797,0.00008838852],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008163649,0.0002159487,0.00074819825,0.00038455863,0.000063709245,0.0000051771017,0.00017733689,0.000018337249,0.000111432935],"category_scores_gemma":[0.00085556146,0.00014762736,0.00003326596,0.00029801182,0.00040489982,0.0002858298,0.00023296445,0.00022490499,3.1694236e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008784794,0.00052439026,0.61692274,0.0011918277,0.0009888607,0.000060887025,0.0028699713,0.000014074531,0.0019245193,0.0062703383,0.017737713,0.3506162],"study_design_scores_gemma":[0.05589871,0.009952252,0.7138602,0.009982394,0.0028771001,0.00008472643,0.07511319,0.05155041,0.0005845592,0.02113412,0.058353096,0.0006092389],"about_ca_topic_score_codex":0.0013019609,"about_ca_topic_score_gemma":0.00034020797,"teacher_disagreement_score":0.35000697,"about_ca_system_score_codex":0.00006854334,"about_ca_system_score_gemma":0.00005863042,"threshold_uncertainty_score":0.6020069},"labels":[],"label_agreement":null},{"id":"W4407084498","doi":"10.1038/s41746-024-01408-x","title":"The early warning paradox","year":2025,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"South London and Maudsley NHS Foundation Trust; Dalhousie University; King's College London; Faculty of Medicine, Dalhousie University; National Institute for Health and Care Research; University College London","keywords":"Warning system; Computer science; Health care; Artificial intelligence; Data science; Political science","score_opus":0.009609612946296298,"score_gpt":0.2926380783571856,"score_spread":0.2830284654108893,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407084498","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08601798,0.0038535497,0.26126286,0.22117507,0.004377985,0.0005775149,0.0000020045113,0.0010974982,0.42163554],"genre_scores_gemma":[0.99191564,0.000018325183,0.00041219644,0.0012023315,0.0001612237,0.0000129607515,0.0000017707063,0.0000060271427,0.006269538],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99877834,0.000053198306,0.00026051444,0.00027543944,0.00032787342,0.00030465896],"domain_scores_gemma":[0.9983284,0.0008081129,0.000072468116,0.00061727356,0.000082665494,0.00009109137],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036231912,0.00011530883,0.00014845715,0.000080458565,0.00030177954,0.00021351675,0.0009832081,0.000041946456,0.0000062829213],"category_scores_gemma":[0.0012786175,0.000068210866,0.000032112046,0.00053512247,0.00013284365,0.0003015019,0.0002539258,0.00033609287,0.00006964063],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000076249453,0.0000106754505,0.03343753,0.000028779126,0.000016072849,0.000019910885,0.00091696373,0.000023771041,0.000011483812,0.23059185,0.0077364394,0.7271989],"study_design_scores_gemma":[0.00088676455,0.0005372632,0.18791959,0.00054377096,0.000009718676,0.00003096475,0.00021493073,0.02478733,0.000033639804,0.048022144,0.7367384,0.00027551822],"about_ca_topic_score_codex":0.00007421609,"about_ca_topic_score_gemma":0.000005130439,"teacher_disagreement_score":0.9058976,"about_ca_system_score_codex":0.00003757202,"about_ca_system_score_gemma":0.00007295149,"threshold_uncertainty_score":0.27815583},"labels":[],"label_agreement":null},{"id":"W4407152308","doi":"10.1038/s41746-025-01490-9","title":"An institutional framework to support ethical fair and equitable artificial intelligence augmented care","year":2025,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Health Services; Libin Cardiovascular Institute of Alberta; University of Calgary","funders":"Alberta Innovates","keywords":"Assisted living; Ethical issues; Sociology; Psychology; Political science; Engineering ethics; Business; Nursing; Medicine; Engineering","score_opus":0.1355132359718842,"score_gpt":0.476926062226695,"score_spread":0.3414128262548108,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407152308","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7424196,0.00063657586,0.14980915,0.076315716,0.002557221,0.0013087862,0.00004084091,0.00025490436,0.026657218],"genre_scores_gemma":[0.98819953,0.00003270906,0.0011146802,0.009349953,0.00075333886,0.000049935406,0.00019208247,0.0000134830925,0.00029430434],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980472,0.000027341743,0.00061184,0.0004664713,0.0004215999,0.00042559585],"domain_scores_gemma":[0.99838996,0.0002801532,0.0000500016,0.000353997,0.0004308342,0.0004950792],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003337105,0.00019419362,0.00034323864,0.0002915134,0.00025189648,0.00007081138,0.0001401551,0.00034202373,0.00030096847],"category_scores_gemma":[0.0021825235,0.00016324053,0.000038382783,0.00064918963,0.00040225874,0.00022427294,0.000074616066,0.0006541515,0.00011809747],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046481236,0.00022135043,0.010799876,0.00030075826,0.000033969387,0.000041000956,0.0065305866,0.000033961205,0.0007140446,0.122183874,0.0023226938,0.85635304],"study_design_scores_gemma":[0.0006114807,0.026799351,0.036260746,0.011908278,0.00073272845,0.00043057595,0.20055814,0.0036922877,0.048504412,0.5027214,0.16570339,0.002077169],"about_ca_topic_score_codex":0.00018941294,"about_ca_topic_score_gemma":0.000054153257,"teacher_disagreement_score":0.8542759,"about_ca_system_score_codex":0.00020726399,"about_ca_system_score_gemma":0.0006099847,"threshold_uncertainty_score":0.6656756},"labels":[],"label_agreement":null},{"id":"W4407445136","doi":"10.1038/s41746-025-01498-1","title":"Personalized decision making for coronary artery disease treatment using offline reinforcement learning","year":2025,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Coronary Interventions and Diagnostics","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Libin Cardiovascular Institute of Alberta; Foothills Medical Centre; Alberta Health Services; University of Calgary","funders":"Canadian Institutes of Health Research; Alberta Innovates; Government of Canada","keywords":"Reinforcement learning; Coronary artery disease; Reinforcement; Medicine; Disease; Internal medicine; Cardiology; Computer science; Artificial intelligence; Psychology","score_opus":0.042146561779384355,"score_gpt":0.3598822776269549,"score_spread":0.31773571584757054,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407445136","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7828176,0.0029823966,0.20073113,0.0023847218,0.000789242,0.0017434555,0.000048575166,0.00015021107,0.008352681],"genre_scores_gemma":[0.98850983,0.00010212666,0.0009910739,0.00060583616,0.0002671301,0.00007032374,0.0003515931,0.000023548086,0.009078547],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99863577,0.000011985396,0.0004945218,0.0003115553,0.0002741418,0.00027204878],"domain_scores_gemma":[0.998692,0.0005993002,0.000098980716,0.00025576795,0.00016373553,0.00019024774],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000104301565,0.00022954446,0.00041235212,0.00023580431,0.00015361731,0.000032102114,0.00006351157,0.000052752646,0.0003650562],"category_scores_gemma":[0.0010941818,0.0001724542,0.00023462532,0.00018635337,0.00012471685,0.0001323661,0.00005301437,0.000094354036,0.000010465541],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.014010023,0.0017963757,0.12721765,0.00088344805,0.0009398807,0.0010863806,0.00062384125,0.003386294,0.0007268304,0.0054283678,0.0070707994,0.83683014],"study_design_scores_gemma":[0.06896739,0.022043794,0.18400498,0.038723443,0.0055262656,0.0006707143,0.0043061455,0.281084,0.00015167112,0.007021693,0.3862006,0.0012993063],"about_ca_topic_score_codex":0.000006348721,"about_ca_topic_score_gemma":0.0000021753576,"teacher_disagreement_score":0.8355308,"about_ca_system_score_codex":0.00034732508,"about_ca_system_score_gemma":0.00016658277,"threshold_uncertainty_score":0.7032478},"labels":[],"label_agreement":null},{"id":"W4407570587","doi":"10.1038/s41746-025-01500-w","title":"Identifying major depressive disorder in older adults through naturalistic driving behaviors and machine learning","year":2025,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Older Adults Driving Studies","field":"Health Professions","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; University of Calgary","funders":"National Institute on Aging; National Institutes of Health","keywords":"Naturalistic observation; Depression (economics); Logistic regression; Demographics; Population; Poison control; Gerontology; Psychology; Medicine; Demography; Medical emergency; Environmental health","score_opus":0.023867289696770707,"score_gpt":0.38041774277749,"score_spread":0.3565504530807193,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407570587","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9810192,0.0047194194,0.0006986937,0.003379754,0.00097492407,0.000898138,0.000012851382,0.00018629713,0.008110745],"genre_scores_gemma":[0.9939943,0.0002633536,0.000070214104,0.00047459756,0.00013547139,0.00014094496,0.00005365579,0.000036579233,0.00483089],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9977099,0.00014936154,0.0006919067,0.0005314357,0.0003138108,0.00060361525],"domain_scores_gemma":[0.9980557,0.001267211,0.00020621018,0.0002457968,0.00014012553,0.00008494095],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022718456,0.00030252122,0.0005465028,0.000252372,0.000674855,0.000030614898,0.00018518695,0.00016401225,0.0000990103],"category_scores_gemma":[0.0030137964,0.00023443534,0.000039007584,0.00048337184,0.00024361462,0.00050322415,0.00046305187,0.0012008226,0.000021023796],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002037887,0.00005681021,0.9766855,0.000591493,0.00003600667,0.00003495215,0.01394851,0.0000024026533,0.000040811963,0.00024981413,0.0006666563,0.007666663],"study_design_scores_gemma":[0.0045107757,0.000061150444,0.9679851,0.011033218,0.000077410936,0.0000037693821,0.013832483,0.00016684529,0.000007916181,0.00078626024,0.0013046745,0.00023041363],"about_ca_topic_score_codex":0.0014319825,"about_ca_topic_score_gemma":0.004041281,"teacher_disagreement_score":0.012975115,"about_ca_system_score_codex":0.00012531134,"about_ca_system_score_gemma":0.00004910442,"threshold_uncertainty_score":0.95599955},"labels":[],"label_agreement":null},{"id":"W4407597584","doi":"10.1038/s41746-025-01496-3","title":"Self supervised artificial intelligence predicts poor outcome from primary cutaneous squamous cell carcinoma at diagnosis","year":2025,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Nonmelanoma Skin Cancer Studies","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Cancer Institute; National Institutes of Health; University of Glasgow; School of Medicine, New York University; York University","keywords":"Basal cell; Outcome (game theory); Primary (astronomy); Medicine; Artificial intelligence; Oncology; Dermatology; Internal medicine; Computer science; Mathematics; Physics","score_opus":0.02564036948994932,"score_gpt":0.26943358098213277,"score_spread":0.24379321149218344,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407597584","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89692605,0.0053808107,0.0003109406,0.007977605,0.0016274386,0.0011501155,0.00025127715,0.00032979727,0.08604596],"genre_scores_gemma":[0.9913822,0.00017114783,0.0005113285,0.0032747164,0.0010134451,0.00017335331,0.00029861412,0.00006776636,0.0031074542],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99640393,0.000041119383,0.0010948506,0.00090242206,0.00086195645,0.00069573725],"domain_scores_gemma":[0.99716175,0.0012812254,0.0001704133,0.000796195,0.00020138096,0.0003890222],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00013463802,0.0005578955,0.0011885223,0.00030485442,0.00019040775,0.000047972113,0.00036857548,0.00022408903,0.0005662859],"category_scores_gemma":[0.00079232355,0.0004506829,0.00019955896,0.00059649016,0.00045107253,0.00018041223,0.00044754945,0.0004224613,0.00027818224],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011079484,0.00090699067,0.9114727,0.00097488484,0.00021350101,0.0019856063,0.0018248005,0.0000038905596,0.00081856694,0.00015583444,0.018091032,0.062444266],"study_design_scores_gemma":[0.010792496,0.008503902,0.7987972,0.0020946807,0.0039134915,0.00072723004,0.004109321,0.0016266442,0.05559298,0.0050844364,0.10625574,0.0025018598],"about_ca_topic_score_codex":0.00023892029,"about_ca_topic_score_gemma":0.00006420276,"teacher_disagreement_score":0.112675466,"about_ca_system_score_codex":0.000906228,"about_ca_system_score_gemma":0.00022074714,"threshold_uncertainty_score":0.9997945},"labels":[],"label_agreement":null},{"id":"W4407599026","doi":"10.1038/s41746-025-01499-0","title":"Self-supervised identification and elimination of harmful datasets in distributed machine learning for medical image analysis","year":2025,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut Universitaire de Gériatrie de Montréal; Hotchkiss Brain Institute; Alberta Children's Hospital; Women and Children’s Health Research Institute; Université de Montréal; University of Alberta; University of Calgary","funders":"Parkinson Association of Alberta; Parkinson Vereniging; Consortium canadien en neurodégénérescence associée au vieillissement; Alzheimer's Disease Neuroimaging Initiative","keywords":"Identification (biology); Computer science; Artificial intelligence; Machine learning; Pattern recognition (psychology); Image (mathematics); Biology","score_opus":0.013682276940011692,"score_gpt":0.3329284566835312,"score_spread":0.31924617974351954,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407599026","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.65231436,0.0018608262,0.111166686,0.22918187,0.0003173791,0.0024820524,0.0018373642,0.0003271542,0.00051229465],"genre_scores_gemma":[0.98724914,0.00015045003,0.0003730879,0.0010602984,0.000046591307,0.000046312125,0.010990238,0.000012364436,0.00007151961],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99825937,0.00004273914,0.0006647216,0.0003742005,0.00047740628,0.00018155394],"domain_scores_gemma":[0.99827677,0.0009341853,0.00015239812,0.0002867408,0.00021658109,0.0001333176],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0007617918,0.00015227892,0.00055164687,0.0007592788,0.000045250083,0.000028529823,0.00011780275,0.00010684885,0.00005948403],"category_scores_gemma":[0.008353689,0.00013075587,0.000071708535,0.0014105584,0.00016180142,0.00021871264,0.00007358444,0.00018941687,0.0000016869418],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0020462521,0.0040036375,0.5742792,0.008927044,0.0033851054,0.00021063848,0.0026782434,0.00015681054,0.020064475,0.001986312,0.033054106,0.34920815],"study_design_scores_gemma":[0.013482589,0.00073685125,0.518168,0.0017055522,0.0036994747,0.00001579694,0.0005511821,0.42018655,0.003346506,0.00039442035,0.03739542,0.0003176658],"about_ca_topic_score_codex":0.00011384737,"about_ca_topic_score_gemma":0.000059082096,"teacher_disagreement_score":0.42002973,"about_ca_system_score_codex":0.0001225933,"about_ca_system_score_gemma":0.00011915281,"threshold_uncertainty_score":0.99999934},"labels":[],"label_agreement":null},{"id":"W4407878819","doi":"10.1038/s41746-025-01517-1","title":"A new metric to understand the association between heart rate variability and menstrual regularity","year":2025,"lang":"en","type":"editorial","venue":"npj Digital Medicine","topic":"Heart Rate Variability and Autonomic Control","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Metric (unit); Association (psychology); Heart rate variability; Medicine; Internal medicine; Cardiology; Mathematics; Statistics; Psychology; Heart rate; Engineering; Operations management","score_opus":0.013056061513045053,"score_gpt":0.2793498388235639,"score_spread":0.26629377731051884,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407878819","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013769904,0.00083483924,0.007653849,0.21315143,0.72074604,0.007186378,0.0020834147,0.0005028761,0.03407129],"genre_scores_gemma":[0.17793715,0.00008530473,0.00032068367,0.0018731323,0.7834102,0.000041212978,0.0009865081,0.0000755444,0.035270274],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99612385,0.00034052314,0.0009493143,0.00091013307,0.0011172786,0.0005589199],"domain_scores_gemma":[0.9851189,0.012636155,0.0002582112,0.0008739253,0.00047818013,0.00063461845],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00481163,0.00048922654,0.001644987,0.00033196303,0.00018328297,0.00018162323,0.00022502814,0.00102763,0.000107596556],"category_scores_gemma":[0.03983691,0.00033093977,0.00017065082,0.0009692877,0.00017178235,0.0001742616,0.0002135667,0.0014857744,0.00002761944],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001280141,0.000048759124,0.0021057194,0.0002573375,0.0004902276,0.000004925234,0.00034042506,7.092649e-7,0.000056249926,0.00022786301,0.9776434,0.01869638],"study_design_scores_gemma":[0.0029545478,0.00063784287,0.018684978,0.00054125354,0.0010109528,0.0000023152274,0.00014786178,0.000017580265,0.00001572563,0.0026796598,0.97304124,0.00026604382],"about_ca_topic_score_codex":0.00043496318,"about_ca_topic_score_gemma":0.000027717468,"teacher_disagreement_score":0.21127829,"about_ca_system_score_codex":0.0014189839,"about_ca_system_score_gemma":0.0023484847,"threshold_uncertainty_score":0.9999143},"labels":[],"label_agreement":null},{"id":"W4408167715","doi":"10.1038/s41746-025-01542-0","title":"Red teaming ChatGPT in medicine to yield real-world insights on model behavior","year":2025,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Yield (engineering); Psychology; Physics","score_opus":0.18042169334002062,"score_gpt":0.4531145109831594,"score_spread":0.2726928176431388,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408167715","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7145814,0.0001895963,0.0005646332,0.054665033,0.0009980473,0.0012433764,0.0000037635316,0.00012926578,0.2276249],"genre_scores_gemma":[0.9774374,0.000096775795,0.0001021749,0.0076046237,0.000703136,0.00016514678,0.00005367503,0.000027851975,0.013809252],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9975911,0.000020700227,0.0009334209,0.0005247761,0.00050170394,0.00042831135],"domain_scores_gemma":[0.9982505,0.0005206928,0.000097180586,0.0005497178,0.00021718662,0.00036476387],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029226017,0.00027043582,0.00064959115,0.0012887868,0.00009055625,0.000015531226,0.00016651624,0.0001489111,0.00014476229],"category_scores_gemma":[0.0024801749,0.00020339982,0.00004855856,0.0014329683,0.000173986,0.00016950237,0.000046139212,0.00044459928,0.00006963281],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017804565,0.0015433866,0.09659509,0.0005762759,0.00007242131,0.00031480027,0.021405797,0.00041771925,0.010406152,0.020275824,0.08436977,0.7622423],"study_design_scores_gemma":[0.004831049,0.020985698,0.56081843,0.11553019,0.0011963039,0.000118600175,0.04675532,0.026772955,0.047003247,0.055153836,0.1175144,0.0033199415],"about_ca_topic_score_codex":0.0020026513,"about_ca_topic_score_gemma":0.0010440684,"teacher_disagreement_score":0.75892234,"about_ca_system_score_codex":0.00040177867,"about_ca_system_score_gemma":0.00027546997,"threshold_uncertainty_score":0.8294404},"labels":[],"label_agreement":null},{"id":"W4408246736","doi":"10.1038/s41746-025-01549-7","title":"A mobile health application that supports a patient centered approach to cardiovascular risk management","year":2025,"lang":"en","type":"editorial","venue":"npj Digital Medicine","topic":"Mobile Health and mHealth Applications","field":"Health Professions","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada); University of Toronto","funders":"","keywords":"Risk management; Cardiovascular health; Health management system; Medicine; Computer science; Business; Risk analysis (engineering); Internal medicine; Alternative medicine; Pathology; Disease","score_opus":0.02011256007668555,"score_gpt":0.3630981489450321,"score_spread":0.34298558886834657,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408246736","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000048396418,0.014062814,0.044126056,0.0011577976,0.63384587,0.074784875,0.005679536,0.00086533406,0.22542931],"genre_scores_gemma":[0.008099859,0.027869578,0.002210076,0.0064843986,0.5403442,0.36743656,0.031574693,0.000337168,0.015643505],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9913353,0.00042414633,0.0023111023,0.0018891927,0.0022417274,0.0017985865],"domain_scores_gemma":[0.9928859,0.00079763104,0.001315354,0.0027209017,0.0005535716,0.0017266396],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0019903171,0.0007968914,0.0020387527,0.0007025466,0.0011725196,0.000028018023,0.00073720596,0.0009979078,0.000062713945],"category_scores_gemma":[0.0006167882,0.0006853791,0.00037253308,0.0009865453,0.00011684325,0.00012914144,0.00054082763,0.002375201,0.00041349346],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008347113,0.00023014947,0.00010228562,0.004725148,0.00018750894,0.00000263885,0.0008392262,0.000016164728,2.8269962e-8,0.00042464942,0.6675512,0.3258375],"study_design_scores_gemma":[0.0019188764,0.0008522056,0.00007178425,0.0019187994,0.00022782985,0.0000010500682,0.0020954933,0.000025160687,1.283504e-7,0.0004559323,0.9920508,0.00038194272],"about_ca_topic_score_codex":0.0015608327,"about_ca_topic_score_gemma":0.000059446644,"teacher_disagreement_score":0.32545555,"about_ca_system_score_codex":0.0017043238,"about_ca_system_score_gemma":0.0020753979,"threshold_uncertainty_score":0.9999264},"labels":[],"label_agreement":null},{"id":"W4408314709","doi":"10.1038/s41746-025-01503-7","title":"Bias recognition and mitigation strategies in artificial intelligence healthcare applications","year":2025,"lang":"en","type":"review","venue":"npj Digital Medicine","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":206,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Libin Cardiovascular Institute of Alberta; University of Calgary","funders":"","keywords":"Health care; Computer science; Artificial intelligence; Psychology; Political science","score_opus":0.45352658605033463,"score_gpt":0.5016546083278605,"score_spread":0.04812802227752583,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408314709","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00011825722,0.98851645,0.0015494301,0.0031416342,0.0003838291,0.0027364092,0.00008760583,0.000085143045,0.0033812518],"genre_scores_gemma":[0.0047334014,0.99066067,0.000116996365,0.00025733138,0.0008894856,0.00076509576,0.0023643079,0.000030365953,0.00018232077],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972083,0.000088790606,0.0015022956,0.0005831077,0.00029174183,0.0003257615],"domain_scores_gemma":[0.9979247,0.00089363457,0.00032797275,0.00034015957,0.0002860138,0.00022752429],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003838977,0.0003593407,0.0012471683,0.0007821393,0.00009553938,0.00008547205,0.00010807268,0.0004228995,0.000054038464],"category_scores_gemma":[0.0009054926,0.00029527902,0.00011268429,0.0012109051,0.00027904974,0.0002833553,0.000035089888,0.0006250963,0.00012481511],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015109606,0.00007911915,0.000028691858,0.02262673,0.00001734968,0.0000072410853,0.00039694028,1.5363514e-7,2.430975e-7,0.0023123263,0.000082476894,0.9744336],"study_design_scores_gemma":[0.000066153814,0.0010048402,0.000042548632,0.150744,0.00078529434,0.00021459644,0.013597736,0.000039442453,0.000022136068,0.17750348,0.6552514,0.00072839274],"about_ca_topic_score_codex":0.000372598,"about_ca_topic_score_gemma":0.00020549199,"teacher_disagreement_score":0.97370523,"about_ca_system_score_codex":0.0002652693,"about_ca_system_score_gemma":0.0013041971,"threshold_uncertainty_score":0.99994993},"labels":[],"label_agreement":null},{"id":"W4408391722","doi":"10.1038/s41746-025-01526-0","title":"Holistic AI analysis of hybrid cardiac perfusion images for mortality prediction","year":2025,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Cardiac Imaging and Diagnostics","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; University of Calgary","funders":"National Heart, Lung, and Blood Institute","keywords":"Myocardial perfusion imaging; Medicine; Perfusion; Receiver operating characteristic; Confidence interval; Correction for attenuation; Internal medicine; Radiology; Cardiology; Nuclear medicine; Positron emission