{"id":"W3198582500","doi":"10.1016/j.urolonc.2021.08.007","title":"A machine learning approach to predict progression on active surveillance for prostate cancer","year":2021,"lang":"en","type":"article","venue":"Urologic Oncology Seminars and Original Investigations","topic":"Prostate Cancer Diagnosis and Treatment","field":"Medicine","cited_by":28,"is_retracted":false,"has_abstract":false,"ca_institutions":"McMaster University","funders":"National Institute of Neurological Disorders and Stroke","keywords":"Random forest; Prostate cancer; Machine learning; Artificial intelligence; Logistic regression; Support vector machine; Cohort; Artificial neural network; Medicine; Test set; Oncology; Cancer; Computer science; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001706527,0.0005559386,0.0008107491,0.001810416,0.000526523,0.001178217,0.0009908528,0.001102789,0.001377565],"category_scores_gemma":[0.004765232,0.0002354503,0.0009359149,0.000873225,0.0002673383,0.0007050994,0.0005274088,0.001500303,0.0004036083],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006989028,"about_ca_system_score_gemma":0.0008927159,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006646038,"about_ca_topic_score_gemma":0.005240418,"domain_scores_codex":[0.9994505,0.0001999115,0.00005515353,0.0001357758,0.00009000446,0.0000686952],"domain_scores_gemma":[0.9975724,0.001824458,0.0001213388,0.00008446623,0.0003260073,0.0000714663],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006260902,0.001227638,0.06227542,0.00009927872,0.0004081966,0.00023206,0.00009177341,0.3805069,0.001811619,0.003322227,0.005676843,0.543722],"study_design_scores_gemma":[0.00001320253,0.00007451919,0.003034014,0.00000827212,0.00002853143,0.000038632,0.00001371421,0.9936923,0.0002731466,0.002511187,0.0003046317,0.000007995844],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4409113,0.003162842,0.5417856,0.003650641,0.0005891815,0.0002521278,0.001617919,0.001364175,0.006666042],"genre_scores_gemma":[0.9448875,0.0003618349,0.05029405,0.0002453575,0.0003485444,0.0001031372,0.0009788213,0.00002849213,0.00275237],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006646038,"threshold_uncertainty_score":0.01321471,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03209663178769579,"score_gpt":0.3407601208232074,"score_spread":0.3086634890355117,"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."}}