{"id":"W3188019074","doi":"10.1016/j.euf.2021.07.004","title":"Standardized Reporting of Machine Learning Applications in Urology: The STREAM-URO Framework","year":2021,"lang":"en","type":"article","venue":"European Urology Focus","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":67,"is_retracted":false,"has_abstract":false,"ca_institutions":"McMaster University; Vector Institute; University of British Columbia; Hospital for Sick Children; Sinai Health System; Lunenfeld-Tanenbaum Research Institute; University of Toronto","funders":"","keywords":"Medicine; Comparability; Interpretability; Urology; Medical physics; Machine learning; Computer science","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":[0.001534013,0.0001032814,0.0002937019,0.00008135917,0.0001424199,0.000007718708,0.0001020739,0.00008895204,0.0001776448],"category_scores_gemma":[0.005574244,0.00007927565,0.00007987762,0.0003871382,0.0001547247,0.00002263051,0.00006570813,0.0007821473,0.00004055115],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002737321,"about_ca_system_score_gemma":0.000193476,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000143141,"about_ca_topic_score_gemma":0.0001112313,"domain_scores_codex":[0.9976537,0.0006244239,0.001069066,0.000284223,0.0001242301,0.0002443639],"domain_scores_gemma":[0.9979599,0.0007195984,0.0006194644,0.0004244287,0.0002110166,0.0000656528],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003356823,0.0003311355,0.8260615,0.00006306988,0.00008286111,0.0004401774,0.006257928,0.0007228439,0.002575407,0.005872814,0.0002478698,0.1570087],"study_design_scores_gemma":[0.000888595,0.002676112,0.5398517,0.0001854743,0.0007200691,0.001541102,0.01134556,0.003143892,0.04534888,0.04649379,0.3470225,0.0007824186],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9519821,0.004067616,0.01216141,0.0160692,0.0002685042,0.0004090514,0.000005770294,0.00007670838,0.01495967],"genre_scores_gemma":[0.9978384,0.0001634905,0.0007434154,0.0007614405,0.0002186114,0.00001711155,0.00003092863,0.00002519472,0.0002013942],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3467746,"threshold_uncertainty_score":0.6673293,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07995403360563962,"score_gpt":0.3892031829367393,"score_spread":0.3092491493310996,"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."}}