tomography","score_opus":0.019801064390448767,"score_gpt":0.3370345495886497,"score_spread":0.31723348519820094,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408391722","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90702826,0.0034980185,0.035701297,0.0034533746,0.0017202313,0.000976994,0.002625937,0.00018665729,0.04480926],"genre_scores_gemma":[0.9966666,0.000097001845,0.000055838394,0.00051721017,0.00033048517,0.000034741824,0.0012330115,0.000013458025,0.0010516222],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99861336,0.000017361375,0.0004672699,0.00030633013,0.00038954502,0.00020611868],"domain_scores_gemma":[0.9983205,0.0005401702,0.00009631206,0.0004382358,0.0004784038,0.00012634754],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030990312,0.00016635162,0.0008730695,0.0005681751,0.000050740167,0.000022088561,0.00006234797,0.000046500372,0.000030682277],"category_scores_gemma":[0.0035330236,0.00013340436,0.0003971375,0.00085511856,0.00024255824,0.00011408046,0.0000411368,0.00012671521,0.0000024612004],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021939585,0.00023471496,0.8939954,0.00043614575,0.0023064988,0.000021247757,0.00009876655,0.00011722232,0.0028669063,0.00046481212,0.070569254,0.028669627],"study_design_scores_gemma":[0.0019267297,0.0003687659,0.9663164,0.0005797747,0.014737,0.000005933418,0.00024765803,0.0027841215,0.0027919302,0.00058008544,0.009532874,0.00012873138],"about_ca_topic_score_codex":0.00008443677,"about_ca_topic_score_gemma":7.9858796e-7,"teacher_disagreement_score":0.0896384,"about_ca_system_score_codex":0.00007284179,"about_ca_system_score_gemma":0.00010404571,"threshold_uncertainty_score":0.5440072},"labels":[],"label_agreement":null},{"id":"W4408607306","doi":"10.1038/s41746-025-01557-7","title":"Credibility assessment of a mechanistic model of atherosclerosis to predict cardiovascular outcomes under lipid-lowering therapy","year":2025,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Lipoproteins and Cardiovascular Health","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Population Health Research Institute","funders":"Novartis Pharma","keywords":"Credibility; Medicine; Internal medicine; Political science","score_opus":0.04198192115583864,"score_gpt":0.3190774672488459,"score_spread":0.27709554609300724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408607306","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.79910433,0.0010243458,0.18988976,0.0010466031,0.00031919006,0.0015549901,0.00006421043,0.000078597055,0.006917989],"genre_scores_gemma":[0.99748677,0.0003595402,0.0011014531,0.0005636305,0.00012731315,0.0000864247,0.00001933535,0.00003302777,0.0002224785],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99703455,0.000045383455,0.00079616497,0.0004911061,0.0013041574,0.00032865457],"domain_scores_gemma":[0.9977378,0.00010584004,0.00011816864,0.0014407051,0.00035036603,0.00024711195],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011641968,0.0002866177,0.0016248543,0.00024871813,0.000046955105,0.000010822089,0.00019712035,0.00012842215,0.000029232797],"category_scores_gemma":[0.00041888628,0.00020148224,0.0007593491,0.00050405896,0.00015827872,0.00009159179,0.000113851675,0.00020137941,0.0000012976906],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015739999,0.004318975,0.2444498,0.0082652,0.025461063,0.000029194405,0.0017291603,0.025306033,0.08651907,0.018456766,0.001034063,0.58285666],"study_design_scores_gemma":[0.027517233,0.0070406157,0.8958363,0.009221548,0.003275175,0.000028682936,0.0016420641,0.021572027,0.02185728,0.008172359,0.0028376437,0.0009990728],"about_ca_topic_score_codex":0.00023674764,"about_ca_topic_score_gemma":0.0000043146247,"teacher_disagreement_score":0.6513865,"about_ca_system_score_codex":0.00018370873,"about_ca_system_score_gemma":0.00040152372,"threshold_uncertainty_score":0.8216207},"labels":[],"label_agreement":null},{"id":"W4408736524","doi":"10.1038/s41746-025-01543-z","title":"A systematic review and meta-analysis of diagnostic performance comparison between generative AI and physicians","year":2025,"lang":"en","type":"review","venue":"npj Digital Medicine","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":125,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Meta-analysis; Generative grammar; Reliability (semiconductor); Diagnostic accuracy; Systematic review; Artificial intelligence; Diagnostic test; Computer science; Medical physics; MEDLINE; Machine learning; Medicine; Pathology; Internal medicine; Pediatrics","score_opus":0.29517280464675494,"score_gpt":0.5007602912495945,"score_spread":0.2055874866028396,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408736524","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000033254753,0.9948751,0.00013395975,0.001608922,0.00005186108,0.002794931,0.00013515688,0.000017560753,0.0003492772],"genre_scores_gemma":[0.005033895,0.992389,0.000016742602,0.0009852183,0.00011703748,0.00034288768,0.0005350723,0.000018022985,0.00056210486],"study_design_codex":"systematic_review","study_design_gemma":"meta_analysis","domain_scores_codex":[0.99692446,0.0001483965,0.00197579,0.0004153145,0.000338181,0.00019787469],"domain_scores_gemma":[0.9945521,0.0037096646,0.00082299946,0.00046170835,0.0003073453,0.00014621578],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045621058,0.00039923048,0.011248772,0.00047975843,0.00005933022,0.0000201962,0.00010729417,0.00015598703,0.000042057247],"category_scores_gemma":[0.0032445558,0.00023782068,0.0006002715,0.0012849652,0.00024726236,0.000116358926,0.000047220085,0.0003281568,0.0000064291467],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000011238573,0.000034058707,0.0000751193,0.75994843,0.040925696,0.0000013889596,0.00033063864,1.9053427e-7,9.900789e-9,0.000018933846,0.00038211734,0.19828227],"study_design_scores_gemma":[0.00001693639,0.0002594722,0.000009980699,0.22696011,0.7678839,0.0000064744618,0.00014444809,0.000030720214,9.1107256e-7,0.00001315557,0.0045423955,0.00013149137],"about_ca_topic_score_codex":0.000059108672,"about_ca_topic_score_gemma":0.0000072663356,"teacher_disagreement_score":0.7269582,"about_ca_system_score_codex":0.000060360493,"about_ca_system_score_gemma":0.00019039173,"threshold_uncertainty_score":0.96980464},"labels":[],"label_agreement":null},{"id":"W4409205845","doi":"10.1038/s41746-024-01401-4","title":"The role of open standards in catalysing knowledge transfer to deliver climate adaptive care","year":2025,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Climate Change and Health Impacts","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre for Global Health Research","funders":"Wellcome Trust","keywords":"Business; Knowledge management; Psychology; Computer science","score_opus":0.027916820747261952,"score_gpt":0.3536539947254493,"score_spread":0.32573717397818736,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409205845","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6343652,0.001695679,0.00004312132,0.0012589009,0.00010049706,0.00059037516,0.00016954525,0.000010427606,0.36176628],"genre_scores_gemma":[0.9993375,0.00015850589,0.000010622057,0.00028869545,0.000022270347,0.000019948431,0.000014958585,0.000007330503,0.00014015398],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.998972,0.000020349366,0.00026723236,0.00019029116,0.00023902954,0.00031107615],"domain_scores_gemma":[0.999507,0.000124631,0.000016850143,0.00019420021,0.00003660664,0.00012069818],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003382503,0.000103019775,0.00021880631,0.000057160472,0.00011019303,0.000036592097,0.0003368779,0.000034269495,0.00014917],"category_scores_gemma":[0.00012736661,0.00006592061,0.000021396216,0.0004535324,0.00016077966,0.00024274879,0.00030450008,0.00008552828,0.000034033677],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005571234,0.00010142649,0.036988363,0.00008709362,0.000013946646,0.000008337596,0.035179965,0.000049742357,0.0023594038,0.0010678082,0.003920553,0.91966623],"study_design_scores_gemma":[0.0063059237,0.0027609805,0.36027303,0.005001916,0.00012864618,0.000007064931,0.13583218,0.00061574037,0.013134035,0.0046755443,0.4705134,0.00075153296],"about_ca_topic_score_codex":0.00082452694,"about_ca_topic_score_gemma":0.005463948,"teacher_disagreement_score":0.9189147,"about_ca_system_score_codex":0.00036083208,"about_ca_system_score_gemma":0.00003481295,"threshold_uncertainty_score":0.30490112},"labels":[],"label_agreement":null},{"id":"W4409288098","doi":"10.1038/s41746-025-01600-7","title":"A group concept mapping study of stakeholder perspectives on digital therapeutics economic value drivers","year":2025,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Innovative Approaches in Technology and Social Development","field":"Business, Management and Accounting","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Value (mathematics); Stakeholder; Group (periodic table); Business; Knowledge management; Computer science; Political science; Public relations; Physics","score_opus":0.04443250498983316,"score_gpt":0.2564893627936412,"score_spread":0.21205685780380806,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409288098","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.84890634,0.000053114883,0.0004986766,0.0010476785,0.0003789894,0.0004309296,0.000004832829,0.00010827916,0.14857113],"genre_scores_gemma":[0.9985399,0.00000387097,0.000018728588,0.00071787235,0.0002172761,0.000018548842,0.000024177647,0.00001390846,0.00044571512],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.998949,0.0000061038772,0.00035092386,0.00031117297,0.00018363656,0.000199166],"domain_scores_gemma":[0.999421,0.00007701813,0.00018858706,0.00020285555,0.00010465416,0.0000058631467],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016513577,0.00019369613,0.00032117742,0.00039175956,0.00013194479,0.00008759328,0.0002699822,0.000087599714,0.000033314594],"category_scores_gemma":[0.000107748296,0.00016198095,0.000038734524,0.000499438,0.00045883315,0.0006062311,0.0001718994,0.0001977173,0.00002141586],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000084330495,0.0008863557,0.051924538,0.00006182549,0.0005875443,0.000011697769,0.011139984,0.000019623027,0.000052614414,0.88199997,0.0015292871,0.051702254],"study_design_scores_gemma":[0.0074673616,0.00067920564,0.12646443,0.000515058,0.00015674869,0.0000012414279,0.76362306,0.0003408268,0.00008038255,0.05837501,0.041548938,0.0007477448],"about_ca_topic_score_codex":0.000024417155,"about_ca_topic_score_gemma":0.0000027080366,"teacher_disagreement_score":0.82362497,"about_ca_system_score_codex":0.0001220849,"about_ca_system_score_gemma":0.000025165562,"threshold_uncertainty_score":0.66053915},"labels":[],"label_agreement":null},{"id":"W4409450984","doi":"10.1038/s41746-025-01504-6","title":"Network analysis of extraintestinal manifestations and associated autoimmune disorders in Crohn’s disease and ulcerative colitis","year":2025,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Inflammatory Bowel Disease","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Health Services; University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Innovates; University of Alberta; Alberta Machine Intelligence Institute; Canadian Institutes of Health Research; Mitacs; Canadian Institute for Advanced Research","keywords":"Ulcerative colitis; Gastroenterology; Inflammatory bowel disease; Medicine; Internal medicine; Crohn's disease; Disease; Colitis; Immunology","score_opus":0.005243474519808263,"score_gpt":0.24593388146755812,"score_spread":0.24069040694774987,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409450984","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9946212,0.00038353453,0.00030431722,0.0003309383,0.000030721647,0.0001892666,0.000115522686,0.000007525188,0.00401694],"genre_scores_gemma":[0.9988791,0.00006728713,0.000019959542,0.00013277864,0.000018641009,0.00002027004,0.00039387034,0.0000059025024,0.00046221574],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99929506,0.000042954336,0.00023254965,0.00020482502,0.0000802291,0.00014438132],"domain_scores_gemma":[0.99959797,0.000060037764,0.00006956852,0.0001252883,0.000064306485,0.000082818035],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011011738,0.00010583234,0.00017297764,0.00012615703,0.00004149627,0.000014771262,0.00005047535,0.000041910374,0.000012846466],"category_scores_gemma":[0.00069295545,0.000100273974,0.00003383424,0.0002919914,0.00028836206,0.00000867133,0.000053973527,0.00004835498,1.610435e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005862479,0.000118010576,0.9892676,0.00006397769,0.0006057628,0.00012732297,0.0002293999,0.00041734395,0.0003360745,0.0022910342,0.00054418336,0.005413062],"study_design_scores_gemma":[0.0007808636,0.000051797066,0.99602973,0.00010384021,0.0003040116,6.838644e-7,0.00018732242,0.0010953164,0.0000021425526,0.0012815741,0.000081439655,0.00008129693],"about_ca_topic_score_codex":0.000028657392,"about_ca_topic_score_gemma":0.0007530063,"teacher_disagreement_score":0.0067621316,"about_ca_system_score_codex":0.000015083203,"about_ca_system_score_gemma":0.00007092936,"threshold_uncertainty_score":0.4089054},"labels":[],"label_agreement":null},{"id":"W4409574103","doi":"10.1038/s41746-025-01603-4","title":"Genomic language models could transform medicine but not yet","year":2025,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Genetics, Bioinformatics, and Biomedical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; University of Toronto; University Health Network","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto","keywords":"Genomic medicine; Computational biology; Computer science; Natural language processing; Biology; Genetics; Linguistics; Philosophy","score_opus":0.017822393763525825,"score_gpt":0.2972402323870185,"score_spread":0.2794178386234927,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409574103","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5201331,0.005176991,0.020406254,0.02741306,0.0012959132,0.0010246389,0.0002905373,0.000095389114,0.42416415],"genre_scores_gemma":[0.9789221,0.0013376751,0.00011760061,0.0030703112,0.000531755,0.000018832763,0.0005894973,0.000021526594,0.015390698],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99808246,0.000018505025,0.0005356012,0.00035289765,0.0005255954,0.00048494712],"domain_scores_gemma":[0.99896353,0.00006253785,0.000066802735,0.00047261958,0.00014642806,0.00028804853],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003602193,0.00025836012,0.0003640935,0.00017485692,0.00007710999,0.000029771327,0.0004582513,0.00024912352,0.000105488885],"category_scores_gemma":[0.0005375853,0.0001819972,0.00008443962,0.00020117103,0.0007744066,0.000013863135,0.00014432984,0.00021406823,0.000038429116],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005968106,0.00019097367,0.0002521259,0.00052021944,0.00031369217,0.000040863146,0.0014284938,0.000029724382,0.58795774,0.0020527185,0.11800732,0.2886093],"study_design_scores_gemma":[0.0141365845,0.006209526,0.0031477816,0.0011869213,0.00025822668,0.00009709333,0.010467309,0.0059224362,0.18802969,0.008591519,0.76057446,0.0013784856],"about_ca_topic_score_codex":0.000074862386,"about_ca_topic_score_gemma":0.000031439537,"teacher_disagreement_score":0.6425671,"about_ca_system_score_codex":0.000037318183,"about_ca_system_score_gemma":0.00016147233,"threshold_uncertainty_score":0.742163},"labels":[],"label_agreement":null},{"id":"W4409592185","doi":"10.1038/s41746-025-01633-y","title":"Overcoming barriers in the use of artificial intelligence in point of care ultrasound","year":2025,"lang":"en","type":"review","venue":"npj Digital Medicine","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Point (geometry); Point of care ultrasound; Point of care; Ultrasound; Psychology; Medicine; Nursing; Radiology; Mathematics","score_opus":0.2450677226408029,"score_gpt":0.4572266373648512,"score_spread":0.2121589147240483,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409592185","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002205144,0.99289685,0.00017761528,0.00045308506,0.0006348952,0.0018422462,0.000067865505,0.00001201199,0.001710294],"genre_scores_gemma":[0.09244726,0.90666294,0.00007460387,0.00019303146,0.0002558191,0.000069702255,0.00021976171,0.000022858883,0.000054039865],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9967404,0.00014221462,0.002034047,0.00034415003,0.0004481461,0.0002910165],"domain_scores_gemma":[0.99483186,0.0038654297,0.00042438554,0.0005474764,0.0002231881,0.00010767028],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0005276382,0.00029762182,0.0017276144,0.0007493781,0.00002703797,0.000017980265,0.00026608017,0.0002851498,0.000073138086],"category_scores_gemma":[0.009544939,0.00019083884,0.00022362085,0.0014396851,0.00036755588,0.0001688859,0.000036423688,0.00062465685,0.0000055240907],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000055326054,0.00008077405,0.0006413884,0.022077734,0.000022363227,0.000020414755,0.0070492593,0.000005099176,0.0000014550299,0.00075071893,0.00015652555,0.9691389],"study_design_scores_gemma":[0.00013040028,0.0021559529,0.000220961,0.36995783,0.0011572274,0.00016721495,0.08875499,0.00005842189,0.00019605168,0.003641276,0.53288037,0.00067930896],"about_ca_topic_score_codex":0.0010702653,"about_ca_topic_score_gemma":0.00035525646,"teacher_disagreement_score":0.9684596,"about_ca_system_score_codex":0.00025531958,"about_ca_system_score_gemma":0.00112737,"threshold_uncertainty_score":0.9987981},"labels":[],"label_agreement":null},{"id":"W4409592247","doi":"10.1038/s41746-025-01620-3","title":"Advancing perioperative care with digital applications and wearables","year":2025,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Surgical Simulation and Training","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"University of Toronto; University of Stirling","keywords":"Wearable computer; Perioperative; Computer science; Medicine; Embedded system","score_opus":0.006988882406895331,"score_gpt":0.28216643632543276,"score_spread":0.27517755391853743,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409592247","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2851928,0.0018410444,0.0045361985,0.0026613937,0.00004582156,0.0006498822,0.000020605838,0.00015749646,0.7048948],"genre_scores_gemma":[0.9965075,0.000021110622,0.00012673535,0.0005998627,0.00009243223,0.000037176593,0.00010823434,0.000011276407,0.0024956232],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99926007,0.0000040376212,0.00016919922,0.00023245448,0.00017501508,0.00015924418],"domain_scores_gemma":[0.9993872,0.00015536115,0.000028071177,0.00013625316,0.00014428647,0.00014879946],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000030394027,0.00012839185,0.00025008997,0.00009569851,0.00009862263,0.00006137108,0.000033234806,0.000039507173,0.00005185647],"category_scores_gemma":[0.00012423516,0.00008219854,0.00002175221,0.00029314664,0.00023049607,0.00023060346,0.000024246148,0.00011898281,0.0000092674445],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004041093,0.00010579655,0.10635947,0.00030778584,0.0001432018,0.000059301947,0.0030625802,0.00004551939,0.00012754416,0.010611232,0.000099609315,0.87867385],"study_design_scores_gemma":[0.015399132,0.0014045571,0.04577464,0.0026713114,0.00020614032,0.0001259322,0.04555918,0.0005947533,0.00020186004,0.00054712367,0.88712054,0.00039482643],"about_ca_topic_score_codex":0.0000032924509,"about_ca_topic_score_gemma":0.000002795723,"teacher_disagreement_score":0.88702095,"about_ca_system_score_codex":0.000039391416,"about_ca_system_score_gemma":0.00006771465,"threshold_uncertainty_score":0.3351959},"labels":[],"label_agreement":null},{"id":"W4409616732","doi":"10.1038/s41746-025-01631-0","title":"Germany and Europe lead digital innovation and AI with collaborative health data use at continental level","year":2025,"lang":"en","type":"editorial","venue":"npj Digital Medicine","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; University Hospital Foundation; Alberta Innovates; University of Alberta; Canadian Institutes of Health Research; Mitacs; Canadian Institute for Advanced Research","keywords":"Lead (geology); Digital health; Data science; Computer science; Political science; Geology; Health care","score_opus":0.16509422631681908,"score_gpt":0.432839027021419,"score_spread":0.26774480070459994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409616732","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23005506,0.008809351,0.001216313,0.09927891,0.6207499,0.0068378807,0.019802386,0.00048010206,0.0127701145],"genre_scores_gemma":[0.3002904,0.0034310913,0.00026060597,0.0064079766,0.5439321,0.00008141595,0.09078642,0.00021566037,0.054594312],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9968883,0.00003912576,0.0009734961,0.0008892721,0.00081491884,0.00039490178],"domain_scores_gemma":[0.99571335,0.0010652472,0.00047511506,0.00068104,0.0017920631,0.00027318715],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00035677504,0.00043862892,0.0008985914,0.0004017533,0.00020850259,0.00027505882,0.00017270753,0.0003457799,0.00001907644],"category_scores_gemma":[0.006203266,0.00032725956,0.000014469094,0.0010591969,0.00064270373,0.0012542979,0.0003047269,0.0007604675,0.00001891315],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00069252576,0.00009587986,0.0041358927,0.00062555535,0.000097208045,0.000043996406,0.000812412,8.3252225e-8,0.00001226795,0.00011211475,0.9352055,0.058166523],"study_design_scores_gemma":[0.00062864705,0.0020580213,0.0015486003,0.0028777204,0.00011220202,0.00007018299,0.0011121539,0.000048960323,0.000027936134,0.00006826483,0.991151,0.00029634402],"about_ca_topic_score_codex":0.00046487342,"about_ca_topic_score_gemma":0.00025096515,"teacher_disagreement_score":0.092870936,"about_ca_system_score_codex":0.00025205757,"about_ca_system_score_gemma":0.0020856827,"threshold_uncertainty_score":0.9999179},"labels":[],"label_agreement":null},{"id":"W4409764913","doi":"10.1038/s41746-025-01608-z","title":"Evaluating compliance with HeatSuite for monitoring in situ physiological and perceptual responses and personal environmental exposure","year":2025,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Thermoregulation and physiological responses","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Montreal Heart Institute; Lakehead University","funders":"","keywords":"Compliance (psychology); Perception; In situ; Psychology; Audiology; Environmental science; Medicine; Neuroscience; Social psychology; Geography","score_opus":0.12784788968261468,"score_gpt":0.39214694804338923,"score_spread":0.26429905836077455,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409764913","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99749476,0.00093409943,0.000044649893,0.00073592144,0.000028740458,0.00038196085,0.000016125392,0.000024011044,0.00033975797],"genre_scores_gemma":[0.9982823,0.000042336706,0.00032736044,0.00032597873,0.00010523716,0.00003418922,0.000025128034,0.000007551662,0.0008498914],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9991487,0.000041637977,0.00017745052,0.00029032218,0.00016847665,0.00017339802],"domain_scores_gemma":[0.9991365,0.00063439383,0.00003314377,0.00008266145,0.000018814651,0.00009449905],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014625704,0.00014479671,0.000310207,0.00006827144,0.00006859744,0.000014787244,0.00003208249,0.000061032082,0.000028982493],"category_scores_gemma":[0.00047824575,0.00008912467,0.000022378958,0.00008142161,0.0004221673,0.00007410356,0.000036890953,0.00012227299,9.0560656e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.015159367,0.00013889722,0.07315382,0.00012408917,0.00003730022,0.000018129584,0.0014084756,0.000004556826,0.76348466,0.00009731873,0.000034387882,0.14633901],"study_design_scores_gemma":[0.0032382838,0.0029224202,0.9901142,0.0006287498,0.000025592906,0.00002792082,0.0019143212,0.0002567996,0.00046643775,0.00015131103,0.00016387147,0.0000900563],"about_ca_topic_score_codex":0.0000016547812,"about_ca_topic_score_gemma":5.012841e-7,"teacher_disagreement_score":0.9169604,"about_ca_system_score_codex":0.000037215974,"about_ca_system_score_gemma":0.000024399516,"threshold_uncertainty_score":0.36343983},"labels":[],"label_agreement":null},{"id":"W4410050779","doi":"10.1038/s41746-025-01647-6","title":"The FAIIR conversational AI agent assistant for youth mental health service provision","year":2025,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada Research Chairs; York University; University of Toronto; Trent University; University of Waterloo; Humber Polytechnic; The King's University; Schwartz/Reisman Emergency Medicine Institute; Queen's University","funders":"Canadian Institutes of Health Research; Natural Sciences and Engineering