{"id":"W4387664127","doi":"10.1097/xcs.0000000000000893","title":"Remote Assessment of Real-World Surgical Safety Checklist Performance Using the OR Black Box: A Multi-Institutional Evaluation","year":2023,"lang":"en","type":"article","venue":"Journal of the American College of Surgeons","topic":"Patient Safety and Medication Errors","field":"Health Professions","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; St. Michael's Hospital","funders":"","keywords":"Checklist; Medicine; Debriefing; Patient safety; Scale (ratio); Medical emergency; Medical education; Health care; 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":[0.02103748,0.0007053142,0.0006394802,0.004143902,0.0008287106,0.001272463,0.0008857948,0.0003427821,0.001029138],"category_scores_gemma":[0.01928308,0.0004009903,0.001076681,0.001787932,0.0008453521,0.001651866,0.003447091,0.000422804,0.000372308],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001353199,"about_ca_system_score_gemma":0.002119342,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001901604,"about_ca_topic_score_gemma":0.004213841,"domain_scores_codex":[0.9876657,0.007005909,0.00176391,0.0009040823,0.001975725,0.000684629],"domain_scores_gemma":[0.9649624,0.006728814,0.01356166,0.002728246,0.008935965,0.003083016],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0009807537,0.0005532498,0.9737325,0.0001214457,0.0001466781,0.0001266481,0.001201349,0.000353404,0.0009037591,0.00002319934,0.0002252218,0.02163178],"study_design_scores_gemma":[0.00008057431,0.004836882,0.9897078,0.00007571132,0.00009425501,0.0002264079,0.002113978,0.001197823,0.001111861,0.00003003649,0.0004823135,0.00004233999],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9969403,0.00008437416,0.001582436,0.00002119905,0.000007381854,0.0005916256,0.0002635258,0.00003543435,0.0004736781],"genre_scores_gemma":[0.9936361,0.0001195973,0.004431389,0.00002935743,0.00001828848,0.0009719338,0.0006183946,0.00001641637,0.0001584773],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02103748,"threshold_uncertainty_score":0.1112582,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1371241023328436,"score_gpt":0.4643747923525416,"score_spread":0.327250690019698,"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."}}