{"id":"W1836271141","doi":"10.1111/medu.12080","title":"Checklists improve experts’ diagnostic decisions","year":2013,"lang":"en","type":"article","venue":"Medical Education","topic":"Clinical Reasoning and Diagnostic Skills","field":"Medicine","cited_by":93,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; University Health Network","funders":"","keywords":"Checklist; Context (archaeology); Interpretation (philosophy); Computer science; Cognition; Diagnostic accuracy; Medical physics; Medicine; Psychology; Cognitive psychology; Radiology; Psychiatry","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":[0.02677917,0.0008842941,0.0006880108,0.003835244,0.0007218221,0.001913006,0.001071425,0.001344996,0.00910919],"category_scores_gemma":[0.2494028,0.0004496556,0.001271075,0.001124137,0.00126907,0.002882942,0.003219996,0.001111081,0.001315077],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001395989,"about_ca_system_score_gemma":0.00240461,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001407825,"about_ca_topic_score_gemma":0.001818072,"domain_scores_codex":[0.961288,0.02289406,0.0041398,0.002278059,0.008569352,0.0008305994],"domain_scores_gemma":[0.6426465,0.2578799,0.05535625,0.01315114,0.02580001,0.005166207],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00208966,0.001131418,0.146238,0.004375775,0.0006432951,0.0004530607,0.007094244,0.004009163,0.006605868,0.001462045,0.0183337,0.8075638],"study_design_scores_gemma":[0.001786203,0.00644376,0.8626757,0.008627097,0.001048631,0.003844644,0.007269897,0.01385147,0.01300532,0.01926764,0.06166913,0.0005105686],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8565516,0.008785545,0.08744518,0.01043806,0.0007692198,0.001576615,0.0009482096,0.00216759,0.03131803],"genre_scores_gemma":[0.9057211,0.002338939,0.08775348,0.001385067,0.0004816162,0.0003885112,0.0004232552,0.0001496864,0.001358262],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02677917,"threshold_uncertainty_score":0.1416234,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01513996075955962,"score_gpt":0.3605869921277853,"score_spread":0.3454470313682256,"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."}}