Research Council of Canada; Government of Canada; Canadian Institute for Advanced Research","keywords":"Mental health; Service (business); Psychology; Mental health service; Applied psychology; Medical education; Computer science; Business; Psychiatry; Medicine; Marketing","score_opus":0.02464288804654949,"score_gpt":0.33109618985023775,"score_spread":0.30645330180368824,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410050779","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0033123689,0.0011426976,0.19486694,0.79076385,0.0028220671,0.0016792782,0.000118036005,0.000279472,0.005015278],"genre_scores_gemma":[0.97703165,0.000022205515,0.0010560144,0.020102015,0.00016208671,0.000044454457,0.00016732166,0.000009924119,0.0014043011],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.998412,0.000059782647,0.0003849868,0.00035694346,0.00046732728,0.00031897498],"domain_scores_gemma":[0.99871343,0.00035534645,0.00014748565,0.00041798223,0.00022927472,0.0001364746],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005742019,0.00014003558,0.0001867184,0.00007718719,0.00048074938,0.00016576263,0.00062175514,0.00003860865,0.0000059315353],"category_scores_gemma":[0.00038115642,0.00008806333,0.000041212294,0.00038607224,0.00007017529,0.00027423108,0.00019964691,0.00019001734,0.000010437185],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020841513,0.00015419554,0.0058989744,0.000903797,0.00011439644,0.00000332487,0.022726823,0.00011557513,0.0000304254,0.27579474,0.08663937,0.60740995],"study_design_scores_gemma":[0.0025721353,0.0010832764,0.01064998,0.0007873916,0.0000137572,0.000009761458,0.0028846562,0.14076056,0.00001855797,0.006710738,0.83425885,0.00025032816],"about_ca_topic_score_codex":0.00016829174,"about_ca_topic_score_gemma":0.00005660741,"teacher_disagreement_score":0.9737193,"about_ca_system_score_codex":0.0001714688,"about_ca_system_score_gemma":0.00041498247,"threshold_uncertainty_score":0.36975843},"labels":[],"label_agreement":null},{"id":"W4410051951","doi":"10.1038/s41746-025-01652-9","title":"Multimodal GPT model for assisting thyroid nodule diagnosis and management","year":2025,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Nodule (geology); Thyroid; Thyroid nodules; Medicine; Radiology; Medical physics; Computer science; Pathology; Internal medicine; Biology","score_opus":0.016335792338386838,"score_gpt":0.31319797271692323,"score_spread":0.2968621803785364,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410051951","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34574834,0.003449338,0.40576273,0.072066694,0.00094988977,0.0026652506,0.00004386515,0.00042269452,0.16889118],"genre_scores_gemma":[0.9785376,0.00032613706,0.0096469745,0.0038305684,0.00024096871,0.00016333186,0.00006574092,0.000028551876,0.0071601174],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987408,0.0000060454536,0.00032692656,0.0003741554,0.0002496734,0.00030240667],"domain_scores_gemma":[0.99916637,0.00027791358,0.00006365227,0.00022746217,0.00007145475,0.00019314142],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027447855,0.00018618605,0.00039184777,0.00019236933,0.000120693665,0.00004037449,0.00009664985,0.000062627965,0.000013326105],"category_scores_gemma":[0.0011555873,0.00014176052,0.00006610116,0.00017157782,0.00020405394,0.00010036457,0.00009607921,0.0002162184,0.0000030434624],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026607618,0.0003376127,0.054509144,0.0018023233,0.0003966723,0.00009251961,0.0005116966,0.00038607774,0.000608789,0.01450923,0.055998072,0.8705818],"study_design_scores_gemma":[0.007870845,0.00042114579,0.017143883,0.0020834545,0.0004481268,0.00003473052,0.00029530097,0.9277854,0.000076813245,0.0046822256,0.038902607,0.00025549225],"about_ca_topic_score_codex":0.000013254976,"about_ca_topic_score_gemma":0.0000011280949,"teacher_disagreement_score":0.9273993,"about_ca_system_score_codex":0.00005565823,"about_ca_system_score_gemma":0.000029746529,"threshold_uncertainty_score":0.5780826},"labels":[],"label_agreement":null},{"id":"W4410060872","doi":"10.1038/s41746-025-01589-z","title":"Expert of Experts Verification and Alignment (EVAL) Framework for Large Language Models Safety in Gastroenterology","year":2025,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"National Institute of Diabetes and Digestive and Kidney Diseases; National Institutes of Health","keywords":"Computer science; Medical physics; Medicine; Natural language processing; Internal medicine","score_opus":0.0731186697190006,"score_gpt":0.42059776275548383,"score_spread":0.3474790930364832,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410060872","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8761424,0.002079638,0.10291709,0.015403982,0.0004558854,0.00085680065,0.000019049052,0.000025381405,0.0020997864],"genre_scores_gemma":[0.9965671,0.0002791432,0.00084646774,0.0018182523,0.00014739546,0.000084884785,0.000078836325,0.000008305363,0.00016962376],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.99901175,0.00001730883,0.00044422038,0.00020619604,0.000119296805,0.00020122339],"domain_scores_gemma":[0.9993338,0.00023980628,0.000069125635,0.00020147866,0.000083835774,0.00007197914],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002164978,0.0000927108,0.00027832942,0.00014703117,0.000027935053,0.0000045713027,0.000046838475,0.00009671654,0.000023549745],"category_scores_gemma":[0.0005195109,0.00007591834,0.000027557451,0.000125284,0.000077079174,0.00009427281,0.000018125324,0.00007607159,7.936796e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008322283,0.0020448873,0.1412239,0.0016319938,0.00017881549,0.000021302534,0.10073635,0.000046073976,0.0125221405,0.15803279,0.008056688,0.5671828],"study_design_scores_gemma":[0.009308242,0.015059669,0.08362339,0.01851605,0.0003953187,0.00011940283,0.40351954,0.0366634,0.06942568,0.3179254,0.044336386,0.0011075191],"about_ca_topic_score_codex":0.00013059803,"about_ca_topic_score_gemma":0.000031649386,"teacher_disagreement_score":0.56607527,"about_ca_system_score_codex":0.00008138163,"about_ca_system_score_gemma":0.000053923668,"threshold_uncertainty_score":0.30958602},"labels":[],"label_agreement":null},{"id":"W4410077357","doi":"10.1038/s41746-025-01613-2","title":"Artificial intelligence guided imaging as a tool to fill gaps in health care delivery","year":2025,"lang":"en","type":"editorial","venue":"npj Digital Medicine","topic":"Ultrasound in Clinical Applications","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada); University of Toronto","funders":"","keywords":"Health care delivery; Health care; Medical imaging; Medical physics; Psychology; Computer science; Medicine; Artificial intelligence; Political science","score_opus":0.031623406733021206,"score_gpt":0.39802968690714635,"score_spread":0.36640628017412513,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410077357","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0045211166,0.005745521,0.0033495922,0.06651664,0.83097476,0.0065738377,0.0021972184,0.00065896835,0.07946234],"genre_scores_gemma":[0.061711133,0.0010917896,0.002434338,0.012710795,0.9053721,0.0006490641,0.008842049,0.00018874089,0.0069999904],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99434465,0.00005408094,0.0023237348,0.0011651446,0.0014050616,0.00070732675],"domain_scores_gemma":[0.9929985,0.00409375,0.00036414264,0.0010881422,0.0009051909,0.0005502784],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00064695213,0.00055931136,0.0014721798,0.00063103496,0.0000987883,0.000082945495,0.00054620474,0.0005136206,0.0003371784],"category_scores_gemma":[0.03025525,0.0004889699,0.00019559736,0.0011695944,0.0003059268,0.00015567863,0.00024271267,0.0016339541,0.00044673315],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022821363,0.00017846843,0.00018225802,0.0006630565,0.00003928778,0.000054905075,0.00066580245,0.0000050498693,0.000022323859,0.0004778157,0.8792395,0.1182433],"study_design_scores_gemma":[0.0004940045,0.000908204,0.00012625591,0.0054891887,0.00008940996,0.000014760696,0.0011359055,0.000019851901,0.00004456173,0.002970465,0.9883147,0.000392731],"about_ca_topic_score_codex":0.00094186043,"about_ca_topic_score_gemma":0.00014336729,"teacher_disagreement_score":0.117850564,"about_ca_system_score_codex":0.0010832781,"about_ca_system_score_gemma":0.002574573,"threshold_uncertainty_score":0.9997562},"labels":[],"label_agreement":null},{"id":"W4410180988","doi":"10.1038/s41746-025-01594-2","title":"High performance with fewer labels using semi-weakly supervised learning for pulmonary embolism diagnosis","year":2025,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Venous Thromboembolism Diagnosis and Management","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"North York General Hospital; St. Michael's Hospital; University of Toronto","funders":"","keywords":"Pulmonary embolism; Medicine; Artificial intelligence; Radiology; Pattern recognition (psychology); Machine learning; Computer science; Surgery","score_opus":0.017536285781197394,"score_gpt":0.2670570294513299,"score_spread":0.24952074367013252,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410180988","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9727151,0.00085952965,0.0011873686,0.006322273,0.0004968004,0.0014416244,0.000013447855,0.00019827121,0.016765628],"genre_scores_gemma":[0.9913426,0.00060991634,0.0005120393,0.0022968007,0.00052640593,0.0003328666,0.00016974508,0.00006792497,0.0041417168],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9978956,0.000019863342,0.00048028948,0.00054763356,0.00047282208,0.0005837944],"domain_scores_gemma":[0.9987357,0.00025513596,0.0001258899,0.0004027351,0.00027382944,0.000206654],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00023743502,0.00037721565,0.0009947869,0.0003398623,0.00025603772,0.000064415995,0.00017772005,0.00012369557,0.00015568771],"category_scores_gemma":[0.00028966716,0.0002741925,0.000095922645,0.0005755887,0.00021282234,0.0003776258,0.00011216234,0.00027720732,0.000016494145],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0020857777,0.0040672645,0.36847243,0.0063901283,0.0024992262,0.00045053317,0.0019310997,0.0033660966,0.006849899,0.008641479,0.031518593,0.5637275],"study_design_scores_gemma":[0.019736188,0.009373812,0.59642214,0.018171087,0.004555581,0.0002017858,0.0039032442,0.022318693,0.00870918,0.000972307,0.31379062,0.0018453491],"about_ca_topic_score_codex":0.00011196303,"about_ca_topic_score_gemma":0.0000040800464,"teacher_disagreement_score":0.56188214,"about_ca_system_score_codex":0.00015220484,"about_ca_system_score_gemma":0.00012405647,"threshold_uncertainty_score":0.99997103},"labels":[],"label_agreement":null},{"id":"W4410338461","doi":"10.1038/s41746-025-01677-0","title":"Integrating personalized shape prediction, biomechanical modeling, and wearables for bone stress prediction in runners","year":2025,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Lower Extremity Biomechanics and Pathologies","field":"Engineering","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Key Research and Development Program of Zhejiang Province; Science Fund for Distinguished Young Scholars of Zhejiang Province; National Key Research and Development Program of China; China Scholarship Council","keywords":"Wearable computer; Stress (linguistics); Computer science; Stress fractures; Predictive modelling; Medicine; Machine learning; Physical therapy; Embedded system","score_opus":0.01601490327838731,"score_gpt":0.24070193530536232,"score_spread":0.22468703202697501,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410338461","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.648357,0.0061364975,0.3248014,0.001468643,0.002228711,0.0012635706,0.0041065966,0.0012225059,0.010415137],"genre_scores_gemma":[0.99834394,0.00024068414,0.0005566585,0.000048606144,0.00011260301,0.00008015848,0.0003463987,0.000019370755,0.00025156257],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990254,0.000007901116,0.00034986457,0.00025688316,0.00013358601,0.00022635423],"domain_scores_gemma":[0.9996256,0.00011834016,0.00002429145,0.000116885,0.00005462131,0.000060239203],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019333498,0.00017177948,0.00026850498,0.00027416815,0.00005135093,0.000050979463,0.00008348431,0.0001394643,0.000039903407],"category_scores_gemma":[0.00032617163,0.00014249395,0.00003674008,0.00029000334,0.00006507166,0.00020651509,0.000036485802,0.00015179963,8.6524756e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008564691,0.0005654298,0.009443058,0.004421842,0.0006715916,0.00009430419,0.007310193,0.011682605,0.11276426,0.057025712,0.05541845,0.7397461],"study_design_scores_gemma":[0.0012802276,0.00015382723,0.00006703147,0.00083586946,0.000023919767,0.000007893918,0.0015329705,0.9877569,0.00020706718,0.0049015633,0.003115856,0.00011683815],"about_ca_topic_score_codex":0.000013508339,"about_ca_topic_score_gemma":0.000018185869,"teacher_disagreement_score":0.97607434,"about_ca_system_score_codex":0.00006420916,"about_ca_system_score_gemma":0.000018374805,"threshold_uncertainty_score":0.58107346},"labels":[],"label_agreement":null},{"id":"W4410340931","doi":"10.1038/s41746-025-01671-6","title":"Patient perceptions of empathy in physician and artificial intelligence chatbot responses to patient questions about cancer","year":2025,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Empathy and Medical Education","field":"Medicine","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; Princess Margaret Cancer Centre; Public Health Ontario; McMaster University; University of Toronto","funders":"","keywords":"Chatbot; Empathy; Perception; Psychology; Cancer; Medicine; World Wide Web; Computer science; Social psychology; Internal medicine","score_opus":0.02187257003682483,"score_gpt":0.3515933215733571,"score_spread":0.32972075153653224,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410340931","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9827836,0.0007805676,0.00043174048,0.011551823,0.00043232046,0.00053115014,0.000038093058,0.000025546888,0.0034251485],"genre_scores_gemma":[0.9965748,0.0001862679,0.000102377366,0.0026124972,0.0001339144,0.00011838606,0.00002767009,0.000008952025,0.00023513573],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99871397,0.000031605927,0.00051611185,0.00025946758,0.00027726655,0.00020155044],"domain_scores_gemma":[0.9991779,0.00016647328,0.00007310224,0.00019590298,0.0001695665,0.000217085],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011584095,0.00013740796,0.0003326197,0.000366156,0.000046996087,0.000009666775,0.000049050075,0.000069157046,0.000068251975],"category_scores_gemma":[0.0013999711,0.00010919904,0.000036735513,0.00062087097,0.00026786487,0.000095674666,0.000042307933,0.00018205949,0.000008414678],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044569533,0.00076113996,0.0075470847,0.00014431457,0.000024749557,0.000011237891,0.06587217,0.00001373355,0.0019858193,0.002157968,0.00079400087,0.9202421],"study_design_scores_gemma":[0.0010580696,0.0057896366,0.6862532,0.013624808,0.00025019958,0.000021896056,0.2689725,0.00037808352,0.007931112,0.0077874092,0.007467199,0.00046591234],"about_ca_topic_score_codex":0.00026244146,"about_ca_topic_score_gemma":0.00008132121,"teacher_disagreement_score":0.9197762,"about_ca_system_score_codex":0.00011169198,"about_ca_system_score_gemma":0.00024525073,"threshold_uncertainty_score":0.44530076},"labels":[],"label_agreement":null},{"id":"W4410420109","doi":"10.1038/s41746-025-01661-8","title":"FedWeight: mitigating covariate shift of federated learning on electronic health records data through patients re-weighting","year":2025,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre; McGill University; University of Calgary; University of British Columbia; Vector Institute; Mila - Quebec Artificial Intelligence Institute","funders":"Fonds de recherche du Québec – Nature et technologies; Canadian Institutes of Health Research; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Health records; Covariate; Electronic health record; Weighting; Computer science; Data science; Medicine; Machine learning; Political science; Health care","score_opus":0.03778939891977748,"score_gpt":0.3398083588284275,"score_spread":0.30201895990865,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410420109","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45329404,0.0020795134,0.3067136,0.08356854,0.0037798781,0.0021453616,0.000079439495,0.0016438115,0.14669581],"genre_scores_gemma":[0.99441206,0.000042401138,0.0024906807,0.002201036,0.0001399688,0.00000819336,0.00035057456,0.000025238025,0.0003298627],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99633884,0.00032762607,0.0009845905,0.00090395316,0.0006878458,0.00075711065],"domain_scores_gemma":[0.99710304,0.00085237843,0.00066107477,0.0010404246,0.0002034032,0.00013969601],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010855872,0.00029535213,0.00059877394,0.00019564247,0.0005087748,0.00015378337,0.001364815,0.00010085793,0.000025666834],"category_scores_gemma":[0.0032445397,0.00024877882,0.00004257067,0.0010581553,0.000104279185,0.00087526976,0.0007081146,0.0010359067,0.000017465492],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014555681,0.00040425843,0.1708948,0.0012197739,0.00018798528,0.000021360323,0.0075209946,0.0005344073,0.000027245751,0.13479109,0.006557294,0.6776952],"study_design_scores_gemma":[0.014827526,0.022633037,0.17968363,0.023899373,0.000100387704,0.000027198725,0.0019821422,0.5129241,0.00056600006,0.073710576,0.16697432,0.002671731],"about_ca_topic_score_codex":0.0009476264,"about_ca_topic_score_gemma":0.00007727002,"teacher_disagreement_score":0.6750235,"about_ca_system_score_codex":0.0002685932,"about_ca_system_score_gemma":0.00061621703,"threshold_uncertainty_score":0.9999964},"labels":[],"label_agreement":null},{"id":"W4410709191","doi":"10.1038/s41746-025-01734-8","title":"Platform matters -- Differences in COVID data collected from Android and iOS app users","year":2025,"lang":"en","type":"editorial","venue":"npj Digital Medicine","topic":"COVID-19 and Mental Health","field":"Psychology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Coronavirus disease 2019 (COVID-19); Android (operating system); Mobile apps; Smartphone app; Android app; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); 2019-20 coronavirus outbreak; Computer science; World Wide Web; Operating system; Biology; Medicine; Virology; Infectious disease (medical specialty)","score_opus":0.06513390869637474,"score_gpt":0.38842689675778436,"score_spread":0.3232929880614096,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410709191","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03177864,0.0040206322,0.00006328714,0.0041727726,0.9243366,0.0014007562,0.013826745,0.00019484482,0.020205721],"genre_scores_gemma":[0.10963414,0.0036153318,0.000047238056,0.009588896,0.76055324,0.0002662095,0.07400493,0.00018010213,0.0421099],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9968995,0.00005356688,0.00073644676,0.0011217906,0.00066778605,0.0005209182],"domain_scores_gemma":[0.99451584,0.0038930043,0.00023484806,0.000976598,0.000046047375,0.00033367414],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00026599437,0.00046279703,0.0010495988,0.0004328549,0.00008251627,0.00009860245,0.00082044024,0.0006874268,0.0005298448],"category_scores_gemma":[0.0010748013,0.00037771589,0.00003290593,0.00043447342,0.00034279455,0.00030186182,0.00042807855,0.0008773823,0.00004196479],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006163734,0.00011743357,0.004011223,0.00033166018,0.00011282922,0.000120036675,0.0012546701,1.5725139e-8,0.000002588732,0.000015832898,0.97835886,0.015058497],"study_design_scores_gemma":[0.005550385,0.0005108228,0.007046112,0.0016576411,0.00009285625,0.0000033314816,0.0018474833,0.000012141672,4.649075e-7,0.0002790094,0.9826616,0.0003381362],"about_ca_topic_score_codex":0.012433422,"about_ca_topic_score_gemma":0.0045069857,"teacher_disagreement_score":0.16378336,"about_ca_system_score_codex":0.00046303618,"about_ca_system_score_gemma":0.0010838219,"threshold_uncertainty_score":0.9998675},"labels":[],"label_agreement":null},{"id":"W4410842945","doi":"10.1038/s41746-025-01729-5","title":"Comparative analysis of natural language processing methodologies for classifying computed tomography enterography reports in Crohn’s disease patients","year":2025,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Alberta Innovates; Canadian Institutes of Health Research; Mitacs; University of Alberta; CIHR Skin Research Training Centre; Alberta Machine Intelligence Institute; Government of Canada; Canadian Institute for Advanced Research; Natural Sciences and Engineering Research Council of Canada; Alberta Health Services","keywords":"Crohn's disease; Computed tomography; Medicine; Disease; Radiology; Crohn disease; Artificial intelligence; Natural language processing; Computer science; Pathology","score_opus":0.02703396727880505,"score_gpt":0.3803729274664553,"score_spread":0.35333896018765026,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410842945","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9781195,0.0038202663,0.014296882,0.0010169995,0.00032210076,0.00066964864,0.000020153206,0.00008308195,0.0016514012],"genre_scores_gemma":[0.995105,0.000007813321,0.003671309,0.00055674673,0.00004539567,0.000033981563,0.0004988615,0.000009591183,0.00007127541],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9982657,0.000055846267,0.00070201606,0.00038604796,0.0003273211,0.00026311478],"domain_scores_gemma":[0.9985783,0.00051514874,0.00029308983,0.00024201993,0.00023149443,0.00013995363],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040353168,0.00020002188,0.0009914596,0.0016046095,0.00005153935,0.000030201407,0.00010585177,0.00005229399,0.0000057854713],"category_scores_gemma":[0.0017353185,0.00014610942,0.00027270862,0.0022324806,0.00036400493,0.00014478766,0.00005589646,0.0002824739,7.93713e-8],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004977821,0.00026729223,0.8978922,0.000532412,0.00086766126,0.00012672441,0.001404118,0.000109948094,0.00027783812,0.00005530257,0.0004919939,0.097476736],"study_design_scores_gemma":[0.0019577155,0.00013308841,0.9618769,0.0012028468,0.0011342943,0.0000021843593,0.00093412574,0.032048915,0.000050891853,0.00019252913,0.00035102112,0.00011546379],"about_ca_topic_score_codex":0.000030638585,"about_ca_topic_score_gemma":0.0000067600286,"teacher_disagreement_score":0.097361274,"about_ca_system_score_codex":0.000044926634,"about_ca_system_score_gemma":0.00006171882,"threshold_uncertainty_score":0.5958169},"labels":[],"label_agreement":null},{"id":"W4410862324","doi":"10.1038/s41746-025-01731-x","title":"An equity analysis of remote patient monitoring programs unveils assumptions on digital health equity","year":2025,"lang":"en","type":"review","venue":"npj Digital Medicine","topic":"Telemedicine and Telehealth Implementation","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; University of Toronto; Toronto Metropolitan University; University Health Network; University of Waterloo; Public Health Ontario; Women's College Hospital; Trillium Health Centre","funders":"","keywords":"Equity (law); Health equity; Equity capital markets; Business; Actuarial science; Public economics; Economics; Finance; Political science; Economic growth; Health care; Private equity","score_opus":0.18509983071898095,"score_gpt":0.5201478932135105,"score_spread":0.33504806249452956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410862324","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012792189,0.97189814,0.0011386214,0.0012596705,0.0011746492,0.005513965,0.0013343719,0.00039204778,0.016009323],"genre_scores_gemma":[0.0420006,0.94052994,0.00037024982,0.0004911301,0.0010168126,0.00011909808,0.015065141,0.00009175932,0.00031524815],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99319553,0.00012634807,0.0029818877,0.0009839578,0.0017875417,0.0009247563],"domain_scores_gemma":[0.995197,0.00048999244,0.0016633649,0.0012934557,0.0003740365,0.0009821547],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00077087374,0.0007872557,0.0049054646,0.0021097134,0.00015640327,0.000092421426,0.0004001285,0.00030936184,0.00008365608],"category_scores_gemma":[0.0009435083,0.00057088205,0.0007687676,0.0036642116,0.00025450674,0.00038066102,0.00028120796,0.0007826445,0.000016502647],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000056991372,0.00063931104,0.00078512455,0.021539327,0.0015206231,0.000029776455,0.00027970874,9.0182255e-7,2.9218552e-7,0.00008981202,0.0006807706,0.97437733],"study_design_scores_gemma":[0.0022457994,0.01602449,0.0020647575,0.08921671,0.012645098,0.000049015096,0.00095510925,0.000053724554,0.0000025360082,0.00015961326,0.87592894,0.0006541999],"about_ca_topic_score_codex":0.00023534203,"about_ca_topic_score_gemma":0.000025158259,"teacher_disagreement_score":0.9737232,"about_ca_system_score_codex":0.0010032856,"about_ca_system_score_gemma":0.0014528226,"threshold_uncertainty_score":0.99967426},"labels":[],"label_agreement":null},{"id":"W4410915363","doi":"10.1038/s41746-025-01717-9","title":"A