{"id":"W4384071974","doi":"10.1097/sla.0000000000005998","title":"The Association of ACGME Milestones With Performance on American Board of Surgery Assessments","year":2023,"lang":"en","type":"article","venue":"Annals of Surgery","topic":"Surgical Simulation and Training","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Milestone; Medicine; Board certification; Graduate medical education; Predictive validity; Specialty; Cohort; Logistic regression; Certification; Competence (human resources); Maintenance of Certification; Family medicine; Educational measurement; MEDLINE; Accreditation; Continuing medical education; Internal medicine; Medical education; Psychology; Clinical psychology; Continuing education; 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":[],"consensus_categories":[],"category_scores_codex":[0.002671103,0.0001813894,0.000154203,0.001107177,0.0002777525,0.0005341165,0.000530258,0.0003180802,0.002562255],"category_scores_gemma":[0.02231997,0.0001466463,0.0002335477,0.0007804716,0.0002622153,0.0005536434,0.0009495979,0.0007552954,0.0003582144],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000527993,"about_ca_system_score_gemma":0.0007784587,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0107711,"about_ca_topic_score_gemma":0.01518377,"domain_scores_codex":[0.9982883,0.000449695,0.0001553783,0.00035854,0.0005092485,0.0002387731],"domain_scores_gemma":[0.9825122,0.004021341,0.008321995,0.0007145552,0.002508383,0.001921602],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00002120564,0.00001758901,0.9979997,0.000005098767,0.00001848896,0.000005531077,0.00003916655,0.00009248719,0.00002529718,0.0000134645,0.0001900264,0.001572018],"study_design_scores_gemma":[8.978773e-7,0.00002297686,0.9994821,0.000004470614,0.000003065662,0.0000181462,0.00005366878,0.0002477845,0.000021248,0.000009780498,0.0001343939,0.000001454694],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9974464,0.0002121693,0.0002095905,0.0002195953,0.00001358964,0.00001434408,0.0006769581,0.00001304459,0.001194261],"genre_scores_gemma":[0.999077,0.00005913082,0.0001303253,0.00001385813,0.000008499102,0.0000107713,0.0004417135,0.000002943456,0.000255778],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0107711,"threshold_uncertainty_score":0.02141678,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2501109553208242,"score_gpt":0.4006004015661108,"score_spread":0.1504894462452866,"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."}}