{"id":"W2955915380","doi":"10.1016/j.jsurg.2019.06.011","title":"Automated Methods of Technical Skill Assessment in Surgery: A Systematic Review","year":2019,"lang":"en","type":"review","venue":"Journal of surgical education","topic":"Surgical Simulation and Training","field":"Medicine","cited_by":97,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto; McMaster University","funders":"","keywords":"Computer science; Apprenticeship; Curriculum; Quality (philosophy); Medical physics; Match moving; Motion (physics); Artificial intelligence; Medicine; Psychology","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":[0.006762062,0.0002934011,0.006651992,0.0007480245,0.00001311614,0.00001422185,0.0001607059,0.0003405232,0.0002932858],"category_scores_gemma":[0.002269774,0.0001816138,0.001552935,0.001158611,0.00003960903,0.00009174543,0.00002779664,0.000918655,0.00001365789],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005043273,"about_ca_system_score_gemma":0.003770435,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003493857,"about_ca_topic_score_gemma":1.676143e-7,"domain_scores_codex":[0.9933584,0.001572154,0.004025012,0.000206309,0.000647299,0.0001907662],"domain_scores_gemma":[0.9908182,0.004766865,0.003344142,0.000348631,0.0005089865,0.0002131491],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","study_design_scores_codex":[0.00001430391,0.0006208267,0.00002854398,0.78948,0.0001751742,0.00004537551,0.00001170841,0.00000119112,1.192688e-7,0.0001145695,0.0003610614,0.2091471],"study_design_scores_gemma":[0.0004287176,0.00007258007,0.0000897611,0.7296574,0.003175884,0.001519658,0.00002352712,0.00003877472,1.35968e-7,0.000009901703,0.2648519,0.0001317995],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00001424876,0.9958211,0.0000375256,0.0002429762,0.0005619822,0.001511761,0.00000204789,0.00002771597,0.001780606],"genre_scores_gemma":[0.0003024773,0.996405,0.002826196,0.0001014254,0.0001254145,0.00004931725,0.00004616123,0.00003269305,0.0001113312],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.2644908,"threshold_uncertainty_score":0.7405997,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1174483065900212,"score_gpt":0.5300127657927944,"score_spread":0.4125644592027732,"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."}}