general framework for governing marketed AI/ML medical devices","year":2025,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":45,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Social Sciences and Humanities Research Council of Canada; Social Sciences and Humanities Research Council; Novo Nordisk Fonden; Hong Kong Government; Novo Nordisk; Research Grants Council, University Grants Committee","keywords":"Food and drug administration; Adverse Event Reporting System; Adverse effect; Event (particle physics); Patient safety; Medical device; Computer science; Medicine; Medical emergency; Pharmacology; Health care","score_opus":0.091916835929367,"score_gpt":0.4670960794225148,"score_spread":0.3751792434931478,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410915363","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5465278,0.0030561436,0.12713954,0.25482202,0.00502333,0.0017381328,0.000038227587,0.00035566953,0.06129918],"genre_scores_gemma":[0.9711837,0.00008916515,0.0014323778,0.020567302,0.0022401125,0.00009762408,0.00016052471,0.000023624409,0.004205572],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981007,0.000022962719,0.0006093903,0.00034682287,0.00053394906,0.00038619724],"domain_scores_gemma":[0.99780494,0.0011477148,0.000097823606,0.0002951386,0.00031264607,0.00034173872],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00044884547,0.00018060459,0.0004062517,0.00016382735,0.00012919871,0.000037439604,0.00015295373,0.00028422414,0.00063680514],"category_scores_gemma":[0.009311584,0.00013870634,0.0000905715,0.0004491812,0.000200637,0.00016048146,0.000039125815,0.00039796627,0.00006058358],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000782704,0.00024760325,0.08055961,0.00085322914,0.00015766334,0.000033952987,0.0009141017,0.0000019438114,0.00011906416,0.02942767,0.08239699,0.80450547],"study_design_scores_gemma":[0.0012140828,0.002481707,0.043243263,0.010911282,0.00045044132,0.00013649424,0.0057790196,0.009901483,0.002011106,0.09044888,0.83279306,0.00062919216],"about_ca_topic_score_codex":0.00015736584,"about_ca_topic_score_gemma":0.000037026395,"teacher_disagreement_score":0.8038763,"about_ca_system_score_codex":0.0001383806,"about_ca_system_score_gemma":0.00057808793,"threshold_uncertainty_score":0.9990334},"labels":[],"label_agreement":null},{"id":"W4411029103","doi":"10.1038/s41746-025-01713-z","title":"A scoping review of routinely collected linked data in research on gambling harm","year":2025,"lang":"en","type":"review","venue":"npj Digital Medicine","topic":"Gambling Behavior and Treatments","field":"Psychology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Greo","funders":"","keywords":"Harm; Public health; Psychology; Mental health; Narrative review; Linkage (software); Intervention (counseling); Medicine; Social psychology; Psychiatry; Nursing","score_opus":0.7965077450069757,"score_gpt":0.664300455026394,"score_spread":0.13220728998058173,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411029103","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000018470617,0.9379989,0.0000025703396,0.0001465245,0.0006651411,0.0035651634,0.0003705351,0.000051013787,0.057181712],"genre_scores_gemma":[0.00025173766,0.99164456,0.000015557604,0.000096567775,0.00018608604,0.00038000173,0.0031229523,0.00006171947,0.004240792],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.99491924,0.0005411771,0.0018828629,0.0011327191,0.00090965367,0.00061436556],"domain_scores_gemma":[0.9941076,0.0026794958,0.00048333817,0.0023053424,0.00027826524,0.00014598342],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0020333417,0.00050374336,0.0034149834,0.0015680068,0.00005983865,0.000035402292,0.0012569788,0.00038137814,0.00048095515],"category_scores_gemma":[0.004452125,0.0003657616,0.00019078683,0.0037349125,0.00022375016,0.00010704534,0.00045194433,0.0011720008,0.00017583623],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035609042,0.000506237,0.000079598394,0.25664306,0.00015889558,0.00025690315,0.00008218009,1.1671388e-8,6.025559e-8,0.00010362909,0.0056159985,0.73651785],"study_design_scores_gemma":[0.0011357026,0.00039893764,0.000103176404,0.8859837,0.00051874603,0.000021015087,0.000035871577,2.2879455e-7,7.402143e-8,0.00001235833,0.111601256,0.0001889399],"about_ca_topic_score_codex":0.00014651146,"about_ca_topic_score_gemma":0.00002225181,"teacher_disagreement_score":0.7363289,"about_ca_system_score_codex":0.00020585084,"about_ca_system_score_gemma":0.0008732006,"threshold_uncertainty_score":0.9998794},"labels":[],"label_agreement":null},{"id":"W4411091046","doi":"10.1038/s41746-025-01730-y","title":"Foundation versus domain-specific models for left ventricular segmentation on cardiac ultrasound","year":2025,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Cardiovascular Function and Risk Factors","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Foundation (evidence); Cardiology; Internal medicine; Ultrasound; Segmentation; Domain (mathematical analysis); Cardiac Ultrasound; Medicine; Radiology; Computer science; Artificial intelligence; Mathematics; Political science; Mathematical analysis; Law","score_opus":0.023279553426098745,"score_gpt":0.28125084830986935,"score_spread":0.25797129488377063,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411091046","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.50676185,0.0025042817,0.345615,0.004237425,0.012773127,0.0041009914,0.000097743956,0.0004204305,0.12348915],"genre_scores_gemma":[0.9942891,0.000400442,0.0003144879,0.00038863337,0.0007969634,0.000056808494,0.0013754114,0.000030000392,0.002348179],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986145,0.000023601464,0.0003041507,0.00035165914,0.00048500433,0.00022106608],"domain_scores_gemma":[0.99895364,0.00034033612,0.00006333573,0.00034206497,0.00017767953,0.00012292013],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002199864,0.00019712976,0.0004148647,0.00025912805,0.00011808367,0.00004726346,0.000053907504,0.0001003904,0.00008509057],"category_scores_gemma":[0.0001597156,0.0001506017,0.00032887037,0.00027849778,0.00009932886,0.0002000663,0.0000123213285,0.00013098853,0.0000488961],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.01669549,0.0012474221,0.018788554,0.000894276,0.006470499,0.00014709333,0.002320865,0.0021666929,0.014971335,0.113191046,0.18602905,0.6370777],"study_design_scores_gemma":[0.016627802,0.001595998,0.011445901,0.00043061998,0.00063918764,0.0000340792,0.0023197874,0.00016419409,0.00249577,0.0032173858,0.9607214,0.00030788672],"about_ca_topic_score_codex":0.0000069365205,"about_ca_topic_score_gemma":9.087784e-7,"teacher_disagreement_score":0.77469236,"about_ca_system_score_codex":0.0003072157,"about_ca_system_score_gemma":0.000064795706,"threshold_uncertainty_score":0.6141359},"labels":[],"label_agreement":null},{"id":"W4411135877","doi":"10.1038/s41746-025-01708-w","title":"SQL on FHIR - Tabular views of FHIR data using FHIRPath","year":2025,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Electronic Health Records Systems","field":"Health Professions","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Google (Canada)","funders":"","keywords":"JSON; Computer science; Software portability; Implementation; Interoperability; XML; SQL; Database; Consistency (knowledge bases); XML database; Variety (cybernetics); Analytics; Software engineering; Programming language; World Wide Web","score_opus":0.3929743979072785,"score_gpt":0.5836401917415056,"score_spread":0.1906657938342271,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411135877","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4924722,0.008994865,0.006705803,0.0131909065,0.008711505,0.005487063,0.0005953674,0.0004024483,0.46343985],"genre_scores_gemma":[0.9859834,0.00018596702,0.00019312852,0.0035682854,0.0011270881,0.000057977093,0.00030562695,0.000054115157,0.008524428],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9959111,0.00037709795,0.0016166075,0.0006114174,0.0005897247,0.00089401164],"domain_scores_gemma":[0.99583375,0.0012828876,0.00057729235,0.0018283272,0.00022314242,0.0002545841],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019019747,0.00029091112,0.0009728452,0.000338739,0.0003137531,0.000008242636,0.0008174262,0.00027267513,0.00022745038],"category_scores_gemma":[0.002542773,0.00021556739,0.000050078957,0.00079582154,0.00016026228,0.0003112831,0.00037846566,0.000917518,0.00018117546],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000813026,0.0009675894,0.092523284,0.01351337,0.00046412577,0.00009942333,0.0048780157,0.000028142309,0.004673304,0.038041696,0.6124504,0.23154762],"study_design_scores_gemma":[0.0032740433,0.0009050644,0.0035685725,0.01109007,0.0000983423,0.0000064324927,0.002396671,0.0023212912,0.00008310054,0.0018064117,0.9741332,0.00031681856],"about_ca_topic_score_codex":0.0007477039,"about_ca_topic_score_gemma":0.00017461079,"teacher_disagreement_score":0.4935112,"about_ca_system_score_codex":0.00046189767,"about_ca_system_score_gemma":0.001493336,"threshold_uncertainty_score":0.8790583},"labels":[],"label_agreement":null},{"id":"W4411239302","doi":"10.1038/s41746-025-01776-y","title":"How generative AI voice agents will transform medicine","year":2025,"lang":"en","type":"review","venue":"npj Digital Medicine","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan; Royal University Hospital","funders":"","keywords":"Generative grammar; Computer science; Speech recognition; Artificial intelligence","score_opus":0.24802792299454235,"score_gpt":0.49047777204552384,"score_spread":0.2424498490509815,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411239302","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000045457177,0.9022821,0.0010500182,0.057115655,0.002834155,0.0024817935,0.00008254262,0.00014585082,0.03400332],"genre_scores_gemma":[0.0004398605,0.9552285,0.000037433147,0.004456576,0.0056156204,0.00027082814,0.0020588518,0.00008709756,0.03180521],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9957595,0.000097289696,0.0015939949,0.0009160801,0.00093797984,0.000695187],"domain_scores_gemma":[0.99660635,0.0008959651,0.00042953982,0.00080176455,0.00061619945,0.0006501669],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00041096326,0.00088271406,0.003472741,0.00080005784,0.00018305692,0.00007695837,0.00036277116,0.0006814902,0.00043050837],"category_scores_gemma":[0.0027450887,0.00056180113,0.00043418194,0.0013409263,0.0006381383,0.00053035276,0.000049605966,0.0011577815,0.00015267708],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028726343,0.00010041873,0.000009935407,0.022158794,0.00022339722,0.000064357846,0.0008070923,5.0359525e-8,5.928851e-7,0.00032314326,0.068004765,0.9082787],"study_design_scores_gemma":[0.00018850037,0.0011116329,0.0000027645451,0.07197356,0.0017781255,0.00015317978,0.0009044115,0.000008862979,0.0000092935015,0.0010524506,0.92246246,0.00035478035],"about_ca_topic_score_codex":0.00016334552,"about_ca_topic_score_gemma":0.00003334913,"teacher_disagreement_score":0.90792394,"about_ca_system_score_codex":0.0005386067,"about_ca_system_score_gemma":0.0013804622,"threshold_uncertainty_score":0.9996833},"labels":[],"label_agreement":null},{"id":"W4411325124","doi":"10.1038/s41746-025-01572-8","title":"Exploratory digital outcome measures of motor sign progression in Parkinson’s disease patients treated with prasinezumab","year":2025,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Parkinson's Disease Mechanisms and Treatments","field":"Medicine","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Centre for Movement Disorders; Montreal General Hospital","funders":"Prothena; F. Hoffmann-La Roche","keywords":"Motor symptoms; Sign (mathematics); Parkinson's disease; Medicine; Physical medicine and rehabilitation; Outcome (game theory); Disease; Internal medicine; Psychology; Oncology; Physical therapy","score_opus":0.02742494539960681,"score_gpt":0.28500332780698706,"score_spread":0.25757838240738024,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411325124","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99205965,0.00085680425,0.000119630444,0.00040690345,0.00011406804,0.0014099926,0.00022772845,0.00011386412,0.004691362],"genre_scores_gemma":[0.9983024,0.000025014957,0.00005158156,0.00016649287,0.000048190774,0.00018672265,0.00042811656,0.00004219113,0.00074927806],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9976024,0.00003211556,0.00063080486,0.0005356805,0.0008243562,0.00037461726],"domain_scores_gemma":[0.99853283,0.000081106766,0.00020392083,0.00045195076,0.0002727279,0.00045747642],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000089199144,0.00039730297,0.0007449395,0.00047710928,0.000046234254,0.000036932546,0.00013206463,0.00009005539,0.00002855725],"category_scores_gemma":[0.0005409473,0.00025051637,0.0001031801,0.000603872,0.00021725081,0.00047404342,0.000059415866,0.00015069766,0.000013390138],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0042959275,0.002408372,0.941419,0.00025199205,0.00016889133,0.00036686938,0.000089094465,9.692823e-7,0.00008850194,0.000068601024,0.00027763564,0.05056411],"study_design_scores_gemma":[0.01440345,0.0026026806,0.96966225,0.00269442,0.0003294054,0.000003651034,0.00019033928,0.000039037677,0.00031456808,0.0002000013,0.009320719,0.00023949721],"about_ca_topic_score_codex":0.000013160248,"about_ca_topic_score_gemma":0.0000041815197,"teacher_disagreement_score":0.050324615,"about_ca_system_score_codex":0.00022262518,"about_ca_system_score_gemma":0.00023914687,"threshold_uncertainty_score":0.9999947},"labels":[],"label_agreement":null},{"id":"W4411420803","doi":"10.1038/s41746-025-01714-y","title":"Predicting outcomes after moderate and severe traumatic brain injury using artificial intelligence: a systematic review","year":2025,"lang":"en","type":"review","venue":"npj Digital Medicine","topic":"Trauma and Emergency Care Studies","field":"Medicine","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Health Science Centre; Institute for Clinical Evaluative Sciences; University of Toronto; SickKids Foundation; Hospital for Sick Children; Public Health Ontario","funders":"","keywords":"Generalizability theory; Traumatic brain injury; Sample size determination; Robustness (evolution); Medicine; Psychology; Clinical psychology; Psychiatry; Statistics; Developmental psychology","score_opus":0.10241858000182504,"score_gpt":0.40356665024897453,"score_spread":0.3011480702471495,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411420803","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000741574,0.9904058,0.00019715037,0.00075792574,0.00060548604,0.0043441597,0.00014135172,0.0001329122,0.0033410832],"genre_scores_gemma":[0.0018222043,0.9954181,0.000059647824,0.0009722248,0.00030184202,0.00046828168,0.00010221238,0.000075524826,0.0007799835],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.99533343,0.0001545308,0.0026288372,0.0007075041,0.0006799539,0.00049573416],"domain_scores_gemma":[0.9975077,0.00083726307,0.0005569398,0.00064135244,0.00020334989,0.00025341715],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005777907,0.00091859134,0.0071500256,0.0004360342,0.00012788516,0.00005683939,0.0001868111,0.0002807742,0.000090405825],"category_scores_gemma":[0.0045199282,0.00055633124,0.0006125079,0.0007451019,0.00024809845,0.00020127502,0.00016895964,0.0005984944,0.000024756022],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019931498,0.000037406873,0.000019028359,0.73090345,0.0006322474,0.000077336816,0.00019127049,7.050677e-8,2.2204247e-8,0.000062052175,0.00023245103,0.26782474],"study_design_scores_gemma":[0.00011906869,0.00020525254,0.000007973384,0.98128164,0.0123253185,0.00042792436,0.00048814045,0.000045364097,8.072086e-8,0.00029093036,0.0043706177,0.00043768657],"about_ca_topic_score_codex":0.000016565307,"about_ca_topic_score_gemma":0.000007480201,"teacher_disagreement_score":0.26738706,"about_ca_system_score_codex":0.00017272292,"about_ca_system_score_gemma":0.0002989457,"threshold_uncertainty_score":0.9996888},"labels":[],"label_agreement":null},{"id":"W4411437632","doi":"10.1038/s41746-025-01769-x","title":"Liquid white box model as an explainable AI for surgery","year":2025,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"SAFER; Computer science; Task (project management); Process (computing); Artificial intelligence; Machine learning; Constant (computer programming); Engineering","score_opus":0.14338238123961417,"score_gpt":0.447061201775422,"score_spread":0.30367882053580786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411437632","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8323641,0.00057619886,0.02885549,0.083689585,0.0016868638,0.001197273,0.000018986191,0.00022436075,0.05138717],"genre_scores_gemma":[0.972487,0.00006127098,0.00018157698,0.011061424,0.0007643219,0.0001475099,0.00025305199,0.000024562187,0.015019312],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984552,0.000013263127,0.00054995343,0.0003454836,0.00024112247,0.00039493944],"domain_scores_gemma":[0.99842405,0.00037059863,0.00007252175,0.00038324,0.0004648828,0.00028473162],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038543475,0.00016984672,0.00041332236,0.00028672308,0.00013796067,0.00003486218,0.000090475885,0.00013780112,0.00011287015],"category_scores_gemma":[0.0018864265,0.00013912685,0.00008829018,0.000349707,0.00013092741,0.0004483328,0.000020363337,0.00016829548,0.0000435881],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0061380696,0.001418804,0.024084182,0.0020779078,0.00016900474,0.000055236367,0.0075382413,0.00031083377,0.0020370518,0.02452276,0.4343849,0.49726298],"study_design_scores_gemma":[0.0020609435,0.018862555,0.0037179755,0.009294448,0.0009748437,0.00023022517,0.04687571,0.08601456,0.061230958,0.2636735,0.5050525,0.002011741],"about_ca_topic_score_codex":0.00015606575,"about_ca_topic_score_gemma":0.000019679353,"teacher_disagreement_score":0.49525124,"about_ca_system_score_codex":0.000124158,"about_ca_system_score_gemma":0.000748886,"threshold_uncertainty_score":0.5673428},"labels":[],"label_agreement":null},{"id":"W4411441832","doi":"10.1038/s41746-025-01787-9","title":"Breaking geographic and language barriers in neuropsychology: online administration of MoCA in diverse populations","year":2025,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Neurobiology of Language and Bilingualism","field":"Neuroscience","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Generalizability theory; Montreal Cognitive Assessment; Neuropsychology; Psychology; Concordance; Cognition; Applied psychology; Developmental psychology; Medicine; Cognitive impairment; Psychiatry","score_opus":0.030883530761761525,"score_gpt":0.3500380281936913,"score_spread":0.31915449743192975,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411441832","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99528354,0.00010996426,0.0000073824654,0.0017858711,0.00018485817,0.0001346894,0.000033716195,0.000021711296,0.0024382859],"genre_scores_gemma":[0.9984161,0.000021040609,0.000012717988,0.0014049994,0.000024207442,0.0000024423769,0.000021655325,0.000004487249,0.000092332324],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9991899,0.000055113047,0.0002748002,0.00026389808,0.000078217774,0.00013803245],"domain_scores_gemma":[0.99958104,0.00016563074,0.00006407734,0.00013832319,0.000009666374,0.000041291696],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000087245,0.00009086184,0.00017764232,0.00039689543,0.000026187436,0.000007876023,0.000102628735,0.00005674894,0.00001678518],"category_scores_gemma":[0.001183546,0.00007638432,0.000018090803,0.0005014692,0.00031267034,0.0001255905,0.000042952925,0.00015559165,5.6351195e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004967833,0.00051025604,0.5716435,0.00013053692,0.000009179121,0.004794467,0.006191375,0.000027374384,0.35723624,0.004933322,0.00013584616,0.053891137],"study_design_scores_gemma":[0.0051063313,0.0011203095,0.9737892,0.0006087245,0.000037149843,0.00053604075,0.006111187,0.00039691155,0.00733889,0.00407994,0.0005248186,0.00035050864],"about_ca_topic_score_codex":0.000093303686,"about_ca_topic_score_gemma":0.00038070336,"teacher_disagreement_score":0.4021457,"about_ca_system_score_codex":0.000006785149,"about_ca_system_score_gemma":0.000022717926,"threshold_uncertainty_score":0.3114862},"labels":[],"label_agreement":null},{"id":"W4411485357","doi":"10.1038/s41746-025-01749-1","title":"Few shot learning for phenotype-driven diagnosis of patients with rare genetic diseases","year":2025,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Genomics and Rare Diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Wellcome Trust; National Human Genome Research Institute; National Center for Advancing Translational Sciences; National Institute of Neurological Disorders and Stroke; U.S. Air Force; European Bioinformatics Institute; Harvard Data Science Initiative, Harvard University; Common Fund; Microsoft Research; AstraZeneca; National Institutes of Health; National Science Foundation","keywords":"Disease; Clinical phenotype; Medicine; Rare disease; Medical diagnosis; Machine learning; Phenotype; Artificial intelligence; Bioinformatics; Computer science; Pathology; Gene; Biology; Genetics","score_opus":0.005285920508350112,"score_gpt":0.2271593874211226,"score_spread":0.2218734669127725,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411485357","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99601,0.001745635,0.000456481,0.00010958187,0.00008892808,0.00031317156,0.00020461527,0.000008771151,0.0010628094],"genre_scores_gemma":[0.99817085,0.000091065245,0.000072898074,0.00014980201,0.00009769148,0.00006234498,0.0010086449,0.000016360886,0.00033035423],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9993518,0.000008708315,0.0001682278,0.000227768,0.0000983799,0.0001451444],"domain_scores_gemma":[0.99948746,0.00003801576,0.000071532326,0.00016871144,0.00015577019,0.000078489495],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000013375016,0.00012342028,0.00018067667,0.000045878933,0.000047701356,0.000012051826,0.00011767941,0.000044976012,0.000016858827],"category_scores_gemma":[0.0002443691,0.00008971681,0.000059308597,0.00007718264,0.000111279034,0.0000038882677,0.000056992492,0.000029277648,8.597221e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040322574,0.00022718907,0.97563654,0.00017332107,0.00013496685,0.0000025327445,0.00002959471,0.00024262018,0.0006149636,0.000054712273,0.003025692,0.019454647],"study_design_scores_gemma":[0.0037195326,0.0023036252,0.9391616,0.00030258633,0.00026946064,7.0055603e-7,0.00019995608,0.00006327524,0.001767209,0.00022540311,0.051705204,0.0002814771],"about_ca_topic_score_codex":0.0000039715082,"about_ca_topic_score_gemma":0.0000041203675,"teacher_disagreement_score":0.048679512,"about_ca_system_score_codex":0.000007353845,"about_ca_system_score_gemma":0.00006094368,"threshold_uncertainty_score":0.3658545},"labels":[],"label_agreement":null},{"id":"W4411517551","doi":"10.1038/s41746-025-01793-x","title":"Author Correction: Patient perceptions of empathy in physician and artificial intelligence chatbot responses to patient questions about cancer","year":2025,"lang":"en","type":"erratum","venue":"npj Digital Medicine","topic":"Empathy and Medical Education","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; Princess Margaret Cancer Centre; Public Health Ontario; McMaster University; University of Toronto","funders":"","keywords":"Chatbot; Empathy; Perception; Psychology; Medicine; Medical education; Artificial intelligence; Computer science; Social