{"id":"W2006326318","doi":"10.4300/jgme-d-11-00123.1","title":"Prospective Comparison of Live Evaluation and Video Review in the Evaluation of Operator Performance in a Pediatric Emergency Airway Simulation","year":2012,"lang":"en","type":"article","venue":"Journal of Graduate Medical Education","topic":"Simulation-Based Education in Healthcare","field":"Medicine","cited_by":33,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa Skills and Simulation Centre","funders":"","keywords":"Inter-rater reliability; Concordance; Medicine; Intra-rater reliability; Intubation; Reliability (semiconductor); Confidence interval; Medical physics; Rating scale; Psychology; Surgery","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":[0.02530685,0.0005615935,0.0005793792,0.00124732,0.0003825839,0.00102055,0.0007816807,0.000633843,0.001015981],"category_scores_gemma":[0.08528249,0.000595876,0.0006348511,0.0005914194,0.0008165466,0.001527307,0.001483831,0.0005705857,0.0003375845],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001103018,"about_ca_system_score_gemma":0.001290795,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002071777,"about_ca_topic_score_gemma":0.003373515,"domain_scores_codex":[0.9741745,0.01744574,0.002029518,0.002274967,0.003461183,0.0006140722],"domain_scores_gemma":[0.904458,0.04696661,0.02288899,0.004020534,0.01861888,0.003047048],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"nonrandomized_trial","study_design_scores_codex":[0.03006355,0.002658052,0.8649816,0.001121348,0.0009942179,0.0003054377,0.00587722,0.001630043,0.003604586,0.0002201254,0.0006933502,0.08785056],"study_design_scores_gemma":[0.001363887,0.0367474,0.9468868,0.0002945808,0.0004692503,0.0007637014,0.002328148,0.006305646,0.003350983,0.0001071027,0.001249914,0.0001326865],"study_design_candidate":"nonrandomized_trial","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9960606,0.0005703784,0.001899022,0.00002705058,0.00004412499,0.0005765362,0.0001169407,0.00002684618,0.0006784624],"genre_scores_gemma":[0.9967797,0.0001678477,0.002269301,0.00002481578,0.00002912269,0.000472832,0.0001227495,0.000006603038,0.0001270598],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02530685,"threshold_uncertainty_score":0.133837,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1591514316052036,"score_gpt":0.5048788781775292,"score_spread":0.3457274465723256,"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."}}