{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01054357,0.001713909,0.01018642,0.006500339,0.0005379771,0.003024344,0.002840702,0.002209209,0.004761496],"category_scores_gemma":[0.05154462,0.001269938,0.009110874,0.006265255,0.001201759,0.002634438,0.001918214,0.001830475,0.0003977138],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002297941,"about_ca_system_score_gemma":0.007552193,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01020554,"about_ca_topic_score_gemma":0.03924896,"domain_scores_codex":[0.9904346,0.003527541,0.003110522,0.0009104792,0.001830815,0.0001859867],"domain_scores_gemma":[0.9592125,0.03340334,0.004642617,0.0005698279,0.001926677,0.0002450722],"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":[0.0004406406,0.00004597386,0.001075035,0.8935066,0.02381783,0.00005257655,0.0002129641,0.0001428816,0.0001145981,0.0001603235,0.001118998,0.07931174],"study_design_scores_gemma":[0.001384523,0.0006049035,0.009602263,0.6942755,0.2758694,0.000394894,0.0004996326,0.0003773427,0.000262735,0.000552844,0.01604014,0.0001357842],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0008861109,0.9981364,0.0002775482,0.00007923017,0.00007641219,0.0002362096,0.0001583062,0.000009073388,0.0001407074],"genre_scores_gemma":[0.01648031,0.9805502,0.001951702,0.0003807837,0.00006555754,0.0003146306,0.0001388163,0.000009625996,0.0001082857],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.01054357,"threshold_uncertainty_score":0.05576038,"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."}}