psychology; Neuroscience","score_opus":0.02723350731082351,"score_gpt":0.3541193089833024,"score_spread":0.3268858016724789,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411517551","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7405498,0.012198186,0.0012495033,0.06080351,0.110879876,0.0050902986,0.0011045397,0.00026539213,0.0678589],"genre_scores_gemma":[0.934037,0.0011158056,0.000083392755,0.0028086673,0.0023806358,0.00046161583,0.0007039321,0.000045734618,0.058363184],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972634,0.00007701699,0.0010387582,0.0005872042,0.0006778155,0.00035583836],"domain_scores_gemma":[0.99817693,0.0002690171,0.00027328526,0.00039568456,0.000441244,0.00044383528],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00019185797,0.0003746855,0.0008866916,0.00081241457,0.00009403854,0.000023958328,0.00011141037,0.00038273586,0.00019534687],"category_scores_gemma":[0.003423562,0.00031284374,0.000103397935,0.0009677142,0.000417727,0.00012244366,0.00008643071,0.0009473935,0.000015367437],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046435752,0.00075398566,0.0003653594,0.000428655,0.000052202173,0.000025635183,0.053053375,0.0000082125225,0.000058901674,0.00017063909,0.2973564,0.6472623],"study_design_scores_gemma":[0.001131963,0.01495225,0.10905846,0.08454299,0.001220564,0.00011853172,0.3127618,0.0008777622,0.00080349547,0.002422107,0.47051913,0.0015909453],"about_ca_topic_score_codex":0.0006051121,"about_ca_topic_score_gemma":0.00027116155,"teacher_disagreement_score":0.6456713,"about_ca_system_score_codex":0.000350052,"about_ca_system_score_gemma":0.0011505294,"threshold_uncertainty_score":0.99993235},"labels":[],"label_agreement":null},{"id":"W4412177579","doi":"10.1038/s41746-025-01856-z","title":"Leveraging retinal vascular features in non-invasive, early diagnosis of preeclampsia","year":2025,"lang":"en","type":"editorial","venue":"npj Digital Medicine","topic":"Pregnancy and preeclampsia studies","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Retinal; Preeclampsia; Ophthalmology; Medicine; Computer science; Biology; Pregnancy","score_opus":0.01007991421159916,"score_gpt":0.26353163630142945,"score_spread":0.2534517220898303,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412177579","genre_codex":"editorial","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.048981693,0.055815876,0.00009212654,0.002744892,0.67917705,0.0034300766,0.0005661365,0.00026854718,0.20892362],"genre_scores_gemma":[0.5955436,0.011313633,0.0001718136,0.00023540681,0.38373905,0.00048008093,0.00129956,0.0001295745,0.0070872344],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99564415,0.00007419725,0.001075365,0.0008996181,0.0016759145,0.00063078245],"domain_scores_gemma":[0.9952273,0.0027794647,0.00040636887,0.00092476775,0.0004631155,0.00019902173],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00045700534,0.0007363769,0.0022705619,0.0007240224,0.00007805334,0.00003564236,0.00046889464,0.0009882515,0.000059332357],"category_scores_gemma":[0.008045424,0.00059337163,0.00039275704,0.0007413732,0.0005433277,0.00022621236,0.00031872926,0.0018094502,0.000010191494],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004595488,0.00022709907,0.06067454,0.0042514703,0.0007065257,0.00037245947,0.0021374729,0.0000017158912,0.000021462276,0.000031331085,0.9240311,0.00708528],"study_design_scores_gemma":[0.01439624,0.0033766883,0.21361844,0.12756209,0.002147301,0.000026206917,0.00093855645,0.0000043109485,0.0007257431,0.0013492864,0.63457423,0.0012808762],"about_ca_topic_score_codex":0.0004721061,"about_ca_topic_score_gemma":0.00006506966,"teacher_disagreement_score":0.54656196,"about_ca_system_score_codex":0.00020848734,"about_ca_system_score_gemma":0.00064001646,"threshold_uncertainty_score":0.9996518},"labels":[],"label_agreement":null},{"id":"W4412415311","doi":"10.1038/s41746-025-01781-1","title":"COLA-GLM: collaborative one-shot and lossless algorithms of generalized linear models for decentralized observational healthcare data","year":2025,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Health, Environment, Cognitive Aging","field":"Environmental Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"National Center for Advancing Translational Sciences; Patient-Centered Outcomes Research Institute; U.S. National Library of Medicine; National Institute on Aging; National Institutes of Health; National Institute of Allergy and Infectious Diseases","keywords":"Generalized linear model; Observational study; Lossless compression; Algorithm; Computer science; Generalized linear mixed model; Linear model; Mathematics; Data mining; Statistics; Data compression","score_opus":0.19570447180624165,"score_gpt":0.3864879120330753,"score_spread":0.19078344022683366,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412415311","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7805725,0.002580111,0.16272458,0.034473415,0.0004905656,0.0054660235,0.0057490994,0.00010737781,0.007836356],"genre_scores_gemma":[0.9762487,0.0008552183,0.017457249,0.003119128,0.00009665562,0.00010765513,0.0016287527,0.0000301859,0.00045647018],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997791,0.0000765341,0.00056476385,0.00070472376,0.00049226434,0.00037072194],"domain_scores_gemma":[0.99858344,0.00042759857,0.00019469693,0.00050687895,0.000071264425,0.00021614235],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00055824965,0.0002106142,0.00046052696,0.000063222345,0.00014304137,0.000022322956,0.00034331097,0.000097448115,0.00012413398],"category_scores_gemma":[0.00052186917,0.00019159228,0.000024531666,0.00045084348,0.0005745883,0.00074108783,0.00035044647,0.00013194988,0.000005249249],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003347047,0.0024109536,0.29214132,0.0025037427,0.0009404536,0.00004447501,0.009263651,0.00614812,0.01820291,0.038254306,0.031317662,0.59542537],"study_design_scores_gemma":[0.03422977,0.0023448858,0.2357099,0.002605806,0.0005251414,0.00001887391,0.0051205736,0.47966868,0.0047636735,0.056035686,0.1770578,0.0019192153],"about_ca_topic_score_codex":0.0003098324,"about_ca_topic_score_gemma":0.000110453664,"teacher_disagreement_score":0.59350616,"about_ca_system_score_codex":0.00017966711,"about_ca_system_score_gemma":0.00012244737,"threshold_uncertainty_score":0.7812906},"labels":[],"label_agreement":null},{"id":"W4412492683","doi":"10.1038/s41746-025-01867-w","title":"Commercialization of medical artificial intelligence technologies: challenges and opportunities","year":2025,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Aortic aneurysm repair treatments","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"HORIZON EUROPE Framework Programme","keywords":"Commercialization; Computer science; Artificial intelligence; Data science; Business; Marketing","score_opus":0.11966165964490702,"score_gpt":0.35208222806657447,"score_spread":0.23242056842166745,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412492683","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3344346,0.043322634,0.012545512,0.37230653,0.00074082514,0.0014379492,0.000024340436,0.0010986886,0.23408893],"genre_scores_gemma":[0.9898346,0.0091439895,0.0000698999,0.0003814325,0.000044505567,0.000015137706,0.000025755031,0.000009901143,0.00047474905],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99860924,0.000015873115,0.00048575908,0.00021868527,0.0005171882,0.00015322996],"domain_scores_gemma":[0.9992373,0.00020722771,0.0000936175,0.00025955148,0.00010923043,0.0000930491],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021638509,0.00014394711,0.00041397722,0.00022382541,0.000030640258,0.000006681762,0.00011922442,0.00017906632,0.00007007413],"category_scores_gemma":[0.0016206217,0.0001049767,0.000032532094,0.00013645759,0.00090471614,0.00007452253,0.00011783728,0.00013268652,0.000003596162],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007817585,0.00018806296,0.0012449259,0.0002688911,0.00007909665,0.0001057119,0.0004329209,8.920165e-8,0.00002771355,0.12010699,0.0005123989,0.87695503],"study_design_scores_gemma":[0.0096576335,0.01825924,0.06692872,0.032295223,0.0031079175,0.002352643,0.247745,0.008123889,0.017220367,0.45559287,0.13675378,0.0019626925],"about_ca_topic_score_codex":0.000012257917,"about_ca_topic_score_gemma":0.000004728851,"teacher_disagreement_score":0.8749923,"about_ca_system_score_codex":0.000031529624,"about_ca_system_score_gemma":0.00012220752,"threshold_uncertainty_score":0.4280826},"labels":[],"label_agreement":null},{"id":"W4412493510","doi":"10.1038/s41746-025-01821-w","title":"Negative control-calibrated difference-in-difference analyses: addressing unmeasured confounding in RWD with application to racial/ethnic differences","year":2025,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Center for Advancing Translational Sciences; National Institute of Diabetes and Digestive and Kidney Diseases; National Institute of Allergy and Infectious Diseases; National Eye Institute; National Institute of Mental Health; U.S. National Library of Medicine; Patient-Centered Outcomes Research Institute; National Institute on Aging; National Institutes of Health","keywords":"Confounding; Ethnic group; Causal inference; Health records; Health equity; Control (management); Health care; Medicine; Psychology; Computer science; Statistics; Mathematics; Public health; Artificial intelligence; Nursing; Internal medicine","score_opus":0.19159917289522901,"score_gpt":0.4660973734039519,"score_spread":0.27449820050872287,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412493510","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5851677,0.00014789762,0.40581015,0.000751872,0.0000646813,0.0013772418,0.00001798151,0.0003094015,0.006353071],"genre_scores_gemma":[0.9964132,0.000019487685,0.0023734826,0.00036986303,0.000051311737,0.0004064519,0.000020462465,0.000032178345,0.00031361447],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99714446,0.00015136234,0.0009116132,0.00067495677,0.0005649578,0.0005526217],"domain_scores_gemma":[0.9966749,0.0020683974,0.00032505838,0.0005109258,0.00024636014,0.00017436793],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003668761,0.00046826896,0.0011362974,0.0007723429,0.00007772416,0.00010500502,0.00046748464,0.00018279617,0.00002501368],"category_scores_gemma":[0.003077459,0.00033532697,0.0000461766,0.002174338,0.00040067284,0.00039492248,0.00008882007,0.00049264304,0.0000049185664],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0035130477,0.0016964298,0.25209665,0.001202514,0.0005488937,0.00019561735,0.015587582,0.0003609693,0.23930357,0.20402034,0.00026410978,0.28121027],"study_design_scores_gemma":[0.006953993,0.0012472301,0.3124357,0.011345692,0.00020335455,0.000009511136,0.0040230122,0.007431225,0.012154855,0.6429501,0.000039344304,0.0012059393],"about_ca_topic_score_codex":0.00018700378,"about_ca_topic_score_gemma":0.0010583458,"teacher_disagreement_score":0.4389298,"about_ca_system_score_codex":0.0003272925,"about_ca_system_score_gemma":0.00016739343,"threshold_uncertainty_score":0.9999099},"labels":[],"label_agreement":null},{"id":"W4412521323","doi":"10.1038/s41746-025-01847-0","title":"A randomized controlled trial of a digital cognitive behavioral therapy for insomnia for older adults","year":2025,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Sleep and related disorders","field":"Psychology","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"National Institutes of Health","keywords":"Insomnia; Cognitive behavioral therapy for insomnia; Randomized controlled trial; Sleep onset latency; Medicine; Physical therapy; Cognitive behavioral therapy; Population; Cognition; Sleep onset; Psychiatry; Clinical psychology; Internal medicine","score_opus":0.017703968686758106,"score_gpt":0.35003974165360285,"score_spread":0.33233577296684474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412521323","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90177286,0.002758136,0.0045375414,0.0011851774,0.0030368806,0.025712984,0.00026992866,0.000093867944,0.060632654],"genre_scores_gemma":[0.9900032,0.000044720666,0.0000102595595,0.00029580962,0.000220988,0.004797416,0.0002787817,0.000030105854,0.004318692],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.998169,0.000056291236,0.0008967296,0.00036616364,0.00019334487,0.00031847623],"domain_scores_gemma":[0.9957386,0.0033659944,0.00030229765,0.00018554511,0.0003290888,0.00007846457],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003481764,0.00026889873,0.001640359,0.00026368213,0.00005137975,0.000031635587,0.0001466574,0.00024580903,0.00013544982],"category_scores_gemma":[0.0015409488,0.00016711278,0.00064005266,0.00021349684,0.00047758417,0.00013728562,0.000015805119,0.00012307445,0.0000070830147],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.8812255,0.0023623593,0.000044643588,0.000021908152,0.0017998456,0.00000220535,0.0021236655,9.4066706e-8,0.000004030023,0.0014351596,0.002766785,0.108213775],"study_design_scores_gemma":[0.9881878,0.0034824107,0.000030312605,0.0003575497,0.0008469846,0.0000016327831,0.003516506,0.00003328423,0.00001634385,0.0022292293,0.0011411194,0.00015683271],"about_ca_topic_score_codex":0.000014872208,"about_ca_topic_score_gemma":0.0000013219949,"teacher_disagreement_score":0.10805694,"about_ca_system_score_codex":0.000013724385,"about_ca_system_score_gemma":0.000066846216,"threshold_uncertainty_score":0.68146616},"labels":[],"label_agreement":null},{"id":"W4412523007","doi":"10.1038/s41746-025-01846-1","title":"Unlocking efficiency in real-world collaborative studies: a multi-site international study with one-shot lossless GLMM algorithm","year":2025,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"National Center for Advancing Translational Sciences; National Institute of Diabetes and Digestive and Kidney Diseases; National Institute of Allergy and Infectious Diseases; National Eye Institute; National Institute of Mental Health; U.S. National Library of Medicine; Patient-Centered Outcomes Research Institute; National Institute on Aging; National Institutes of Health; U.S. Department of Veterans Affairs","keywords":"Lossless compression; Computer science; Generalized linear mixed model; Homomorphic encryption; Data mining; Algorithm; Encryption; Statistics; Econometrics; Data compression; Machine learning; Computer security; Mathematics","score_opus":0.07732397268261708,"score_gpt":0.3788656639012991,"score_spread":0.301541691218682,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412523007","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29777646,0.0014709758,0.6032641,0.057429742,0.0028539682,0.0034613088,0.00021408261,0.0020918085,0.031437572],"genre_scores_gemma":[0.95096195,0.000097367425,0.048122264,0.00025122348,0.000061809835,0.00010408414,0.000026828497,0.000013972332,0.00036048808],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99737006,0.00006082652,0.00053996244,0.0008793201,0.0007488052,0.0004010403],"domain_scores_gemma":[0.9957945,0.0005371149,0.00018738347,0.0029704995,0.00044769264,0.00006281643],"candidate_categories":["metaresearch","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.00054714177,0.0002900038,0.0005114999,0.00089989067,0.00010914233,0.00019556745,0.009840694,0.000059756076,0.0000042258716],"category_scores_gemma":[0.009195963,0.00022177439,0.000021329795,0.004017338,0.00043695024,0.0010728731,0.020419624,0.00036958652,0.000008355553],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003798578,0.0072080176,0.37201497,0.00022883782,0.0016841589,0.0023475944,0.020214656,0.00028767964,0.00029648416,0.010015355,0.042221673,0.5431007],"study_design_scores_gemma":[0.03995093,0.008444286,0.22674362,0.012413572,0.00022268326,0.00005785834,0.0621993,0.5764093,0.0019012595,0.059335485,0.009131349,0.0031903742],"about_ca_topic_score_codex":0.00018521777,"about_ca_topic_score_gemma":0.00092401385,"teacher_disagreement_score":0.6531855,"about_ca_system_score_codex":0.000419336,"about_ca_system_score_gemma":0.0001729508,"threshold_uncertainty_score":0.99915},"labels":[],"label_agreement":null},{"id":"W4412545680","doi":"10.1038/s41746-025-01782-0","title":"Modeling trajectories of routine blood tests as dynamic biomarkers for outcome in spinal cord injury","year":2025,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Spinal Cord Injury Research","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; International Collaboration On Repair Discoveries; University of British Columbia; University of Waterloo","funders":"Departament de Recerca i Universitats, Generalitat de Catalunya; University of California, San Francisco; Centro de Investigación Biomédica en Red de Salud Mental; Generalitat de Catalunya; Agencia Estatal de Investigación; Wings for Life; Craig H. Neilsen Foundation; U.S. Department of Defense","keywords":"Medicine; Spinal cord injury; Receiver operating characteristic; Injury Severity Score; Area under the curve; Internal medicine; Spinal cord; Physical therapy; Anesthesia; Poison control; Emergency medicine; Injury prevention","score_opus":0.05263423305394568,"score_gpt":0.4353869461618379,"score_spread":0.3827527131078922,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412545680","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9867639,0.0007910834,0.0011781222,0.0029181975,0.00031743365,0.0011201879,0.000047653513,0.00006906057,0.006794391],"genre_scores_gemma":[0.997669,0.00003413566,0.00046200148,0.00027061146,0.000099529345,0.00007628003,0.00007550166,0.00003516037,0.00127782],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9975178,0.000021519898,0.0009515072,0.00043949124,0.0005790792,0.00049057143],"domain_scores_gemma":[0.9986994,0.00021444299,0.00009771994,0.0004325752,0.00037987862,0.0001759436],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005205259,0.0002754567,0.00082880305,0.0008492615,0.000042419757,0.000018812327,0.00024159705,0.0001377486,0.000040302868],"category_scores_gemma":[0.004297304,0.00022114252,0.00013393202,0.0011229381,0.0003132769,0.00019071747,0.000095237,0.0003205399,0.0000064018104],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.13067408,0.0018357123,0.4684114,0.0048105097,0.0010142272,0.00028730126,0.00017292555,0.000023506025,0.07279716,0.0040885825,0.0007076822,0.31517693],"study_design_scores_gemma":[0.066415004,0.25951236,0.54425037,0.022881348,0.002380509,0.0005423864,0.0072094626,0.05750471,0.016055565,0.018412102,0.0026916575,0.0021445022],"about_ca_topic_score_codex":0.0002444411,"about_ca_topic_score_gemma":0.0000420547,"teacher_disagreement_score":0.31303245,"about_ca_system_score_codex":0.00016792335,"about_ca_system_score_gemma":0.0003215354,"threshold_uncertainty_score":0.90179306},"labels":[],"label_agreement":null},{"id":"W4412631047","doi":"10.1038/s41746-025-01788-8","title":"Personalized federated learning for predicting disability progression in multiple sclerosis using real-world routine clinical data","year":2025,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Cegep de Saint Jerome; Centre intégré de santé et de services sociaux de Chaudière-Appalaches; Université de Montréal","funders":"Cliniques Universitaires Saint-Luc; Faculty of Medicine and Health, University of Sydney; Allergan; EMD Serono; Koç Üniversitesi Translasyonel Tıp Araştırma Merkezi; Szegedi Tudományegyetem; Vlaamse regering; Universiteit Hasselt; Debreceni Egyetem; Universiteit Antwerpen; Koning Boudewijnstichting; lékařská fakulta Univerzity Karlovy; Teva Pharmaceutical Industries; Università di Bologna; Razi University; Hunter Medical Research Institute; Univerzita Karlova v Praze; Karadeniz Teknik Üniversitesi; Sanofi Genzyme; Universität Basel; Agentschap Innoveren en Ondernemen; KU Leuven; Università degli Studi di Firenze; Eisai; Universidade do Porto; Fonds Wetenschappelijk Onderzoek; Všeobecná Fakultní Nemocnice v Praze; Biogen; Celgene; Koç Üniversitesi; H. Lundbeck A/S; Monash University; Alexion Pharmaceuticals; European Commission; Multiple Sclerosis International Federation; Sultan Qaboos University; Sanofi; American University of Beirut; Bristol-Myers Squibb; Università di Catania; Amgen","keywords":"Multiple sclerosis; Real world data; Computer science; Medicine; Data science; Psychiatry","score_opus":0.20644145412923182,"score_gpt":0.41874933950563153,"score_spread":0.21230788537639972,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412631047","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5189584,0.00016831102,0.4744191,0.002528763,0.0013856381,0.0009839521,0.000016571656,0.0003934552,0.0011458143],"genre_scores_gemma":[0.9923364,0.000022444015,0.00688647,0.0001029591,0.00032016446,0.000036919784,0.0000830405,0.000014526315,0.00019707161],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99747306,0.00015447443,0.0007960891,0.0008799201,0.00035008832,0.00034636317],"domain_scores_gemma":[0.99734324,0.001549955,0.00023655304,0.00064559537,0.00012464651,0.00009998537],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017965656,0.0001858093,0.00042162882,0.00012684439,0.00027023983,0.00018274362,0.00067723484,0.00009644715,0.000005113815],"category_scores_gemma":[0.004726878,0.00015484258,0.000053864416,0.0010341895,0.00033209767,0.0010937611,0.0006607891,0.0003797954,0.0000010808064],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019059269,0.00012808121,0.6312663,0.00007596549,0.00002161698,0.0000018152543,0.00015684075,0.00013423632,0.0002545909,0.000117636955,0.0002466159,0.3674057],"study_design_scores_gemma":[0.0034219294,0.00027663633,0.10777698,0.0015557288,0.000020657953,0.000001939283,0.0001773213,0.8843067,0.00013826817,0.0002227066,0.0019469243,0.00015417262],"about_ca_topic_score_codex":0.000310257,"about_ca_topic_score_gemma":0.000318564,"teacher_disagreement_score":0.8841725,"about_ca_system_score_codex":0.0003136073,"about_ca_system_score_gemma":0.00014483366,"threshold_uncertainty_score":0.63142973},"labels":[],"label_agreement":null},{"id":"W4412638611","doi":"10.1038/s41746-025-01865-y","title":"Predicting outcomes following endovascular aortoiliac revascularization using machine learning","year":2025,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Peripheral Artery Disease Management","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Medical Association; University Health Network; Artificial Intelligence in Medicine (Canada); University of Toronto; St. Michael's Hospital","funders":"Physicians' Services Incorporated Foundation; Canadian Institutes of Health Research; Canadian Society for Vascular Surgery; Brigham and Women's Hospital; University of Toronto; Ministry of Health, Ontario","keywords":"Logistic regression; Medicine; Aortoiliac occlusive disease; Revascularization; Machine learning; Surgery; Internal medicine; Computer science","score_opus":0.01414783431449215,"score_gpt":0.28351279598300394,"score_spread":0.2693649616685118,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412638611","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9612239,0.0017583568,0.008262172,0.0021318635,0.00063429395,0.00080395304,0.000004175644,0.00042123217,0.024760023],"genre_scores_gemma":[0.9937468,0.000032099426,0.0004169462,0.0012369521,0.00014560597,0.00002401069,0.00020819357,0.00004035691,0.004149035],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9978064,0.000051400657,0.00056849123,0.0004824335,0.000700581,0.00039071066],"domain_scores_gemma":[0.9990717,0.00008677202,0.0001113288,0.0004457749,0.00009105631,0.00019335013],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035146187,0.00030730173,0.0006645321,0.00033015723,0.00019914177,0.00006586678,0.00013110937,0.00007977669,0.00010991618],"category_scores_gemma":[0.0013613725,0.00024243815,0.00033888122,0.0006111864,0.00008633826,0.00037775427,0.00015646216,0.00028631603,0.000017582142],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004144422,0.000119839766,0.9805102,0.00024009474,0.00087026856,0.00017112007,0.00013510928,0.00023115875,0.0021533475,0.00019093018,0.000090195215,0.015246318],"study_design_scores_gemma":[0.019781917,0.0009227491,0.78396624,0.0067973766,0.0053403606,0.00008029133,0.0016326773,0.12638755,0.00067230733,0.0008354983,0.052503537,0.0010795037],"about_ca_topic_score_codex":0.00010519919,"about_ca_topic_score_gemma":0.000005976535,"teacher_disagreement_score":0.19654395,"about_ca_system_score_codex":0.00021127744,"about_ca_system_score_gemma":0.00006962155,"threshold_uncertainty_score":0.98863405},"labels":[],"label_agreement":null},{"id":"W4412824780","doi":"10.1038/s41746-025-01809-6","title":"Design specifications for biomedical virtual twins in engineered adoptive cellular immunotherapies","year":2025,"lang":"en","type":"review","venue":"npj Digital Medicine","topic":"CAR-T cell therapy research","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Care Foundation","funders":"National Cancer Institute; European Commission","keywords":"Immune system; Computer science; Computational biology; Adoptive cell