{"id":"W2951405082","doi":"10.1016/j.jsurg.2019.05.015","title":"Artificial Intelligence in Medical Education: Best Practices Using Machine Learning to Assess Surgical Expertise in Virtual Reality Simulation","year":2019,"lang":"en","type":"article","venue":"Journal of surgical education","topic":"Surgical Simulation and Training","field":"Medicine","cited_by":283,"is_retracted":false,"has_abstract":false,"ca_institutions":"Montreal General Hospital; Montreal Neurological Institute and Hospital; McGill University","funders":"Montreal Neurological Institute and Hospital; Royal College of Physicians and Surgeons of Canada; McGill University; Williams","keywords":"Virtual reality; Checklist; Computer science; Artificial intelligence; Quality (philosophy); Psychomotor learning; Field (mathematics); Machine learning; Medicine; Psychology; Cognition","routes":{"ca_aff":true,"ca_fund":true,"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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002301042,0.0001695509,0.0005010398,0.0005781639,0.00004949751,0.0000598244,0.0001275649,0.0002237321,0.001768679],"category_scores_gemma":[0.003007811,0.0001455103,0.000124608,0.0009345542,0.0000427423,0.0004783411,0.00003541692,0.0009101662,0.00004215742],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004417523,"about_ca_system_score_gemma":0.002218314,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003482815,"about_ca_topic_score_gemma":0.00006705256,"domain_scores_codex":[0.9967288,0.0004456906,0.001327618,0.0002814069,0.0009645335,0.0002519535],"domain_scores_gemma":[0.9971378,0.001081605,0.0007160422,0.0001486837,0.0004307478,0.0004850678],"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":[0.002974913,0.004606855,0.1768738,0.00006339331,0.00002654022,0.000288869,0.002026046,0.1666943,0.0001204317,0.001622063,0.000008132426,0.6446947],"study_design_scores_gemma":[0.003131709,0.001087484,0.02350542,0.00228327,0.00007398242,0.00150285,0.007726109,0.9152895,0.000240556,0.0004462924,0.04422413,0.0004886708],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9912821,0.0003539797,0.0006277915,0.004267695,0.0009027123,0.0003277713,4.033014e-7,0.00001172306,0.002225817],"genre_scores_gemma":[0.9981661,0.00009666137,0.0004550262,0.0002746333,0.0007793583,0.000005999705,0.00001634986,0.00001762124,0.000188281],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7485952,"threshold_uncertainty_score":0.9991438,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1747863888737946,"score_gpt":0.4830863517665958,"score_spread":0.3082999628928011,"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."}}