{"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,"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","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002010759,0.0006905813,0.0005246071,0.00121939,0.000282782,0.0007519366,0.001014086,0.00091953,0.001322804],"category_scores_gemma":[0.003549415,0.0002947404,0.0004984477,0.0005633219,0.0002417769,0.0005335067,0.001005599,0.0007363503,0.0006852781],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008210784,"about_ca_system_score_gemma":0.001265787,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006570005,"about_ca_topic_score_gemma":0.007761054,"domain_scores_codex":[0.9993243,0.0001755348,0.00005805794,0.0001776276,0.000179079,0.0000854262],"domain_scores_gemma":[0.9987082,0.0003939176,0.00008285054,0.0001211982,0.000611969,0.00008180062],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000242581,0.0003700721,0.0195076,0.0001110067,0.0001643026,0.0001291103,0.00006196056,0.1708016,0.02730333,0.0008311339,0.008492908,0.7719844],"study_design_scores_gemma":[0.00001695335,0.00005070361,0.001709625,0.00001029208,0.00001172004,0.00002490373,0.000006763789,0.9926302,0.004701593,0.0003393215,0.0004922054,0.00000555027],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3722607,0.001384695,0.6119979,0.0008697723,0.0002882845,0.0003398496,0.0009532983,0.008705007,0.003200524],"genre_scores_gemma":[0.7569972,0.0002281246,0.2367761,0.0004755787,0.00005442969,0.0001534497,0.001906226,0.0001220026,0.003287019],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006570005,"threshold_uncertainty_score":0.01306355,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01486408446087495,"score_gpt":0.2718944423352889,"score_spread":0.257030357874414,"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."}}