transfer; Psychology; Neuroscience; Human–computer interaction; Medicine; Biology; Immunology; T cell","score_opus":0.12884270219560104,"score_gpt":0.36965207301881325,"score_spread":0.24080937082321222,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412824780","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000038667104,0.96043867,0.026643433,0.0007860695,0.00055038976,0.005582032,0.00027360438,0.00013206461,0.0055898754],"genre_scores_gemma":[0.00008460083,0.9661688,0.00079281884,0.00010164869,0.001140763,0.0011407314,0.00224981,0.00015386239,0.028166967],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9960421,0.00013362191,0.0013869228,0.0008283198,0.00087389245,0.0007351715],"domain_scores_gemma":[0.9946447,0.0035917908,0.0002206656,0.0009488014,0.00025045974,0.00034355448],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00077651057,0.0007374867,0.0031019393,0.0017448247,0.00006715735,0.000057265428,0.0005374105,0.000608582,0.0012429545],"category_scores_gemma":[0.001866009,0.00054455746,0.00056134723,0.0017684257,0.00062553986,0.0001242459,0.00009662259,0.0009737919,0.00008340365],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028931172,0.00043786998,9.927357e-7,0.007837864,0.0005988689,0.000100696816,0.00038506425,8.54526e-7,0.000320146,0.00062814984,0.005102884,0.9842973],"study_design_scores_gemma":[0.0031681072,0.0018169979,0.0000031221696,0.028620174,0.000510317,0.00005279911,0.00027344134,0.00004072999,0.000028420009,0.0001303284,0.9649762,0.0003793913],"about_ca_topic_score_codex":0.000011088187,"about_ca_topic_score_gemma":0.0000010590156,"teacher_disagreement_score":0.9839179,"about_ca_system_score_codex":0.0006443802,"about_ca_system_score_gemma":0.0013899063,"threshold_uncertainty_score":0.9997006},"labels":[],"label_agreement":null},{"id":"W4413025308","doi":"10.1038/s41746-025-01785-x","title":"Evaluation of the NHS active 10 walking app intervention through time-series analysis in 201,688 individuals","year":2025,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Physical Activity and Health","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brock University","funders":"NIHR Cambridge Biomedical Research Centre; Medical Research Council; National Institute for Health and Care Research","keywords":"Confidence interval; Medicine; Physical therapy; Download; Mobile apps; Interrupted Time Series Analysis; Smartphone app; Baseline (sea); Intervention (counseling); Gerontology; Computer science; Nursing; Internal medicine; World Wide Web","score_opus":0.04303133617467004,"score_gpt":0.3796007687839775,"score_spread":0.3365694326093075,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413025308","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9219041,0.0002489597,0.0002664669,0.005303975,0.000114137496,0.0005765408,0.00003061241,0.000024674799,0.07153055],"genre_scores_gemma":[0.99790657,0.000013688543,0.000021045991,0.00018151132,0.00008019561,0.000024467836,0.00008634422,0.0000058391092,0.0016803358],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.998296,0.00014064343,0.00039725864,0.0002112618,0.0007941354,0.00016067839],"domain_scores_gemma":[0.99902594,0.00020383215,0.00019504275,0.0002688826,0.00026686903,0.00003941516],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008498841,0.000119614924,0.00055989524,0.0002313776,0.000044643843,0.000010136318,0.000105917185,0.00007330982,0.00036938858],"category_scores_gemma":[0.001488197,0.00007636389,0.00015690853,0.0013888446,0.00019433376,0.00043505427,0.00007269009,0.00021232956,0.000013861903],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001231075,0.004379027,0.06261167,0.0009077051,0.0040809712,0.0000054336474,0.010278211,0.00014832387,0.005623493,0.004802783,0.006115741,0.89981556],"study_design_scores_gemma":[0.00590251,0.0012855587,0.9267162,0.0030241122,0.0049376474,0.0000035894814,0.0022787452,0.001933876,0.008763605,0.041833077,0.0031377722,0.0001833093],"about_ca_topic_score_codex":0.0001683914,"about_ca_topic_score_gemma":0.00010287192,"teacher_disagreement_score":0.8996323,"about_ca_system_score_codex":0.0002057577,"about_ca_system_score_gemma":0.000155097,"threshold_uncertainty_score":0.4044546},"labels":[],"label_agreement":null},{"id":"W4413101641","doi":"10.1038/s41746-025-01885-8","title":"Next-generation AI framework for comprehensive oral leukoplakia evaluation and management","year":2025,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Oral Health Pathology and Treatment","field":"Dentistry","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Key Research and Development Program of Zhejiang Province; University of Toronto","keywords":"Medicine; Leukoplakia; Cancer; Dysplasia; Medical physics; Oncology; Internal medicine","score_opus":0.13863102041058403,"score_gpt":0.43334405007988225,"score_spread":0.29471302966929824,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413101641","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9361905,0.0032201728,0.036168456,0.0071364734,0.0030160742,0.002618236,0.000053955508,0.0001374573,0.011458673],"genre_scores_gemma":[0.99432015,0.00005809139,0.0014585911,0.00238078,0.00018876171,0.00018655662,0.00029810664,0.000007774509,0.001101182],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9991441,0.000028148632,0.00023033122,0.000256841,0.00017940592,0.00016117617],"domain_scores_gemma":[0.99944484,0.00014473966,0.00005630393,0.00016581237,0.0001349997,0.000053318105],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015207287,0.00011984351,0.00019276982,0.00008794458,0.0001301439,0.000034061577,0.00004594312,0.00010507624,0.000045698005],"category_scores_gemma":[0.00011339973,0.00009673269,0.00002449432,0.00011701076,0.00008951305,0.00016985503,0.000032931155,0.00009009757,0.000037902926],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035467776,0.00023327224,0.014126061,0.00065737433,0.0002767256,0.00009723669,0.00027355226,0.000029152916,0.00016780797,0.25816724,0.052501593,0.6731153],"study_design_scores_gemma":[0.023379914,0.00302968,0.41761371,0.002086342,0.0018800262,0.00013576135,0.0018510817,0.021316556,0.00074235786,0.38902074,0.13817683,0.00076699426],"about_ca_topic_score_codex":0.0000070410274,"about_ca_topic_score_gemma":0.000021838454,"teacher_disagreement_score":0.6723483,"about_ca_system_score_codex":0.00008039414,"about_ca_system_score_gemma":0.000025861389,"threshold_uncertainty_score":0.39446446},"labels":[],"label_agreement":null},{"id":"W4413112041","doi":"10.1038/s41746-025-01913-7","title":"Systematic review on the technology’s role in supporting lung cancer patients in the treatment journey","year":2025,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Cancer survivorship and care","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Herbert Irving Comprehensive Cancer Center, Columbia University","keywords":"Telehealth; Psychological intervention; Intervention (counseling); Medicine; Lung cancer; Distress; Systematic review; Telemedicine; MEDLINE; Intensive care medicine; Psychology; Health care; Nursing; Clinical psychology; Oncology","score_opus":0.011587656336277799,"score_gpt":0.31449894429511366,"score_spread":0.3029112879588359,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413112041","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7702536,0.097054385,0.0000031126617,0.085353084,0.00048159782,0.0050630746,0.000020388876,0.000056837383,0.041713927],"genre_scores_gemma":[0.9878586,0.0041345377,3.2655134e-7,0.0065207505,0.000051769915,0.00070373813,0.000018840226,0.000009730699,0.00070172374],"study_design_codex":"observational","study_design_gemma":"systematic_review","domain_scores_codex":[0.99858195,0.000063432104,0.00058365933,0.0001976557,0.00033335222,0.00023996827],"domain_scores_gemma":[0.9990728,0.0002735311,0.0001420126,0.0004083776,0.00006772446,0.000035554192],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044150956,0.0001709832,0.0006023852,0.00021293221,0.00003918837,0.000015345391,0.00018604512,0.000059780705,0.00005011956],"category_scores_gemma":[0.0009431837,0.00007134414,0.00006804232,0.00091485895,0.000074599266,0.000046349192,0.000020555693,0.00025206822,0.0000061167552],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000256869,0.0019657116,0.7576139,0.15554535,0.0005387876,0.0002837317,0.015552696,0.0000042461234,0.000030792577,0.0039725024,0.01631983,0.04791559],"study_design_scores_gemma":[0.0054229335,0.002078738,0.039417,0.92408526,0.0012778074,0.000026681022,0.019574206,0.00012912198,0.00012942257,0.0008110697,0.006729621,0.00031815426],"about_ca_topic_score_codex":0.00043373613,"about_ca_topic_score_gemma":0.001221975,"teacher_disagreement_score":0.7685399,"about_ca_system_score_codex":0.0003839943,"about_ca_system_score_gemma":0.0000936409,"threshold_uncertainty_score":0.29093295},"labels":[],"label_agreement":null},{"id":"W4413257288","doi":"10.1038/s41746-025-01909-3","title":"Establishing organizational AI governance in healthcare: a case study in Canada","year":2025,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Trillium Health Centre","funders":"","keywords":"Corporate governance; Knowledge management; Health care; Context (archaeology); Stakeholder; Process (computing); Work (physics); Conceptual framework; Project governance; Business; Process management; Public relations; Political science; Sociology; Engineering; Computer science; Social science","score_opus":0.05621195265910539,"score_gpt":0.3895348396450215,"score_spread":0.3333228869859161,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413257288","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9264374,0.0004032093,0.000031108866,0.06981395,0.00073573884,0.00060965534,0.000006955502,0.00001626032,0.0019457493],"genre_scores_gemma":[0.99329484,0.000027824435,0.000011012102,0.0060542505,0.000192129,0.000030042986,0.000028997722,0.000011441401,0.0003494815],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99840635,0.000034925684,0.0006430176,0.00028556533,0.00034958488,0.00028055956],"domain_scores_gemma":[0.99902296,0.00033667343,0.000069295806,0.00021510615,0.00021653496,0.00013941716],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025710787,0.00012401868,0.00030855957,0.00017152955,0.00005005023,0.000022313108,0.00007977998,0.00005156035,0.00007233454],"category_scores_gemma":[0.0021532509,0.00011035401,0.000010770213,0.0014077269,0.000040575134,0.00024406119,0.000030196778,0.00036328583,0.0000042851048],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050783587,0.00020495345,0.94809407,0.00009729064,0.0000067968913,0.00250873,0.001588676,0.00001589121,0.0000041993394,0.0007528328,0.0025351557,0.0441406],"study_design_scores_gemma":[0.0017260691,0.0011507508,0.8662953,0.0028471386,0.000049430317,0.0016036851,0.11325974,0.0016844838,0.00020057979,0.005037318,0.0057057366,0.00043981677],"about_ca_topic_score_codex":0.9756108,"about_ca_topic_score_gemma":0.9813994,"teacher_disagreement_score":0.11167107,"about_ca_system_score_codex":0.0017421804,"about_ca_system_score_gemma":0.0046816817,"threshold_uncertainty_score":0.8305102},"labels":[],"label_agreement":null},{"id":"W4413288733","doi":"10.1038/s41746-025-01941-3","title":"Incorporating large language models as clinical decision support in oncology: the Woollie model","year":2025,"lang":"en","type":"editorial","venue":"npj Digital Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Clinical decision making; Medicine; Oncology; Internal medicine; Computer science; Medical physics; Intensive care medicine","score_opus":0.019810511979871853,"score_gpt":0.40243749621926206,"score_spread":0.38262698423939023,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413288733","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005139059,0.0021649166,0.024050547,0.018502882,0.6138919,0.0018446333,0.00027351076,0.00033696857,0.33379558],"genre_scores_gemma":[0.1472938,0.0017309617,0.0035226177,0.010434292,0.8044274,0.00013997422,0.00434614,0.0002552222,0.02784958],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99428856,0.00016354598,0.0019690113,0.0009812679,0.0018677996,0.00072983507],"domain_scores_gemma":[0.99158967,0.0060128774,0.00061766355,0.0010020552,0.00029862623,0.00047911596],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.0045746774,0.0005948678,0.001962242,0.000468613,0.0001385884,0.00008823471,0.00072821777,0.0013858376,0.00011260258],"category_scores_gemma":[0.03270349,0.00036748187,0.0003177295,0.0005688851,0.00059377874,0.0002571681,0.0004972302,0.005813658,0.00006210693],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044881384,0.00031182243,0.0002432439,0.00015340667,0.00009670187,0.00095235964,0.0006579154,0.00032262446,0.0000050426333,0.00043282355,0.83469,0.16168529],"study_design_scores_gemma":[0.0077955737,0.001218218,0.000031273394,0.0031917933,0.00032368815,0.0000543912,0.0007806669,0.17670925,9.036036e-7,0.00959631,0.7999312,0.00036670416],"about_ca_topic_score_codex":0.000118390395,"about_ca_topic_score_gemma":0.000044974717,"teacher_disagreement_score":0.30594602,"about_ca_system_score_codex":0.00041388016,"about_ca_system_score_gemma":0.0030255248,"threshold_uncertainty_score":0.9999106},"labels":[],"label_agreement":null},{"id":"W4414702782","doi":"10.1038/s41746-025-02004-3","title":"Large language models forecast patient health trajectories enabling digital twins","year":2025,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Eisai; Northern California Institute for Research and Education; Pfizer; Novartis Pharmaceuticals Corporation; Biogen; F. Hoffmann-La Roche; Roche; Eli Lilly and Company; BioClinica; European Commission; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; National Institute on Aging; Alzheimer's Association; Foundation for the National Institutes of Health","keywords":"Benchmarking; Health care; Health records; Normalization (sociology); Imputation (statistics); Generative grammar; Database normalization; Missing data","score_opus":0.09066821201173551,"score_gpt":0.3957070671382421,"score_spread":0.3050388551265066,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414702782","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90302384,0.004197408,0.0090386635,0.021002136,0.0016889975,0.0010189427,0.0001178372,0.00026629827,0.059645876],"genre_scores_gemma":[0.99290335,0.000098530574,0.000048111448,0.0037979835,0.0005977625,0.000033751763,0.00036284092,0.000024678748,0.002133007],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.99800456,0.000016571665,0.0007009477,0.00035618024,0.0003859248,0.0005358416],"domain_scores_gemma":[0.99880224,0.00019530566,0.00012513786,0.00035128588,0.00021518135,0.00031085405],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001906256,0.00021532881,0.00045544942,0.000273842,0.00017046237,0.000075317446,0.00009685022,0.00010027507,0.000081153295],"category_scores_gemma":[0.0007389533,0.0001677839,0.00008589635,0.00055669545,0.0001295529,0.0005450612,0.000046524383,0.00026985814,0.000040197705],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022381288,0.00064333965,0.012029975,0.0005875958,0.00009170426,0.00003842965,0.042412367,0.000027515196,0.000100139136,0.0077296365,0.015902609,0.92021286],"study_design_scores_gemma":[0.0028236397,0.012022051,0.0059540006,0.011228336,0.00029598185,0.0003250997,0.53308797,0.010042213,0.0074552675,0.057598487,0.35753563,0.0016313369],"about_ca_topic_score_codex":0.0003137581,"about_ca_topic_score_gemma":0.0000703808,"teacher_disagreement_score":0.91858155,"about_ca_system_score_codex":0.00025993978,"about_ca_system_score_gemma":0.00049404916,"threshold_uncertainty_score":0.6842029},"labels":[],"label_agreement":null},{"id":"W4414750656","doi":"10.1038/s41746-025-01943-1","title":"A longitudinal analysis of declining medical safety messaging in generative AI models","year":2025,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Ethics and Social Impacts of AI","field":"Social Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Disclaimer; Generative grammar; The Internet; Generative model; Function (biology); Patient safety; MEDLINE","score_opus":0.0645174626387021,"score_gpt":0.4407533161531101,"score_spread":0.37623585351440797,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414750656","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20385051,0.00058882963,0.014043989,0.10153399,0.0002848668,0.00019166997,0.00001788797,0.00004660932,0.67944163],"genre_scores_gemma":[0.9968696,0.00025704014,0.000051200313,0.0020120484,0.000112684516,0.0000032121222,0.000015229736,0.000004625317,0.0006743272],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9978912,0.00012559367,0.0005220243,0.0002295063,0.0009381403,0.00029352252],"domain_scores_gemma":[0.9982663,0.0009999503,0.00010857837,0.00013268439,0.0003081721,0.00018434858],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022480413,0.000108146625,0.0005512408,0.00048403128,0.000196281,0.00005899113,0.00026956128,0.00019326145,0.000163613],"category_scores_gemma":[0.005608228,0.0000908668,0.0001090757,0.0021976943,0.0008627761,0.00056044187,0.000073062205,0.0003632258,9.1914427e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007218671,0.0001590412,0.13319284,0.000027505901,0.00089816,0.00004823691,0.047251344,0.0011721326,0.000013261046,0.79394996,0.00091398595,0.022301376],"study_design_scores_gemma":[0.0056226104,0.00048645705,0.1884101,0.003518772,0.0021221666,0.0000013129971,0.083253115,0.075544536,0.000055954955,0.62586534,0.014082815,0.0010367965],"about_ca_topic_score_codex":0.003124585,"about_ca_topic_score_gemma":0.010163837,"teacher_disagreement_score":0.7930191,"about_ca_system_score_codex":0.00012317255,"about_ca_system_score_gemma":0.0006478297,"threshold_uncertainty_score":0.67139775},"labels":[],"label_agreement":null},{"id":"W4415300695","doi":"10.1038/s41746-025-02008-z","title":"When helpfulness backfires: LLMs and the risk of false medical information due to sycophantic behavior","year":2025,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Topic Modeling","field":"Computer Science","cited_by":52,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Google Research; National Center for Advancing Translational Sciences; European Commission; Harvard Catalyst; National Cancer Institute; National Institutes of Health; Harvard University; Patient-Centered Outcomes Research Institute","keywords":"Helpfulness; Vulnerability (computing); Consistency (knowledge bases); Suspect; Risk assessment; Benchmark (surveying); Baseline (sea); Sophistication","score_opus":0.008338394089495093,"score_gpt":0.2471250392254192,"score_spread":0.2387866451359241,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415300695","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32202372,0.00023665013,0.6641446,0.008768124,0.00053475634,0.00039059765,0.000005501395,0.000056711524,0.0038393908],"genre_scores_gemma":[0.9978627,0.000017550854,0.00084958976,0.0010615585,0.000056626413,0.000035610028,0.000003037383,0.0000026415782,0.00011069086],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986818,0.00003974123,0.00042987568,0.00016376752,0.00053122325,0.00015358714],"domain_scores_gemma":[0.9988757,0.0003807034,0.000096820855,0.0004275253,0.00010145629,0.00011779038],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00060605846,0.00010539236,0.00026540735,0.00013713018,0.000060074843,0.00008081345,0.00060796866,0.00005838003,0.000016713044],"category_scores_gemma":[0.0016186706,0.00006139327,0.000030263784,0.0002791077,0.00020023987,0.0006595148,0.0003426172,0.00013299771,0.000012946688],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043711403,0.000039204228,0.0032769423,0.0000934445,0.000031708692,0.0000139364365,0.0044460613,0.000024960547,0.0000100424195,0.06713468,0.0011246575,0.92376065],"study_design_scores_gemma":[0.03703792,0.0018272349,0.17050615,0.007823034,0.0007135108,0.00058009534,0.0062552453,0.5138574,0.002142129,0.21242008,0.045084603,0.001752569],"about_ca_topic_score_codex":0.0001327986,"about_ca_topic_score_gemma":0.000011072784,"teacher_disagreement_score":0.9220081,"about_ca_system_score_codex":0.000016373262,"about_ca_system_score_gemma":0.000077259305,"threshold_uncertainty_score":0.25035447},"labels":[],"label_agreement":null},{"id":"W4415522504","doi":"10.1038/s41746-025-01898-3","title":"Active remote monitoring of long-term conditions with mobile devices: a systematic review of cost-effectiveness analyses","year":2025,"lang":"en","type":"review","venue":"npj Digital Medicine","topic":"Mobile Health and mHealth Applications","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; St. Paul's Hospital; Providence Health Care","funders":"Programme Grants for Applied Research; Versus Arthritis; Department of Health and Social Care; National Institute for Health and Care Research","keywords":"Psychological intervention; Intervention (counseling); Systematic review; MEDLINE; Mobile device; Activity-based costing; Telemedicine; Resource (disambiguation)","score_opus":0.17242635264472064,"score_gpt":0.5681198573434592,"score_spread":0.39569350469873854,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415522504","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000018615927,0.95334685,0.0004928764,0.000038238322,0.0003126356,0.040819325,0.000892377,0.00006755008,0.004011541],"genre_scores_gemma":[0.000493364,0.9636452,0.000042077423,0.0001355764,0.00018914939,0.033927374,0.0011797671,0.000056156317,0.00033130794],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.99370426,0.0011353516,0.0033928098,0.0005814157,0.0006151475,0.0005710312],"domain_scores_gemma":[0.98506445,0.008353819,0.0038470828,0.0011975844,0.0011244854,0.00041257314],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011143326,0.0005784561,0.006727399,0.0005558974,0.0002730455,0.000004519124,0.0004897283,0.00037196523,0.000104239116],"category_scores_gemma":[0.0020251886,0.00035806096,0.0003480412,0.0018026144,0.00026576733,0.00016213355,0.000110926754,0.000882588,0.000035751047],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019058252,0.00007526362,0.00012806802,0.85913944,0.00030289666,0.0000049604573,0.00005166524,2.2535215e-7,1.9504492e-7,0.00007406148,0.0000878573,0.14011629],"study_design_scores_gemma":[0.00055467937,0.00035027458,0.00022767419,0.9732708,0.0051364047,0.000014514153,0.0002558102,4.088606e-7,0.0000012641523,0.00001400455,0.019976597,0.00019757128],"about_ca_topic_score_codex":0.00008680408,"about_ca_topic_score_gemma":0.000014631521,"teacher_disagreement_score":0.13991873,"about_ca_system_score_codex":0.00049433834,"about_ca_system_score_gemma":0.003039795,"threshold_uncertainty_score":0.9998871},"labels":[],"label_agreement":null},{"id":"W4415779145","doi":"10.1038/s41746-025-02037-8","title":"Can human connection amplify digital health outcomes? Familial involvement in a mobile health app","year":2025,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Mobile Health and mHealth Applications","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Digital health; mHealth; Mobile apps; Intervention (counseling); Health intervention; Health care; Telemedicine; Social support; Mobile device","score_opus":0.04879999159743522,"score_gpt":0.444024934513129,"score_spread":0.3952249429156938,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415779145","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49737772,0.0063647325,0.0042031794,0.28696448,0.007807132,0.06275181,0.0022227801,0.0021493621,0.13015881],"genre_scores_gemma":[0.9390119,0.00047895714,0.00003299917,0.03962794,0.00042188686,0.01410298,0.0015633336,0.000047831018,0.0047122273],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9942906,0.0002495862,0.0025212034,0.00080565753,0.0005431699,0.0015897878],"domain_scores_gemma":[0.9965704,0.00070811564,0.0007229069,0.0007731361,0.00017532917,0.0010501108],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013452912,0.00041400947,0.001194853,0.0006689794,0.0012481327,0.000032691212,0.00032669466,0.00026761278,0.00015786485],"category_scores_gemma":[0.00048192168,0.00035386955,0.00008423708,0.0010801803,0.00021103284,0.00027070864,0.00016915845,0.001251094,0.00014206166],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015992286,0.0011187814,0.35851395,0.004095436,0.00005585333,0.000006079526,0.0050264355,0.000015368329,0.000019159404,0.07755277,0.15078497,0.40265125],"study_design_scores_gemma":[0.0074287965,0.002070795,0.119451016,0.002080663,0.000010702967,0.0000024267858,0.013505393,0.00004744679,0.0000011450353,0.009818093,0.8452323,0.00035120934],"about_ca_topic_score_codex":0.007088004,"about_ca_topic_score_gemma":0.007715433,"teacher_disagreement_score":0.69444734,"about_ca_system_score_codex":0.002061488,"about_ca_system_score_gemma":0.0029894751,"threshold_uncertainty_score":0.99989134},"labels":[],"label_agreement":null},{"id":"W4415823167","doi":"10.1038/s41746-025-02136-6","title":"The