{"id":"W2766049277","doi":"10.1097/sla.0000000000002562","title":"A Novel Method of Setting Performance Standards in Surgery Using Patient Outcomes","year":2017,"lang":"en","type":"article","venue":"Annals of Surgery","topic":"Surgical Simulation and Training","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; St. Michael's Hospital","funders":"","keywords":"Medicine; Receiver operating characteristic; Context (archaeology); Outcome (game theory); Credentialing; Learning curve; Brier score; Prostatectomy; Gold standard (test); Youden's J statistic; Medical physics; Machine learning; Computer science; Medical education","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":[0.03890875,0.001675381,0.001174738,0.005189056,0.0009585306,0.0044014,0.002166799,0.001370611,0.003869347],"category_scores_gemma":[0.1551135,0.0004950051,0.001506415,0.003557318,0.0018341,0.003145468,0.004127548,0.002819758,0.001386937],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002134252,"about_ca_system_score_gemma":0.003582034,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00143235,"about_ca_topic_score_gemma":0.001332823,"domain_scores_codex":[0.951171,0.0255588,0.003826403,0.006652935,0.01203208,0.0007588112],"domain_scores_gemma":[0.922105,0.0383188,0.01271421,0.01088673,0.01493364,0.001041624],"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":[0.001131222,0.0009037701,0.07833633,0.0006856086,0.0005412749,0.0001977262,0.002491171,0.02167265,0.005847618,0.05350801,0.008207371,0.8264773],"study_design_scores_gemma":[0.001010021,0.00692695,0.1591076,0.001818739,0.00100964,0.001854676,0.002541641,0.4999763,0.05434059,0.1848678,0.08541826,0.001127786],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02156308,0.0002116732,0.9674118,0.000675586,0.0002123498,0.0009192439,0.0004978574,0.001319192,0.007189197],"genre_scores_gemma":[0.3207051,0.0001699684,0.6725789,0.0004824359,0.0001892842,0.002792862,0.0006424454,0.000437757,0.002001393],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.03890875,"threshold_uncertainty_score":0.2057716,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3931333246652206,"score_gpt":0.4601567062742004,"score_spread":0.06702338160897975,"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."}}