{"id":"W4295751219","doi":"10.1097/xcs.0000000000000341","title":"How Well Is Surgical Improvement Being Conducted? Evaluation of 50 Local Surgery-Related Improvement Efforts","year":2022,"lang":"en","type":"article","venue":"Journal of the American College of Surgeons","topic":"Surgical Simulation and Training","field":"Medicine","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Medicine; Quality management; Accreditation; Documentation; Stakeholder; Performance improvement; Quality (philosophy); Program evaluation; PDCA; Operations management; Medical education; Statistics; Management","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02041603,0.0004327014,0.0003669338,0.003720897,0.0007163238,0.001001367,0.0007053579,0.000462615,0.001389141],"category_scores_gemma":[0.05199486,0.0002352587,0.0006262055,0.002544347,0.001329559,0.001292082,0.002589293,0.0004873356,0.0002352159],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002096439,"about_ca_system_score_gemma":0.002985222,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001940732,"about_ca_topic_score_gemma":0.004989984,"domain_scores_codex":[0.9778032,0.01049532,0.002912344,0.0009022522,0.00634889,0.001538031],"domain_scores_gemma":[0.9287382,0.02373262,0.02615514,0.002497887,0.01372641,0.005149692],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003009237,0.0005239401,0.9299843,0.000365287,0.0001310784,0.0001089221,0.005254248,0.0004097168,0.0009716944,0.000121551,0.0005576013,0.0612707],"study_design_scores_gemma":[0.00001406802,0.001357393,0.9911283,0.0001106448,0.00004791731,0.00006673668,0.005036584,0.0005184925,0.0008943199,0.00003989847,0.0007684008,0.00001713012],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9972516,0.0001788704,0.0004572248,0.0001116882,0.00000581052,0.0001590682,0.0001055239,0.00002426364,0.001705915],"genre_scores_gemma":[0.9981832,0.0001565688,0.001101627,0.00003366011,0.000004943351,0.0001288067,0.0001426791,0.00000446672,0.0002439905],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.979584,"threshold_uncertainty_score":0.1079715,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02634213875406615,"score_gpt":0.2844111629729541,"score_spread":0.2580690242188879,"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."}}