npj Digital Medicine Editorial Fellowship","year":2025,"lang":"en","type":"letter","venue":"npj Digital Medicine","topic":"Academic Publishing and Open Access","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada); University of Toronto","funders":"","keywords":"Editorial board; Digital era; MEDLINE; Digital health","score_opus":0.06681438086622891,"score_gpt":0.3873468695377768,"score_spread":0.3205324886715479,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415823167","genre_codex":"commentary","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000501755,0.0007590574,0.00017802401,0.5729101,0.1143569,0.00040698526,0.00023869568,0.0001516603,0.31094846],"genre_scores_gemma":[0.009302469,0.00011319946,0.000004210841,0.29480645,0.44192073,0.00004907584,0.0008883309,0.000077364784,0.25283816],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9814583,0.00031322957,0.0030656806,0.0020195062,0.0116768675,0.0014664383],"domain_scores_gemma":[0.9667828,0.026927713,0.0014753377,0.0027319067,0.0015883099,0.0004939253],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.0069798776,0.0010883155,0.0020147448,0.00093418104,0.0007908742,0.0064785895,0.011772545,0.0023544177,0.0005987326],"category_scores_gemma":[0.12949839,0.000526065,0.00040562052,0.0026688536,0.0029483477,0.0043066167,0.0016068864,0.007479213,0.00095602125],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006626037,0.000014179818,0.00025126076,0.000023822398,0.00009196151,0.00014587895,0.00023034644,6.0620897e-7,0.0000011566452,0.00029797378,0.93363243,0.065244146],"study_design_scores_gemma":[0.0011910564,0.00026738603,0.00008002506,0.00076724763,0.00008820997,0.00003962414,0.0007333404,0.000016554062,0.0000016773406,0.047222,0.9490714,0.00052145694],"about_ca_topic_score_codex":0.00012560934,"about_ca_topic_score_gemma":0.000009578229,"teacher_disagreement_score":0.32756382,"about_ca_system_score_codex":0.00026705788,"about_ca_system_score_gemma":0.0007541031,"threshold_uncertainty_score":0.99982184},"labels":[],"label_agreement":null},{"id":"W4415836469","doi":"10.1038/s41746-026-02694-3","title":"Methods for Classifying Physical Activities Using Accelerometer Data: A Scoping Review","year":2025,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Physical Activity and Health","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Accelerometer; Population; Physical activity; Variety (cybernetics); Data collection","score_opus":0.4272794391005607,"score_gpt":0.5904747825367035,"score_spread":0.16319534343614278,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415836469","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17457438,0.065931454,0.62743837,0.050419744,0.0021447353,0.011701518,0.00025818933,0.000729191,0.066802405],"genre_scores_gemma":[0.9592712,0.0024809102,0.0222425,0.012422303,0.0019558456,0.0001725927,0.0003637026,0.00007344331,0.0010174818],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.99847597,0.000057880854,0.00037531875,0.00048214712,0.00023291745,0.00037577772],"domain_scores_gemma":[0.99757385,0.0014492719,0.00012746386,0.0006304616,0.00007892439,0.00014004408],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004706961,0.00021983811,0.0012252466,0.00013508974,0.00012632472,0.000034332897,0.00021191919,0.0000636394,0.000019387926],"category_scores_gemma":[0.0017564773,0.00016084635,0.00011590505,0.00044505633,0.00020854974,0.0007944042,0.00021030981,0.00029889998,0.0000031957227],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028990876,0.0008821408,0.00012993967,0.050962236,0.00026054526,0.00000828601,0.0001922608,5.069617e-7,0.020899966,0.0014073476,0.003370976,0.9215959],"study_design_scores_gemma":[0.010818707,0.0039599556,0.0011950542,0.8498433,0.0035973242,0.00013073729,0.00069416367,0.024650639,0.010010584,0.014417411,0.079462506,0.0012195708],"about_ca_topic_score_codex":0.0000120024515,"about_ca_topic_score_gemma":0.0000012319639,"teacher_disagreement_score":0.9203763,"about_ca_system_score_codex":0.00011061463,"about_ca_system_score_gemma":0.00035055564,"threshold_uncertainty_score":0.65591234},"labels":[],"label_agreement":null},{"id":"W4415985271","doi":"10.1038/s41746-025-02113-z","title":"Reporting guidelines for studies involving generative artificial intelligence applications: what do I use, and when?","year":2025,"lang":"en","type":"letter","venue":"npj Digital Medicine","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Impact; McMaster University; Hamilton General Hospital","funders":"","keywords":"Generative grammar; Applications of artificial intelligence; Generative model; Systematic review","score_opus":0.6199859904263239,"score_gpt":0.5294689304570316,"score_spread":0.09051705996929227,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415985271","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00090677594,0.039778795,0.02122676,0.9325663,0.002163772,0.0029748492,0.00003871358,0.00012418041,0.00021986825],"genre_scores_gemma":[0.0056600897,0.028360697,0.011008427,0.90503937,0.039534684,0.0025491628,0.0020589095,0.00012794776,0.0056607127],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9946097,0.000039798895,0.0034506237,0.00091862696,0.0005034012,0.00047786004],"domain_scores_gemma":[0.9905175,0.0025487966,0.0016254216,0.00062326423,0.004532506,0.00015248886],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00095806585,0.00047227627,0.0011814431,0.00042568892,0.000305866,0.0004023653,0.00015043373,0.00054528273,0.000024715202],"category_scores_gemma":[0.034082394,0.00036784887,0.00013915196,0.00035667224,0.0005116156,0.0008497685,0.000099628225,0.00086753134,0.000010019363],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038030976,0.000026916523,0.0003004596,0.0014411389,0.00016380711,0.000032302363,0.0019101368,0.0000017137421,0.00003423194,0.0007666494,0.54003644,0.45524818],"study_design_scores_gemma":[0.00004942988,0.00058869453,0.000014941724,0.011436329,0.0004981806,0.000105293766,0.032941625,0.00037461342,0.0010265392,0.11768144,0.83480835,0.00047458734],"about_ca_topic_score_codex":0.000109698565,"about_ca_topic_score_gemma":0.00003230743,"teacher_disagreement_score":0.4547736,"about_ca_system_score_codex":0.0002337052,"about_ca_system_score_gemma":0.0004842861,"threshold_uncertainty_score":0.99987733},"labels":[],"label_agreement":null},{"id":"W4415988375","doi":"10.1038/s41746-025-02035-w","title":"A generalizable 3D framework and model for self-supervised learning in medical imaging","year":2025,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; Vector Institute; Sunnybrook Health Science Centre; University of Toronto","funders":"Google Research; National Institute of Mental Health; National Institute on Aging; Faculty of Health Sciences, Queen's University; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; University of California, Los Angeles; Genentech; National Institutes of Health; H. Lundbeck A/S; Servier; Temerty Family Foundation; Eisai; McDonnell Center for Systems Neuroscience; Queen's University; University of Ottawa; Canada Research Chairs; Natural Sciences and Engineering Research Council of Canada; BioClinica; Biogen; Pfizer; Centre for Addiction and Mental Health Foundation; IXICO; Alliance de recherche numérique du Canada; Bristol-Myers Squibb; Government of Ontario; London Health Sciences Foundation; Northern California Institute for Research and Education; McMaster University; Novartis Pharmaceuticals Corporation; Eli Lilly and Company; National Center for Advancing Translational Sciences; Meso Scale Diagnostics; Alzheimer's Disease Neuroimaging Initiative; Alzheimer's Association; Foundation for the National Institutes of Health","keywords":"Generalizability theory; Medical imaging; Limiting; Pretext; Visualization; Medical diagnosis","score_opus":0.013154579935456661,"score_gpt":0.2818658981233288,"score_spread":0.26871131818787214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415988375","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0040476765,0.0005880167,0.972978,0.009042457,0.00017862397,0.00016877685,5.113439e-7,0.00021287765,0.012783052],"genre_scores_gemma":[0.8797436,0.00006691622,0.11391769,0.0045791054,0.000094442046,0.0000369112,0.000008379937,0.000013361696,0.0015396128],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99870706,0.000030013749,0.00028843625,0.00035487808,0.00032715543,0.0002924737],"domain_scores_gemma":[0.9991447,0.00042465594,0.0000461902,0.00017988938,0.00005937248,0.00014521237],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047243704,0.00013233117,0.00022887044,0.00021566405,0.00010513909,0.00014537068,0.00032693765,0.00007554558,0.000015374259],"category_scores_gemma":[0.0012882443,0.00011455922,0.00002669574,0.00044056086,0.00007455567,0.0004675811,0.00016215666,0.0002928849,0.0000034215686],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033849818,0.00010287098,0.01193981,0.0001505757,0.000032326418,0.000051448733,0.007532614,0.009900917,0.00007548076,0.20494026,0.0019794765,0.76326036],"study_design_scores_gemma":[0.0010984108,0.000033973138,0.00034454567,0.00030073384,0.000004592137,0.000008027655,0.00019704198,0.9752865,0.0000024578776,0.013391933,0.009224797,0.000106981155],"about_ca_topic_score_codex":0.000008968298,"about_ca_topic_score_gemma":0.0000025980794,"teacher_disagreement_score":0.9653856,"about_ca_system_score_codex":0.00003773581,"about_ca_system_score_gemma":0.00013545762,"threshold_uncertainty_score":0.46715894},"labels":[],"label_agreement":null},{"id":"W4416182962","doi":"10.1038/s41746-025-02060-9","title":"Changes in emergency and primary care use after adding virtual physicians to HealthLink BC’s 8-1-1 program","year":2025,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Telemedicine and Telehealth Implementation","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Burnaby Hospital; Ministry of Health; Simon Fraser University; Providence Health Care; Michael Smith Health Research BC; University of British Columbia; University of British Columbia Hospital","funders":"Canadian Institutes of Health Research; Ministry of Health, British Columbia","keywords":"Telehealth; Primary care; Health care; Intervention (counseling); Telemedicine; Emergency department; Primary health care; Service (business); Health services","score_opus":0.023557614888375756,"score_gpt":0.3509752794104472,"score_spread":0.32741766452207144,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416182962","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96745855,0.0012783263,0.00010772908,0.022594376,0.0005663038,0.0022217936,0.000056732875,0.00015835172,0.005557847],"genre_scores_gemma":[0.9857379,0.00047294731,0.00039195016,0.010928462,0.0005372355,0.0003983388,0.00045258287,0.000028513377,0.0010520584],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9981426,0.000024067682,0.00056145736,0.00042528097,0.00035591915,0.0004906947],"domain_scores_gemma":[0.9991528,0.000094757044,0.00008627575,0.00024814316,0.00014448892,0.0002735419],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001345228,0.00023801487,0.0005208549,0.0005156712,0.0000571964,0.000020927746,0.00006414893,0.0000803882,0.000071312206],"category_scores_gemma":[0.0002525834,0.00019801993,0.00003120341,0.00076646346,0.00008328202,0.00023062673,0.00007608154,0.00024079332,0.000009036186],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039349333,0.00013596613,0.22188404,0.0009072867,0.000026475122,0.000060543283,0.0029131954,2.3537396e-7,0.00019529444,0.000110501394,0.006692245,0.7666807],"study_design_scores_gemma":[0.0036832232,0.004440257,0.84099907,0.0023771357,0.00008924987,0.0000132111645,0.0048322272,0.000013381433,0.00007799961,0.00005531269,0.14322041,0.00019852567],"about_ca_topic_score_codex":0.00024737322,"about_ca_topic_score_gemma":0.001179056,"teacher_disagreement_score":0.7664822,"about_ca_system_score_codex":0.00020882476,"about_ca_system_score_gemma":0.00012244262,"threshold_uncertainty_score":0.8075018},"labels":[],"label_agreement":null},{"id":"W4416291556","doi":"10.1038/s41746-025-02032-z","title":"EVA-X: a foundation model for general chest x-ray analysis with self-supervised learning","year":2025,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; University of Toronto; University Health Network","funders":"National Natural Science Foundation of China","keywords":"Generalization; Domain (mathematical analysis); Medical imaging; Foundation (evidence); Annotation; Image (mathematics); Medical diagnosis","score_opus":0.02589900046911592,"score_gpt":0.32086587292028484,"score_spread":0.2949668724511689,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416291556","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5909832,0.00025300225,0.32762486,0.07035291,0.00021349637,0.001794435,0.000019375859,0.0007398908,0.008018819],"genre_scores_gemma":[0.9765696,0.000025148478,0.008148028,0.008297709,0.00028617142,0.00015650902,0.0005093459,0.000040391096,0.0059671085],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99821115,0.000021075284,0.00041461422,0.0005341196,0.00047212516,0.0003469414],"domain_scores_gemma":[0.9984816,0.00041979807,0.00011633247,0.00040670022,0.00039452384,0.00018105867],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029547254,0.00027037432,0.00068584934,0.0006750024,0.0001414761,0.00007447361,0.00012494632,0.000105265266,0.00006355007],"category_scores_gemma":[0.0009849416,0.00020198553,0.00016566081,0.00147084,0.00012440108,0.00025104382,0.00004226947,0.00022062112,0.000011083285],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0060365996,0.0040214737,0.32205853,0.005257861,0.018845463,0.00019645177,0.014869795,0.24788304,0.010850509,0.005644106,0.053822,0.31051418],"study_design_scores_gemma":[0.005748975,0.00088747614,0.010445451,0.00048495436,0.003906954,0.0000046933837,0.00024836612,0.94588107,0.00009595199,0.00018244614,0.03188475,0.00022892116],"about_ca_topic_score_codex":0.00005417967,"about_ca_topic_score_gemma":0.00003099966,"teacher_disagreement_score":0.69799805,"about_ca_system_score_codex":0.0002558444,"about_ca_system_score_gemma":0.00035749667,"threshold_uncertainty_score":0.82367307},"labels":[],"label_agreement":null},{"id":"W4416312374","doi":"10.1038/s41746-025-02048-5","title":"AI and innovation in clinical trials","year":2025,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kingston General Hospital; Queen's University","funders":"","keywords":"Clinical trial; Perspective (graphical); Reinforcement learning; Face (sociological concept); MEDLINE; Research design","score_opus":0.508434571892996,"score_gpt":0.6210337541863907,"score_spread":0.11259918229339472,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416312374","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88031363,0.0005212372,0.0011185484,0.09226139,0.0010555305,0.0005032967,0.0000017760105,0.00003398652,0.024190584],"genre_scores_gemma":[0.98753095,0.00014064199,0.000034688554,0.010163681,0.00053545175,0.000015494346,0.000038418035,0.0000048963325,0.0015357537],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9979707,0.00007548314,0.0014986782,0.00019467167,0.00012918809,0.00013129496],"domain_scores_gemma":[0.99846065,0.0009858505,0.0001257165,0.00015206332,0.00020486211,0.00007083654],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0029851294,0.00007815187,0.00044989682,0.0005077381,0.000024986779,0.00001616534,0.00003153608,0.00011847903,0.000056455254],"category_scores_gemma":[0.01985873,0.000056927045,0.000026496766,0.0010535291,0.00015680028,0.000128473,0.000015566406,0.00025097834,0.0000165335],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016569249,0.000089233756,0.20018595,0.000070535905,0.000012136794,0.0000052631513,0.00025113137,1.3817821e-7,0.00010127174,0.009685955,0.008687236,0.78074545],"study_design_scores_gemma":[0.0025183202,0.0028600134,0.62484753,0.004611479,0.00020871073,0.00005398734,0.00667184,0.0013859608,0.0023198754,0.12905079,0.22510605,0.0003654618],"about_ca_topic_score_codex":0.000080601756,"about_ca_topic_score_gemma":0.00001449968,"teacher_disagreement_score":0.78038,"about_ca_system_score_codex":0.000044104454,"about_ca_system_score_gemma":0.00020607485,"threshold_uncertainty_score":0.9883974},"labels":[],"label_agreement":null},{"id":"W4416590576","doi":"10.1038/s41746-025-02095-y","title":"Multimodal analysis of whole slide images in colorectal cancer","year":2025,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Leeds Biomedical Research Centre; National Health and Medical Research Council; Medical Research Council; National Institutes of Health; Gemeinsame Bundesausschuss; Deutsche Forschungsgemeinschaft; Deutsche Krebshilfe; European Commission; HORIZON EUROPE Framework Programme; Department of Health and Social Care; National Institute for Health and Care Research; Deutscher Akademischer Austauschdienst; University of New South Wales; Nvidia","keywords":"Multimodal therapy; Modality (human–computer interaction); Modalities; Colorectal cancer; Digital pathology; Treatment modality; MEDLINE","score_opus":0.007855304520056427,"score_gpt":0.2872012234811282,"score_spread":0.27934591896107175,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416590576","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8486759,0.0007419739,0.122591116,0.004839109,0.0009054545,0.00022724974,0.00003634541,0.00011688318,0.021865984],"genre_scores_gemma":[0.9989295,0.000019886,0.00047285773,0.00015142177,0.00004120316,0.00002564014,0.0000055899163,0.0000035579617,0.00035033087],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99898565,0.000017644476,0.0002962608,0.0002862062,0.00024899747,0.00016524173],"domain_scores_gemma":[0.9993945,0.00015580619,0.00008731017,0.00023257262,0.00008905111,0.000040786093],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013515126,0.00010077674,0.00032407165,0.0006606937,0.000021274856,0.000028572533,0.00037552632,0.000045709985,0.00002095846],"category_scores_gemma":[0.00015352787,0.000084806365,0.000060459803,0.0028342812,0.00012515775,0.00041977043,0.00012348135,0.00010482936,0.000003057846],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000103701794,0.00018947454,0.21294917,0.00008848481,0.0007183327,0.000033733333,0.001756295,0.0054999883,0.050995763,0.0023568461,0.0040069064,0.7213013],"study_design_scores_gemma":[0.0021243547,0.0003905323,0.7811526,0.00040778873,0.00028609278,0.0000026000253,0.00029930004,0.15831265,0.05077588,0.002196595,0.003747398,0.0003042078],"about_ca_topic_score_codex":0.00061130873,"about_ca_topic_score_gemma":0.00036306458,"teacher_disagreement_score":0.7209971,"about_ca_system_score_codex":0.00015198608,"about_ca_system_score_gemma":0.000082266204,"threshold_uncertainty_score":0.34583032},"labels":[],"label_agreement":null},{"id":"W4416794473","doi":"10.1038/s41746-025-02112-0","title":"Protecting patient privacy in tabular synthetic health data: a regulatory perspective","year":2025,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Ethics in Clinical Research","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Children's Hospital of Eastern Ontario; University of Ottawa","funders":"Canadian Institutes of Health Research; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Deutsche Forschungsgemeinschaft","keywords":"Perspective (graphical); Vulnerability (computing); Information privacy; Health care; Data Protection Act 1998; Health data; Confidentiality; Privacy by Design","score_opus":0.3416064273130466,"score_gpt":0.5648084510093156,"score_spread":0.22320202369626907,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416794473","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5730518,0.007946353,0.0011430106,0.2821192,0.0008098464,0.00514335,0.00005791497,0.00028787978,0.1294406],"genre_scores_gemma":[0.99502856,0.00017219281,0.00034013795,0.0025686752,0.00018794548,0.00005504063,0.00003863252,0.00002829535,0.0015805479],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9963328,0.00014482696,0.0008888987,0.00086875225,0.001237483,0.00052722485],"domain_scores_gemma":[0.9928716,0.0042947056,0.00017433109,0.001846518,0.00048206796,0.00033077438],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.003992109,0.00020182185,0.00066596334,0.00040516967,0.00011165348,0.00003237266,0.00047515685,0.00021288787,0.00005619714],"category_scores_gemma":[0.095731445,0.00015567649,0.00005232353,0.0008612029,0.0006111264,0.00021947801,0.00071500073,0.0025270618,0.000025472753],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0030923905,0.0048132804,0.070439294,0.007960459,0.0007473995,0.001415129,0.025891865,0.000021689553,0.001515184,0.20631042,0.018425066,0.6593678],"study_design_scores_gemma":[0.028234161,0.019981876,0.15823376,0.09671993,0.0002994093,0.00029422005,0.10182112,0.0036584123,0.0016914109,0.47424078,0.11316164,0.0016633014],"about_ca_topic_score_codex":0.00037774697,"about_ca_topic_score_gemma":0.00011615142,"teacher_disagreement_score":0.65770453,"about_ca_system_score_codex":0.00080692524,"about_ca_system_score_gemma":0.001572491,"threshold_uncertainty_score":0.99977416},"labels":[],"label_agreement":null},{"id":"W4416992434","doi":"10.1038/s41746-025-02187-9","title":"Predicting 1-year successful clinical use of an arteriovenous access for hemodialysis using machine learning","year":2025,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Central Venous Catheters and Hemodialysis","field":"Health Professions","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Medical Association; University Health Network; Artificial Intelligence in Medicine (Canada); University of Toronto; St. Michael's Hospital","funders":"Canadian Institutes of Health Research; Physicians' Services Incorporated Foundation; Brigham and Women's Hospital; University of Toronto; Ministry of Health, Ontario","keywords":"Logistic regression; Vascular access; Hemodialysis; Clinical Practice; Hemodialysis access; Quality (philosophy); Predictive modelling","score_opus":0.13690241328961808,"score_gpt":0.4586209028823281,"score_spread":0.32171848959271,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416992434","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9893215,0.00010282363,0.006273145,0.0005093763,0.00079393364,0.0008472459,0.00014959693,0.00010528124,0.0018971238],"genre_scores_gemma":[0.9969007,0.00011439674,0.00075562164,0.0005613415,0.00070333853,0.000031833348,0.0002705035,0.000039010214,0.0006232615],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970348,0.0002488841,0.0013904426,0.00046450374,0.00029768032,0.000563717],"domain_scores_gemma":[0.99663025,0.0018136671,0.0005715504,0.00041819407,0.00033924446,0.00022706907],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00097203214,0.00022937995,0.0009792126,0.00044062964,0.0005388935,0.000054686247,0.0003277483,0.0002397142,0.0001386804],"category_scores_gemma":[0.0025488483,0.00018455874,0.00024847078,0.0007066636,0.00019758847,0.0007490579,0.00019687277,0.0005587409,0.0000042266342],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00056002464,0.00035771081,0.9675981,0.00041970855,0.00025152016,0.0000059050985,0.00113617,0.00019854473,0.00043877107,0.00016177938,0.00033947983,0.028532326],"study_design_scores_gemma":[0.034857254,0.007762031,0.33545464,0.008837148,0.005435306,0.00001807813,0.014343337,0.46735117,0.00066981313,0.00493391,0.11821587,0.0021214539],"about_ca_topic_score_codex":0.0011747481,"about_ca_topic_score_gemma":0.00026958282,"teacher_disagreement_score":0.63214344,"about_ca_system_score_codex":0.00009072856,"about_ca_system_score_gemma":0.00021041279,"threshold_uncertainty_score":0.7526087},"labels":[],"label_agreement":null},{"id":"W4417034086","doi":"10.1038/s41746-025-02121-z","title":"African digital health strategic plans analysis: key weaknesses in contextualization, intervention focus, and technological foresight","year":2025,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Mobile Health and mHealth Applications","field":"Health Professions","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Digital health; Futures studies; Consistency (knowledge bases); Strengths and weaknesses; Strategic planning; Key (lock); Quality (philosophy); Intervention (counseling); Health