{"id":"W3161520686","doi":"10.1007/s00330-021-08021-6","title":"ESUR/ESUI position paper: developing artificial intelligence for precision diagnosis of prostate cancer using magnetic resonance imaging","year":2021,"lang":"en","type":"article","venue":"European Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":68,"is_retracted":false,"has_abstract":true,"ca_institutions":"Sinai Health System; University of Toronto; University Health Network","funders":"Berlin Institute of Health","keywords":"Medicine; Neuroradiology; Magnetic resonance imaging; Prostate cancer; Interventional radiology; Radiology; Position (finance); Ultrasound; Medical physics; Prostate; Position statement; Cancer; Nuclear medicine; Neurology; Internal medicine","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007192958,0.0001482461,0.0003550548,0.00009742845,0.0001157778,0.00002060239,0.0001077321,0.00003567747,0.00008893418],"category_scores_gemma":[0.001031572,0.0001394368,0.0000960359,0.0002155435,0.0001627682,0.00006806493,0.00007488921,0.0002356216,0.000005368608],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009362296,"about_ca_system_score_gemma":0.0001764469,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003071939,"about_ca_topic_score_gemma":0.00000386644,"domain_scores_codex":[0.9982932,0.000309278,0.0005430941,0.0004034028,0.0001364914,0.000314556],"domain_scores_gemma":[0.9990256,0.0002983208,0.0001534377,0.000217782,0.0002188012,0.00008610408],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0002128722,0.00006400343,0.04456602,0.0001520287,0.00002207941,0.0002972418,0.0006280638,0.0006490833,0.05119042,0.001084795,0.0004247162,0.9007087],"study_design_scores_gemma":[0.004168384,0.001484909,0.3629089,0.008706969,0.0009125877,0.004826749,0.00105676,0.3248985,0.1412271,0.01007919,0.1379141,0.001815866],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8877367,0.03047761,0.07077385,0.008680712,0.0009456163,0.0005796873,0.00002631936,0.00007155193,0.0007079783],"genre_scores_gemma":[0.9324058,0.003207852,0.06126343,0.002256532,0.0005710309,0.00003455517,0.00005078977,0.0000716317,0.0001383859],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8988928,"threshold_uncertainty_score":0.5686066,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02711200094160532,"score_gpt":0.3238093566749438,"score_spread":0.2966973557333385,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}