{"id":"W3151539628","doi":"10.1016/j.amjsurg.2021.03.064","title":"Objective Structured Assessment of technical skill (OSATS) in the Surgical Skills and Technology Elective Program (SSTEP): Comparison of peer and expert raters","year":2021,"lang":"en","type":"article","venue":"The American Journal of Surgery","topic":"Surgical Simulation and Training","field":"Medicine","cited_by":36,"is_retracted":false,"has_abstract":false,"ca_institutions":"Kingston Health Sciences Centre; Kingston General Hospital; Queen's University","funders":"","keywords":"Intraclass correlation; Reliability (semiconductor); Medical education; Task (project management); Medicine; Session (web analytics); Medical physics; Psychology; Physical therapy; Computer science; Psychometrics; Clinical psychology; Engineering","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":[0.007773519,0.0004724273,0.000721327,0.001388207,0.0003804015,0.0006516312,0.0005115723,0.0004376443,0.001800732],"category_scores_gemma":[0.02736726,0.0002100487,0.0007055021,0.0005194826,0.0004478526,0.001195278,0.001266546,0.0004950705,0.0005485349],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004001763,"about_ca_system_score_gemma":0.0007226598,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001018548,"about_ca_topic_score_gemma":0.002680881,"domain_scores_codex":[0.9943213,0.001693508,0.001029563,0.0006089465,0.002114745,0.0002318804],"domain_scores_gemma":[0.9663695,0.01367435,0.007489947,0.001086185,0.009624339,0.001755776],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.007832529,0.002288084,0.9080207,0.0004221791,0.0005322491,0.0001316368,0.003015862,0.00104528,0.0059102,0.0001344615,0.0009931236,0.06967374],"study_design_scores_gemma":[0.0006080953,0.0106681,0.9776034,0.00008963911,0.0001911674,0.0003440953,0.002799998,0.003590762,0.002866467,0.0001664887,0.001011979,0.00005965252],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9961244,0.0001084337,0.001326896,0.0000315595,0.00004645902,0.0002966892,0.0002982102,0.00002602404,0.001741364],"genre_scores_gemma":[0.9946302,0.000177302,0.003244412,0.00004646974,0.00004255625,0.0003151657,0.0005269004,0.00001884691,0.0009981425],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007773519,"threshold_uncertainty_score":0.04111081,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0229720155041902,"score_gpt":0.3806514651017053,"score_spread":0.3576794495975151,"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."}}