care","score_opus":0.03862351533191962,"score_gpt":0.40707074641118285,"score_spread":0.36844723107926325,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417034086","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3454255,0.018112112,0.095481314,0.22509076,0.0010076726,0.017150838,0.0013603176,0.0016236558,0.29474786],"genre_scores_gemma":[0.9948551,0.00054954994,0.000027254848,0.0013514553,0.00007928968,0.0015690698,0.00052577024,0.000013649513,0.0010288781],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.997055,0.00015819432,0.0014053452,0.0005012002,0.00024156016,0.00063869834],"domain_scores_gemma":[0.9980614,0.00069545524,0.00038683612,0.00035808212,0.00016177693,0.00033642244],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007057741,0.00022418195,0.0007033729,0.0008766622,0.00039171474,0.000036142435,0.00020170395,0.0002365052,0.00008557446],"category_scores_gemma":[0.0007516721,0.00017132839,0.000059438942,0.0022457168,0.0003117288,0.0002743228,0.00009961444,0.00051573955,0.00002446736],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023497167,0.00045836702,0.35824677,0.0014256526,0.0001465266,0.000007766874,0.0014855823,0.000005809358,0.000004511,0.46517497,0.008281399,0.16452768],"study_design_scores_gemma":[0.010480633,0.0015915794,0.36546564,0.0046766526,0.00027992696,0.000009627639,0.05368352,0.0016975041,0.0000051506277,0.18894076,0.3724989,0.0006701059],"about_ca_topic_score_codex":0.0004998817,"about_ca_topic_score_gemma":0.0037872016,"teacher_disagreement_score":0.6494296,"about_ca_system_score_codex":0.00022407391,"about_ca_system_score_gemma":0.00043421533,"threshold_uncertainty_score":0.69865686},"labels":[],"label_agreement":null},{"id":"W4417102935","doi":"10.1038/s41746-025-02196-8","title":"Self-supervised stain normalization empowers privacy-preserving and model generalization in digital pathology","year":2025,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Zhejiang University; Hangzhou Science and Technology Bureau; Natural Science Foundation of Zhejiang Province; National Natural Science Foundation of China","keywords":"Normalization (sociology); Stain; Digital pathology; Database normalization; Pattern recognition (psychology); Generalization","score_opus":0.009580765354644742,"score_gpt":0.25238780492241375,"score_spread":0.242807039567769,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417102935","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16551821,0.00026430344,0.8230569,0.0020495874,0.00027874252,0.00025448063,0.000004044606,0.00021090226,0.008362863],"genre_scores_gemma":[0.9935376,0.000092290225,0.005508697,0.00053232437,0.00005315769,0.000022295515,0.000030109748,0.000011572199,0.0002119361],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987172,0.000023616316,0.00034446878,0.0004236638,0.00024764132,0.00024342838],"domain_scores_gemma":[0.9992612,0.00007188076,0.00007590387,0.00041051954,0.00011206327,0.00006841013],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001796786,0.00015778844,0.0002011733,0.00035295202,0.000065125285,0.00019149482,0.0004408091,0.00009416526,0.000003149384],"category_scores_gemma":[0.00035118798,0.00014790852,0.000019083924,0.000808958,0.00007033442,0.0021760538,0.0004444615,0.000111562,0.0000021473302],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019191201,0.0005020255,0.1336716,0.00095840567,0.00012559173,0.00018326416,0.025867429,0.04337595,0.0038051754,0.13946043,0.0073813363,0.6444769],"study_design_scores_gemma":[0.0009927766,0.000120408054,0.0016378806,0.00012232743,0.0000057207308,0.000013596091,0.00010553779,0.9739406,0.00014327753,0.021641845,0.0011285242,0.00014750673],"about_ca_topic_score_codex":0.000012595221,"about_ca_topic_score_gemma":0.00001010161,"teacher_disagreement_score":0.93056464,"about_ca_system_score_codex":0.0001640942,"about_ca_system_score_gemma":0.00009322312,"threshold_uncertainty_score":0.6031534},"labels":[],"label_agreement":null},{"id":"W4417113689","doi":"10.1038/s41746-025-02143-7","title":"Explainable AI-driven precision clinical trial enrichment: demonstration of the NetraAI platform with a phase II depression trial","year":2025,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Digital Mental Health Interventions","field":"Psychology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; Centre for Addiction and Mental Health","funders":"National Institute of Mental Health; Intramural Research Program; National Institutes of Health","keywords":"Leverage (statistics); Clinical trial; Feature (linguistics); Precision medicine; Sample size determination; Feature selection; Personalized medicine; Statistical model","score_opus":0.07177566798547645,"score_gpt":0.46214385272827285,"score_spread":0.3903681847427964,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417113689","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85979867,0.00017478026,0.0019746518,0.0020612297,0.0054946356,0.003072865,0.000055393615,0.00006424502,0.12730351],"genre_scores_gemma":[0.9914303,0.0000034903458,0.000038186463,0.0004008111,0.00041456736,0.00023585018,0.000071959774,0.000017674374,0.0073872027],"study_design_codex":"design_other","study_design_gemma":"randomized_trial","domain_scores_codex":[0.9970603,0.00011085238,0.001492625,0.00045851158,0.00052969356,0.00034802777],"domain_scores_gemma":[0.9981018,0.00050868286,0.0004891162,0.00061741873,0.00012397887,0.00015901223],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005927158,0.00022706972,0.00050889276,0.0001784476,0.00020644638,0.00004156217,0.00038701567,0.00020126475,0.00021185898],"category_scores_gemma":[0.00052060775,0.00013291194,0.00020400574,0.0005503396,0.00039122178,0.0005294301,0.00016725942,0.00037978674,0.0000214341],"study_design_candidate":"randomized_trial","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.42607024,0.008586962,0.0016365886,0.00007776065,0.00018483656,0.000014472043,0.00042729735,0.0000039742604,0.000024823865,0.011270718,0.019161096,0.5325412],"study_design_scores_gemma":[0.87991166,0.076040424,0.0033366256,0.0030752865,0.00026487166,0.000032391228,0.00090450206,0.00016027618,0.00054178305,0.006717629,0.028708417,0.0003061415],"about_ca_topic_score_codex":0.000041961986,"about_ca_topic_score_gemma":0.000021060416,"teacher_disagreement_score":0.5322351,"about_ca_system_score_codex":0.00009464019,"about_ca_system_score_gemma":0.00015836567,"threshold_uncertainty_score":0.54199916},"labels":[],"label_agreement":null},{"id":"W4417201030","doi":"10.1038/s41746-025-02140-w","title":"EchoGraph system for automated quality assessment of echocardiography reports","year":2025,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"National Heart, Lung, and Blood Institute; Mayo Clinic","keywords":"Schema (genetic algorithms); Variance (accounting); Quality assessment; Quality Score; F1 score; Quality (philosophy); Sensitivity (control systems)","score_opus":0.1342374651418137,"score_gpt":0.5010621793141272,"score_spread":0.36682471417231355,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417201030","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8724142,0.000758595,0.022163115,0.005794499,0.0038741597,0.0026525995,0.000046919416,0.00093503034,0.09136091],"genre_scores_gemma":[0.99828297,0.000024732317,0.00070589787,0.0002623763,0.00021710127,0.0001165785,0.00015741446,0.000012922975,0.00021998338],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99791694,0.000032632568,0.001151851,0.00031431313,0.00035052802,0.00023371611],"domain_scores_gemma":[0.99802136,0.00040128434,0.00029867483,0.0004940675,0.0006444165,0.0001402122],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00084815366,0.00014839004,0.0006058402,0.00046943728,0.00007320618,0.000014847811,0.00006666336,0.00012624533,0.000010277312],"category_scores_gemma":[0.0007940813,0.00011566667,0.00021186298,0.0008982227,0.00018395252,0.00010499393,0.000017220074,0.00012114559,0.0000012130932],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002864282,0.00046576984,0.84657097,0.0056537353,0.00053519505,0.000035299927,0.0005046678,0.000025660247,0.0029878884,0.011531243,0.020397892,0.11100527],"study_design_scores_gemma":[0.0013503226,0.0040137656,0.8931966,0.011513645,0.0012417777,0.00017724965,0.023223035,0.005743386,0.019761601,0.012006094,0.027101273,0.0006712945],"about_ca_topic_score_codex":0.00027591508,"about_ca_topic_score_gemma":0.0000042548877,"teacher_disagreement_score":0.12586883,"about_ca_system_score_codex":0.00012076043,"about_ca_system_score_gemma":0.0003208144,"threshold_uncertainty_score":0.47167498},"labels":[],"label_agreement":null},{"id":"W4417327849","doi":"10.1038/s41746-025-02126-8","title":"Crossing borders securely: synthetic data and federated networks for privacy-preserving access to real-world data and emerging use cases","year":2025,"lang":"en","type":"review","venue":"npj Digital Medicine","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Data sharing; Health care; Data access; Health data; Information privacy; Big data; Emerging technologies; Data Protection Act 1998","score_opus":0.1734012673839101,"score_gpt":0.4299672340503494,"score_spread":0.2565659666664393,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417327849","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000031026688,0.7993196,0.17866965,0.01445951,0.0008082308,0.002338039,0.003051891,0.00093526964,0.0003867745],"genre_scores_gemma":[0.0007791278,0.96617544,0.02735832,0.00035583388,0.0002663046,0.000105222316,0.0047099036,0.000100010744,0.00014984873],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99412113,0.00012619955,0.0011795737,0.0031045408,0.0005255705,0.0009430109],"domain_scores_gemma":[0.9638737,0.00801086,0.0007045657,0.026852177,0.00020173081,0.0003569718],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0012173951,0.0008729317,0.0021603815,0.00087196083,0.0006786877,0.007432712,0.06158362,0.00028635745,0.0000040209115],"category_scores_gemma":[0.16469562,0.00071194384,0.00005961906,0.0023908513,0.00067224045,0.0071542375,0.39367408,0.0007269866,0.0000011791593],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008972387,0.00001820522,0.000081431135,0.0046133264,0.00011824864,0.00007462858,0.000020622529,0.0000011074126,8.6179845e-8,0.00006787193,0.23942697,0.7555685],"study_design_scores_gemma":[0.00032663954,0.00009799023,0.000024056439,0.038729634,0.0003488498,0.00011174702,0.000028320675,0.116757944,3.4117375e-7,0.0017461708,0.84112376,0.00070453715],"about_ca_topic_score_codex":0.0005809482,"about_ca_topic_score_gemma":0.00060527906,"teacher_disagreement_score":0.754864,"about_ca_system_score_codex":0.00012153268,"about_ca_system_score_gemma":0.0004916289,"threshold_uncertainty_score":0.9995332},"labels":[],"label_agreement":null},{"id":"W4417345758","doi":"10.1038/s41746-025-02199-5","title":"ECG sonification methods for robust and generalizable clinical decision support","year":2025,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"ECG Monitoring and Analysis","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Khalifa University of Science, Technology and Research","keywords":"Sonification; Generalizability theory; Preprocessor; Auditory display; Modality (human–computer interaction); Perception; Waveform; Visualization; Auditory perception","score_opus":0.0893443131597174,"score_gpt":0.48691363593901416,"score_spread":0.39756932277929674,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417345758","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033289,0.0011591191,0.94685584,0.006448877,0.00076729,0.00035572762,0.0000071221652,0.00009531362,0.011021682],"genre_scores_gemma":[0.35764688,0.0010039036,0.59796405,0.0022871383,0.0017224519,0.00007723014,0.00030224904,0.0000449466,0.03895118],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.998725,0.000029075285,0.00054577156,0.0003566205,0.00015290525,0.00019064959],"domain_scores_gemma":[0.9984836,0.00075732864,0.00008490733,0.0003106562,0.00018905805,0.00017443098],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010008175,0.00013324489,0.00049362885,0.00018036409,0.00007843068,0.000032833916,0.00007127201,0.000120455144,0.00003536676],"category_scores_gemma":[0.0025070983,0.000095446296,0.00011101772,0.0002917543,0.0001405489,0.00010267519,0.000037043897,0.00012896571,0.000006597866],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015987255,0.00010318685,0.04529914,0.00009142123,0.000118226424,0.0000041411427,0.000030373109,0.000009302799,0.00044908843,0.00024232865,0.020047035,0.9334459],"study_design_scores_gemma":[0.014568513,0.003689433,0.07807282,0.0020979298,0.0025950707,0.00008231639,0.00093100953,0.123588935,0.002209286,0.010348751,0.7612364,0.0005795241],"about_ca_topic_score_codex":0.000011601548,"about_ca_topic_score_gemma":9.895167e-7,"teacher_disagreement_score":0.93286633,"about_ca_system_score_codex":0.00003349369,"about_ca_system_score_gemma":0.000075921474,"threshold_uncertainty_score":0.3892187},"labels":[],"label_agreement":null},{"id":"W4417458211","doi":"10.1038/s41746-025-02237-2","title":"SLEEPYLAND: trust begins with fair evaluation of automatic sleep staging models","year":2025,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"EEG and Brain-Computer Interfaces","field":"Neuroscience","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Center for Research Resources; National Institute of Biomedical Imaging and Bioengineering; National Institute of Arthritis and Musculoskeletal and Skin Diseases; National Institute of Nursing Research; National Heart, Lung, and Blood Institute; National Institute on Aging; University of California, Davis; National Center for Advancing Translational Sciences; Johns Hopkins Bloomberg School of Public Health; Danmarks Tekniske Universitet; York University; Jazz Pharmaceuticals; National Institutes of Health; H. Lundbeck A/S; University of Minnesota; Lundbeckfonden; Case Western Reserve University; Johns Hopkins University; University of Washington; Eunice Kennedy Shriver National Institute of Child Health and Human Development; American Sleep Medicine Foundation","keywords":"Ambiguity; Ensemble forecasting; Ensemble learning; Deep learning; Multiple Models; Sleep (system call)","score_opus":0.03979580373329172,"score_gpt":0.3027297654122166,"score_spread":0.26293396167892485,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417458211","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90351933,0.00008502734,0.014529814,0.0013408237,0.00027363558,0.0003390625,0.000012973455,0.000114624876,0.07978473],"genre_scores_gemma":[0.9988982,0.0000029740884,0.00010398009,0.00045311812,0.00005031206,0.000015705726,0.000006048402,0.000010744599,0.0004589031],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983782,0.000054884105,0.00030701348,0.00031498392,0.0007449082,0.00020001641],"domain_scores_gemma":[0.9991304,0.00028627535,0.00011981948,0.00027783695,0.00012743978,0.0000582095],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003133298,0.00015302918,0.00026844448,0.00020640506,0.00005379754,0.00004740488,0.0002562524,0.00003461201,0.000044374447],"category_scores_gemma":[0.00039224437,0.00010085726,0.000029618383,0.00040977748,0.00021752584,0.00048890075,0.000061873056,0.00010790185,0.0000056984513],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020846857,0.0006414939,0.006092407,0.00080275047,0.00016739995,0.0000454594,0.008607695,0.034190983,0.05552452,0.025179213,0.0037953947,0.8647442],"study_design_scores_gemma":[0.0024505646,0.00053600274,0.0013582037,0.0010250937,0.00010556876,0.000015778565,0.0005781612,0.9446525,0.037850812,0.010894961,0.00035287268,0.00017946346],"about_ca_topic_score_codex":0.000012194615,"about_ca_topic_score_gemma":0.0000031563798,"teacher_disagreement_score":0.91046154,"about_ca_system_score_codex":0.00005279801,"about_ca_system_score_gemma":0.000073110015,"threshold_uncertainty_score":0.41128394},"labels":[],"label_agreement":null},{"id":"W4417464377","doi":"10.1038/s41746-025-02156-2","title":"Application of artificial intelligence to measure and predict patient values and preferences: a scoping review","year":2025,"lang":"en","type":"review","venue":"npj Digital Medicine","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Universiteit Utrecht; National Natural Science Foundation of China","keywords":"Measure (data warehouse); Health care; Transparency (behavior); Healthcare delivery; Quality (philosophy); Key (lock); Patient data; Data quality","score_opus":0.24832521945420064,"score_gpt":0.4720544596880523,"score_spread":0.22372924023385168,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417464377","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000052891977,0.9897508,0.0033089381,0.00074376597,0.00022715752,0.0049350313,0.000030648484,0.000036752957,0.00091403193],"genre_scores_gemma":[0.0018775187,0.9966801,0.000166775,0.0003614795,0.00026858138,0.00044391214,0.0001459487,0.000019676583,0.000036023248],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.99717903,0.000069377595,0.0015496591,0.0005490194,0.00043009987,0.00022279026],"domain_scores_gemma":[0.9978568,0.0006642004,0.00041356354,0.00040555245,0.00037525734,0.00028465924],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043690728,0.00032597783,0.001795676,0.0003035971,0.000059655686,0.000020722784,0.00011496886,0.00019998389,0.000020865918],"category_scores_gemma":[0.003091692,0.00023038177,0.00009189236,0.00067439384,0.00023336592,0.000100884106,0.00008465201,0.00026779878,0.000011370815],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014122001,0.000040466595,0.000021670097,0.19341332,0.00002765313,9.60805e-7,0.00028210203,6.515713e-8,3.547028e-7,0.00011433351,0.00013521854,0.80594975],"study_design_scores_gemma":[0.000010595526,0.0010343995,0.00000457285,0.973219,0.0009145854,0.000040443178,0.0004622317,0.000015254308,0.000020471154,0.0018485378,0.022234669,0.00019523648],"about_ca_topic_score_codex":0.000070065274,"about_ca_topic_score_gemma":0.000011918233,"teacher_disagreement_score":0.8057545,"about_ca_system_score_codex":0.00007236581,"about_ca_system_score_gemma":0.0006357971,"threshold_uncertainty_score":0.9394696},"labels":[],"label_agreement":null},{"id":"W4417524858","doi":"10.1038/s41746-025-02233-6","title":"Artificial intelligence-driven multivariate integration for pulmonary arterial pressure prediction in pulmonary hypertension","year":2025,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Pulmonary Hypertension Research and Treatments","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Circle Cardiovascular Imaging","funders":"National Natural Science Foundation of China","keywords":"Pulmonary hypertension; Pulmonary artery; Observational study; Multivariate statistics; Blood pressure; Multivariate analysis; Disease","score_opus":0.04991447093708016,"score_gpt":0.32106144978562773,"score_spread":0.27114697884854755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417524858","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8947006,0.0022800015,0.020067882,0.027317848,0.0040222374,0.009003773,0.00070566643,0.00057873817,0.04132325],"genre_scores_gemma":[0.99451685,0.00007430353,0.00031761706,0.00032816446,0.00052208256,0.00024516665,0.0012296276,0.000029301973,0.002736865],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99771154,0.000049144735,0.00071048766,0.00061281666,0.00045934907,0.0004566347],"domain_scores_gemma":[0.99872273,0.00027904366,0.00008933381,0.00037165714,0.00030960163,0.00022764344],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020802926,0.00030646115,0.0005960591,0.0005852877,0.00012016867,0.000037195754,0.00013247503,0.0002273714,0.00010380312],"category_scores_gemma":[0.0010136103,0.0002220654,0.00012493855,0.0005602094,0.00020045483,0.00039413673,0.00007441363,0.00030617576,0.000037352722],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.013803077,0.005116283,0.0153238475,0.00045496103,0.00041608282,0.002921837,0.00015284486,0.00008337473,0.18027365,0.0020728332,0.0039918544,0.7753894],"study_design_scores_gemma":[0.007306289,0.0063978164,0.34469506,0.007533088,0.0011768023,0.0015766805,0.0024606332,0.54806477,0.012930517,0.03839987,0.028522566,0.00093588873],"about_ca_topic_score_codex":0.00009416091,"about_ca_topic_score_gemma":0.000009647538,"teacher_disagreement_score":0.77445346,"about_ca_system_score_codex":0.00011691185,"about_ca_system_score_gemma":0.0001554753,"threshold_uncertainty_score":0.9055564},"labels":[],"label_agreement":null},{"id":"W7116749688","doi":"10.1038/s41746-025-02226-5","title":"Distinct visual biases affect humans and artificial intelligence in medical imaging diagnoses","year":2025,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hotchkiss Brain Institute; Alberta Children's Hospital; University of Victoria; University of Calgary","funders":"","keywords":"Medical diagnosis; Medical imaging; Perspective (graphical); Affect (linguistics); Disease","score_opus":0.1092436917726968,"score_gpt":0.4687334621065086,"score_spread":0.3594897703338118,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7116749688","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96283954,0.0017784185,0.0018438295,0.024033599,0.00083200313,0.00046569572,0.000005355738,0.000092108334,0.008109462],"genre_scores_gemma":[0.99706787,0.00027566444,0.000021886655,0.0016780737,0.0006592301,0.000045953137,0.00007059145,0.000015710388,0.00016504036],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9979659,0.00004460882,0.0007373168,0.00042199143,0.00045354257,0.00037666596],"domain_scores_gemma":[0.99751747,0.0017989769,0.00007131132,0.00020371999,0.000121132565,0.00028736296],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0004954365,0.0002083499,0.0004301779,0.00043285982,0.000105556115,0.000050806415,0.00010983975,0.000113342794,0.0003235502],"category_scores_gemma":[0.009851761,0.00016529753,0.00004571416,0.0006430329,0.0006059098,0.00021152693,0.00007093367,0.00035844735,0.000035558216],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011395361,0.00027145,0.2386457,0.00014487679,0.00001204636,0.00015341007,0.0006719369,6.8119004e-7,0.00007159617,0.002098281,0.00087377144,0.7569423],"study_design_scores_gemma":[0.0007146378,0.0029190988,0.8219309,0.02240424,0.00033488427,0.0004576741,0.037453428,0.023202777,0.009209408,0.06885032,0.011305768,0.0012168483],"about_ca_topic_score_codex":0.0007179709,"about_ca_topic_score_gemma":0.0005072137,"teacher_disagreement_score":0.75572544,"about_ca_system_score_codex":0.00010983101,"about_ca_system_score_gemma":0.00029147405,"threshold_uncertainty_score":0.99848866},"labels":[],"label_agreement":null},{"id":"W7116894095","doi":"10.1038/s41746-025-02256-z","title":"The impact of GenAI on applicant behaviour, performance, and interview reliability during virtual interviews for medical school admissions","year":2025,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; University of British Columbia Hospital","funders":"","keywords":"Harm; Reliability (semiconductor); Guard (computer science); Test (biology); Control (management); Medical school; Treatment and control groups","score_opus":0.07737484030008086,"score_gpt":0.4451734372443007,"score_spread":0.36779859694421985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7116894095","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98290235,0.00069465267,0.00020857244,0.0125488145,0.0003199045,0.0009379156,0.000012065984,0.00002780299,0.0023479224],"genre_scores_gemma":[0.9970338,0.0010482486,0.000012595315,0.00059853465,0.0002408932,0.000138836,0.000024811101,0.00001172317,0.0008905568],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99837863,0.00003557863,0.00076870056,0.00026369625,0.00029599346,0.00025738915],"domain_scores_gemma":[0.9979091,0.0006290214,0.00012321887,0.0003966648,0.00023463946,0.00070732256],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00083038595,0.0001619373,0.0003935199,0.00011852868,0.00017138266,0.000017599896,0.00015680958,0.00011237073,0.00021690884],"category_scores_gemma":[0.007942513,0.00008424463,0.00012425767,0.0002351399,0.00030357644,0.00007640233,0.00007071682,0.00031168596,0.00000646735],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010429177,0.0004168078,0.0753187,0.0011247173,0.000080499995,0.0000026523655,0.00072207296,0.0000021841308,0.00024097427,0.0003697565,0.009200237,0.91147846],"study_design_scores_gemma":[0.0030763103,0.02658733,0.86989194,0.033427246,0.00054978876,0.00020442352,0.011865294,0.006450662,0.01133305,0.0044255783,0.031463344,0.00072500866],"about_ca_topic_score_codex":0.00013370806,"about_ca_topic_score_gemma":0.000014679333,"teacher_disagreement_score":0.9107535,"about_ca_system_score_codex":0.00016386887,"about_ca_system_score_gemma":0.000737932,"threshold_uncertainty_score":0.95085025},"labels":[],"label_agreement":null}]}